/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/af4779ec3bff/Spark-X2.6-4B-Q8_0.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.055.608 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.055.663 I srv llama_server: initializing ... 0.00.055.668 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.055.753 I srv init_listene: The UI is disabled 0.00.055.755 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.055.793 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.057.439 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/af4779ec3bff/Spark-X2.6-4B-Q8_0.gguf' 0.00.598.537 I cmn init: llama threadpool init, n_threads = 8 0.00.690.444 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.00.699.536 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.699.548 I srv llama_server: model loaded 0.00.699.550 I srv llama_server: listening on http://127.0.0.1:8091 1.13.479.304 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 1.13.479.342 I slot launch_slot_: id 0 | task 2 | processing task, is_child = 0 1.13.479.344 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 1.13.479.372 I slot launch_slot_: id 1 | task 1 | processing task, is_child = 0 1.13.479.377 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 1.13.479.402 I slot launch_slot_: id 2 | task 0 | processing task, is_child = 0 1.13.479.404 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 1.13.479.429 I slot launch_slot_: id 3 | task 3 | processing task, is_child = 0 1.14.550.457 I slot print_timing: id 0 | task 2 | prompt eval time = 1031.77 ms / 130 tokens ( 7.94 ms per token, 126.00 tokens per second) 1.14.550.461 I slot print_timing: id 0 | task 2 | eval time = 39.25 ms / 2 tokens ( 39.25 ms per token, 25.48 tokens per second) 1.14.550.462 I slot print_timing: id 0 | task 2 | total time = 1071.02 ms / 132 tokens 1.14.550.463 I slot print_timing: id 0 | task 2 | graphs reused = 1 1.14.550.463 I slot print_timing: id 0 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.550.488 I slot release: id 0 | task 2 | stop processing: n_tokens = 131, truncated = 0 1.14.552.271 I slot print_timing: id 1 | task 1 | prompt eval time = 1034.15 ms / 134 tokens ( 7.72 ms per token, 129.57 tokens per second) 1.14.552.274 I slot print_timing: id 1 | task 1 | eval time = 38.67 ms / 2 tokens ( 38.67 ms per token, 25.86 tokens per second) 1.14.552.275 I slot print_timing: id 1 | task 1 | total time = 1072.83 ms / 136 tokens 1.14.552.275 I slot print_timing: id 1 | task 1 | graphs reused = 1 1.14.552.276 I slot print_timing: id 1 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.552.296 I slot release: id 1 | task 1 | stop processing: n_tokens = 135, truncated = 0 1.14.554.111 I slot print_timing: id 2 | task 0 | prompt eval time = 1036.43 ms / 128 tokens ( 8.10 ms per token, 123.50 tokens per second) 1.14.554.117 I slot print_timing: id 2 | task 0 | eval time = 38.23 ms / 2 tokens ( 38.23 ms per token, 26.15 tokens per second) 1.14.554.118 I slot print_timing: id 2 | task 0 | total time = 1074.66 ms / 130 tokens 1.14.554.118 I slot print_timing: id 2 | task 0 | graphs reused = 1 1.14.554.118 I slot print_timing: id 2 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.554.137 I slot release: id 2 | task 0 | stop processing: n_tokens = 129, truncated = 0 1.14.585.326 I slot print_timing: id 3 | task 3 | prompt eval time = 1038.49 ms / 142 tokens ( 7.31 ms per token, 136.74 tokens per second) 1.14.585.330 I slot print_timing: id 3 | task 3 | eval time = 67.38 ms / 3 tokens ( 33.69 ms per token, 29.68 tokens per second) 1.14.585.331 I slot print_timing: id 3 | task 3 | total time = 1105.87 ms / 145 tokens 1.14.585.331 I slot print_timing: id 3 | task 3 | graphs reused = 1 1.14.585.332 I slot print_timing: id 3 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.585.352 I slot release: id 3 | task 3 | stop processing: n_tokens = 144, truncated = 0 1.14.585.358 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.281 1.14.588.974 I slot launch_slot_: id 1 | task 9 | processing task, is_child = 0 1.14.598.898 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.282 1.14.599.039 I slot launch_slot_: id 0 | task 10 | processing task, is_child = 0 1.14.599.115 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.287 1.14.599.194 I slot launch_slot_: id 2 | task 11 | processing task, is_child = 0 1.14.599.229 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.319 (> 0.100 thold), f_keep = 0.264 1.14.599.303 I slot launch_slot_: id 3 | task 12 | processing task, is_child = 0 1.15.797.702 I slot print_timing: id 2 | task 11 | prompt eval time = 1161.60 ms / 164 tokens ( 7.08 ms per token, 141.18 tokens per second) 1.15.797.706 I slot print_timing: id 2 | task 11 | eval time = 36.22 ms / 2 tokens ( 36.22 ms per token, 27.61 tokens per second) 1.15.797.707 I slot print_timing: id 2 | task 11 | total time = 1197.82 ms / 166 tokens 1.15.797.707 I slot print_timing: id 2 | task 11 | graphs reused = 1 1.15.797.708 I slot print_timing: id 2 | task 11 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.797.734 I slot release: id 2 | task 11 | stop processing: n_tokens = 174, truncated = 0 1.15.799.206 I slot print_timing: id 3 | task 12 | prompt eval time = 1162.74 ms / 110 tokens ( 10.57 ms per token, 94.60 tokens per second) 1.15.799.213 I slot print_timing: id 3 | task 12 | eval time = 36.37 ms / 2 tokens ( 36.37 ms per token, 27.49 tokens per second) 1.15.799.214 I slot print_timing: id 3 | task 12 | total time = 1199.11 ms / 112 tokens 1.15.799.214 I slot print_timing: id 3 | task 12 | graphs reused = 1 1.15.799.215 I slot print_timing: id 3 | task 12 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.799.231 I slot release: id 3 | task 12 | stop processing: n_tokens = 120, truncated = 0 1.15.830.829 I slot print_timing: id 0 | task 10 | prompt eval time = 1159.66 ms / 204 tokens ( 5.68 ms per token, 175.91 tokens per second) 1.15.830.834 I slot print_timing: id 0 | task 10 | eval time = 71.85 ms / 3 tokens ( 35.92 ms per token, 27.84 tokens per second) 1.15.830.835 I slot print_timing: id 0 | task 10 | total time = 1231.51 ms / 207 tokens 1.15.830.835 I slot print_timing: id 0 | task 10 | graphs reused = 1 1.15.830.836 I slot print_timing: id 0 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.830.861 I slot release: id 0 | task 10 | stop processing: n_tokens = 215, truncated = 0 1.15.832.958 I slot print_timing: id 1 | task 9 | prompt eval time = 1160.54 ms / 159 tokens ( 7.30 ms per token, 137.00 tokens per second) 1.15.832.961 I slot print_timing: id 1 | task 9 | eval time = 72.78 ms / 3 tokens ( 36.39 ms per token, 27.48 tokens per second) 1.15.832.962 I slot print_timing: id 1 | task 9 | total time = 1233.32 ms / 162 tokens 1.15.832.962 I slot print_timing: id 1 | task 9 | graphs reused = 1 1.15.832.963 I slot print_timing: id 1 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.832.979 I slot release: id 1 | task 9 | stop processing: n_tokens = 170, truncated = 0 1.15.832.985 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.172 1.15.839.702 I slot launch_slot_: id 0 | task 18 | processing task, is_child = 0 1.15.852.828 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.297 (> 0.100 thold), f_keep = 0.224 1.15.852.935 I slot launch_slot_: id 1 | task 19 | processing task, is_child = 0 1.15.853.019 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.213 1.15.853.111 I slot launch_slot_: id 2 | task 20 | processing task, is_child = 0 1.15.853.150 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.287 (> 0.100 thold), f_keep = 0.308 1.15.853.234 I slot launch_slot_: id 3 | task 21 | processing task, is_child = 0 1.16.828.835 I slot print_timing: id 0 | task 18 | prompt eval time = 932.24 ms / 151 tokens ( 6.17 ms per token, 161.97 tokens per second) 1.16.828.841 I slot print_timing: id 0 | task 18 | eval time = 43.34 ms / 2 tokens ( 43.34 ms per token, 23.07 tokens per second) 1.16.828.842 I slot print_timing: id 0 | task 18 | total time = 975.59 ms / 153 tokens 1.16.828.843 I slot print_timing: id 0 | task 18 | graphs reused = 1 1.16.828.843 I slot print_timing: id 0 | task 18 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.828.872 I slot release: id 0 | task 18 | stop processing: n_tokens = 161, truncated = 0 1.16.830.975 I slot print_timing: id 1 | task 19 | prompt eval time = 935.50 ms / 119 tokens ( 7.86 ms per token, 127.20 tokens per second) 1.16.830.980 I slot print_timing: id 1 | task 19 | eval time = 42.00 ms / 2 tokens ( 42.00 ms per token, 23.81 tokens per second) 1.16.830.981 I slot print_timing: id 1 | task 19 | total time = 977.51 ms / 121 tokens 1.16.830.981 I slot print_timing: id 1 | task 19 | graphs reused = 1 1.16.830.982 I slot print_timing: id 1 | task 19 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.831.000 I slot release: id 1 | task 19 | stop processing: n_tokens = 129, truncated = 0 1.16.833.052 I slot print_timing: id 2 | task 20 | prompt eval time = 938.74 ms / 127 tokens ( 7.39 ms per token, 135.29 tokens per second) 1.16.833.056 I slot print_timing: id 2 | task 20 | eval time = 40.68 ms / 2 tokens ( 40.68 ms per token, 24.58 tokens per second) 1.16.833.057 I slot print_timing: id 2 | task 20 | total time = 979.42 ms / 129 tokens 1.16.833.057 I slot print_timing: id 2 | task 20 | graphs reused = 1 1.16.833.058 I slot print_timing: id 2 | task 20 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.833.076 I slot release: id 2 | task 20 | stop processing: n_tokens = 137, truncated = 0 1.16.835.094 I slot print_timing: id 3 | task 21 | prompt eval time = 941.71 ms / 120 tokens ( 7.85 ms per token, 127.43 tokens per second) 1.16.835.097 I slot print_timing: id 3 | task 21 | eval time = 39.57 ms / 2 tokens ( 39.57 ms per token, 25.27 tokens per second) 1.16.835.098 I slot print_timing: id 3 | task 21 | total time = 981.28 ms / 122 tokens 1.16.835.099 I slot print_timing: id 3 | task 21 | graphs reused = 1 1.16.835.099 I slot print_timing: id 3 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.835.112 I slot release: id 3 | task 21 | stop processing: n_tokens = 130, truncated = 0 1.16.835.996 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.230 1.16.839.813 I slot launch_slot_: id 0 | task 26 | processing task, is_child = 0 1.16.849.518 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.287 1.16.849.659 I slot launch_slot_: id 1 | task 27 | processing task, is_child = 0 1.16.849.734 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.270 1.16.849.827 I slot launch_slot_: id 2 | task 28 | processing task, is_child = 0 1.16.849.863 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.285 1.16.849.950 I slot launch_slot_: id 3 | task 29 | processing task, is_child = 0 1.17.980.617 I slot print_timing: id 2 | task 28 | prompt eval time = 1095.56 ms / 138 tokens ( 7.94 ms per token, 125.96 tokens per second) 1.17.980.620 I slot print_timing: id 2 | task 28 | eval time = 34.75 ms / 2 tokens ( 34.75 ms per token, 28.78 tokens per second) 1.17.980.620 I slot print_timing: id 2 | task 28 | total time = 1130.31 ms / 140 tokens 1.17.980.621 I slot print_timing: id 2 | task 28 | graphs reused = 1 1.17.980.621 I slot print_timing: id 2 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.980.642 I slot release: id 2 | task 28 | stop processing: n_tokens = 148, truncated = 0 1.17.981.949 I slot print_timing: id 3 | task 29 | prompt eval time = 1096.62 ms / 122 tokens ( 8.99 ms per token, 111.25 tokens per second) 1.17.981.951 I slot print_timing: id 3 | task 29 | eval time = 34.86 ms / 2 tokens ( 34.86 ms per token, 28.68 tokens per second) 1.17.981.951 I slot print_timing: id 3 | task 29 | total time = 1131.49 ms / 124 tokens 1.17.981.952 I slot print_timing: id 3 | task 29 | graphs reused = 1 1.17.981.952 I slot print_timing: id 3 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.981.970 I slot release: id 3 | task 29 | stop processing: n_tokens = 132, truncated = 0 1.18.012.777 I slot print_timing: id 0 | task 26 | prompt eval time = 1093.48 ms / 145 tokens ( 7.54 ms per token, 132.60 tokens per second) 1.18.012.782 I slot print_timing: id 0 | task 26 | eval time = 69.34 ms / 3 tokens ( 34.67 ms per token, 28.84 tokens per second) 1.18.012.782 I slot print_timing: id 0 | task 26 | total time = 1162.82 ms / 148 tokens 1.18.012.783 I slot print_timing: id 0 | task 26 | graphs reused = 1 1.18.012.783 I slot print_timing: id 0 | task 26 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.012.801 I slot release: id 0 | task 26 | stop processing: n_tokens = 156, truncated = 0 1.18.014.332 I slot print_timing: id 1 | task 27 | prompt eval time = 1094.52 ms / 184 tokens ( 5.95 ms per token, 168.11 tokens per second) 1.18.014.334 I slot print_timing: id 1 | task 27 | eval time = 69.66 ms / 3 tokens ( 34.83 ms per token, 28.71 tokens per second) 1.18.014.334 I slot print_timing: id 1 | task 27 | total time = 1164.18 ms / 187 tokens 1.18.014.335 I slot print_timing: id 1 | task 27 | graphs reused = 1 1.18.014.335 I slot print_timing: id 1 | task 27 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.014.348 I slot release: id 1 | task 27 | stop processing: n_tokens = 195, truncated = 0 1.18.014.353 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.237 1.18.019.267 I slot launch_slot_: id 0 | task 35 | processing task, is_child = 0 1.18.029.003 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.190 1.18.029.163 I slot launch_slot_: id 1 | task 36 | processing task, is_child = 0 1.18.029.246 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.250 1.18.029.352 I slot launch_slot_: id 2 | task 37 | processing task, is_child = 0 1.18.029.394 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.280 1.18.030.117 I slot launch_slot_: id 3 | task 38 | processing task, is_child = 0 1.19.142.996 I slot print_timing: id 1 | task 36 | prompt eval time = 1078.34 ms / 181 tokens ( 5.96 ms per token, 167.85 tokens per second) 1.19.142.999 I slot print_timing: id 1 | task 36 | eval time = 34.35 ms / 2 tokens ( 34.35 ms per token, 29.11 tokens per second) 1.19.142.999 I slot print_timing: id 1 | task 36 | total time = 1112.69 ms / 183 tokens 1.19.142.999 I slot print_timing: id 1 | task 36 | graphs reused = 1 1.19.143.000 I slot print_timing: id 1 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.143.028 I slot release: id 1 | task 36 | stop processing: n_tokens = 191, truncated = 0 1.19.144.173 I slot print_timing: id 2 | task 37 | prompt eval time = 1079.21 ms / 149 tokens ( 7.24 ms per token, 138.06 tokens per second) 1.19.144.181 I slot print_timing: id 2 | task 37 | eval time = 34.47 ms / 2 tokens ( 34.47 ms per token, 29.01 tokens per second) 1.19.144.181 I slot print_timing: id 2 | task 37 | total time = 1113.69 ms / 151 tokens 1.19.144.181 I slot print_timing: id 2 | task 37 | graphs reused = 1 1.19.144.182 I slot print_timing: id 2 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.144.193 I slot release: id 2 | task 37 | stop processing: n_tokens = 159, truncated = 0 1.19.145.351 I slot print_timing: id 3 | task 38 | prompt eval time = 1080.13 ms / 127 tokens ( 8.50 ms per token, 117.58 tokens per second) 1.19.145.357 I slot print_timing: id 3 | task 38 | eval time = 34.58 ms / 2 tokens ( 34.58 ms per token, 28.92 tokens per second) 1.19.145.358 I slot print_timing: id 3 | task 38 | total time = 1114.71 ms / 129 tokens 1.19.145.358 I slot print_timing: id 3 | task 38 | graphs reused = 1 1.19.145.358 I slot print_timing: id 3 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.145.373 I slot release: id 3 | task 38 | stop processing: n_tokens = 137, truncated = 0 1.19.174.209 I slot print_timing: id 0 | task 35 | prompt eval time = 1077.40 ms / 133 tokens ( 8.10 ms per token, 123.44 tokens per second) 1.19.174.212 I slot print_timing: id 0 | task 35 | eval time = 66.68 ms / 3 tokens ( 33.34 ms per token, 29.99 tokens per second) 1.19.174.212 I slot print_timing: id 0 | task 35 | total time = 1144.08 ms / 136 tokens 1.19.174.213 I slot print_timing: id 0 | task 35 | graphs reused = 1 1.19.174.213 I slot print_timing: id 0 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.174.226 I slot release: id 0 | task 35 | stop processing: n_tokens = 144, truncated = 0 1.19.174.232 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.298 (> 0.100 thold), f_keep = 0.257 1.19.177.780 I slot launch_slot_: id 0 | task 44 | processing task, is_child = 0 1.19.190.390 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.194 1.19.190.506 I slot launch_slot_: id 1 | task 45 | processing task, is_child = 0 1.19.190.586 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.233 1.19.190.682 I slot launch_slot_: id 2 | task 46 | processing task, is_child = 0 1.19.190.724 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.277 1.19.190.821 I slot launch_slot_: id 3 | task 47 | processing task, is_child = 0 1.20.240.048 I slot print_timing: id 0 | task 44 | prompt eval time = 980.03 ms / 115 tokens ( 8.52 ms per token, 117.34 tokens per second) 1.20.240.053 I slot print_timing: id 0 | task 44 | eval time = 69.18 ms / 3 tokens ( 34.59 ms per token, 28.91 tokens per second) 1.20.240.054 I slot print_timing: id 0 | task 44 | total time = 1049.21 ms / 118 tokens 1.20.240.055 I slot print_timing: id 0 | task 44 | graphs reused = 2 1.20.240.055 I slot print_timing: id 0 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.240.074 I slot release: id 0 | task 44 | stop processing: n_tokens = 126, truncated = 0 1.20.241.561 I slot print_timing: id 1 | task 45 | prompt eval time = 981.06 ms / 144 tokens ( 6.81 ms per token, 146.78 tokens per second) 1.20.241.563 I slot print_timing: id 1 | task 45 | eval time = 69.49 ms / 3 tokens ( 34.74 ms per token, 28.78 tokens per second) 1.20.241.564 I slot print_timing: id 1 | task 45 | total time = 1050.55 ms / 147 tokens 1.20.241.564 I slot print_timing: id 1 | task 45 | graphs reused = 2 1.20.241.565 I slot print_timing: id 1 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.241.580 I slot release: id 1 | task 45 | stop processing: n_tokens = 155, truncated = 0 1.20.243.074 I slot print_timing: id 2 | task 46 | prompt eval time = 982.24 ms / 148 tokens ( 6.64 ms per token, 150.68 tokens per second) 1.20.243.077 I slot print_timing: id 2 | task 46 | eval time = 69.63 ms / 3 tokens ( 34.82 ms per token, 28.72 tokens per second) 1.20.243.078 I slot print_timing: id 2 | task 46 | total time = 1051.87 ms / 151 tokens 1.20.243.078 I slot print_timing: id 2 | task 46 | graphs reused = 2 1.20.243.078 I slot print_timing: id 2 | task 46 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.243.090 I slot release: id 2 | task 46 | stop processing: n_tokens = 159, truncated = 0 1.20.244.570 I slot print_timing: id 3 | task 47 | prompt eval time = 983.43 ms / 122 tokens ( 8.06 ms per token, 124.06 tokens per second) 1.20.244.572 I slot print_timing: id 3 | task 47 | eval time = 69.77 ms / 3 tokens ( 34.88 ms per token, 28.67 tokens per second) 1.20.244.573 I slot print_timing: id 3 | task 47 | total time = 1053.20 ms / 125 tokens 1.20.244.573 I slot print_timing: id 3 | task 47 | graphs reused = 2 1.20.244.574 I slot print_timing: id 3 | task 47 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.244.584 I slot release: id 3 | task 47 | stop processing: n_tokens = 133, truncated = 0 1.20.244.976 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.286 1.20.248.115 I slot launch_slot_: id 3 | task 53 | processing task, is_child = 0 1.20.258.095 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.294 1.20.258.198 I slot launch_slot_: id 0 | task 54 | processing task, is_child = 0 1.20.258.298 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.239 1.20.258.388 I slot launch_slot_: id 1 | task 55 | processing task, is_child = 0 1.20.258.432 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.308 (> 0.100 thold), f_keep = 0.233 1.20.258.526 I slot launch_slot_: id 2 | task 56 | processing task, is_child = 0 1.21.231.089 I slot print_timing: id 0 | task 54 | prompt eval time = 937.99 ms / 124 tokens ( 7.56 ms per token, 132.20 tokens per second) 1.21.231.093 I slot print_timing: id 0 | task 54 | eval time = 34.56 ms / 2 tokens ( 34.56 ms per token, 28.93 tokens per second) 1.21.231.093 I slot print_timing: id 0 | task 54 | total time = 972.55 ms / 126 tokens 1.21.231.094 I slot print_timing: id 0 | task 54 | graphs reused = 2 1.21.231.094 I slot print_timing: id 0 | task 54 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.231.115 I slot release: id 0 | task 54 | stop processing: n_tokens = 134, truncated = 0 1.21.233.403 I slot print_timing: id 2 | task 56 | prompt eval time = 940.03 ms / 111 tokens ( 8.47 ms per token, 118.08 tokens per second) 1.21.233.405 I slot print_timing: id 2 | task 56 | eval time = 34.52 ms / 2 tokens ( 34.52 ms per token, 28.97 tokens per second) 1.21.233.406 I slot print_timing: id 2 | task 56 | total time = 974.55 ms / 113 tokens 1.21.233.406 I slot print_timing: id 2 | task 56 | graphs reused = 2 1.21.233.406 I slot print_timing: id 2 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.233.422 I slot release: id 2 | task 56 | stop processing: n_tokens = 121, truncated = 0 1.21.234.544 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.276 1.21.236.158 I slot launch_slot_: id 0 | task 61 | processing task, is_child = 0 1.21.237.084 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.306 1.21.237.144 I slot launch_slot_: id 2 | task 62 | processing task, is_child = 0 1.21.317.133 I slot print_timing: id 1 | task 55 | prompt eval time = 939.04 ms / 148 tokens ( 6.34 ms per token, 157.61 tokens per second) 1.21.317.136 I slot print_timing: id 1 | task 55 | eval time = 119.40 ms / 3 tokens ( 59.70 ms per token, 16.75 tokens per second) 1.21.317.138 I slot print_timing: id 1 | task 55 | total time = 1058.43 ms / 151 tokens 1.21.317.138 I slot print_timing: id 1 | task 55 | graphs reused = 2 1.21.317.139 I slot print_timing: id 1 | task 55 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.317.159 I slot release: id 1 | task 55 | stop processing: n_tokens = 159, truncated = 0 1.21.318.651 I slot print_timing: id 3 | task 53 | prompt eval time = 940.98 ms / 114 tokens ( 8.25 ms per token, 121.15 tokens per second) 1.21.318.653 I slot print_timing: id 3 | task 53 | eval time = 118.59 ms / 3 tokens ( 59.29 ms per token, 16.87 tokens per second) 1.21.318.654 I slot print_timing: id 3 | task 53 | total time = 1059.56 ms / 117 tokens 1.21.318.654 I slot print_timing: id 3 | task 53 | graphs reused = 2 1.21.318.655 I slot print_timing: id 3 | task 53 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.318.667 I slot release: id 3 | task 53 | stop processing: n_tokens = 125, truncated = 0 1.21.528.335 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.322 (> 0.100 thold), f_keep = 0.233 1.21.777.390 I slot launch_slot_: id 1 | task 65 | processing task, is_child = 0 1.21.780.908 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.311 (> 0.100 thold), f_keep = 0.304 1.21.781.009 I slot launch_slot_: id 3 | task 66 | processing task, is_child = 0 1.22.333.370 I slot print_timing: id 0 | task 61 | prompt eval time = 629.83 ms / 131 tokens ( 4.81 ms per token, 207.99 tokens per second) 1.22.333.373 I slot print_timing: id 0 | task 61 | eval time = 466.38 ms / 2 tokens ( 466.38 ms per token, 2.14 tokens per second) 1.22.333.374 I slot print_timing: id 0 | task 61 | total time = 1096.21 ms / 133 tokens 1.22.333.374 I slot print_timing: id 0 | task 61 | graphs reused = 2 1.22.333.375 I slot print_timing: id 0 | task 61 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.333.420 I slot release: id 0 | task 61 | stop processing: n_tokens = 141, truncated = 0 1.22.423.169 I slot print_timing: id 2 | task 62 | prompt eval time = 630.90 ms / 138 tokens ( 4.57 ms per token, 218.74 tokens per second) 1.22.423.172 I slot print_timing: id 2 | task 62 | eval time = 555.00 ms / 3 tokens ( 277.50 ms per token, 3.60 tokens per second) 1.22.423.173 I slot print_timing: id 2 | task 62 | total time = 1185.90 ms / 141 tokens 1.22.423.173 I slot print_timing: id 2 | task 62 | graphs reused = 2 1.22.423.174 I slot print_timing: id 2 | task 62 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.423.192 I slot release: id 2 | task 62 | stop processing: n_tokens = 149, truncated = 0 1.22.424.315 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.262 1.22.427.882 I slot launch_slot_: id 0 | task 70 | processing task, is_child = 0 1.22.430.159 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.248 1.22.430.236 I slot launch_slot_: id 2 | task 71 | processing task, is_child = 0 1.22.510.607 I slot print_timing: id 1 | task 65 | prompt eval time = 640.43 ms / 106 tokens ( 6.04 ms per token, 165.51 tokens per second) 1.22.510.610 I slot print_timing: id 1 | task 65 | eval time = 88.62 ms / 2 tokens ( 88.62 ms per token, 11.28 tokens per second) 1.22.510.610 I slot print_timing: id 1 | task 65 | total time = 729.06 ms / 108 tokens 1.22.510.611 I slot print_timing: id 1 | task 65 | graphs reused = 2 1.22.510.611 I slot print_timing: id 1 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.510.626 I slot release: id 1 | task 65 | stop processing: n_tokens = 116, truncated = 0 1.23.150.745 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.319 1.23.153.184 I slot launch_slot_: id 1 | task 74 | processing task, is_child = 0 1.23.543.350 I slot print_timing: id 3 | task 66 | prompt eval time = 642.14 ms / 113 tokens ( 5.68 ms per token, 175.97 tokens per second) 1.23.543.368 I slot print_timing: id 3 | task 66 | eval time = 1119.01 ms / 5 tokens ( 279.75 ms per token, 3.57 tokens per second) 1.23.543.369 I slot print_timing: id 3 | task 66 | total time = 1761.15 ms / 118 tokens 1.23.543.371 I slot print_timing: id 3 | task 66 | graphs reused = 2 1.23.543.372 I slot print_timing: id 3 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.543.484 I slot release: id 3 | task 66 | stop processing: n_tokens = 126, truncated = 0 1.23.633.497 I slot print_timing: id 0 | task 70 | prompt eval time = 838.24 ms / 194 tokens ( 4.32 ms per token, 231.44 tokens per second) 1.23.633.503 I slot print_timing: id 0 | task 70 | eval time = 365.01 ms / 3 tokens ( 182.50 ms per token, 5.48 tokens per second) 1.23.633.504 I slot print_timing: id 0 | task 70 | total time = 1203.25 ms / 197 tokens 1.23.633.505 I slot print_timing: id 0 | task 70 | graphs reused = 2 1.23.633.506 I slot print_timing: id 0 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.633.547 I slot release: id 0 | task 70 | stop processing: n_tokens = 205, truncated = 0 1.23.638.421 I slot print_timing: id 2 | task 71 | prompt eval time = 839.87 ms / 181 tokens ( 4.64 ms per token, 215.51 tokens per second) 1.23.638.425 I slot print_timing: id 2 | task 71 | eval time = 368.13 ms / 3 tokens ( 184.07 ms per token, 5.43 tokens per second) 1.23.638.426 I slot print_timing: id 2 | task 71 | total time = 1208.01 ms / 184 tokens 1.23.638.427 I slot print_timing: id 2 | task 71 | graphs reused = 2 1.23.638.427 I slot print_timing: id 2 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.638.456 I slot release: id 2 | task 71 | stop processing: n_tokens = 192, truncated = 0 1.23.638.464 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.180 1.23.645.141 I slot launch_slot_: id 0 | task 78 | processing task, is_child = 0 1.23.653.615 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.193 1.23.653.734 I slot launch_slot_: id 2 | task 79 | processing task, is_child = 0 1.23.653.776 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.294 1.23.653.870 I slot launch_slot_: id 3 | task 80 | processing task, is_child = 0 1.23.710.539 I slot print_timing: id 1 | task 74 | prompt eval time = 480.85 ms / 134 tokens ( 3.59 ms per token, 278.67 tokens per second) 1.23.710.543 I slot print_timing: id 1 | task 74 | eval time = 74.50 ms / 2 tokens ( 74.50 ms per token, 13.42 tokens per second) 1.23.710.544 I slot print_timing: id 1 | task 74 | total time = 555.36 ms / 136 tokens 1.23.710.545 I slot print_timing: id 1 | task 74 | graphs reused = 2 1.23.710.545 I slot print_timing: id 1 | task 74 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.710.568 I slot release: id 1 | task 74 | stop processing: n_tokens = 144, truncated = 0 1.24.503.820 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.257 1.24.577.124 I slot launch_slot_: id 1 | task 83 | processing task, is_child = 0 1.24.978.362 I slot print_timing: id 2 | task 79 | prompt eval time = 1015.14 ms / 171 tokens ( 5.94 ms per token, 168.45 tokens per second) 1.24.978.365 I slot print_timing: id 2 | task 79 | eval time = 309.12 ms / 2 tokens ( 309.12 ms per token, 3.23 tokens per second) 1.24.978.366 I slot print_timing: id 2 | task 79 | total time = 1324.26 ms / 173 tokens 1.24.978.366 I slot print_timing: id 2 | task 79 | graphs reused = 2 1.24.978.367 I slot print_timing: id 2 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.978.407 I slot release: id 2 | task 79 | stop processing: n_tokens = 181, truncated = 0 1.25.065.795 I slot print_timing: id 0 | task 78 | prompt eval time = 1014.15 ms / 168 tokens ( 6.04 ms per token, 165.66 tokens per second) 1.25.065.797 I slot print_timing: id 0 | task 78 | eval time = 397.76 ms / 3 tokens ( 198.88 ms per token, 5.03 tokens per second) 1.25.065.798 I slot print_timing: id 0 | task 78 | total time = 1411.91 ms / 171 tokens 1.25.065.798 I slot print_timing: id 0 | task 78 | graphs reused = 2 1.25.065.798 I slot print_timing: id 0 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.065.818 I slot release: id 0 | task 78 | stop processing: n_tokens = 179, truncated = 0 1.25.068.119 I slot print_timing: id 3 | task 80 | prompt eval time = 1016.18 ms / 152 tokens ( 6.69 ms per token, 149.58 tokens per second) 1.25.068.124 I slot print_timing: id 3 | task 80 | eval time = 397.66 ms / 3 tokens ( 198.83 ms per token, 5.03 tokens per second) 1.25.068.126 I slot print_timing: id 3 | task 80 | total time = 1413.85 ms / 155 tokens 1.25.068.126 I slot print_timing: id 3 | task 80 | graphs reused = 2 1.25.068.126 I slot print_timing: id 3 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.068.140 I slot release: id 3 | task 80 | stop processing: n_tokens = 163, truncated = 0 1.25.068.145 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.207 1.25.072.354 I slot launch_slot_: id 0 | task 87 | processing task, is_child = 0 1.25.077.229 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.204 1.25.077.298 I slot launch_slot_: id 2 | task 88 | processing task, is_child = 0 1.25.077.324 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.227 1.25.077.378 I slot launch_slot_: id 3 | task 89 | processing task, is_child = 0 1.25.131.514 I slot print_timing: id 1 | task 83 | prompt eval time = 488.60 ms / 143 tokens ( 3.42 ms per token, 292.67 tokens per second) 1.25.131.518 I slot print_timing: id 1 | task 83 | eval time = 64.47 ms / 2 tokens ( 64.47 ms per token, 15.51 tokens per second) 1.25.131.519 I slot print_timing: id 1 | task 83 | total time = 553.07 ms / 145 tokens 1.25.131.519 I slot print_timing: id 1 | task 83 | graphs reused = 2 1.25.131.520 I slot print_timing: id 1 | task 83 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.131.541 I slot release: id 1 | task 83 | stop processing: n_tokens = 153, truncated = 0 1.25.734.942 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.322 (> 0.100 thold), f_keep = 0.248 1.25.847.231 I slot launch_slot_: id 1 | task 92 | processing task, is_child = 0 1.26.203.528 I slot print_timing: id 0 | task 87 | prompt eval time = 860.20 ms / 125 tokens ( 6.88 ms per token, 145.32 tokens per second) 1.26.203.535 I slot print_timing: id 0 | task 87 | eval time = 265.94 ms / 2 tokens ( 265.94 ms per token, 3.76 tokens per second) 1.26.203.536 I slot print_timing: id 0 | task 87 | total time = 1126.14 ms / 127 tokens 1.26.203.537 I slot print_timing: id 0 | task 87 | graphs reused = 2 1.26.203.537 I slot print_timing: id 0 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.203.564 I slot release: id 0 | task 87 | stop processing: n_tokens = 135, truncated = 0 1.26.204.682 I slot print_timing: id 2 | task 88 | prompt eval time = 861.35 ms / 130 tokens ( 6.63 ms per token, 150.93 tokens per second) 1.26.204.684 I slot print_timing: id 2 | task 88 | eval time = 265.82 ms / 2 tokens ( 265.82 ms per token, 3.76 tokens per second) 1.26.204.684 I slot print_timing: id 2 | task 88 | total time = 1127.18 ms / 132 tokens 1.26.204.685 I slot print_timing: id 2 | task 88 | graphs reused = 2 1.26.204.685 I slot print_timing: id 2 | task 88 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.204.699 I slot release: id 2 | task 88 | stop processing: n_tokens = 140, truncated = 0 1.26.205.788 I slot print_timing: id 3 | task 89 | prompt eval time = 862.50 ms / 166 tokens ( 5.20 ms per token, 192.46 tokens per second) 1.26.205.791 I slot print_timing: id 3 | task 89 | eval time = 265.65 ms / 2 tokens ( 265.65 ms per token, 3.76 tokens per second) 1.26.205.791 I slot print_timing: id 3 | task 89 | total time = 1128.16 ms / 168 tokens 1.26.205.791 I slot print_timing: id 3 | task 89 | graphs reused = 2 1.26.205.792 I slot print_timing: id 3 | task 89 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.205.806 I slot release: id 3 | task 89 | stop processing: n_tokens = 176, truncated = 0 1.26.238.440 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.222 1.26.242.038 I slot launch_slot_: id 3 | task 96 | processing task, is_child = 0 1.26.247.177 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.281 1.26.247.284 I slot launch_slot_: id 0 | task 97 | processing task, is_child = 0 1.26.247.313 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.264 1.26.247.379 I slot launch_slot_: id 2 | task 98 | processing task, is_child = 0 1.26.304.003 I slot print_timing: id 1 | task 92 | prompt eval time = 390.71 ms / 109 tokens ( 3.58 ms per token, 278.98 tokens per second) 1.26.304.005 I slot print_timing: id 1 | task 92 | eval time = 65.57 ms / 2 tokens ( 65.57 ms per token, 15.25 tokens per second) 1.26.304.006 I slot print_timing: id 1 | task 92 | total time = 456.28 ms / 111 tokens 1.26.304.006 I slot print_timing: id 1 | task 92 | graphs reused = 2 1.26.304.007 I slot print_timing: id 1 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.304.023 I slot release: id 1 | task 92 | stop processing: n_tokens = 119, truncated = 0 1.27.103.606 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.311 1.27.145.925 I slot launch_slot_: id 1 | task 101 | processing task, is_child = 0 1.27.508.588 I slot print_timing: id 2 | task 98 | prompt eval time = 994.16 ms / 170 tokens ( 5.85 ms per token, 171.00 tokens per second) 1.27.508.592 I slot print_timing: id 2 | task 98 | eval time = 266.90 ms / 2 tokens ( 266.90 ms per token, 3.75 tokens per second) 1.27.508.593 I slot print_timing: id 2 | task 98 | total time = 1261.07 ms / 172 tokens 1.27.508.593 I slot print_timing: id 2 | task 98 | graphs reused = 2 1.27.508.594 I slot print_timing: id 2 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.508.617 I slot release: id 2 | task 98 | stop processing: n_tokens = 180, truncated = 0 1.27.509.730 I slot print_timing: id 3 | task 96 | prompt eval time = 995.24 ms / 160 tokens ( 6.22 ms per token, 160.77 tokens per second) 1.27.509.732 I slot print_timing: id 3 | task 96 | eval time = 266.86 ms / 2 tokens ( 266.86 ms per token, 3.75 tokens per second) 1.27.509.733 I slot print_timing: id 3 | task 96 | total time = 1262.10 ms / 162 tokens 1.27.509.733 I slot print_timing: id 3 | task 96 | graphs reused = 2 1.27.509.733 I slot print_timing: id 3 | task 96 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.509.748 I slot release: id 3 | task 96 | stop processing: n_tokens = 170, truncated = 0 1.27.570.404 I slot print_timing: id 0 | task 97 | prompt eval time = 993.27 ms / 167 tokens ( 5.95 ms per token, 168.13 tokens per second) 1.27.570.406 I slot print_timing: id 0 | task 97 | eval time = 329.75 ms / 3 tokens ( 164.87 ms per token, 6.07 tokens per second) 1.27.570.406 I slot print_timing: id 0 | task 97 | total time = 1323.02 ms / 170 tokens 1.27.570.407 I slot print_timing: id 0 | task 97 | graphs reused = 2 1.27.570.407 I slot print_timing: id 0 | task 97 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.570.423 I slot release: id 0 | task 97 | stop processing: n_tokens = 178, truncated = 0 1.27.571.617 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.317 (> 0.100 thold), f_keep = 0.213 1.27.575.525 I slot launch_slot_: id 0 | task 105 | processing task, is_child = 0 1.27.582.312 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.206 1.27.582.384 I slot launch_slot_: id 2 | task 106 | processing task, is_child = 0 1.27.582.414 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.218 1.27.582.990 I slot launch_slot_: id 3 | task 107 | processing task, is_child = 0 1.27.639.277 I slot print_timing: id 1 | task 101 | prompt eval time = 424.10 ms / 113 tokens ( 3.75 ms per token, 266.45 tokens per second) 1.27.639.279 I slot print_timing: id 1 | task 101 | eval time = 67.66 ms / 2 tokens ( 67.66 ms per token, 14.78 tokens per second) 1.27.639.280 I slot print_timing: id 1 | task 101 | total time = 491.76 ms / 115 tokens 1.27.639.280 I slot print_timing: id 1 | task 101 | graphs reused = 2 1.27.639.281 I slot print_timing: id 1 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.639.295 I slot release: id 1 | task 101 | stop processing: n_tokens = 123, truncated = 0 1.28.243.606 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.301 1.28.285.478 I slot launch_slot_: id 1 | task 110 | processing task, is_child = 0 1.28.689.632 I slot print_timing: id 0 | task 105 | prompt eval time = 792.95 ms / 111 tokens ( 7.14 ms per token, 139.98 tokens per second) 1.28.689.635 I slot print_timing: id 0 | task 105 | eval time = 313.68 ms / 2 tokens ( 313.68 ms per token, 3.19 tokens per second) 1.28.689.635 I slot print_timing: id 0 | task 105 | total time = 1106.63 ms / 113 tokens 1.28.689.636 I slot print_timing: id 0 | task 105 | graphs reused = 2 1.28.689.636 I slot print_timing: id 0 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.689.657 I slot release: id 0 | task 105 | stop processing: n_tokens = 121, truncated = 0 1.28.690.765 I slot print_timing: id 2 | task 106 | prompt eval time = 794.14 ms / 136 tokens ( 5.84 ms per token, 171.25 tokens per second) 1.28.690.766 I slot print_timing: id 2 | task 106 | eval time = 313.49 ms / 2 tokens ( 313.49 ms per token, 3.19 tokens per second) 1.28.690.767 I slot print_timing: id 2 | task 106 | total time = 1107.63 ms / 138 tokens 1.28.690.767 I slot print_timing: id 2 | task 106 | graphs reused = 2 1.28.690.768 I slot print_timing: id 2 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.690.780 I slot release: id 2 | task 106 | stop processing: n_tokens = 146, truncated = 0 1.28.691.912 I slot print_timing: id 3 | task 107 | prompt eval time = 795.29 ms / 126 tokens ( 6.31 ms per token, 158.43 tokens per second) 1.28.691.914 I slot print_timing: id 3 | task 107 | eval time = 313.36 ms / 2 tokens ( 313.36 ms per token, 3.19 tokens per second) 1.28.691.914 I slot print_timing: id 3 | task 107 | total time = 1108.65 ms / 128 tokens 1.28.691.914 I slot print_timing: id 3 | task 107 | graphs reused = 2 1.28.691.915 I slot print_timing: id 3 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.691.925 I slot release: id 3 | task 107 | stop processing: n_tokens = 136, truncated = 0 1.28.724.806 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.306 1.28.726.908 I slot launch_slot_: id 0 | task 114 | processing task, is_child = 0 1.28.732.651 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.253 1.28.733.239 I slot launch_slot_: id 2 | task 115 | processing task, is_child = 0 1.28.733.269 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.279 1.28.733.329 I slot launch_slot_: id 3 | task 116 | processing task, is_child = 0 1.28.789.707 I slot print_timing: id 1 | task 110 | prompt eval time = 438.85 ms / 149 tokens ( 2.95 ms per token, 339.52 tokens per second) 1.28.789.709 I slot print_timing: id 1 | task 110 | eval time = 64.90 ms / 2 tokens ( 64.90 ms per token, 15.41 tokens per second) 1.28.789.709 I slot print_timing: id 1 | task 110 | total time = 503.75 ms / 151 tokens 1.28.789.710 I slot print_timing: id 1 | task 110 | graphs reused = 2 1.28.789.710 I slot print_timing: id 1 | task 110 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.789.728 I slot release: id 1 | task 110 | stop processing: n_tokens = 159, truncated = 0 1.29.395.353 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.233 1.29.467.310 I slot launch_slot_: id 1 | task 119 | processing task, is_child = 0 1.29.871.144 I slot print_timing: id 2 | task 115 | prompt eval time = 825.67 ms / 126 tokens ( 6.55 ms per token, 152.60 tokens per second) 1.29.871.147 I slot print_timing: id 2 | task 115 | eval time = 312.02 ms / 2 tokens ( 312.02 ms per token, 3.20 tokens per second) 1.29.871.147 I slot print_timing: id 2 | task 115 | total time = 1137.69 ms / 128 tokens 1.29.871.148 I slot print_timing: id 2 | task 115 | graphs reused = 2 1.29.871.148 I slot print_timing: id 2 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.871.167 I slot release: id 2 | task 115 | stop processing: n_tokens = 136, truncated = 0 1.29.960.019 I slot print_timing: id 0 | task 114 | prompt eval time = 824.67 ms / 124 tokens ( 6.65 ms per token, 150.36 tokens per second) 1.29.960.021 I slot print_timing: id 0 | task 114 | eval time = 402.02 ms / 3 tokens ( 201.01 ms per token, 4.97 tokens per second) 1.29.960.021 I slot print_timing: id 0 | task 114 | total time = 1226.68 ms / 127 tokens 1.29.960.022 I slot print_timing: id 0 | task 114 | graphs reused = 2 1.29.960.022 I slot print_timing: id 0 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.960.040 I slot release: id 0 | task 114 | stop processing: n_tokens = 135, truncated = 0 1.29.962.323 I slot print_timing: id 3 | task 116 | prompt eval time = 826.61 ms / 148 tokens ( 5.59 ms per token, 179.04 tokens per second) 1.29.962.325 I slot print_timing: id 3 | task 116 | eval time = 402.15 ms / 3 tokens ( 201.08 ms per token, 4.97 tokens per second) 1.29.962.326 I slot print_timing: id 3 | task 116 | total time = 1228.76 ms / 151 tokens 1.29.962.326 I slot print_timing: id 3 | task 116 | graphs reused = 2 1.29.962.326 I slot print_timing: id 3 | task 116 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.962.340 I slot release: id 3 | task 116 | stop processing: n_tokens = 159, truncated = 0 1.29.962.345 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.239 1.29.965.517 I slot launch_slot_: id 3 | task 123 | processing task, is_child = 0 1.29.967.713 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.287 (> 0.100 thold), f_keep = 0.274 1.29.968.251 I slot launch_slot_: id 0 | task 124 | processing task, is_child = 0 1.29.968.279 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.311 (> 0.100 thold), f_keep = 0.272 1.29.968.789 I slot launch_slot_: id 2 | task 125 | processing task, is_child = 0 1.30.024.989 I slot print_timing: id 1 | task 119 | prompt eval time = 493.37 ms / 143 tokens ( 3.45 ms per token, 289.84 tokens per second) 1.30.024.995 I slot print_timing: id 1 | task 119 | eval time = 63.77 ms / 2 tokens ( 63.77 ms per token, 15.68 tokens per second) 1.30.024.995 I slot print_timing: id 1 | task 119 | total time = 557.14 ms / 145 tokens 1.30.024.995 I slot print_timing: id 1 | task 119 | graphs reused = 2 1.30.024.996 I slot print_timing: id 1 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.025.014 I slot release: id 1 | task 119 | stop processing: n_tokens = 153, truncated = 0 1.30.584.743 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.280 (> 0.100 thold), f_keep = 0.242 1.30.656.656 I slot launch_slot_: id 1 | task 128 | processing task, is_child = 0 1.31.015.693 I slot print_timing: id 0 | task 124 | prompt eval time = 778.31 ms / 120 tokens ( 6.49 ms per token, 154.18 tokens per second) 1.31.015.695 I slot print_timing: id 0 | task 124 | eval time = 268.59 ms / 2 tokens ( 268.59 ms per token, 3.72 tokens per second) 1.31.015.696 I slot print_timing: id 0 | task 124 | total time = 1046.89 ms / 122 tokens 1.31.015.696 I slot print_timing: id 0 | task 124 | graphs reused = 2 1.31.015.697 I slot print_timing: id 0 | task 124 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.015.714 I slot release: id 0 | task 124 | stop processing: n_tokens = 130, truncated = 0 1.31.016.825 I slot print_timing: id 2 | task 125 | prompt eval time = 779.30 ms / 110 tokens ( 7.08 ms per token, 141.15 tokens per second) 1.31.016.827 I slot print_timing: id 2 | task 125 | eval time = 268.61 ms / 2 tokens ( 268.61 ms per token, 3.72 tokens per second) 1.31.016.828 I slot print_timing: id 2 | task 125 | total time = 1047.91 ms / 112 tokens 1.31.016.828 I slot print_timing: id 2 | task 125 | graphs reused = 2 1.31.016.828 I slot print_timing: id 2 | task 125 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.016.839 I slot release: id 2 | task 125 | stop processing: n_tokens = 120, truncated = 0 1.31.017.940 I slot print_timing: id 3 | task 123 | prompt eval time = 780.43 ms / 136 tokens ( 5.74 ms per token, 174.26 tokens per second) 1.31.017.941 I slot print_timing: id 3 | task 123 | eval time = 268.49 ms / 2 tokens ( 268.49 ms per token, 3.72 tokens per second) 1.31.017.942 I slot print_timing: id 3 | task 123 | total time = 1048.92 ms / 138 tokens 1.31.017.942 I slot print_timing: id 3 | task 123 | graphs reused = 2 1.31.017.943 I slot print_timing: id 3 | task 123 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.017.953 I slot release: id 3 | task 123 | stop processing: n_tokens = 146, truncated = 0 1.31.050.700 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.285 1.31.052.290 I slot launch_slot_: id 0 | task 132 | processing task, is_child = 0 1.31.055.349 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.145 (> 0.100 thold), f_keep = 0.308 1.31.055.420 I slot launch_slot_: id 2 | task 133 | processing task, is_child = 0 1.31.055.448 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.307 (> 0.100 thold), f_keep = 0.267 1.31.055.513 I slot launch_slot_: id 3 | task 134 | processing task, is_child = 0 1.31.111.837 I slot print_timing: id 1 | task 128 | prompt eval time = 393.55 ms / 123 tokens ( 3.20 ms per token, 312.54 tokens per second) 1.31.111.840 I slot print_timing: id 1 | task 128 | eval time = 61.14 ms / 2 tokens ( 61.14 ms per token, 16.36 tokens per second) 1.31.111.840 I slot print_timing: id 1 | task 128 | total time = 454.69 ms / 125 tokens 1.31.111.841 I slot print_timing: id 1 | task 128 | graphs reused = 2 1.31.111.841 I slot print_timing: id 1 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.111.855 I slot release: id 1 | task 128 | stop processing: n_tokens = 133, truncated = 0 1.31.814.147 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.278 1.32.067.695 I slot launch_slot_: id 1 | task 137 | processing task, is_child = 0 1.32.475.478 I slot print_timing: id 2 | task 133 | prompt eval time = 1107.65 ms / 247 tokens ( 4.48 ms per token, 222.99 tokens per second) 1.32.475.481 I slot print_timing: id 2 | task 133 | eval time = 312.19 ms / 2 tokens ( 312.19 ms per token, 3.20 tokens per second) 1.32.475.482 I slot print_timing: id 2 | task 133 | total time = 1419.84 ms / 249 tokens 1.32.475.482 I slot print_timing: id 2 | task 133 | graphs reused = 2 1.32.475.482 I slot print_timing: id 2 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.475.506 I slot release: id 2 | task 133 | stop processing: n_tokens = 257, truncated = 0 1.32.476.595 I slot print_timing: id 3 | task 134 | prompt eval time = 1108.71 ms / 118 tokens ( 9.40 ms per token, 106.43 tokens per second) 1.32.476.600 I slot print_timing: id 3 | task 134 | eval time = 312.15 ms / 2 tokens ( 312.15 ms per token, 3.20 tokens per second) 1.32.476.601 I slot print_timing: id 3 | task 134 | total time = 1420.86 ms / 120 tokens 1.32.476.601 I slot print_timing: id 3 | task 134 | graphs reused = 2 1.32.476.601 I slot print_timing: id 3 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.476.613 I slot release: id 3 | task 134 | stop processing: n_tokens = 128, truncated = 0 1.32.537.549 I slot print_timing: id 0 | task 132 | prompt eval time = 1106.68 ms / 175 tokens ( 6.32 ms per token, 158.13 tokens per second) 1.32.537.551 I slot print_timing: id 0 | task 132 | eval time = 375.35 ms / 3 tokens ( 187.67 ms per token, 5.33 tokens per second) 1.32.537.552 I slot print_timing: id 0 | task 132 | total time = 1482.03 ms / 178 tokens 1.32.537.552 I slot print_timing: id 0 | task 132 | graphs reused = 2 1.32.537.552 I slot print_timing: id 0 | task 132 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.537.567 I slot release: id 0 | task 132 | stop processing: n_tokens = 186, truncated = 0 1.32.538.705 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.305 1.32.540.785 I slot launch_slot_: id 3 | task 141 | processing task, is_child = 0 1.32.549.344 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.199 1.32.549.906 I slot launch_slot_: id 0 | task 142 | processing task, is_child = 0 1.32.549.945 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.144 1.32.550.471 I slot launch_slot_: id 2 | task 143 | processing task, is_child = 0 1.33.433.696 I slot print_timing: id 1 | task 137 | prompt eval time = 469.34 ms / 138 tokens ( 3.40 ms per token, 294.03 tokens per second) 1.33.433.699 I slot print_timing: id 1 | task 137 | eval time = 894.99 ms / 3 tokens ( 447.50 ms per token, 2.23 tokens per second) 1.33.433.699 I slot print_timing: id 1 | task 137 | total time = 1364.33 ms / 141 tokens 1.33.433.700 I slot print_timing: id 1 | task 137 | graphs reused = 2 1.33.433.700 I slot print_timing: id 1 | task 137 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.433.720 I slot release: id 1 | task 137 | stop processing: n_tokens = 149, truncated = 0 1.33.502.170 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.248 1.33.503.445 I slot launch_slot_: id 1 | task 147 | processing task, is_child = 0 1.33.563.996 I slot print_timing: id 2 | task 143 | prompt eval time = 950.41 ms / 145 tokens ( 6.55 ms per token, 152.57 tokens per second) 1.33.563.999 I slot print_timing: id 2 | task 143 | eval time = 62.99 ms / 2 tokens ( 62.99 ms per token, 15.88 tokens per second) 1.33.564.000 I slot print_timing: id 2 | task 143 | total time = 1013.40 ms / 147 tokens 1.33.564.000 I slot print_timing: id 2 | task 143 | graphs reused = 2 1.33.564.000 I slot print_timing: id 2 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.564.019 I slot release: id 2 | task 143 | stop processing: n_tokens = 155, truncated = 0 1.33.565.125 I slot print_timing: id 3 | task 141 | prompt eval time = 951.47 ms / 158 tokens ( 6.02 ms per token, 166.06 tokens per second) 1.33.565.127 I slot print_timing: id 3 | task 141 | eval time = 62.96 ms / 2 tokens ( 62.96 ms per token, 15.88 tokens per second) 1.33.565.127 I slot print_timing: id 3 | task 141 | total time = 1014.43 ms / 160 tokens 1.33.565.127 I slot print_timing: id 3 | task 141 | graphs reused = 2 1.33.565.128 I slot print_timing: id 3 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.565.142 I slot release: id 3 | task 141 | stop processing: n_tokens = 168, truncated = 0 1.33.848.512 I slot print_timing: id 0 | task 142 | prompt eval time = 949.49 ms / 182 tokens ( 5.22 ms per token, 191.68 tokens per second) 1.33.848.517 I slot print_timing: id 0 | task 142 | eval time = 348.53 ms / 3 tokens ( 174.27 ms per token, 5.74 tokens per second) 1.33.848.518 I slot print_timing: id 0 | task 142 | total time = 1298.02 ms / 185 tokens 1.33.848.519 I slot print_timing: id 0 | task 142 | graphs reused = 2 1.33.848.520 I slot print_timing: id 0 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.848.563 I slot release: id 0 | task 142 | stop processing: n_tokens = 193, truncated = 0 1.33.848.581 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.192 1.33.856.432 I slot launch_slot_: id 0 | task 150 | processing task, is_child = 0 1.33.866.464 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.345 (> 0.100 thold), f_keep = 0.258 1.33.866.597 I slot launch_slot_: id 2 | task 151 | processing task, is_child = 0 1.33.866.643 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.185 (> 0.100 thold), f_keep = 0.220 1.33.867.914 I slot launch_slot_: id 3 | task 152 | processing task, is_child = 0 1.34.816.142 I slot print_timing: id 1 | task 147 | prompt eval time = 425.12 ms / 162 tokens ( 2.62 ms per token, 381.07 tokens per second) 1.34.816.144 I slot print_timing: id 1 | task 147 | eval time = 887.57 ms / 2 tokens ( 887.57 ms per token, 1.13 tokens per second) 1.34.816.145 I slot print_timing: id 1 | task 147 | total time = 1312.69 ms / 164 tokens 1.34.816.145 I slot print_timing: id 1 | task 147 | graphs reused = 2 1.34.816.146 I slot print_timing: id 1 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.816.167 I slot release: id 1 | task 147 | stop processing: n_tokens = 172, truncated = 0 1.34.884.398 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.215 1.34.887.788 I slot launch_slot_: id 1 | task 156 | processing task, is_child = 0 1.34.946.758 I slot print_timing: id 2 | task 151 | prompt eval time = 1013.64 ms / 107 tokens ( 9.47 ms per token, 105.56 tokens per second) 1.34.946.763 I slot print_timing: id 2 | task 151 | eval time = 63.64 ms / 2 tokens ( 63.64 ms per token, 15.71 tokens per second) 1.34.946.764 I slot print_timing: id 2 | task 151 | total time = 1077.28 ms / 109 tokens 1.34.946.764 I slot print_timing: id 2 | task 151 | graphs reused = 2 1.34.946.765 I slot print_timing: id 2 | task 151 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.946.784 I slot release: id 2 | task 151 | stop processing: n_tokens = 117, truncated = 0 1.35.208.847 I slot print_timing: id 0 | task 150 | prompt eval time = 1013.91 ms / 229 tokens ( 4.43 ms per token, 225.86 tokens per second) 1.35.208.849 I slot print_timing: id 0 | task 150 | eval time = 326.99 ms / 3 tokens ( 163.50 ms per token, 6.12 tokens per second) 1.35.208.851 I slot print_timing: id 0 | task 150 | total time = 1340.90 ms / 232 tokens 1.35.208.851 I slot print_timing: id 0 | task 150 | graphs reused = 2 1.35.208.852 I slot print_timing: id 0 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.208.879 I slot release: id 0 | task 150 | stop processing: n_tokens = 240, truncated = 0 1.35.210.050 I slot print_timing: id 3 | task 152 | prompt eval time = 1014.69 ms / 191 tokens ( 5.31 ms per token, 188.24 tokens per second) 1.35.210.052 I slot print_timing: id 3 | task 152 | eval time = 325.65 ms / 3 tokens ( 162.83 ms per token, 6.14 tokens per second) 1.35.210.053 I slot print_timing: id 3 | task 152 | total time = 1340.34 ms / 194 tokens 1.35.210.053 I slot print_timing: id 3 | task 152 | graphs reused = 2 1.35.210.053 I slot print_timing: id 3 | task 152 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.210.081 I slot release: id 3 | task 152 | stop processing: n_tokens = 202, truncated = 0 1.35.210.088 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.154 1.35.216.488 I slot launch_slot_: id 0 | task 159 | processing task, is_child = 0 1.35.221.455 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.316 1.35.221.524 I slot launch_slot_: id 2 | task 160 | processing task, is_child = 0 1.35.221.555 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.183 1.35.221.620 I slot launch_slot_: id 3 | task 161 | processing task, is_child = 0 1.36.206.147 I slot print_timing: id 1 | task 156 | prompt eval time = 390.97 ms / 117 tokens ( 3.34 ms per token, 299.25 tokens per second) 1.36.206.152 I slot print_timing: id 1 | task 156 | eval time = 927.37 ms / 3 tokens ( 463.69 ms per token, 2.16 tokens per second) 1.36.206.152 I slot print_timing: id 1 | task 156 | total time = 1318.34 ms / 120 tokens 1.36.206.153 I slot print_timing: id 1 | task 156 | graphs reused = 2 1.36.206.153 I slot print_timing: id 1 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.206.185 I slot release: id 1 | task 156 | stop processing: n_tokens = 128, truncated = 0 1.36.272.939 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.297 1.36.276.139 I slot launch_slot_: id 1 | task 166 | processing task, is_child = 0 1.36.336.934 I slot print_timing: id 0 | task 159 | prompt eval time = 982.72 ms / 143 tokens ( 6.87 ms per token, 145.51 tokens per second) 1.36.336.940 I slot print_timing: id 0 | task 159 | eval time = 132.57 ms / 3 tokens ( 66.28 ms per token, 15.09 tokens per second) 1.36.336.941 I slot print_timing: id 0 | task 159 | total time = 1115.29 ms / 146 tokens 1.36.336.942 I slot print_timing: id 0 | task 159 | graphs reused = 2 1.36.336.943 I slot print_timing: id 0 | task 159 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.336.998 I slot release: id 0 | task 159 | stop processing: n_tokens = 154, truncated = 0 1.36.339.047 I slot print_timing: id 2 | task 160 | prompt eval time = 985.96 ms / 140 tokens ( 7.04 ms per token, 141.99 tokens per second) 1.36.339.051 I slot print_timing: id 2 | task 160 | eval time = 130.88 ms / 3 tokens ( 65.44 ms per token, 15.28 tokens per second) 1.36.339.052 I slot print_timing: id 2 | task 160 | total time = 1116.84 ms / 143 tokens 1.36.339.053 I slot print_timing: id 2 | task 160 | graphs reused = 2 1.36.339.054 I slot print_timing: id 2 | task 160 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.339.092 I slot release: id 2 | task 160 | stop processing: n_tokens = 151, truncated = 0 1.36.340.993 I slot print_timing: id 3 | task 161 | prompt eval time = 987.90 ms / 175 tokens ( 5.65 ms per token, 177.14 tokens per second) 1.36.340.998 I slot print_timing: id 3 | task 161 | eval time = 130.77 ms / 3 tokens ( 65.38 ms per token, 15.29 tokens per second) 1.36.340.999 I slot print_timing: id 3 | task 161 | total time = 1118.67 ms / 178 tokens 1.36.341.000 I slot print_timing: id 3 | task 161 | graphs reused = 2 1.36.341.000 I slot print_timing: id 3 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.341.035 I slot release: id 3 | task 161 | stop processing: n_tokens = 186, truncated = 0 1.36.589.870 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.306 (> 0.100 thold), f_keep = 0.240 1.36.596.092 I slot launch_slot_: id 0 | task 170 | processing task, is_child = 0 1.36.607.013 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.253 (> 0.100 thold), f_keep = 0.245 1.36.607.141 I slot launch_slot_: id 2 | task 171 | processing task, is_child = 0 1.36.607.191 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.199 1.36.608.345 I slot launch_slot_: id 3 | task 172 | processing task, is_child = 0 1.37.417.356 I slot print_timing: id 1 | task 166 | prompt eval time = 313.69 ms / 122 tokens ( 2.57 ms per token, 388.92 tokens per second) 1.37.417.373 I slot print_timing: id 1 | task 166 | eval time = 827.46 ms / 3 tokens ( 413.73 ms per token, 2.42 tokens per second) 1.37.417.374 I slot print_timing: id 1 | task 166 | total time = 1141.15 ms / 125 tokens 1.37.417.376 I slot print_timing: id 1 | task 166 | graphs reused = 2 1.37.417.377 I slot print_timing: id 1 | task 166 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.417.455 I slot release: id 1 | task 166 | stop processing: n_tokens = 133, truncated = 0 1.37.495.042 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.278 1.37.498.267 I slot launch_slot_: id 1 | task 176 | processing task, is_child = 0 1.37.558.945 I slot print_timing: id 0 | task 170 | prompt eval time = 881.75 ms / 112 tokens ( 7.87 ms per token, 127.02 tokens per second) 1.37.558.958 I slot print_timing: id 0 | task 170 | eval time = 68.82 ms / 2 tokens ( 68.82 ms per token, 14.53 tokens per second) 1.37.558.959 I slot print_timing: id 0 | task 170 | total time = 950.57 ms / 114 tokens 1.37.558.961 I slot print_timing: id 0 | task 170 | graphs reused = 2 1.37.558.962 I slot print_timing: id 0 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.559.033 I slot release: id 0 | task 170 | stop processing: n_tokens = 122, truncated = 0 1.37.560.976 I slot print_timing: id 2 | task 171 | prompt eval time = 884.08 ms / 137 tokens ( 6.45 ms per token, 154.96 tokens per second) 1.37.560.986 I slot print_timing: id 2 | task 171 | eval time = 68.28 ms / 2 tokens ( 68.28 ms per token, 14.65 tokens per second) 1.37.560.987 I slot print_timing: id 2 | task 171 | total time = 952.36 ms / 139 tokens 1.37.560.988 I slot print_timing: id 2 | task 171 | graphs reused = 2 1.37.560.988 I slot print_timing: id 2 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.561.037 I slot release: id 2 | task 171 | stop processing: n_tokens = 147, truncated = 0 1.37.847.601 I slot print_timing: id 3 | task 172 | prompt eval time = 886.16 ms / 162 tokens ( 5.47 ms per token, 182.81 tokens per second) 1.37.847.609 I slot print_timing: id 3 | task 172 | eval time = 352.55 ms / 3 tokens ( 176.27 ms per token, 5.67 tokens per second) 1.37.847.617 I slot print_timing: id 3 | task 172 | total time = 1238.70 ms / 165 tokens 1.37.847.622 I slot print_timing: id 3 | task 172 | graphs reused = 2 1.37.847.623 I slot print_timing: id 3 | task 172 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.847.716 I slot release: id 3 | task 172 | stop processing: n_tokens = 173, truncated = 0 1.37.847.752 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.311 1.37.855.264 I slot launch_slot_: id 0 | task 179 | processing task, is_child = 0 1.37.869.514 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.252 1.37.869.660 I slot launch_slot_: id 2 | task 180 | processing task, is_child = 0 1.37.869.714 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.214 1.37.869.821 I slot launch_slot_: id 3 | task 181 | processing task, is_child = 0 1.38.684.027 I slot print_timing: id 1 | task 176 | prompt eval time = 434.66 ms / 138 tokens ( 3.15 ms per token, 317.49 tokens per second) 1.38.684.037 I slot print_timing: id 1 | task 176 | eval time = 751.05 ms / 2 tokens ( 751.05 ms per token, 1.33 tokens per second) 1.38.684.038 I slot print_timing: id 1 | task 176 | total time = 1185.71 ms / 140 tokens 1.38.684.040 I slot print_timing: id 1 | task 176 | graphs reused = 2 1.38.684.041 I slot print_timing: id 1 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.684.137 I slot release: id 1 | task 176 | stop processing: n_tokens = 148, truncated = 0 1.38.760.890 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.250 1.38.766.261 I slot launch_slot_: id 1 | task 185 | processing task, is_child = 0 1.38.829.064 I slot print_timing: id 2 | task 180 | prompt eval time = 885.74 ms / 132 tokens ( 6.71 ms per token, 149.03 tokens per second) 1.38.829.076 I slot print_timing: id 2 | task 180 | eval time = 70.42 ms / 2 tokens ( 70.42 ms per token, 14.20 tokens per second) 1.38.829.077 I slot print_timing: id 2 | task 180 | total time = 956.15 ms / 134 tokens 1.38.829.079 I slot print_timing: id 2 | task 180 | graphs reused = 2 1.38.829.080 I slot print_timing: id 2 | task 180 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.829.151 I slot release: id 2 | task 180 | stop processing: n_tokens = 142, truncated = 0 1.39.197.537 I slot print_timing: id 0 | task 179 | prompt eval time = 886.58 ms / 122 tokens ( 7.27 ms per token, 137.61 tokens per second) 1.39.197.553 I slot print_timing: id 0 | task 179 | eval time = 441.08 ms / 3 tokens ( 220.54 ms per token, 4.53 tokens per second) 1.39.197.554 I slot print_timing: id 0 | task 179 | total time = 1327.67 ms / 125 tokens 1.39.197.556 I slot print_timing: id 0 | task 179 | graphs reused = 2 1.39.197.557 I slot print_timing: id 0 | task 179 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.197.668 I slot release: id 0 | task 179 | stop processing: n_tokens = 133, truncated = 0 1.39.199.802 I slot print_timing: id 3 | task 181 | prompt eval time = 887.70 ms / 183 tokens ( 4.85 ms per token, 206.15 tokens per second) 1.39.199.808 I slot print_timing: id 3 | task 181 | eval time = 438.94 ms / 3 tokens ( 219.47 ms per token, 4.56 tokens per second) 1.39.199.812 I slot print_timing: id 3 | task 181 | total time = 1326.63 ms / 186 tokens 1.39.199.812 I slot print_timing: id 3 | task 181 | graphs reused = 2 1.39.199.813 I slot print_timing: id 3 | task 181 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.199.869 I slot release: id 3 | task 181 | stop processing: n_tokens = 194, truncated = 0 1.39.199.896 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.198 (> 0.100 thold), f_keep = 0.278 1.39.205.694 I slot launch_slot_: id 0 | task 188 | processing task, is_child = 0 1.39.221.191 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.261 1.39.221.343 I slot launch_slot_: id 2 | task 189 | processing task, is_child = 0 1.39.221.395 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.191 1.39.222.898 I slot launch_slot_: id 3 | task 190 | processing task, is_child = 0 1.40.005.109 I slot print_timing: id 1 | task 185 | prompt eval time = 518.05 ms / 183 tokens ( 2.83 ms per token, 353.25 tokens per second) 1.40.005.121 I slot print_timing: id 1 | task 185 | eval time = 720.73 ms / 2 tokens ( 720.73 ms per token, 1.39 tokens per second) 1.40.005.123 I slot print_timing: id 1 | task 185 | total time = 1238.78 ms / 185 tokens 1.40.005.125 I slot print_timing: id 1 | task 185 | graphs reused = 2 1.40.005.126 I slot print_timing: id 1 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.005.233 I slot release: id 1 | task 185 | stop processing: n_tokens = 193, truncated = 0 1.40.083.289 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.192 1.40.092.831 I slot launch_slot_: id 1 | task 194 | processing task, is_child = 0 1.40.156.556 I slot print_timing: id 2 | task 189 | prompt eval time = 856.55 ms / 117 tokens ( 7.32 ms per token, 136.59 tokens per second) 1.40.156.562 I slot print_timing: id 2 | task 189 | eval time = 75.25 ms / 2 tokens ( 75.25 ms per token, 13.29 tokens per second) 1.40.156.564 I slot print_timing: id 2 | task 189 | total time = 931.80 ms / 119 tokens 1.40.156.565 I slot print_timing: id 2 | task 189 | graphs reused = 2 1.40.156.566 I slot print_timing: id 2 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.156.597 I slot release: id 2 | task 189 | stop processing: n_tokens = 127, truncated = 0 1.40.159.068 I slot print_timing: id 3 | task 190 | prompt eval time = 858.26 ms / 125 tokens ( 6.87 ms per token, 145.64 tokens per second) 1.40.159.072 I slot print_timing: id 3 | task 190 | eval time = 75.82 ms / 2 tokens ( 75.82 ms per token, 13.19 tokens per second) 1.40.159.073 I slot print_timing: id 3 | task 190 | total time = 934.08 ms / 127 tokens 1.40.159.073 I slot print_timing: id 3 | task 190 | graphs reused = 2 1.40.159.074 I slot print_timing: id 3 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.159.116 I slot release: id 3 | task 190 | stop processing: n_tokens = 135, truncated = 0 1.40.400.226 I slot print_timing: id 0 | task 188 | prompt eval time = 856.30 ms / 178 tokens ( 4.81 ms per token, 207.87 tokens per second) 1.40.400.233 I slot print_timing: id 0 | task 188 | eval time = 320.97 ms / 3 tokens ( 160.48 ms per token, 6.23 tokens per second) 1.40.400.235 I slot print_timing: id 0 | task 188 | total time = 1177.26 ms / 181 tokens 1.40.400.241 I slot print_timing: id 0 | task 188 | graphs reused = 2 1.40.400.242 I slot print_timing: id 0 | task 188 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.400.345 I slot release: id 0 | task 188 | stop processing: n_tokens = 189, truncated = 0 1.40.400.389 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.302 (> 0.100 thold), f_keep = 0.281 1.40.407.583 I slot launch_slot_: id 3 | task 197 | processing task, is_child = 0 1.40.417.469 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.196 1.40.418.703 I slot launch_slot_: id 0 | task 198 | processing task, is_child = 0 1.40.418.753 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.291 1.40.418.866 I slot launch_slot_: id 2 | task 199 | processing task, is_child = 0 1.41.147.051 I slot print_timing: id 1 | task 194 | prompt eval time = 388.12 ms / 125 tokens ( 3.10 ms per token, 322.07 tokens per second) 1.41.147.062 I slot print_timing: id 1 | task 194 | eval time = 666.06 ms / 2 tokens ( 666.06 ms per token, 1.50 tokens per second) 1.41.147.063 I slot print_timing: id 1 | task 194 | total time = 1054.17 ms / 127 tokens 1.41.147.065 I slot print_timing: id 1 | task 194 | graphs reused = 2 1.41.147.066 I slot print_timing: id 1 | task 194 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.147.155 I slot release: id 1 | task 194 | stop processing: n_tokens = 135, truncated = 0 1.41.223.494 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.274 1.41.228.296 I slot launch_slot_: id 1 | task 203 | processing task, is_child = 0 1.41.288.857 I slot print_timing: id 0 | task 198 | prompt eval time = 800.27 ms / 131 tokens ( 6.11 ms per token, 163.69 tokens per second) 1.41.288.866 I slot print_timing: id 0 | task 198 | eval time = 69.68 ms / 2 tokens ( 69.68 ms per token, 14.35 tokens per second) 1.41.288.867 I slot print_timing: id 0 | task 198 | total time = 869.95 ms / 133 tokens 1.41.288.869 I slot print_timing: id 0 | task 198 | graphs reused = 2 1.41.288.870 I slot print_timing: id 0 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.288.957 I slot release: id 0 | task 198 | stop processing: n_tokens = 141, truncated = 0 1.41.533.210 I slot print_timing: id 2 | task 199 | prompt eval time = 801.06 ms / 143 tokens ( 5.60 ms per token, 178.51 tokens per second) 1.41.533.216 I slot print_timing: id 2 | task 199 | eval time = 311.74 ms / 3 tokens ( 155.87 ms per token, 6.42 tokens per second) 1.41.533.218 I slot print_timing: id 2 | task 199 | total time = 1112.80 ms / 146 tokens 1.41.533.220 I slot print_timing: id 2 | task 199 | graphs reused = 3 1.41.533.221 I slot print_timing: id 2 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.533.374 I slot release: id 2 | task 199 | stop processing: n_tokens = 154, truncated = 0 1.41.535.741 I slot print_timing: id 3 | task 197 | prompt eval time = 802.73 ms / 117 tokens ( 6.86 ms per token, 145.75 tokens per second) 1.41.535.747 I slot print_timing: id 3 | task 197 | eval time = 312.26 ms / 3 tokens ( 156.13 ms per token, 6.40 tokens per second) 1.41.535.748 I slot print_timing: id 3 | task 197 | total time = 1114.99 ms / 120 tokens 1.41.535.749 I slot print_timing: id 3 | task 197 | graphs reused = 3 1.41.535.750 I slot print_timing: id 3 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.535.791 I slot release: id 3 | task 197 | stop processing: n_tokens = 128, truncated = 0 1.41.535.824 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.262 1.41.542.095 I slot launch_slot_: id 0 | task 206 | processing task, is_child = 0 1.41.551.515 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.240 1.41.551.653 I slot launch_slot_: id 2 | task 207 | processing task, is_child = 0 1.41.551.703 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.289 1.41.551.810 I slot launch_slot_: id 3 | task 208 | processing task, is_child = 0 1.42.378.931 I slot print_timing: id 1 | task 203 | prompt eval time = 384.68 ms / 130 tokens ( 2.96 ms per token, 337.95 tokens per second) 1.42.378.936 I slot print_timing: id 1 | task 203 | eval time = 765.94 ms / 3 tokens ( 382.97 ms per token, 2.61 tokens per second) 1.42.378.937 I slot print_timing: id 1 | task 203 | total time = 1150.61 ms / 133 tokens 1.42.378.937 I slot print_timing: id 1 | task 203 | graphs reused = 3 1.42.378.938 I slot print_timing: id 1 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.378.979 I slot release: id 1 | task 203 | stop processing: n_tokens = 141, truncated = 0 1.42.443.312 I slot print_timing: id 0 | task 206 | prompt eval time = 824.60 ms / 132 tokens ( 6.25 ms per token, 160.08 tokens per second) 1.42.443.321 I slot print_timing: id 0 | task 206 | eval time = 66.88 ms / 2 tokens ( 66.88 ms per token, 14.95 tokens per second) 1.42.443.322 I slot print_timing: id 0 | task 206 | total time = 891.48 ms / 134 tokens 1.42.443.323 I slot print_timing: id 0 | task 206 | graphs reused = 3 1.42.443.323 I slot print_timing: id 0 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.443.358 I slot release: id 0 | task 206 | stop processing: n_tokens = 142, truncated = 0 1.42.445.859 I slot print_timing: id 2 | task 207 | prompt eval time = 828.79 ms / 131 tokens ( 6.33 ms per token, 158.06 tokens per second) 1.42.445.869 I slot print_timing: id 2 | task 207 | eval time = 63.90 ms / 2 tokens ( 63.90 ms per token, 15.65 tokens per second) 1.42.445.870 I slot print_timing: id 2 | task 207 | total time = 892.69 ms / 133 tokens 1.42.445.870 I slot print_timing: id 2 | task 207 | graphs reused = 3 1.42.445.871 I slot print_timing: id 2 | task 207 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.445.904 I slot release: id 2 | task 207 | stop processing: n_tokens = 141, truncated = 0 1.42.448.387 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.325 (> 0.100 thold), f_keep = 0.261 1.42.455.550 I slot launch_slot_: id 0 | task 213 | processing task, is_child = 0 1.42.463.968 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.262 1.42.464.079 I slot launch_slot_: id 1 | task 214 | processing task, is_child = 0 1.42.464.121 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.262 1.42.464.993 I slot launch_slot_: id 2 | task 215 | processing task, is_child = 0 1.42.523.063 I slot print_timing: id 3 | task 208 | prompt eval time = 831.20 ms / 124 tokens ( 6.70 ms per token, 149.18 tokens per second) 1.42.523.067 I slot print_timing: id 3 | task 208 | eval time = 138.44 ms / 3 tokens ( 69.22 ms per token, 14.45 tokens per second) 1.42.523.069 I slot print_timing: id 3 | task 208 | total time = 969.64 ms / 127 tokens 1.42.523.070 I slot print_timing: id 3 | task 208 | graphs reused = 3 1.42.523.071 I slot print_timing: id 3 | task 208 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.523.100 I slot release: id 3 | task 208 | stop processing: n_tokens = 135, truncated = 0 1.43.172.730 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.274 1.43.244.200 I slot launch_slot_: id 3 | task 218 | processing task, is_child = 0 1.43.655.796 I slot print_timing: id 0 | task 213 | prompt eval time = 853.94 ms / 105 tokens ( 8.13 ms per token, 122.96 tokens per second) 1.43.655.799 I slot print_timing: id 0 | task 213 | eval time = 336.85 ms / 2 tokens ( 336.85 ms per token, 2.97 tokens per second) 1.43.655.800 I slot print_timing: id 0 | task 213 | total time = 1190.79 ms / 107 tokens 1.43.655.800 I slot print_timing: id 0 | task 213 | graphs reused = 3 1.43.655.801 I slot print_timing: id 0 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.655.833 I slot release: id 0 | task 213 | stop processing: n_tokens = 115, truncated = 0 1.43.656.904 I slot print_timing: id 1 | task 214 | prompt eval time = 854.95 ms / 160 tokens ( 5.34 ms per token, 187.15 tokens per second) 1.43.656.907 I slot print_timing: id 1 | task 214 | eval time = 336.75 ms / 2 tokens ( 336.75 ms per token, 2.97 tokens per second) 1.43.656.907 I slot print_timing: id 1 | task 214 | total time = 1191.70 ms / 162 tokens 1.43.656.908 I slot print_timing: id 1 | task 214 | graphs reused = 3 1.43.656.908 I slot print_timing: id 1 | task 214 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.656.927 I slot release: id 1 | task 214 | stop processing: n_tokens = 170, truncated = 0 1.43.658.051 I slot print_timing: id 2 | task 215 | prompt eval time = 856.05 ms / 143 tokens ( 5.99 ms per token, 167.05 tokens per second) 1.43.658.053 I slot print_timing: id 2 | task 215 | eval time = 336.61 ms / 2 tokens ( 336.61 ms per token, 2.97 tokens per second) 1.43.658.054 I slot print_timing: id 2 | task 215 | total time = 1192.66 ms / 145 tokens 1.43.658.054 I slot print_timing: id 2 | task 215 | graphs reused = 3 1.43.658.054 I slot print_timing: id 2 | task 215 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.658.067 I slot release: id 2 | task 215 | stop processing: n_tokens = 153, truncated = 0 1.43.691.202 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.311 (> 0.100 thold), f_keep = 0.330 1.43.693.004 I slot launch_slot_: id 0 | task 222 | processing task, is_child = 0 1.43.699.279 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.218 1.43.699.347 I slot launch_slot_: id 1 | task 223 | processing task, is_child = 0 1.43.699.377 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.306 (> 0.100 thold), f_keep = 0.242 1.43.699.438 I slot launch_slot_: id 2 | task 224 | processing task, is_child = 0 1.43.753.592 I slot print_timing: id 3 | task 218 | prompt eval time = 444.21 ms / 173 tokens ( 2.57 ms per token, 389.45 tokens per second) 1.43.753.595 I slot print_timing: id 3 | task 218 | eval time = 62.39 ms / 2 tokens ( 62.39 ms per token, 16.03 tokens per second) 1.43.753.596 I slot print_timing: id 3 | task 218 | total time = 506.61 ms / 175 tokens 1.43.753.596 I slot print_timing: id 3 | task 218 | graphs reused = 3 1.43.753.596 I slot print_timing: id 3 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.753.618 I slot release: id 3 | task 218 | stop processing: n_tokens = 183, truncated = 0 1.44.311.491 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.202 1.44.425.969 I slot launch_slot_: id 3 | task 227 | processing task, is_child = 0 1.44.783.388 I slot print_timing: id 0 | task 222 | prompt eval time = 800.04 ms / 113 tokens ( 7.08 ms per token, 141.24 tokens per second) 1.44.783.391 I slot print_timing: id 0 | task 222 | eval time = 283.90 ms / 2 tokens ( 283.90 ms per token, 3.52 tokens per second) 1.44.783.391 I slot print_timing: id 0 | task 222 | total time = 1083.94 ms / 115 tokens 1.44.783.391 I slot print_timing: id 0 | task 222 | graphs reused = 3 1.44.783.392 I slot print_timing: id 0 | task 222 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.783.422 I slot release: id 0 | task 222 | stop processing: n_tokens = 123, truncated = 0 1.44.785.625 I slot print_timing: id 2 | task 224 | prompt eval time = 802.06 ms / 112 tokens ( 7.16 ms per token, 139.64 tokens per second) 1.44.785.627 I slot print_timing: id 2 | task 224 | eval time = 283.88 ms / 2 tokens ( 283.88 ms per token, 3.52 tokens per second) 1.44.785.627 I slot print_timing: id 2 | task 224 | total time = 1085.94 ms / 114 tokens 1.44.785.628 I slot print_timing: id 2 | task 224 | graphs reused = 3 1.44.785.628 I slot print_timing: id 2 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.785.659 I slot release: id 2 | task 224 | stop processing: n_tokens = 122, truncated = 0 1.44.843.466 I slot print_timing: id 1 | task 223 | prompt eval time = 801.05 ms / 161 tokens ( 4.98 ms per token, 200.99 tokens per second) 1.44.843.468 I slot print_timing: id 1 | task 223 | eval time = 342.84 ms / 3 tokens ( 171.42 ms per token, 5.83 tokens per second) 1.44.843.469 I slot print_timing: id 1 | task 223 | total time = 1143.90 ms / 164 tokens 1.44.843.469 I slot print_timing: id 1 | task 223 | graphs reused = 3 1.44.843.470 I slot print_timing: id 1 | task 223 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.843.487 I slot release: id 1 | task 223 | stop processing: n_tokens = 172, truncated = 0 1.44.844.762 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.301 1.44.845.954 I slot launch_slot_: id 0 | task 231 | processing task, is_child = 0 1.44.850.302 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.306 (> 0.100 thold), f_keep = 0.215 1.44.850.957 I slot launch_slot_: id 1 | task 232 | processing task, is_child = 0 1.44.850.989 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.301 (> 0.100 thold), f_keep = 0.303 1.44.851.486 I slot launch_slot_: id 2 | task 233 | processing task, is_child = 0 1.44.905.655 I slot print_timing: id 3 | task 227 | prompt eval time = 416.58 ms / 152 tokens ( 2.74 ms per token, 364.88 tokens per second) 1.44.905.657 I slot print_timing: id 3 | task 227 | eval time = 60.89 ms / 2 tokens ( 60.89 ms per token, 16.42 tokens per second) 1.44.905.658 I slot print_timing: id 3 | task 227 | total time = 477.47 ms / 154 tokens 1.44.905.658 I slot print_timing: id 3 | task 227 | graphs reused = 3 1.44.905.659 I slot print_timing: id 3 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.905.676 I slot release: id 3 | task 227 | stop processing: n_tokens = 162, truncated = 0 1.45.509.929 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.228 1.45.536.296 I slot launch_slot_: id 3 | task 236 | processing task, is_child = 0 1.45.893.280 I slot print_timing: id 0 | task 231 | prompt eval time = 757.86 ms / 140 tokens ( 5.41 ms per token, 184.73 tokens per second) 1.45.893.282 I slot print_timing: id 0 | task 231 | eval time = 283.92 ms / 2 tokens ( 283.92 ms per token, 3.52 tokens per second) 1.45.893.283 I slot print_timing: id 0 | task 231 | total time = 1041.78 ms / 142 tokens 1.45.893.283 I slot print_timing: id 0 | task 231 | graphs reused = 3 1.45.893.284 I slot print_timing: id 0 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.893.308 I slot release: id 0 | task 231 | stop processing: n_tokens = 150, truncated = 0 1.45.895.528 I slot print_timing: id 2 | task 233 | prompt eval time = 759.96 ms / 114 tokens ( 6.67 ms per token, 150.01 tokens per second) 1.45.895.529 I slot print_timing: id 2 | task 233 | eval time = 283.84 ms / 2 tokens ( 283.84 ms per token, 3.52 tokens per second) 1.45.895.530 I slot print_timing: id 2 | task 233 | total time = 1043.80 ms / 116 tokens 1.45.895.530 I slot print_timing: id 2 | task 233 | graphs reused = 3 1.45.895.531 I slot print_timing: id 2 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.895.546 I slot release: id 2 | task 233 | stop processing: n_tokens = 124, truncated = 0 1.45.953.239 I slot print_timing: id 1 | task 232 | prompt eval time = 758.85 ms / 112 tokens ( 6.78 ms per token, 147.59 tokens per second) 1.45.953.243 I slot print_timing: id 1 | task 232 | eval time = 342.78 ms / 3 tokens ( 171.39 ms per token, 5.83 tokens per second) 1.45.953.244 I slot print_timing: id 1 | task 232 | total time = 1101.62 ms / 115 tokens 1.45.953.244 I slot print_timing: id 1 | task 232 | graphs reused = 3 1.45.953.245 I slot print_timing: id 1 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.953.267 I slot release: id 1 | task 232 | stop processing: n_tokens = 123, truncated = 0 1.45.954.618 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.247 1.45.956.477 I slot launch_slot_: id 0 | task 240 | processing task, is_child = 0 1.45.958.308 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.301 1.45.958.377 I slot launch_slot_: id 1 | task 241 | processing task, is_child = 0 1.45.958.401 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.292 (> 0.100 thold), f_keep = 0.306 1.45.958.455 I slot launch_slot_: id 2 | task 242 | processing task, is_child = 0 1.46.643.422 I slot print_timing: id 3 | task 236 | prompt eval time = 416.82 ms / 155 tokens ( 2.69 ms per token, 371.87 tokens per second) 1.46.643.427 I slot print_timing: id 3 | task 236 | eval time = 688.80 ms / 3 tokens ( 344.40 ms per token, 2.90 tokens per second) 1.46.643.428 I slot print_timing: id 3 | task 236 | total time = 1105.62 ms / 158 tokens 1.46.643.429 I slot print_timing: id 3 | task 236 | graphs reused = 3 1.46.643.429 I slot print_timing: id 3 | task 236 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.643.453 I slot release: id 3 | task 236 | stop processing: n_tokens = 166, truncated = 0 1.46.699.597 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.223 1.46.705.989 I slot launch_slot_: id 3 | task 246 | processing task, is_child = 0 1.46.741.690 I slot print_timing: id 1 | task 241 | prompt eval time = 738.94 ms / 125 tokens ( 5.91 ms per token, 169.16 tokens per second) 1.46.741.694 I slot print_timing: id 1 | task 241 | eval time = 44.17 ms / 2 tokens ( 44.17 ms per token, 22.64 tokens per second) 1.46.741.694 I slot print_timing: id 1 | task 241 | total time = 783.11 ms / 127 tokens 1.46.741.695 I slot print_timing: id 1 | task 241 | graphs reused = 3 1.46.741.696 I slot print_timing: id 1 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.741.722 I slot release: id 1 | task 241 | stop processing: n_tokens = 135, truncated = 0 1.46.743.806 I slot print_timing: id 2 | task 242 | prompt eval time = 740.89 ms / 121 tokens ( 6.12 ms per token, 163.32 tokens per second) 1.46.743.809 I slot print_timing: id 2 | task 242 | eval time = 44.23 ms / 2 tokens ( 44.23 ms per token, 22.61 tokens per second) 1.46.743.809 I slot print_timing: id 2 | task 242 | total time = 785.12 ms / 123 tokens 1.46.743.809 I slot print_timing: id 2 | task 242 | graphs reused = 3 1.46.743.810 I slot print_timing: id 2 | task 242 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.743.828 I slot release: id 2 | task 242 | stop processing: n_tokens = 131, truncated = 0 1.47.079.981 I slot print_timing: id 0 | task 240 | prompt eval time = 737.21 ms / 134 tokens ( 5.50 ms per token, 181.77 tokens per second) 1.47.079.992 I slot print_timing: id 0 | task 240 | eval time = 384.27 ms / 3 tokens ( 192.13 ms per token, 5.20 tokens per second) 1.47.079.994 I slot print_timing: id 0 | task 240 | total time = 1121.48 ms / 137 tokens 1.47.079.999 I slot print_timing: id 0 | task 240 | graphs reused = 3 1.47.080.006 I slot print_timing: id 0 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.080.113 I slot release: id 0 | task 240 | stop processing: n_tokens = 145, truncated = 0 1.47.080.150 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.255 1.47.089.026 I slot launch_slot_: id 0 | task 249 | processing task, is_child = 0 1.47.098.388 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.274 1.47.098.520 I slot launch_slot_: id 1 | task 250 | processing task, is_child = 0 1.47.098.570 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.311 (> 0.100 thold), f_keep = 0.282 1.47.098.680 I slot launch_slot_: id 2 | task 251 | processing task, is_child = 0 1.47.965.312 I slot print_timing: id 3 | task 246 | prompt eval time = 456.47 ms / 170 tokens ( 2.69 ms per token, 372.42 tokens per second) 1.47.965.329 I slot print_timing: id 3 | task 246 | eval time = 802.82 ms / 3 tokens ( 401.41 ms per token, 2.49 tokens per second) 1.47.965.330 I slot print_timing: id 3 | task 246 | total time = 1259.29 ms / 173 tokens 1.47.965.331 I slot print_timing: id 3 | task 246 | graphs reused = 3 1.47.965.332 I slot print_timing: id 3 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.965.435 I slot release: id 3 | task 246 | stop processing: n_tokens = 181, truncated = 0 1.48.003.500 I slot print_timing: id 2 | task 251 | prompt eval time = 864.09 ms / 110 tokens ( 7.86 ms per token, 127.30 tokens per second) 1.48.003.505 I slot print_timing: id 2 | task 251 | eval time = 40.13 ms / 2 tokens ( 40.13 ms per token, 24.92 tokens per second) 1.48.003.506 I slot print_timing: id 2 | task 251 | total time = 904.21 ms / 112 tokens 1.48.003.507 I slot print_timing: id 2 | task 251 | graphs reused = 3 1.48.003.507 I slot print_timing: id 2 | task 251 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.003.535 I slot release: id 2 | task 251 | stop processing: n_tokens = 120, truncated = 0 1.48.003.547 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.308 1.48.007.565 I slot launch_slot_: id 2 | task 256 | processing task, is_child = 0 1.48.014.267 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.204 1.48.015.243 I slot launch_slot_: id 3 | task 257 | processing task, is_child = 0 1.48.047.958 I slot print_timing: id 0 | task 249 | prompt eval time = 860.43 ms / 159 tokens ( 5.41 ms per token, 184.79 tokens per second) 1.48.047.962 I slot print_timing: id 0 | task 249 | eval time = 88.83 ms / 3 tokens ( 44.41 ms per token, 22.51 tokens per second) 1.48.047.962 I slot print_timing: id 0 | task 249 | total time = 949.26 ms / 162 tokens 1.48.047.963 I slot print_timing: id 0 | task 249 | graphs reused = 3 1.48.047.963 I slot print_timing: id 0 | task 249 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.047.984 I slot release: id 0 | task 249 | stop processing: n_tokens = 170, truncated = 0 1.48.049.597 I slot print_timing: id 1 | task 250 | prompt eval time = 862.37 ms / 131 tokens ( 6.58 ms per token, 151.91 tokens per second) 1.48.049.604 I slot print_timing: id 1 | task 250 | eval time = 88.24 ms / 3 tokens ( 44.12 ms per token, 22.66 tokens per second) 1.48.049.605 I slot print_timing: id 1 | task 250 | total time = 950.61 ms / 134 tokens 1.48.049.605 I slot print_timing: id 1 | task 250 | graphs reused = 3 1.48.049.606 I slot print_timing: id 1 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.049.621 I slot release: id 1 | task 250 | stop processing: n_tokens = 142, truncated = 0 1.48.544.070 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.218 1.48.660.334 I slot launch_slot_: id 0 | task 260 | processing task, is_child = 0 1.48.664.602 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.261 1.48.666.213 I slot launch_slot_: id 1 | task 261 | processing task, is_child = 0 1.49.193.972 I slot print_timing: id 3 | task 257 | prompt eval time = 722.00 ms / 155 tokens ( 4.66 ms per token, 214.68 tokens per second) 1.49.193.979 I slot print_timing: id 3 | task 257 | eval time = 456.49 ms / 2 tokens ( 456.49 ms per token, 2.19 tokens per second) 1.49.193.980 I slot print_timing: id 3 | task 257 | total time = 1178.49 ms / 157 tokens 1.49.193.982 I slot print_timing: id 3 | task 257 | graphs reused = 3 1.49.193.983 I slot print_timing: id 3 | task 257 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.194.078 I slot release: id 3 | task 257 | stop processing: n_tokens = 165, truncated = 0 1.49.265.561 I slot print_timing: id 2 | task 256 | prompt eval time = 719.33 ms / 188 tokens ( 3.83 ms per token, 261.35 tokens per second) 1.49.265.572 I slot print_timing: id 2 | task 256 | eval time = 530.96 ms / 3 tokens ( 265.48 ms per token, 3.77 tokens per second) 1.49.265.573 I slot print_timing: id 2 | task 256 | total time = 1250.29 ms / 191 tokens 1.49.265.574 I slot print_timing: id 2 | task 256 | graphs reused = 3 1.49.265.575 I slot print_timing: id 2 | task 256 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.265.686 I slot release: id 2 | task 256 | stop processing: n_tokens = 199, truncated = 0 1.49.265.709 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.253 (> 0.100 thold), f_keep = 0.186 1.49.275.325 I slot launch_slot_: id 2 | task 265 | processing task, is_child = 0 1.49.280.421 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.224 1.49.281.609 I slot launch_slot_: id 3 | task 266 | processing task, is_child = 0 1.49.316.871 I slot print_timing: id 1 | task 261 | prompt eval time = 597.06 ms / 148 tokens ( 4.03 ms per token, 247.88 tokens per second) 1.49.316.875 I slot print_timing: id 1 | task 261 | eval time = 53.23 ms / 2 tokens ( 53.23 ms per token, 18.78 tokens per second) 1.49.316.877 I slot print_timing: id 1 | task 261 | total time = 650.30 ms / 150 tokens 1.49.316.878 I slot print_timing: id 1 | task 261 | graphs reused = 3 1.49.316.878 I slot print_timing: id 1 | task 261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.316.905 I slot release: id 1 | task 261 | stop processing: n_tokens = 158, truncated = 0 1.49.861.694 I slot print_timing: id 0 | task 260 | prompt eval time = 595.29 ms / 117 tokens ( 5.09 ms per token, 196.54 tokens per second) 1.49.861.708 I slot print_timing: id 0 | task 260 | eval time = 600.14 ms / 3 tokens ( 300.07 ms per token, 3.33 tokens per second) 1.49.861.710 I slot print_timing: id 0 | task 260 | total time = 1195.42 ms / 120 tokens 1.49.861.712 I slot print_timing: id 0 | task 260 | graphs reused = 3 1.49.861.713 I slot print_timing: id 0 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.861.813 I slot release: id 0 | task 260 | stop processing: n_tokens = 128, truncated = 0 1.49.861.850 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.289 1.49.867.514 I slot launch_slot_: id 0 | task 269 | processing task, is_child = 0 1.49.873.820 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.241 1.49.873.987 I slot launch_slot_: id 1 | task 270 | processing task, is_child = 0 1.50.466.448 I slot print_timing: id 2 | task 265 | prompt eval time = 657.19 ms / 137 tokens ( 4.80 ms per token, 208.46 tokens per second) 1.50.466.456 I slot print_timing: id 2 | task 265 | eval time = 527.59 ms / 2 tokens ( 527.59 ms per token, 1.90 tokens per second) 1.50.466.458 I slot print_timing: id 2 | task 265 | total time = 1184.78 ms / 139 tokens 1.50.466.460 I slot print_timing: id 2 | task 265 | graphs reused = 3 1.50.466.464 I slot print_timing: id 2 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.466.575 I slot release: id 2 | task 265 | stop processing: n_tokens = 147, truncated = 0 1.50.469.038 I slot print_timing: id 3 | task 266 | prompt eval time = 659.47 ms / 159 tokens ( 4.15 ms per token, 241.10 tokens per second) 1.50.469.048 I slot print_timing: id 3 | task 266 | eval time = 527.64 ms / 2 tokens ( 527.64 ms per token, 1.90 tokens per second) 1.50.469.049 I slot print_timing: id 3 | task 266 | total time = 1187.12 ms / 161 tokens 1.50.469.051 I slot print_timing: id 3 | task 266 | graphs reused = 3 1.50.469.052 I slot print_timing: id 3 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.469.108 I slot release: id 3 | task 266 | stop processing: n_tokens = 169, truncated = 0 1.50.515.251 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.291 (> 0.100 thold), f_keep = 0.252 1.50.520.938 I slot launch_slot_: id 2 | task 274 | processing task, is_child = 0 1.50.524.542 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.219 1.50.525.629 I slot launch_slot_: id 3 | task 275 | processing task, is_child = 0 1.50.964.368 I slot print_timing: id 0 | task 269 | prompt eval time = 638.86 ms / 136 tokens ( 4.70 ms per token, 212.88 tokens per second) 1.50.964.371 I slot print_timing: id 0 | task 269 | eval time = 451.50 ms / 3 tokens ( 225.75 ms per token, 4.43 tokens per second) 1.50.964.371 I slot print_timing: id 0 | task 269 | total time = 1090.36 ms / 139 tokens 1.50.964.371 I slot print_timing: id 0 | task 269 | graphs reused = 4 1.50.964.372 I slot print_timing: id 0 | task 269 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.964.404 I slot release: id 0 | task 269 | stop processing: n_tokens = 147, truncated = 0 1.50.965.585 I slot print_timing: id 1 | task 270 | prompt eval time = 640.91 ms / 152 tokens ( 4.22 ms per token, 237.16 tokens per second) 1.50.965.587 I slot print_timing: id 1 | task 270 | eval time = 450.34 ms / 3 tokens ( 225.17 ms per token, 4.44 tokens per second) 1.50.965.588 I slot print_timing: id 1 | task 270 | total time = 1091.25 ms / 155 tokens 1.50.965.588 I slot print_timing: id 1 | task 270 | graphs reused = 4 1.50.965.588 I slot print_timing: id 1 | task 270 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.965.607 I slot release: id 1 | task 270 | stop processing: n_tokens = 163, truncated = 0 1.51.002.060 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.252 1.51.003.238 I slot launch_slot_: id 0 | task 279 | processing task, is_child = 0 1.51.004.470 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.227 1.51.004.540 I slot launch_slot_: id 1 | task 280 | processing task, is_child = 0 1.51.059.865 I slot print_timing: id 2 | task 274 | prompt eval time = 475.23 ms / 118 tokens ( 4.03 ms per token, 248.30 tokens per second) 1.51.059.871 I slot print_timing: id 2 | task 274 | eval time = 58.99 ms / 2 tokens ( 58.99 ms per token, 16.95 tokens per second) 1.51.059.872 I slot print_timing: id 2 | task 274 | total time = 534.22 ms / 120 tokens 1.51.059.872 I slot print_timing: id 2 | task 274 | graphs reused = 4 1.51.059.873 I slot print_timing: id 2 | task 274 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.059.893 I slot release: id 2 | task 274 | stop processing: n_tokens = 128, truncated = 0 1.51.060.986 I slot print_timing: id 3 | task 275 | prompt eval time = 476.19 ms / 124 tokens ( 3.84 ms per token, 260.40 tokens per second) 1.51.060.990 I slot print_timing: id 3 | task 275 | eval time = 58.93 ms / 2 tokens ( 58.93 ms per token, 16.97 tokens per second) 1.51.060.991 I slot print_timing: id 3 | task 275 | total time = 535.12 ms / 126 tokens 1.51.060.991 I slot print_timing: id 3 | task 275 | graphs reused = 4 1.51.060.991 I slot print_timing: id 3 | task 275 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.061.005 I slot release: id 3 | task 275 | stop processing: n_tokens = 134, truncated = 0 1.51.552.076 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.289 1.51.578.860 I slot launch_slot_: id 2 | task 283 | processing task, is_child = 0 1.51.581.126 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.276 1.51.581.200 I slot launch_slot_: id 3 | task 284 | processing task, is_child = 0 1.52.188.240 I slot print_timing: id 1 | task 280 | prompt eval time = 639.20 ms / 164 tokens ( 3.90 ms per token, 256.57 tokens per second) 1.52.188.243 I slot print_timing: id 1 | task 280 | eval time = 544.35 ms / 2 tokens ( 544.35 ms per token, 1.84 tokens per second) 1.52.188.244 I slot print_timing: id 1 | task 280 | total time = 1183.55 ms / 166 tokens 1.52.188.244 I slot print_timing: id 1 | task 280 | graphs reused = 4 1.52.188.244 I slot print_timing: id 1 | task 280 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.188.289 I slot release: id 1 | task 280 | stop processing: n_tokens = 174, truncated = 0 1.52.251.582 I slot print_timing: id 0 | task 279 | prompt eval time = 638.24 ms / 159 tokens ( 4.01 ms per token, 249.12 tokens per second) 1.52.251.585 I slot print_timing: id 0 | task 279 | eval time = 608.79 ms / 3 tokens ( 304.40 ms per token, 3.29 tokens per second) 1.52.251.586 I slot print_timing: id 0 | task 279 | total time = 1247.03 ms / 162 tokens 1.52.251.586 I slot print_timing: id 0 | task 279 | graphs reused = 4 1.52.251.587 I slot print_timing: id 0 | task 279 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.251.604 I slot release: id 0 | task 279 | stop processing: n_tokens = 170, truncated = 0 1.52.254.189 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.218 1.52.257.684 I slot launch_slot_: id 0 | task 288 | processing task, is_child = 0 1.52.261.036 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.314 (> 0.100 thold), f_keep = 0.213 1.52.261.617 I slot launch_slot_: id 1 | task 289 | processing task, is_child = 0 1.52.317.179 I slot print_timing: id 2 | task 283 | prompt eval time = 668.53 ms / 152 tokens ( 4.40 ms per token, 227.36 tokens per second) 1.52.317.182 I slot print_timing: id 2 | task 283 | eval time = 64.25 ms / 2 tokens ( 64.25 ms per token, 15.56 tokens per second) 1.52.317.182 I slot print_timing: id 2 | task 283 | total time = 732.78 ms / 154 tokens 1.52.317.182 I slot print_timing: id 2 | task 283 | graphs reused = 4 1.52.317.183 I slot print_timing: id 2 | task 283 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.317.201 I slot release: id 2 | task 283 | stop processing: n_tokens = 162, truncated = 0 1.52.318.317 I slot print_timing: id 3 | task 284 | prompt eval time = 669.66 ms / 154 tokens ( 4.35 ms per token, 229.97 tokens per second) 1.52.318.322 I slot print_timing: id 3 | task 284 | eval time = 64.13 ms / 2 tokens ( 64.13 ms per token, 15.59 tokens per second) 1.52.318.322 I slot print_timing: id 3 | task 284 | total time = 733.79 ms / 156 tokens 1.52.318.322 I slot print_timing: id 3 | task 284 | graphs reused = 4 1.52.318.323 I slot print_timing: id 3 | task 284 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.318.334 I slot release: id 3 | task 284 | stop processing: n_tokens = 164, truncated = 0 1.52.668.618 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.228 1.52.782.429 I slot launch_slot_: id 2 | task 292 | processing task, is_child = 0 1.52.785.579 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.226 1.52.785.657 I slot launch_slot_: id 3 | task 293 | processing task, is_child = 0 1.53.385.528 I slot print_timing: id 0 | task 288 | prompt eval time = 583.60 ms / 158 tokens ( 3.69 ms per token, 270.73 tokens per second) 1.53.385.531 I slot print_timing: id 0 | task 288 | eval time = 540.30 ms / 2 tokens ( 540.30 ms per token, 1.85 tokens per second) 1.53.385.531 I slot print_timing: id 0 | task 288 | total time = 1123.90 ms / 160 tokens 1.53.385.532 I slot print_timing: id 0 | task 288 | graphs reused = 4 1.53.385.532 I slot print_timing: id 0 | task 288 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.385.555 I slot release: id 0 | task 288 | stop processing: n_tokens = 168, truncated = 0 1.53.386.693 I slot print_timing: id 1 | task 289 | prompt eval time = 584.56 ms / 109 tokens ( 5.36 ms per token, 186.47 tokens per second) 1.53.386.699 I slot print_timing: id 1 | task 289 | eval time = 540.39 ms / 2 tokens ( 540.39 ms per token, 1.85 tokens per second) 1.53.386.699 I slot print_timing: id 1 | task 289 | total time = 1124.95 ms / 111 tokens 1.53.386.700 I slot print_timing: id 1 | task 289 | graphs reused = 4 1.53.386.700 I slot print_timing: id 1 | task 289 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.386.718 I slot release: id 1 | task 289 | stop processing: n_tokens = 119, truncated = 0 1.53.424.748 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.330 (> 0.100 thold), f_keep = 0.220 1.53.428.907 I slot launch_slot_: id 0 | task 297 | processing task, is_child = 0 1.53.429.893 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.311 1.53.429.967 I slot launch_slot_: id 1 | task 298 | processing task, is_child = 0 1.53.485.546 I slot print_timing: id 2 | task 292 | prompt eval time = 636.63 ms / 117 tokens ( 5.44 ms per token, 183.78 tokens per second) 1.53.485.552 I slot print_timing: id 2 | task 292 | eval time = 62.08 ms / 2 tokens ( 62.08 ms per token, 16.11 tokens per second) 1.53.485.553 I slot print_timing: id 2 | task 292 | total time = 698.71 ms / 119 tokens 1.53.485.553 I slot print_timing: id 2 | task 292 | graphs reused = 4 1.53.485.553 I slot print_timing: id 2 | task 292 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.485.569 I slot release: id 2 | task 292 | stop processing: n_tokens = 127, truncated = 0 1.53.934.291 I slot print_timing: id 3 | task 293 | prompt eval time = 637.77 ms / 188 tokens ( 3.39 ms per token, 294.78 tokens per second) 1.53.934.297 I slot print_timing: id 3 | task 293 | eval time = 509.53 ms / 3 tokens ( 254.77 ms per token, 3.93 tokens per second) 1.53.934.298 I slot print_timing: id 3 | task 293 | total time = 1147.30 ms / 191 tokens 1.53.934.298 I slot print_timing: id 3 | task 293 | graphs reused = 4 1.53.934.298 I slot print_timing: id 3 | task 293 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.934.336 I slot release: id 3 | task 293 | stop processing: n_tokens = 199, truncated = 0 1.53.934.363 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.291 1.53.938.635 I slot launch_slot_: id 2 | task 301 | processing task, is_child = 0 1.53.941.592 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.186 1.53.941.688 I slot launch_slot_: id 3 | task 302 | processing task, is_child = 0 1.54.428.566 I slot print_timing: id 0 | task 297 | prompt eval time = 570.92 ms / 103 tokens ( 5.54 ms per token, 180.41 tokens per second) 1.54.428.568 I slot print_timing: id 0 | task 297 | eval time = 427.66 ms / 2 tokens ( 427.66 ms per token, 2.34 tokens per second) 1.54.428.568 I slot print_timing: id 0 | task 297 | total time = 998.59 ms / 105 tokens 1.54.428.569 I slot print_timing: id 0 | task 297 | graphs reused = 4 1.54.428.569 I slot print_timing: id 0 | task 297 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.428.596 I slot release: id 0 | task 297 | stop processing: n_tokens = 113, truncated = 0 1.54.490.721 I slot print_timing: id 1 | task 298 | prompt eval time = 571.91 ms / 125 tokens ( 4.58 ms per token, 218.56 tokens per second) 1.54.490.725 I slot print_timing: id 1 | task 298 | eval time = 488.69 ms / 3 tokens ( 244.35 ms per token, 4.09 tokens per second) 1.54.490.725 I slot print_timing: id 1 | task 298 | total time = 1060.61 ms / 128 tokens 1.54.490.726 I slot print_timing: id 1 | task 298 | graphs reused = 4 1.54.490.726 I slot print_timing: id 1 | task 298 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.490.744 I slot release: id 1 | task 298 | stop processing: n_tokens = 136, truncated = 0 1.54.493.346 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.327 1.54.494.544 I slot launch_slot_: id 0 | task 306 | processing task, is_child = 0 1.54.496.305 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.272 1.54.496.867 I slot launch_slot_: id 1 | task 307 | processing task, is_child = 0 1.54.553.321 I slot print_timing: id 3 | task 302 | prompt eval time = 550.67 ms / 128 tokens ( 4.30 ms per token, 232.44 tokens per second) 1.54.553.324 I slot print_timing: id 3 | task 302 | eval time = 59.98 ms / 2 tokens ( 59.98 ms per token, 16.67 tokens per second) 1.54.553.324 I slot print_timing: id 3 | task 302 | total time = 610.65 ms / 130 tokens 1.54.553.325 I slot print_timing: id 3 | task 302 | graphs reused = 4 1.54.553.325 I slot print_timing: id 3 | task 302 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.553.340 I slot release: id 3 | task 302 | stop processing: n_tokens = 138, truncated = 0 1.55.095.584 I slot print_timing: id 2 | task 301 | prompt eval time = 549.51 ms / 113 tokens ( 4.86 ms per token, 205.64 tokens per second) 1.55.095.587 I slot print_timing: id 2 | task 301 | eval time = 603.54 ms / 3 tokens ( 301.77 ms per token, 3.31 tokens per second) 1.55.095.588 I slot print_timing: id 2 | task 301 | total time = 1153.05 ms / 116 tokens 1.55.095.589 I slot print_timing: id 2 | task 301 | graphs reused = 4 1.55.095.589 I slot print_timing: id 2 | task 301 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.095.616 I slot release: id 2 | task 301 | stop processing: n_tokens = 124, truncated = 0 1.55.095.626 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.298 1.55.098.473 I slot launch_slot_: id 2 | task 310 | processing task, is_child = 0 1.55.100.869 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.268 1.55.101.421 I slot launch_slot_: id 3 | task 311 | processing task, is_child = 0 1.55.695.909 I slot print_timing: id 0 | task 306 | prompt eval time = 664.93 ms / 166 tokens ( 4.01 ms per token, 249.65 tokens per second) 1.55.695.915 I slot print_timing: id 0 | task 306 | eval time = 534.10 ms / 3 tokens ( 267.05 ms per token, 3.74 tokens per second) 1.55.695.915 I slot print_timing: id 0 | task 306 | total time = 1199.03 ms / 169 tokens 1.55.695.916 I slot print_timing: id 0 | task 306 | graphs reused = 4 1.55.695.916 I slot print_timing: id 0 | task 306 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.695.938 I slot release: id 0 | task 306 | stop processing: n_tokens = 177, truncated = 0 1.55.697.043 I slot print_timing: id 1 | task 307 | prompt eval time = 665.93 ms / 145 tokens ( 4.59 ms per token, 217.74 tokens per second) 1.55.697.045 I slot print_timing: id 1 | task 307 | eval time = 534.11 ms / 3 tokens ( 267.06 ms per token, 3.74 tokens per second) 1.55.697.046 I slot print_timing: id 1 | task 307 | total time = 1200.04 ms / 148 tokens 1.55.697.046 I slot print_timing: id 1 | task 307 | graphs reused = 4 1.55.697.046 I slot print_timing: id 1 | task 307 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.697.058 I slot release: id 1 | task 307 | stop processing: n_tokens = 156, truncated = 0 1.55.729.568 I slot print_timing: id 2 | task 310 | prompt eval time = 594.85 ms / 127 tokens ( 4.68 ms per token, 213.50 tokens per second) 1.55.729.570 I slot print_timing: id 2 | task 310 | eval time = 31.37 ms / 2 tokens ( 31.37 ms per token, 31.88 tokens per second) 1.55.729.570 I slot print_timing: id 2 | task 310 | total time = 626.22 ms / 129 tokens 1.55.729.571 I slot print_timing: id 2 | task 310 | graphs reused = 4 1.55.729.571 I slot print_timing: id 2 | task 310 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.729.586 I slot release: id 2 | task 310 | stop processing: n_tokens = 137, truncated = 0 1.55.730.680 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.209 1.55.734.167 I slot launch_slot_: id 0 | task 316 | processing task, is_child = 0 1.55.739.191 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.237 1.55.739.703 I slot launch_slot_: id 1 | task 317 | processing task, is_child = 0 1.55.739.733 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.270 1.55.740.255 I slot launch_slot_: id 2 | task 318 | processing task, is_child = 0 1.55.794.703 I slot print_timing: id 3 | task 311 | prompt eval time = 595.97 ms / 139 tokens ( 4.29 ms per token, 233.24 tokens per second) 1.55.794.708 I slot print_timing: id 3 | task 311 | eval time = 95.27 ms / 3 tokens ( 47.63 ms per token, 20.99 tokens per second) 1.55.794.713 I slot print_timing: id 3 | task 311 | total time = 691.23 ms / 142 tokens 1.55.794.713 I slot print_timing: id 3 | task 311 | graphs reused = 4 1.55.794.714 I slot print_timing: id 3 | task 311 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.794.734 I slot release: id 3 | task 311 | stop processing: n_tokens = 150, truncated = 0 1.56.494.509 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.247 1.56.567.375 I slot launch_slot_: id 3 | task 321 | processing task, is_child = 0 1.56.979.641 I slot print_timing: id 2 | task 318 | prompt eval time = 903.08 ms / 142 tokens ( 6.36 ms per token, 157.24 tokens per second) 1.56.979.644 I slot print_timing: id 2 | task 318 | eval time = 336.06 ms / 2 tokens ( 336.06 ms per token, 2.98 tokens per second) 1.56.979.645 I slot print_timing: id 2 | task 318 | total time = 1239.14 ms / 144 tokens 1.56.979.645 I slot print_timing: id 2 | task 318 | graphs reused = 4 1.56.979.646 I slot print_timing: id 2 | task 318 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.979.683 I slot release: id 2 | task 318 | stop processing: n_tokens = 152, truncated = 0 1.57.041.425 I slot print_timing: id 1 | task 317 | prompt eval time = 901.97 ms / 161 tokens ( 5.60 ms per token, 178.50 tokens per second) 1.57.041.430 I slot print_timing: id 1 | task 317 | eval time = 399.06 ms / 3 tokens ( 199.53 ms per token, 5.01 tokens per second) 1.57.041.431 I slot print_timing: id 1 | task 317 | total time = 1301.03 ms / 164 tokens 1.57.041.431 I slot print_timing: id 1 | task 317 | graphs reused = 4 1.57.041.431 I slot print_timing: id 1 | task 317 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.041.447 I slot release: id 1 | task 317 | stop processing: n_tokens = 172, truncated = 0 1.57.042.798 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.215 1.57.047.180 I slot launch_slot_: id 1 | task 325 | processing task, is_child = 0 1.57.049.325 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.243 1.57.049.398 I slot launch_slot_: id 2 | task 326 | processing task, is_child = 0 1.57.713.619 I slot print_timing: id 0 | task 316 | prompt eval time = 900.96 ms / 124 tokens ( 7.27 ms per token, 137.63 tokens per second) 1.57.713.622 I slot print_timing: id 0 | task 316 | eval time = 1072.38 ms / 5 tokens ( 268.10 ms per token, 3.73 tokens per second) 1.57.713.623 I slot print_timing: id 0 | task 316 | total time = 1973.35 ms / 129 tokens 1.57.713.623 I slot print_timing: id 0 | task 316 | graphs reused = 4 1.57.713.624 I slot print_timing: id 0 | task 316 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.713.648 I slot release: id 0 | task 316 | stop processing: n_tokens = 137, truncated = 0 1.57.714.818 I slot print_timing: id 3 | task 321 | prompt eval time = 473.44 ms / 173 tokens ( 2.74 ms per token, 365.41 tokens per second) 1.57.714.820 I slot print_timing: id 3 | task 321 | eval time = 672.02 ms / 3 tokens ( 336.01 ms per token, 2.98 tokens per second) 1.57.714.821 I slot print_timing: id 3 | task 321 | total time = 1145.46 ms / 176 tokens 1.57.714.821 I slot print_timing: id 3 | task 321 | graphs reused = 4 1.57.714.821 I slot print_timing: id 3 | task 321 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.714.836 I slot release: id 3 | task 321 | stop processing: n_tokens = 184, truncated = 0 1.57.752.403 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.325 (> 0.100 thold), f_keep = 0.270 1.57.753.667 I slot launch_slot_: id 0 | task 330 | processing task, is_child = 0 1.57.757.302 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.201 1.57.757.377 I slot launch_slot_: id 3 | task 331 | processing task, is_child = 0 1.58.298.712 I slot print_timing: id 1 | task 325 | prompt eval time = 701.74 ms / 122 tokens ( 5.75 ms per token, 173.85 tokens per second) 1.58.298.717 I slot print_timing: id 1 | task 325 | eval time = 547.56 ms / 3 tokens ( 273.78 ms per token, 3.65 tokens per second) 1.58.298.718 I slot print_timing: id 1 | task 325 | total time = 1249.30 ms / 125 tokens 1.58.298.718 I slot print_timing: id 1 | task 325 | graphs reused = 4 1.58.298.718 I slot print_timing: id 1 | task 325 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.298.738 I slot release: id 1 | task 325 | stop processing: n_tokens = 133, truncated = 0 1.58.299.876 I slot print_timing: id 2 | task 326 | prompt eval time = 702.87 ms / 190 tokens ( 3.70 ms per token, 270.32 tokens per second) 1.58.299.880 I slot print_timing: id 2 | task 326 | eval time = 547.48 ms / 3 tokens ( 273.74 ms per token, 3.65 tokens per second) 1.58.299.881 I slot print_timing: id 2 | task 326 | total time = 1250.35 ms / 193 tokens 1.58.299.881 I slot print_timing: id 2 | task 326 | graphs reused = 4 1.58.299.882 I slot print_timing: id 2 | task 326 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.299.900 I slot release: id 2 | task 326 | stop processing: n_tokens = 201, truncated = 0 1.58.361.834 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.278 1.58.363.041 I slot launch_slot_: id 1 | task 336 | processing task, is_child = 0 1.58.367.038 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.184 1.58.367.626 I slot launch_slot_: id 2 | task 335 | processing task, is_child = 0 1.58.424.092 I slot print_timing: id 0 | task 330 | prompt eval time = 603.18 ms / 105 tokens ( 5.74 ms per token, 174.08 tokens per second) 1.58.424.097 I slot print_timing: id 0 | task 330 | eval time = 63.53 ms / 2 tokens ( 63.53 ms per token, 15.74 tokens per second) 1.58.424.098 I slot print_timing: id 0 | task 330 | total time = 666.71 ms / 107 tokens 1.58.424.098 I slot print_timing: id 0 | task 330 | graphs reused = 4 1.58.424.099 I slot print_timing: id 0 | task 330 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.424.117 I slot release: id 0 | task 330 | stop processing: n_tokens = 115, truncated = 0 1.58.891.671 I slot print_timing: id 3 | task 331 | prompt eval time = 604.32 ms / 162 tokens ( 3.73 ms per token, 268.07 tokens per second) 1.58.891.678 I slot print_timing: id 3 | task 331 | eval time = 529.80 ms / 3 tokens ( 264.90 ms per token, 3.77 tokens per second) 1.58.891.680 I slot print_timing: id 3 | task 331 | total time = 1134.12 ms / 165 tokens 1.58.891.682 I slot print_timing: id 3 | task 331 | graphs reused = 5 1.58.891.683 I slot print_timing: id 3 | task 331 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.891.800 I slot release: id 3 | task 331 | stop processing: n_tokens = 173, truncated = 0 1.58.891.839 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.322 1.58.897.129 I slot launch_slot_: id 0 | task 339 | processing task, is_child = 0 1.59.257.627 I slot print_timing: id 1 | task 336 | prompt eval time = 600.97 ms / 126 tokens ( 4.77 ms per token, 209.66 tokens per second) 1.59.257.637 I slot print_timing: id 1 | task 336 | eval time = 288.97 ms / 2 tokens ( 288.97 ms per token, 3.46 tokens per second) 1.59.257.639 I slot print_timing: id 1 | task 336 | total time = 889.94 ms / 128 tokens 1.59.257.641 I slot print_timing: id 1 | task 336 | graphs reused = 5 1.59.257.642 I slot print_timing: id 1 | task 336 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.257.748 I slot release: id 1 | task 336 | stop processing: n_tokens = 136, truncated = 0 1.59.260.147 I slot print_timing: id 2 | task 335 | prompt eval time = 603.88 ms / 136 tokens ( 4.44 ms per token, 225.21 tokens per second) 1.59.260.153 I slot print_timing: id 2 | task 335 | eval time = 288.47 ms / 2 tokens ( 288.47 ms per token, 3.47 tokens per second) 1.59.260.154 I slot print_timing: id 2 | task 335 | total time = 892.36 ms / 138 tokens 1.59.260.155 I slot print_timing: id 2 | task 335 | graphs reused = 5 1.59.260.156 I slot print_timing: id 2 | task 335 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.260.200 I slot release: id 2 | task 335 | stop processing: n_tokens = 146, truncated = 0 1.59.356.128 I slot print_timing: id 0 | task 339 | prompt eval time = 393.20 ms / 146 tokens ( 2.69 ms per token, 371.31 tokens per second) 1.59.356.132 I slot print_timing: id 0 | task 339 | eval time = 58.59 ms / 3 tokens ( 29.29 ms per token, 34.14 tokens per second) 1.59.356.134 I slot print_timing: id 0 | task 339 | total time = 451.78 ms / 149 tokens 1.59.356.135 I slot print_timing: id 0 | task 339 | graphs reused = 6 1.59.356.135 I slot print_timing: id 0 | task 339 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.356.161 I slot release: id 0 | task 339 | stop processing: n_tokens = 157, truncated = 0 1.59.379.142 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 173, t_last = 319222415582 1.59.379.208 I slot launch_slot_: id 3 | task 345 | processing task, is_child = 0 1.59.388.222 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 136, t_last = 319222781530 1.59.388.265 I slot launch_slot_: id 1 | task 346 | processing task, is_child = 0 1.59.388.321 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 146, t_last = 319222783982 1.59.388.359 I slot launch_slot_: id 2 | task 347 | processing task, is_child = 0 1.59.388.386 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 157, t_last = 319222879943 1.59.388.422 I slot launch_slot_: id 0 | task 348 | processing task, is_child = 0 2.02.666.801 I slot print_timing: id 0 | task 348 | prompt processing, n_tokens = 683, progress = 0.57, t = 3.28 s / 208.34 tokens per second 2.02.748.077 I slot print_timing: id 1 | task 346 | prompt processing, n_tokens = 655, progress = 0.56, t = 3.28 s / 199.80 tokens per second 2.02.760.668 I slot print_timing: id 2 | task 347 | prompt processing, n_tokens = 674, progress = 0.57, t = 3.28 s / 205.60 tokens per second 2.02.771.942 I slot print_timing: id 3 | task 345 | prompt processing, n_tokens = 36, progress = 0.04, t = 3.28 s / 10.98 tokens per second 2.05.561.521 I slot print_timing: id 0 | task 348 | prompt processing, n_tokens = 1086, progress = 0.91, t = 6.17 s / 175.93 tokens per second 2.05.938.917 I slot print_timing: id 1 | task 346 | prompt processing, n_tokens = 1086, progress = 0.93, t = 6.17 s / 175.93 tokens per second 2.05.951.709 I slot print_timing: id 2 | task 347 | prompt processing, n_tokens = 1086, progress = 0.91, t = 6.17 s / 175.93 tokens per second 2.05.962.844 I slot print_timing: id 3 | task 345 | prompt processing, n_tokens = 670, progress = 0.57, t = 6.17 s / 108.54 tokens per second 2.06.767.632 I slot print_timing: id 0 | task 348 | prompt processing, n_tokens = 1195, progress = 1.00, t = 7.38 s / 161.94 tokens per second 2.07.298.780 I slot print_timing: id 1 | task 346 | prompt processing, n_tokens = 1167, progress = 1.00, t = 7.38 s / 158.15 tokens per second 2.07.312.266 I slot print_timing: id 2 | task 347 | prompt processing, n_tokens = 1186, progress = 1.00, t = 7.38 s / 160.73 tokens per second 2.07.324.213 I slot print_timing: id 3 | task 345 | prompt processing, n_tokens = 1086, progress = 0.92, t = 7.38 s / 147.18 tokens per second 2.07.570.620 I slot print_timing: id 3 | task 345 | prompt processing, n_tokens = 1182, progress = 1.00, t = 8.18 s / 144.53 tokens per second 2.09.064.601 I slot print_timing: id 0 | task 348 | prompt eval time = 8179.85 ms / 1199 tokens ( 6.82 ms per token, 146.58 tokens per second) 2.09.064.605 I slot print_timing: id 0 | task 348 | eval time = 1496.32 ms / 40 tokens ( 38.37 ms per token, 26.06 tokens per second) 2.09.064.606 I slot print_timing: id 0 | task 348 | total time = 9676.17 ms / 1239 tokens 2.09.064.606 I slot print_timing: id 0 | task 348 | graphs reused = 44 2.09.064.607 I slot print_timing: id 0 | task 348 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.064.673 I slot release: id 0 | task 348 | stop processing: n_tokens = 1247, truncated = 0 2.09.105.133 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.894 2.09.105.163 I slot launch_slot_: id 0 | task 393 | processing task, is_child = 0 2.10.801.650 I slot print_timing: id 3 | task 345 | prompt eval time = 8252.89 ms / 1186 tokens ( 6.96 ms per token, 143.71 tokens per second) 2.10.801.655 I slot print_timing: id 3 | task 345 | eval time = 3160.03 ms / 78 tokens ( 41.04 ms per token, 24.37 tokens per second) 2.10.801.656 I slot print_timing: id 3 | task 345 | total time = 11412.92 ms / 1264 tokens 2.10.801.657 I slot print_timing: id 3 | task 345 | graphs reused = 80 2.10.801.658 I slot print_timing: id 3 | task 345 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.801.723 I slot release: id 3 | task 345 | stop processing: n_tokens = 1272, truncated = 0 2.10.837.749 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.877 2.10.837.773 I slot launch_slot_: id 3 | task 433 | processing task, is_child = 0 2.11.227.195 I slot print_timing: id 1 | task 346 | prompt eval time = 8180.89 ms / 1171 tokens ( 6.99 ms per token, 143.14 tokens per second) 2.11.227.199 I slot print_timing: id 1 | task 346 | eval time = 3657.75 ms / 83 tokens ( 44.61 ms per token, 22.42 tokens per second) 2.11.227.200 I slot print_timing: id 1 | task 346 | total time = 11838.64 ms / 1254 tokens 2.11.227.201 I slot print_timing: id 1 | task 346 | graphs reused = 80 2.11.227.201 I slot print_timing: id 1 | task 346 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.227.283 I slot release: id 1 | task 346 | stop processing: n_tokens = 1262, truncated = 0 2.11.294.086 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.884 2.11.294.114 I slot launch_slot_: id 1 | task 438 | processing task, is_child = 0 2.12.225.207 I slot print_timing: id 2 | task 347 | n_gen = 100, tg = 21.27 t/s, tg_3s = 21.48 t/s 2.13.801.029 I slot print_timing: id 0 | task 393 | n_gen = 100, tg = 22.72 t/s, tg_3s = 22.95 t/s 2.14.328.109 I slot print_timing: id 2 | task 347 | prompt eval time = 8181.97 ms / 1190 tokens ( 6.88 ms per token, 145.44 tokens per second) 2.14.328.116 I slot print_timing: id 2 | task 347 | eval time = 6757.50 ms / 156 tokens ( 43.60 ms per token, 22.94 tokens per second) 2.14.328.117 I slot print_timing: id 2 | task 347 | total time = 14939.47 ms / 1346 tokens 2.14.328.118 I slot print_timing: id 2 | task 347 | graphs reused = 149 2.14.328.118 I slot print_timing: id 2 | task 347 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.328.180 I slot release: id 2 | task 347 | stop processing: n_tokens = 1354, truncated = 0 2.14.391.659 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.823 2.14.391.685 I slot launch_slot_: id 2 | task 512 | processing task, is_child = 0 2.15.570.815 I slot print_timing: id 3 | task 433 | n_gen = 100, tg = 22.60 t/s, tg_3s = 22.83 t/s 2.15.718.079 I slot print_timing: id 1 | task 438 | n_gen = 100, tg = 24.60 t/s, tg_3s = 24.85 t/s 2.15.754.202 I slot print_timing: id 0 | task 393 | prompt eval time = 339.24 ms / 107 tokens ( 3.17 ms per token, 315.41 tokens per second) 2.15.754.206 I slot print_timing: id 0 | task 393 | eval time = 6309.79 ms / 144 tokens ( 44.12 ms per token, 22.66 tokens per second) 2.15.754.206 I slot print_timing: id 0 | task 393 | total time = 6649.03 ms / 251 tokens 2.15.754.207 I slot print_timing: id 0 | task 393 | graphs reused = 175 2.15.754.208 I slot print_timing: id 0 | task 393 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.754.280 I slot release: id 0 | task 393 | stop processing: n_tokens = 1365, truncated = 0 2.15.794.963 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.817 2.15.794.992 I slot launch_slot_: id 0 | task 543 | processing task, is_child = 0 2.18.571.706 I slot print_timing: id 3 | task 433 | n_gen = 173, tg = 23.30 t/s, tg_3s = 24.33 t/s 2.18.718.360 I slot print_timing: id 1 | task 438 | n_gen = 173, tg = 24.48 t/s, tg_3s = 24.33 t/s 2.18.719.832 I slot print_timing: id 2 | task 512 | n_gen = 100, tg = 24.87 t/s, tg_3s = 25.12 t/s 2.19.471.548 I slot print_timing: id 3 | task 433 | prompt eval time = 352.18 ms / 114 tokens ( 3.09 ms per token, 323.70 tokens per second) 2.19.471.552 I slot print_timing: id 3 | task 433 | eval time = 8281.58 ms / 197 tokens ( 42.25 ms per token, 23.67 tokens per second) 2.19.471.552 I slot print_timing: id 3 | task 433 | total time = 8633.76 ms / 311 tokens 2.19.471.553 I slot print_timing: id 3 | task 433 | graphs reused = 264 2.19.471.553 I slot print_timing: id 3 | task 433 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.471.628 I slot release: id 3 | task 433 | stop processing: n_tokens = 1425, truncated = 0 2.19.507.750 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.782 2.19.507.778 I slot launch_slot_: id 3 | task 636 | processing task, is_child = 0 2.19.897.369 I slot print_timing: id 2 | task 512 | prompt eval time = 347.82 ms / 89 tokens ( 3.91 ms per token, 255.88 tokens per second) 2.19.897.385 I slot print_timing: id 2 | task 512 | eval time = 5157.82 ms / 123 tokens ( 42.28 ms per token, 23.65 tokens per second) 2.19.897.386 I slot print_timing: id 2 | task 512 | total time = 5505.65 ms / 212 tokens 2.19.897.388 I slot print_timing: id 2 | task 512 | graphs reused = 264 2.19.897.389 I slot print_timing: id 2 | task 512 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.897.580 I slot release: id 2 | task 512 | stop processing: n_tokens = 1326, truncated = 0 2.19.965.311 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.841 2.19.965.348 I slot launch_slot_: id 2 | task 640 | processing task, is_child = 0 2.20.462.771 I slot print_timing: id 0 | task 543 | n_gen = 100, tg = 22.85 t/s, tg_3s = 23.08 t/s 2.21.364.022 I slot print_timing: id 1 | task 438 | prompt eval time = 399.39 ms / 117 tokens ( 3.41 ms per token, 292.95 tokens per second) 2.21.364.028 I slot print_timing: id 1 | task 438 | eval time = 9670.51 ms / 227 tokens ( 42.79 ms per token, 23.37 tokens per second) 2.21.364.029 I slot print_timing: id 1 | task 438 | total time = 10069.90 ms / 344 tokens 2.21.364.029 I slot print_timing: id 1 | task 438 | graphs reused = 291 2.21.364.030 I slot print_timing: id 1 | task 438 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.364.099 I slot release: id 1 | task 438 | stop processing: n_tokens = 1458, truncated = 0 2.21.429.515 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.765 2.21.429.539 I slot launch_slot_: id 1 | task 672 | processing task, is_child = 0 2.22.187.221 I slot print_timing: id 0 | task 543 | prompt eval time = 335.70 ms / 118 tokens ( 2.84 ms per token, 351.50 tokens per second) 2.22.187.228 I slot print_timing: id 0 | task 543 | eval time = 6056.52 ms / 138 tokens ( 44.21 ms per token, 22.62 tokens per second) 2.22.187.228 I slot print_timing: id 0 | task 543 | total time = 6392.22 ms / 256 tokens 2.22.187.229 I slot print_timing: id 0 | task 543 | graphs reused = 301 2.22.187.230 I slot print_timing: id 0 | task 543 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.187.293 I slot release: id 0 | task 543 | stop processing: n_tokens = 1370, truncated = 0 2.22.227.761 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.814 2.22.227.794 I slot launch_slot_: id 0 | task 687 | processing task, is_child = 0 2.24.430.497 I slot print_timing: id 3 | task 636 | n_gen = 100, tg = 21.85 t/s, tg_3s = 22.07 t/s 2.24.541.418 I slot print_timing: id 2 | task 640 | n_gen = 100, tg = 23.40 t/s, tg_3s = 23.64 t/s 2.25.104.769 I slot print_timing: id 2 | task 640 | prompt eval time = 345.23 ms / 100 tokens ( 3.45 ms per token, 289.66 tokens per second) 2.25.104.776 I slot print_timing: id 2 | task 640 | eval time = 4794.18 ms / 115 tokens ( 42.05 ms per token, 23.78 tokens per second) 2.25.104.776 I slot print_timing: id 2 | task 640 | total time = 5139.41 ms / 215 tokens 2.25.104.777 I slot print_timing: id 2 | task 640 | graphs reused = 370 2.25.104.777 I slot print_timing: id 2 | task 640 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.104.836 I slot release: id 2 | task 640 | stop processing: n_tokens = 1329, truncated = 0 2.25.168.295 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.839 2.25.168.324 I slot launch_slot_: id 2 | task 760 | processing task, is_child = 0 2.25.601.886 I slot print_timing: id 0 | task 687 | prompt eval time = 279.61 ms / 76 tokens ( 3.68 ms per token, 271.81 tokens per second) 2.25.601.893 I slot print_timing: id 0 | task 687 | eval time = 3094.47 ms / 76 tokens ( 41.26 ms per token, 24.24 tokens per second) 2.25.601.893 I slot print_timing: id 0 | task 687 | total time = 3374.08 ms / 152 tokens 2.25.601.894 I slot print_timing: id 0 | task 687 | graphs reused = 372 2.25.601.894 I slot print_timing: id 0 | task 687 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.601.951 I slot release: id 0 | task 687 | stop processing: n_tokens = 1266, truncated = 0 2.25.645.741 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.881 2.25.645.777 I slot launch_slot_: id 0 | task 767 | processing task, is_child = 0 2.25.960.037 I slot print_timing: id 1 | task 672 | prompt eval time = 338.85 ms / 76 tokens ( 4.46 ms per token, 224.29 tokens per second) 2.25.960.043 I slot print_timing: id 1 | task 672 | eval time = 4191.64 ms / 94 tokens ( 45.07 ms per token, 22.19 tokens per second) 2.25.960.044 I slot print_timing: id 1 | task 672 | total time = 4530.49 ms / 170 tokens 2.25.960.044 I slot print_timing: id 1 | task 672 | graphs reused = 373 2.25.960.045 I slot print_timing: id 1 | task 672 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.960.091 I slot release: id 1 | task 672 | stop processing: n_tokens = 1284, truncated = 0 2.26.028.281 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.868 2.26.028.316 I slot launch_slot_: id 1 | task 772 | processing task, is_child = 0 2.27.442.375 I slot print_timing: id 3 | task 636 | n_gen = 158, tg = 20.81 t/s, tg_3s = 19.26 t/s 2.29.770.946 I slot print_timing: id 2 | task 760 | n_gen = 100, tg = 23.15 t/s, tg_3s = 23.39 t/s 2.29.993.802 I slot print_timing: id 0 | task 767 | n_gen = 100, tg = 24.31 t/s, tg_3s = 24.56 t/s 2.30.031.105 I slot print_timing: id 0 | task 767 | prompt eval time = 276.26 ms / 99 tokens ( 2.79 ms per token, 358.35 tokens per second) 2.30.031.109 I slot print_timing: id 0 | task 767 | eval time = 4109.05 ms / 101 tokens ( 41.09 ms per token, 24.34 tokens per second) 2.30.031.110 I slot print_timing: id 0 | task 767 | total time = 4385.32 ms / 200 tokens 2.30.031.111 I slot print_timing: id 0 | task 767 | graphs reused = 468 2.30.031.111 I slot print_timing: id 0 | task 767 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.031.172 I slot release: id 0 | task 767 | stop processing: n_tokens = 1314, truncated = 0 2.30.071.637 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.849 2.30.071.668 I slot launch_slot_: id 0 | task 872 | processing task, is_child = 0 2.30.304.208 I slot print_timing: id 1 | task 772 | n_gen = 100, tg = 25.50 t/s, tg_3s = 25.76 t/s 2.30.458.507 I slot print_timing: id 3 | task 636 | n_gen = 234, tg = 22.07 t/s, tg_3s = 25.20 t/s 2.32.416.603 I slot print_timing: id 3 | task 636 | prompt eval time = 391.81 ms / 145 tokens ( 2.70 ms per token, 370.08 tokens per second) 2.32.416.606 I slot print_timing: id 3 | task 636 | eval time = 12517.01 ms / 286 tokens ( 43.92 ms per token, 22.77 tokens per second) 2.32.416.608 I slot print_timing: id 3 | task 636 | total time = 12908.82 ms / 431 tokens 2.32.416.608 I slot print_timing: id 3 | task 636 | graphs reused = 523 2.32.416.609 I slot print_timing: id 3 | task 636 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.416.673 I slot release: id 3 | task 636 | stop processing: n_tokens = 1545, truncated = 0 2.32.452.833 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.722 2.32.452.856 I slot launch_slot_: id 3 | task 932 | processing task, is_child = 0 2.32.780.632 I slot print_timing: id 2 | task 760 | n_gen = 169, tg = 23.06 t/s, tg_3s = 22.93 t/s 2.33.309.056 I slot print_timing: id 1 | task 772 | n_gen = 173, tg = 24.97 t/s, tg_3s = 24.29 t/s 2.33.761.993 I slot print_timing: id 2 | task 760 | prompt eval time = 326.73 ms / 72 tokens ( 4.54 ms per token, 220.37 tokens per second) 2.33.761.996 I slot print_timing: id 2 | task 760 | eval time = 8266.93 ms / 195 tokens ( 42.61 ms per token, 23.47 tokens per second) 2.33.761.997 I slot print_timing: id 2 | task 760 | total time = 8593.66 ms / 267 tokens 2.33.761.998 I slot print_timing: id 2 | task 760 | graphs reused = 548 2.33.761.999 I slot print_timing: id 2 | task 760 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.762.069 I slot release: id 2 | task 760 | stop processing: n_tokens = 1381, truncated = 0 2.33.825.718 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.807 2.33.825.744 I slot launch_slot_: id 2 | task 962 | processing task, is_child = 0 2.34.568.596 I slot print_timing: id 0 | task 872 | n_gen = 100, tg = 23.21 t/s, tg_3s = 23.44 t/s 2.35.017.069 I slot print_timing: id 0 | task 872 | prompt eval time = 231.40 ms / 62 tokens ( 3.73 ms per token, 267.93 tokens per second) 2.35.017.075 I slot print_timing: id 0 | task 872 | eval time = 4713.99 ms / 112 tokens ( 42.47 ms per token, 23.55 tokens per second) 2.35.017.076 I slot print_timing: id 0 | task 872 | total time = 4945.39 ms / 174 tokens 2.35.017.076 I slot print_timing: id 0 | task 872 | graphs reused = 570 2.35.017.077 I slot print_timing: id 0 | task 872 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.017.134 I slot release: id 0 | task 872 | stop processing: n_tokens = 1288, truncated = 0 2.35.057.584 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.866 2.35.057.610 I slot launch_slot_: id 0 | task 989 | processing task, is_child = 0 2.36.342.953 I slot print_timing: id 1 | task 772 | n_gen = 242, tg = 24.29 t/s, tg_3s = 22.74 t/s 2.36.946.173 I slot print_timing: id 3 | task 932 | n_gen = 100, tg = 23.77 t/s, tg_3s = 24.01 t/s 2.37.809.169 I slot print_timing: id 2 | task 962 | prompt eval time = 327.21 ms / 74 tokens ( 4.42 ms per token, 226.15 tokens per second) 2.37.809.175 I slot print_timing: id 2 | task 962 | eval time = 3656.20 ms / 94 tokens ( 39.31 ms per token, 25.44 tokens per second) 2.37.809.177 I slot print_timing: id 2 | task 962 | total time = 3983.41 ms / 168 tokens 2.37.809.178 I slot print_timing: id 2 | task 962 | graphs reused = 637 2.37.809.178 I slot print_timing: id 2 | task 962 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.809.236 I slot release: id 2 | task 962 | stop processing: n_tokens = 1282, truncated = 0 2.37.872.825 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.870 2.37.872.856 I slot launch_slot_: id 2 | task 1060 | processing task, is_child = 0 2.38.590.724 I slot print_timing: id 0 | task 989 | prompt eval time = 230.88 ms / 59 tokens ( 3.91 ms per token, 255.55 tokens per second) 2.38.590.727 I slot print_timing: id 0 | task 989 | eval time = 3302.23 ms / 81 tokens ( 41.28 ms per token, 24.23 tokens per second) 2.38.590.729 I slot print_timing: id 0 | task 989 | total time = 3533.11 ms / 140 tokens 2.38.590.730 I slot print_timing: id 0 | task 989 | graphs reused = 646 2.38.590.730 I slot print_timing: id 0 | task 989 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.590.787 I slot release: id 0 | task 989 | stop processing: n_tokens = 1254, truncated = 0 2.38.631.492 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.889 2.38.631.516 I slot launch_slot_: id 0 | task 1074 | processing task, is_child = 0 2.39.359.410 I slot print_timing: id 1 | task 772 | n_gen = 309, tg = 23.81 t/s, tg_3s = 22.21 t/s 2.39.966.927 I slot print_timing: id 3 | task 932 | n_gen = 167, tg = 23.10 t/s, tg_3s = 22.18 t/s 2.40.380.220 I slot print_timing: id 3 | task 932 | prompt eval time = 328.85 ms / 111 tokens ( 2.96 ms per token, 337.54 tokens per second) 2.40.380.224 I slot print_timing: id 3 | task 932 | eval time = 7598.51 ms / 178 tokens ( 42.93 ms per token, 23.29 tokens per second) 2.40.380.224 I slot print_timing: id 3 | task 932 | total time = 7927.35 ms / 289 tokens 2.40.380.225 I slot print_timing: id 3 | task 932 | graphs reused = 685 2.40.380.226 I slot print_timing: id 3 | task 932 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.380.287 I slot release: id 3 | task 932 | stop processing: n_tokens = 1403, truncated = 0 2.40.416.657 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.795 2.40.416.683 I slot launch_slot_: id 3 | task 1117 | processing task, is_child = 0 2.41.911.013 I slot print_timing: id 0 | task 1074 | prompt eval time = 272.06 ms / 70 tokens ( 3.89 ms per token, 257.29 tokens per second) 2.41.911.017 I slot print_timing: id 0 | task 1074 | eval time = 3007.42 ms / 74 tokens ( 41.20 ms per token, 24.27 tokens per second) 2.41.911.018 I slot print_timing: id 0 | task 1074 | total time = 3279.49 ms / 144 tokens 2.41.911.018 I slot print_timing: id 0 | task 1074 | graphs reused = 715 2.41.911.023 I slot print_timing: id 0 | task 1074 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.911.089 I slot release: id 0 | task 1074 | stop processing: n_tokens = 1258, truncated = 0 2.41.951.780 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.886 2.41.951.806 I slot launch_slot_: id 0 | task 1152 | processing task, is_child = 0 2.42.377.410 I slot print_timing: id 1 | task 772 | n_gen = 378, tg = 23.63 t/s, tg_3s = 22.86 t/s 2.42.572.214 I slot print_timing: id 2 | task 1060 | n_gen = 100, tg = 22.71 t/s, tg_3s = 22.93 t/s 2.42.648.010 I slot print_timing: id 1 | task 772 | prompt eval time = 393.78 ms / 125 tokens ( 3.15 ms per token, 317.43 tokens per second) 2.42.648.016 I slot print_timing: id 1 | task 772 | eval time = 16225.90 ms / 385 tokens ( 42.25 ms per token, 23.67 tokens per second) 2.42.648.016 I slot print_timing: id 1 | task 772 | total time = 16619.69 ms / 510 tokens 2.42.648.017 I slot print_timing: id 1 | task 772 | graphs reused = 727 2.42.648.018 I slot print_timing: id 1 | task 772 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.648.079 I slot release: id 1 | task 772 | stop processing: n_tokens = 1624, truncated = 0 2.42.714.210 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.687 2.42.714.239 I slot launch_slot_: id 1 | task 1168 | processing task, is_child = 0 2.43.691.332 I slot print_timing: id 2 | task 1060 | prompt eval time = 339.18 ms / 76 tokens ( 4.46 ms per token, 224.07 tokens per second) 2.43.691.338 I slot print_timing: id 2 | task 1060 | eval time = 5479.29 ms / 122 tokens ( 45.28 ms per token, 22.08 tokens per second) 2.43.691.338 I slot print_timing: id 2 | task 1060 | total time = 5818.47 ms / 198 tokens 2.43.691.339 I slot print_timing: id 2 | task 1060 | graphs reused = 743 2.43.691.340 I slot print_timing: id 2 | task 1060 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.691.399 I slot release: id 2 | task 1060 | stop processing: n_tokens = 1312, truncated = 0 2.43.755.267 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.850 2.43.755.292 I slot launch_slot_: id 2 | task 1189 | processing task, is_child = 0 2.45.169.889 I slot print_timing: id 3 | task 1117 | n_gen = 100, tg = 22.37 t/s, tg_3s = 22.60 t/s 2.46.440.738 I slot print_timing: id 0 | task 1152 | n_gen = 100, tg = 23.26 t/s, tg_3s = 23.49 t/s 2.46.590.972 I slot print_timing: id 0 | task 1152 | prompt eval time = 232.19 ms / 65 tokens ( 3.57 ms per token, 279.94 tokens per second) 2.46.590.976 I slot print_timing: id 0 | task 1152 | eval time = 4406.97 ms / 104 tokens ( 42.79 ms per token, 23.37 tokens per second) 2.46.590.977 I slot print_timing: id 0 | task 1152 | total time = 4639.16 ms / 169 tokens 2.46.590.977 I slot print_timing: id 0 | task 1152 | graphs reused = 810 2.46.590.978 I slot print_timing: id 0 | task 1152 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.591.045 I slot release: id 0 | task 1152 | stop processing: n_tokens = 1283, truncated = 0 2.46.631.577 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.870 2.46.631.602 I slot launch_slot_: id 0 | task 1261 | processing task, is_child = 0 2.47.258.105 I slot print_timing: id 1 | task 1168 | n_gen = 100, tg = 23.49 t/s, tg_3s = 23.73 t/s 2.47.634.142 I slot print_timing: id 1 | task 1168 | prompt eval time = 329.62 ms / 71 tokens ( 4.64 ms per token, 215.40 tokens per second) 2.47.634.149 I slot print_timing: id 1 | task 1168 | eval time = 4590.28 ms / 110 tokens ( 42.11 ms per token, 23.75 tokens per second) 2.47.634.150 I slot print_timing: id 1 | task 1168 | total time = 4919.89 ms / 181 tokens 2.47.634.150 I slot print_timing: id 1 | task 1168 | graphs reused = 828 2.47.634.151 I slot print_timing: id 1 | task 1168 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.634.210 I slot release: id 1 | task 1168 | stop processing: n_tokens = 1295, truncated = 0 2.47.699.457 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.861 2.47.699.489 I slot launch_slot_: id 1 | task 1283 | processing task, is_child = 0 2.48.197.804 I slot print_timing: id 3 | task 1117 | n_gen = 165, tg = 22.00 t/s, tg_3s = 21.47 t/s 2.48.349.210 I slot print_timing: id 2 | task 1189 | n_gen = 100, tg = 22.97 t/s, tg_3s = 23.20 t/s 2.49.700.154 I slot print_timing: id 2 | task 1189 | prompt eval time = 284.18 ms / 62 tokens ( 4.58 ms per token, 218.17 tokens per second) 2.49.700.157 I slot print_timing: id 2 | task 1189 | eval time = 5660.67 ms / 136 tokens ( 41.93 ms per token, 23.85 tokens per second) 2.49.700.158 I slot print_timing: id 2 | task 1189 | total time = 5944.85 ms / 198 tokens 2.49.700.159 I slot print_timing: id 2 | task 1189 | graphs reused = 870 2.49.700.159 I slot print_timing: id 2 | task 1189 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.700.215 I slot release: id 2 | task 1189 | stop processing: n_tokens = 1312, truncated = 0 2.49.763.770 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.850 2.49.763.802 I slot launch_slot_: id 2 | task 1330 | processing task, is_child = 0 2.51.208.220 I slot print_timing: id 3 | task 1117 | n_gen = 236, tg = 22.46 t/s, tg_3s = 23.58 t/s 2.51.353.717 I slot print_timing: id 0 | task 1261 | n_gen = 100, tg = 22.51 t/s, tg_3s = 22.74 t/s 2.52.144.995 I slot print_timing: id 1 | task 1283 | n_gen = 100, tg = 24.36 t/s, tg_3s = 24.61 t/s 2.53.275.267 I slot print_timing: id 3 | task 1117 | prompt eval time = 327.47 ms / 106 tokens ( 3.09 ms per token, 323.70 tokens per second) 2.53.275.272 I slot print_timing: id 3 | task 1117 | eval time = 12531.11 ms / 291 tokens ( 43.21 ms per token, 23.14 tokens per second) 2.53.275.272 I slot print_timing: id 3 | task 1117 | total time = 12858.58 ms / 397 tokens 2.53.275.273 I slot print_timing: id 3 | task 1117 | graphs reused = 952 2.53.275.274 I slot print_timing: id 3 | task 1117 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.275.342 I slot release: id 3 | task 1117 | stop processing: n_tokens = 1511, truncated = 0 2.53.311.498 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.738 2.53.311.526 I slot launch_slot_: id 3 | task 1417 | processing task, is_child = 0 2.54.037.403 I slot print_timing: id 2 | task 1330 | n_gen = 100, tg = 25.45 t/s, tg_3s = 25.70 t/s 2.54.371.589 I slot print_timing: id 0 | task 1261 | n_gen = 176, tg = 23.60 t/s, tg_3s = 25.18 t/s 2.55.159.427 I slot print_timing: id 1 | task 1283 | n_gen = 176, tg = 24.72 t/s, tg_3s = 25.21 t/s 2.56.635.279 I slot print_timing: id 0 | task 1261 | prompt eval time = 323.67 ms / 105 tokens ( 3.08 ms per token, 324.40 tokens per second) 2.56.635.285 I slot print_timing: id 0 | task 1261 | eval time = 9680.00 ms / 236 tokens ( 41.19 ms per token, 24.28 tokens per second) 2.56.635.286 I slot print_timing: id 0 | task 1261 | total time = 10003.67 ms / 341 tokens 2.56.635.287 I slot print_timing: id 0 | task 1261 | graphs reused = 1033 2.56.635.287 I slot print_timing: id 0 | task 1261 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.635.353 I slot release: id 0 | task 1261 | stop processing: n_tokens = 1456, truncated = 0 2.56.676.028 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.766 2.56.676.054 I slot launch_slot_: id 0 | task 1503 | processing task, is_child = 0 2.57.050.350 I slot print_timing: id 2 | task 1330 | n_gen = 176, tg = 25.35 t/s, tg_3s = 25.22 t/s 2.57.318.039 I slot print_timing: id 1 | task 1283 | prompt eval time = 381.41 ms / 111 tokens ( 3.44 ms per token, 291.03 tokens per second) 2.57.318.046 I slot print_timing: id 1 | task 1283 | eval time = 9237.14 ms / 229 tokens ( 40.51 ms per token, 24.68 tokens per second) 2.57.318.046 I slot print_timing: id 1 | task 1283 | total time = 9618.54 ms / 340 tokens 2.57.318.047 I slot print_timing: id 1 | task 1283 | graphs reused = 1044 2.57.318.048 I slot print_timing: id 1 | task 1283 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.318.118 I slot release: id 1 | task 1283 | stop processing: n_tokens = 1454, truncated = 0 2.57.383.997 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.767 2.57.384.028 I slot launch_slot_: id 1 | task 1518 | processing task, is_child = 0 2.57.714.328 I slot print_timing: id 3 | task 1417 | n_gen = 100, tg = 23.76 t/s, tg_3s = 24.00 t/s 2.58.729.982 I slot print_timing: id 3 | task 1417 | prompt eval time = 236.09 ms / 68 tokens ( 3.47 ms per token, 288.02 tokens per second) 2.58.729.989 I slot print_timing: id 3 | task 1417 | eval time = 5182.36 ms / 127 tokens ( 41.13 ms per token, 24.31 tokens per second) 2.58.729.990 I slot print_timing: id 3 | task 1417 | total time = 5418.45 ms / 195 tokens 2.58.729.991 I slot print_timing: id 3 | task 1417 | graphs reused = 1070 2.58.729.991 I slot print_timing: id 3 | task 1417 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.730.051 I slot release: id 3 | task 1417 | stop processing: n_tokens = 1309, truncated = 0 2.58.766.249 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.852 2.58.766.276 I slot launch_slot_: id 3 | task 1549 | processing task, is_child = 0 2.59.831.899 I slot print_timing: id 0 | task 1503 | prompt eval time = 228.81 ms / 62 tokens ( 3.69 ms per token, 270.97 tokens per second) 2.59.831.903 I slot print_timing: id 0 | task 1503 | eval time = 2927.03 ms / 66 tokens ( 45.03 ms per token, 22.21 tokens per second) 2.59.831.904 I slot print_timing: id 0 | task 1503 | total time = 3155.83 ms / 128 tokens 2.59.831.904 I slot print_timing: id 0 | task 1503 | graphs reused = 1090 2.59.831.905 I slot print_timing: id 0 | task 1503 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.831.963 I slot release: id 0 | task 1503 | stop processing: n_tokens = 1242, truncated = 0 2.59.872.525 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.899 2.59.872.557 I slot launch_slot_: id 0 | task 1574 | processing task, is_child = 0 3.00.081.099 I slot print_timing: id 2 | task 1330 | n_gen = 239, tg = 23.96 t/s, tg_3s = 20.79 t/s 3.00.979.532 I slot print_timing: id 1 | task 1518 | prompt eval time = 328.02 ms / 74 tokens ( 4.43 ms per token, 225.59 tokens per second) 3.00.979.536 I slot print_timing: id 1 | task 1518 | eval time = 3267.47 ms / 77 tokens ( 42.99 ms per token, 23.26 tokens per second) 3.00.979.536 I slot print_timing: id 1 | task 1518 | total time = 3595.49 ms / 151 tokens 3.00.979.537 I slot print_timing: id 1 | task 1518 | graphs reused = 1112 3.00.979.538 I slot print_timing: id 1 | task 1518 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.979.605 I slot release: id 1 | task 1518 | stop processing: n_tokens = 1265, truncated = 0 3.01.045.101 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.881 3.01.045.136 I slot launch_slot_: id 1 | task 1600 | processing task, is_child = 0 3.03.110.987 I slot print_timing: id 2 | task 1330 | n_gen = 311, tg = 23.91 t/s, tg_3s = 23.76 t/s 3.03.263.051 I slot print_timing: id 3 | task 1549 | n_gen = 100, tg = 23.47 t/s, tg_3s = 23.71 t/s 3.03.789.526 I slot print_timing: id 3 | task 1549 | prompt eval time = 278.61 ms / 80 tokens ( 3.48 ms per token, 287.14 tokens per second) 3.03.789.532 I slot print_timing: id 3 | task 1549 | eval time = 4744.64 ms / 114 tokens ( 41.99 ms per token, 23.82 tokens per second) 3.03.789.533 I slot print_timing: id 3 | task 1549 | total time = 5023.24 ms / 194 tokens 3.03.789.534 I slot print_timing: id 3 | task 1549 | graphs reused = 1174 3.03.789.534 I slot print_timing: id 3 | task 1549 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.789.592 I slot release: id 3 | task 1549 | stop processing: n_tokens = 1308, truncated = 0 3.03.825.876 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.852 3.03.825.901 I slot launch_slot_: id 3 | task 1668 | processing task, is_child = 0 3.04.381.282 I slot print_timing: id 0 | task 1574 | n_gen = 100, tg = 23.39 t/s, tg_3s = 23.62 t/s 3.05.321.807 I slot print_timing: id 1 | task 1600 | n_gen = 100, tg = 25.11 t/s, tg_3s = 25.36 t/s 3.05.811.972 I slot print_timing: id 2 | task 1330 | prompt eval time = 383.12 ms / 128 tokens ( 2.99 ms per token, 334.10 tokens per second) 3.05.811.979 I slot print_timing: id 2 | task 1330 | eval time = 15665.04 ms / 377 tokens ( 41.66 ms per token, 24.00 tokens per second) 3.05.811.980 I slot print_timing: id 2 | task 1330 | total time = 16048.16 ms / 505 tokens 3.05.811.980 I slot print_timing: id 2 | task 1330 | graphs reused = 1218 3.05.811.981 I slot print_timing: id 2 | task 1330 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.812.047 I slot release: id 2 | task 1330 | stop processing: n_tokens = 1619, truncated = 0 3.05.875.592 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.689 3.05.875.623 I slot launch_slot_: id 2 | task 1717 | processing task, is_child = 0 3.07.382.583 I slot print_timing: id 0 | task 1574 | n_gen = 172, tg = 23.64 t/s, tg_3s = 23.99 t/s 3.07.869.507 I slot print_timing: id 0 | task 1574 | prompt eval time = 275.68 ms / 87 tokens ( 3.17 ms per token, 315.59 tokens per second) 3.07.869.510 I slot print_timing: id 0 | task 1574 | eval time = 7721.26 ms / 185 tokens ( 41.96 ms per token, 23.83 tokens per second) 3.07.869.511 I slot print_timing: id 0 | task 1574 | total time = 7996.94 ms / 272 tokens 3.07.869.512 I slot print_timing: id 0 | task 1574 | graphs reused = 1261 3.07.869.512 I slot print_timing: id 0 | task 1574 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.869.579 I slot release: id 0 | task 1574 | stop processing: n_tokens = 1387, truncated = 0 3.07.909.970 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.804 3.07.909.996 I slot launch_slot_: id 0 | task 1765 | processing task, is_child = 0 3.08.346.689 I slot print_timing: id 1 | task 1600 | n_gen = 166, tg = 23.68 t/s, tg_3s = 21.82 t/s 3.08.390.245 I slot print_timing: id 3 | task 1668 | n_gen = 100, tg = 23.16 t/s, tg_3s = 23.39 t/s 3.10.042.753 I slot print_timing: id 1 | task 1600 | prompt eval time = 333.73 ms / 97 tokens ( 3.44 ms per token, 290.65 tokens per second) 3.10.042.756 I slot print_timing: id 1 | task 1600 | eval time = 8663.88 ms / 211 tokens ( 41.26 ms per token, 24.24 tokens per second) 3.10.042.757 I slot print_timing: id 1 | task 1600 | total time = 8997.61 ms / 308 tokens 3.10.042.758 I slot print_timing: id 1 | task 1600 | graphs reused = 1309 3.10.042.758 I slot print_timing: id 1 | task 1600 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.042.821 I slot release: id 1 | task 1600 | stop processing: n_tokens = 1422, truncated = 0 3.10.108.273 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.784 3.10.108.300 I slot launch_slot_: id 1 | task 1817 | processing task, is_child = 0 3.10.524.256 I slot print_timing: id 2 | task 1717 | n_gen = 100, tg = 22.99 t/s, tg_3s = 23.22 t/s 3.11.392.681 I slot print_timing: id 3 | task 1668 | n_gen = 171, tg = 23.36 t/s, tg_3s = 23.65 t/s 3.11.430.206 I slot print_timing: id 3 | task 1668 | prompt eval time = 288.88 ms / 71 tokens ( 4.07 ms per token, 245.77 tokens per second) 3.11.430.214 I slot print_timing: id 3 | task 1668 | eval time = 7315.41 ms / 172 tokens ( 42.78 ms per token, 23.38 tokens per second) 3.11.430.214 I slot print_timing: id 3 | task 1668 | total time = 7604.30 ms / 243 tokens 3.11.430.215 I slot print_timing: id 3 | task 1668 | graphs reused = 1333 3.11.430.216 I slot print_timing: id 3 | task 1668 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.430.277 I slot release: id 3 | task 1668 | stop processing: n_tokens = 1357, truncated = 0 3.11.466.347 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.822 3.11.466.372 I slot launch_slot_: id 3 | task 1846 | processing task, is_child = 0 3.12.496.838 I slot print_timing: id 0 | task 1765 | n_gen = 100, tg = 23.24 t/s, tg_3s = 23.47 t/s 3.13.556.171 I slot print_timing: id 2 | task 1717 | n_gen = 175, tg = 23.71 t/s, tg_3s = 24.74 t/s 3.14.007.690 I slot print_timing: id 2 | task 1717 | prompt eval time = 341.94 ms / 90 tokens ( 3.80 ms per token, 263.21 tokens per second) 3.14.007.694 I slot print_timing: id 2 | task 1717 | eval time = 7790.12 ms / 187 tokens ( 41.88 ms per token, 23.88 tokens per second) 3.14.007.695 I slot print_timing: id 2 | task 1717 | total time = 8132.06 ms / 277 tokens 3.14.007.695 I slot print_timing: id 2 | task 1717 | graphs reused = 1392 3.14.007.696 I slot print_timing: id 2 | task 1717 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.007.755 I slot release: id 2 | task 1717 | stop processing: n_tokens = 1391, truncated = 0 3.14.071.290 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.802 3.14.071.319 I slot launch_slot_: id 2 | task 1910 | processing task, is_child = 0 3.14.748.588 I slot print_timing: id 1 | task 1817 | n_gen = 100, tg = 23.23 t/s, tg_3s = 23.46 t/s 3.15.497.227 I slot print_timing: id 0 | task 1765 | n_gen = 171, tg = 23.41 t/s, tg_3s = 23.66 t/s 3.15.802.624 I slot print_timing: id 3 | task 1846 | n_gen = 100, tg = 24.41 t/s, tg_3s = 24.66 t/s 3.16.778.086 I slot print_timing: id 3 | task 1846 | prompt eval time = 280.46 ms / 94 tokens ( 2.98 ms per token, 335.16 tokens per second) 3.16.778.089 I slot print_timing: id 3 | task 1846 | eval time = 5031.24 ms / 126 tokens ( 40.25 ms per token, 24.84 tokens per second) 3.16.778.090 I slot print_timing: id 3 | task 1846 | total time = 5311.71 ms / 220 tokens 3.16.778.091 I slot print_timing: id 3 | task 1846 | graphs reused = 1453 3.16.778.091 I slot print_timing: id 3 | task 1846 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.778.149 I slot release: id 3 | task 1846 | stop processing: n_tokens = 1334, truncated = 0 3.16.814.459 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.836 3.16.814.489 I slot launch_slot_: id 3 | task 1976 | processing task, is_child = 0 3.17.784.349 I slot print_timing: id 1 | task 1817 | n_gen = 174, tg = 23.71 t/s, tg_3s = 24.38 t/s 3.18.420.500 I slot print_timing: id 2 | task 1910 | n_gen = 100, tg = 24.92 t/s, tg_3s = 25.17 t/s 3.18.530.146 I slot print_timing: id 0 | task 1765 | n_gen = 245, tg = 23.70 t/s, tg_3s = 24.40 t/s 3.19.131.634 I slot print_timing: id 0 | task 1765 | prompt eval time = 326.11 ms / 125 tokens ( 2.61 ms per token, 383.31 tokens per second) 3.19.131.640 I slot print_timing: id 0 | task 1765 | eval time = 10895.52 ms / 261 tokens ( 41.91 ms per token, 23.86 tokens per second) 3.19.131.640 I slot print_timing: id 0 | task 1765 | total time = 11221.63 ms / 386 tokens 3.19.131.641 I slot print_timing: id 0 | task 1765 | graphs reused = 1505 3.19.131.641 I slot print_timing: id 0 | task 1765 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.131.703 I slot release: id 0 | task 1765 | stop processing: n_tokens = 1500, truncated = 0 3.19.172.195 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.743 3.19.172.219 I slot launch_slot_: id 0 | task 2033 | processing task, is_child = 0 3.20.122.567 I slot print_timing: id 1 | task 1817 | prompt eval time = 378.36 ms / 106 tokens ( 3.57 ms per token, 280.16 tokens per second) 3.20.122.571 I slot print_timing: id 1 | task 1817 | eval time = 9635.90 ms / 231 tokens ( 41.90 ms per token, 23.87 tokens per second) 3.20.122.572 I slot print_timing: id 1 | task 1817 | total time = 10014.26 ms / 337 tokens 3.20.122.573 I slot print_timing: id 1 | task 1817 | graphs reused = 1523 3.20.122.573 I slot print_timing: id 1 | task 1817 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.122.641 I slot release: id 1 | task 1817 | stop processing: n_tokens = 1451, truncated = 0 3.20.187.699 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.768 3.20.187.731 I slot launch_slot_: id 1 | task 2055 | processing task, is_child = 0 3.21.354.529 I slot print_timing: id 3 | task 1976 | n_gen = 100, tg = 23.52 t/s, tg_3s = 23.76 t/s 3.21.428.188 I slot print_timing: id 2 | task 1910 | n_gen = 167, tg = 23.78 t/s, tg_3s = 22.28 t/s 3.23.451.028 I slot print_timing: id 0 | task 2033 | n_gen = 100, tg = 24.70 t/s, tg_3s = 24.95 t/s 3.23.827.412 I slot print_timing: id 0 | task 2033 | prompt eval time = 271.12 ms / 71 tokens ( 3.82 ms per token, 261.88 tokens per second) 3.23.827.419 I slot print_timing: id 0 | task 2033 | eval time = 4384.07 ms / 110 tokens ( 40.22 ms per token, 24.86 tokens per second) 3.23.827.421 I slot print_timing: id 0 | task 2033 | total time = 4655.19 ms / 181 tokens 3.23.827.422 I slot print_timing: id 0 | task 2033 | graphs reused = 1610 3.23.827.422 I slot print_timing: id 0 | task 2033 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.827.481 I slot release: id 0 | task 2033 | stop processing: n_tokens = 1295, truncated = 0 3.23.829.026 I slot print_timing: id 1 | task 2055 | prompt eval time = 332.76 ms / 81 tokens ( 4.11 ms per token, 243.42 tokens per second) 3.23.829.029 I slot print_timing: id 1 | task 2055 | eval time = 3308.53 ms / 89 tokens ( 37.60 ms per token, 26.60 tokens per second) 3.23.829.030 I slot print_timing: id 1 | task 2055 | total time = 3641.29 ms / 170 tokens 3.23.829.030 I slot print_timing: id 1 | task 2055 | graphs reused = 1610 3.23.829.031 I slot print_timing: id 1 | task 2055 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.829.080 I slot release: id 1 | task 2055 | stop processing: n_tokens = 1284, truncated = 0 3.23.865.681 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.861 3.23.865.707 I slot launch_slot_: id 0 | task 2147 | processing task, is_child = 0 3.23.893.144 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.868 3.23.893.180 I slot launch_slot_: id 1 | task 2148 | processing task, is_child = 0 3.24.375.438 I slot print_timing: id 3 | task 1976 | n_gen = 171, tg = 23.51 t/s, tg_3s = 23.50 t/s 3.24.451.538 I slot print_timing: id 2 | task 1910 | n_gen = 238, tg = 23.69 t/s, tg_3s = 23.48 t/s 3.25.054.965 I slot print_timing: id 3 | task 1976 | prompt eval time = 330.81 ms / 114 tokens ( 2.90 ms per token, 344.61 tokens per second) 3.25.054.969 I slot print_timing: id 3 | task 1976 | eval time = 7909.66 ms / 189 tokens ( 42.07 ms per token, 23.77 tokens per second) 3.25.054.970 I slot print_timing: id 3 | task 1976 | total time = 8240.47 ms / 303 tokens 3.25.054.970 I slot print_timing: id 3 | task 1976 | graphs reused = 1630 3.25.054.971 I slot print_timing: id 3 | task 1976 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.055.037 I slot release: id 3 | task 1976 | stop processing: n_tokens = 1417, truncated = 0 3.25.091.052 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.787 3.25.091.084 I slot launch_slot_: id 3 | task 2172 | processing task, is_child = 0 3.26.011.004 I slot print_timing: id 2 | task 1910 | prompt eval time = 376.15 ms / 103 tokens ( 3.65 ms per token, 273.82 tokens per second) 3.26.011.008 I slot print_timing: id 2 | task 1910 | eval time = 11563.52 ms / 274 tokens ( 42.36 ms per token, 23.61 tokens per second) 3.26.011.008 I slot print_timing: id 2 | task 1910 | total time = 11939.67 ms / 377 tokens 3.26.011.009 I slot print_timing: id 2 | task 1910 | graphs reused = 1646 3.26.011.010 I slot print_timing: id 2 | task 1910 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.011.072 I slot release: id 2 | task 1910 | stop processing: n_tokens = 1491, truncated = 0 3.26.074.435 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.748 3.26.074.468 I slot launch_slot_: id 2 | task 2193 | processing task, is_child = 0 3.28.514.638 I slot print_timing: id 0 | task 2147 | n_gen = 100, tg = 23.47 t/s, tg_3s = 23.71 t/s 3.28.516.215 I slot print_timing: id 1 | task 2148 | n_gen = 100, tg = 23.47 t/s, tg_3s = 23.70 t/s 3.28.737.945 I slot print_timing: id 0 | task 2147 | prompt eval time = 403.05 ms / 77 tokens ( 5.23 ms per token, 191.04 tokens per second) 3.28.737.948 I slot print_timing: id 0 | task 2147 | eval time = 4441.70 ms / 106 tokens ( 42.30 ms per token, 23.64 tokens per second) 3.28.737.949 I slot print_timing: id 0 | task 2147 | total time = 4844.75 ms / 183 tokens 3.28.737.950 I slot print_timing: id 0 | task 2147 | graphs reused = 1706 3.28.737.950 I slot print_timing: id 0 | task 2147 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.738.020 I slot release: id 0 | task 2147 | stop processing: n_tokens = 1297, truncated = 0 3.28.778.052 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.860 3.28.778.077 I slot launch_slot_: id 0 | task 2259 | processing task, is_child = 0 3.29.137.314 I slot print_timing: id 1 | task 2148 | prompt eval time = 401.94 ms / 74 tokens ( 5.43 ms per token, 184.11 tokens per second) 3.29.137.320 I slot print_timing: id 1 | task 2148 | eval time = 4839.95 ms / 110 tokens ( 44.40 ms per token, 22.52 tokens per second) 3.29.137.321 I slot print_timing: id 1 | task 2148 | total time = 5241.88 ms / 184 tokens 3.29.137.321 I slot print_timing: id 1 | task 2148 | graphs reused = 1707 3.29.137.322 I slot print_timing: id 1 | task 2148 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.137.367 I slot release: id 1 | task 2148 | stop processing: n_tokens = 1298, truncated = 0 3.29.200.594 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.859 3.29.200.619 I slot launch_slot_: id 1 | task 2264 | processing task, is_child = 0 3.29.922.123 I slot print_timing: id 3 | task 2172 | n_gen = 100, tg = 21.75 t/s, tg_3s = 21.97 t/s 3.30.668.542 I slot print_timing: id 2 | task 2193 | n_gen = 100, tg = 23.23 t/s, tg_3s = 23.46 t/s 3.30.930.514 I slot print_timing: id 2 | task 2193 | prompt eval time = 331.43 ms / 97 tokens ( 3.42 ms per token, 292.67 tokens per second) 3.30.930.521 I slot print_timing: id 2 | task 2193 | eval time = 4524.61 ms / 107 tokens ( 42.68 ms per token, 23.43 tokens per second) 3.30.930.522 I slot print_timing: id 2 | task 2193 | total time = 4856.04 ms / 204 tokens 3.30.930.523 I slot print_timing: id 2 | task 2193 | graphs reused = 1743 3.30.930.523 I slot print_timing: id 2 | task 2193 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.930.588 I slot release: id 2 | task 2193 | stop processing: n_tokens = 1318, truncated = 0 3.30.994.177 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.846 3.30.994.219 I slot launch_slot_: id 2 | task 2305 | processing task, is_child = 0 3.32.571.262 I slot print_timing: id 3 | task 2172 | prompt eval time = 279.60 ms / 86 tokens ( 3.25 ms per token, 307.58 tokens per second) 3.32.571.266 I slot print_timing: id 3 | task 2172 | eval time = 7200.57 ms / 164 tokens ( 44.18 ms per token, 22.64 tokens per second) 3.32.571.267 I slot print_timing: id 3 | task 2172 | total time = 7480.17 ms / 250 tokens 3.32.571.267 I slot print_timing: id 3 | task 2172 | graphs reused = 1776 3.32.571.268 I slot print_timing: id 3 | task 2172 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.571.337 I slot release: id 3 | task 2172 | stop processing: n_tokens = 1364, truncated = 0 3.32.607.340 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.817 3.32.607.365 I slot launch_slot_: id 3 | task 2343 | processing task, is_child = 0 3.33.562.787 I slot print_timing: id 0 | task 2259 | n_gen = 100, tg = 22.18 t/s, tg_3s = 22.41 t/s 3.33.714.512 I slot print_timing: id 1 | task 2264 | n_gen = 100, tg = 23.72 t/s, tg_3s = 23.96 t/s 3.34.166.675 I slot print_timing: id 2 | task 2305 | prompt eval time = 293.81 ms / 65 tokens ( 4.52 ms per token, 221.23 tokens per second) 3.34.166.679 I slot print_timing: id 2 | task 2305 | eval time = 2878.63 ms / 72 tokens ( 40.54 ms per token, 24.66 tokens per second) 3.34.166.680 I slot print_timing: id 2 | task 2305 | total time = 3172.45 ms / 137 tokens 3.34.166.680 I slot print_timing: id 2 | task 2305 | graphs reused = 1809 3.34.166.681 I slot print_timing: id 2 | task 2305 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.166.743 I slot release: id 2 | task 2305 | stop processing: n_tokens = 1251, truncated = 0 3.34.230.251 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.891 3.34.230.285 I slot launch_slot_: id 2 | task 2381 | processing task, is_child = 0 3.36.589.358 I slot print_timing: id 0 | task 2259 | n_gen = 173, tg = 22.97 t/s, tg_3s = 24.12 t/s 3.36.740.781 I slot print_timing: id 1 | task 2264 | n_gen = 173, tg = 23.89 t/s, tg_3s = 24.12 t/s 3.36.892.829 I slot print_timing: id 3 | task 2343 | n_gen = 100, tg = 24.72 t/s, tg_3s = 24.97 t/s 3.37.112.618 I slot print_timing: id 0 | task 2259 | prompt eval time = 321.78 ms / 101 tokens ( 3.19 ms per token, 313.88 tokens per second) 3.37.112.625 I slot print_timing: id 0 | task 2259 | eval time = 8012.75 ms / 187 tokens ( 43.08 ms per token, 23.21 tokens per second) 3.37.112.626 I slot print_timing: id 0 | task 2259 | total time = 8334.53 ms / 288 tokens 3.37.112.626 I slot print_timing: id 0 | task 2259 | graphs reused = 1876 3.37.112.627 I slot print_timing: id 0 | task 2259 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.112.698 I slot release: id 0 | task 2259 | stop processing: n_tokens = 1402, truncated = 0 3.37.153.192 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.795 3.37.153.222 I slot launch_slot_: id 0 | task 2453 | processing task, is_child = 0 3.38.437.638 I slot print_timing: id 2 | task 2381 | n_gen = 100, tg = 25.52 t/s, tg_3s = 25.78 t/s 3.39.374.949 I slot print_timing: id 1 | task 2264 | prompt eval time = 339.56 ms / 86 tokens ( 3.95 ms per token, 253.27 tokens per second) 3.39.374.954 I slot print_timing: id 1 | task 2264 | eval time = 9834.76 ms / 239 tokens ( 41.32 ms per token, 24.20 tokens per second) 3.39.374.955 I slot print_timing: id 1 | task 2264 | total time = 10174.32 ms / 325 tokens 3.39.374.956 I slot print_timing: id 1 | task 2264 | graphs reused = 1929 3.39.374.956 I slot print_timing: id 1 | task 2264 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.375.018 I slot release: id 1 | task 2264 | stop processing: n_tokens = 1439, truncated = 0 3.39.438.413 I slot print_timing: id 2 | task 2381 | prompt eval time = 328.08 ms / 73 tokens ( 4.49 ms per token, 222.51 tokens per second) 3.39.438.417 I slot print_timing: id 2 | task 2381 | eval time = 4880.04 ms / 126 tokens ( 39.04 ms per token, 25.61 tokens per second) 3.39.438.417 I slot print_timing: id 2 | task 2381 | total time = 5208.12 ms / 199 tokens 3.39.438.418 I slot print_timing: id 2 | task 2381 | graphs reused = 1929 3.39.438.418 I slot print_timing: id 2 | task 2381 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.438.483 I slot release: id 2 | task 2381 | stop processing: n_tokens = 1313, truncated = 0 3.39.440.083 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.775 3.39.440.113 I slot launch_slot_: id 1 | task 2510 | processing task, is_child = 0 3.39.470.913 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.849 3.39.470.942 I slot launch_slot_: id 2 | task 2511 | processing task, is_child = 0 3.39.954.577 I slot print_timing: id 3 | task 2343 | n_gen = 165, tg = 23.21 t/s, tg_3s = 21.23 t/s 3.41.566.946 I slot print_timing: id 0 | task 2453 | n_gen = 100, tg = 23.66 t/s, tg_3s = 23.90 t/s 3.41.721.485 I slot print_timing: id 3 | task 2343 | prompt eval time = 279.96 ms / 81 tokens ( 3.46 ms per token, 289.33 tokens per second) 3.41.721.489 I slot print_timing: id 3 | task 2343 | eval time = 8834.16 ms / 212 tokens ( 41.87 ms per token, 23.88 tokens per second) 3.41.721.490 I slot print_timing: id 3 | task 2343 | total time = 9114.11 ms / 293 tokens 3.41.721.490 I slot print_timing: id 3 | task 2343 | graphs reused = 1975 3.41.721.491 I slot print_timing: id 3 | task 2343 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.721.551 I slot release: id 3 | task 2343 | stop processing: n_tokens = 1407, truncated = 0 3.41.757.492 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.792 3.41.757.519 I slot launch_slot_: id 3 | task 2562 | processing task, is_child = 0 3.42.067.434 I slot print_timing: id 0 | task 2453 | prompt eval time = 229.30 ms / 66 tokens ( 3.47 ms per token, 287.83 tokens per second) 3.42.067.437 I slot print_timing: id 0 | task 2453 | eval time = 4684.90 ms / 108 tokens ( 43.78 ms per token, 22.84 tokens per second) 3.42.067.437 I slot print_timing: id 0 | task 2453 | total time = 4914.21 ms / 174 tokens 3.42.067.438 I slot print_timing: id 0 | task 2453 | graphs reused = 1975 3.42.067.438 I slot print_timing: id 0 | task 2453 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.067.482 I slot release: id 0 | task 2453 | stop processing: n_tokens = 1288, truncated = 0 3.42.104.907 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.866 3.42.104.927 I slot launch_slot_: id 0 | task 2567 | processing task, is_child = 0 3.43.638.666 I slot print_timing: id 1 | task 2510 | prompt eval time = 481.49 ms / 96 tokens ( 5.02 ms per token, 199.38 tokens per second) 3.43.638.670 I slot print_timing: id 1 | task 2510 | eval time = 3686.22 ms / 87 tokens ( 42.86 ms per token, 23.33 tokens per second) 3.43.638.671 I slot print_timing: id 1 | task 2510 | total time = 4167.71 ms / 183 tokens 3.43.638.671 I slot print_timing: id 1 | task 2510 | graphs reused = 2006 3.43.638.672 I slot print_timing: id 1 | task 2510 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.638.733 I slot release: id 1 | task 2510 | stop processing: n_tokens = 1297, truncated = 0 3.43.704.427 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.860 3.43.704.461 I slot launch_slot_: id 1 | task 2603 | processing task, is_child = 0 3.44.416.529 I slot print_timing: id 2 | task 2511 | n_gen = 100, tg = 22.18 t/s, tg_3s = 22.41 t/s 3.44.642.467 I slot print_timing: id 2 | task 2511 | prompt eval time = 480.08 ms / 84 tokens ( 5.72 ms per token, 174.97 tokens per second) 3.44.642.474 I slot print_timing: id 2 | task 2511 | eval time = 4688.96 ms / 106 tokens ( 44.66 ms per token, 22.39 tokens per second) 3.44.642.474 I slot print_timing: id 2 | task 2511 | total time = 5169.04 ms / 190 tokens 3.44.642.475 I slot print_timing: id 2 | task 2511 | graphs reused = 2021 3.44.642.476 I slot print_timing: id 2 | task 2511 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.642.533 I slot release: id 2 | task 2511 | stop processing: n_tokens = 1304, truncated = 0 3.44.706.048 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.855 3.44.706.072 I slot launch_slot_: id 2 | task 2623 | processing task, is_child = 0 3.46.631.691 I slot print_timing: id 3 | task 2562 | n_gen = 100, tg = 21.53 t/s, tg_3s = 21.75 t/s 3.46.777.335 I slot print_timing: id 0 | task 2567 | n_gen = 100, tg = 22.77 t/s, tg_3s = 23.00 t/s 3.47.156.391 I slot print_timing: id 3 | task 2562 | prompt eval time = 276.78 ms / 70 tokens ( 3.95 ms per token, 252.91 tokens per second) 3.47.156.395 I slot print_timing: id 3 | task 2562 | eval time = 5122.09 ms / 114 tokens ( 45.33 ms per token, 22.06 tokens per second) 3.47.156.395 I slot print_timing: id 3 | task 2562 | total time = 5398.87 ms / 184 tokens 3.47.156.396 I slot print_timing: id 3 | task 2562 | graphs reused = 2075 3.47.156.397 I slot print_timing: id 3 | task 2562 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.156.459 I slot release: id 3 | task 2562 | stop processing: n_tokens = 1298, truncated = 0 3.47.192.387 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.859 3.47.192.416 I slot launch_slot_: id 3 | task 2682 | processing task, is_child = 0 3.48.296.749 I slot print_timing: id 1 | task 2603 | n_gen = 100, tg = 23.23 t/s, tg_3s = 23.47 t/s 3.49.012.845 I slot print_timing: id 2 | task 2623 | n_gen = 100, tg = 25.22 t/s, tg_3s = 25.48 t/s 3.49.805.358 I slot print_timing: id 0 | task 2567 | n_gen = 175, tg = 23.59 t/s, tg_3s = 24.77 t/s 3.50.794.106 I slot print_timing: id 3 | task 2682 | prompt eval time = 279.57 ms / 93 tokens ( 3.01 ms per token, 332.65 tokens per second) 3.50.794.112 I slot print_timing: id 3 | task 2682 | eval time = 3322.11 ms / 89 tokens ( 37.75 ms per token, 26.49 tokens per second) 3.50.794.113 I slot print_timing: id 3 | task 2682 | total time = 3601.68 ms / 182 tokens 3.50.794.113 I slot print_timing: id 3 | task 2682 | graphs reused = 2162 3.50.794.114 I slot print_timing: id 3 | task 2682 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.794.168 I slot release: id 3 | task 2682 | stop processing: n_tokens = 1296, truncated = 0 3.50.830.330 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.860 3.50.830.357 I slot launch_slot_: id 3 | task 2774 | processing task, is_child = 0 3.51.301.334 I slot print_timing: id 1 | task 2603 | n_gen = 173, tg = 23.67 t/s, tg_3s = 24.30 t/s 3.52.020.825 I slot print_timing: id 2 | task 2623 | n_gen = 173, tg = 24.81 t/s, tg_3s = 24.27 t/s 3.52.430.620 I slot print_timing: id 1 | task 2603 | prompt eval time = 331.00 ms / 88 tokens ( 3.76 ms per token, 265.86 tokens per second) 3.52.430.627 I slot print_timing: id 1 | task 2603 | eval time = 8395.15 ms / 203 tokens ( 41.56 ms per token, 24.06 tokens per second) 3.52.430.628 I slot print_timing: id 1 | task 2603 | total time = 8726.15 ms / 291 tokens 3.52.430.628 I slot print_timing: id 1 | task 2603 | graphs reused = 2195 3.52.430.629 I slot print_timing: id 1 | task 2603 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.430.687 I slot release: id 1 | task 2603 | stop processing: n_tokens = 1405, truncated = 0 3.52.496.002 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.794 3.52.496.035 I slot launch_slot_: id 1 | task 2812 | processing task, is_child = 0 3.52.823.860 I slot print_timing: id 0 | task 2567 | n_gen = 242, tg = 23.19 t/s, tg_3s = 22.20 t/s 3.55.044.379 I slot print_timing: id 2 | task 2623 | n_gen = 247, tg = 24.71 t/s, tg_3s = 24.47 t/s 3.55.118.142 I slot print_timing: id 1 | task 2812 | prompt eval time = 289.23 ms / 57 tokens ( 5.07 ms per token, 197.07 tokens per second) 3.55.118.145 I slot print_timing: id 1 | task 2812 | eval time = 2332.87 ms / 63 tokens ( 37.63 ms per token, 26.58 tokens per second) 3.55.118.146 I slot print_timing: id 1 | task 2812 | total time = 2622.10 ms / 120 tokens 3.55.118.147 I slot print_timing: id 1 | task 2812 | graphs reused = 2256 3.55.118.147 I slot print_timing: id 1 | task 2812 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.118.204 I slot release: id 1 | task 2812 | stop processing: n_tokens = 1234, truncated = 0 3.55.121.134 I slot print_timing: id 3 | task 2774 | n_gen = 100, tg = 24.98 t/s, tg_3s = 25.23 t/s 3.55.183.811 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.904 3.55.183.843 I slot launch_slot_: id 1 | task 2878 | processing task, is_child = 0 3.55.855.879 I slot print_timing: id 0 | task 2567 | n_gen = 315, tg = 23.39 t/s, tg_3s = 24.08 t/s 3.56.495.890 I slot print_timing: id 0 | task 2567 | prompt eval time = 325.47 ms / 119 tokens ( 2.74 ms per token, 365.62 tokens per second) 3.56.495.897 I slot print_timing: id 0 | task 2567 | eval time = 14065.48 ms / 332 tokens ( 42.49 ms per token, 23.53 tokens per second) 3.56.495.899 I slot print_timing: id 0 | task 2567 | total time = 14390.95 ms / 451 tokens 3.56.495.899 I slot print_timing: id 0 | task 2567 | graphs reused = 2281 3.56.495.900 I slot print_timing: id 0 | task 2567 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.495.963 I slot release: id 0 | task 2567 | stop processing: n_tokens = 1565, truncated = 0 3.56.536.808 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.712 3.56.536.832 I slot launch_slot_: id 0 | task 2908 | processing task, is_child = 0 3.58.065.788 I slot print_timing: id 2 | task 2623 | n_gen = 313, tg = 24.04 t/s, tg_3s = 21.84 t/s 3.58.141.890 I slot print_timing: id 3 | task 2774 | n_gen = 166, tg = 23.63 t/s, tg_3s = 21.85 t/s 3.59.154.990 I slot print_timing: id 1 | task 2878 | prompt eval time = 330.40 ms / 79 tokens ( 4.18 ms per token, 239.10 tokens per second) 3.59.154.998 I slot print_timing: id 1 | task 2878 | eval time = 3640.74 ms / 91 tokens ( 40.45 ms per token, 24.72 tokens per second) 3.59.154.999 I slot print_timing: id 1 | task 2878 | total time = 3971.14 ms / 170 tokens 3.59.155.000 I slot print_timing: id 1 | task 2878 | graphs reused = 2341 3.59.155.000 I slot print_timing: id 1 | task 2878 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.155.079 I slot release: id 1 | task 2878 | stop processing: n_tokens = 1284, truncated = 0 3.59.220.685 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.868 3.59.220.716 I slot launch_slot_: id 1 | task 2973 | processing task, is_child = 0 4.00.873.725 I slot print_timing: id 0 | task 2908 | n_gen = 100, tg = 24.65 t/s, tg_3s = 24.90 t/s 4.00.914.559 I slot print_timing: id 2 | task 2623 | prompt eval time = 381.41 ms / 133 tokens ( 2.87 ms per token, 348.70 tokens per second) 4.00.914.563 I slot print_timing: id 2 | task 2623 | eval time = 15827.07 ms / 381 tokens ( 41.65 ms per token, 24.01 tokens per second) 4.00.914.564 I slot print_timing: id 2 | task 2623 | total time = 16208.48 ms / 514 tokens 4.00.914.564 I slot print_timing: id 2 | task 2623 | graphs reused = 2376 4.00.914.565 I slot print_timing: id 2 | task 2623 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.914.632 I slot release: id 2 | task 2623 | stop processing: n_tokens = 1628, truncated = 0 4.00.978.256 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.685 4.00.978.280 I slot launch_slot_: id 2 | task 3013 | processing task, is_child = 0 4.01.261.988 I slot print_timing: id 3 | task 2774 | n_gen = 234, tg = 23.06 t/s, tg_3s = 21.79 t/s 4.01.918.443 I slot print_timing: id 0 | task 2908 | prompt eval time = 320.21 ms / 101 tokens ( 3.17 ms per token, 315.41 tokens per second) 4.01.918.447 I slot print_timing: id 0 | task 2908 | eval time = 5061.39 ms / 119 tokens ( 42.89 ms per token, 23.31 tokens per second) 4.01.918.448 I slot print_timing: id 0 | task 2908 | total time = 5381.60 ms / 220 tokens 4.01.918.448 I slot print_timing: id 0 | task 2908 | graphs reused = 2390 4.01.918.449 I slot print_timing: id 0 | task 2908 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.918.512 I slot release: id 0 | task 2908 | stop processing: n_tokens = 1334, truncated = 0 4.01.959.050 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.836 4.01.959.074 I slot launch_slot_: id 0 | task 3032 | processing task, is_child = 0 4.03.813.640 I slot print_timing: id 1 | task 2973 | n_gen = 100, tg = 23.23 t/s, tg_3s = 23.47 t/s 4.04.267.047 I slot print_timing: id 3 | task 2774 | n_gen = 307, tg = 23.34 t/s, tg_3s = 24.29 t/s 4.05.277.942 I slot print_timing: id 2 | task 3013 | n_gen = 100, tg = 25.23 t/s, tg_3s = 25.49 t/s 4.05.916.384 I slot print_timing: id 2 | task 3013 | prompt eval time = 375.99 ms / 103 tokens ( 3.65 ms per token, 273.94 tokens per second) 4.05.916.392 I slot print_timing: id 2 | task 3013 | eval time = 4562.10 ms / 117 tokens ( 39.33 ms per token, 25.43 tokens per second) 4.05.916.393 I slot print_timing: id 2 | task 3013 | total time = 4938.10 ms / 220 tokens 4.05.916.394 I slot print_timing: id 2 | task 3013 | graphs reused = 2487 4.05.916.394 I slot print_timing: id 2 | task 3013 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.916.454 I slot release: id 2 | task 3013 | stop processing: n_tokens = 1334, truncated = 0 4.05.976.936 I slot print_timing: id 0 | task 3032 | n_gen = 100, tg = 26.44 t/s, tg_3s = 26.71 t/s 4.05.980.107 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.836 4.05.980.134 I slot launch_slot_: id 2 | task 3134 | processing task, is_child = 0 4.06.848.797 I slot print_timing: id 1 | task 2973 | n_gen = 173, tg = 23.57 t/s, tg_3s = 24.05 t/s 4.07.076.937 I slot print_timing: id 3 | task 2774 | prompt eval time = 327.75 ms / 103 tokens ( 3.18 ms per token, 314.27 tokens per second) 4.07.076.944 I slot print_timing: id 3 | task 2774 | eval time = 15918.83 ms / 374 tokens ( 42.68 ms per token, 23.43 tokens per second) 4.07.076.945 I slot print_timing: id 3 | task 2774 | total time = 16246.57 ms / 477 tokens 4.07.076.945 I slot print_timing: id 3 | task 2774 | graphs reused = 2506 4.07.076.946 I slot print_timing: id 3 | task 2774 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.077.008 I slot release: id 3 | task 2774 | stop processing: n_tokens = 1591, truncated = 0 4.07.113.128 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.701 4.07.113.157 I slot launch_slot_: id 3 | task 3158 | processing task, is_child = 0 4.07.916.157 I slot print_timing: id 1 | task 2973 | prompt eval time = 331.51 ms / 78 tokens ( 4.25 ms per token, 235.29 tokens per second) 4.07.916.162 I slot print_timing: id 1 | task 2973 | eval time = 8363.92 ms / 196 tokens ( 42.89 ms per token, 23.31 tokens per second) 4.07.916.163 I slot print_timing: id 1 | task 2973 | total time = 8695.43 ms / 274 tokens 4.07.916.163 I slot print_timing: id 1 | task 2973 | graphs reused = 2519 4.07.916.164 I slot print_timing: id 1 | task 2973 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.916.221 I slot release: id 1 | task 2973 | stop processing: n_tokens = 1388, truncated = 0 4.07.981.415 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.803 4.07.981.446 I slot launch_slot_: id 1 | task 3176 | processing task, is_child = 0 4.08.981.819 I slot print_timing: id 0 | task 3032 | n_gen = 157, tg = 23.11 t/s, tg_3s = 18.97 t/s 4.10.635.046 I slot print_timing: id 2 | task 3134 | n_gen = 100, tg = 22.92 t/s, tg_3s = 23.16 t/s 4.10.823.758 I slot print_timing: id 3 | task 3158 | prompt eval time = 276.17 ms / 77 tokens ( 3.59 ms per token, 278.82 tokens per second) 4.10.823.761 I slot print_timing: id 3 | task 3158 | eval time = 3434.42 ms / 82 tokens ( 42.40 ms per token, 23.58 tokens per second) 4.10.823.762 I slot print_timing: id 3 | task 3158 | total time = 3710.59 ms / 159 tokens 4.10.823.763 I slot print_timing: id 3 | task 3158 | graphs reused = 2582 4.10.823.763 I slot print_timing: id 3 | task 3158 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.823.825 I slot release: id 3 | task 3158 | stop processing: n_tokens = 1273, truncated = 0 4.10.859.960 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.876 4.10.859.983 I slot launch_slot_: id 3 | task 3244 | processing task, is_child = 0 4.11.786.697 I slot print_timing: id 2 | task 3134 | prompt eval time = 336.31 ms / 83 tokens ( 4.05 ms per token, 246.80 tokens per second) 4.11.786.701 I slot print_timing: id 2 | task 3134 | eval time = 5470.25 ms / 126 tokens ( 43.76 ms per token, 22.85 tokens per second) 4.11.786.702 I slot print_timing: id 2 | task 3134 | total time = 5806.56 ms / 209 tokens 4.11.786.703 I slot print_timing: id 2 | task 3134 | graphs reused = 2599 4.11.786.704 I slot print_timing: id 2 | task 3134 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.786.770 I slot release: id 2 | task 3134 | stop processing: n_tokens = 1323, truncated = 0 4.11.851.029 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.843 4.11.851.058 I slot launch_slot_: id 2 | task 3266 | processing task, is_child = 0 4.12.038.315 I slot print_timing: id 0 | task 3032 | n_gen = 229, tg = 23.25 t/s, tg_3s = 23.56 t/s 4.12.561.654 I slot print_timing: id 0 | task 3032 | prompt eval time = 273.82 ms / 100 tokens ( 2.74 ms per token, 365.20 tokens per second) 4.12.561.658 I slot print_timing: id 0 | task 3032 | eval time = 10328.75 ms / 241 tokens ( 43.04 ms per token, 23.24 tokens per second) 4.12.561.658 I slot print_timing: id 0 | task 3032 | total time = 10602.57 ms / 341 tokens 4.12.561.659 I slot print_timing: id 0 | task 3032 | graphs reused = 2609 4.12.561.660 I slot print_timing: id 0 | task 3032 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.561.723 I slot release: id 0 | task 3032 | stop processing: n_tokens = 1455, truncated = 0 4.12.563.293 I slot print_timing: id 1 | task 3176 | n_gen = 100, tg = 23.85 t/s, tg_3s = 24.09 t/s 4.12.603.383 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.766 4.12.603.413 I slot launch_slot_: id 0 | task 3281 | processing task, is_child = 0 4.14.830.916 I slot print_timing: id 1 | task 3176 | prompt eval time = 430.39 ms / 146 tokens ( 2.95 ms per token, 339.23 tokens per second) 4.14.830.923 I slot print_timing: id 1 | task 3176 | eval time = 6419.08 ms / 155 tokens ( 41.68 ms per token, 23.99 tokens per second) 4.14.830.924 I slot print_timing: id 1 | task 3176 | total time = 6849.46 ms / 301 tokens 4.14.830.924 I slot print_timing: id 1 | task 3176 | graphs reused = 2661 4.14.830.925 I slot print_timing: id 1 | task 3176 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.830.987 I slot release: id 1 | task 3176 | stop processing: n_tokens = 1415, truncated = 0 4.14.896.447 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.788 4.14.896.475 I slot launch_slot_: id 1 | task 3337 | processing task, is_child = 0 4.15.540.776 I slot print_timing: id 2 | task 3266 | prompt eval time = 290.54 ms / 57 tokens ( 5.10 ms per token, 196.19 tokens per second) 4.15.540.783 I slot print_timing: id 2 | task 3266 | eval time = 3399.17 ms / 78 tokens ( 44.15 ms per token, 22.65 tokens per second) 4.15.540.783 I slot print_timing: id 2 | task 3266 | total time = 3689.71 ms / 135 tokens 4.15.540.784 I slot print_timing: id 2 | task 3266 | graphs reused = 2668 4.15.540.785 I slot print_timing: id 2 | task 3266 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.540.842 I slot release: id 2 | task 3266 | stop processing: n_tokens = 1249, truncated = 0 4.15.604.120 I slot print_timing: id 3 | task 3244 | n_gen = 100, tg = 22.01 t/s, tg_3s = 22.24 t/s 4.15.604.129 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.893 4.15.604.152 I slot launch_slot_: id 2 | task 3349 | processing task, is_child = 0 4.15.842.247 I slot print_timing: id 3 | task 3244 | prompt eval time = 246.82 ms / 67 tokens ( 3.68 ms per token, 271.45 tokens per second) 4.15.842.252 I slot print_timing: id 3 | task 3244 | eval time = 4735.44 ms / 101 tokens ( 47.35 ms per token, 21.12 tokens per second) 4.15.842.252 I slot print_timing: id 3 | task 3244 | total time = 4982.26 ms / 168 tokens 4.15.842.253 I slot print_timing: id 3 | task 3244 | graphs reused = 2668 4.15.842.254 I slot print_timing: id 3 | task 3244 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.842.325 I slot release: id 3 | task 3244 | stop processing: n_tokens = 1282, truncated = 0 4.15.913.508 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.870 4.15.913.570 I slot launch_slot_: id 3 | task 3352 | processing task, is_child = 0 4.17.035.055 I slot print_timing: id 0 | task 3281 | prompt eval time = 275.83 ms / 89 tokens ( 3.10 ms per token, 322.66 tokens per second) 4.17.035.059 I slot print_timing: id 0 | task 3281 | eval time = 4155.80 ms / 91 tokens ( 46.18 ms per token, 21.66 tokens per second) 4.17.035.060 I slot print_timing: id 0 | task 3281 | total time = 4431.63 ms / 180 tokens 4.17.035.060 I slot print_timing: id 0 | task 3281 | graphs reused = 2688 4.17.035.061 I slot print_timing: id 0 | task 3281 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.035.123 I slot release: id 0 | task 3281 | stop processing: n_tokens = 1294, truncated = 0 4.17.075.428 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.862 4.17.075.456 I slot launch_slot_: id 0 | task 3378 | processing task, is_child = 0 4.19.599.242 I slot print_timing: id 1 | task 3337 | prompt eval time = 333.04 ms / 71 tokens ( 4.69 ms per token, 213.19 tokens per second) 4.19.599.249 I slot print_timing: id 1 | task 3337 | eval time = 4369.72 ms / 99 tokens ( 44.59 ms per token, 22.43 tokens per second) 4.19.599.250 I slot print_timing: id 1 | task 3337 | total time = 4702.76 ms / 170 tokens 4.19.599.250 I slot print_timing: id 1 | task 3337 | graphs reused = 2747 4.19.599.251 I slot print_timing: id 1 | task 3337 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.599.317 I slot release: id 1 | task 3337 | stop processing: n_tokens = 1284, truncated = 0 4.19.664.617 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.868 4.19.664.649 I slot launch_slot_: id 1 | task 3442 | processing task, is_child = 0 4.20.352.501 I slot print_timing: id 2 | task 3349 | n_gen = 100, tg = 22.30 t/s, tg_3s = 22.53 t/s 4.20.428.998 I slot print_timing: id 3 | task 3352 | n_gen = 100, tg = 23.44 t/s, tg_3s = 23.68 t/s 4.21.360.040 I slot print_timing: id 0 | task 3378 | n_gen = 100, tg = 24.69 t/s, tg_3s = 24.94 t/s 4.23.353.238 I slot print_timing: id 2 | task 3349 | n_gen = 180, tg = 24.06 t/s, tg_3s = 26.66 t/s 4.23.429.926 I slot print_timing: id 3 | task 3352 | n_gen = 180, tg = 24.78 t/s, tg_3s = 26.66 t/s 4.23.691.473 I slot print_timing: id 2 | task 3349 | prompt eval time = 309.33 ms / 84 tokens ( 3.68 ms per token, 271.55 tokens per second) 4.23.691.481 I slot print_timing: id 2 | task 3349 | eval time = 7777.98 ms / 189 tokens ( 41.37 ms per token, 24.17 tokens per second) 4.23.691.481 I slot print_timing: id 2 | task 3349 | total time = 8087.31 ms / 273 tokens 4.23.691.482 I slot print_timing: id 2 | task 3349 | graphs reused = 2844 4.23.691.483 I slot print_timing: id 2 | task 3349 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.691.541 I slot release: id 2 | task 3349 | stop processing: n_tokens = 1387, truncated = 0 4.23.753.428 I slot print_timing: id 1 | task 3442 | n_gen = 100, tg = 26.43 t/s, tg_3s = 26.69 t/s 4.23.755.037 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.804 4.23.755.061 I slot launch_slot_: id 2 | task 3544 | processing task, is_child = 0 4.24.142.254 I slot print_timing: id 0 | task 3378 | prompt eval time = 274.83 ms / 88 tokens ( 3.12 ms per token, 320.20 tokens per second) 4.24.142.262 I slot print_timing: id 0 | task 3378 | eval time = 6791.96 ms / 165 tokens ( 41.41 ms per token, 24.15 tokens per second) 4.24.142.263 I slot print_timing: id 0 | task 3378 | total time = 7066.79 ms / 253 tokens 4.24.142.264 I slot print_timing: id 0 | task 3378 | graphs reused = 2844 4.24.142.265 I slot print_timing: id 0 | task 3378 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.142.350 I slot release: id 0 | task 3378 | stop processing: n_tokens = 1367, truncated = 0 4.24.186.470 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.816 4.24.186.498 I slot launch_slot_: id 0 | task 3548 | processing task, is_child = 0 4.24.477.752 I slot print_timing: id 3 | task 3352 | prompt eval time = 292.38 ms / 72 tokens ( 4.06 ms per token, 246.25 tokens per second) 4.24.477.757 I slot print_timing: id 3 | task 3352 | eval time = 8271.78 ms / 193 tokens ( 43.08 ms per token, 23.21 tokens per second) 4.24.477.758 I slot print_timing: id 3 | task 3352 | total time = 8564.17 ms / 265 tokens 4.24.477.759 I slot print_timing: id 3 | task 3352 | graphs reused = 2845 4.24.477.760 I slot print_timing: id 3 | task 3352 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.477.833 I slot release: id 3 | task 3352 | stop processing: n_tokens = 1379, truncated = 0 4.24.515.400 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.809 4.24.515.435 I slot launch_slot_: id 3 | task 3552 | processing task, is_child = 0 4.25.150.836 I slot print_timing: id 1 | task 3442 | prompt eval time = 342.69 ms / 94 tokens ( 3.65 ms per token, 274.30 tokens per second) 4.25.150.840 I slot print_timing: id 1 | task 3442 | eval time = 5143.48 ms / 117 tokens ( 44.34 ms per token, 22.55 tokens per second) 4.25.150.842 I slot print_timing: id 1 | task 3442 | total time = 5486.18 ms / 211 tokens 4.25.150.843 I slot print_timing: id 1 | task 3442 | graphs reused = 2853 4.25.150.843 I slot print_timing: id 1 | task 3442 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.150.905 I slot release: id 1 | task 3442 | stop processing: n_tokens = 1325, truncated = 0 4.25.215.721 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.842 4.25.215.754 I slot launch_slot_: id 1 | task 3565 | processing task, is_child = 0 4.28.596.594 I slot print_timing: id 2 | task 3544 | n_gen = 100, tg = 22.25 t/s, tg_3s = 22.48 t/s 4.28.705.585 I slot print_timing: id 0 | task 3548 | n_gen = 100, tg = 23.38 t/s, tg_3s = 23.61 t/s 4.28.822.869 I slot print_timing: id 3 | task 3552 | n_gen = 100, tg = 24.67 t/s, tg_3s = 24.92 t/s 4.29.270.442 I slot print_timing: id 1 | task 3565 | n_gen = 100, tg = 26.64 t/s, tg_3s = 26.91 t/s 4.31.151.734 I slot print_timing: id 3 | task 3552 | prompt eval time = 294.84 ms / 84 tokens ( 3.51 ms per token, 284.90 tokens per second) 4.31.151.739 I slot print_timing: id 3 | task 3552 | eval time = 6341.45 ms / 162 tokens ( 39.39 ms per token, 25.39 tokens per second) 4.31.151.740 I slot print_timing: id 3 | task 3552 | total time = 6636.29 ms / 246 tokens 4.31.151.741 I slot print_timing: id 3 | task 3552 | graphs reused = 3000 4.31.151.741 I slot print_timing: id 3 | task 3552 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.151.805 I slot release: id 3 | task 3552 | stop processing: n_tokens = 1360, truncated = 0 4.31.187.987 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.820 4.31.188.014 I slot launch_slot_: id 3 | task 3718 | processing task, is_child = 0 4.31.632.551 I slot print_timing: id 2 | task 3544 | n_gen = 175, tg = 23.25 t/s, tg_3s = 24.70 t/s 4.31.742.453 I slot print_timing: id 0 | task 3548 | n_gen = 175, tg = 23.93 t/s, tg_3s = 24.70 t/s 4.32.306.221 I slot print_timing: id 1 | task 3565 | n_gen = 175, tg = 25.77 t/s, tg_3s = 24.71 t/s 4.33.353.387 I slot print_timing: id 0 | task 3548 | prompt eval time = 284.29 ms / 88 tokens ( 3.23 ms per token, 309.54 tokens per second) 4.33.353.390 I slot print_timing: id 0 | task 3548 | eval time = 8882.59 ms / 218 tokens ( 40.93 ms per token, 24.43 tokens per second) 4.33.353.391 I slot print_timing: id 0 | task 3548 | total time = 9166.88 ms / 306 tokens 4.33.353.392 I slot print_timing: id 0 | task 3548 | graphs reused = 3049 4.33.353.392 I slot print_timing: id 0 | task 3548 | graph reallocs = 0 / 0 (same size) / (changed size) 4.33.353.457 I slot release: id 0 | task 3548 | stop processing: n_tokens = 1420, truncated = 0 4.33.394.167 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.785 4.33.394.200 I slot launch_slot_: id 0 | task 3772 | processing task, is_child = 0 4.34.668.819 I slot print_timing: id 2 | task 3544 | n_gen = 250, tg = 23.67 t/s, tg_3s = 24.70 t/s 4.34.817.776 I slot print_timing: id 1 | task 3565 | prompt eval time = 338.97 ms / 74 tokens ( 4.58 ms per token, 218.31 tokens per second) 4.34.817.784 I slot print_timing: id 1 | task 3565 | eval time = 9263.05 ms / 236 tokens ( 39.42 ms per token, 25.37 tokens per second) 4.34.817.785 I slot print_timing: id 1 | task 3565 | total time = 9602.01 ms / 310 tokens 4.34.817.785 I slot print_timing: id 1 | task 3565 | graphs reused = 3079 4.34.817.786 I slot print_timing: id 1 | task 3565 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.817.845 I slot release: id 1 | task 3565 | stop processing: n_tokens = 1424, truncated = 0 4.34.882.838 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.783 4.34.882.864 I slot launch_slot_: id 1 | task 3806 | processing task, is_child = 0 4.35.818.557 I slot print_timing: id 3 | task 3718 | n_gen = 100, tg = 22.80 t/s, tg_3s = 23.03 t/s 4.36.079.302 I slot print_timing: id 2 | task 3544 | prompt eval time = 392.13 ms / 111 tokens ( 3.53 ms per token, 283.07 tokens per second) 4.36.079.306 I slot print_timing: id 2 | task 3544 | eval time = 11932.10 ms / 277 tokens ( 43.23 ms per token, 23.13 tokens per second) 4.36.079.306 I slot print_timing: id 2 | task 3544 | total time = 12324.23 ms / 388 tokens 4.36.079.307 I slot print_timing: id 2 | task 3544 | graphs reused = 3098 4.36.079.308 I slot print_timing: id 2 | task 3544 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.079.367 I slot release: id 2 | task 3544 | stop processing: n_tokens = 1502, truncated = 0 4.36.142.757 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.742 4.36.142.781 I slot launch_slot_: id 2 | task 3830 | processing task, is_child = 0 4.37.129.985 I slot print_timing: id 3 | task 3718 | prompt eval time = 288.49 ms / 73 tokens ( 3.95 ms per token, 253.05 tokens per second) 4.37.129.989 I slot print_timing: id 3 | task 3718 | eval time = 5653.48 ms / 127 tokens ( 44.87 ms per token, 22.29 tokens per second) 4.37.129.990 I slot print_timing: id 3 | task 3718 | total time = 5941.96 ms / 200 tokens 4.37.129.990 I slot print_timing: id 3 | task 3718 | graphs reused = 3114 4.37.129.991 I slot print_timing: id 3 | task 3718 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.130.052 I slot release: id 3 | task 3718 | stop processing: n_tokens = 1314, truncated = 0 4.37.166.304 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.849 4.37.166.337 I slot launch_slot_: id 3 | task 3851 | processing task, is_child = 0 4.38.322.975 I slot print_timing: id 0 | task 3772 | n_gen = 100, tg = 21.33 t/s, tg_3s = 21.54 t/s 4.39.560.523 I slot print_timing: id 1 | task 3806 | n_gen = 100, tg = 23.36 t/s, tg_3s = 23.60 t/s 4.40.425.460 I slot print_timing: id 2 | task 3830 | n_gen = 100, tg = 25.12 t/s, tg_3s = 25.38 t/s 4.41.177.262 I slot print_timing: id 3 | task 3851 | n_gen = 100, tg = 26.62 t/s, tg_3s = 26.88 t/s 4.41.323.038 I slot print_timing: id 0 | task 3772 | n_gen = 180, tg = 23.42 t/s, tg_3s = 26.67 t/s 4.41.814.667 I slot print_timing: id 3 | task 3851 | prompt eval time = 291.22 ms / 79 tokens ( 3.69 ms per token, 271.28 tokens per second) 4.41.814.670 I slot print_timing: id 3 | task 3851 | eval time = 4357.11 ms / 117 tokens ( 37.56 ms per token, 26.62 tokens per second) 4.41.814.671 I slot print_timing: id 3 | task 3851 | total time = 4648.32 ms / 196 tokens 4.41.814.671 I slot print_timing: id 3 | task 3851 | graphs reused = 3229 4.41.814.672 I slot print_timing: id 3 | task 3851 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.814.731 I slot release: id 3 | task 3851 | stop processing: n_tokens = 1310, truncated = 0 4.41.850.783 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.851 4.41.850.809 I slot launch_slot_: id 3 | task 3971 | processing task, is_child = 0 4.42.411.330 I slot print_timing: id 2 | task 3830 | prompt eval time = 342.14 ms / 92 tokens ( 3.72 ms per token, 268.90 tokens per second) 4.42.411.338 I slot print_timing: id 2 | task 3830 | eval time = 5926.40 ms / 147 tokens ( 40.59 ms per token, 24.64 tokens per second) 4.42.411.338 I slot print_timing: id 2 | task 3830 | total time = 6268.54 ms / 239 tokens 4.42.411.339 I slot print_timing: id 2 | task 3830 | graphs reused = 3235 4.42.411.340 I slot print_timing: id 2 | task 3830 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.411.405 I slot release: id 2 | task 3830 | stop processing: n_tokens = 1353, truncated = 0 4.42.477.091 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.824 4.42.477.117 I slot launch_slot_: id 2 | task 3982 | processing task, is_child = 0 4.42.766.339 I slot print_timing: id 1 | task 3806 | n_gen = 172, tg = 22.97 t/s, tg_3s = 22.46 t/s 4.43.700.168 I slot print_timing: id 0 | task 3772 | prompt eval time = 286.74 ms / 97 tokens ( 2.96 ms per token, 338.28 tokens per second) 4.43.700.172 I slot print_timing: id 0 | task 3772 | eval time = 10019.21 ms / 228 tokens ( 44.14 ms per token, 22.66 tokens per second) 4.43.700.173 I slot print_timing: id 0 | task 3772 | total time = 10305.96 ms / 325 tokens 4.43.700.173 I slot print_timing: id 0 | task 3772 | graphs reused = 3256 4.43.700.174 I slot print_timing: id 0 | task 3772 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.700.238 I slot release: id 0 | task 3772 | stop processing: n_tokens = 1439, truncated = 0 4.43.740.737 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.775 4.43.740.766 I slot launch_slot_: id 0 | task 4008 | processing task, is_child = 0 4.45.784.796 I slot print_timing: id 1 | task 3806 | n_gen = 245, tg = 23.32 t/s, tg_3s = 24.18 t/s 4.46.425.768 I slot print_timing: id 3 | task 3971 | n_gen = 100, tg = 23.11 t/s, tg_3s = 23.35 t/s 4.46.799.971 I slot print_timing: id 2 | task 3982 | n_gen = 100, tg = 25.19 t/s, tg_3s = 25.44 t/s 4.47.737.958 I slot print_timing: id 0 | task 4008 | n_gen = 100, tg = 26.60 t/s, tg_3s = 26.87 t/s 4.48.603.391 I slot print_timing: id 0 | task 4008 | prompt eval time = 275.01 ms / 88 tokens ( 3.13 ms per token, 319.99 tokens per second) 4.48.603.395 I slot print_timing: id 0 | task 4008 | eval time = 4587.61 ms / 123 tokens ( 37.60 ms per token, 26.59 tokens per second) 4.48.603.396 I slot print_timing: id 0 | task 4008 | total time = 4862.62 ms / 211 tokens 4.48.603.396 I slot print_timing: id 0 | task 4008 | graphs reused = 3377 4.48.603.397 I slot print_timing: id 0 | task 4008 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.603.468 I slot release: id 0 | task 4008 | stop processing: n_tokens = 1325, truncated = 0 4.48.644.414 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.842 4.48.644.439 I slot launch_slot_: id 0 | task 4134 | processing task, is_child = 0 4.48.852.244 I slot print_timing: id 1 | task 3806 | n_gen = 322, tg = 23.73 t/s, tg_3s = 25.10 t/s 4.48.922.726 I slot print_timing: id 3 | task 3971 | prompt eval time = 291.52 ms / 83 tokens ( 3.51 ms per token, 284.71 tokens per second) 4.48.922.732 I slot print_timing: id 3 | task 3971 | eval time = 6780.39 ms / 161 tokens ( 42.38 ms per token, 23.60 tokens per second) 4.48.922.732 I slot print_timing: id 3 | task 3971 | total time = 7071.91 ms / 244 tokens 4.48.922.733 I slot print_timing: id 3 | task 3971 | graphs reused = 3378 4.48.922.733 I slot print_timing: id 3 | task 3971 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.922.774 I slot release: id 3 | task 3971 | stop processing: n_tokens = 1358, truncated = 0 4.48.957.772 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.821 4.48.957.791 I slot launch_slot_: id 3 | task 4138 | processing task, is_child = 0 4.49.804.803 I slot print_timing: id 2 | task 3982 | n_gen = 169, tg = 24.22 t/s, tg_3s = 22.96 t/s 4.51.043.966 I slot print_timing: id 1 | task 3806 | prompt eval time = 440.37 ms / 142 tokens ( 3.10 ms per token, 322.45 tokens per second) 4.51.043.969 I slot print_timing: id 1 | task 3806 | eval time = 15720.72 ms / 374 tokens ( 42.15 ms per token, 23.73 tokens per second) 4.51.043.970 I slot print_timing: id 1 | task 3806 | total time = 16161.09 ms / 516 tokens 4.51.043.971 I slot print_timing: id 1 | task 3806 | graphs reused = 3425 4.51.043.971 I slot print_timing: id 1 | task 3806 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.044.037 I slot release: id 1 | task 3806 | stop processing: n_tokens = 1630, truncated = 0 4.51.109.369 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.684 4.51.109.404 I slot launch_slot_: id 1 | task 4190 | processing task, is_child = 0 4.52.808.503 I slot print_timing: id 2 | task 3982 | n_gen = 241, tg = 24.15 t/s, tg_3s = 23.97 t/s 4.53.105.601 I slot print_timing: id 0 | task 4134 | prompt eval time = 275.09 ms / 91 tokens ( 3.02 ms per token, 330.80 tokens per second) 4.53.105.607 I slot print_timing: id 0 | task 4134 | eval time = 4186.06 ms / 99 tokens ( 42.71 ms per token, 23.41 tokens per second) 4.53.105.608 I slot print_timing: id 0 | task 4134 | total time = 4461.15 ms / 190 tokens 4.53.105.608 I slot print_timing: id 0 | task 4134 | graphs reused = 3468 4.53.105.609 I slot print_timing: id 0 | task 4134 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.105.678 I slot release: id 0 | task 4134 | stop processing: n_tokens = 1304, truncated = 0 4.53.146.225 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.855 4.53.146.251 I slot launch_slot_: id 0 | task 4238 | processing task, is_child = 0 4.53.459.649 I slot print_timing: id 3 | task 4138 | n_gen = 100, tg = 23.45 t/s, tg_3s = 23.69 t/s 4.55.375.526 I slot print_timing: id 1 | task 4190 | n_gen = 100, tg = 25.20 t/s, tg_3s = 25.46 t/s 4.55.828.310 I slot print_timing: id 2 | task 3982 | n_gen = 316, tg = 24.31 t/s, tg_3s = 24.84 t/s 4.56.468.761 I slot print_timing: id 3 | task 4138 | n_gen = 180, tg = 24.75 t/s, tg_3s = 26.59 t/s 4.57.142.235 I slot print_timing: id 0 | task 4238 | n_gen = 100, tg = 26.60 t/s, tg_3s = 26.87 t/s 4.57.145.291 I slot print_timing: id 2 | task 3982 | prompt eval time = 392.47 ms / 108 tokens ( 3.63 ms per token, 275.18 tokens per second) 4.57.145.293 I slot print_timing: id 2 | task 3982 | eval time = 14275.70 ms / 351 tokens ( 40.79 ms per token, 24.52 tokens per second) 4.57.145.298 I slot print_timing: id 2 | task 3982 | total time = 14668.17 ms / 459 tokens 4.57.145.299 I slot print_timing: id 2 | task 3982 | graphs reused = 3566 4.57.145.300 I slot print_timing: id 2 | task 3982 | graph reallocs = 0 / 0 (same size) / (changed size) 4.57.145.363 I slot release: id 2 | task 3982 | stop processing: n_tokens = 1573, truncated = 0 4.57.208.544 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.709 4.57.208.574 I slot launch_slot_: id 2 | task 4341 | processing task, is_child = 0 4.57.918.703 I slot print_timing: id 0 | task 4238 | prompt eval time = 273.71 ms / 78 tokens ( 3.51 ms per token, 284.97 tokens per second) 4.57.918.710 I slot print_timing: id 0 | task 4238 | eval time = 4498.73 ms / 113 tokens ( 40.17 ms per token, 24.90 tokens per second) 4.57.918.711 I slot print_timing: id 0 | task 4238 | total time = 4772.44 ms / 191 tokens 4.57.918.711 I slot print_timing: id 0 | task 4238 | graphs reused = 3575 4.57.918.712 I slot print_timing: id 0 | task 4238 | graph reallocs = 0 / 0 (same size) / (changed size) 4.57.918.786 I slot release: id 0 | task 4238 | stop processing: n_tokens = 1305, truncated = 0 4.57.959.367 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.854 4.57.959.393 I slot launch_slot_: id 0 | task 4355 | processing task, is_child = 0 4.58.402.140 I slot print_timing: id 1 | task 4190 | n_gen = 167, tg = 23.87 t/s, tg_3s = 22.14 t/s 4.58.706.286 I slot print_timing: id 3 | task 4138 | prompt eval time = 279.97 ms / 95 tokens ( 2.95 ms per token, 339.32 tokens per second) 4.58.706.290 I slot print_timing: id 3 | task 4138 | eval time = 9468.52 ms / 226 tokens ( 42.08 ms per token, 23.76 tokens per second) 4.58.706.291 I slot print_timing: id 3 | task 4138 | total time = 9748.49 ms / 321 tokens 4.58.706.292 I slot print_timing: id 3 | task 4138 | graphs reused = 3587 4.58.706.292 I slot print_timing: id 3 | task 4138 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.706.347 I slot release: id 3 | task 4138 | stop processing: n_tokens = 1435, truncated = 0 4.58.742.363 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.777 4.58.742.387 I slot launch_slot_: id 3 | task 4371 | processing task, is_child = 0 4.59.244.912 I slot print_timing: id 1 | task 4190 | prompt eval time = 338.09 ms / 98 tokens ( 3.45 ms per token, 289.87 tokens per second) 4.59.244.918 I slot print_timing: id 1 | task 4190 | eval time = 7797.41 ms / 184 tokens ( 42.61 ms per token, 23.47 tokens per second) 4.59.244.919 I slot print_timing: id 1 | task 4190 | total time = 8135.50 ms / 282 tokens 4.59.244.920 I slot print_timing: id 1 | task 4190 | graphs reused = 3592 4.59.244.920 I slot print_timing: id 1 | task 4190 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.244.989 I slot release: id 1 | task 4190 | stop processing: n_tokens = 1395, truncated = 0 4.59.311.425 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.799 4.59.311.453 I slot launch_slot_: id 1 | task 4381 | processing task, is_child = 0 5.01.974.139 I slot print_timing: id 2 | task 4341 | n_gen = 100, tg = 22.32 t/s, tg_3s = 22.55 t/s 5.02.425.672 I slot print_timing: id 3 | task 4371 | prompt eval time = 276.88 ms / 74 tokens ( 3.74 ms per token, 267.26 tokens per second) 5.02.425.676 I slot print_timing: id 3 | task 4371 | eval time = 3406.40 ms / 84 tokens ( 41.04 ms per token, 24.37 tokens per second) 5.02.425.677 I slot print_timing: id 3 | task 4371 | total time = 3683.28 ms / 158 tokens 5.02.425.678 I slot print_timing: id 3 | task 4371 | graphs reused = 3664 5.02.425.678 I slot print_timing: id 3 | task 4371 | graph reallocs = 0 / 0 (same size) / (changed size) 5.02.425.740 I slot release: id 3 | task 4371 | stop processing: n_tokens = 1272, truncated = 0 5.02.458.885 I slot print_timing: id 0 | task 4355 | n_gen = 100, tg = 23.48 t/s, tg_3s = 23.72 t/s 5.02.461.843 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.877 5.02.461.868 I slot launch_slot_: id 3 | task 4459 | processing task, is_child = 0 5.03.069.067 I slot print_timing: id 1 | task 4381 | prompt eval time = 329.84 ms / 75 tokens ( 4.40 ms per token, 227.39 tokens per second) 5.03.069.071 I slot print_timing: id 1 | task 4381 | eval time = 3427.77 ms / 84 tokens ( 41.30 ms per token, 24.21 tokens per second) 5.03.069.072 I slot print_timing: id 1 | task 4381 | total time = 3757.60 ms / 159 tokens 5.03.069.072 I slot print_timing: id 1 | task 4381 | graphs reused = 3669 5.03.069.073 I slot print_timing: id 1 | task 4381 | graph reallocs = 0 / 0 (same size) / (changed size) 5.03.069.134 I slot release: id 1 | task 4381 | stop processing: n_tokens = 1273, truncated = 0 5.03.134.927 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.876 5.03.134.965 I slot launch_slot_: id 1 | task 4469 | processing task, is_child = 0 5.04.233.020 I slot print_timing: id 0 | task 4355 | prompt eval time = 283.58 ms / 89 tokens ( 3.19 ms per token, 313.85 tokens per second) 5.04.233.027 I slot print_timing: id 0 | task 4355 | eval time = 5990.04 ms / 131 tokens ( 46.08 ms per token, 21.70 tokens per second) 5.04.233.028 I slot print_timing: id 0 | task 4355 | total time = 6273.62 ms / 220 tokens 5.04.233.028 I slot print_timing: id 0 | task 4355 | graphs reused = 3688 5.04.233.029 I slot print_timing: id 0 | task 4355 | graph reallocs = 0 / 0 (same size) / (changed size) 5.04.233.093 I slot release: id 0 | task 4355 | stop processing: n_tokens = 1334, truncated = 0 5.04.273.797 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.836 5.04.273.824 I slot launch_slot_: id 0 | task 4493 | processing task, is_child = 0 5.05.002.453 I slot print_timing: id 2 | task 4341 | n_gen = 159, tg = 21.17 t/s, tg_3s = 19.48 t/s 5.05.563.395 I slot print_timing: id 2 | task 4341 | prompt eval time = 330.51 ms / 95 tokens ( 3.48 ms per token, 287.43 tokens per second) 5.05.563.400 I slot print_timing: id 2 | task 4341 | eval time = 8024.30 ms / 174 tokens ( 46.38 ms per token, 21.56 tokens per second) 5.05.563.400 I slot print_timing: id 2 | task 4341 | total time = 8354.81 ms / 269 tokens 5.05.563.401 I slot print_timing: id 2 | task 4341 | graphs reused = 3715 5.05.563.402 I slot print_timing: id 2 | task 4341 | graph reallocs = 0 / 0 (same size) / (changed size) 5.05.563.459 I slot release: id 2 | task 4341 | stop processing: n_tokens = 1383, truncated = 0 5.05.627.155 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.806 5.05.627.181 I slot launch_slot_: id 2 | task 4524 | processing task, is_child = 0 5.07.365.212 I slot print_timing: id 3 | task 4459 | n_gen = 100, tg = 21.88 t/s, tg_3s = 22.10 t/s 5.07.699.790 I slot print_timing: id 1 | task 4469 | n_gen = 100, tg = 23.45 t/s, tg_3s = 23.69 t/s 5.08.556.220 I slot print_timing: id 0 | task 4493 | n_gen = 100, tg = 24.70 t/s, tg_3s = 24.95 t/s 5.09.683.858 I slot print_timing: id 2 | task 4524 | n_gen = 100, tg = 26.65 t/s, tg_3s = 26.92 t/s 5.10.283.265 I slot print_timing: id 0 | task 4493 | prompt eval time = 273.99 ms / 92 tokens ( 2.98 ms per token, 335.78 tokens per second) 5.10.283.269 I slot print_timing: id 0 | task 4493 | eval time = 5735.44 ms / 146 tokens ( 39.55 ms per token, 25.28 tokens per second) 5.10.283.270 I slot print_timing: id 0 | task 4493 | total time = 6009.43 ms / 238 tokens 5.10.283.271 I slot print_timing: id 0 | task 4493 | graphs reused = 3829 5.10.283.271 I slot print_timing: id 0 | task 4493 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.283.332 I slot release: id 0 | task 4493 | stop processing: n_tokens = 1352, truncated = 0 5.10.323.962 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.825 5.10.323.993 I slot launch_slot_: id 0 | task 4643 | processing task, is_child = 0 5.10.534.691 I slot print_timing: id 3 | task 4459 | n_gen = 180, tg = 23.27 t/s, tg_3s = 25.24 t/s 5.10.711.818 I slot print_timing: id 1 | task 4469 | n_gen = 175, tg = 24.06 t/s, tg_3s = 24.90 t/s 5.10.944.563 I slot print_timing: id 2 | task 4524 | prompt eval time = 341.34 ms / 80 tokens ( 4.27 ms per token, 234.37 tokens per second) 5.10.944.569 I slot print_timing: id 2 | task 4524 | eval time = 4976.03 ms / 128 tokens ( 39.18 ms per token, 25.52 tokens per second) 5.10.944.570 I slot print_timing: id 2 | task 4524 | total time = 5317.37 ms / 208 tokens 5.10.944.571 I slot print_timing: id 2 | task 4524 | graphs reused = 3838 5.10.944.571 I slot print_timing: id 2 | task 4524 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.944.629 I slot release: id 2 | task 4524 | stop processing: n_tokens = 1322, truncated = 0 5.11.008.062 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.843 5.11.008.087 I slot launch_slot_: id 2 | task 4656 | processing task, is_child = 0 5.12.097.785 I slot print_timing: id 1 | task 4469 | prompt eval time = 343.83 ms / 96 tokens ( 3.58 ms per token, 279.21 tokens per second) 5.12.097.791 I slot print_timing: id 1 | task 4469 | eval time = 8618.98 ms / 205 tokens ( 42.25 ms per token, 23.67 tokens per second) 5.12.097.791 I slot print_timing: id 1 | task 4469 | total time = 8962.81 ms / 301 tokens 5.12.097.792 I slot print_timing: id 1 | task 4469 | graphs reused = 3858 5.12.097.793 I slot print_timing: id 1 | task 4469 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.097.854 I slot release: id 1 | task 4469 | stop processing: n_tokens = 1414, truncated = 0 5.12.163.275 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.789 5.12.163.304 I slot launch_slot_: id 1 | task 4681 | processing task, is_child = 0 5.13.565.439 I slot print_timing: id 3 | task 4459 | n_gen = 244, tg = 22.66 t/s, tg_3s = 21.12 t/s 5.14.916.988 I slot print_timing: id 0 | task 4643 | n_gen = 100, tg = 22.94 t/s, tg_3s = 23.17 t/s 5.15.369.479 I slot print_timing: id 2 | task 4656 | n_gen = 100, tg = 24.34 t/s, tg_3s = 24.59 t/s 5.15.745.930 I slot print_timing: id 3 | task 4459 | prompt eval time = 379.22 ms / 151 tokens ( 2.51 ms per token, 398.18 tokens per second) 5.15.745.933 I slot print_timing: id 3 | task 4459 | eval time = 12904.83 ms / 302 tokens ( 42.87 ms per token, 23.32 tokens per second) 5.15.745.934 I slot print_timing: id 3 | task 4459 | total time = 13284.05 ms / 453 tokens 5.15.745.935 I slot print_timing: id 3 | task 4459 | graphs reused = 3941 5.15.745.935 I slot print_timing: id 3 | task 4459 | graph reallocs = 0 / 0 (same size) / (changed size) 5.15.746.005 I slot release: id 3 | task 4459 | stop processing: n_tokens = 1567, truncated = 0 5.15.781.945 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.712 5.15.781.973 I slot launch_slot_: id 3 | task 4770 | processing task, is_child = 0 5.16.204.660 I slot print_timing: id 2 | task 4656 | prompt eval time = 294.04 ms / 63 tokens ( 4.67 ms per token, 214.25 tokens per second) 5.16.204.664 I slot print_timing: id 2 | task 4656 | eval time = 4902.52 ms / 118 tokens ( 41.90 ms per token, 23.87 tokens per second) 5.16.204.665 I slot print_timing: id 2 | task 4656 | total time = 5196.56 ms / 181 tokens 5.16.204.666 I slot print_timing: id 2 | task 4656 | graphs reused = 3945 5.16.204.666 I slot print_timing: id 2 | task 4656 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.204.726 I slot release: id 2 | task 4656 | stop processing: n_tokens = 1295, truncated = 0 5.16.269.302 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.861 5.16.269.329 I slot launch_slot_: id 2 | task 4779 | processing task, is_child = 0 5.16.767.422 I slot print_timing: id 1 | task 4681 | n_gen = 100, tg = 23.44 t/s, tg_3s = 23.67 t/s 5.17.106.930 I slot print_timing: id 0 | task 4643 | prompt eval time = 276.49 ms / 95 tokens ( 2.91 ms per token, 343.59 tokens per second) 5.17.106.935 I slot print_timing: id 0 | task 4643 | eval time = 6506.44 ms / 145 tokens ( 45.18 ms per token, 22.13 tokens per second) 5.17.106.935 I slot print_timing: id 0 | task 4643 | total time = 6782.93 ms / 240 tokens 5.17.106.936 I slot print_timing: id 0 | task 4643 | graphs reused = 3956 5.17.106.937 I slot print_timing: id 0 | task 4643 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.107.012 I slot release: id 0 | task 4643 | stop processing: n_tokens = 1354, truncated = 0 5.17.147.633 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.823 5.17.147.656 I slot launch_slot_: id 0 | task 4795 | processing task, is_child = 0 5.18.781.242 I slot print_timing: id 1 | task 4681 | prompt eval time = 379.95 ms / 105 tokens ( 3.62 ms per token, 276.35 tokens per second) 5.18.781.245 I slot print_timing: id 1 | task 4681 | eval time = 6237.98 ms / 148 tokens ( 42.44 ms per token, 23.57 tokens per second) 5.18.781.246 I slot print_timing: id 1 | task 4681 | total time = 6617.93 ms / 253 tokens 5.18.781.247 I slot print_timing: id 1 | task 4681 | graphs reused = 3992 5.18.781.247 I slot print_timing: id 1 | task 4681 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.781.305 I slot release: id 1 | task 4681 | stop processing: n_tokens = 1367, truncated = 0 5.18.846.621 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.816 5.18.846.653 I slot launch_slot_: id 1 | task 4835 | processing task, is_child = 0 5.20.234.187 I slot print_timing: id 3 | task 4770 | prompt eval time = 234.77 ms / 62 tokens ( 3.79 ms per token, 264.09 tokens per second) 5.20.234.192 I slot print_timing: id 3 | task 4770 | eval time = 4217.44 ms / 91 tokens ( 46.86 ms per token, 21.34 tokens per second) 5.20.234.193 I slot print_timing: id 3 | task 4770 | total time = 4452.21 ms / 153 tokens 5.20.234.193 I slot print_timing: id 3 | task 4770 | graphs reused = 4019 5.20.234.194 I slot print_timing: id 3 | task 4770 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.234.252 I slot release: id 3 | task 4770 | stop processing: n_tokens = 1267, truncated = 0 5.20.270.285 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.880 5.20.270.309 I slot launch_slot_: id 3 | task 4867 | processing task, is_child = 0 5.21.128.292 I slot print_timing: id 2 | task 4779 | n_gen = 100, tg = 22.11 t/s, tg_3s = 22.33 t/s 5.21.688.047 I slot print_timing: id 0 | task 4795 | n_gen = 100, tg = 23.22 t/s, tg_3s = 23.46 t/s 5.23.150.788 I slot print_timing: id 1 | task 4835 | n_gen = 100, tg = 24.91 t/s, tg_3s = 25.16 t/s 5.24.165.120 I slot print_timing: id 2 | task 4779 | n_gen = 181, tg = 23.95 t/s, tg_3s = 26.67 t/s 5.24.315.546 I slot print_timing: id 3 | task 4867 | n_gen = 100, tg = 26.64 t/s, tg_3s = 26.90 t/s 5.24.723.036 I slot print_timing: id 0 | task 4795 | n_gen = 181, tg = 24.66 t/s, tg_3s = 26.69 t/s 5.24.726.076 I slot print_timing: id 2 | task 4779 | prompt eval time = 381.40 ms / 133 tokens ( 2.87 ms per token, 348.71 tokens per second) 5.24.726.079 I slot print_timing: id 2 | task 4779 | eval time = 8075.33 ms / 196 tokens ( 41.41 ms per token, 24.15 tokens per second) 5.24.726.080 I slot print_timing: id 2 | task 4779 | total time = 8456.74 ms / 329 tokens 5.24.726.081 I slot print_timing: id 2 | task 4779 | graphs reused = 4128 5.24.726.081 I slot print_timing: id 2 | task 4779 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.726.140 I slot release: id 2 | task 4779 | stop processing: n_tokens = 1443, truncated = 0 5.24.789.665 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.773 5.24.789.690 I slot launch_slot_: id 2 | task 4981 | processing task, is_child = 0 5.25.801.228 I slot print_timing: id 0 | task 4795 | prompt eval time = 277.37 ms / 94 tokens ( 2.95 ms per token, 338.90 tokens per second) 5.25.801.232 I slot print_timing: id 0 | task 4795 | eval time = 8376.19 ms / 203 tokens ( 41.47 ms per token, 24.12 tokens per second) 5.25.801.233 I slot print_timing: id 0 | task 4795 | total time = 8653.56 ms / 297 tokens 5.25.801.233 I slot print_timing: id 0 | task 4795 | graphs reused = 4146 5.25.801.234 I slot print_timing: id 0 | task 4795 | graph reallocs = 0 / 0 (same size) / (changed size) 5.25.801.305 I slot release: id 0 | task 4795 | stop processing: n_tokens = 1411, truncated = 0 5.25.841.986 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.790 5.25.842.011 I slot launch_slot_: id 0 | task 5004 | processing task, is_child = 0 5.26.153.546 I slot print_timing: id 1 | task 4835 | n_gen = 168, tg = 23.93 t/s, tg_3s = 22.65 t/s 5.26.762.995 I slot print_timing: id 3 | task 4867 | prompt eval time = 328.40 ms / 110 tokens ( 2.99 ms per token, 334.96 tokens per second) 5.26.763.002 I slot print_timing: id 3 | task 4867 | eval time = 6164.28 ms / 153 tokens ( 40.55 ms per token, 24.66 tokens per second) 5.26.763.003 I slot print_timing: id 3 | task 4867 | total time = 6492.68 ms / 263 tokens 5.26.763.004 I slot print_timing: id 3 | task 4867 | graphs reused = 4163 5.26.763.004 I slot print_timing: id 3 | task 4867 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.763.061 I slot release: id 3 | task 4867 | stop processing: n_tokens = 1377, truncated = 0 5.26.799.395 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.810 5.26.799.424 I slot launch_slot_: id 3 | task 5025 | processing task, is_child = 0 5.28.742.047 I slot print_timing: id 2 | task 4981 | prompt eval time = 293.79 ms / 68 tokens ( 4.32 ms per token, 231.46 tokens per second) 5.28.742.051 I slot print_timing: id 2 | task 4981 | eval time = 3658.56 ms / 86 tokens ( 43.04 ms per token, 23.23 tokens per second) 5.28.742.051 I slot print_timing: id 2 | task 4981 | total time = 3952.35 ms / 154 tokens 5.28.742.052 I slot print_timing: id 2 | task 4981 | graphs reused = 4205 5.28.742.053 I slot print_timing: id 2 | task 4981 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.742.110 I slot release: id 2 | task 4981 | stop processing: n_tokens = 1268, truncated = 0 5.28.805.619 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.879 5.28.805.645 I slot launch_slot_: id 2 | task 5072 | processing task, is_child = 0 5.29.181.883 I slot print_timing: id 1 | task 4835 | n_gen = 234, tg = 23.29 t/s, tg_3s = 21.79 t/s 5.30.311.812 I slot print_timing: id 1 | task 4835 | prompt eval time = 329.30 ms / 85 tokens ( 3.87 ms per token, 258.13 tokens per second) 5.30.311.816 I slot print_timing: id 1 | task 4835 | eval time = 11135.85 ms / 264 tokens ( 42.34 ms per token, 23.62 tokens per second) 5.30.311.817 I slot print_timing: id 1 | task 4835 | total time = 11465.15 ms / 349 tokens 5.30.311.818 I slot print_timing: id 1 | task 4835 | graphs reused = 4235 5.30.311.818 I slot print_timing: id 1 | task 4835 | graph reallocs = 0 / 0 (same size) / (changed size) 5.30.311.881 I slot release: id 1 | task 4835 | stop processing: n_tokens = 1463, truncated = 0 5.30.377.209 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 5.30.377.242 I slot launch_slot_: id 1 | task 5107 | processing task, is_child = 0 5.30.608.836 I slot print_timing: id 0 | task 5004 | n_gen = 100, tg = 22.04 t/s, tg_3s = 22.26 t/s 5.31.307.909 I slot print_timing: id 0 | task 5004 | prompt eval time = 274.04 ms / 100 tokens ( 2.74 ms per token, 364.91 tokens per second) 5.31.307.915 I slot print_timing: id 0 | task 5004 | eval time = 5191.85 ms / 117 tokens ( 44.76 ms per token, 22.34 tokens per second) 5.31.307.916 I slot print_timing: id 0 | task 5004 | total time = 5465.89 ms / 217 tokens 5.31.307.917 I slot print_timing: id 0 | task 5004 | graphs reused = 4250 5.31.307.917 I slot print_timing: id 0 | task 5004 | graph reallocs = 0 / 0 (same size) / (changed size) 5.31.307.981 I slot release: id 0 | task 5004 | stop processing: n_tokens = 1331, truncated = 0 5.31.348.632 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.838 5.31.348.655 I slot launch_slot_: id 0 | task 5127 | processing task, is_child = 0 5.31.627.203 I slot print_timing: id 3 | task 5025 | n_gen = 100, tg = 21.99 t/s, tg_3s = 22.21 t/s 5.33.355.562 I slot print_timing: id 2 | task 5072 | n_gen = 100, tg = 23.50 t/s, tg_3s = 23.74 t/s 5.34.632.715 I slot print_timing: id 1 | task 5107 | n_gen = 100, tg = 25.20 t/s, tg_3s = 25.46 t/s 5.34.635.661 I slot print_timing: id 3 | task 5025 | n_gen = 180, tg = 23.83 t/s, tg_3s = 26.59 t/s 5.35.345.640 I slot print_timing: id 0 | task 5127 | n_gen = 100, tg = 26.60 t/s, tg_3s = 26.87 t/s 5.35.798.732 I slot print_timing: id 1 | task 5107 | prompt eval time = 327.13 ms / 73 tokens ( 4.48 ms per token, 223.15 tokens per second) 5.35.798.736 I slot print_timing: id 1 | task 5107 | eval time = 5094.35 ms / 131 tokens ( 39.19 ms per token, 25.52 tokens per second) 5.35.798.736 I slot print_timing: id 1 | task 5107 | total time = 5421.48 ms / 204 tokens 5.35.798.737 I slot print_timing: id 1 | task 5107 | graphs reused = 4361 5.35.798.738 I slot print_timing: id 1 | task 5107 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.798.797 I slot release: id 1 | task 5107 | stop processing: n_tokens = 1318, truncated = 0 5.35.864.313 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.846 5.35.864.357 I slot launch_slot_: id 1 | task 5242 | processing task, is_child = 0 5.36.356.819 I slot print_timing: id 2 | task 5072 | n_gen = 171, tg = 23.57 t/s, tg_3s = 23.66 t/s 5.37.641.219 I slot print_timing: id 3 | task 5025 | n_gen = 251, tg = 23.77 t/s, tg_3s = 23.62 t/s 5.38.349.012 I slot print_timing: id 0 | task 5127 | n_gen = 171, tg = 25.28 t/s, tg_3s = 23.64 t/s 5.39.368.520 I slot print_timing: id 2 | task 5072 | n_gen = 251, tg = 24.45 t/s, tg_3s = 26.56 t/s 5.39.784.305 I slot print_timing: id 2 | task 5072 | prompt eval time = 337.56 ms / 70 tokens ( 4.82 ms per token, 207.37 tokens per second) 5.39.784.311 I slot print_timing: id 2 | task 5072 | eval time = 10641.08 ms / 262 tokens ( 40.77 ms per token, 24.53 tokens per second) 5.39.784.312 I slot print_timing: id 2 | task 5072 | total time = 10978.65 ms / 332 tokens 5.39.784.312 I slot print_timing: id 2 | task 5072 | graphs reused = 4454 5.39.784.313 I slot print_timing: id 2 | task 5072 | graph reallocs = 0 / 0 (same size) / (changed size) 5.39.784.374 I slot release: id 2 | task 5072 | stop processing: n_tokens = 1446, truncated = 0 5.39.847.923 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.771 5.39.847.947 I slot launch_slot_: id 2 | task 5340 | processing task, is_child = 0 5.40.254.623 I slot print_timing: id 1 | task 5242 | n_gen = 100, tg = 24.67 t/s, tg_3s = 24.92 t/s 5.40.641.575 I slot print_timing: id 3 | task 5025 | n_gen = 323, tg = 23.82 t/s, tg_3s = 24.00 t/s 5.41.352.184 I slot print_timing: id 0 | task 5127 | n_gen = 243, tg = 24.88 t/s, tg_3s = 23.97 t/s 5.42.027.594 I slot print_timing: id 0 | task 5127 | prompt eval time = 275.31 ms / 91 tokens ( 3.03 ms per token, 330.54 tokens per second) 5.42.027.600 I slot print_timing: id 0 | task 5127 | eval time = 10403.62 ms / 261 tokens ( 40.01 ms per token, 24.99 tokens per second) 5.42.027.601 I slot print_timing: id 0 | task 5127 | total time = 10678.93 ms / 352 tokens 5.42.027.601 I slot print_timing: id 0 | task 5127 | graphs reused = 4501 5.42.027.602 I slot print_timing: id 0 | task 5127 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.027.667 I slot release: id 0 | task 5127 | stop processing: n_tokens = 1466, truncated = 0 5.42.068.779 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.761 5.42.068.806 I slot launch_slot_: id 0 | task 5393 | processing task, is_child = 0 5.43.260.167 I slot print_timing: id 1 | task 5242 | n_gen = 174, tg = 24.65 t/s, tg_3s = 24.62 t/s 5.43.677.185 I slot print_timing: id 3 | task 5025 | n_gen = 398, tg = 23.99 t/s, tg_3s = 24.71 t/s 5.44.128.393 I slot print_timing: id 2 | task 5340 | n_gen = 100, tg = 25.06 t/s, tg_3s = 25.31 t/s 5.44.916.468 I slot print_timing: id 1 | task 5242 | prompt eval time = 377.58 ms / 105 tokens ( 3.60 ms per token, 278.09 tokens per second) 5.44.916.473 I slot print_timing: id 1 | task 5242 | eval time = 8674.52 ms / 218 tokens ( 39.97 ms per token, 25.02 tokens per second) 5.44.916.474 I slot print_timing: id 1 | task 5242 | total time = 9052.10 ms / 323 tokens 5.44.916.474 I slot print_timing: id 1 | task 5242 | graphs reused = 4569 5.44.916.475 I slot print_timing: id 1 | task 5242 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.916.537 I slot release: id 1 | task 5242 | stop processing: n_tokens = 1437, truncated = 0 5.44.980.233 I slot print_timing: id 2 | task 5340 | prompt eval time = 329.45 ms / 79 tokens ( 4.17 ms per token, 239.79 tokens per second) 5.44.980.240 I slot print_timing: id 2 | task 5340 | eval time = 4802.83 ms / 122 tokens ( 39.69 ms per token, 25.19 tokens per second) 5.44.980.240 I slot print_timing: id 2 | task 5340 | total time = 5132.28 ms / 201 tokens 5.44.980.241 I slot print_timing: id 2 | task 5340 | graphs reused = 4569 5.44.980.241 I slot print_timing: id 2 | task 5340 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.980.307 I slot release: id 2 | task 5340 | stop processing: n_tokens = 1315, truncated = 0 5.44.981.902 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.776 5.44.981.932 I slot launch_slot_: id 1 | task 5465 | processing task, is_child = 0 5.45.013.840 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.848 5.45.013.868 I slot launch_slot_: id 2 | task 5466 | processing task, is_child = 0 5.46.609.584 I slot print_timing: id 0 | task 5393 | n_gen = 100, tg = 23.22 t/s, tg_3s = 23.45 t/s 5.46.689.652 I slot print_timing: id 3 | task 5025 | n_gen = 464, tg = 23.67 t/s, tg_3s = 21.91 t/s 5.49.276.339 I slot print_timing: id 1 | task 5465 | n_gen = 100, tg = 26.58 t/s, tg_3s = 26.85 t/s 5.49.277.803 I slot print_timing: id 2 | task 5466 | n_gen = 100, tg = 26.58 t/s, tg_3s = 26.85 t/s 5.49.612.201 I slot print_timing: id 0 | task 5393 | n_gen = 180, tg = 24.63 t/s, tg_3s = 26.64 t/s 5.49.691.657 I slot print_timing: id 3 | task 5025 | n_gen = 544, tg = 24.06 t/s, tg_3s = 26.65 t/s 5.49.915.586 I slot print_timing: id 2 | task 5466 | prompt eval time = 537.60 ms / 98 tokens ( 5.49 ms per token, 182.29 tokens per second) 5.49.915.590 I slot print_timing: id 2 | task 5466 | eval time = 4361.90 ms / 117 tokens ( 37.60 ms per token, 26.59 tokens per second) 5.49.915.591 I slot print_timing: id 2 | task 5466 | total time = 4899.49 ms / 215 tokens 5.49.915.591 I slot print_timing: id 2 | task 5466 | graphs reused = 4684 5.49.915.592 I slot print_timing: id 2 | task 5466 | graph reallocs = 0 / 0 (same size) / (changed size) 5.49.915.654 I slot release: id 2 | task 5466 | stop processing: n_tokens = 1329, truncated = 0 5.49.979.233 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.839 5.49.979.259 I slot launch_slot_: id 2 | task 5586 | processing task, is_child = 0 5.52.283.859 I slot print_timing: id 1 | task 5465 | n_gen = 172, tg = 25.40 t/s, tg_3s = 23.94 t/s 5.52.621.315 I slot print_timing: id 0 | task 5393 | n_gen = 252, tg = 24.43 t/s, tg_3s = 23.93 t/s 5.52.701.799 I slot print_timing: id 3 | task 5025 | n_gen = 616, tg = 24.05 t/s, tg_3s = 23.92 t/s 5.53.788.608 I slot print_timing: id 0 | task 5393 | prompt eval time = 277.12 ms / 97 tokens ( 2.86 ms per token, 350.03 tokens per second) 5.53.788.617 I slot print_timing: id 0 | task 5393 | eval time = 11442.67 ms / 283 tokens ( 40.58 ms per token, 24.64 tokens per second) 5.53.788.617 I slot print_timing: id 0 | task 5393 | total time = 11719.79 ms / 380 tokens 5.53.788.618 I slot print_timing: id 0 | task 5393 | graphs reused = 4774 5.53.788.620 I slot print_timing: id 0 | task 5393 | graph reallocs = 0 / 0 (same size) / (changed size) 5.53.788.686 I slot release: id 0 | task 5393 | stop processing: n_tokens = 1494, truncated = 0 5.53.829.501 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.746 5.53.829.533 I slot launch_slot_: id 0 | task 5682 | processing task, is_child = 0 5.54.253.559 I slot print_timing: id 2 | task 5586 | n_gen = 100, tg = 25.17 t/s, tg_3s = 25.42 t/s 5.55.310.155 I slot print_timing: id 1 | task 5465 | n_gen = 247, tg = 25.21 t/s, tg_3s = 24.78 t/s 5.55.727.633 I slot print_timing: id 3 | task 5025 | n_gen = 691, tg = 24.12 t/s, tg_3s = 24.79 t/s 5.57.274.969 I slot print_timing: id 2 | task 5586 | n_gen = 180, tg = 25.74 t/s, tg_3s = 26.48 t/s 5.57.614.426 I slot print_timing: id 2 | task 5586 | prompt eval time = 341.05 ms / 93 tokens ( 3.67 ms per token, 272.69 tokens per second) 5.57.614.429 I slot print_timing: id 2 | task 5586 | eval time = 7294.11 ms / 189 tokens ( 38.80 ms per token, 25.77 tokens per second) 5.57.614.430 I slot print_timing: id 2 | task 5586 | total time = 7635.16 ms / 282 tokens 5.57.614.431 I slot print_timing: id 2 | task 5586 | graphs reused = 4867 5.57.614.431 I slot print_timing: id 2 | task 5586 | graph reallocs = 0 / 0 (same size) / (changed size) 5.57.614.493 I slot release: id 2 | task 5586 | stop processing: n_tokens = 1396, truncated = 0 5.57.678.189 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.799 5.57.678.218 I slot launch_slot_: id 2 | task 5779 | processing task, is_child = 0 5.58.116.936 I slot print_timing: id 0 | task 5682 | n_gen = 100, tg = 24.65 t/s, tg_3s = 24.90 t/s 5.58.310.579 I slot print_timing: id 1 | task 5465 | n_gen = 319, tg = 24.92 t/s, tg_3s = 24.00 t/s 5.58.728.609 I slot print_timing: id 3 | task 5025 | n_gen = 763, tg = 24.11 t/s, tg_3s = 23.99 t/s 5.59.479.944 I slot print_timing: id 0 | task 5682 | prompt eval time = 270.62 ms / 76 tokens ( 3.56 ms per token, 280.84 tokens per second) 5.59.479.951 I slot print_timing: id 0 | task 5682 | eval time = 5379.79 ms / 136 tokens ( 39.85 ms per token, 25.09 tokens per second) 5.59.479.952 I slot print_timing: id 0 | task 5682 | total time = 5650.40 ms / 212 tokens 5.59.479.952 I slot print_timing: id 0 | task 5682 | graphs reused = 4905 5.59.479.953 I slot print_timing: id 0 | task 5682 | graph reallocs = 0 / 0 (same size) / (changed size) 5.59.480.020 I slot release: id 0 | task 5682 | stop processing: n_tokens = 1326, truncated = 0 5.59.520.604 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.841 5.59.520.630 I slot launch_slot_: id 0 | task 5822 | processing task, is_child = 0 6.01.326.375 I slot print_timing: id 1 | task 5465 | n_gen = 392, tg = 24.79 t/s, tg_3s = 24.21 t/s 6.01.748.127 I slot print_timing: id 3 | task 5025 | n_gen = 836, tg = 24.12 t/s, tg_3s = 24.18 t/s 6.02.013.301 I slot print_timing: id 2 | task 5779 | n_gen = 100, tg = 24.70 t/s, tg_3s = 24.95 t/s 6.02.847.204 I slot print_timing: id 2 | task 5779 | prompt eval time = 327.46 ms / 71 tokens ( 4.61 ms per token, 216.82 tokens per second) 6.02.847.210 I slot print_timing: id 2 | task 5779 | eval time = 4841.52 ms / 122 tokens ( 40.01 ms per token, 24.99 tokens per second) 6.02.847.210 I slot print_timing: id 2 | task 5779 | total time = 5168.98 ms / 193 tokens 6.02.847.211 I slot print_timing: id 2 | task 5779 | graphs reused = 4983 6.02.847.212 I slot print_timing: id 2 | task 5779 | graph reallocs = 0 / 0 (same size) / (changed size) 6.02.847.273 I slot release: id 2 | task 5779 | stop processing: n_tokens = 1307, truncated = 0 6.02.911.554 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.853 6.02.911.592 I slot launch_slot_: id 2 | task 5905 | processing task, is_child = 0 6.03.850.001 I slot print_timing: id 0 | task 5822 | n_gen = 100, tg = 24.74 t/s, tg_3s = 24.99 t/s 6.04.345.765 I slot print_timing: id 1 | task 5465 | n_gen = 465, tg = 24.69 t/s, tg_3s = 24.18 t/s 6.04.766.081 I slot print_timing: id 3 | task 5025 | n_gen = 909, tg = 24.12 t/s, tg_3s = 24.19 t/s 6.05.752.314 I slot print_timing: id 2 | task 5905 | prompt eval time = 287.23 ms / 64 tokens ( 4.49 ms per token, 222.82 tokens per second) 6.05.752.321 I slot print_timing: id 2 | task 5905 | eval time = 2553.48 ms / 68 tokens ( 38.11 ms per token, 26.24 tokens per second) 6.05.752.323 I slot print_timing: id 2 | task 5905 | total time = 2840.72 ms / 132 tokens 6.05.752.324 I slot print_timing: id 2 | task 5905 | graphs reused = 5049 6.05.752.324 I slot print_timing: id 2 | task 5905 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.752.382 I slot release: id 2 | task 5905 | stop processing: n_tokens = 1246, truncated = 0 6.05.816.255 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.895 6.05.816.282 I slot launch_slot_: id 2 | task 5976 | processing task, is_child = 0 6.06.880.170 I slot print_timing: id 0 | task 5822 | n_gen = 172, tg = 24.32 t/s, tg_3s = 23.76 t/s 6.07.375.472 I slot print_timing: id 1 | task 5465 | n_gen = 537, tg = 24.56 t/s, tg_3s = 23.76 t/s 6.07.795.058 I slot print_timing: id 3 | task 5025 | n_gen = 981, tg = 24.10 t/s, tg_3s = 23.77 t/s 6.09.425.934 I slot print_timing: id 3 | task 5025 | prompt eval time = 326.11 ms / 106 tokens ( 3.08 ms per token, 325.04 tokens per second) 6.09.425.941 I slot print_timing: id 3 | task 5025 | eval time = 42300.39 ms / 1024 tokens ( 41.35 ms per token, 24.18 tokens per second) 6.09.425.942 I slot print_timing: id 3 | task 5025 | total time = 42626.50 ms / 1130 tokens 6.09.425.942 I slot print_timing: id 3 | task 5025 | graphs reused = 5134 6.09.425.943 I slot print_timing: id 3 | task 5025 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.426.008 I slot release: id 3 | task 5025 | stop processing: n_tokens = 2244, truncated = 0 6.09.462.075 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.497 6.09.497.510 I slot launch_slot_: id 3 | task 6066 | processing task, is_child = 0 6.09.893.354 I slot print_timing: id 0 | task 5822 | n_gen = 245, tg = 24.29 t/s, tg_3s = 24.23 t/s 6.10.162.975 I slot print_timing: id 2 | task 5976 | n_gen = 100, tg = 24.70 t/s, tg_3s = 24.95 t/s 6.10.386.526 I slot print_timing: id 1 | task 5465 | n_gen = 610, tg = 24.52 t/s, tg_3s = 24.24 t/s 6.12.226.107 I slot print_timing: id 0 | task 5822 | prompt eval time = 327.03 ms / 127 tokens ( 2.58 ms per token, 388.34 tokens per second) 6.12.226.111 I slot print_timing: id 0 | task 5822 | eval time = 12378.44 ms / 307 tokens ( 40.45 ms per token, 24.72 tokens per second) 6.12.226.111 I slot print_timing: id 0 | task 5822 | total time = 12705.47 ms / 434 tokens 6.12.226.112 I slot print_timing: id 0 | task 5822 | graphs reused = 5198 6.12.226.113 I slot print_timing: id 0 | task 5822 | graph reallocs = 0 / 0 (same size) / (changed size) 6.12.226.177 I slot release: id 0 | task 5822 | stop processing: n_tokens = 1548, truncated = 0 6.12.266.896 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.720 6.12.266.922 I slot launch_slot_: id 0 | task 6135 | processing task, is_child = 0 6.13.169.674 I slot print_timing: id 2 | task 5976 | n_gen = 174, tg = 24.66 t/s, tg_3s = 24.61 t/s 6.13.243.062 I slot print_timing: id 1 | task 5465 | prompt eval time = 538.42 ms / 108 tokens ( 4.99 ms per token, 200.59 tokens per second) 6.13.243.065 I slot print_timing: id 1 | task 5465 | eval time = 27690.77 ms / 680 tokens ( 40.78 ms per token, 24.52 tokens per second) 6.13.243.066 I slot print_timing: id 1 | task 5465 | total time = 28229.18 ms / 788 tokens 6.13.243.066 I slot print_timing: id 1 | task 5465 | graphs reused = 5216 6.13.243.067 I slot print_timing: id 1 | task 5465 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.243.127 I slot release: id 1 | task 5465 | stop processing: n_tokens = 1902, truncated = 0 6.13.308.338 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.586 6.13.308.366 I slot launch_slot_: id 1 | task 6157 | processing task, is_child = 0 6.14.034.110 I slot print_timing: id 3 | task 6066 | n_gen = 100, tg = 23.29 t/s, tg_3s = 23.53 t/s 6.14.071.331 I slot print_timing: id 3 | task 6066 | prompt eval time = 286.56 ms / 70 tokens ( 4.09 ms per token, 244.27 tokens per second) 6.14.071.334 I slot print_timing: id 3 | task 6066 | eval time = 4287.24 ms / 101 tokens ( 42.87 ms per token, 23.33 tokens per second) 6.14.071.335 I slot print_timing: id 3 | task 6066 | total time = 4573.81 ms / 171 tokens 6.14.071.336 I slot print_timing: id 3 | task 6066 | graphs reused = 5226 6.14.071.336 I slot print_timing: id 3 | task 6066 | graph reallocs = 0 / 0 (same size) / (changed size) 6.14.071.402 I slot release: id 3 | task 6066 | stop processing: n_tokens = 1284, truncated = 0 6.14.107.304 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.868 6.14.107.330 I slot launch_slot_: id 3 | task 6172 | processing task, is_child = 0 6.15.731.568 I slot print_timing: id 2 | task 5976 | prompt eval time = 339.33 ms / 74 tokens ( 4.59 ms per token, 218.08 tokens per second) 6.15.731.571 I slot print_timing: id 2 | task 5976 | eval time = 9575.95 ms / 230 tokens ( 41.82 ms per token, 23.91 tokens per second) 6.15.731.573 I slot print_timing: id 2 | task 5976 | total time = 9915.27 ms / 304 tokens 6.15.731.573 I slot print_timing: id 2 | task 5976 | graphs reused = 5262 6.15.731.574 I slot print_timing: id 2 | task 5976 | graph reallocs = 0 / 0 (same size) / (changed size) 6.15.731.640 I slot release: id 2 | task 5976 | stop processing: n_tokens = 1418, truncated = 0 6.15.794.866 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.786 6.15.794.894 I slot launch_slot_: id 2 | task 6213 | processing task, is_child = 0 6.17.123.269 I slot print_timing: id 0 | task 6135 | n_gen = 100, tg = 21.67 t/s, tg_3s = 21.89 t/s 6.17.389.956 I slot print_timing: id 3 | task 6172 | prompt eval time = 238.78 ms / 65 tokens ( 3.67 ms per token, 272.21 tokens per second) 6.17.389.959 I slot print_timing: id 3 | task 6172 | eval time = 3043.83 ms / 72 tokens ( 42.87 ms per token, 23.33 tokens per second) 6.17.389.960 I slot print_timing: id 3 | task 6172 | total time = 3282.62 ms / 137 tokens 6.17.389.961 I slot print_timing: id 3 | task 6172 | graphs reused = 5291 6.17.389.962 I slot print_timing: id 3 | task 6172 | graph reallocs = 0 / 0 (same size) / (changed size) 6.17.390.019 I slot release: id 3 | task 6172 | stop processing: n_tokens = 1251, truncated = 0 6.17.426.042 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.891 6.17.426.065 I slot launch_slot_: id 3 | task 6248 | processing task, is_child = 0 6.18.119.115 I slot print_timing: id 1 | task 6157 | n_gen = 100, tg = 22.16 t/s, tg_3s = 22.38 t/s 6.18.492.980 I slot print_timing: id 0 | task 6135 | prompt eval time = 287.45 ms / 88 tokens ( 3.27 ms per token, 306.14 tokens per second) 6.18.492.987 I slot print_timing: id 0 | task 6135 | eval time = 5938.60 ms / 131 tokens ( 45.68 ms per token, 21.89 tokens per second) 6.18.492.988 I slot print_timing: id 0 | task 6135 | total time = 6226.05 ms / 219 tokens 6.18.492.989 I slot print_timing: id 0 | task 6135 | graphs reused = 5311 6.18.492.989 I slot print_timing: id 0 | task 6135 | graph reallocs = 0 / 0 (same size) / (changed size) 6.18.493.059 I slot release: id 0 | task 6135 | stop processing: n_tokens = 1333, truncated = 0 6.18.533.581 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.836 6.18.533.605 I slot launch_slot_: id 0 | task 6273 | processing task, is_child = 0 6.20.398.998 I slot print_timing: id 2 | task 6213 | n_gen = 100, tg = 23.70 t/s, tg_3s = 23.94 t/s 6.21.147.243 I slot print_timing: id 1 | task 6157 | n_gen = 174, tg = 23.08 t/s, tg_3s = 24.44 t/s 6.21.676.601 I slot print_timing: id 3 | task 6248 | n_gen = 100, tg = 24.93 t/s, tg_3s = 25.18 t/s 6.22.575.889 I slot print_timing: id 0 | task 6273 | n_gen = 100, tg = 26.63 t/s, tg_3s = 26.90 t/s 6.23.366.776 I slot print_timing: id 1 | task 6157 | prompt eval time = 343.02 ms / 96 tokens ( 3.57 ms per token, 279.86 tokens per second) 6.23.366.782 I slot print_timing: id 1 | task 6157 | eval time = 9715.38 ms / 233 tokens ( 41.88 ms per token, 23.88 tokens per second) 6.23.366.783 I slot print_timing: id 1 | task 6157 | total time = 10058.40 ms / 329 tokens 6.23.366.784 I slot print_timing: id 1 | task 6157 | graphs reused = 5431 6.23.366.784 I slot print_timing: id 1 | task 6157 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.366.847 I slot release: id 1 | task 6157 | stop processing: n_tokens = 1442, truncated = 0 6.23.430.404 I slot print_timing: id 2 | task 6213 | n_gen = 180, tg = 24.83 t/s, tg_3s = 26.39 t/s 6.23.432.017 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.773 6.23.432.047 I slot launch_slot_: id 1 | task 6397 | processing task, is_child = 0 6.24.683.380 I slot print_timing: id 3 | task 6248 | n_gen = 172, tg = 24.50 t/s, tg_3s = 23.95 t/s 6.25.578.175 I slot print_timing: id 0 | task 6273 | n_gen = 172, tg = 25.45 t/s, tg_3s = 23.98 t/s 6.26.446.112 I slot print_timing: id 2 | task 6213 | n_gen = 253, tg = 24.65 t/s, tg_3s = 24.21 t/s 6.27.423.705 I slot print_timing: id 1 | task 6397 | prompt eval time = 338.89 ms / 85 tokens ( 3.99 ms per token, 250.82 tokens per second) 6.27.423.711 I slot print_timing: id 1 | task 6397 | eval time = 3652.75 ms / 98 tokens ( 37.66 ms per token, 26.56 tokens per second) 6.27.423.712 I slot print_timing: id 1 | task 6397 | total time = 3991.65 ms / 183 tokens 6.27.423.712 I slot print_timing: id 1 | task 6397 | graphs reused = 5526 6.27.423.713 I slot print_timing: id 1 | task 6397 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.423.775 I slot release: id 1 | task 6397 | stop processing: n_tokens = 1297, truncated = 0 6.27.488.923 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.860 6.27.488.947 I slot launch_slot_: id 1 | task 6498 | processing task, is_child = 0 6.27.782.259 I slot print_timing: id 3 | task 6248 | n_gen = 247, tg = 24.41 t/s, tg_3s = 24.20 t/s 6.28.075.361 I slot print_timing: id 2 | task 6213 | prompt eval time = 427.73 ms / 145 tokens ( 2.95 ms per token, 339.00 tokens per second) 6.28.075.367 I slot print_timing: id 2 | task 6213 | eval time = 11852.72 ms / 287 tokens ( 41.44 ms per token, 24.13 tokens per second) 6.28.075.368 I slot print_timing: id 2 | task 6213 | total time = 12280.45 ms / 432 tokens 6.28.075.369 I slot print_timing: id 2 | task 6213 | graphs reused = 5530 6.28.075.369 I slot print_timing: id 2 | task 6213 | graph reallocs = 0 / 0 (same size) / (changed size) 6.28.075.448 I slot release: id 2 | task 6213 | stop processing: n_tokens = 1546, truncated = 0 6.28.139.039 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.721 6.28.139.068 I slot launch_slot_: id 2 | task 6507 | processing task, is_child = 0 6.28.591.932 I slot print_timing: id 0 | task 6273 | n_gen = 235, tg = 24.04 t/s, tg_3s = 20.90 t/s 6.28.629.747 I slot print_timing: id 0 | task 6273 | prompt eval time = 324.87 ms / 123 tokens ( 2.64 ms per token, 378.61 tokens per second) 6.28.629.754 I slot print_timing: id 0 | task 6273 | eval time = 9771.26 ms / 236 tokens ( 41.58 ms per token, 24.05 tokens per second) 6.28.629.755 I slot print_timing: id 0 | task 6273 | total time = 10096.14 ms / 359 tokens 6.28.629.756 I slot print_timing: id 0 | task 6273 | graphs reused = 5533 6.28.629.756 I slot print_timing: id 0 | task 6273 | graph reallocs = 0 / 0 (same size) / (changed size) 6.28.629.824 I slot release: id 0 | task 6273 | stop processing: n_tokens = 1473, truncated = 0 6.28.670.733 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.757 6.28.670.761 I slot launch_slot_: id 0 | task 6515 | processing task, is_child = 0 6.30.819.924 I slot print_timing: id 3 | task 6248 | n_gen = 311, tg = 23.64 t/s, tg_3s = 21.07 t/s 6.32.167.377 I slot print_timing: id 1 | task 6498 | n_gen = 100, tg = 23.09 t/s, tg_3s = 23.32 t/s 6.32.469.599 I slot print_timing: id 2 | task 6507 | n_gen = 100, tg = 24.80 t/s, tg_3s = 25.05 t/s 6.32.730.263 I slot print_timing: id 0 | task 6515 | n_gen = 100, tg = 26.59 t/s, tg_3s = 26.86 t/s 6.33.826.749 I slot print_timing: id 3 | task 6248 | n_gen = 391, tg = 24.19 t/s, tg_3s = 26.61 t/s 6.35.179.622 I slot print_timing: id 1 | task 6498 | n_gen = 180, tg = 24.52 t/s, tg_3s = 26.56 t/s 6.35.482.549 I slot print_timing: id 2 | task 6507 | n_gen = 180, tg = 25.56 t/s, tg_3s = 26.55 t/s 6.35.742.932 I slot print_timing: id 0 | task 6515 | n_gen = 180, tg = 26.57 t/s, tg_3s = 26.55 t/s 6.36.535.843 I slot print_timing: id 1 | task 6498 | prompt eval time = 390.02 ms / 120 tokens ( 3.25 ms per token, 307.67 tokens per second) 6.36.535.848 I slot print_timing: id 1 | task 6498 | eval time = 8656.86 ms / 216 tokens ( 40.26 ms per token, 24.84 tokens per second) 6.36.535.848 I slot print_timing: id 1 | task 6498 | total time = 9046.89 ms / 336 tokens 6.36.535.849 I slot print_timing: id 1 | task 6498 | graphs reused = 5732 6.36.535.850 I slot print_timing: id 1 | task 6498 | graph reallocs = 0 / 0 (same size) / (changed size) 6.36.535.918 I slot release: id 1 | task 6498 | stop processing: n_tokens = 1450, truncated = 0 6.36.601.495 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.769 6.36.601.527 I slot launch_slot_: id 1 | task 6719 | processing task, is_child = 0 6.36.839.822 I slot print_timing: id 3 | task 6248 | n_gen = 465, tg = 24.25 t/s, tg_3s = 24.56 t/s 6.37.994.852 I slot print_timing: id 0 | task 6515 | prompt eval time = 336.45 ms / 111 tokens ( 3.03 ms per token, 329.91 tokens per second) 6.37.994.856 I slot print_timing: id 0 | task 6515 | eval time = 8987.63 ms / 232 tokens ( 38.91 ms per token, 25.70 tokens per second) 6.37.994.857 I slot print_timing: id 0 | task 6515 | total time = 9324.08 ms / 343 tokens 6.37.994.857 I slot print_timing: id 0 | task 6515 | graphs reused = 5759 6.37.994.858 I slot print_timing: id 0 | task 6515 | graph reallocs = 0 / 0 (same size) / (changed size) 6.37.994.923 I slot release: id 0 | task 6515 | stop processing: n_tokens = 1457, truncated = 0 6.38.035.610 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.765 6.38.035.639 I slot launch_slot_: id 0 | task 6751 | processing task, is_child = 0 6.38.517.794 I slot print_timing: id 2 | task 6507 | n_gen = 247, tg = 24.50 t/s, tg_3s = 22.07 t/s 6.39.085.000 I slot print_timing: id 2 | task 6507 | prompt eval time = 339.10 ms / 85 tokens ( 3.99 ms per token, 250.67 tokens per second) 6.39.085.004 I slot print_timing: id 2 | task 6507 | eval time = 10606.83 ms / 262 tokens ( 40.64 ms per token, 24.61 tokens per second) 6.39.085.004 I slot print_timing: id 2 | task 6507 | total time = 10945.92 ms / 347 tokens 6.39.085.005 I slot print_timing: id 2 | task 6507 | graphs reused = 5779 6.39.085.006 I slot print_timing: id 2 | task 6507 | graph reallocs = 0 / 0 (same size) / (changed size) 6.39.085.068 I slot release: id 2 | task 6507 | stop processing: n_tokens = 1461, truncated = 0 6.39.148.656 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.763 6.39.148.682 I slot launch_slot_: id 2 | task 6775 | processing task, is_child = 0 6.39.864.547 I slot print_timing: id 3 | task 6248 | n_gen = 530, tg = 23.87 t/s, tg_3s = 21.49 t/s 6.41.180.329 I slot print_timing: id 1 | task 6719 | n_gen = 100, tg = 23.31 t/s, tg_3s = 23.55 t/s 6.42.345.839 I slot print_timing: id 0 | task 6751 | n_gen = 100, tg = 24.57 t/s, tg_3s = 24.82 t/s 6.42.885.990 I slot print_timing: id 3 | task 6248 | n_gen = 610, tg = 24.19 t/s, tg_3s = 26.48 t/s 6.43.223.207 I slot print_timing: id 2 | task 6775 | n_gen = 100, tg = 26.44 t/s, tg_3s = 26.71 t/s 6.43.332.881 I slot print_timing: id 0 | task 6751 | prompt eval time = 280.75 ms / 71 tokens ( 3.95 ms per token, 252.89 tokens per second) 6.43.332.888 I slot print_timing: id 0 | task 6751 | eval time = 5016.48 ms / 126 tokens ( 40.13 ms per token, 24.92 tokens per second) 6.43.332.889 I slot print_timing: id 0 | task 6751 | total time = 5297.23 ms / 197 tokens 6.43.332.890 I slot print_timing: id 0 | task 6751 | graphs reused = 5879 6.43.332.890 I slot print_timing: id 0 | task 6751 | graph reallocs = 0 / 0 (same size) / (changed size) 6.43.332.952 I slot release: id 0 | task 6751 | stop processing: n_tokens = 1311, truncated = 0 6.43.373.210 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.850 6.43.373.236 I slot launch_slot_: id 0 | task 6881 | processing task, is_child = 0 6.44.062.735 I slot print_timing: id 1 | task 6719 | prompt eval time = 332.11 ms / 96 tokens ( 3.46 ms per token, 289.07 tokens per second) 6.44.062.738 I slot print_timing: id 1 | task 6719 | eval time = 7129.09 ms / 171 tokens ( 41.94 ms per token, 23.85 tokens per second) 6.44.062.739 I slot print_timing: id 1 | task 6719 | total time = 7461.20 ms / 267 tokens 6.44.062.740 I slot print_timing: id 1 | task 6719 | graphs reused = 5890 6.44.062.740 I slot print_timing: id 1 | task 6719 | graph reallocs = 0 / 0 (same size) / (changed size) 6.44.062.799 I slot release: id 1 | task 6719 | stop processing: n_tokens = 1381, truncated = 0 6.44.128.548 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.807 6.44.128.582 I slot launch_slot_: id 1 | task 6896 | processing task, is_child = 0 6.45.899.058 I slot print_timing: id 3 | task 6248 | n_gen = 677, tg = 23.98 t/s, tg_3s = 22.24 t/s 6.46.236.276 I slot print_timing: id 2 | task 6775 | n_gen = 167, tg = 24.56 t/s, tg_3s = 22.24 t/s 6.47.254.237 I slot print_timing: id 2 | task 6775 | prompt eval time = 329.94 ms / 86 tokens ( 3.84 ms per token, 260.66 tokens per second) 6.47.254.241 I slot print_timing: id 2 | task 6775 | eval time = 7775.60 ms / 194 tokens ( 40.29 ms per token, 24.82 tokens per second) 6.47.254.241 I slot print_timing: id 2 | task 6775 | total time = 8105.54 ms / 280 tokens 6.47.254.242 I slot print_timing: id 2 | task 6775 | graphs reused = 5963 6.47.254.242 I slot print_timing: id 2 | task 6775 | graph reallocs = 0 / 0 (same size) / (changed size) 6.47.254.301 I slot release: id 2 | task 6775 | stop processing: n_tokens = 1394, truncated = 0 6.47.318.028 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.800 6.47.318.057 I slot launch_slot_: id 2 | task 6974 | processing task, is_child = 0 6.48.053.263 I slot print_timing: id 0 | task 6881 | n_gen = 100, tg = 22.45 t/s, tg_3s = 22.68 t/s 6.48.582.049 I slot print_timing: id 1 | task 6896 | n_gen = 100, tg = 24.01 t/s, tg_3s = 24.25 t/s 6.48.924.592 I slot print_timing: id 3 | task 6248 | n_gen = 747, tg = 23.90 t/s, tg_3s = 23.14 t/s 6.49.334.892 I slot print_timing: id 0 | task 6881 | prompt eval time = 270.63 ms / 76 tokens ( 3.56 ms per token, 280.83 tokens per second) 6.49.334.897 I slot print_timing: id 0 | task 6881 | eval time = 5691.02 ms / 134 tokens ( 42.79 ms per token, 23.37 tokens per second) 6.49.334.898 I slot print_timing: id 0 | task 6881 | total time = 5961.65 ms / 210 tokens 6.49.334.898 I slot print_timing: id 0 | task 6881 | graphs reused = 6004 6.49.334.899 I slot print_timing: id 0 | task 6881 | graph reallocs = 0 / 0 (same size) / (changed size) 6.49.334.968 I slot release: id 0 | task 6881 | stop processing: n_tokens = 1324, truncated = 0 6.49.375.845 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.842 6.49.375.871 I slot launch_slot_: id 0 | task 7020 | processing task, is_child = 0 6.51.617.228 I slot print_timing: id 1 | task 6896 | n_gen = 175, tg = 24.31 t/s, tg_3s = 24.71 t/s 6.51.694.298 I slot print_timing: id 2 | task 6974 | n_gen = 100, tg = 25.08 t/s, tg_3s = 25.33 t/s 6.51.960.308 I slot print_timing: id 3 | task 6248 | n_gen = 822, tg = 23.97 t/s, tg_3s = 24.71 t/s 6.52.748.495 I slot print_timing: id 1 | task 6896 | prompt eval time = 329.86 ms / 83 tokens ( 3.97 ms per token, 251.62 tokens per second) 6.52.748.501 I slot print_timing: id 1 | task 6896 | eval time = 8290.05 ms / 205 tokens ( 40.64 ms per token, 24.61 tokens per second) 6.52.748.502 I slot print_timing: id 1 | task 6896 | total time = 8619.90 ms / 288 tokens 6.52.748.511 I slot print_timing: id 1 | task 6896 | graphs reused = 6086 6.52.748.512 I slot print_timing: id 1 | task 6896 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.748.573 I slot release: id 1 | task 6896 | stop processing: n_tokens = 1402, truncated = 0 6.52.814.337 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.795 6.52.814.368 I slot launch_slot_: id 1 | task 7106 | processing task, is_child = 0 6.53.727.087 I slot print_timing: id 0 | task 7020 | n_gen = 100, tg = 24.29 t/s, tg_3s = 24.53 t/s 6.54.713.606 I slot print_timing: id 2 | task 6974 | n_gen = 171, tg = 24.40 t/s, tg_3s = 23.52 t/s 6.54.786.030 I slot print_timing: id 0 | task 7020 | prompt eval time = 275.24 ms / 86 tokens ( 3.20 ms per token, 312.46 tokens per second) 6.54.786.038 I slot print_timing: id 0 | task 7020 | eval time = 5134.91 ms / 128 tokens ( 40.43 ms per token, 24.73 tokens per second) 6.54.786.038 I slot print_timing: id 0 | task 7020 | total time = 5410.15 ms / 214 tokens 6.54.786.039 I slot print_timing: id 0 | task 7020 | graphs reused = 6126 6.54.786.039 I slot print_timing: id 0 | task 7020 | graph reallocs = 0 / 0 (same size) / (changed size) 6.54.786.108 I slot release: id 0 | task 7020 | stop processing: n_tokens = 1328, truncated = 0 6.54.826.643 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.840 6.54.826.673 I slot launch_slot_: id 0 | task 7152 | processing task, is_child = 0 6.55.036.978 I slot print_timing: id 3 | task 6248 | n_gen = 890, tg = 23.81 t/s, tg_3s = 22.10 t/s 6.56.291.426 I slot print_timing: id 2 | task 6974 | prompt eval time = 428.75 ms / 142 tokens ( 3.02 ms per token, 331.20 tokens per second) 6.56.291.432 I slot print_timing: id 2 | task 6974 | eval time = 8544.61 ms / 207 tokens ( 41.48 ms per token, 24.11 tokens per second) 6.56.291.433 I slot print_timing: id 2 | task 6974 | total time = 8973.36 ms / 349 tokens 6.56.291.433 I slot print_timing: id 2 | task 6974 | graphs reused = 6157 6.56.291.434 I slot print_timing: id 2 | task 6974 | graph reallocs = 0 / 0 (same size) / (changed size) 6.56.291.497 I slot release: id 2 | task 6974 | stop processing: n_tokens = 1463, truncated = 0 6.56.355.324 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.762 6.56.355.348 I slot launch_slot_: id 2 | task 7187 | processing task, is_child = 0 6.57.510.980 I slot print_timing: id 1 | task 7106 | n_gen = 100, tg = 22.92 t/s, tg_3s = 23.15 t/s 6.58.042.867 I slot print_timing: id 3 | task 6248 | n_gen = 959, tg = 23.75 t/s, tg_3s = 22.95 t/s 6.59.061.372 I slot print_timing: id 1 | task 7106 | prompt eval time = 377.85 ms / 103 tokens ( 3.67 ms per token, 272.60 tokens per second) 6.59.061.378 I slot print_timing: id 1 | task 7106 | eval time = 5869.15 ms / 141 tokens ( 41.92 ms per token, 23.85 tokens per second) 6.59.061.379 I slot print_timing: id 1 | task 7106 | total time = 6246.99 ms / 244 tokens 6.59.061.380 I slot print_timing: id 1 | task 7106 | graphs reused = 6217 6.59.061.380 I slot print_timing: id 1 | task 7106 | graph reallocs = 0 / 0 (same size) / (changed size) 6.59.061.438 I slot release: id 1 | task 7106 | stop processing: n_tokens = 1358, truncated = 0 6.59.126.984 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.821 6.59.127.014 I slot launch_slot_: id 1 | task 7252 | processing task, is_child = 0 6.59.490.759 I slot print_timing: id 0 | task 7152 | n_gen = 100, tg = 22.59 t/s, tg_3s = 22.82 t/s 7.00.252.368 I slot print_timing: id 0 | task 7152 | prompt eval time = 281.75 ms / 71 tokens ( 3.97 ms per token, 252.00 tokens per second) 7.00.252.375 I slot print_timing: id 0 | task 7152 | eval time = 5143.94 ms / 120 tokens ( 43.23 ms per token, 23.13 tokens per second) 7.00.252.376 I slot print_timing: id 0 | task 7152 | total time = 5425.69 ms / 191 tokens 7.00.252.376 I slot print_timing: id 0 | task 7152 | graphs reused = 6237 7.00.252.377 I slot print_timing: id 0 | task 7152 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.252.436 I slot release: id 0 | task 7152 | stop processing: n_tokens = 1305, truncated = 0 7.00.749.704 I slot print_timing: id 2 | task 7187 | n_gen = 100, tg = 24.73 t/s, tg_3s = 24.98 t/s 7.00.751.249 I slot print_timing: id 3 | task 6248 | prompt eval time = 279.03 ms / 83 tokens ( 3.36 ms per token, 297.46 tokens per second) 7.00.751.252 I slot print_timing: id 3 | task 6248 | eval time = 43046.15 ms / 1024 tokens ( 42.08 ms per token, 23.77 tokens per second) 7.00.751.253 I slot print_timing: id 3 | task 6248 | total time = 43325.18 ms / 1107 tokens 7.00.751.253 I slot print_timing: id 3 | task 6248 | graphs reused = 6250 7.00.751.254 I slot print_timing: id 3 | task 6248 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.751.314 I slot release: id 3 | task 6248 | stop processing: n_tokens = 2220, truncated = 0 7.02.831.759 I slot print_timing: id 1 | task 7252 | n_gen = 100, tg = 29.32 t/s, tg_3s = 29.62 t/s 7.02.994.063 I slot print_timing: id 1 | task 7252 | prompt eval time = 328.20 ms / 71 tokens ( 4.62 ms per token, 216.33 tokens per second) 7.02.994.069 I slot print_timing: id 1 | task 7252 | eval time = 3538.83 ms / 105 tokens ( 34.03 ms per token, 29.39 tokens per second) 7.02.994.070 I slot print_timing: id 1 | task 7252 | total time = 3867.04 ms / 176 tokens 7.02.994.071 I slot print_timing: id 1 | task 7252 | graphs reused = 6318 7.02.994.071 I slot print_timing: id 1 | task 7252 | graph reallocs = 0 / 0 (same size) / (changed size) 7.02.994.130 I slot release: id 1 | task 7252 | stop processing: n_tokens = 1290, truncated = 0 7.03.771.885 I slot print_timing: id 2 | task 7187 | n_gen = 196, tg = 27.76 t/s, tg_3s = 31.77 t/s 7.04.030.699 I slot print_timing: id 2 | task 7187 | prompt eval time = 391.72 ms / 117 tokens ( 3.35 ms per token, 298.68 tokens per second) 7.04.030.706 I slot print_timing: id 2 | task 7187 | eval time = 7283.62 ms / 205 tokens ( 35.70 ms per token, 28.01 tokens per second) 7.04.030.706 I slot print_timing: id 2 | task 7187 | total time = 7675.34 ms / 322 tokens 7.04.030.707 I slot print_timing: id 2 | task 7187 | graphs reused = 6353 7.04.030.708 I slot print_timing: id 2 | task 7187 | graph reallocs = 0 / 0 (same size) / (changed size) 7.04.030.764 I slot release: id 2 | task 7187 | stop processing: n_tokens = 1436, truncated = 0 7.04.050.299 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1305, t_last = 319523776218 7.04.080.955 I slot launch_slot_: id 0 | task 7395 | processing task, is_child = 0 7.04.166.523 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2220, t_last = 319524275096 7.04.167.571 I slot launch_slot_: id 3 | task 7396 | processing task, is_child = 0 7.04.167.754 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1290, t_last = 319526517912 7.04.168.648 I slot launch_slot_: id 1 | task 7397 | processing task, is_child = 0 7.04.168.743 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1436, t_last = 319527554546 7.04.169.606 I slot launch_slot_: id 2 | task 7398 | processing task, is_child = 0 7.09.073.500 I slot print_timing: id 0 | task 7395 | prompt processing, n_tokens = 642, progress = 0.84, t = 4.90 s / 130.92 tokens per second 7.09.102.999 I slot print_timing: id 1 | task 7397 | prompt processing, n_tokens = 842, progress = 0.88, t = 4.90 s / 171.71 tokens per second 7.09.106.654 I slot print_timing: id 2 | task 7398 | prompt processing, n_tokens = 865, progress = 0.89, t = 4.90 s / 176.40 tokens per second 7.09.108.451 I slot print_timing: id 3 | task 7396 | prompt processing, n_tokens = 616, progress = 0.79, t = 4.90 s / 125.62 tokens per second 7.09.918.284 I slot print_timing: id 0 | task 7395 | prompt processing, n_tokens = 762, progress = 0.99, t = 5.75 s / 132.55 tokens per second 7.10.047.234 I slot print_timing: id 1 | task 7397 | prompt processing, n_tokens = 955, progress = 1.00, t = 5.75 s / 166.13 tokens per second 7.10.052.664 I slot print_timing: id 2 | task 7398 | prompt processing, n_tokens = 972, progress = 1.00, t = 5.75 s / 169.09 tokens per second 7.10.056.791 I slot print_timing: id 3 | task 7396 | prompt processing, n_tokens = 774, progress = 0.99, t = 5.75 s / 134.65 tokens per second 7.10.162.457 I slot print_timing: id 0 | task 7395 | prompt eval time = 5951.57 ms / 766 tokens ( 7.77 ms per token, 128.71 tokens per second) 7.10.162.461 I slot print_timing: id 0 | task 7395 | eval time = 41.27 ms / 2 tokens ( 41.27 ms per token, 24.23 tokens per second) 7.10.162.462 I slot print_timing: id 0 | task 7395 | total time = 5992.83 ms / 768 tokens 7.10.162.462 I slot print_timing: id 0 | task 7395 | graphs reused = 6354 7.10.162.463 I slot print_timing: id 0 | task 7395 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.162.516 I slot release: id 0 | task 7395 | stop processing: n_tokens = 776, truncated = 0 7.10.164.308 I slot print_timing: id 1 | task 7397 | prompt eval time = 5953.70 ms / 959 tokens ( 6.21 ms per token, 161.08 tokens per second) 7.10.164.311 I slot print_timing: id 1 | task 7397 | eval time = 40.88 ms / 2 tokens ( 40.88 ms per token, 24.46 tokens per second) 7.10.164.312 I slot print_timing: id 1 | task 7397 | total time = 5994.58 ms / 961 tokens 7.10.164.312 I slot print_timing: id 1 | task 7397 | graphs reused = 6354 7.10.164.313 I slot print_timing: id 1 | task 7397 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.164.365 I slot release: id 1 | task 7397 | stop processing: n_tokens = 969, truncated = 0 7.10.166.160 I slot print_timing: id 2 | task 7398 | prompt eval time = 5955.69 ms / 976 tokens ( 6.10 ms per token, 163.88 tokens per second) 7.10.166.162 I slot print_timing: id 2 | task 7398 | eval time = 40.64 ms / 2 tokens ( 40.64 ms per token, 24.60 tokens per second) 7.10.166.163 I slot print_timing: id 2 | task 7398 | total time = 5996.34 ms / 978 tokens 7.10.166.164 I slot print_timing: id 2 | task 7398 | graphs reused = 6354 7.10.166.164 I slot print_timing: id 2 | task 7398 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.166.211 I slot release: id 2 | task 7398 | stop processing: n_tokens = 986, truncated = 0 7.10.168.020 I slot print_timing: id 3 | task 7396 | prompt eval time = 5958.03 ms / 778 tokens ( 7.66 ms per token, 130.58 tokens per second) 7.10.168.024 I slot print_timing: id 3 | task 7396 | eval time = 40.10 ms / 2 tokens ( 40.10 ms per token, 24.94 tokens per second) 7.10.168.024 I slot print_timing: id 3 | task 7396 | total time = 5998.13 ms / 780 tokens 7.10.168.025 I slot print_timing: id 3 | task 7396 | graphs reused = 6354 7.10.168.025 I slot print_timing: id 3 | task 7396 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.168.067 I slot release: id 3 | task 7396 | stop processing: n_tokens = 788, truncated = 0 7.10.174.260 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 776, t_last = 319533686298 7.10.197.685 I slot launch_slot_: id 0 | task 7404 | processing task, is_child = 0 7.10.282.701 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 969, t_last = 319533688147 7.10.282.868 I slot launch_slot_: id 1 | task 7405 | processing task, is_child = 0 7.10.283.002 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 319533689993 7.10.283.121 I slot launch_slot_: id 2 | task 7406 | processing task, is_child = 0 7.10.283.185 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 788, t_last = 319533691849 7.10.283.287 I slot launch_slot_: id 3 | task 7407 | processing task, is_child = 0 7.14.750.157 I slot print_timing: id 0 | task 7404 | prompt processing, n_tokens = 690, progress = 0.87, t = 4.47 s / 154.47 tokens per second 7.14.780.937 I slot print_timing: id 1 | task 7405 | prompt processing, n_tokens = 690, progress = 0.87, t = 4.47 s / 154.48 tokens per second 7.14.787.889 I slot print_timing: id 2 | task 7406 | prompt processing, n_tokens = 690, progress = 0.82, t = 4.47 s / 154.49 tokens per second 7.14.794.693 I slot print_timing: id 3 | task 7407 | prompt processing, n_tokens = 690, progress = 0.81, t = 4.47 s / 154.49 tokens per second 7.15.682.742 I slot print_timing: id 0 | task 7404 | prompt processing, n_tokens = 792, progress = 1.00, t = 5.40 s / 146.68 tokens per second 7.15.717.023 I slot print_timing: id 1 | task 7405 | prompt processing, n_tokens = 794, progress = 1.00, t = 5.40 s / 147.06 tokens per second 7.15.722.731 I slot print_timing: id 2 | task 7406 | prompt processing, n_tokens = 837, progress = 1.00, t = 5.40 s / 155.03 tokens per second 7.15.726.847 I slot print_timing: id 3 | task 7407 | prompt processing, n_tokens = 845, progress = 1.00, t = 5.40 s / 156.52 tokens per second 7.15.832.088 I slot print_timing: id 0 | task 7404 | prompt eval time = 5507.70 ms / 796 tokens ( 6.92 ms per token, 144.52 tokens per second) 7.15.832.093 I slot print_timing: id 0 | task 7404 | eval time = 41.09 ms / 2 tokens ( 41.09 ms per token, 24.34 tokens per second) 7.15.832.093 I slot print_timing: id 0 | task 7404 | total time = 5548.79 ms / 798 tokens 7.15.832.094 I slot print_timing: id 0 | task 7404 | graphs reused = 6354 7.15.832.095 I slot print_timing: id 0 | task 7404 | graph reallocs = 0 / 0 (same size) / (changed size) 7.15.832.149 I slot release: id 0 | task 7404 | stop processing: n_tokens = 806, truncated = 0 7.15.834.025 I slot print_timing: id 1 | task 7405 | prompt eval time = 5509.76 ms / 798 tokens ( 6.90 ms per token, 144.83 tokens per second) 7.15.834.028 I slot print_timing: id 1 | task 7405 | eval time = 40.77 ms / 2 tokens ( 40.77 ms per token, 24.53 tokens per second) 7.15.834.029 I slot print_timing: id 1 | task 7405 | total time = 5550.53 ms / 800 tokens 7.15.834.029 I slot print_timing: id 1 | task 7405 | graphs reused = 6354 7.15.834.030 I slot print_timing: id 1 | task 7405 | graph reallocs = 0 / 0 (same size) / (changed size) 7.15.834.059 I slot release: id 1 | task 7405 | stop processing: n_tokens = 808, truncated = 0 7.15.835.908 I slot print_timing: id 2 | task 7406 | prompt eval time = 5511.81 ms / 841 tokens ( 6.55 ms per token, 152.58 tokens per second) 7.15.835.912 I slot print_timing: id 2 | task 7406 | eval time = 40.40 ms / 2 tokens ( 40.40 ms per token, 24.75 tokens per second) 7.15.835.913 I slot print_timing: id 2 | task 7406 | total time = 5552.21 ms / 843 tokens 7.15.835.913 I slot print_timing: id 2 | task 7406 | graphs reused = 6354 7.15.835.914 I slot print_timing: id 2 | task 7406 | graph reallocs = 0 / 0 (same size) / (changed size) 7.15.835.949 I slot release: id 2 | task 7406 | stop processing: n_tokens = 851, truncated = 0 7.15.837.717 I slot print_timing: id 3 | task 7407 | prompt eval time = 5513.78 ms / 849 tokens ( 6.49 ms per token, 153.98 tokens per second) 7.15.837.720 I slot print_timing: id 3 | task 7407 | eval time = 40.06 ms / 2 tokens ( 40.06 ms per token, 24.96 tokens per second) 7.15.837.721 I slot print_timing: id 3 | task 7407 | total time = 5553.84 ms / 851 tokens 7.15.837.721 I slot print_timing: id 3 | task 7407 | graphs reused = 6354 7.15.837.722 I slot print_timing: id 3 | task 7407 | graph reallocs = 0 / 0 (same size) / (changed size) 7.15.837.750 I slot release: id 3 | task 7407 | stop processing: n_tokens = 859, truncated = 0 7.15.843.542 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.874 (> 0.100 thold), f_keep = 0.901 7.15.843.627 I slot launch_slot_: id 0 | task 7413 | processing task, is_child = 0 7.15.898.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.292 MiB) 7.15.898.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.306 MiB) 7.15.898.222 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.106 MiB) 7.15.925.904 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 808, t_last = 319539357842 7.15.926.102 I slot launch_slot_: id 1 | task 7414 | processing task, is_child = 0 7.15.926.245 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 851, t_last = 319539359731 7.15.926.349 I slot launch_slot_: id 2 | task 7415 | processing task, is_child = 0 7.15.926.415 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 859, t_last = 319539361532 7.15.926.517 I slot launch_slot_: id 3 | task 7416 | processing task, is_child = 0 7.19.988.950 I slot print_timing: id 1 | task 7414 | prompt processing, n_tokens = 739, progress = 0.85, t = 4.06 s / 182.06 tokens per second 7.19.991.231 I slot print_timing: id 2 | task 7415 | prompt processing, n_tokens = 739, progress = 0.84, t = 4.06 s / 182.07 tokens per second 7.19.993.328 I slot print_timing: id 3 | task 7416 | prompt processing, n_tokens = 817, progress = 0.86, t = 4.06 s / 201.29 tokens per second 7.20.710.227 I slot print_timing: id 0 | task 7413 | prompt eval time = 4062.41 ms / 105 tokens ( 38.69 ms per token, 25.85 tokens per second) 7.20.710.231 I slot print_timing: id 0 | task 7413 | eval time = 721.29 ms / 2 tokens ( 721.29 ms per token, 1.39 tokens per second) 7.20.710.236 I slot print_timing: id 0 | task 7413 | total time = 4783.70 ms / 107 tokens 7.20.710.238 I slot print_timing: id 0 | task 7413 | graphs reused = 6354 7.20.710.244 I slot print_timing: id 0 | task 7413 | graph reallocs = 0 / 0 (same size) / (changed size) 7.20.710.289 I slot release: id 0 | task 7413 | stop processing: n_tokens = 832, truncated = 0 7.20.710.300 I slot print_timing: id 1 | task 7414 | prompt processing, n_tokens = 864, progress = 1.00, t = 4.78 s / 180.75 tokens per second 7.20.712.484 I slot print_timing: id 2 | task 7415 | prompt processing, n_tokens = 874, progress = 1.00, t = 4.78 s / 182.85 tokens per second 7.20.714.652 I slot print_timing: id 3 | task 7416 | prompt processing, n_tokens = 945, progress = 1.00, t = 4.78 s / 197.71 tokens per second 7.20.779.160 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 319544234071 7.20.779.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.770 MiB) 7.20.779.276 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 49.369 MiB) 7.20.779.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.490 MiB) 7.20.779.282 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.614 MiB) 7.20.779.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.524 MiB) 7.20.779.287 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 7.20.808.414 I slot launch_slot_: id 0 | task 7421 | processing task, is_child = 0 7.21.574.568 I slot print_timing: id 1 | task 7414 | prompt eval time = 4847.44 ms / 868 tokens ( 5.58 ms per token, 179.06 tokens per second) 7.21.574.572 I slot print_timing: id 1 | task 7414 | eval time = 798.46 ms / 2 tokens ( 798.46 ms per token, 1.25 tokens per second) 7.21.574.572 I slot print_timing: id 1 | task 7414 | total time = 5645.90 ms / 870 tokens 7.21.574.573 I slot print_timing: id 1 | task 7414 | graphs reused = 6354 7.21.574.573 I slot print_timing: id 1 | task 7414 | graph reallocs = 0 / 0 (same size) / (changed size) 7.21.574.653 I slot release: id 1 | task 7414 | stop processing: n_tokens = 878, truncated = 0 7.21.575.796 I slot print_timing: id 2 | task 7415 | prompt eval time = 4848.75 ms / 878 tokens ( 5.52 ms per token, 181.08 tokens per second) 7.21.575.798 I slot print_timing: id 2 | task 7415 | eval time = 798.18 ms / 2 tokens ( 798.18 ms per token, 1.25 tokens per second) 7.21.575.798 I slot print_timing: id 2 | task 7415 | total time = 5646.93 ms / 880 tokens 7.21.575.799 I slot print_timing: id 2 | task 7415 | graphs reused = 6354 7.21.575.799 I slot print_timing: id 2 | task 7415 | graph reallocs = 0 / 0 (same size) / (changed size) 7.21.575.831 I slot release: id 2 | task 7415 | stop processing: n_tokens = 888, truncated = 0 7.21.576.950 I slot print_timing: id 3 | task 7416 | prompt eval time = 4850.11 ms / 949 tokens ( 5.11 ms per token, 195.67 tokens per second) 7.21.576.955 I slot print_timing: id 3 | task 7416 | eval time = 797.79 ms / 2 tokens ( 797.79 ms per token, 1.25 tokens per second) 7.21.576.955 I slot print_timing: id 3 | task 7416 | total time = 5647.90 ms / 951 tokens 7.21.576.955 I slot print_timing: id 3 | task 7416 | graphs reused = 6354 7.21.576.956 I slot print_timing: id 3 | task 7416 | graph reallocs = 0 / 0 (same size) / (changed size) 7.21.577.012 I slot release: id 3 | task 7416 | stop processing: n_tokens = 959, truncated = 0 7.22.251.848 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 878, t_last = 319545098435 7.22.251.966 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.508 MiB) 7.22.251.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 51.830 MiB) 7.22.251.976 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.631 MiB) 7.22.251.980 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.922 MiB) 7.22.251.984 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.431 MiB) 7.22.251.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.029 MiB) 7.22.490.962 I slot launch_slot_: id 1 | task 7425 | processing task, is_child = 0 7.22.491.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.493 MiB) 7.22.491.164 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 7.22.491.173 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.798 MiB) 7.22.491.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.185 MiB) 7.22.491.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.783 MiB) 7.22.534.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.321 MiB) 7.22.534.231 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.614 MiB) 7.22.534.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.508 MiB) 7.22.534.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 7.22.534.239 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.215 MiB) 7.22.534.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.154 MiB) 7.22.568.124 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 888, t_last = 319545099613 7.22.568.271 I slot launch_slot_: id 2 | task 7426 | processing task, is_child = 0 7.22.568.359 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 959, t_last = 319545100795 7.22.568.466 I slot launch_slot_: id 3 | task 7427 | processing task, is_child = 0 7.27.489.405 I slot print_timing: id 0 | task 7421 | prompt eval time = 4487.78 ms / 988 tokens ( 4.54 ms per token, 220.15 tokens per second) 7.27.489.419 I slot print_timing: id 0 | task 7421 | eval time = 2193.14 ms / 2 tokens ( 2193.14 ms per token, 0.46 tokens per second) 7.27.489.420 I slot print_timing: id 0 | task 7421 | total time = 6680.92 ms / 990 tokens 7.27.489.422 I slot print_timing: id 0 | task 7421 | graphs reused = 6354 7.27.489.433 I slot print_timing: id 0 | task 7421 | graph reallocs = 0 / 0 (same size) / (changed size) 7.27.489.604 I slot release: id 0 | task 7421 | stop processing: n_tokens = 998, truncated = 0 7.27.489.677 I slot print_timing: id 1 | task 7425 | prompt processing, n_tokens = 871, progress = 0.85, t = 4.91 s / 177.49 tokens per second 7.27.497.220 I slot print_timing: id 2 | task 7426 | prompt processing, n_tokens = 747, progress = 0.82, t = 4.91 s / 152.24 tokens per second 7.27.501.422 I slot print_timing: id 3 | task 7427 | prompt processing, n_tokens = 1294, progress = 0.72, t = 4.91 s / 263.77 tokens per second 7.28.385.218 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 998, t_last = 319551013387 7.28.385.514 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.735 MiB) 7.28.385.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.877 MiB) 7.28.385.538 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.829 MiB) 7.28.385.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.814 MiB) 7.28.386.309 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.445 MiB) 7.28.981.080 I slot launch_slot_: id 0 | task 7431 | processing task, is_child = 0 7.28.981.684 I slot print_timing: id 1 | task 7425 | prompt processing, n_tokens = 1019, progress = 1.00, t = 5.81 s / 175.47 tokens per second 7.28.985.915 I slot print_timing: id 2 | task 7426 | prompt processing, n_tokens = 914, progress = 1.00, t = 5.81 s / 157.41 tokens per second 7.28.989.968 I slot print_timing: id 3 | task 7427 | prompt processing, n_tokens = 1806, progress = 1.00, t = 5.81 s / 311.07 tokens per second 7.30.310.479 I slot print_timing: id 1 | task 7425 | prompt eval time = 7117.58 ms / 1023 tokens ( 6.96 ms per token, 143.73 tokens per second) 7.30.310.494 I slot print_timing: id 1 | task 7425 | eval time = 614.95 ms / 2 tokens ( 614.95 ms per token, 1.63 tokens per second) 7.30.310.495 I slot print_timing: id 1 | task 7425 | total time = 7732.53 ms / 1025 tokens 7.30.310.497 I slot print_timing: id 1 | task 7425 | graphs reused = 6354 7.30.310.498 I slot print_timing: id 1 | task 7425 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.310.639 I slot release: id 1 | task 7425 | stop processing: n_tokens = 1033, truncated = 0 7.30.312.972 I slot print_timing: id 2 | task 7426 | prompt eval time = 7119.35 ms / 918 tokens ( 7.76 ms per token, 128.94 tokens per second) 7.30.312.980 I slot print_timing: id 2 | task 7426 | eval time = 614.91 ms / 2 tokens ( 614.91 ms per token, 1.63 tokens per second) 7.30.312.982 I slot print_timing: id 2 | task 7426 | total time = 7734.26 ms / 920 tokens 7.30.312.983 I slot print_timing: id 2 | task 7426 | graphs reused = 6354 7.30.312.984 I slot print_timing: id 2 | task 7426 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.313.105 I slot release: id 2 | task 7426 | stop processing: n_tokens = 928, truncated = 0 7.30.315.230 I slot print_timing: id 3 | task 7427 | prompt eval time = 7120.74 ms / 1810 tokens ( 3.93 ms per token, 254.19 tokens per second) 7.30.315.239 I slot print_timing: id 3 | task 7427 | eval time = 615.04 ms / 2 tokens ( 615.04 ms per token, 1.63 tokens per second) 7.30.315.240 I slot print_timing: id 3 | task 7427 | total time = 7735.78 ms / 1812 tokens 7.30.315.242 I slot print_timing: id 3 | task 7427 | graphs reused = 6354 7.30.315.243 I slot print_timing: id 3 | task 7427 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.315.465 I slot release: id 3 | task 7427 | stop processing: n_tokens = 1820, truncated = 0 7.30.330.722 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1033, t_last = 319553834421 7.30.330.866 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 51.092 MiB) 7.30.330.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.539 MiB) 7.30.331.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.154 MiB) 7.30.331.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.660 MiB) 7.30.331.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.954 MiB) 7.30.668.556 I slot launch_slot_: id 1 | task 7435 | processing task, is_child = 0 7.30.668.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.907 MiB) 7.30.669.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.430 MiB) 7.30.670.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 49.123 MiB) 7.30.671.335 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.982 MiB) 7.30.671.931 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.892 MiB) 7.30.672.445 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 7.30.705.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 7.30.706.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.278 MiB) 7.30.706.502 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.430 MiB) 7.30.706.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 7.30.707.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.321 MiB) 7.30.707.605 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 7.30.707.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.521 MiB) 7.30.733.924 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 319553836887 7.30.734.119 I slot launch_slot_: id 2 | task 7436 | processing task, is_child = 0 7.30.734.229 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1820, t_last = 319553839250 7.30.734.376 I slot launch_slot_: id 3 | task 7437 | processing task, is_child = 0 7.34.065.182 I slot print_timing: id 0 | task 7431 | prompt eval time = 3053.49 ms / 934 tokens ( 3.27 ms per token, 305.88 tokens per second) 7.34.065.195 I slot print_timing: id 0 | task 7431 | eval time = 2030.55 ms / 2 tokens ( 2030.55 ms per token, 0.49 tokens per second) 7.34.065.196 I slot print_timing: id 0 | task 7431 | total time = 5084.04 ms / 936 tokens 7.34.065.198 I slot print_timing: id 0 | task 7431 | graphs reused = 6355 7.34.065.200 I slot print_timing: id 0 | task 7431 | graph reallocs = 0 / 0 (same size) / (changed size) 7.34.065.359 I slot release: id 0 | task 7431 | stop processing: n_tokens = 944, truncated = 0 7.34.065.422 I slot print_timing: id 1 | task 7435 | prompt processing, n_tokens = 759, progress = 0.87, t = 3.32 s / 228.66 tokens per second 7.34.072.653 I slot print_timing: id 2 | task 7436 | prompt processing, n_tokens = 590, progress = 0.84, t = 3.32 s / 177.80 tokens per second 7.34.076.607 I slot print_timing: id 3 | task 7437 | prompt processing, n_tokens = 590, progress = 0.81, t = 3.32 s / 177.83 tokens per second 7.34.638.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 944, t_last = 319557589141 7.34.638.917 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.753 MiB) 7.34.638.927 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.708 MiB) 7.34.638.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.507 MiB) 7.34.638.934 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 7.34.639.472 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.648 MiB) 7.34.639.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.999 MiB) 7.34.640.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.231 MiB) 7.34.717.430 I slot launch_slot_: id 0 | task 7441 | processing task, is_child = 0 7.34.717.931 I slot print_timing: id 1 | task 7435 | prompt processing, n_tokens = 868, progress = 1.00, t = 3.90 s / 222.74 tokens per second 7.34.721.956 I slot print_timing: id 2 | task 7436 | prompt processing, n_tokens = 696, progress = 0.99, t = 3.90 s / 178.64 tokens per second 7.34.725.879 I slot print_timing: id 3 | task 7437 | prompt processing, n_tokens = 724, progress = 0.99, t = 3.90 s / 185.86 tokens per second 7.35.791.038 I slot print_timing: id 1 | task 7435 | prompt eval time = 4352.72 ms / 872 tokens ( 4.99 ms per token, 200.33 tokens per second) 7.35.791.055 I slot print_timing: id 1 | task 7435 | eval time = 696.43 ms / 2 tokens ( 696.43 ms per token, 1.44 tokens per second) 7.35.791.061 I slot print_timing: id 1 | task 7435 | total time = 5049.15 ms / 874 tokens 7.35.791.063 I slot print_timing: id 1 | task 7435 | graphs reused = 6355 7.35.791.064 I slot print_timing: id 1 | task 7435 | graph reallocs = 0 / 0 (same size) / (changed size) 7.35.791.207 I slot release: id 1 | task 7435 | stop processing: n_tokens = 882, truncated = 0 7.35.794.260 I slot print_timing: id 2 | task 7436 | prompt eval time = 4354.07 ms / 700 tokens ( 6.22 ms per token, 160.77 tokens per second) 7.35.794.266 I slot print_timing: id 2 | task 7436 | eval time = 697.48 ms / 2 tokens ( 697.48 ms per token, 1.43 tokens per second) 7.35.794.267 I slot print_timing: id 2 | task 7436 | total time = 5051.55 ms / 702 tokens 7.35.794.268 I slot print_timing: id 2 | task 7436 | graphs reused = 6355 7.35.794.269 I slot print_timing: id 2 | task 7436 | graph reallocs = 0 / 0 (same size) / (changed size) 7.35.794.418 I slot release: id 2 | task 7436 | stop processing: n_tokens = 710, truncated = 0 7.35.796.474 I slot print_timing: id 3 | task 7437 | prompt eval time = 4355.42 ms / 728 tokens ( 5.98 ms per token, 167.15 tokens per second) 7.35.796.481 I slot print_timing: id 3 | task 7437 | eval time = 697.64 ms / 2 tokens ( 697.64 ms per token, 1.43 tokens per second) 7.35.796.482 I slot print_timing: id 3 | task 7437 | total time = 5053.07 ms / 730 tokens 7.35.796.483 I slot print_timing: id 3 | task 7437 | graphs reused = 6355 7.35.796.484 I slot print_timing: id 3 | task 7437 | graph reallocs = 0 / 0 (same size) / (changed size) 7.35.796.562 I slot release: id 3 | task 7437 | stop processing: n_tokens = 738, truncated = 0 7.36.064.951 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.882 7.36.065.107 I slot launch_slot_: id 2 | task 7446 | processing task, is_child = 0 7.36.065.276 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.063 MiB) 7.36.065.282 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 7.36.065.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.015 MiB) 7.36.065.532 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.923 MiB) 7.36.066.260 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.216 MiB) 7.36.066.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.324 MiB) 7.36.093.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.354 MiB) 7.36.093.553 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.091 MiB) 7.36.094.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.879 MiB) 7.36.094.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.368 MiB) 7.36.094.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.660 MiB) 7.36.115.936 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.848 7.36.116.019 I slot launch_slot_: id 3 | task 7447 | processing task, is_child = 0 7.36.116.107 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 319559314989 7.36.116.229 I slot launch_slot_: id 1 | task 7448 | processing task, is_child = 0 7.37.047.574 I slot print_timing: id 0 | task 7441 | prompt eval time = 1347.48 ms / 703 tokens ( 1.92 ms per token, 521.71 tokens per second) 7.37.047.578 I slot print_timing: id 0 | task 7441 | eval time = 982.63 ms / 2 tokens ( 982.63 ms per token, 1.02 tokens per second) 7.37.047.578 I slot print_timing: id 0 | task 7441 | total time = 2330.12 ms / 705 tokens 7.37.047.578 I slot print_timing: id 0 | task 7441 | graphs reused = 6355 7.37.047.579 I slot print_timing: id 0 | task 7441 | graph reallocs = 0 / 0 (same size) / (changed size) 7.37.047.649 I slot release: id 0 | task 7441 | stop processing: n_tokens = 713, truncated = 0 7.37.769.110 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 713, t_last = 319560571432 7.37.769.222 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.075 MiB) 7.37.769.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.555 MiB) 7.37.769.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.493 MiB) 7.37.769.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 7.37.770.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.216 MiB) 7.37.770.989 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.306 MiB) 7.37.787.341 I slot launch_slot_: id 0 | task 7451 | processing task, is_child = 0 7.38.779.447 I slot print_timing: id 2 | task 7446 | prompt eval time = 1651.07 ms / 89 tokens ( 18.55 ms per token, 53.90 tokens per second) 7.38.779.450 I slot print_timing: id 2 | task 7446 | eval time = 1011.50 ms / 2 tokens ( 1011.50 ms per token, 0.99 tokens per second) 7.38.779.450 I slot print_timing: id 2 | task 7446 | total time = 2662.57 ms / 91 tokens 7.38.779.451 I slot print_timing: id 2 | task 7446 | graphs reused = 6355 7.38.779.451 I slot print_timing: id 2 | task 7446 | graph reallocs = 0 / 0 (same size) / (changed size) 7.38.779.510 I slot release: id 2 | task 7446 | stop processing: n_tokens = 716, truncated = 0 7.38.780.649 I slot print_timing: id 3 | task 7447 | prompt eval time = 1649.48 ms / 95 tokens ( 17.36 ms per token, 57.59 tokens per second) 7.38.780.655 I slot print_timing: id 3 | task 7447 | eval time = 1011.55 ms / 2 tokens ( 1011.55 ms per token, 0.99 tokens per second) 7.38.780.655 I slot print_timing: id 3 | task 7447 | total time = 2661.02 ms / 97 tokens 7.38.780.656 I slot print_timing: id 3 | task 7447 | graphs reused = 6355 7.38.780.656 I slot print_timing: id 3 | task 7447 | graph reallocs = 0 / 0 (same size) / (changed size) 7.38.780.699 I slot release: id 3 | task 7447 | stop processing: n_tokens = 722, truncated = 0 7.39.443.674 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 319562303292 7.39.443.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 7.39.443.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.845 MiB) 7.39.444.428 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.829 MiB) 7.39.444.994 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.738 MiB) 7.39.445.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.354 MiB) 7.39.445.909 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.292 MiB) 7.39.465.998 I slot launch_slot_: id 2 | task 7454 | processing task, is_child = 0 7.39.466.063 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.848 MiB) 7.39.466.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.894 MiB) 7.39.466.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.939 MiB) 7.39.466.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.770 MiB) 7.39.466.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 35.199 MiB) 7.39.467.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.293 MiB) 7.39.467.586 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.708 MiB) 7.39.487.003 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 722, t_last = 319562304481 7.39.487.126 I slot launch_slot_: id 3 | task 7455 | processing task, is_child = 0 7.41.297.367 I slot print_timing: id 1 | task 7448 | prompt eval time = 3327.43 ms / 864 tokens ( 3.85 ms per token, 259.66 tokens per second) 7.41.297.376 I slot print_timing: id 1 | task 7448 | eval time = 1853.69 ms / 2 tokens ( 1853.69 ms per token, 0.54 tokens per second) 7.41.297.376 I slot print_timing: id 1 | task 7448 | total time = 5181.12 ms / 866 tokens 7.41.297.377 I slot print_timing: id 1 | task 7448 | graphs reused = 6355 7.41.297.377 I slot print_timing: id 1 | task 7448 | graph reallocs = 0 / 0 (same size) / (changed size) 7.41.297.450 I slot release: id 1 | task 7448 | stop processing: n_tokens = 874, truncated = 0 7.41.297.473 I slot print_timing: id 0 | task 7451 | prompt processing, n_tokens = 977, progress = 1.00, t = 3.51 s / 278.44 tokens per second 7.42.549.963 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 874, t_last = 319564821232 7.42.550.064 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.891 MiB) 7.42.550.069 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.883 MiB) 7.42.550.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.662 MiB) 7.42.550.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.109 MiB) 7.42.551.295 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.846 MiB) 7.42.551.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.784 MiB) 7.42.564.879 I slot launch_slot_: id 1 | task 7458 | processing task, is_child = 0 7.42.565.084 I slot print_timing: id 2 | task 7454 | prompt processing, n_tokens = 850, progress = 0.86, t = 3.06 s / 278.00 tokens per second 7.42.566.844 I slot print_timing: id 3 | task 7455 | prompt processing, n_tokens = 850, progress = 0.83, t = 3.06 s / 278.06 tokens per second 7.43.942.699 I slot print_timing: id 0 | task 7451 | prompt eval time = 4762.60 ms / 981 tokens ( 4.85 ms per token, 205.98 tokens per second) 7.43.942.703 I slot print_timing: id 0 | task 7451 | eval time = 1392.74 ms / 2 tokens ( 1392.74 ms per token, 0.72 tokens per second) 7.43.942.703 I slot print_timing: id 0 | task 7451 | total time = 6155.34 ms / 983 tokens 7.43.942.704 I slot print_timing: id 0 | task 7451 | graphs reused = 6355 7.43.942.704 I slot print_timing: id 0 | task 7451 | graph reallocs = 0 / 0 (same size) / (changed size) 7.43.942.791 I slot release: id 0 | task 7451 | stop processing: n_tokens = 991, truncated = 0 7.43.946.615 I slot print_timing: id 2 | task 7454 | prompt processing, n_tokens = 991, progress = 1.00, t = 4.45 s / 222.69 tokens per second 7.43.951.843 I slot print_timing: id 3 | task 7455 | prompt processing, n_tokens = 1021, progress = 1.00, t = 4.45 s / 229.46 tokens per second 7.44.629.960 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.894 7.44.630.100 I slot launch_slot_: id 0 | task 7461 | processing task, is_child = 0 7.45.119.817 I slot print_timing: id 2 | task 7454 | prompt eval time = 5137.42 ms / 995 tokens ( 5.16 ms per token, 193.68 tokens per second) 7.45.119.819 I slot print_timing: id 2 | task 7454 | eval time = 491.03 ms / 2 tokens ( 491.03 ms per token, 2.04 tokens per second) 7.45.119.820 I slot print_timing: id 2 | task 7454 | total time = 5628.45 ms / 997 tokens 7.45.119.820 I slot print_timing: id 2 | task 7454 | graphs reused = 6355 7.45.119.821 I slot print_timing: id 2 | task 7454 | graph reallocs = 0 / 0 (same size) / (changed size) 7.45.119.891 I slot release: id 2 | task 7454 | stop processing: n_tokens = 1005, truncated = 0 7.45.121.030 I slot print_timing: id 3 | task 7455 | prompt eval time = 5137.93 ms / 1025 tokens ( 5.01 ms per token, 199.50 tokens per second) 7.45.121.033 I slot print_timing: id 3 | task 7455 | eval time = 491.08 ms / 2 tokens ( 491.08 ms per token, 2.04 tokens per second) 7.45.121.033 I slot print_timing: id 3 | task 7455 | total time = 5629.01 ms / 1027 tokens 7.45.121.034 I slot print_timing: id 3 | task 7455 | graphs reused = 6355 7.45.121.034 I slot print_timing: id 3 | task 7455 | graph reallocs = 0 / 0 (same size) / (changed size) 7.45.121.074 I slot release: id 3 | task 7455 | stop processing: n_tokens = 1035, truncated = 0 7.45.169.011 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1005, t_last = 319568643673 7.45.169.099 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.954 MiB) 7.45.169.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.016 MiB) 7.45.169.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.953 MiB) 7.45.169.560 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.414 MiB) 7.45.169.883 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.194 MiB) 7.45.177.196 I slot launch_slot_: id 2 | task 7464 | processing task, is_child = 0 7.45.177.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.213 MiB) 7.45.183.715 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 319568644856 7.45.183.855 I slot launch_slot_: id 3 | task 7465 | processing task, is_child = 0 7.46.604.040 I slot print_timing: id 0 | task 7461 | prompt eval time = 537.75 ms / 105 tokens ( 5.12 ms per token, 195.26 tokens per second) 7.46.604.042 I slot print_timing: id 0 | task 7461 | eval time = 1436.17 ms / 2 tokens ( 1436.17 ms per token, 0.70 tokens per second) 7.46.604.043 I slot print_timing: id 0 | task 7461 | total time = 1973.92 ms / 107 tokens 7.46.604.043 I slot print_timing: id 0 | task 7461 | graphs reused = 6355 7.46.604.044 I slot print_timing: id 0 | task 7461 | graph reallocs = 0 / 0 (same size) / (changed size) 7.46.604.094 I slot release: id 0 | task 7461 | stop processing: n_tokens = 992, truncated = 0 7.46.605.179 I slot print_timing: id 1 | task 7458 | prompt eval time = 2604.12 ms / 987 tokens ( 2.64 ms per token, 379.02 tokens per second) 7.46.605.184 I slot print_timing: id 1 | task 7458 | eval time = 1436.17 ms / 2 tokens ( 1436.17 ms per token, 0.70 tokens per second) 7.46.605.184 I slot print_timing: id 1 | task 7458 | total time = 4040.29 ms / 989 tokens 7.46.605.185 I slot print_timing: id 1 | task 7458 | graphs reused = 6355 7.46.605.185 I slot print_timing: id 1 | task 7458 | graph reallocs = 0 / 0 (same size) / (changed size) 7.46.605.214 I slot release: id 1 | task 7458 | stop processing: n_tokens = 997, truncated = 0 7.47.500.333 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 992, t_last = 319570127876 7.47.681.345 I slot launch_slot_: id 0 | task 7468 | processing task, is_child = 0 7.47.681.538 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.178 MiB) 7.47.694.604 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 997, t_last = 319570128996 7.47.694.831 I slot launch_slot_: id 1 | task 7469 | processing task, is_child = 0 7.49.793.663 I slot print_timing: id 2 | task 7464 | prompt processing, n_tokens = 871, progress = 1.00, t = 4.43 s / 196.49 tokens per second 7.49.795.869 I slot print_timing: id 3 | task 7465 | prompt processing, n_tokens = 1010, progress = 1.00, t = 4.43 s / 227.85 tokens per second 7.51.003.420 I slot print_timing: id 0 | task 7468 | prompt processing, n_tokens = 768, progress = 0.86, t = 3.31 s / 232.28 tokens per second 7.51.005.410 I slot print_timing: id 1 | task 7469 | prompt processing, n_tokens = 768, progress = 0.77, t = 3.31 s / 232.31 tokens per second 7.51.686.062 I slot print_timing: id 2 | task 7464 | prompt eval time = 5818.45 ms / 875 tokens ( 6.65 ms per token, 150.38 tokens per second) 7.51.686.065 I slot print_timing: id 2 | task 7464 | eval time = 683.74 ms / 2 tokens ( 683.74 ms per token, 1.46 tokens per second) 7.51.686.065 I slot print_timing: id 2 | task 7464 | total time = 6502.19 ms / 877 tokens 7.51.686.066 I slot print_timing: id 2 | task 7464 | graphs reused = 6355 7.51.686.066 I slot print_timing: id 2 | task 7464 | graph reallocs = 0 / 0 (same size) / (changed size) 7.51.686.110 I slot release: id 2 | task 7464 | stop processing: n_tokens = 885, truncated = 0 7.51.687.227 I slot print_timing: id 3 | task 7465 | prompt eval time = 5819.32 ms / 1014 tokens ( 5.74 ms per token, 174.25 tokens per second) 7.51.687.231 I slot print_timing: id 3 | task 7465 | eval time = 683.81 ms / 2 tokens ( 683.81 ms per token, 1.46 tokens per second) 7.51.687.231 I slot print_timing: id 3 | task 7465 | total time = 6503.13 ms / 1016 tokens 7.51.687.231 I slot print_timing: id 3 | task 7465 | graphs reused = 6355 7.51.687.232 I slot print_timing: id 3 | task 7465 | graph reallocs = 0 / 0 (same size) / (changed size) 7.51.687.294 I slot release: id 3 | task 7465 | stop processing: n_tokens = 1024, truncated = 0 7.51.687.311 I slot print_timing: id 0 | task 7468 | prompt processing, n_tokens = 890, progress = 1.00, t = 3.99 s / 223.05 tokens per second 7.51.690.591 I slot print_timing: id 1 | task 7469 | prompt processing, n_tokens = 998, progress = 1.00, t = 3.99 s / 250.14 tokens per second 7.51.729.598 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.785 7.51.729.674 I slot launch_slot_: id 3 | task 7474 | processing task, is_child = 0 7.51.729.754 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 350.955 MiB) 7.51.735.639 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 319575209892 7.51.735.761 I slot launch_slot_: id 2 | task 7475 | processing task, is_child = 0 7.52.729.558 I slot print_timing: id 0 | task 7468 | prompt eval time = 4033.69 ms / 894 tokens ( 4.51 ms per token, 221.63 tokens per second) 7.52.729.561 I slot print_timing: id 0 | task 7468 | eval time = 1001.02 ms / 2 tokens ( 1001.02 ms per token, 1.00 tokens per second) 7.52.729.562 I slot print_timing: id 0 | task 7468 | total time = 5034.71 ms / 896 tokens 7.52.729.562 I slot print_timing: id 0 | task 7468 | graphs reused = 6355 7.52.729.563 I slot print_timing: id 0 | task 7468 | graph reallocs = 0 / 0 (same size) / (changed size) 7.52.729.632 I slot release: id 0 | task 7468 | stop processing: n_tokens = 904, truncated = 0 7.52.730.746 I slot print_timing: id 1 | task 7469 | prompt eval time = 4034.32 ms / 1002 tokens ( 4.03 ms per token, 248.37 tokens per second) 7.52.730.747 I slot print_timing: id 1 | task 7469 | eval time = 1001.15 ms / 2 tokens ( 1001.15 ms per token, 1.00 tokens per second) 7.52.730.749 I slot print_timing: id 1 | task 7469 | total time = 5035.48 ms / 1004 tokens 7.52.730.749 I slot print_timing: id 1 | task 7469 | graphs reused = 6355 7.52.730.749 I slot print_timing: id 1 | task 7469 | graph reallocs = 0 / 0 (same size) / (changed size) 7.52.730.786 I slot release: id 1 | task 7469 | stop processing: n_tokens = 1012, truncated = 0 7.53.287.595 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.889 7.53.287.693 I slot launch_slot_: id 0 | task 7478 | processing task, is_child = 0 7.53.287.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.932 MiB) 7.53.297.048 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1012, t_last = 319576254568 7.53.297.186 I slot launch_slot_: id 1 | task 7479 | processing task, is_child = 0 7.54.566.149 I slot print_timing: id 3 | task 7474 | prompt eval time = 1551.62 ms / 102 tokens ( 15.21 ms per token, 65.74 tokens per second) 7.54.566.154 I slot print_timing: id 3 | task 7474 | eval time = 1278.54 ms / 2 tokens ( 1278.54 ms per token, 0.78 tokens per second) 7.54.566.154 I slot print_timing: id 3 | task 7474 | total time = 2830.16 ms / 104 tokens 7.54.566.155 I slot print_timing: id 3 | task 7474 | graphs reused = 6355 7.54.566.156 I slot print_timing: id 3 | task 7474 | graph reallocs = 0 / 0 (same size) / (changed size) 7.54.566.232 I slot release: id 3 | task 7474 | stop processing: n_tokens = 907, truncated = 0 7.55.188.871 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 319578090014 7.55.188.977 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.095 MiB) 7.55.197.029 I slot launch_slot_: id 3 | task 7482 | processing task, is_child = 0 7.56.171.565 I slot print_timing: id 0 | task 7478 | prompt eval time = 1890.55 ms / 81 tokens ( 23.34 ms per token, 42.84 tokens per second) 7.56.171.571 I slot print_timing: id 0 | task 7478 | eval time = 983.81 ms / 2 tokens ( 983.81 ms per token, 1.02 tokens per second) 7.56.171.572 I slot print_timing: id 0 | task 7478 | total time = 2874.36 ms / 83 tokens 7.56.171.573 I slot print_timing: id 0 | task 7478 | graphs reused = 6355 7.56.171.573 I slot print_timing: id 0 | task 7478 | graph reallocs = 0 / 0 (same size) / (changed size) 7.56.171.651 I slot release: id 0 | task 7478 | stop processing: n_tokens = 886, truncated = 0 7.56.172.785 I slot print_timing: id 2 | task 7475 | prompt eval time = 3453.09 ms / 983 tokens ( 3.51 ms per token, 284.67 tokens per second) 7.56.172.790 I slot print_timing: id 2 | task 7475 | eval time = 983.92 ms / 2 tokens ( 983.92 ms per token, 1.02 tokens per second) 7.56.172.790 I slot print_timing: id 2 | task 7475 | total time = 4437.02 ms / 985 tokens 7.56.172.791 I slot print_timing: id 2 | task 7475 | graphs reused = 6355 7.56.172.791 I slot print_timing: id 2 | task 7475 | graph reallocs = 0 / 0 (same size) / (changed size) 7.56.172.839 I slot release: id 2 | task 7475 | stop processing: n_tokens = 993, truncated = 0 7.56.869.071 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 319579695433 7.56.882.832 I slot launch_slot_: id 0 | task 7485 | processing task, is_child = 0 7.56.882.923 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.434 MiB) 7.56.891.733 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 993, t_last = 319579696621 7.56.891.864 I slot launch_slot_: id 2 | task 7486 | processing task, is_child = 0 7.59.137.051 I slot print_timing: id 1 | task 7479 | prompt eval time = 3570.13 ms / 931 tokens ( 3.83 ms per token, 260.77 tokens per second) 7.59.137.054 I slot print_timing: id 1 | task 7479 | eval time = 2267.97 ms / 2 tokens ( 2267.97 ms per token, 0.44 tokens per second) 7.59.137.055 I slot print_timing: id 1 | task 7479 | total time = 5838.11 ms / 933 tokens 7.59.137.055 I slot print_timing: id 1 | task 7479 | graphs reused = 6355 7.59.137.056 I slot print_timing: id 1 | task 7479 | graph reallocs = 0 / 0 (same size) / (changed size) 7.59.137.131 I slot release: id 1 | task 7479 | stop processing: n_tokens = 941, truncated = 0 7.59.141.845 I slot print_timing: id 3 | task 7482 | prompt processing, n_tokens = 880, progress = 1.00, t = 3.94 s / 223.51 tokens per second 8.00.272.255 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 319582660913 8.00.272.383 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 403.801 MiB) 8.00.288.049 I slot launch_slot_: id 1 | task 7489 | processing task, is_child = 0 8.00.288.061 I slot print_timing: id 0 | task 7485 | prompt processing, n_tokens = 753, progress = 0.82, t = 3.38 s / 222.83 tokens per second 8.00.292.177 I slot print_timing: id 2 | task 7486 | prompt processing, n_tokens = 1148, progress = 0.85, t = 3.38 s / 339.74 tokens per second 8.02.320.250 I slot print_timing: id 3 | task 7482 | prompt eval time = 5073.49 ms / 884 tokens ( 5.74 ms per token, 174.24 tokens per second) 8.02.320.262 I slot print_timing: id 3 | task 7482 | eval time = 2047.99 ms / 2 tokens ( 2047.99 ms per token, 0.49 tokens per second) 8.02.320.262 I slot print_timing: id 3 | task 7482 | total time = 7121.49 ms / 886 tokens 8.02.320.263 I slot print_timing: id 3 | task 7482 | graphs reused = 6355 8.02.320.264 I slot print_timing: id 3 | task 7482 | graph reallocs = 0 / 0 (same size) / (changed size) 8.02.320.344 I slot release: id 3 | task 7482 | stop processing: n_tokens = 894, truncated = 0 8.02.320.369 I slot print_timing: id 0 | task 7485 | prompt processing, n_tokens = 914, progress = 1.00, t = 5.43 s / 168.41 tokens per second 8.02.325.620 I slot print_timing: id 2 | task 7486 | prompt processing, n_tokens = 1349, progress = 1.00, t = 5.43 s / 248.57 tokens per second 8.02.903.168 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 319585844126 8.02.916.644 I slot launch_slot_: id 3 | task 7492 | processing task, is_child = 0 8.04.513.373 I slot print_timing: id 0 | task 7485 | prompt eval time = 6010.15 ms / 918 tokens ( 6.55 ms per token, 152.74 tokens per second) 8.04.513.386 I slot print_timing: id 0 | task 7485 | eval time = 1611.30 ms / 2 tokens ( 1611.30 ms per token, 0.62 tokens per second) 8.04.513.388 I slot print_timing: id 0 | task 7485 | total time = 7621.45 ms / 920 tokens 8.04.513.397 I slot print_timing: id 0 | task 7485 | graphs reused = 6355 8.04.513.399 I slot print_timing: id 0 | task 7485 | graph reallocs = 0 / 0 (same size) / (changed size) 8.04.513.554 I slot release: id 0 | task 7485 | stop processing: n_tokens = 928, truncated = 0 8.04.515.941 I slot print_timing: id 2 | task 7486 | prompt eval time = 6011.08 ms / 1353 tokens ( 4.44 ms per token, 225.08 tokens per second) 8.04.515.947 I slot print_timing: id 2 | task 7486 | eval time = 1612.78 ms / 2 tokens ( 1612.78 ms per token, 0.62 tokens per second) 8.04.515.948 I slot print_timing: id 2 | task 7486 | total time = 7623.86 ms / 1355 tokens 8.04.515.949 I slot print_timing: id 2 | task 7486 | graphs reused = 6355 8.04.515.950 I slot print_timing: id 2 | task 7486 | graph reallocs = 0 / 0 (same size) / (changed size) 8.04.516.082 I slot release: id 2 | task 7486 | stop processing: n_tokens = 1363, truncated = 0 8.04.516.141 I slot print_timing: id 1 | task 7489 | prompt processing, n_tokens = 1336, progress = 1.00, t = 4.22 s / 316.80 tokens per second 8.05.239.116 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 319588037336 8.05.239.446 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.635 MiB) 8.05.271.385 I slot launch_slot_: id 0 | task 7495 | processing task, is_child = 0 8.05.271.524 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 245.780 MiB) 8.05.271.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 248.171 MiB) 8.05.298.969 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.869 8.05.299.039 I slot launch_slot_: id 2 | task 7496 | processing task, is_child = 0 8.06.210.067 I slot print_timing: id 1 | task 7489 | prompt eval time = 4947.11 ms / 1340 tokens ( 3.69 ms per token, 270.86 tokens per second) 8.06.210.071 I slot print_timing: id 1 | task 7489 | eval time = 970.99 ms / 2 tokens ( 970.99 ms per token, 1.03 tokens per second) 8.06.210.071 I slot print_timing: id 1 | task 7489 | total time = 5918.10 ms / 1342 tokens 8.06.210.072 I slot print_timing: id 1 | task 7489 | graphs reused = 6355 8.06.210.072 I slot print_timing: id 1 | task 7489 | graph reallocs = 0 / 0 (same size) / (changed size) 8.06.210.142 I slot release: id 1 | task 7489 | stop processing: n_tokens = 1350, truncated = 0 8.06.215.413 I slot print_timing: id 3 | task 7492 | prompt processing, n_tokens = 1251, progress = 1.00, t = 3.29 s / 380.19 tokens per second 8.06.912.111 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1350, t_last = 319589733925 8.06.912.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.323 MiB) 8.06.939.945 I slot launch_slot_: id 1 | task 7499 | processing task, is_child = 0 8.07.650.185 I slot print_timing: id 2 | task 7496 | prompt eval time = 1611.56 ms / 121 tokens ( 13.32 ms per token, 75.08 tokens per second) 8.07.650.188 I slot print_timing: id 2 | task 7496 | eval time = 739.29 ms / 2 tokens ( 739.29 ms per token, 1.35 tokens per second) 8.07.650.189 I slot print_timing: id 2 | task 7496 | total time = 2350.85 ms / 123 tokens 8.07.650.192 I slot print_timing: id 2 | task 7496 | graphs reused = 6355 8.07.650.192 I slot print_timing: id 2 | task 7496 | graph reallocs = 0 / 0 (same size) / (changed size) 8.07.650.257 I slot release: id 2 | task 7496 | stop processing: n_tokens = 1306, truncated = 0 8.07.651.439 I slot print_timing: id 3 | task 7492 | prompt eval time = 3993.62 ms / 1255 tokens ( 3.18 ms per token, 314.25 tokens per second) 8.07.651.442 I slot print_timing: id 3 | task 7492 | eval time = 739.34 ms / 2 tokens ( 739.34 ms per token, 1.35 tokens per second) 8.07.651.445 I slot print_timing: id 3 | task 7492 | total time = 4732.95 ms / 1257 tokens 8.07.651.445 I slot print_timing: id 3 | task 7492 | graphs reused = 6355 8.07.651.446 I slot print_timing: id 3 | task 7492 | graph reallocs = 0 / 0 (same size) / (changed size) 8.07.651.499 I slot release: id 3 | task 7492 | stop processing: n_tokens = 1265, truncated = 0 8.08.302.723 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1306, t_last = 319591174039 8.08.302.888 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.136 MiB) 8.08.327.228 I slot launch_slot_: id 2 | task 7502 | processing task, is_child = 0 8.08.327.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.184 MiB) 8.08.348.659 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1265, t_last = 319591175281 8.08.348.821 I slot launch_slot_: id 3 | task 7503 | processing task, is_child = 0 8.09.748.516 I slot print_timing: id 0 | task 7495 | prompt eval time = 3003.66 ms / 782 tokens ( 3.84 ms per token, 260.35 tokens per second) 8.09.748.519 I slot print_timing: id 0 | task 7495 | eval time = 1445.80 ms / 2 tokens ( 1445.80 ms per token, 0.69 tokens per second) 8.09.748.524 I slot print_timing: id 0 | task 7495 | total time = 4449.46 ms / 784 tokens 8.09.748.525 I slot print_timing: id 0 | task 7495 | graphs reused = 6355 8.09.748.525 I slot print_timing: id 0 | task 7495 | graph reallocs = 0 / 0 (same size) / (changed size) 8.09.748.572 I slot release: id 0 | task 7495 | stop processing: n_tokens = 792, truncated = 0 8.11.057.434 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 792, t_last = 319593272354 8.11.057.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 230.309 MiB) 8.11.070.531 I slot launch_slot_: id 0 | task 7506 | processing task, is_child = 0 8.12.048.463 I slot print_timing: id 1 | task 7499 | prompt eval time = 4115.69 ms / 801 tokens ( 5.14 ms per token, 194.62 tokens per second) 8.12.048.466 I slot print_timing: id 1 | task 7499 | eval time = 991.03 ms / 2 tokens ( 991.03 ms per token, 1.01 tokens per second) 8.12.048.467 I slot print_timing: id 1 | task 7499 | total time = 5106.72 ms / 803 tokens 8.12.048.467 I slot print_timing: id 1 | task 7499 | graphs reused = 6355 8.12.048.467 I slot print_timing: id 1 | task 7499 | graph reallocs = 0 / 0 (same size) / (changed size) 8.12.048.562 I slot release: id 1 | task 7499 | stop processing: n_tokens = 811, truncated = 0 8.12.052.830 I slot print_timing: id 2 | task 7502 | prompt processing, n_tokens = 853, progress = 1.00, t = 3.70 s / 230.74 tokens per second 8.12.055.069 I slot print_timing: id 3 | task 7503 | prompt processing, n_tokens = 882, progress = 1.00, t = 3.70 s / 238.60 tokens per second 8.12.704.731 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 811, t_last = 319595572344 8.12.704.830 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.776 MiB) 8.12.718.435 I slot launch_slot_: id 1 | task 7509 | processing task, is_child = 0 8.13.566.952 I slot print_timing: id 2 | task 7502 | prompt eval time = 4352.89 ms / 857 tokens ( 5.08 ms per token, 196.88 tokens per second) 8.13.566.955 I slot print_timing: id 2 | task 7502 | eval time = 863.56 ms / 2 tokens ( 863.56 ms per token, 1.16 tokens per second) 8.13.566.956 I slot print_timing: id 2 | task 7502 | total time = 5216.45 ms / 859 tokens 8.13.566.957 I slot print_timing: id 2 | task 7502 | graphs reused = 6355 8.13.566.957 I slot print_timing: id 2 | task 7502 | graph reallocs = 0 / 0 (same size) / (changed size) 8.13.567.038 I slot release: id 2 | task 7502 | stop processing: n_tokens = 867, truncated = 0 8.13.568.181 I slot print_timing: id 3 | task 7503 | prompt eval time = 4353.96 ms / 886 tokens ( 4.91 ms per token, 203.49 tokens per second) 8.13.568.184 I slot print_timing: id 3 | task 7503 | eval time = 863.45 ms / 2 tokens ( 863.45 ms per token, 1.16 tokens per second) 8.13.568.185 I slot print_timing: id 3 | task 7503 | total time = 5217.41 ms / 888 tokens 8.13.568.185 I slot print_timing: id 3 | task 7503 | graphs reused = 6355 8.13.568.185 I slot print_timing: id 3 | task 7503 | graph reallocs = 0 / 0 (same size) / (changed size) 8.13.568.224 I slot release: id 3 | task 7503 | stop processing: n_tokens = 896, truncated = 0 8.14.122.372 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 867, t_last = 319597090820 8.14.122.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.981 MiB) 8.14.132.905 I slot launch_slot_: id 2 | task 7512 | processing task, is_child = 0 8.14.132.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 234.388 MiB) 8.14.143.745 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 896, t_last = 319597092006 8.14.143.871 I slot launch_slot_: id 3 | task 7513 | processing task, is_child = 0 8.15.375.268 I slot print_timing: id 0 | task 7506 | prompt eval time = 3051.82 ms / 778 tokens ( 3.92 ms per token, 254.93 tokens per second) 8.15.375.270 I slot print_timing: id 0 | task 7506 | eval time = 1252.89 ms / 2 tokens ( 1252.89 ms per token, 0.80 tokens per second) 8.15.375.271 I slot print_timing: id 0 | task 7506 | total time = 4304.71 ms / 780 tokens 8.15.375.272 I slot print_timing: id 0 | task 7506 | graphs reused = 6355 8.15.375.272 I slot print_timing: id 0 | task 7506 | graph reallocs = 0 / 0 (same size) / (changed size) 8.15.375.318 I slot release: id 0 | task 7506 | stop processing: n_tokens = 788, truncated = 0 8.16.718.981 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.849 (> 0.100 thold), f_keep = 0.862 8.16.719.120 I slot launch_slot_: id 0 | task 7516 | processing task, is_child = 0 8.17.425.322 I slot print_timing: id 1 | task 7509 | prompt eval time = 3996.77 ms / 843 tokens ( 4.74 ms per token, 210.92 tokens per second) 8.17.425.325 I slot print_timing: id 1 | task 7509 | eval time = 706.34 ms / 2 tokens ( 706.34 ms per token, 1.42 tokens per second) 8.17.425.325 I slot print_timing: id 1 | task 7509 | total time = 4703.11 ms / 845 tokens 8.17.425.326 I slot print_timing: id 1 | task 7509 | graphs reused = 6355 8.17.425.326 I slot print_timing: id 1 | task 7509 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.425.373 I slot release: id 1 | task 7509 | stop processing: n_tokens = 853, truncated = 0 8.17.428.229 I slot print_timing: id 2 | task 7512 | prompt processing, n_tokens = 758, progress = 0.99, t = 3.28 s / 231.19 tokens per second 8.17.430.265 I slot print_timing: id 3 | task 7513 | prompt processing, n_tokens = 764, progress = 0.99, t = 3.28 s / 233.04 tokens per second 8.17.499.396 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 853, t_last = 319600949155 8.17.499.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.374 MiB) 8.17.511.556 I slot launch_slot_: id 1 | task 7519 | processing task, is_child = 0 8.18.263.874 I slot print_timing: id 0 | task 7516 | prompt eval time = 778.02 ms / 121 tokens ( 6.43 ms per token, 155.52 tokens per second) 8.18.263.879 I slot print_timing: id 0 | task 7516 | eval time = 766.72 ms / 2 tokens ( 766.72 ms per token, 1.30 tokens per second) 8.18.263.880 I slot print_timing: id 0 | task 7516 | total time = 1544.73 ms / 123 tokens 8.18.263.880 I slot print_timing: id 0 | task 7516 | graphs reused = 6355 8.18.263.881 I slot print_timing: id 0 | task 7516 | graph reallocs = 0 / 0 (same size) / (changed size) 8.18.263.933 I slot release: id 0 | task 7516 | stop processing: n_tokens = 801, truncated = 0 8.18.265.757 I slot print_timing: id 2 | task 7512 | prompt eval time = 3352.71 ms / 762 tokens ( 4.40 ms per token, 227.28 tokens per second) 8.18.265.761 I slot print_timing: id 2 | task 7512 | eval time = 767.46 ms / 2 tokens ( 767.46 ms per token, 1.30 tokens per second) 8.18.265.762 I slot print_timing: id 2 | task 7512 | total time = 4120.17 ms / 764 tokens 8.18.265.762 I slot print_timing: id 2 | task 7512 | graphs reused = 6355 8.18.265.763 I slot print_timing: id 2 | task 7512 | graph reallocs = 0 / 0 (same size) / (changed size) 8.18.265.791 I slot release: id 2 | task 7512 | stop processing: n_tokens = 772, truncated = 0 8.18.267.750 I slot print_timing: id 3 | task 7513 | prompt eval time = 3353.61 ms / 768 tokens ( 4.37 ms per token, 229.01 tokens per second) 8.18.267.753 I slot print_timing: id 3 | task 7513 | eval time = 768.36 ms / 2 tokens ( 768.36 ms per token, 1.30 tokens per second) 8.18.267.754 I slot print_timing: id 3 | task 7513 | total time = 4121.97 ms / 770 tokens 8.18.267.755 I slot print_timing: id 3 | task 7513 | graphs reused = 6355 8.18.267.755 I slot print_timing: id 3 | task 7513 | graph reallocs = 0 / 0 (same size) / (changed size) 8.18.267.784 I slot release: id 3 | task 7513 | stop processing: n_tokens = 778, truncated = 0 8.18.275.364 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 801, t_last = 319601787715 8.18.275.503 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.859 MiB) 8.18.905.232 I slot launch_slot_: id 0 | task 7522 | processing task, is_child = 0 8.18.905.434 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.360 MiB) 8.18.928.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.014 MiB) 8.18.939.068 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 319601789573 8.18.939.234 I slot launch_slot_: id 2 | task 7523 | processing task, is_child = 0 8.18.939.322 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 319601791566 8.18.939.452 I slot launch_slot_: id 3 | task 7524 | processing task, is_child = 0 8.21.169.750 I slot print_timing: id 1 | task 7519 | prompt processing, n_tokens = 948, progress = 1.00, t = 3.61 s / 262.75 tokens per second 8.23.224.515 I slot print_timing: id 0 | task 7522 | prompt processing, n_tokens = 817, progress = 0.88, t = 4.28 s / 190.71 tokens per second 8.23.228.368 I slot print_timing: id 2 | task 7523 | prompt processing, n_tokens = 817, progress = 0.87, t = 4.28 s / 190.83 tokens per second 8.23.231.407 I slot print_timing: id 3 | task 7524 | prompt processing, n_tokens = 817, progress = 0.88, t = 4.28 s / 190.84 tokens per second 8.23.915.143 I slot print_timing: id 1 | task 7519 | prompt eval time = 5712.92 ms / 952 tokens ( 6.00 ms per token, 166.64 tokens per second) 8.23.915.147 I slot print_timing: id 1 | task 7519 | eval time = 690.64 ms / 2 tokens ( 690.64 ms per token, 1.45 tokens per second) 8.23.915.147 I slot print_timing: id 1 | task 7519 | total time = 6403.56 ms / 954 tokens 8.23.915.147 I slot print_timing: id 1 | task 7519 | graphs reused = 6355 8.23.915.148 I slot print_timing: id 1 | task 7519 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.915.200 I slot release: id 1 | task 7519 | stop processing: n_tokens = 962, truncated = 0 8.23.915.214 I slot print_timing: id 0 | task 7522 | prompt processing, n_tokens = 922, progress = 1.00, t = 4.97 s / 185.34 tokens per second 8.23.919.062 I slot print_timing: id 2 | task 7523 | prompt processing, n_tokens = 940, progress = 1.00, t = 4.97 s / 189.06 tokens per second 8.23.920.957 I slot print_timing: id 3 | task 7524 | prompt processing, n_tokens = 924, progress = 1.00, t = 4.97 s / 185.85 tokens per second 8.23.990.152 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.887 8.23.990.242 I slot launch_slot_: id 1 | task 7529 | processing task, is_child = 0 8.24.270.197 I slot print_timing: id 0 | task 7522 | prompt eval time = 5048.44 ms / 926 tokens ( 5.45 ms per token, 183.42 tokens per second) 8.24.270.200 I slot print_timing: id 0 | task 7522 | eval time = 282.29 ms / 2 tokens ( 282.29 ms per token, 3.54 tokens per second) 8.24.270.200 I slot print_timing: id 0 | task 7522 | total time = 5330.73 ms / 928 tokens 8.24.270.201 I slot print_timing: id 0 | task 7522 | graphs reused = 6355 8.24.270.201 I slot print_timing: id 0 | task 7522 | graph reallocs = 0 / 0 (same size) / (changed size) 8.24.270.249 I slot release: id 0 | task 7522 | stop processing: n_tokens = 936, truncated = 0 8.24.271.417 I slot print_timing: id 2 | task 7523 | prompt eval time = 5046.93 ms / 944 tokens ( 5.35 ms per token, 187.04 tokens per second) 8.24.271.422 I slot print_timing: id 2 | task 7523 | eval time = 282.38 ms / 2 tokens ( 282.38 ms per token, 3.54 tokens per second) 8.24.271.423 I slot print_timing: id 2 | task 7523 | total time = 5329.30 ms / 946 tokens 8.24.271.423 I slot print_timing: id 2 | task 7523 | graphs reused = 6355 8.24.271.423 I slot print_timing: id 2 | task 7523 | graph reallocs = 0 / 0 (same size) / (changed size) 8.24.271.461 I slot release: id 2 | task 7523 | stop processing: n_tokens = 954, truncated = 0 8.24.272.593 I slot print_timing: id 3 | task 7524 | prompt eval time = 5047.80 ms / 928 tokens ( 5.44 ms per token, 183.84 tokens per second) 8.24.272.595 I slot print_timing: id 3 | task 7524 | eval time = 282.45 ms / 2 tokens ( 282.45 ms per token, 3.54 tokens per second) 8.24.272.596 I slot print_timing: id 3 | task 7524 | total time = 5330.25 ms / 930 tokens 8.24.272.596 I slot print_timing: id 3 | task 7524 | graphs reused = 6355 8.24.272.596 I slot print_timing: id 3 | task 7524 | graph reallocs = 0 / 0 (same size) / (changed size) 8.24.272.618 I slot release: id 3 | task 7524 | stop processing: n_tokens = 938, truncated = 0 8.24.306.983 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 319607794031 8.24.307.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.037 MiB) 8.24.313.220 I slot launch_slot_: id 0 | task 7532 | processing task, is_child = 0 8.24.313.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 242.264 MiB) 8.24.319.391 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 233.544 MiB) 8.24.325.446 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 319607795243 8.24.325.584 I slot launch_slot_: id 2 | task 7533 | processing task, is_child = 0 8.24.325.653 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 319607796400 8.24.325.753 I slot launch_slot_: id 3 | task 7534 | processing task, is_child = 0 8.25.966.724 I slot print_timing: id 1 | task 7529 | prompt eval time = 316.73 ms / 107 tokens ( 2.96 ms per token, 337.83 tokens per second) 8.25.966.727 I slot print_timing: id 1 | task 7529 | eval time = 1659.73 ms / 2 tokens ( 1659.73 ms per token, 0.60 tokens per second) 8.25.966.728 I slot print_timing: id 1 | task 7529 | total time = 1976.46 ms / 109 tokens 8.25.966.728 I slot print_timing: id 1 | task 7529 | graphs reused = 6355 8.25.966.729 I slot print_timing: id 1 | task 7529 | graph reallocs = 0 / 0 (same size) / (changed size) 8.25.966.806 I slot release: id 1 | task 7529 | stop processing: n_tokens = 961, truncated = 0 8.27.809.713 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 319609490588 8.27.809.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.291 MiB) 8.27.887.286 I slot launch_slot_: id 1 | task 7537 | processing task, is_child = 0 8.27.887.301 I slot print_timing: id 0 | task 7532 | prompt processing, n_tokens = 668, progress = 0.85, t = 3.48 s / 191.74 tokens per second 8.27.889.817 I slot print_timing: id 2 | task 7533 | prompt processing, n_tokens = 668, progress = 0.85, t = 3.48 s / 191.75 tokens per second 8.27.891.648 I slot print_timing: id 3 | task 7534 | prompt processing, n_tokens = 818, progress = 0.85, t = 3.48 s / 234.82 tokens per second 8.29.158.902 I slot print_timing: id 0 | task 7532 | prompt processing, n_tokens = 785, progress = 0.99, t = 4.83 s / 162.42 tokens per second 8.29.240.103 I slot print_timing: id 2 | task 7533 | prompt processing, n_tokens = 785, progress = 0.99, t = 4.83 s / 162.43 tokens per second 8.29.242.137 I slot print_timing: id 3 | task 7534 | prompt processing, n_tokens = 963, progress = 1.00, t = 4.83 s / 199.27 tokens per second 8.30.208.652 I slot print_timing: id 0 | task 7532 | prompt eval time = 5595.17 ms / 789 tokens ( 7.09 ms per token, 141.01 tokens per second) 8.30.208.655 I slot print_timing: id 0 | task 7532 | eval time = 287.71 ms / 2 tokens ( 287.71 ms per token, 3.48 tokens per second) 8.30.208.655 I slot print_timing: id 0 | task 7532 | total time = 5882.89 ms / 791 tokens 8.30.208.656 I slot print_timing: id 0 | task 7532 | graphs reused = 6355 8.30.208.656 I slot print_timing: id 0 | task 7532 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.208.704 I slot release: id 0 | task 7532 | stop processing: n_tokens = 799, truncated = 0 8.30.209.855 I slot print_timing: id 2 | task 7533 | prompt eval time = 5596.14 ms / 789 tokens ( 7.09 ms per token, 140.99 tokens per second) 8.30.209.858 I slot print_timing: id 2 | task 7533 | eval time = 287.71 ms / 2 tokens ( 287.71 ms per token, 3.48 tokens per second) 8.30.209.861 I slot print_timing: id 2 | task 7533 | total time = 5883.85 ms / 791 tokens 8.30.209.861 I slot print_timing: id 2 | task 7533 | graphs reused = 6355 8.30.209.861 I slot print_timing: id 2 | task 7533 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.209.901 I slot release: id 2 | task 7533 | stop processing: n_tokens = 799, truncated = 0 8.30.211.032 I slot print_timing: id 3 | task 7534 | prompt eval time = 5597.15 ms / 967 tokens ( 5.79 ms per token, 172.77 tokens per second) 8.30.211.033 I slot print_timing: id 3 | task 7534 | eval time = 287.69 ms / 2 tokens ( 287.69 ms per token, 3.48 tokens per second) 8.30.211.034 I slot print_timing: id 3 | task 7534 | total time = 5884.85 ms / 969 tokens 8.30.211.034 I slot print_timing: id 3 | task 7534 | graphs reused = 6355 8.30.211.034 I slot print_timing: id 3 | task 7534 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.211.083 I slot release: id 3 | task 7534 | stop processing: n_tokens = 977, truncated = 0 8.30.245.683 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.874 8.30.245.748 I slot launch_slot_: id 3 | task 7542 | processing task, is_child = 0 8.30.245.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 209.775 MiB) 8.30.251.445 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.570 MiB) 8.30.257.374 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 319613732486 8.30.257.533 I slot launch_slot_: id 0 | task 7543 | processing task, is_child = 0 8.30.257.612 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 319613733683 8.30.257.732 I slot launch_slot_: id 2 | task 7544 | processing task, is_child = 0 8.31.746.415 I slot print_timing: id 1 | task 7537 | prompt eval time = 2356.10 ms / 947 tokens ( 2.49 ms per token, 401.94 tokens per second) 8.31.746.421 I slot print_timing: id 1 | task 7537 | eval time = 1500.72 ms / 2 tokens ( 1500.72 ms per token, 0.67 tokens per second) 8.31.746.421 I slot print_timing: id 1 | task 7537 | total time = 3856.82 ms / 949 tokens 8.31.746.422 I slot print_timing: id 1 | task 7537 | graphs reused = 6355 8.31.746.422 I slot print_timing: id 1 | task 7537 | graph reallocs = 0 / 0 (same size) / (changed size) 8.31.746.504 I slot release: id 1 | task 7537 | stop processing: n_tokens = 957, truncated = 0 8.33.065.238 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 957, t_last = 319615270286 8.33.065.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.735 MiB) 8.33.073.154 I slot launch_slot_: id 1 | task 7547 | processing task, is_child = 0 8.34.196.759 I slot print_timing: id 3 | task 7542 | prompt eval time = 2807.03 ms / 108 tokens ( 25.99 ms per token, 38.47 tokens per second) 8.34.196.763 I slot print_timing: id 3 | task 7542 | eval time = 1131.53 ms / 2 tokens ( 1131.53 ms per token, 0.88 tokens per second) 8.34.196.763 I slot print_timing: id 3 | task 7542 | total time = 3938.56 ms / 110 tokens 8.34.196.763 I slot print_timing: id 3 | task 7542 | graphs reused = 6355 8.34.196.764 I slot print_timing: id 3 | task 7542 | graph reallocs = 0 / 0 (same size) / (changed size) 8.34.196.823 I slot release: id 3 | task 7542 | stop processing: n_tokens = 963, truncated = 0 8.34.196.836 I slot print_timing: id 0 | task 7543 | prompt processing, n_tokens = 886, progress = 1.00, t = 3.94 s / 224.99 tokens per second 8.34.202.622 I slot print_timing: id 2 | task 7544 | prompt processing, n_tokens = 917, progress = 1.00, t = 3.94 s / 232.88 tokens per second 8.34.917.276 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 963, t_last = 319617720605 8.34.917.402 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.419 MiB) 8.34.925.958 I slot launch_slot_: id 3 | task 7550 | processing task, is_child = 0 8.35.799.626 I slot print_timing: id 0 | task 7543 | prompt eval time = 4658.26 ms / 890 tokens ( 5.23 ms per token, 191.06 tokens per second) 8.35.799.630 I slot print_timing: id 0 | task 7543 | eval time = 883.61 ms / 2 tokens ( 883.61 ms per token, 1.13 tokens per second) 8.35.799.630 I slot print_timing: id 0 | task 7543 | total time = 5541.87 ms / 892 tokens 8.35.799.631 I slot print_timing: id 0 | task 7543 | graphs reused = 6355 8.35.799.631 I slot print_timing: id 0 | task 7543 | graph reallocs = 0 / 0 (same size) / (changed size) 8.35.799.709 I slot release: id 0 | task 7543 | stop processing: n_tokens = 900, truncated = 0 8.35.800.875 I slot print_timing: id 2 | task 7544 | prompt eval time = 4659.28 ms / 921 tokens ( 5.06 ms per token, 197.67 tokens per second) 8.35.800.879 I slot print_timing: id 2 | task 7544 | eval time = 883.62 ms / 2 tokens ( 883.62 ms per token, 1.13 tokens per second) 8.35.800.879 I slot print_timing: id 2 | task 7544 | total time = 5542.90 ms / 923 tokens 8.35.800.879 I slot print_timing: id 2 | task 7544 | graphs reused = 6355 8.35.800.880 I slot print_timing: id 2 | task 7544 | graph reallocs = 0 / 0 (same size) / (changed size) 8.35.800.920 I slot release: id 2 | task 7544 | stop processing: n_tokens = 931, truncated = 0 8.36.501.207 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.897 8.36.501.337 I slot launch_slot_: id 0 | task 7553 | processing task, is_child = 0 8.36.501.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 250.844 MiB) 8.36.510.526 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 319619324702 8.36.510.641 I slot launch_slot_: id 2 | task 7554 | processing task, is_child = 0 8.38.084.530 I slot print_timing: id 1 | task 7547 | prompt eval time = 3426.24 ms / 894 tokens ( 3.83 ms per token, 260.93 tokens per second) 8.38.084.537 I slot print_timing: id 1 | task 7547 | eval time = 1583.33 ms / 2 tokens ( 1583.33 ms per token, 0.63 tokens per second) 8.38.084.537 I slot print_timing: id 1 | task 7547 | total time = 5009.57 ms / 896 tokens 8.38.084.537 I slot print_timing: id 1 | task 7547 | graphs reused = 6355 8.38.084.538 I slot print_timing: id 1 | task 7547 | graph reallocs = 0 / 0 (same size) / (changed size) 8.38.084.624 I slot release: id 1 | task 7547 | stop processing: n_tokens = 904, truncated = 0 8.38.089.588 I slot print_timing: id 3 | task 7550 | prompt processing, n_tokens = 890, progress = 1.00, t = 3.16 s / 282.03 tokens per second 8.38.730.985 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 319621608406 8.38.731.089 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.430 MiB) 8.38.737.464 I slot launch_slot_: id 1 | task 7557 | processing task, is_child = 0 8.40.228.281 I slot print_timing: id 0 | task 7553 | prompt eval time = 2219.16 ms / 83 tokens ( 26.74 ms per token, 37.40 tokens per second) 8.40.228.286 I slot print_timing: id 0 | task 7553 | eval time = 1498.46 ms / 2 tokens ( 1498.46 ms per token, 0.67 tokens per second) 8.40.228.287 I slot print_timing: id 0 | task 7553 | total time = 3717.62 ms / 85 tokens 8.40.228.287 I slot print_timing: id 0 | task 7553 | graphs reused = 6355 8.40.228.288 I slot print_timing: id 0 | task 7553 | graph reallocs = 0 / 0 (same size) / (changed size) 8.40.228.375 I slot release: id 0 | task 7553 | stop processing: n_tokens = 891, truncated = 0 8.40.229.524 I slot print_timing: id 3 | task 7550 | prompt eval time = 3803.30 ms / 894 tokens ( 4.25 ms per token, 235.06 tokens per second) 8.40.229.527 I slot print_timing: id 3 | task 7550 | eval time = 1498.54 ms / 2 tokens ( 1498.54 ms per token, 0.67 tokens per second) 8.40.229.527 I slot print_timing: id 3 | task 7550 | total time = 5301.84 ms / 896 tokens 8.40.229.527 I slot print_timing: id 3 | task 7550 | graphs reused = 6355 8.40.229.528 I slot print_timing: id 3 | task 7550 | graph reallocs = 0 / 0 (same size) / (changed size) 8.40.229.570 I slot release: id 3 | task 7550 | stop processing: n_tokens = 904, truncated = 0 8.40.232.277 I slot print_timing: id 2 | task 7554 | prompt processing, n_tokens = 1211, progress = 1.00, t = 3.71 s / 325.99 tokens per second 8.40.842.297 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 319623752157 8.40.842.392 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 302.916 MiB) 8.40.851.184 I slot launch_slot_: id 0 | task 7560 | processing task, is_child = 0 8.40.851.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.719 MiB) 8.40.857.069 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 319623753352 8.40.857.193 I slot launch_slot_: id 3 | task 7561 | processing task, is_child = 0 8.44.183.953 I slot print_timing: id 2 | task 7554 | prompt eval time = 4329.91 ms / 1215 tokens ( 3.56 ms per token, 280.61 tokens per second) 8.44.183.956 I slot print_timing: id 2 | task 7554 | eval time = 3341.66 ms / 2 tokens ( 3341.66 ms per token, 0.30 tokens per second) 8.44.183.956 I slot print_timing: id 2 | task 7554 | total time = 7671.57 ms / 1217 tokens 8.44.183.957 I slot print_timing: id 2 | task 7554 | graphs reused = 6355 8.44.183.957 I slot print_timing: id 2 | task 7554 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.184.022 I slot release: id 2 | task 7554 | stop processing: n_tokens = 1225, truncated = 0 8.44.184.047 I slot print_timing: id 0 | task 7560 | prompt processing, n_tokens = 764, progress = 0.60, t = 3.33 s / 229.73 tokens per second 8.44.187.317 I slot print_timing: id 1 | task 7557 | prompt processing, n_tokens = 1222, progress = 1.00, t = 5.45 s / 224.41 tokens per second 8.44.189.429 I slot print_timing: id 3 | task 7561 | prompt processing, n_tokens = 1112, progress = 0.42, t = 3.32 s / 334.57 tokens per second 8.46.420.423 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1225, t_last = 319627707804 8.46.420.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 233.966 MiB) 8.46.429.270 I slot launch_slot_: id 2 | task 7564 | processing task, is_child = 0 8.46.429.286 I slot print_timing: id 0 | task 7560 | prompt processing, n_tokens = 1051, progress = 0.82, t = 5.56 s / 188.96 tokens per second 8.49.800.573 I slot print_timing: id 1 | task 7557 | prompt eval time = 7682.93 ms / 1226 tokens ( 6.27 ms per token, 159.57 tokens per second) 8.49.800.579 I slot print_timing: id 1 | task 7557 | eval time = 3380.15 ms / 2 tokens ( 3380.15 ms per token, 0.30 tokens per second) 8.49.800.579 I slot print_timing: id 1 | task 7557 | total time = 11063.08 ms / 1228 tokens 8.49.800.588 I slot print_timing: id 1 | task 7557 | graphs reused = 6355 8.49.800.588 I slot print_timing: id 1 | task 7557 | graph reallocs = 0 / 0 (same size) / (changed size) 8.49.800.687 I slot release: id 1 | task 7557 | stop processing: n_tokens = 1236, truncated = 0 8.49.800.725 I slot print_timing: id 0 | task 7560 | prompt processing, n_tokens = 1276, progress = 1.00, t = 8.94 s / 142.69 tokens per second 8.49.804.871 I slot print_timing: id 2 | task 7564 | prompt processing, n_tokens = 1822, progress = 0.71, t = 3.37 s / 540.91 tokens per second 8.49.804.889 I slot print_timing: id 3 | task 7561 | prompt processing, n_tokens = 2146, progress = 0.81, t = 5.56 s / 385.96 tokens per second 8.50.618.274 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1236, t_last = 319633324472 8.50.618.390 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 251.828 MiB) 8.50.627.297 I slot launch_slot_: id 1 | task 7567 | processing task, is_child = 0 8.53.930.791 I slot print_timing: id 0 | task 7560 | prompt eval time = 9761.07 ms / 1280 tokens ( 7.63 ms per token, 131.13 tokens per second) 8.53.930.794 I slot print_timing: id 0 | task 7560 | eval time = 3312.52 ms / 2 tokens ( 3312.52 ms per token, 0.30 tokens per second) 8.53.930.794 I slot print_timing: id 0 | task 7560 | total time = 13073.58 ms / 1282 tokens 8.53.930.795 I slot print_timing: id 0 | task 7560 | graphs reused = 6355 8.53.930.795 I slot print_timing: id 0 | task 7560 | graph reallocs = 0 / 0 (same size) / (changed size) 8.53.930.857 I slot release: id 0 | task 7560 | stop processing: n_tokens = 1290, truncated = 0 8.53.930.880 I slot print_timing: id 1 | task 7567 | prompt processing, n_tokens = 2047, progress = 0.73, t = 3.30 s / 619.86 tokens per second 8.53.930.899 I slot print_timing: id 2 | task 7564 | prompt processing, n_tokens = 2052, progress = 0.80, t = 4.19 s / 490.19 tokens per second 8.53.934.185 I slot print_timing: id 3 | task 7561 | prompt processing, n_tokens = 2353, progress = 0.88, t = 9.76 s / 241.14 tokens per second 8.55.436.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1290, t_last = 319637454639 8.55.436.418 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 303.408 MiB) 8.55.468.091 I slot launch_slot_: id 0 | task 7570 | processing task, is_child = 0 8.57.896.168 I slot print_timing: id 1 | task 7567 | prompt processing, n_tokens = 2301, progress = 0.82, t = 4.81 s / 478.48 tokens per second 8.58.741.473 I slot print_timing: id 2 | task 7564 | prompt processing, n_tokens = 2353, progress = 0.92, t = 9.01 s / 261.29 tokens per second 8.58.748.006 I slot print_timing: id 3 | task 7561 | prompt processing, n_tokens = 2658, progress = 1.00, t = 14.58 s / 182.34 tokens per second 8.59.614.225 I slot print_timing: id 0 | task 7570 | prompt processing, n_tokens = 2213, progress = 0.81, t = 4.14 s / 534.31 tokens per second 8.59.621.279 I slot print_timing: id 1 | task 7567 | prompt processing, n_tokens = 2353, progress = 0.84, t = 8.98 s / 261.95 tokens per second 8.59.625.335 I slot print_timing: id 2 | task 7564 | prompt processing, n_tokens = 2564, progress = 1.00, t = 13.18 s / 194.55 tokens per second 9.00.760.921 I slot print_timing: id 3 | task 7561 | prompt eval time = 18754.95 ms / 2662 tokens ( 7.05 ms per token, 141.94 tokens per second) 9.00.760.933 I slot print_timing: id 3 | task 7561 | eval time = 1146.77 ms / 2 tokens ( 1146.77 ms per token, 0.87 tokens per second) 9.00.760.941 I slot print_timing: id 3 | task 7561 | total time = 19901.72 ms / 2664 tokens 9.00.760.948 I slot print_timing: id 3 | task 7561 | graphs reused = 6355 9.00.760.953 I slot print_timing: id 3 | task 7561 | graph reallocs = 0 / 0 (same size) / (changed size) 9.00.761.345 I slot release: id 3 | task 7561 | stop processing: n_tokens = 2672, truncated = 0 9.00.761.401 I slot print_timing: id 0 | task 7570 | prompt processing, n_tokens = 2353, progress = 0.86, t = 5.29 s / 445.08 tokens per second 9.00.767.593 I slot print_timing: id 1 | task 7567 | prompt processing, n_tokens = 2813, progress = 1.00, t = 10.13 s / 277.76 tokens per second 9.01.502.792 I slot print_timing: id 2 | task 7564 | prompt eval time = 14327.58 ms / 2568 tokens ( 5.58 ms per token, 179.23 tokens per second) 9.01.502.799 I slot print_timing: id 2 | task 7564 | eval time = 744.15 ms / 2 tokens ( 744.15 ms per token, 1.34 tokens per second) 9.01.502.801 I slot print_timing: id 2 | task 7564 | total time = 15071.73 ms / 2570 tokens 9.01.502.802 I slot print_timing: id 2 | task 7564 | graphs reused = 6355 9.01.502.803 I slot print_timing: id 2 | task 7564 | graph reallocs = 0 / 0 (same size) / (changed size) 9.01.503.214 I slot release: id 2 | task 7564 | stop processing: n_tokens = 2578, truncated = 0 9.01.503.252 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2672, t_last = 319644285128 9.01.503.655 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 290.012 MiB) 9.01.535.310 I slot launch_slot_: id 3 | task 7575 | processing task, is_child = 0 9.01.535.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.156 MiB) 9.01.556.059 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2578, t_last = 319645026998 9.01.556.296 I slot launch_slot_: id 2 | task 7576 | processing task, is_child = 0 9.01.556.308 I slot print_timing: id 0 | task 7570 | prompt processing, n_tokens = 2725, progress = 1.00, t = 6.03 s / 452.04 tokens per second 9.04.840.997 I slot print_timing: id 1 | task 7567 | prompt eval time = 10873.16 ms / 2817 tokens ( 3.86 ms per token, 259.08 tokens per second) 9.04.841.001 I slot print_timing: id 1 | task 7567 | eval time = 3340.52 ms / 2 tokens ( 3340.52 ms per token, 0.30 tokens per second) 9.04.841.002 I slot print_timing: id 1 | task 7567 | total time = 14213.68 ms / 2819 tokens 9.04.841.002 I slot print_timing: id 1 | task 7567 | graphs reused = 6355 9.04.841.003 I slot print_timing: id 1 | task 7567 | graph reallocs = 0 / 0 (same size) / (changed size) 9.04.841.205 I slot release: id 1 | task 7567 | stop processing: n_tokens = 2827, truncated = 0 9.04.841.241 I slot print_timing: id 2 | task 7576 | prompt processing, n_tokens = 1354, progress = 0.73, t = 3.28 s / 412.84 tokens per second 9.04.844.706 I slot print_timing: id 3 | task 7575 | prompt processing, n_tokens = 689, progress = 0.38, t = 3.28 s / 210.11 tokens per second 9.06.125.644 I slot print_timing: id 0 | task 7570 | prompt eval time = 9371.74 ms / 2729 tokens ( 3.43 ms per token, 291.19 tokens per second) 9.06.125.648 I slot print_timing: id 0 | task 7570 | eval time = 1285.79 ms / 2 tokens ( 1285.79 ms per token, 0.78 tokens per second) 9.06.125.649 I slot print_timing: id 0 | task 7570 | total time = 10657.53 ms / 2731 tokens 9.06.125.649 I slot print_timing: id 0 | task 7570 | graphs reused = 6355 9.06.125.649 I slot print_timing: id 0 | task 7570 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.125.847 I slot release: id 0 | task 7570 | stop processing: n_tokens = 2739, truncated = 0 9.06.125.869 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2827, t_last = 319648364988 9.06.126.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.842 MiB) 9.06.144.207 I slot launch_slot_: id 1 | task 7579 | processing task, is_child = 0 9.06.144.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 235.232 MiB) 9.06.144.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.014 MiB) 9.06.159.959 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2739, t_last = 319649649630 9.06.160.156 I slot launch_slot_: id 0 | task 7580 | processing task, is_child = 0 9.09.433.908 I slot print_timing: id 2 | task 7576 | prompt processing, n_tokens = 1467, progress = 0.79, t = 4.57 s / 321.32 tokens per second 9.09.436.224 I slot print_timing: id 3 | task 7575 | prompt processing, n_tokens = 1294, progress = 0.72, t = 4.57 s / 283.45 tokens per second 9.11.294.073 I slot print_timing: id 0 | task 7580 | prompt processing, n_tokens = 1467, progress = 0.78, t = 5.13 s / 285.75 tokens per second 9.11.969.385 I slot print_timing: id 1 | task 7579 | prompt processing, n_tokens = 1467, progress = 0.71, t = 5.13 s / 285.77 tokens per second 9.11.973.038 I slot print_timing: id 2 | task 7576 | prompt processing, n_tokens = 1866, progress = 1.00, t = 9.74 s / 191.68 tokens per second 9.11.974.941 I slot print_timing: id 3 | task 7575 | prompt processing, n_tokens = 1467, progress = 0.81, t = 9.73 s / 150.70 tokens per second 9.13.494.127 I slot print_timing: id 0 | task 7580 | prompt processing, n_tokens = 1880, progress = 1.00, t = 7.33 s / 256.38 tokens per second 9.13.498.081 I slot print_timing: id 1 | task 7579 | prompt processing, n_tokens = 1565, progress = 0.75, t = 7.33 s / 213.44 tokens per second 9.13.500.560 I slot print_timing: id 3 | task 7575 | prompt processing, n_tokens = 1806, progress = 1.00, t = 11.93 s / 151.34 tokens per second 9.14.448.064 I slot print_timing: id 2 | task 7576 | prompt eval time = 11935.16 ms / 1870 tokens ( 6.38 ms per token, 156.68 tokens per second) 9.14.448.068 I slot print_timing: id 2 | task 7576 | eval time = 953.96 ms / 2 tokens ( 953.96 ms per token, 1.05 tokens per second) 9.14.448.069 I slot print_timing: id 2 | task 7576 | total time = 12889.13 ms / 1872 tokens 9.14.448.070 I slot print_timing: id 2 | task 7576 | graphs reused = 6355 9.14.448.070 I slot print_timing: id 2 | task 7576 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.448.209 I slot release: id 2 | task 7576 | stop processing: n_tokens = 1880, truncated = 0 9.14.449.792 I slot print_timing: id 1 | task 7579 | prompt processing, n_tokens = 2077, progress = 1.00, t = 8.29 s / 250.69 tokens per second 9.14.541.482 I slot print_timing: id 0 | task 7580 | prompt eval time = 8286.68 ms / 1884 tokens ( 4.40 ms per token, 227.35 tokens per second) 9.14.541.488 I slot print_timing: id 0 | task 7580 | eval time = 94.63 ms / 2 tokens ( 94.63 ms per token, 10.57 tokens per second) 9.14.541.489 I slot print_timing: id 0 | task 7580 | total time = 8381.31 ms / 1886 tokens 9.14.541.489 I slot print_timing: id 0 | task 7580 | graphs reused = 6355 9.14.541.490 I slot print_timing: id 0 | task 7580 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.541.571 I slot release: id 0 | task 7580 | stop processing: n_tokens = 1894, truncated = 0 9.14.544.685 I slot print_timing: id 3 | task 7575 | prompt eval time = 12890.39 ms / 1810 tokens ( 7.12 ms per token, 140.41 tokens per second) 9.14.544.687 I slot print_timing: id 3 | task 7575 | eval time = 94.91 ms / 2 tokens ( 94.91 ms per token, 10.54 tokens per second) 9.14.544.688 I slot print_timing: id 3 | task 7575 | total time = 12985.30 ms / 1812 tokens 9.14.544.688 I slot print_timing: id 3 | task 7575 | graphs reused = 6355 9.14.544.689 I slot print_timing: id 3 | task 7575 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.544.741 I slot release: id 3 | task 7575 | stop processing: n_tokens = 1820, truncated = 0 9.14.544.749 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.756 (> 0.100 thold), f_keep = 0.798 9.14.544.828 I slot launch_slot_: id 0 | task 7586 | processing task, is_child = 0 9.14.544.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.965 MiB) 9.14.552.447 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.508 MiB) 9.14.566.947 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1880, t_last = 319657971993 9.14.567.134 I slot launch_slot_: id 2 | task 7587 | processing task, is_child = 0 9.14.567.235 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.831 9.14.567.272 I slot launch_slot_: id 3 | task 7588 | processing task, is_child = 0 9.16.325.781 I slot print_timing: id 1 | task 7579 | prompt eval time = 8382.78 ms / 2081 tokens ( 4.03 ms per token, 248.25 tokens per second) 9.16.325.783 I slot print_timing: id 1 | task 7579 | eval time = 1782.47 ms / 2 tokens ( 1782.47 ms per token, 0.56 tokens per second) 9.16.325.789 I slot print_timing: id 1 | task 7579 | total time = 10165.25 ms / 2083 tokens 9.16.325.789 I slot print_timing: id 1 | task 7579 | graphs reused = 6355 9.16.325.790 I slot print_timing: id 1 | task 7579 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.325.901 I slot release: id 1 | task 7579 | stop processing: n_tokens = 2091, truncated = 0 9.17.050.042 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2091, t_last = 319659849684 9.17.050.209 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.967 MiB) 9.17.067.305 I slot launch_slot_: id 1 | task 7591 | processing task, is_child = 0 9.17.698.695 I slot print_timing: id 0 | task 7586 | prompt eval time = 2481.48 ms / 488 tokens ( 5.08 ms per token, 196.66 tokens per second) 9.17.698.702 I slot print_timing: id 0 | task 7586 | eval time = 649.92 ms / 2 tokens ( 649.92 ms per token, 1.54 tokens per second) 9.17.698.703 I slot print_timing: id 0 | task 7586 | total time = 3131.40 ms / 490 tokens 9.17.698.703 I slot print_timing: id 0 | task 7586 | graphs reused = 6355 9.17.698.704 I slot print_timing: id 0 | task 7586 | graph reallocs = 0 / 0 (same size) / (changed size) 9.17.698.848 I slot release: id 0 | task 7586 | stop processing: n_tokens = 2001, truncated = 0 9.17.700.023 I slot print_timing: id 3 | task 7588 | prompt eval time = 2480.62 ms / 301 tokens ( 8.24 ms per token, 121.34 tokens per second) 9.17.700.027 I slot print_timing: id 3 | task 7588 | eval time = 649.99 ms / 2 tokens ( 649.99 ms per token, 1.54 tokens per second) 9.17.700.027 I slot print_timing: id 3 | task 7588 | total time = 3130.61 ms / 303 tokens 9.17.700.027 I slot print_timing: id 3 | task 7588 | graphs reused = 6355 9.17.700.028 I slot print_timing: id 3 | task 7588 | graph reallocs = 0 / 0 (same size) / (changed size) 9.17.700.085 I slot release: id 3 | task 7588 | stop processing: n_tokens = 1814, truncated = 0 9.17.701.931 I slot print_timing: id 2 | task 7587 | prompt processing, n_tokens = 712, progress = 0.99, t = 3.13 s / 227.59 tokens per second 9.18.346.491 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2001, t_last = 319661222631 9.18.346.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 262.519 MiB) 9.18.363.423 I slot launch_slot_: id 0 | task 7594 | processing task, is_child = 0 9.18.363.538 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.886 MiB) 9.18.363.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.558 MiB) 9.18.384.120 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1814, t_last = 319661223867 9.18.384.311 I slot launch_slot_: id 3 | task 7595 | processing task, is_child = 0 9.19.426.841 I slot print_timing: id 2 | task 7587 | prompt eval time = 3777.37 ms / 716 tokens ( 5.28 ms per token, 189.55 tokens per second) 9.19.426.844 I slot print_timing: id 2 | task 7587 | eval time = 1080.36 ms / 2 tokens ( 1080.36 ms per token, 0.93 tokens per second) 9.19.426.844 I slot print_timing: id 2 | task 7587 | total time = 4857.72 ms / 718 tokens 9.19.426.849 I slot print_timing: id 2 | task 7587 | graphs reused = 6355 9.19.426.850 I slot print_timing: id 2 | task 7587 | graph reallocs = 0 / 0 (same size) / (changed size) 9.19.426.889 I slot release: id 2 | task 7587 | stop processing: n_tokens = 726, truncated = 0 9.20.722.186 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.879 9.20.722.368 I slot launch_slot_: id 2 | task 7598 | processing task, is_child = 0 9.21.391.726 I slot print_timing: id 1 | task 7591 | prompt eval time = 3654.85 ms / 735 tokens ( 4.97 ms per token, 201.10 tokens per second) 9.21.391.729 I slot print_timing: id 1 | task 7591 | eval time = 669.55 ms / 2 tokens ( 669.55 ms per token, 1.49 tokens per second) 9.21.391.729 I slot print_timing: id 1 | task 7591 | total time = 4324.40 ms / 737 tokens 9.21.391.730 I slot print_timing: id 1 | task 7591 | graphs reused = 6355 9.21.391.730 I slot print_timing: id 1 | task 7591 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.391.773 I slot release: id 1 | task 7591 | stop processing: n_tokens = 745, truncated = 0 9.21.391.788 I slot print_timing: id 0 | task 7594 | prompt processing, n_tokens = 744, progress = 0.99, t = 3.01 s / 247.48 tokens per second 9.21.396.881 I slot print_timing: id 3 | task 7595 | prompt processing, n_tokens = 708, progress = 0.99, t = 3.00 s / 235.66 tokens per second 9.21.465.881 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 319664915555 9.21.465.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 231.434 MiB) 9.21.471.635 I slot launch_slot_: id 1 | task 7601 | processing task, is_child = 0 9.21.977.268 I slot print_timing: id 0 | task 7594 | prompt eval time = 3079.12 ms / 748 tokens ( 4.12 ms per token, 242.93 tokens per second) 9.21.977.272 I slot print_timing: id 0 | task 7594 | eval time = 513.81 ms / 2 tokens ( 513.81 ms per token, 1.95 tokens per second) 9.21.977.272 I slot print_timing: id 0 | task 7594 | total time = 3592.92 ms / 750 tokens 9.21.977.273 I slot print_timing: id 0 | task 7594 | graphs reused = 6355 9.21.977.273 I slot print_timing: id 0 | task 7594 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.977.347 I slot release: id 0 | task 7594 | stop processing: n_tokens = 758, truncated = 0 9.21.978.521 I slot print_timing: id 2 | task 7598 | prompt eval time = 739.03 ms / 101 tokens ( 7.32 ms per token, 136.67 tokens per second) 9.21.978.526 I slot print_timing: id 2 | task 7598 | eval time = 513.86 ms / 2 tokens ( 513.86 ms per token, 1.95 tokens per second) 9.21.978.527 I slot print_timing: id 2 | task 7598 | total time = 1252.89 ms / 103 tokens 9.21.978.527 I slot print_timing: id 2 | task 7598 | graphs reused = 6355 9.21.978.528 I slot print_timing: id 2 | task 7598 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.978.565 I slot release: id 2 | task 7598 | stop processing: n_tokens = 740, truncated = 0 9.21.979.755 I slot print_timing: id 3 | task 7595 | prompt eval time = 3079.57 ms / 712 tokens ( 4.33 ms per token, 231.20 tokens per second) 9.21.979.758 I slot print_timing: id 3 | task 7595 | eval time = 513.88 ms / 2 tokens ( 513.88 ms per token, 1.95 tokens per second) 9.21.979.759 I slot print_timing: id 3 | task 7595 | total time = 3593.45 ms / 714 tokens 9.21.979.759 I slot print_timing: id 3 | task 7595 | graphs reused = 6355 9.21.979.766 I slot print_timing: id 3 | task 7595 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.979.795 I slot release: id 3 | task 7595 | stop processing: n_tokens = 722, truncated = 0 9.22.547.842 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 758, t_last = 319665501133 9.22.547.919 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 235.513 MiB) 9.22.873.133 I slot launch_slot_: id 0 | task 7605 | processing task, is_child = 0 9.22.873.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.465 MiB) 9.22.879.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.787 MiB) 9.22.885.174 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 319665502347 9.22.885.309 I slot launch_slot_: id 2 | task 7606 | processing task, is_child = 0 9.22.885.369 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 722, t_last = 319665503577 9.22.885.470 I slot launch_slot_: id 3 | task 7607 | processing task, is_child = 0 9.26.636.265 I slot print_timing: id 1 | task 7601 | prompt eval time = 3211.00 ms / 796 tokens ( 4.03 ms per token, 247.90 tokens per second) 9.26.636.275 I slot print_timing: id 1 | task 7601 | eval time = 1953.59 ms / 2 tokens ( 1953.59 ms per token, 0.51 tokens per second) 9.26.636.277 I slot print_timing: id 1 | task 7601 | total time = 5164.59 ms / 798 tokens 9.26.636.279 I slot print_timing: id 1 | task 7601 | graphs reused = 6355 9.26.636.280 I slot print_timing: id 1 | task 7601 | graph reallocs = 0 / 0 (same size) / (changed size) 9.26.636.418 I slot release: id 1 | task 7601 | stop processing: n_tokens = 806, truncated = 0 9.26.636.476 I slot print_timing: id 0 | task 7605 | prompt processing, n_tokens = 672, progress = 0.85, t = 3.75 s / 179.38 tokens per second 9.26.643.555 I slot print_timing: id 2 | task 7606 | prompt processing, n_tokens = 672, progress = 0.84, t = 3.74 s / 179.47 tokens per second 9.26.647.466 I slot print_timing: id 3 | task 7607 | prompt processing, n_tokens = 891, progress = 0.86, t = 3.74 s / 237.97 tokens per second 9.27.304.815 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 319670160200 9.27.383.104 I slot launch_slot_: id 1 | task 7611 | processing task, is_child = 0 9.27.383.116 I slot print_timing: id 0 | task 7605 | prompt processing, n_tokens = 789, progress = 1.00, t = 4.42 s / 178.53 tokens per second 9.27.385.760 I slot print_timing: id 2 | task 7606 | prompt processing, n_tokens = 799, progress = 1.00, t = 4.42 s / 180.88 tokens per second 9.27.387.690 I slot print_timing: id 3 | task 7607 | prompt processing, n_tokens = 1039, progress = 1.00, t = 4.42 s / 235.21 tokens per second 9.28.663.075 I slot print_timing: id 0 | task 7605 | prompt eval time = 5056.52 ms / 793 tokens ( 6.38 ms per token, 156.83 tokens per second) 9.28.663.080 I slot print_timing: id 0 | task 7605 | eval time = 721.07 ms / 2 tokens ( 721.07 ms per token, 1.39 tokens per second) 9.28.663.081 I slot print_timing: id 0 | task 7605 | total time = 5777.59 ms / 795 tokens 9.28.663.081 I slot print_timing: id 0 | task 7605 | graphs reused = 6355 9.28.663.082 I slot print_timing: id 0 | task 7605 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.663.162 I slot release: id 0 | task 7605 | stop processing: n_tokens = 803, truncated = 0 9.28.664.280 I slot print_timing: id 2 | task 7606 | prompt eval time = 5055.80 ms / 803 tokens ( 6.30 ms per token, 158.83 tokens per second) 9.28.664.283 I slot print_timing: id 2 | task 7606 | eval time = 721.07 ms / 2 tokens ( 721.07 ms per token, 1.39 tokens per second) 9.28.664.284 I slot print_timing: id 2 | task 7606 | total time = 5776.87 ms / 805 tokens 9.28.664.284 I slot print_timing: id 2 | task 7606 | graphs reused = 6355 9.28.664.284 I slot print_timing: id 2 | task 7606 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.664.321 I slot release: id 2 | task 7606 | stop processing: n_tokens = 813, truncated = 0 9.28.665.533 I slot print_timing: id 3 | task 7607 | prompt eval time = 5056.93 ms / 1043 tokens ( 4.85 ms per token, 206.25 tokens per second) 9.28.665.536 I slot print_timing: id 3 | task 7607 | eval time = 721.05 ms / 2 tokens ( 721.05 ms per token, 1.39 tokens per second) 9.28.665.537 I slot print_timing: id 3 | task 7607 | total time = 5777.97 ms / 1045 tokens 9.28.665.537 I slot print_timing: id 3 | task 7607 | graphs reused = 6355 9.28.665.538 I slot print_timing: id 3 | task 7607 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.665.572 I slot release: id 3 | task 7607 | stop processing: n_tokens = 1053, truncated = 0 9.28.923.451 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 319672186944 9.28.923.531 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.073 MiB) 9.28.929.293 I slot launch_slot_: id 0 | task 7616 | processing task, is_child = 0 9.28.929.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.917 MiB) 9.28.935.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.139 MiB) 9.28.941.581 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 813, t_last = 319672188103 9.28.941.706 I slot launch_slot_: id 2 | task 7617 | processing task, is_child = 0 9.28.941.778 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 319672189354 9.28.941.888 I slot launch_slot_: id 3 | task 7618 | processing task, is_child = 0 9.30.705.082 I slot print_timing: id 1 | task 7611 | prompt eval time = 1537.88 ms / 836 tokens ( 1.84 ms per token, 543.61 tokens per second) 9.30.705.084 I slot print_timing: id 1 | task 7611 | eval time = 1781.63 ms / 2 tokens ( 1781.63 ms per token, 0.56 tokens per second) 9.30.705.085 I slot print_timing: id 1 | task 7611 | total time = 3319.51 ms / 838 tokens 9.30.705.085 I slot print_timing: id 1 | task 7611 | graphs reused = 6355 9.30.705.086 I slot print_timing: id 1 | task 7611 | graph reallocs = 0 / 0 (same size) / (changed size) 9.30.705.143 I slot release: id 1 | task 7611 | stop processing: n_tokens = 846, truncated = 0 9.32.346.120 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.869 (> 0.100 thold), f_keep = 0.884 9.32.346.201 I slot launch_slot_: id 1 | task 7621 | processing task, is_child = 0 9.32.346.209 I slot print_timing: id 0 | task 7616 | prompt processing, n_tokens = 712, progress = 0.79, t = 3.40 s / 209.15 tokens per second 9.32.514.900 I slot print_timing: id 2 | task 7617 | prompt processing, n_tokens = 712, progress = 0.80, t = 3.40 s / 209.16 tokens per second 9.32.516.630 I slot print_timing: id 3 | task 7618 | prompt processing, n_tokens = 712, progress = 0.86, t = 3.40 s / 209.17 tokens per second 9.33.449.671 I slot print_timing: id 0 | task 7616 | prompt processing, n_tokens = 895, progress = 1.00, t = 4.51 s / 198.55 tokens per second 9.33.621.072 I slot print_timing: id 2 | task 7617 | prompt processing, n_tokens = 889, progress = 1.00, t = 4.51 s / 197.22 tokens per second 9.33.622.822 I slot print_timing: id 3 | task 7618 | prompt processing, n_tokens = 824, progress = 1.00, t = 4.51 s / 182.81 tokens per second 9.33.718.642 I slot print_timing: id 0 | task 7616 | prompt eval time = 4740.36 ms / 899 tokens ( 5.27 ms per token, 189.65 tokens per second) 9.33.718.647 I slot print_timing: id 0 | task 7616 | eval time = 36.39 ms / 2 tokens ( 36.39 ms per token, 27.48 tokens per second) 9.33.718.648 I slot print_timing: id 0 | task 7616 | total time = 4776.74 ms / 901 tokens 9.33.718.649 I slot print_timing: id 0 | task 7616 | graphs reused = 6355 9.33.718.649 I slot print_timing: id 0 | task 7616 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.718.686 I slot release: id 0 | task 7616 | stop processing: n_tokens = 909, truncated = 0 9.33.719.766 I slot print_timing: id 1 | task 7621 | prompt eval time = 1170.51 ms / 113 tokens ( 10.36 ms per token, 96.54 tokens per second) 9.33.719.768 I slot print_timing: id 1 | task 7621 | eval time = 36.36 ms / 2 tokens ( 36.36 ms per token, 27.51 tokens per second) 9.33.719.769 I slot print_timing: id 1 | task 7621 | total time = 1206.87 ms / 115 tokens 9.33.719.769 I slot print_timing: id 1 | task 7621 | graphs reused = 6355 9.33.719.769 I slot print_timing: id 1 | task 7621 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.719.798 I slot release: id 1 | task 7621 | stop processing: n_tokens = 862, truncated = 0 9.33.720.899 I slot print_timing: id 2 | task 7617 | prompt eval time = 4742.43 ms / 893 tokens ( 5.31 ms per token, 188.30 tokens per second) 9.33.720.902 I slot print_timing: id 2 | task 7617 | eval time = 36.40 ms / 2 tokens ( 36.40 ms per token, 27.47 tokens per second) 9.33.720.902 I slot print_timing: id 2 | task 7617 | total time = 4778.83 ms / 895 tokens 9.33.720.902 I slot print_timing: id 2 | task 7617 | graphs reused = 6355 9.33.720.903 I slot print_timing: id 2 | task 7617 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.720.927 I slot release: id 2 | task 7617 | stop processing: n_tokens = 903, truncated = 0 9.33.722.031 I slot print_timing: id 3 | task 7618 | prompt eval time = 4743.36 ms / 828 tokens ( 5.73 ms per token, 174.56 tokens per second) 9.33.722.033 I slot print_timing: id 3 | task 7618 | eval time = 36.43 ms / 2 tokens ( 36.43 ms per token, 27.45 tokens per second) 9.33.722.033 I slot print_timing: id 3 | task 7618 | total time = 4779.80 ms / 830 tokens 9.33.722.033 I slot print_timing: id 3 | task 7618 | graphs reused = 6355 9.33.722.034 I slot print_timing: id 3 | task 7618 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.722.051 I slot release: id 3 | task 7618 | stop processing: n_tokens = 838, truncated = 0 9.33.724.836 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 909, t_last = 319677242468 9.33.725.064 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 243.671 MiB) 9.33.731.039 I slot launch_slot_: id 0 | task 7625 | processing task, is_child = 0 9.33.731.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.420 MiB) 9.33.731.113 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 298.767 MiB) 9.33.743.936 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.870 MiB) 9.33.749.611 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 319677243580 9.33.749.744 I slot launch_slot_: id 1 | task 7626 | processing task, is_child = 0 9.33.749.875 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 319677244709 9.33.749.972 I slot launch_slot_: id 2 | task 7627 | processing task, is_child = 0 9.33.750.035 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 838, t_last = 319677245833 9.33.750.129 I slot launch_slot_: id 3 | task 7628 | processing task, is_child = 0 9.37.979.206 I slot print_timing: id 0 | task 7625 | prompt processing, n_tokens = 576, progress = 0.85, t = 4.23 s / 136.20 tokens per second 9.38.022.249 I slot print_timing: id 1 | task 7626 | prompt processing, n_tokens = 701, progress = 0.85, t = 4.23 s / 165.77 tokens per second 9.38.025.184 I slot print_timing: id 2 | task 7627 | prompt processing, n_tokens = 701, progress = 0.83, t = 4.23 s / 165.77 tokens per second 9.38.027.507 I slot print_timing: id 3 | task 7628 | prompt processing, n_tokens = 615, progress = 0.82, t = 4.23 s / 145.44 tokens per second 9.38.920.805 I slot print_timing: id 0 | task 7625 | prompt processing, n_tokens = 678, progress = 0.99, t = 5.17 s / 131.12 tokens per second 9.38.964.212 I slot print_timing: id 1 | task 7626 | prompt processing, n_tokens = 818, progress = 1.00, t = 5.17 s / 158.21 tokens per second 9.38.968.041 I slot print_timing: id 2 | task 7627 | prompt processing, n_tokens = 841, progress = 1.00, t = 5.17 s / 162.66 tokens per second 9.38.969.956 I slot print_timing: id 3 | task 7628 | prompt processing, n_tokens = 746, progress = 0.99, t = 5.17 s / 144.29 tokens per second 9.39.065.714 I slot print_timing: id 0 | task 7625 | prompt eval time = 5279.16 ms / 682 tokens ( 7.74 ms per token, 129.19 tokens per second) 9.39.065.717 I slot print_timing: id 0 | task 7625 | eval time = 36.41 ms / 2 tokens ( 36.41 ms per token, 27.47 tokens per second) 9.39.065.717 I slot print_timing: id 0 | task 7625 | total time = 5315.57 ms / 684 tokens 9.39.065.718 I slot print_timing: id 0 | task 7625 | graphs reused = 6355 9.39.065.719 I slot print_timing: id 0 | task 7625 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.065.757 I slot release: id 0 | task 7625 | stop processing: n_tokens = 692, truncated = 0 9.39.066.917 I slot print_timing: id 1 | task 7626 | prompt eval time = 5280.14 ms / 822 tokens ( 6.42 ms per token, 155.68 tokens per second) 9.39.066.920 I slot print_timing: id 1 | task 7626 | eval time = 36.45 ms / 2 tokens ( 36.45 ms per token, 27.44 tokens per second) 9.39.066.920 I slot print_timing: id 1 | task 7626 | total time = 5316.59 ms / 824 tokens 9.39.066.921 I slot print_timing: id 1 | task 7626 | graphs reused = 6355 9.39.066.921 I slot print_timing: id 1 | task 7626 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.066.956 I slot release: id 1 | task 7626 | stop processing: n_tokens = 832, truncated = 0 9.39.068.098 I slot print_timing: id 2 | task 7627 | prompt eval time = 5281.06 ms / 845 tokens ( 6.25 ms per token, 160.01 tokens per second) 9.39.068.101 I slot print_timing: id 2 | task 7627 | eval time = 36.53 ms / 2 tokens ( 36.53 ms per token, 27.38 tokens per second) 9.39.068.101 I slot print_timing: id 2 | task 7627 | total time = 5317.59 ms / 847 tokens 9.39.068.101 I slot print_timing: id 2 | task 7627 | graphs reused = 6355 9.39.068.102 I slot print_timing: id 2 | task 7627 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.068.124 I slot release: id 2 | task 7627 | stop processing: n_tokens = 855, truncated = 0 9.39.069.231 I slot print_timing: id 3 | task 7628 | prompt eval time = 5281.96 ms / 750 tokens ( 7.04 ms per token, 141.99 tokens per second) 9.39.069.233 I slot print_timing: id 3 | task 7628 | eval time = 36.59 ms / 2 tokens ( 36.59 ms per token, 27.33 tokens per second) 9.39.069.234 I slot print_timing: id 3 | task 7628 | total time = 5318.55 ms / 752 tokens 9.39.069.234 I slot print_timing: id 3 | task 7628 | graphs reused = 6355 9.39.069.234 I slot print_timing: id 3 | task 7628 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.069.257 I slot release: id 3 | task 7628 | stop processing: n_tokens = 760, truncated = 0 9.39.072.740 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.874 (> 0.100 thold), f_keep = 0.857 9.39.072.799 I slot launch_slot_: id 3 | task 7634 | processing task, is_child = 0 9.39.072.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.870 MiB) 9.39.078.032 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.093 MiB) 9.39.083.832 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 300.420 MiB) 9.39.089.584 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 319682589540 9.39.089.738 I slot launch_slot_: id 0 | task 7635 | processing task, is_child = 0 9.39.089.867 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 319682590738 9.39.089.962 I slot launch_slot_: id 1 | task 7636 | processing task, is_child = 0 9.39.090.030 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 319682591906 9.39.090.134 I slot launch_slot_: id 2 | task 7637 | processing task, is_child = 0 9.42.276.476 I slot print_timing: id 0 | task 7635 | prompt processing, n_tokens = 590, progress = 0.84, t = 3.19 s / 185.23 tokens per second 9.42.279.655 I slot print_timing: id 1 | task 7636 | prompt processing, n_tokens = 590, progress = 0.82, t = 3.19 s / 185.24 tokens per second 9.42.281.333 I slot print_timing: id 2 | task 7637 | prompt processing, n_tokens = 590, progress = 0.84, t = 3.18 s / 185.25 tokens per second 9.42.995.671 I slot print_timing: id 3 | task 7634 | prompt eval time = 3185.80 ms / 94 tokens ( 33.89 ms per token, 29.51 tokens per second) 9.42.995.674 I slot print_timing: id 3 | task 7634 | eval time = 719.21 ms / 2 tokens ( 719.21 ms per token, 1.39 tokens per second) 9.42.995.674 I slot print_timing: id 3 | task 7634 | total time = 3905.01 ms / 96 tokens 9.42.995.675 I slot print_timing: id 3 | task 7634 | graphs reused = 6355 9.42.995.675 I slot print_timing: id 3 | task 7634 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.995.714 I slot release: id 3 | task 7634 | stop processing: n_tokens = 746, truncated = 0 9.42.995.725 I slot print_timing: id 0 | task 7635 | prompt processing, n_tokens = 697, progress = 0.99, t = 3.90 s / 178.52 tokens per second 9.42.997.799 I slot print_timing: id 1 | task 7636 | prompt processing, n_tokens = 719, progress = 0.99, t = 3.90 s / 184.16 tokens per second 9.42.999.897 I slot print_timing: id 2 | task 7637 | prompt processing, n_tokens = 702, progress = 0.99, t = 3.90 s / 179.81 tokens per second 9.43.056.643 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 319686519496 9.43.056.729 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.436 MiB) 9.43.063.814 I slot launch_slot_: id 3 | task 7642 | processing task, is_child = 0 9.43.402.084 I slot print_timing: id 0 | task 7635 | prompt eval time = 3963.88 ms / 701 tokens ( 5.65 ms per token, 176.85 tokens per second) 9.43.402.086 I slot print_timing: id 0 | task 7635 | eval time = 348.06 ms / 2 tokens ( 348.06 ms per token, 2.87 tokens per second) 9.43.402.087 I slot print_timing: id 0 | task 7635 | total time = 4311.94 ms / 703 tokens 9.43.402.088 I slot print_timing: id 0 | task 7635 | graphs reused = 6355 9.43.402.088 I slot print_timing: id 0 | task 7635 | graph reallocs = 0 / 0 (same size) / (changed size) 9.43.402.158 I slot release: id 0 | task 7635 | stop processing: n_tokens = 711, truncated = 0 9.43.403.420 I slot print_timing: id 1 | task 7636 | prompt eval time = 3965.05 ms / 723 tokens ( 5.48 ms per token, 182.34 tokens per second) 9.43.403.423 I slot print_timing: id 1 | task 7636 | eval time = 348.05 ms / 2 tokens ( 348.05 ms per token, 2.87 tokens per second) 9.43.403.423 I slot print_timing: id 1 | task 7636 | total time = 4313.10 ms / 725 tokens 9.43.403.423 I slot print_timing: id 1 | task 7636 | graphs reused = 6355 9.43.403.424 I slot print_timing: id 1 | task 7636 | graph reallocs = 0 / 0 (same size) / (changed size) 9.43.403.447 I slot release: id 1 | task 7636 | stop processing: n_tokens = 733, truncated = 0 9.43.404.605 I slot print_timing: id 2 | task 7637 | prompt eval time = 3966.14 ms / 706 tokens ( 5.62 ms per token, 178.01 tokens per second) 9.43.404.607 I slot print_timing: id 2 | task 7637 | eval time = 347.97 ms / 2 tokens ( 347.97 ms per token, 2.87 tokens per second) 9.43.404.608 I slot print_timing: id 2 | task 7637 | total time = 4314.11 ms / 708 tokens 9.43.404.608 I slot print_timing: id 2 | task 7637 | graphs reused = 6355 9.43.404.608 I slot print_timing: id 2 | task 7637 | graph reallocs = 0 / 0 (same size) / (changed size) 9.43.404.630 I slot release: id 2 | task 7637 | stop processing: n_tokens = 716, truncated = 0 9.44.063.135 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.880 9.44.063.261 I slot launch_slot_: id 0 | task 7646 | processing task, is_child = 0 9.44.063.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 9.44.283.413 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.766 MiB) 9.44.288.721 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.854 9.44.288.801 I slot launch_slot_: id 1 | task 7647 | processing task, is_child = 0 9.44.288.864 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.874 9.44.288.903 I slot launch_slot_: id 2 | task 7648 | processing task, is_child = 0 9.44.868.908 I slot print_timing: id 3 | task 7642 | prompt eval time = 1717.52 ms / 699 tokens ( 2.46 ms per token, 406.98 tokens per second) 9.44.868.912 I slot print_timing: id 3 | task 7642 | eval time = 87.56 ms / 2 tokens ( 87.56 ms per token, 11.42 tokens per second) 9.44.868.912 I slot print_timing: id 3 | task 7642 | total time = 1805.08 ms / 701 tokens 9.44.868.913 I slot print_timing: id 3 | task 7642 | graphs reused = 6355 9.44.868.913 I slot print_timing: id 3 | task 7642 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.868.951 I slot release: id 3 | task 7642 | stop processing: n_tokens = 709, truncated = 0 9.44.900.850 I slot print_timing: id 0 | task 7646 | prompt eval time = 576.41 ms / 85 tokens ( 6.78 ms per token, 147.46 tokens per second) 9.44.900.853 I slot print_timing: id 0 | task 7646 | eval time = 35.53 ms / 2 tokens ( 35.53 ms per token, 28.15 tokens per second) 9.44.900.853 I slot print_timing: id 0 | task 7646 | total time = 611.94 ms / 87 tokens 9.44.900.854 I slot print_timing: id 0 | task 7646 | graphs reused = 6355 9.44.900.854 I slot print_timing: id 0 | task 7646 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.900.882 I slot release: id 0 | task 7646 | stop processing: n_tokens = 712, truncated = 0 9.44.902.049 I slot print_timing: id 1 | task 7647 | prompt eval time = 575.99 ms / 77 tokens ( 7.48 ms per token, 133.68 tokens per second) 9.44.902.051 I slot print_timing: id 1 | task 7647 | eval time = 35.45 ms / 2 tokens ( 35.45 ms per token, 28.21 tokens per second) 9.44.902.051 I slot print_timing: id 1 | task 7647 | total time = 611.44 ms / 79 tokens 9.44.902.052 I slot print_timing: id 1 | task 7647 | graphs reused = 6355 9.44.902.052 I slot print_timing: id 1 | task 7647 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.902.074 I slot release: id 1 | task 7647 | stop processing: n_tokens = 704, truncated = 0 9.44.903.243 I slot print_timing: id 2 | task 7648 | prompt eval time = 575.55 ms / 79 tokens ( 7.29 ms per token, 137.26 tokens per second) 9.44.903.245 I slot print_timing: id 2 | task 7648 | eval time = 35.41 ms / 2 tokens ( 35.41 ms per token, 28.24 tokens per second) 9.44.903.246 I slot print_timing: id 2 | task 7648 | total time = 610.96 ms / 81 tokens 9.44.903.246 I slot print_timing: id 2 | task 7648 | graphs reused = 6355 9.44.903.246 I slot print_timing: id 2 | task 7648 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.903.265 I slot release: id 2 | task 7648 | stop processing: n_tokens = 706, truncated = 0 9.44.903.271 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.891 9.44.903.323 I slot launch_slot_: id 2 | task 7652 | processing task, is_child = 0 9.44.903.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 9.44.909.933 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.112 MiB) 9.44.916.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.499 MiB) 9.44.923.352 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.891 9.44.923.424 I slot launch_slot_: id 1 | task 7653 | processing task, is_child = 0 9.44.923.563 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.879 9.44.923.604 I slot launch_slot_: id 0 | task 7654 | processing task, is_child = 0 9.44.923.666 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.883 9.44.923.703 I slot launch_slot_: id 3 | task 7655 | processing task, is_child = 0 9.45.751.562 I slot print_timing: id 0 | task 7654 | prompt eval time = 791.37 ms / 80 tokens ( 9.89 ms per token, 101.09 tokens per second) 9.45.751.565 I slot print_timing: id 0 | task 7654 | eval time = 36.48 ms / 2 tokens ( 36.48 ms per token, 27.41 tokens per second) 9.45.751.565 I slot print_timing: id 0 | task 7654 | total time = 827.85 ms / 82 tokens 9.45.751.566 I slot print_timing: id 0 | task 7654 | graphs reused = 6355 9.45.751.566 I slot print_timing: id 0 | task 7654 | graph reallocs = 0 / 0 (same size) / (changed size) 9.45.751.597 I slot release: id 0 | task 7654 | stop processing: n_tokens = 707, truncated = 0 9.45.752.742 I slot print_timing: id 1 | task 7653 | prompt eval time = 790.78 ms / 86 tokens ( 9.20 ms per token, 108.75 tokens per second) 9.45.752.746 I slot print_timing: id 1 | task 7653 | eval time = 36.53 ms / 2 tokens ( 36.53 ms per token, 27.37 tokens per second) 9.45.752.747 I slot print_timing: id 1 | task 7653 | total time = 827.31 ms / 88 tokens 9.45.752.747 I slot print_timing: id 1 | task 7653 | graphs reused = 6355 9.45.752.748 I slot print_timing: id 1 | task 7653 | graph reallocs = 0 / 0 (same size) / (changed size) 9.45.752.770 I slot release: id 1 | task 7653 | stop processing: n_tokens = 714, truncated = 0 9.45.753.931 I slot print_timing: id 2 | task 7652 | prompt eval time = 790.19 ms / 86 tokens ( 9.19 ms per token, 108.83 tokens per second) 9.45.753.933 I slot print_timing: id 2 | task 7652 | eval time = 36.60 ms / 2 tokens ( 36.60 ms per token, 27.32 tokens per second) 9.45.753.934 I slot print_timing: id 2 | task 7652 | total time = 826.79 ms / 88 tokens 9.45.753.934 I slot print_timing: id 2 | task 7652 | graphs reused = 6355 9.45.753.934 I slot print_timing: id 2 | task 7652 | graph reallocs = 0 / 0 (same size) / (changed size) 9.45.753.955 I slot release: id 2 | task 7652 | stop processing: n_tokens = 716, truncated = 0 9.45.755.101 I slot print_timing: id 3 | task 7655 | prompt eval time = 789.78 ms / 121 tokens ( 6.53 ms per token, 153.21 tokens per second) 9.45.755.102 I slot print_timing: id 3 | task 7655 | eval time = 36.46 ms / 2 tokens ( 36.46 ms per token, 27.43 tokens per second) 9.45.755.103 I slot print_timing: id 3 | task 7655 | total time = 826.25 ms / 123 tokens 9.45.755.103 I slot print_timing: id 3 | task 7655 | graphs reused = 6355 9.45.755.103 I slot print_timing: id 3 | task 7655 | graph reallocs = 0 / 0 (same size) / (changed size) 9.45.755.120 I slot release: id 3 | task 7655 | stop processing: n_tokens = 748, truncated = 0 9.45.758.918 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 319689275379 9.45.758.990 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.398 MiB) 9.45.766.935 I slot launch_slot_: id 0 | task 7659 | processing task, is_child = 0 9.45.767.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.000 MiB) 9.45.776.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.694 MiB) 9.45.785.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.451 MiB) 9.45.792.831 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 319689276552 9.45.792.996 I slot launch_slot_: id 1 | task 7660 | processing task, is_child = 0 9.45.793.114 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 319689277737 9.45.793.212 I slot launch_slot_: id 2 | task 7661 | processing task, is_child = 0 9.45.793.288 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 319689278902 9.45.793.380 I slot launch_slot_: id 3 | task 7662 | processing task, is_child = 0 9.48.825.201 I slot print_timing: id 0 | task 7659 | prompt processing, n_tokens = 380, progress = 0.43, t = 3.03 s / 125.34 tokens per second 9.48.870.982 I slot print_timing: id 1 | task 7660 | prompt processing, n_tokens = 363, progress = 0.42, t = 3.03 s / 119.74 tokens per second 9.48.876.137 I slot print_timing: id 2 | task 7661 | prompt processing, n_tokens = 573, progress = 0.53, t = 3.03 s / 189.02 tokens per second 9.48.880.121 I slot print_timing: id 3 | task 7662 | prompt processing, n_tokens = 583, progress = 0.53, t = 3.03 s / 192.33 tokens per second 9.51.247.125 I slot print_timing: id 0 | task 7659 | prompt processing, n_tokens = 761, progress = 0.85, t = 5.45 s / 139.54 tokens per second 9.51.327.198 I slot print_timing: id 1 | task 7660 | prompt processing, n_tokens = 761, progress = 0.87, t = 5.45 s / 139.54 tokens per second 9.51.332.637 I slot print_timing: id 2 | task 7661 | prompt processing, n_tokens = 909, progress = 0.84, t = 5.45 s / 166.69 tokens per second 9.51.336.801 I slot print_timing: id 3 | task 7662 | prompt processing, n_tokens = 909, progress = 0.83, t = 5.45 s / 166.69 tokens per second 9.52.426.465 I slot print_timing: id 0 | task 7659 | prompt processing, n_tokens = 892, progress = 1.00, t = 6.63 s / 134.48 tokens per second 9.52.473.816 I slot print_timing: id 1 | task 7660 | prompt processing, n_tokens = 875, progress = 1.00, t = 6.63 s / 131.92 tokens per second 9.52.479.955 I slot print_timing: id 2 | task 7661 | prompt processing, n_tokens = 1085, progress = 1.00, t = 6.63 s / 163.58 tokens per second 9.52.484.392 I slot print_timing: id 3 | task 7662 | prompt processing, n_tokens = 1095, progress = 1.00, t = 6.63 s / 165.10 tokens per second 9.52.591.279 I slot print_timing: id 0 | task 7659 | prompt eval time = 6756.34 ms / 896 tokens ( 7.54 ms per token, 132.62 tokens per second) 9.52.591.287 I slot print_timing: id 0 | task 7659 | eval time = 41.54 ms / 2 tokens ( 41.54 ms per token, 24.07 tokens per second) 9.52.591.287 I slot print_timing: id 0 | task 7659 | total time = 6797.88 ms / 898 tokens 9.52.591.288 I slot print_timing: id 0 | task 7659 | graphs reused = 6355 9.52.591.288 I slot print_timing: id 0 | task 7659 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.591.346 I slot release: id 0 | task 7659 | stop processing: n_tokens = 906, truncated = 0 9.52.593.144 I slot print_timing: id 1 | task 7660 | prompt eval time = 6758.46 ms / 879 tokens ( 7.69 ms per token, 130.06 tokens per second) 9.52.593.149 I slot print_timing: id 1 | task 7660 | eval time = 41.08 ms / 2 tokens ( 41.08 ms per token, 24.35 tokens per second) 9.52.593.149 I slot print_timing: id 1 | task 7660 | total time = 6799.54 ms / 881 tokens 9.52.593.150 I slot print_timing: id 1 | task 7660 | graphs reused = 6355 9.52.593.150 I slot print_timing: id 1 | task 7660 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.593.197 I slot release: id 1 | task 7660 | stop processing: n_tokens = 889, truncated = 0 9.52.594.995 I slot print_timing: id 2 | task 7661 | prompt eval time = 6760.44 ms / 1089 tokens ( 6.21 ms per token, 161.08 tokens per second) 9.52.594.999 I slot print_timing: id 2 | task 7661 | eval time = 40.78 ms / 2 tokens ( 40.78 ms per token, 24.52 tokens per second) 9.52.594.999 I slot print_timing: id 2 | task 7661 | total time = 6801.22 ms / 1091 tokens 9.52.595.000 I slot print_timing: id 2 | task 7661 | graphs reused = 6355 9.52.595.000 I slot print_timing: id 2 | task 7661 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.595.040 I slot release: id 2 | task 7661 | stop processing: n_tokens = 1099, truncated = 0 9.52.596.837 I slot print_timing: id 3 | task 7662 | prompt eval time = 6762.57 ms / 1099 tokens ( 6.15 ms per token, 162.51 tokens per second) 9.52.596.841 I slot print_timing: id 3 | task 7662 | eval time = 40.34 ms / 2 tokens ( 40.34 ms per token, 24.79 tokens per second) 9.52.596.842 I slot print_timing: id 3 | task 7662 | total time = 6802.91 ms / 1101 tokens 9.52.596.842 I slot print_timing: id 3 | task 7662 | graphs reused = 6355 9.52.596.843 I slot print_timing: id 3 | task 7662 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.596.876 I slot release: id 3 | task 7662 | stop processing: n_tokens = 1109, truncated = 0 9.52.604.400 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.894 9.52.604.461 I slot launch_slot_: id 3 | task 7668 | processing task, is_child = 0 9.52.611.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.356 MiB) 9.52.619.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.147 MiB) 9.52.626.767 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.901 9.52.626.847 I slot launch_slot_: id 2 | task 7669 | processing task, is_child = 0 9.52.627.003 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 906, t_last = 319696115128 9.52.630.765 I slot launch_slot_: id 0 | task 7670 | processing task, is_child = 0 9.52.630.841 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 319696116979 9.52.630.947 I slot launch_slot_: id 1 | task 7671 | processing task, is_child = 0 9.55.307.645 I slot print_timing: id 2 | task 7669 | prompt eval time = 2261.24 ms / 97 tokens ( 23.31 ms per token, 42.90 tokens per second) 9.55.307.655 I slot print_timing: id 2 | task 7669 | eval time = 411.03 ms / 2 tokens ( 411.03 ms per token, 2.43 tokens per second) 9.55.307.660 I slot print_timing: id 2 | task 7669 | total time = 2672.28 ms / 99 tokens 9.55.307.668 I slot print_timing: id 2 | task 7669 | graphs reused = 6355 9.55.307.669 I slot print_timing: id 2 | task 7669 | graph reallocs = 0 / 0 (same size) / (changed size) 9.55.307.835 I slot release: id 2 | task 7669 | stop processing: n_tokens = 1088, truncated = 0 9.55.310.009 I slot print_timing: id 3 | task 7668 | prompt eval time = 2261.39 ms / 110 tokens ( 20.56 ms per token, 48.64 tokens per second) 9.55.310.018 I slot print_timing: id 3 | task 7668 | eval time = 411.07 ms / 2 tokens ( 411.07 ms per token, 2.43 tokens per second) 9.55.310.019 I slot print_timing: id 3 | task 7668 | total time = 2672.46 ms / 112 tokens 9.55.310.020 I slot print_timing: id 3 | task 7668 | graphs reused = 6355 9.55.310.021 I slot print_timing: id 3 | task 7668 | graph reallocs = 0 / 0 (same size) / (changed size) 9.55.310.108 I slot release: id 3 | task 7668 | stop processing: n_tokens = 1102, truncated = 0 9.55.377.857 I slot print_timing: id 0 | task 7670 | prompt eval time = 2674.20 ms / 179 tokens ( 14.94 ms per token, 66.94 tokens per second) 9.55.377.863 I slot print_timing: id 0 | task 7670 | eval time = 72.69 ms / 2 tokens ( 72.69 ms per token, 13.76 tokens per second) 9.55.377.865 I slot print_timing: id 0 | task 7670 | total time = 2746.89 ms / 181 tokens 9.55.377.866 I slot print_timing: id 0 | task 7670 | graphs reused = 6355 9.55.377.867 I slot print_timing: id 0 | task 7670 | graph reallocs = 0 / 0 (same size) / (changed size) 9.55.377.949 I slot release: id 0 | task 7670 | stop processing: n_tokens = 1097, truncated = 0 9.55.380.530 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.903 9.55.380.651 I slot launch_slot_: id 0 | task 7676 | processing task, is_child = 0 9.55.394.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.037 MiB) 9.55.410.766 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.911 9.55.410.852 I slot launch_slot_: id 2 | task 7677 | processing task, is_child = 0 9.55.410.968 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.899 9.55.411.019 I slot launch_slot_: id 3 | task 7678 | processing task, is_child = 0 9.56.031.921 I slot print_timing: id 1 | task 7671 | prompt eval time = 2745.42 ms / 1087 tokens ( 2.53 ms per token, 395.93 tokens per second) 9.56.031.925 I slot print_timing: id 1 | task 7671 | eval time = 651.39 ms / 2 tokens ( 651.39 ms per token, 1.54 tokens per second) 9.56.031.926 I slot print_timing: id 1 | task 7671 | total time = 3396.82 ms / 1089 tokens 9.56.031.926 I slot print_timing: id 1 | task 7671 | graphs reused = 6355 9.56.031.926 I slot print_timing: id 1 | task 7671 | graph reallocs = 0 / 0 (same size) / (changed size) 9.56.031.983 I slot release: id 1 | task 7671 | stop processing: n_tokens = 1097, truncated = 0 9.56.120.322 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.903 9.56.120.411 I slot launch_slot_: id 1 | task 7681 | processing task, is_child = 0 9.56.402.098 I slot print_timing: id 0 | task 7676 | prompt eval time = 706.93 ms / 98 tokens ( 7.21 ms per token, 138.63 tokens per second) 9.56.402.101 I slot print_timing: id 0 | task 7676 | eval time = 284.13 ms / 2 tokens ( 284.13 ms per token, 3.52 tokens per second) 9.56.402.102 I slot print_timing: id 0 | task 7676 | total time = 991.06 ms / 100 tokens 9.56.402.102 I slot print_timing: id 0 | task 7676 | graphs reused = 6355 9.56.402.103 I slot print_timing: id 0 | task 7676 | graph reallocs = 0 / 0 (same size) / (changed size) 9.56.402.175 I slot release: id 0 | task 7676 | stop processing: n_tokens = 1090, truncated = 0 9.56.403.323 I slot print_timing: id 2 | task 7677 | prompt eval time = 705.78 ms / 107 tokens ( 6.60 ms per token, 151.60 tokens per second) 9.56.403.325 I slot print_timing: id 2 | task 7677 | eval time = 284.20 ms / 2 tokens ( 284.20 ms per token, 3.52 tokens per second) 9.56.403.326 I slot print_timing: id 2 | task 7677 | total time = 989.99 ms / 109 tokens 9.56.403.326 I slot print_timing: id 2 | task 7677 | graphs reused = 6355 9.56.403.327 I slot print_timing: id 2 | task 7677 | graph reallocs = 0 / 0 (same size) / (changed size) 9.56.403.363 I slot release: id 2 | task 7677 | stop processing: n_tokens = 1099, truncated = 0 9.56.404.529 I slot print_timing: id 3 | task 7678 | prompt eval time = 704.21 ms / 114 tokens ( 6.18 ms per token, 161.88 tokens per second) 9.56.404.532 I slot print_timing: id 3 | task 7678 | eval time = 284.21 ms / 2 tokens ( 284.21 ms per token, 3.52 tokens per second) 9.56.404.532 I slot print_timing: id 3 | task 7678 | total time = 988.42 ms / 116 tokens 9.56.404.532 I slot print_timing: id 3 | task 7678 | graphs reused = 6355 9.56.404.533 I slot print_timing: id 3 | task 7678 | graph reallocs = 0 / 0 (same size) / (changed size) 9.56.404.559 I slot release: id 3 | task 7678 | stop processing: n_tokens = 1106, truncated = 0 9.56.445.802 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.909 9.56.445.846 I slot launch_slot_: id 0 | task 7684 | processing task, is_child = 0 9.56.445.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.567 MiB) 9.56.445.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 342.409 MiB) 9.56.470.579 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.902 9.56.470.650 I slot launch_slot_: id 2 | task 7685 | processing task, is_child = 0 9.56.470.728 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.896 9.56.470.768 I slot launch_slot_: id 3 | task 7686 | processing task, is_child = 0 9.57.086.489 I slot print_timing: id 1 | task 7681 | prompt eval time = 325.37 ms / 108 tokens ( 3.01 ms per token, 331.93 tokens per second) 9.57.086.492 I slot print_timing: id 1 | task 7681 | eval time = 640.68 ms / 2 tokens ( 640.68 ms per token, 1.56 tokens per second) 9.57.086.492 I slot print_timing: id 1 | task 7681 | total time = 966.05 ms / 110 tokens 9.57.086.493 I slot print_timing: id 1 | task 7681 | graphs reused = 6355 9.57.086.493 I slot print_timing: id 1 | task 7681 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.086.577 I slot release: id 1 | task 7681 | stop processing: n_tokens = 1100, truncated = 0 9.57.162.095 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.901 9.57.162.191 I slot launch_slot_: id 1 | task 7689 | processing task, is_child = 0 9.57.443.513 I slot print_timing: id 0 | task 7684 | prompt eval time = 688.97 ms / 102 tokens ( 6.75 ms per token, 148.05 tokens per second) 9.57.443.515 I slot print_timing: id 0 | task 7684 | eval time = 283.76 ms / 2 tokens ( 283.76 ms per token, 3.52 tokens per second) 9.57.443.516 I slot print_timing: id 0 | task 7684 | total time = 972.73 ms / 104 tokens 9.57.443.516 I slot print_timing: id 0 | task 7684 | graphs reused = 6355 9.57.443.517 I slot print_timing: id 0 | task 7684 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.443.569 I slot release: id 0 | task 7684 | stop processing: n_tokens = 1094, truncated = 0 9.57.444.715 I slot print_timing: id 2 | task 7685 | prompt eval time = 688.30 ms / 105 tokens ( 6.56 ms per token, 152.55 tokens per second) 9.57.444.720 I slot print_timing: id 2 | task 7685 | eval time = 283.80 ms / 2 tokens ( 283.80 ms per token, 3.52 tokens per second) 9.57.444.721 I slot print_timing: id 2 | task 7685 | total time = 972.10 ms / 107 tokens 9.57.444.721 I slot print_timing: id 2 | task 7685 | graphs reused = 6355 9.57.444.722 I slot print_timing: id 2 | task 7685 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.444.755 I slot release: id 2 | task 7685 | stop processing: n_tokens = 1097, truncated = 0 9.57.445.888 I slot print_timing: id 3 | task 7686 | prompt eval time = 687.76 ms / 100 tokens ( 6.88 ms per token, 145.40 tokens per second) 9.57.445.891 I slot print_timing: id 3 | task 7686 | eval time = 283.80 ms / 2 tokens ( 283.80 ms per token, 3.52 tokens per second) 9.57.445.891 I slot print_timing: id 3 | task 7686 | total time = 971.56 ms / 102 tokens 9.57.445.892 I slot print_timing: id 3 | task 7686 | graphs reused = 6355 9.57.445.892 I slot print_timing: id 3 | task 7686 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.445.920 I slot release: id 3 | task 7686 | stop processing: n_tokens = 1092, truncated = 0 9.57.481.377 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1094, t_last = 319700967351 9.57.481.479 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.832 MiB) 9.57.481.484 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.275 MiB) 9.57.490.136 I slot launch_slot_: id 0 | task 7692 | processing task, is_child = 0 9.57.490.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.104 MiB) 9.57.499.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.102 MiB) 9.57.506.501 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1097, t_last = 319700968537 9.57.506.661 I slot launch_slot_: id 2 | task 7693 | processing task, is_child = 0 9.57.506.738 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.908 9.57.506.775 I slot launch_slot_: id 3 | task 7694 | processing task, is_child = 0 9.59.333.540 I slot print_timing: id 1 | task 7689 | prompt eval time = 319.18 ms / 104 tokens ( 3.07 ms per token, 325.84 tokens per second) 9.59.333.543 I slot print_timing: id 1 | task 7689 | eval time = 1852.15 ms / 2 tokens ( 1852.15 ms per token, 0.54 tokens per second) 9.59.333.544 I slot print_timing: id 1 | task 7689 | total time = 2171.33 ms / 106 tokens 9.59.333.545 I slot print_timing: id 1 | task 7689 | graphs reused = 6355 9.59.333.545 I slot print_timing: id 1 | task 7689 | graph reallocs = 0 / 0 (same size) / (changed size) 9.59.333.632 I slot release: id 1 | task 7689 | stop processing: n_tokens = 1096, truncated = 0 10.00.562.852 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1096, t_last = 319702857416 10.00.562.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.040 MiB) 10.00.562.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 222.855 MiB) 10.00.573.389 I slot launch_slot_: id 1 | task 7697 | processing task, is_child = 0 10.00.573.404 I slot print_timing: id 0 | task 7692 | prompt processing, n_tokens = 861, progress = 0.86, t = 3.05 s / 281.84 tokens per second 10.00.575.397 I slot print_timing: id 2 | task 7693 | prompt processing, n_tokens = 861, progress = 0.84, t = 3.05 s / 281.86 tokens per second 10.02.089.417 I slot print_timing: id 3 | task 7694 | prompt eval time = 3055.64 ms / 103 tokens ( 29.67 ms per token, 33.71 tokens per second) 10.02.089.421 I slot print_timing: id 3 | task 7694 | eval time = 1526.56 ms / 2 tokens ( 1526.56 ms per token, 0.66 tokens per second) 10.02.089.421 I slot print_timing: id 3 | task 7694 | total time = 4582.19 ms / 105 tokens 10.02.089.422 I slot print_timing: id 3 | task 7694 | graphs reused = 6355 10.02.089.422 I slot print_timing: id 3 | task 7694 | graph reallocs = 0 / 0 (same size) / (changed size) 10.02.089.501 I slot release: id 3 | task 7694 | stop processing: n_tokens = 1095, truncated = 0 10.02.089.528 I slot print_timing: id 0 | task 7692 | prompt processing, n_tokens = 996, progress = 1.00, t = 4.58 s / 217.40 tokens per second 10.02.094.631 I slot print_timing: id 2 | task 7693 | prompt processing, n_tokens = 1017, progress = 1.00, t = 4.58 s / 221.99 tokens per second 10.02.624.376 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1095, t_last = 319705613283 10.02.624.507 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 222.433 MiB) 10.02.635.632 I slot launch_slot_: id 3 | task 7700 | processing task, is_child = 0 10.03.980.418 I slot print_timing: id 0 | task 7692 | prompt eval time = 5116.30 ms / 1000 tokens ( 5.12 ms per token, 195.45 tokens per second) 10.03.980.429 I slot print_timing: id 0 | task 7692 | eval time = 1357.29 ms / 2 tokens ( 1357.29 ms per token, 0.74 tokens per second) 10.03.980.430 I slot print_timing: id 0 | task 7692 | total time = 6473.60 ms / 1002 tokens 10.03.980.432 I slot print_timing: id 0 | task 7692 | graphs reused = 6355 10.03.980.433 I slot print_timing: id 0 | task 7692 | graph reallocs = 0 / 0 (same size) / (changed size) 10.03.980.589 I slot release: id 0 | task 7692 | stop processing: n_tokens = 1010, truncated = 0 10.03.982.809 I slot print_timing: id 2 | task 7693 | prompt eval time = 5117.37 ms / 1021 tokens ( 5.01 ms per token, 199.52 tokens per second) 10.03.982.815 I slot print_timing: id 2 | task 7693 | eval time = 1358.43 ms / 2 tokens ( 1358.43 ms per token, 0.74 tokens per second) 10.03.982.816 I slot print_timing: id 2 | task 7693 | total time = 6475.80 ms / 1023 tokens 10.03.982.816 I slot print_timing: id 2 | task 7693 | graphs reused = 6355 10.03.982.818 I slot print_timing: id 2 | task 7693 | graph reallocs = 0 / 0 (same size) / (changed size) 10.03.982.918 I slot release: id 2 | task 7693 | stop processing: n_tokens = 1031, truncated = 0 10.03.982.970 I slot print_timing: id 1 | task 7697 | prompt processing, n_tokens = 1087, progress = 1.00, t = 3.40 s / 319.61 tokens per second 10.04.597.333 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.888 10.04.597.753 I slot launch_slot_: id 0 | task 7703 | processing task, is_child = 0 10.04.598.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.839 MiB) 10.04.618.065 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.870 10.04.618.290 I slot launch_slot_: id 2 | task 7704 | processing task, is_child = 0 10.05.526.787 I slot print_timing: id 1 | task 7697 | prompt eval time = 4022.12 ms / 1091 tokens ( 3.69 ms per token, 271.25 tokens per second) 10.05.526.800 I slot print_timing: id 1 | task 7697 | eval time = 929.47 ms / 2 tokens ( 929.47 ms per token, 1.08 tokens per second) 10.05.526.801 I slot print_timing: id 1 | task 7697 | total time = 4951.59 ms / 1093 tokens 10.05.526.803 I slot print_timing: id 1 | task 7697 | graphs reused = 6355 10.05.526.805 I slot print_timing: id 1 | task 7697 | graph reallocs = 0 / 0 (same size) / (changed size) 10.05.527.001 I slot release: id 1 | task 7697 | stop processing: n_tokens = 1101, truncated = 0 10.05.617.183 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1101, t_last = 319709050783 10.05.617.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.063 MiB) 10.05.631.228 I slot launch_slot_: id 1 | task 7707 | processing task, is_child = 0 10.06.089.711 I slot print_timing: id 0 | task 7703 | prompt eval time = 993.60 ms / 143 tokens ( 6.95 ms per token, 143.92 tokens per second) 10.06.089.723 I slot print_timing: id 0 | task 7703 | eval time = 477.75 ms / 2 tokens ( 477.75 ms per token, 2.09 tokens per second) 10.06.089.724 I slot print_timing: id 0 | task 7703 | total time = 1471.36 ms / 145 tokens 10.06.089.725 I slot print_timing: id 0 | task 7703 | graphs reused = 6355 10.06.089.727 I slot print_timing: id 0 | task 7703 | graph reallocs = 0 / 0 (same size) / (changed size) 10.06.089.929 I slot release: id 0 | task 7703 | stop processing: n_tokens = 1041, truncated = 0 10.06.092.437 I slot print_timing: id 2 | task 7704 | prompt eval time = 992.39 ms / 122 tokens ( 8.13 ms per token, 122.94 tokens per second) 10.06.092.445 I slot print_timing: id 2 | task 7704 | eval time = 477.86 ms / 2 tokens ( 477.86 ms per token, 2.09 tokens per second) 10.06.092.446 I slot print_timing: id 2 | task 7704 | total time = 1470.25 ms / 124 tokens 10.06.092.447 I slot print_timing: id 2 | task 7704 | graphs reused = 6355 10.06.092.449 I slot print_timing: id 2 | task 7704 | graph reallocs = 0 / 0 (same size) / (changed size) 10.06.092.573 I slot release: id 2 | task 7704 | stop processing: n_tokens = 1020, truncated = 0 10.06.094.974 I slot print_timing: id 3 | task 7700 | prompt eval time = 2979.83 ms / 1055 tokens ( 2.82 ms per token, 354.05 tokens per second) 10.06.094.981 I slot print_timing: id 3 | task 7700 | eval time = 477.79 ms / 2 tokens ( 477.79 ms per token, 2.09 tokens per second) 10.06.094.982 I slot print_timing: id 3 | task 7700 | total time = 3457.62 ms / 1057 tokens 10.06.094.983 I slot print_timing: id 3 | task 7700 | graphs reused = 6355 10.06.094.985 I slot print_timing: id 3 | task 7700 | graph reallocs = 0 / 0 (same size) / (changed size) 10.06.095.109 I slot release: id 3 | task 7700 | stop processing: n_tokens = 1065, truncated = 0 10.06.109.181 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 319709613711 10.06.109.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 237.342 MiB) 10.06.109.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.050 MiB) 10.06.722.671 I slot launch_slot_: id 0 | task 7710 | processing task, is_child = 0 10.06.722.897 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.498 MiB) 10.06.738.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 227.356 MiB) 10.06.759.996 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1020, t_last = 319709616355 10.06.760.228 I slot launch_slot_: id 2 | task 7711 | processing task, is_child = 0 10.06.760.341 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1065, t_last = 319709618891 10.06.760.488 I slot launch_slot_: id 3 | task 7712 | processing task, is_child = 0 10.10.040.985 I slot print_timing: id 0 | task 7710 | prompt processing, n_tokens = 612, progress = 0.78, t = 3.28 s / 186.63 tokens per second 10.10.044.796 I slot print_timing: id 2 | task 7711 | prompt processing, n_tokens = 612, progress = 0.86, t = 3.28 s / 186.79 tokens per second 10.10.046.666 I slot print_timing: id 3 | task 7712 | prompt processing, n_tokens = 612, progress = 0.84, t = 3.28 s / 186.80 tokens per second 10.10.822.177 I slot print_timing: id 1 | task 7707 | prompt eval time = 4409.71 ms / 745 tokens ( 5.92 ms per token, 168.95 tokens per second) 10.10.822.180 I slot print_timing: id 1 | task 7707 | eval time = 781.22 ms / 2 tokens ( 781.22 ms per token, 1.28 tokens per second) 10.10.822.181 I slot print_timing: id 1 | task 7707 | total time = 5190.93 ms / 747 tokens 10.10.822.181 I slot print_timing: id 1 | task 7707 | graphs reused = 6355 10.10.822.182 I slot print_timing: id 1 | task 7707 | graph reallocs = 0 / 0 (same size) / (changed size) 10.10.822.227 I slot release: id 1 | task 7707 | stop processing: n_tokens = 755, truncated = 0 10.10.822.258 I slot print_timing: id 0 | task 7710 | prompt processing, n_tokens = 783, progress = 0.99, t = 4.06 s / 192.83 tokens per second 10.10.825.407 I slot print_timing: id 2 | task 7711 | prompt processing, n_tokens = 713, progress = 0.99, t = 4.06 s / 175.71 tokens per second 10.10.827.441 I slot print_timing: id 3 | task 7712 | prompt processing, n_tokens = 726, progress = 0.99, t = 4.06 s / 178.93 tokens per second 10.10.896.463 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.858 10.10.896.559 I slot launch_slot_: id 1 | task 7717 | processing task, is_child = 0 10.11.128.023 I slot print_timing: id 0 | task 7710 | prompt eval time = 4133.68 ms / 787 tokens ( 5.25 ms per token, 190.39 tokens per second) 10.11.128.026 I slot print_timing: id 0 | task 7710 | eval time = 233.84 ms / 2 tokens ( 233.84 ms per token, 4.28 tokens per second) 10.11.128.027 I slot print_timing: id 0 | task 7710 | total time = 4367.52 ms / 789 tokens 10.11.128.027 I slot print_timing: id 0 | task 7710 | graphs reused = 6355 10.11.128.028 I slot print_timing: id 0 | task 7710 | graph reallocs = 0 / 0 (same size) / (changed size) 10.11.128.098 I slot release: id 0 | task 7710 | stop processing: n_tokens = 797, truncated = 0 10.11.129.249 I slot print_timing: id 2 | task 7711 | prompt eval time = 4132.01 ms / 717 tokens ( 5.76 ms per token, 173.52 tokens per second) 10.11.129.252 I slot print_timing: id 2 | task 7711 | eval time = 233.92 ms / 2 tokens ( 233.92 ms per token, 4.27 tokens per second) 10.11.129.253 I slot print_timing: id 2 | task 7711 | total time = 4365.93 ms / 719 tokens 10.11.129.253 I slot print_timing: id 2 | task 7711 | graphs reused = 6355 10.11.129.254 I slot print_timing: id 2 | task 7711 | graph reallocs = 0 / 0 (same size) / (changed size) 10.11.129.288 I slot release: id 2 | task 7711 | stop processing: n_tokens = 727, truncated = 0 10.11.130.431 I slot print_timing: id 3 | task 7712 | prompt eval time = 4132.88 ms / 730 tokens ( 5.66 ms per token, 176.63 tokens per second) 10.11.130.434 I slot print_timing: id 3 | task 7712 | eval time = 233.97 ms / 2 tokens ( 233.97 ms per token, 4.27 tokens per second) 10.11.130.434 I slot print_timing: id 3 | task 7712 | total time = 4366.85 ms / 732 tokens 10.11.130.434 I slot print_timing: id 3 | task 7712 | graphs reused = 6355 10.11.130.435 I slot print_timing: id 3 | task 7712 | graph reallocs = 0 / 0 (same size) / (changed size) 10.11.130.462 I slot release: id 3 | task 7712 | stop processing: n_tokens = 740, truncated = 0 10.11.166.889 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.878 10.11.166.944 I slot launch_slot_: id 3 | task 7720 | processing task, is_child = 0 10.11.167.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 206.821 MiB) 10.11.172.980 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 226.512 MiB) 10.11.178.254 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.861 (> 0.100 thold), f_keep = 0.813 10.11.178.322 I slot launch_slot_: id 0 | task 7721 | processing task, is_child = 0 10.11.178.384 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.891 10.11.178.422 I slot launch_slot_: id 2 | task 7722 | processing task, is_child = 0 10.11.727.860 I slot print_timing: id 1 | task 7717 | prompt eval time = 270.32 ms / 97 tokens ( 2.79 ms per token, 358.84 tokens per second) 10.11.727.867 I slot print_timing: id 1 | task 7717 | eval time = 560.97 ms / 2 tokens ( 560.97 ms per token, 1.78 tokens per second) 10.11.727.867 I slot print_timing: id 1 | task 7717 | total time = 831.29 ms / 99 tokens 10.11.727.868 I slot print_timing: id 1 | task 7717 | graphs reused = 6355 10.11.727.869 I slot print_timing: id 1 | task 7717 | graph reallocs = 0 / 0 (same size) / (changed size) 10.11.727.913 I slot release: id 1 | task 7717 | stop processing: n_tokens = 746, truncated = 0 10.11.801.793 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.869 10.11.801.862 I slot launch_slot_: id 1 | task 7725 | processing task, is_child = 0 10.12.033.403 I slot print_timing: id 0 | task 7721 | prompt eval time = 621.12 ms / 105 tokens ( 5.92 ms per token, 169.05 tokens per second) 10.12.033.407 I slot print_timing: id 0 | task 7721 | eval time = 233.85 ms / 2 tokens ( 233.85 ms per token, 4.28 tokens per second) 10.12.033.407 I slot print_timing: id 0 | task 7721 | total time = 854.97 ms / 107 tokens 10.12.033.408 I slot print_timing: id 0 | task 7721 | graphs reused = 6355 10.12.033.408 I slot print_timing: id 0 | task 7721 | graph reallocs = 0 / 0 (same size) / (changed size) 10.12.033.452 I slot release: id 0 | task 7721 | stop processing: n_tokens = 754, truncated = 0 10.12.034.578 I slot print_timing: id 2 | task 7722 | prompt eval time = 620.51 ms / 84 tokens ( 7.39 ms per token, 135.37 tokens per second) 10.12.034.581 I slot print_timing: id 2 | task 7722 | eval time = 233.90 ms / 2 tokens ( 233.90 ms per token, 4.28 tokens per second) 10.12.034.582 I slot print_timing: id 2 | task 7722 | total time = 854.41 ms / 86 tokens 10.12.034.582 I slot print_timing: id 2 | task 7722 | graphs reused = 6355 10.12.034.582 I slot print_timing: id 2 | task 7722 | graph reallocs = 0 / 0 (same size) / (changed size) 10.12.034.615 I slot release: id 2 | task 7722 | stop processing: n_tokens = 733, truncated = 0 10.12.035.750 I slot print_timing: id 3 | task 7720 | prompt eval time = 619.92 ms / 87 tokens ( 7.13 ms per token, 140.34 tokens per second) 10.12.035.755 I slot print_timing: id 3 | task 7720 | eval time = 233.96 ms / 2 tokens ( 233.96 ms per token, 4.27 tokens per second) 10.12.035.756 I slot print_timing: id 3 | task 7720 | total time = 853.88 ms / 89 tokens 10.12.035.756 I slot print_timing: id 3 | task 7720 | graphs reused = 6355 10.12.035.756 I slot print_timing: id 3 | task 7720 | graph reallocs = 0 / 0 (same size) / (changed size) 10.12.035.785 I slot release: id 3 | task 7720 | stop processing: n_tokens = 738, truncated = 0 10.12.069.936 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 319715557234 10.12.070.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.747 MiB) 10.12.077.217 I slot launch_slot_: id 0 | task 7728 | processing task, is_child = 0 10.12.077.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.899 MiB) 10.12.084.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 212.588 MiB) 10.12.090.963 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 733, t_last = 319715558397 10.12.091.088 I slot launch_slot_: id 2 | task 7729 | processing task, is_child = 0 10.12.091.151 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 319715559567 10.12.091.241 I slot launch_slot_: id 3 | task 7730 | processing task, is_child = 0 10.14.302.755 I slot print_timing: id 1 | task 7725 | prompt eval time = 268.06 ms / 100 tokens ( 2.68 ms per token, 373.04 tokens per second) 10.14.302.758 I slot print_timing: id 1 | task 7725 | eval time = 2232.80 ms / 2 tokens ( 2232.80 ms per token, 0.45 tokens per second) 10.14.302.759 I slot print_timing: id 1 | task 7725 | total time = 2500.87 ms / 102 tokens 10.14.302.760 I slot print_timing: id 1 | task 7725 | graphs reused = 6355 10.14.302.760 I slot print_timing: id 1 | task 7725 | graph reallocs = 0 / 0 (same size) / (changed size) 10.14.302.828 I slot release: id 1 | task 7725 | stop processing: n_tokens = 749, truncated = 0 10.16.066.288 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 749, t_last = 319717826610 10.16.066.397 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 210.197 MiB) 10.16.066.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.535 MiB) 10.16.144.281 I slot launch_slot_: id 1 | task 7733 | processing task, is_child = 0 10.16.144.297 I slot print_timing: id 0 | task 7728 | prompt processing, n_tokens = 812, progress = 0.86, t = 3.98 s / 204.28 tokens per second 10.16.146.615 I slot print_timing: id 2 | task 7729 | prompt processing, n_tokens = 812, progress = 0.83, t = 3.97 s / 204.28 tokens per second 10.16.148.336 I slot print_timing: id 3 | task 7730 | prompt processing, n_tokens = 812, progress = 0.84, t = 3.97 s / 204.29 tokens per second 10.17.299.402 I slot print_timing: id 0 | task 7728 | prompt processing, n_tokens = 946, progress = 1.00, t = 5.21 s / 181.64 tokens per second 10.17.909.345 I slot print_timing: id 2 | task 7729 | prompt processing, n_tokens = 981, progress = 1.00, t = 5.21 s / 188.37 tokens per second 10.17.913.544 I slot print_timing: id 3 | task 7730 | prompt processing, n_tokens = 963, progress = 1.00, t = 5.21 s / 184.92 tokens per second 10.18.951.648 I slot print_timing: id 0 | task 7728 | prompt eval time = 6362.39 ms / 950 tokens ( 6.70 ms per token, 149.32 tokens per second) 10.18.951.659 I slot print_timing: id 0 | task 7728 | eval time = 497.97 ms / 2 tokens ( 497.97 ms per token, 2.01 tokens per second) 10.18.951.660 I slot print_timing: id 0 | task 7728 | total time = 6860.36 ms / 952 tokens 10.18.951.662 I slot print_timing: id 0 | task 7728 | graphs reused = 6355 10.18.951.663 I slot print_timing: id 0 | task 7728 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.951.863 I slot release: id 0 | task 7728 | stop processing: n_tokens = 960, truncated = 0 10.18.954.464 I slot print_timing: id 2 | task 7729 | prompt eval time = 6364.56 ms / 985 tokens ( 6.46 ms per token, 154.76 tokens per second) 10.18.954.472 I slot print_timing: id 2 | task 7729 | eval time = 498.45 ms / 2 tokens ( 498.45 ms per token, 2.01 tokens per second) 10.18.954.474 I slot print_timing: id 2 | task 7729 | total time = 6863.01 ms / 987 tokens 10.18.954.475 I slot print_timing: id 2 | task 7729 | graphs reused = 6355 10.18.954.476 I slot print_timing: id 2 | task 7729 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.954.593 I slot release: id 2 | task 7729 | stop processing: n_tokens = 995, truncated = 0 10.18.956.867 I slot print_timing: id 3 | task 7730 | prompt eval time = 6366.65 ms / 967 tokens ( 6.58 ms per token, 151.89 tokens per second) 10.18.956.877 I slot print_timing: id 3 | task 7730 | eval time = 498.61 ms / 2 tokens ( 498.61 ms per token, 2.01 tokens per second) 10.18.956.880 I slot print_timing: id 3 | task 7730 | total time = 6865.26 ms / 969 tokens 10.18.956.881 I slot print_timing: id 3 | task 7730 | graphs reused = 6355 10.18.956.882 I slot print_timing: id 3 | task 7730 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.956.987 I slot release: id 3 | task 7730 | stop processing: n_tokens = 977, truncated = 0 10.18.996.054 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 960, t_last = 319722475645 10.18.996.193 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.574 MiB) 10.19.003.533 I slot launch_slot_: id 0 | task 7738 | processing task, is_child = 0 10.19.024.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 209.212 MiB) 10.19.024.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.359 MiB) 10.19.032.141 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 319722478375 10.19.032.314 I slot launch_slot_: id 2 | task 7739 | processing task, is_child = 0 10.19.032.403 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 319722480770 10.19.032.527 I slot launch_slot_: id 3 | task 7740 | processing task, is_child = 0 10.22.357.066 I slot print_timing: id 1 | task 7733 | prompt eval time = 2849.64 ms / 1043 tokens ( 2.73 ms per token, 366.01 tokens per second) 10.22.357.072 I slot print_timing: id 1 | task 7733 | eval time = 3360.99 ms / 2 tokens ( 3360.99 ms per token, 0.30 tokens per second) 10.22.357.073 I slot print_timing: id 1 | task 7733 | total time = 6210.63 ms / 1045 tokens 10.22.357.073 I slot print_timing: id 1 | task 7733 | graphs reused = 6355 10.22.357.073 I slot print_timing: id 1 | task 7733 | graph reallocs = 0 / 0 (same size) / (changed size) 10.22.357.170 I slot release: id 1 | task 7733 | stop processing: n_tokens = 1053, truncated = 0 10.22.357.206 I slot print_timing: id 0 | task 7738 | prompt processing, n_tokens = 611, progress = 0.55, t = 3.32 s / 183.85 tokens per second 10.22.361.138 I slot print_timing: id 2 | task 7739 | prompt processing, n_tokens = 643, progress = 0.56, t = 3.32 s / 193.49 tokens per second 10.22.362.861 I slot print_timing: id 3 | task 7740 | prompt processing, n_tokens = 793, progress = 0.38, t = 3.32 s / 238.65 tokens per second 10.24.076.278 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 319725880952 10.24.076.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.932 MiB) 10.24.910.661 I slot launch_slot_: id 1 | task 7743 | processing task, is_child = 0 10.24.910.674 I slot print_timing: id 0 | task 7738 | prompt processing, n_tokens = 975, progress = 0.87, t = 5.04 s / 193.31 tokens per second 10.24.912.703 I slot print_timing: id 2 | task 7739 | prompt processing, n_tokens = 975, progress = 0.84, t = 5.04 s / 193.32 tokens per second 10.24.914.422 I slot print_timing: id 3 | task 7740 | prompt processing, n_tokens = 1613, progress = 0.76, t = 5.04 s / 319.83 tokens per second 10.27.588.466 I slot print_timing: id 0 | task 7738 | prompt processing, n_tokens = 1123, progress = 1.00, t = 8.56 s / 131.25 tokens per second 10.28.283.135 I slot print_timing: id 2 | task 7739 | prompt processing, n_tokens = 1155, progress = 1.00, t = 8.56 s / 135.00 tokens per second 10.28.287.371 I slot print_timing: id 3 | task 7740 | prompt processing, n_tokens = 1717, progress = 0.81, t = 8.56 s / 200.69 tokens per second 10.28.866.055 I slot print_timing: id 1 | task 7743 | prompt processing, n_tokens = 1795, progress = 0.84, t = 3.95 s / 454.79 tokens per second 10.28.871.882 I slot print_timing: id 3 | task 7740 | prompt processing, n_tokens = 1795, progress = 0.84, t = 9.83 s / 182.67 tokens per second 10.30.123.575 I slot print_timing: id 2 | task 7739 | prompt eval time = 9833.21 ms / 1159 tokens ( 8.48 ms per token, 117.87 tokens per second) 10.30.123.591 I slot print_timing: id 2 | task 7739 | eval time = 1257.55 ms / 2 tokens ( 1257.55 ms per token, 0.80 tokens per second) 10.30.123.592 I slot print_timing: id 2 | task 7739 | total time = 11090.76 ms / 1161 tokens 10.30.123.594 I slot print_timing: id 2 | task 7739 | graphs reused = 6355 10.30.123.595 I slot print_timing: id 2 | task 7739 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.123.784 I slot release: id 2 | task 7739 | stop processing: n_tokens = 1169, truncated = 0 10.30.123.898 I slot print_timing: id 1 | task 7743 | prompt processing, n_tokens = 2128, progress = 1.00, t = 5.20 s / 408.84 tokens per second 10.30.128.739 I slot print_timing: id 3 | task 7740 | prompt processing, n_tokens = 2125, progress = 1.00, t = 11.08 s / 191.71 tokens per second 10.30.227.433 I slot print_timing: id 0 | task 7738 | prompt eval time = 9830.80 ms / 1127 tokens ( 8.72 ms per token, 114.64 tokens per second) 10.30.227.442 I slot print_timing: id 0 | task 7738 | eval time = 1364.09 ms / 3 tokens ( 682.04 ms per token, 1.47 tokens per second) 10.30.227.442 I slot print_timing: id 0 | task 7738 | total time = 11194.89 ms / 1130 tokens 10.30.227.443 I slot print_timing: id 0 | task 7738 | graphs reused = 6355 10.30.227.444 I slot print_timing: id 0 | task 7738 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.227.517 I slot release: id 0 | task 7738 | stop processing: n_tokens = 1138, truncated = 0 10.30.231.736 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1169, t_last = 319733647566 10.30.255.913 I slot launch_slot_: id 2 | task 7748 | processing task, is_child = 0 10.30.256.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.210 MiB) 10.30.264.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1138, t_last = 319733751299 10.30.264.551 I slot launch_slot_: id 0 | task 7749 | processing task, is_child = 0 10.33.613.634 I slot print_timing: id 1 | task 7743 | prompt eval time = 5317.14 ms / 2132 tokens ( 2.49 ms per token, 400.97 tokens per second) 10.33.613.648 I slot print_timing: id 1 | task 7743 | eval time = 3383.96 ms / 2 tokens ( 3383.96 ms per token, 0.30 tokens per second) 10.33.613.650 I slot print_timing: id 1 | task 7743 | total time = 8701.10 ms / 2134 tokens 10.33.613.653 I slot print_timing: id 1 | task 7743 | graphs reused = 6355 10.33.613.655 I slot print_timing: id 1 | task 7743 | graph reallocs = 0 / 0 (same size) / (changed size) 10.33.614.121 I slot release: id 1 | task 7743 | stop processing: n_tokens = 2142, truncated = 0 10.33.617.254 I slot print_timing: id 3 | task 7740 | prompt eval time = 11198.70 ms / 2129 tokens ( 5.26 ms per token, 190.11 tokens per second) 10.33.617.261 I slot print_timing: id 3 | task 7740 | eval time = 3385.51 ms / 2 tokens ( 3385.51 ms per token, 0.30 tokens per second) 10.33.617.262 I slot print_timing: id 3 | task 7740 | total time = 14584.21 ms / 2131 tokens 10.33.617.263 I slot print_timing: id 3 | task 7740 | graphs reused = 6355 10.33.617.264 I slot print_timing: id 3 | task 7740 | graph reallocs = 0 / 0 (same size) / (changed size) 10.33.617.459 I slot release: id 3 | task 7740 | stop processing: n_tokens = 2139, truncated = 0 10.33.617.531 I slot print_timing: id 0 | task 7749 | prompt processing, n_tokens = 1560, progress = 0.75, t = 3.34 s / 466.50 tokens per second 10.33.626.484 I slot print_timing: id 2 | task 7748 | prompt processing, n_tokens = 486, progress = 0.24, t = 3.34 s / 145.35 tokens per second 10.35.712.127 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.851 (> 0.100 thold), f_keep = 0.855 10.35.712.351 I slot launch_slot_: id 1 | task 7752 | processing task, is_child = 0 10.35.712.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 264.590 MiB) 10.35.903.282 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.856 10.35.903.475 I slot launch_slot_: id 3 | task 7753 | processing task, is_child = 0 10.35.903.499 I slot print_timing: id 0 | task 7749 | prompt processing, n_tokens = 1795, progress = 0.87, t = 5.45 s / 329.51 tokens per second 10.35.911.526 I slot print_timing: id 2 | task 7748 | prompt processing, n_tokens = 1580, progress = 0.75, t = 5.45 s / 290.06 tokens per second 10.37.725.161 I slot print_timing: id 0 | task 7749 | prompt processing, n_tokens = 2072, progress = 1.00, t = 7.46 s / 277.73 tokens per second 10.37.967.018 I slot print_timing: id 2 | task 7748 | prompt processing, n_tokens = 1795, progress = 0.86, t = 7.46 s / 240.61 tokens per second 10.38.583.090 I slot print_timing: id 2 | task 7748 | prompt processing, n_tokens = 2092, progress = 1.00, t = 8.31 s / 251.75 tokens per second 10.38.682.122 I slot print_timing: id 1 | task 7752 | prompt eval time = 2673.41 ms / 320 tokens ( 8.35 ms per token, 119.70 tokens per second) 10.38.682.130 I slot print_timing: id 1 | task 7752 | eval time = 101.31 ms / 2 tokens ( 101.31 ms per token, 9.87 tokens per second) 10.38.682.131 I slot print_timing: id 1 | task 7752 | total time = 2774.72 ms / 322 tokens 10.38.682.132 I slot print_timing: id 1 | task 7752 | graphs reused = 6355 10.38.682.132 I slot print_timing: id 1 | task 7752 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.682.256 I slot release: id 1 | task 7752 | stop processing: n_tokens = 2153, truncated = 0 10.38.686.465 I slot print_timing: id 3 | task 7753 | prompt eval time = 2667.69 ms / 344 tokens ( 7.75 ms per token, 128.95 tokens per second) 10.38.686.470 I slot print_timing: id 3 | task 7753 | eval time = 103.44 ms / 2 tokens ( 103.44 ms per token, 9.67 tokens per second) 10.38.686.471 I slot print_timing: id 3 | task 7753 | total time = 2771.12 ms / 346 tokens 10.38.686.472 I slot print_timing: id 3 | task 7753 | graphs reused = 6355 10.38.686.472 I slot print_timing: id 3 | task 7753 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.686.569 I slot release: id 3 | task 7753 | stop processing: n_tokens = 2177, truncated = 0 10.38.744.109 I slot print_timing: id 0 | task 7749 | prompt eval time = 8313.88 ms / 2076 tokens ( 4.00 ms per token, 249.70 tokens per second) 10.38.744.113 I slot print_timing: id 0 | task 7749 | eval time = 165.66 ms / 3 tokens ( 82.83 ms per token, 12.07 tokens per second) 10.38.744.114 I slot print_timing: id 0 | task 7749 | total time = 8479.54 ms / 2079 tokens 10.38.744.114 I slot print_timing: id 0 | task 7749 | graphs reused = 6355 10.38.744.115 I slot print_timing: id 0 | task 7749 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.744.212 I slot release: id 0 | task 7749 | stop processing: n_tokens = 2087, truncated = 0 10.38.746.017 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.869 (> 0.100 thold), f_keep = 0.877 10.38.746.111 I slot launch_slot_: id 0 | task 7758 | processing task, is_child = 0 10.38.746.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.920 MiB) 10.38.746.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 234.529 MiB) 10.38.777.764 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.301 MiB) 10.38.808.406 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.851 10.38.808.524 I slot launch_slot_: id 1 | task 7759 | processing task, is_child = 0 10.38.808.656 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.806 (> 0.100 thold), f_keep = 0.842 10.38.808.693 I slot launch_slot_: id 3 | task 7760 | processing task, is_child = 0 10.40.715.496 I slot print_timing: id 2 | task 7748 | prompt eval time = 8419.50 ms / 2096 tokens ( 4.02 ms per token, 248.95 tokens per second) 10.40.715.499 I slot print_timing: id 2 | task 7748 | eval time = 2031.06 ms / 3 tokens ( 1015.53 ms per token, 0.98 tokens per second) 10.40.715.500 I slot print_timing: id 2 | task 7748 | total time = 10450.57 ms / 2099 tokens 10.40.715.503 I slot print_timing: id 2 | task 7748 | graphs reused = 6355 10.40.715.504 I slot print_timing: id 2 | task 7748 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.715.655 I slot release: id 2 | task 7748 | stop processing: n_tokens = 2107, truncated = 0 10.40.793.904 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.869 10.40.793.993 I slot launch_slot_: id 2 | task 7763 | processing task, is_child = 0 10.41.194.146 I slot print_timing: id 0 | task 7758 | prompt eval time = 1982.91 ms / 276 tokens ( 7.18 ms per token, 139.19 tokens per second) 10.41.194.153 I slot print_timing: id 0 | task 7758 | eval time = 402.49 ms / 2 tokens ( 402.49 ms per token, 2.48 tokens per second) 10.41.194.154 I slot print_timing: id 0 | task 7758 | total time = 2385.40 ms / 278 tokens 10.41.194.156 I slot print_timing: id 0 | task 7758 | graphs reused = 6355 10.41.194.157 I slot print_timing: id 0 | task 7758 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.194.477 I slot release: id 0 | task 7758 | stop processing: n_tokens = 2108, truncated = 0 10.41.199.833 I slot print_timing: id 3 | task 7760 | prompt eval time = 1978.84 ms / 441 tokens ( 4.49 ms per token, 222.86 tokens per second) 10.41.199.840 I slot print_timing: id 3 | task 7760 | eval time = 405.93 ms / 2 tokens ( 405.93 ms per token, 2.46 tokens per second) 10.41.199.842 I slot print_timing: id 3 | task 7760 | total time = 2384.77 ms / 443 tokens 10.41.199.843 I slot print_timing: id 3 | task 7760 | graphs reused = 6355 10.41.199.844 I slot print_timing: id 3 | task 7760 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.200.035 I slot release: id 3 | task 7760 | stop processing: n_tokens = 2273, truncated = 0 10.41.268.785 I slot print_timing: id 1 | task 7759 | prompt eval time = 1981.88 ms / 354 tokens ( 5.60 ms per token, 178.62 tokens per second) 10.41.268.790 I slot print_timing: id 1 | task 7759 | eval time = 475.99 ms / 3 tokens ( 237.99 ms per token, 4.20 tokens per second) 10.41.268.791 I slot print_timing: id 1 | task 7759 | total time = 2457.87 ms / 357 tokens 10.41.268.792 I slot print_timing: id 1 | task 7759 | graphs reused = 6355 10.41.268.792 I slot print_timing: id 1 | task 7759 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.268.943 I slot release: id 1 | task 7759 | stop processing: n_tokens = 2187, truncated = 0 10.41.271.156 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.838 10.41.271.274 I slot launch_slot_: id 1 | task 7766 | processing task, is_child = 0 10.41.271.507 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.793 MiB) 10.41.311.898 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.694 MiB) 10.41.311.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.934 MiB) 10.41.357.228 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.869 10.41.357.343 I slot launch_slot_: id 0 | task 7767 | processing task, is_child = 0 10.41.357.485 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.806 10.41.357.523 I slot launch_slot_: id 3 | task 7768 | processing task, is_child = 0 10.42.786.420 I slot print_timing: id 2 | task 7763 | prompt eval time = 477.14 ms / 189 tokens ( 2.52 ms per token, 396.11 tokens per second) 10.42.786.422 I slot print_timing: id 2 | task 7763 | eval time = 1515.27 ms / 3 tokens ( 757.64 ms per token, 1.32 tokens per second) 10.42.786.424 I slot print_timing: id 2 | task 7763 | total time = 1992.41 ms / 192 tokens 10.42.786.424 I slot print_timing: id 2 | task 7763 | graphs reused = 6355 10.42.786.425 I slot print_timing: id 2 | task 7763 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.786.521 I slot release: id 2 | task 7763 | stop processing: n_tokens = 2023, truncated = 0 10.42.846.850 I slot print_timing: id 0 | task 7767 | prompt eval time = 1426.61 ms / 226 tokens ( 6.31 ms per token, 158.42 tokens per second) 10.42.846.853 I slot print_timing: id 0 | task 7767 | eval time = 62.70 ms / 2 tokens ( 62.70 ms per token, 15.95 tokens per second) 10.42.846.854 I slot print_timing: id 0 | task 7767 | total time = 1489.31 ms / 228 tokens 10.42.846.854 I slot print_timing: id 0 | task 7767 | graphs reused = 6355 10.42.846.855 I slot print_timing: id 0 | task 7767 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.846.950 I slot release: id 0 | task 7767 | stop processing: n_tokens = 2058, truncated = 0 10.42.848.494 I slot print_timing: id 1 | task 7766 | prompt eval time = 1425.49 ms / 231 tokens ( 6.17 ms per token, 162.05 tokens per second) 10.42.848.497 I slot print_timing: id 1 | task 7766 | eval time = 63.16 ms / 2 tokens ( 63.16 ms per token, 15.83 tokens per second) 10.42.848.498 I slot print_timing: id 1 | task 7766 | total time = 1488.65 ms / 233 tokens 10.42.848.498 I slot print_timing: id 1 | task 7766 | graphs reused = 6355 10.42.848.499 I slot print_timing: id 1 | task 7766 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.848.561 I slot release: id 1 | task 7766 | stop processing: n_tokens = 2064, truncated = 0 10.42.850.317 I slot print_timing: id 3 | task 7768 | prompt eval time = 1425.98 ms / 280 tokens ( 5.09 ms per token, 196.36 tokens per second) 10.42.850.320 I slot print_timing: id 3 | task 7768 | eval time = 62.60 ms / 2 tokens ( 62.60 ms per token, 15.97 tokens per second) 10.42.850.320 I slot print_timing: id 3 | task 7768 | total time = 1488.58 ms / 282 tokens 10.42.850.321 I slot print_timing: id 3 | task 7768 | graphs reused = 6355 10.42.850.321 I slot print_timing: id 3 | task 7768 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.850.386 I slot release: id 3 | task 7768 | stop processing: n_tokens = 2113, truncated = 0 10.42.850.397 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.852 (> 0.100 thold), f_keep = 0.888 10.42.850.486 I slot launch_slot_: id 1 | task 7772 | processing task, is_child = 0 10.42.850.688 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.413 MiB) 10.42.964.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.624 MiB) 10.42.995.639 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.441 MiB) 10.43.016.551 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.890 10.43.016.665 I slot launch_slot_: id 0 | task 7773 | processing task, is_child = 0 10.43.016.887 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.905 10.43.016.931 I slot launch_slot_: id 2 | task 7774 | processing task, is_child = 0 10.43.017.045 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.845 (> 0.100 thold), f_keep = 0.867 10.43.017.081 I slot launch_slot_: id 3 | task 7775 | processing task, is_child = 0 10.45.130.850 I slot print_timing: id 0 | task 7773 | prompt eval time = 2076.32 ms / 193 tokens ( 10.76 ms per token, 92.95 tokens per second) 10.45.130.853 I slot print_timing: id 0 | task 7773 | eval time = 37.44 ms / 2 tokens ( 37.44 ms per token, 26.71 tokens per second) 10.45.130.853 I slot print_timing: id 0 | task 7773 | total time = 2113.75 ms / 195 tokens 10.45.130.854 I slot print_timing: id 0 | task 7773 | graphs reused = 6355 10.45.130.854 I slot print_timing: id 0 | task 7773 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.130.925 I slot release: id 0 | task 7773 | stop processing: n_tokens = 2025, truncated = 0 10.45.132.004 I slot print_timing: id 1 | task 7772 | prompt eval time = 2075.47 ms / 318 tokens ( 6.53 ms per token, 153.22 tokens per second) 10.45.132.006 I slot print_timing: id 1 | task 7772 | eval time = 37.49 ms / 2 tokens ( 37.49 ms per token, 26.67 tokens per second) 10.45.132.007 I slot print_timing: id 1 | task 7772 | total time = 2112.96 ms / 320 tokens 10.45.132.007 I slot print_timing: id 1 | task 7772 | graphs reused = 6355 10.45.132.007 I slot print_timing: id 1 | task 7772 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.132.064 I slot release: id 1 | task 7772 | stop processing: n_tokens = 2151, truncated = 0 10.45.133.142 I slot print_timing: id 2 | task 7774 | prompt eval time = 2074.79 ms / 289 tokens ( 7.18 ms per token, 139.29 tokens per second) 10.45.133.143 I slot print_timing: id 2 | task 7774 | eval time = 37.53 ms / 2 tokens ( 37.53 ms per token, 26.64 tokens per second) 10.45.133.144 I slot print_timing: id 2 | task 7774 | total time = 2112.32 ms / 291 tokens 10.45.133.144 I slot print_timing: id 2 | task 7774 | graphs reused = 6355 10.45.133.144 I slot print_timing: id 2 | task 7774 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.133.186 I slot release: id 2 | task 7774 | stop processing: n_tokens = 2121, truncated = 0 10.45.134.252 I slot print_timing: id 3 | task 7775 | prompt eval time = 2074.09 ms / 336 tokens ( 6.17 ms per token, 162.00 tokens per second) 10.45.134.255 I slot print_timing: id 3 | task 7775 | eval time = 37.51 ms / 2 tokens ( 37.51 ms per token, 26.66 tokens per second) 10.45.134.255 I slot print_timing: id 3 | task 7775 | total time = 2111.60 ms / 338 tokens 10.45.134.255 I slot print_timing: id 3 | task 7775 | graphs reused = 6355 10.45.134.256 I slot print_timing: id 3 | task 7775 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.134.301 I slot release: id 3 | task 7775 | stop processing: n_tokens = 2169, truncated = 0 10.45.143.684 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.852 10.45.143.751 I slot launch_slot_: id 1 | task 7779 | processing task, is_child = 0 10.45.143.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.582 MiB) 10.45.155.327 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.547 MiB) 10.45.170.895 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.290 MiB) 10.45.170.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 256.751 MiB) 10.45.200.516 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.904 10.45.200.604 I slot launch_slot_: id 0 | task 7780 | processing task, is_child = 0 10.45.200.833 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.863 10.45.200.874 I slot launch_slot_: id 2 | task 7781 | processing task, is_child = 0 10.45.200.986 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.822 (> 0.100 thold), f_keep = 0.845 10.45.201.021 I slot launch_slot_: id 3 | task 7782 | processing task, is_child = 0 10.47.476.855 I slot print_timing: id 0 | task 7780 | prompt eval time = 2234.56 ms / 249 tokens ( 8.97 ms per token, 111.43 tokens per second) 10.47.476.860 I slot print_timing: id 0 | task 7780 | eval time = 41.26 ms / 2 tokens ( 41.26 ms per token, 24.24 tokens per second) 10.47.476.861 I slot print_timing: id 0 | task 7780 | total time = 2275.82 ms / 251 tokens 10.47.476.862 I slot print_timing: id 0 | task 7780 | graphs reused = 6355 10.47.476.863 I slot print_timing: id 0 | task 7780 | graph reallocs = 0 / 0 (same size) / (changed size) 10.47.476.989 I slot release: id 0 | task 7780 | stop processing: n_tokens = 2081, truncated = 0 10.47.481.112 I slot print_timing: id 2 | task 7781 | prompt eval time = 2234.49 ms / 387 tokens ( 5.77 ms per token, 173.19 tokens per second) 10.47.481.119 I slot print_timing: id 2 | task 7781 | eval time = 41.78 ms / 2 tokens ( 41.78 ms per token, 23.94 tokens per second) 10.47.481.119 I slot print_timing: id 2 | task 7781 | total time = 2276.27 ms / 389 tokens 10.47.481.120 I slot print_timing: id 2 | task 7781 | graphs reused = 6355 10.47.481.120 I slot print_timing: id 2 | task 7781 | graph reallocs = 0 / 0 (same size) / (changed size) 10.47.481.203 I slot release: id 2 | task 7781 | stop processing: n_tokens = 2219, truncated = 0 10.47.482.984 I slot print_timing: id 3 | task 7782 | prompt eval time = 2234.55 ms / 398 tokens ( 5.61 ms per token, 178.11 tokens per second) 10.47.482.988 I slot print_timing: id 3 | task 7782 | eval time = 41.76 ms / 2 tokens ( 41.76 ms per token, 23.95 tokens per second) 10.47.482.989 I slot print_timing: id 3 | task 7782 | total time = 2276.32 ms / 400 tokens 10.47.482.989 I slot print_timing: id 3 | task 7782 | graphs reused = 6355 10.47.482.990 I slot print_timing: id 3 | task 7782 | graph reallocs = 0 / 0 (same size) / (changed size) 10.47.483.077 I slot release: id 3 | task 7782 | stop processing: n_tokens = 2231, truncated = 0 10.47.513.219 I slot print_timing: id 1 | task 7779 | prompt eval time = 2234.61 ms / 189 tokens ( 11.82 ms per token, 84.58 tokens per second) 10.47.513.222 I slot print_timing: id 1 | task 7779 | eval time = 75.75 ms / 3 tokens ( 37.88 ms per token, 26.40 tokens per second) 10.47.513.223 I slot print_timing: id 1 | task 7779 | total time = 2310.36 ms / 192 tokens 10.47.513.223 I slot print_timing: id 1 | task 7779 | graphs reused = 6355 10.47.513.224 I slot print_timing: id 1 | task 7779 | graph reallocs = 0 / 0 (same size) / (changed size) 10.47.513.318 I slot release: id 1 | task 7779 | stop processing: n_tokens = 2023, truncated = 0 10.47.513.331 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.880 10.47.513.416 I slot launch_slot_: id 0 | task 7787 | processing task, is_child = 0 10.47.513.617 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.644 MiB) 10.47.552.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.909 MiB) 10.47.552.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.485 MiB) 10.47.575.006 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.589 MiB) 10.47.575.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.744 MiB) 10.47.665.231 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.906 10.47.665.304 I slot launch_slot_: id 1 | task 7788 | processing task, is_child = 0 10.47.665.564 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.825 10.47.665.600 I slot launch_slot_: id 2 | task 7789 | processing task, is_child = 0 10.47.665.721 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.821 10.47.665.753 I slot launch_slot_: id 3 | task 7790 | processing task, is_child = 0 10.49.179.436 I slot print_timing: id 0 | task 7787 | prompt eval time = 1476.00 ms / 212 tokens ( 6.96 ms per token, 143.63 tokens per second) 10.49.179.440 I slot print_timing: id 0 | task 7787 | eval time = 37.67 ms / 2 tokens ( 37.67 ms per token, 26.54 tokens per second) 10.49.179.441 I slot print_timing: id 0 | task 7787 | total time = 1513.67 ms / 214 tokens 10.49.179.441 I slot print_timing: id 0 | task 7787 | graphs reused = 6355 10.49.179.442 I slot print_timing: id 0 | task 7787 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.179.528 I slot release: id 0 | task 7787 | stop processing: n_tokens = 2044, truncated = 0 10.49.182.160 I slot print_timing: id 2 | task 7789 | prompt eval time = 1472.52 ms / 124 tokens ( 11.88 ms per token, 84.21 tokens per second) 10.49.182.162 I slot print_timing: id 2 | task 7789 | eval time = 38.07 ms / 2 tokens ( 38.07 ms per token, 26.27 tokens per second) 10.49.182.163 I slot print_timing: id 2 | task 7789 | total time = 1510.59 ms / 126 tokens 10.49.182.163 I slot print_timing: id 2 | task 7789 | graphs reused = 6355 10.49.182.164 I slot print_timing: id 2 | task 7789 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.182.218 I slot release: id 2 | task 7789 | stop processing: n_tokens = 1955, truncated = 0 10.49.183.578 I slot print_timing: id 3 | task 7790 | prompt eval time = 1470.68 ms / 208 tokens ( 7.07 ms per token, 141.43 tokens per second) 10.49.183.581 I slot print_timing: id 3 | task 7790 | eval time = 38.39 ms / 2 tokens ( 38.39 ms per token, 26.05 tokens per second) 10.49.183.582 I slot print_timing: id 3 | task 7790 | total time = 1509.07 ms / 210 tokens 10.49.183.582 I slot print_timing: id 3 | task 7790 | graphs reused = 6355 10.49.183.583 I slot print_timing: id 3 | task 7790 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.183.634 I slot release: id 3 | task 7790 | stop processing: n_tokens = 2041, truncated = 0 10.49.213.931 I slot print_timing: id 1 | task 7788 | prompt eval time = 1475.45 ms / 238 tokens ( 6.20 ms per token, 161.31 tokens per second) 10.49.213.934 I slot print_timing: id 1 | task 7788 | eval time = 70.98 ms / 3 tokens ( 35.49 ms per token, 28.18 tokens per second) 10.49.213.935 I slot print_timing: id 1 | task 7788 | total time = 1546.43 ms / 241 tokens 10.49.213.937 I slot print_timing: id 1 | task 7788 | graphs reused = 6355 10.49.213.937 I slot print_timing: id 1 | task 7788 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.214.027 I slot release: id 1 | task 7788 | stop processing: n_tokens = 2072, truncated = 0 10.49.214.034 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2044, t_last = 319752703312 10.49.214.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.083 MiB) 10.49.287.871 I slot launch_slot_: id 0 | task 7795 | processing task, is_child = 0 10.49.288.029 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.961 MiB) 10.49.366.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.508 MiB) 10.49.366.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.477 MiB) 10.49.414.947 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.515 MiB) 10.49.414.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.437 MiB) 10.49.484.285 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.884 10.49.484.406 I slot launch_slot_: id 1 | task 7796 | processing task, is_child = 0 10.49.484.669 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1955, t_last = 319752706001 10.49.484.827 I slot launch_slot_: id 2 | task 7797 | processing task, is_child = 0 10.49.484.940 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2041, t_last = 319752707416 10.49.485.105 I slot launch_slot_: id 3 | task 7798 | processing task, is_child = 0 10.55.366.801 I slot print_timing: id 0 | task 7795 | prompt processing, n_tokens = 1264, progress = 0.86, t = 5.88 s / 214.96 tokens per second 10.55.370.660 I slot print_timing: id 2 | task 7797 | prompt processing, n_tokens = 1155, progress = 0.69, t = 5.88 s / 196.58 tokens per second 10.56.437.505 I slot print_timing: id 1 | task 7796 | prompt eval time = 5881.26 ms / 172 tokens ( 34.19 ms per token, 29.25 tokens per second) 10.56.437.509 I slot print_timing: id 1 | task 7796 | eval time = 1070.73 ms / 2 tokens ( 1070.73 ms per token, 0.93 tokens per second) 10.56.437.510 I slot print_timing: id 1 | task 7796 | total time = 6951.99 ms / 174 tokens 10.56.437.510 I slot print_timing: id 1 | task 7796 | graphs reused = 6355 10.56.437.510 I slot print_timing: id 1 | task 7796 | graph reallocs = 0 / 0 (same size) / (changed size) 10.56.437.661 I slot release: id 1 | task 7796 | stop processing: n_tokens = 2004, truncated = 0 10.56.437.696 I slot print_timing: id 0 | task 7795 | prompt processing, n_tokens = 1462, progress = 1.00, t = 6.95 s / 210.32 tokens per second 10.56.441.957 I slot print_timing: id 2 | task 7797 | prompt processing, n_tokens = 1264, progress = 0.76, t = 6.95 s / 181.96 tokens per second 10.56.444.186 I slot print_timing: id 3 | task 7798 | prompt processing, n_tokens = 1264, progress = 0.82, t = 3.64 s / 346.88 tokens per second 10.57.664.740 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2004, t_last = 319759961444 10.57.664.929 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.906 MiB) 10.57.703.516 I slot launch_slot_: id 1 | task 7803 | processing task, is_child = 0 10.57.703.813 I slot print_timing: id 2 | task 7797 | prompt processing, n_tokens = 1667, progress = 1.00, t = 8.17 s / 203.95 tokens per second 10.57.705.835 I slot print_timing: id 3 | task 7798 | prompt processing, n_tokens = 1533, progress = 1.00, t = 4.87 s / 314.72 tokens per second 10.58.521.625 I slot print_timing: id 0 | task 7795 | prompt eval time = 8179.61 ms / 1466 tokens ( 5.58 ms per token, 179.23 tokens per second) 10.58.521.629 I slot print_timing: id 0 | task 7795 | eval time = 856.89 ms / 2 tokens ( 856.89 ms per token, 1.17 tokens per second) 10.58.521.630 I slot print_timing: id 0 | task 7795 | total time = 9036.50 ms / 1468 tokens 10.58.521.630 I slot print_timing: id 0 | task 7795 | graphs reused = 6355 10.58.521.631 I slot print_timing: id 0 | task 7795 | graph reallocs = 0 / 0 (same size) / (changed size) 10.58.521.743 I slot release: id 0 | task 7795 | stop processing: n_tokens = 1476, truncated = 0 10.59.177.269 I slot print_timing: id 2 | task 7797 | prompt eval time = 9033.23 ms / 1671 tokens ( 5.41 ms per token, 184.98 tokens per second) 10.59.177.279 I slot print_timing: id 2 | task 7797 | eval time = 654.21 ms / 2 tokens ( 654.21 ms per token, 1.53 tokens per second) 10.59.177.279 I slot print_timing: id 2 | task 7797 | total time = 9687.43 ms / 1673 tokens 10.59.177.279 I slot print_timing: id 2 | task 7797 | graphs reused = 6355 10.59.177.280 I slot print_timing: id 2 | task 7797 | graph reallocs = 0 / 0 (same size) / (changed size) 10.59.177.437 I slot release: id 2 | task 7797 | stop processing: n_tokens = 1681, truncated = 0 10.59.178.681 I slot print_timing: id 3 | task 7798 | prompt eval time = 5732.07 ms / 1537 tokens ( 3.73 ms per token, 268.14 tokens per second) 10.59.178.685 I slot print_timing: id 3 | task 7798 | eval time = 654.13 ms / 2 tokens ( 654.13 ms per token, 1.53 tokens per second) 10.59.178.686 I slot print_timing: id 3 | task 7798 | total time = 6386.21 ms / 1539 tokens 10.59.178.686 I slot print_timing: id 3 | task 7798 | graphs reused = 6355 10.59.178.686 I slot print_timing: id 3 | task 7798 | graph reallocs = 0 / 0 (same size) / (changed size) 10.59.178.742 I slot release: id 3 | task 7798 | stop processing: n_tokens = 1547, truncated = 0 10.59.178.757 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 319762045527 10.59.178.878 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.063 MiB) 10.59.217.029 I slot launch_slot_: id 0 | task 7806 | processing task, is_child = 0 10.59.217.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.143 MiB) 10.59.246.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.053 MiB) 10.59.280.866 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1681, t_last = 319762701221 10.59.281.049 I slot launch_slot_: id 2 | task 7807 | processing task, is_child = 0 10.59.281.146 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1547, t_last = 319762702524 10.59.281.267 I slot launch_slot_: id 3 | task 7808 | processing task, is_child = 0 11.01.744.754 I slot print_timing: id 1 | task 7803 | prompt processing, n_tokens = 991, progress = 1.00, t = 3.99 s / 248.24 tokens per second 11.03.762.456 I slot print_timing: id 0 | task 7806 | prompt processing, n_tokens = 848, progress = 0.86, t = 4.48 s / 189.43 tokens per second 11.03.769.346 I slot print_timing: id 2 | task 7807 | prompt processing, n_tokens = 848, progress = 0.89, t = 4.47 s / 189.51 tokens per second 11.03.773.167 I slot print_timing: id 3 | task 7808 | prompt processing, n_tokens = 848, progress = 0.87, t = 4.47 s / 189.52 tokens per second 11.04.510.686 I slot print_timing: id 1 | task 7803 | prompt eval time = 6058.84 ms / 995 tokens ( 6.09 ms per token, 164.22 tokens per second) 11.04.510.700 I slot print_timing: id 1 | task 7803 | eval time = 748.27 ms / 2 tokens ( 748.27 ms per token, 1.34 tokens per second) 11.04.510.702 I slot print_timing: id 1 | task 7803 | total time = 6807.10 ms / 997 tokens 11.04.510.703 I slot print_timing: id 1 | task 7803 | graphs reused = 6355 11.04.510.705 I slot print_timing: id 1 | task 7803 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.510.894 I slot release: id 1 | task 7803 | stop processing: n_tokens = 1005, truncated = 0 11.04.510.953 I slot print_timing: id 0 | task 7806 | prompt processing, n_tokens = 981, progress = 1.00, t = 5.23 s / 187.74 tokens per second 11.04.518.328 I slot print_timing: id 2 | task 7807 | prompt processing, n_tokens = 954, progress = 1.00, t = 5.22 s / 182.64 tokens per second 11.04.522.489 I slot print_timing: id 3 | task 7808 | prompt processing, n_tokens = 969, progress = 1.00, t = 5.22 s / 185.52 tokens per second 11.04.601.132 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.880 11.04.601.313 I slot launch_slot_: id 1 | task 7813 | processing task, is_child = 0 11.04.888.253 I slot print_timing: id 0 | task 7806 | prompt eval time = 5314.17 ms / 985 tokens ( 5.40 ms per token, 185.35 tokens per second) 11.04.888.260 I slot print_timing: id 0 | task 7806 | eval time = 292.77 ms / 2 tokens ( 292.77 ms per token, 3.42 tokens per second) 11.04.888.261 I slot print_timing: id 0 | task 7806 | total time = 5606.94 ms / 987 tokens 11.04.888.262 I slot print_timing: id 0 | task 7806 | graphs reused = 6355 11.04.888.263 I slot print_timing: id 0 | task 7806 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.888.437 I slot release: id 0 | task 7806 | stop processing: n_tokens = 995, truncated = 0 11.04.890.819 I slot print_timing: id 2 | task 7807 | prompt eval time = 5315.06 ms / 958 tokens ( 5.55 ms per token, 180.24 tokens per second) 11.04.890.830 I slot print_timing: id 2 | task 7807 | eval time = 292.51 ms / 2 tokens ( 292.51 ms per token, 3.42 tokens per second) 11.04.890.831 I slot print_timing: id 2 | task 7807 | total time = 5607.58 ms / 960 tokens 11.04.890.831 I slot print_timing: id 2 | task 7807 | graphs reused = 6355 11.04.890.839 I slot print_timing: id 2 | task 7807 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.890.928 I slot release: id 2 | task 7807 | stop processing: n_tokens = 968, truncated = 0 11.04.893.047 I slot print_timing: id 3 | task 7808 | prompt eval time = 5317.63 ms / 973 tokens ( 5.47 ms per token, 182.98 tokens per second) 11.04.893.054 I slot print_timing: id 3 | task 7808 | eval time = 291.92 ms / 2 tokens ( 291.92 ms per token, 3.43 tokens per second) 11.04.893.055 I slot print_timing: id 3 | task 7808 | total time = 5609.55 ms / 975 tokens 11.04.893.056 I slot print_timing: id 3 | task 7808 | graphs reused = 6355 11.04.893.057 I slot print_timing: id 3 | task 7808 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.893.131 I slot release: id 3 | task 7808 | stop processing: n_tokens = 983, truncated = 0 11.04.932.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 319768412219 11.04.932.946 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 347.262 MiB) 11.04.953.738 I slot launch_slot_: id 0 | task 7816 | processing task, is_child = 0 11.04.953.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 347.754 MiB) 11.04.976.236 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 402.605 MiB) 11.04.997.676 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.913 11.04.997.792 I slot launch_slot_: id 2 | task 7817 | processing task, is_child = 0 11.04.997.878 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.899 11.04.997.920 I slot launch_slot_: id 3 | task 7818 | processing task, is_child = 0 11.05.880.597 I slot print_timing: id 1 | task 7813 | prompt eval time = 331.45 ms / 103 tokens ( 3.22 ms per token, 310.76 tokens per second) 11.05.880.601 I slot print_timing: id 1 | task 7813 | eval time = 947.80 ms / 2 tokens ( 947.80 ms per token, 1.06 tokens per second) 11.05.880.601 I slot print_timing: id 1 | task 7813 | total time = 1279.25 ms / 105 tokens 11.05.880.602 I slot print_timing: id 1 | task 7813 | graphs reused = 6355 11.05.880.602 I slot print_timing: id 1 | task 7813 | graph reallocs = 0 / 0 (same size) / (changed size) 11.05.880.884 I slot release: id 1 | task 7813 | stop processing: n_tokens = 988, truncated = 0 11.06.584.236 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 319769404667 11.06.598.684 I slot launch_slot_: id 1 | task 7821 | processing task, is_child = 0 11.08.661.277 I slot print_timing: id 2 | task 7817 | prompt eval time = 1584.64 ms / 93 tokens ( 17.04 ms per token, 58.69 tokens per second) 11.08.661.288 I slot print_timing: id 2 | task 7817 | eval time = 2078.39 ms / 2 tokens ( 2078.39 ms per token, 0.48 tokens per second) 11.08.661.290 I slot print_timing: id 2 | task 7817 | total time = 3663.03 ms / 95 tokens 11.08.661.292 I slot print_timing: id 2 | task 7817 | graphs reused = 6355 11.08.661.293 I slot print_timing: id 2 | task 7817 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.661.501 I slot release: id 2 | task 7817 | stop processing: n_tokens = 978, truncated = 0 11.08.663.667 I slot print_timing: id 3 | task 7818 | prompt eval time = 1583.79 ms / 98 tokens ( 16.16 ms per token, 61.88 tokens per second) 11.08.663.673 I slot print_timing: id 3 | task 7818 | eval time = 2079.43 ms / 2 tokens ( 2079.43 ms per token, 0.48 tokens per second) 11.08.663.674 I slot print_timing: id 3 | task 7818 | total time = 3663.21 ms / 100 tokens 11.08.663.675 I slot print_timing: id 3 | task 7818 | graphs reused = 6355 11.08.663.676 I slot print_timing: id 3 | task 7818 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.663.784 I slot release: id 3 | task 7818 | stop processing: n_tokens = 983, truncated = 0 11.08.663.842 I slot print_timing: id 0 | task 7816 | prompt processing, n_tokens = 810, progress = 1.00, t = 3.66 s / 221.32 tokens per second 11.09.144.534 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 978, t_last = 319772185283 11.09.144.882 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 346.172 MiB) 11.09.191.762 I slot launch_slot_: id 2 | task 7824 | processing task, is_child = 0 11.09.191.886 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 459.882 MiB) 11.09.242.129 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 983, t_last = 319772187566 11.09.242.305 I slot launch_slot_: id 3 | task 7825 | processing task, is_child = 0 11.12.591.194 I slot print_timing: id 0 | task 7816 | prompt eval time = 4146.55 ms / 814 tokens ( 5.09 ms per token, 196.31 tokens per second) 11.12.591.197 I slot print_timing: id 0 | task 7816 | eval time = 3446.70 ms / 2 tokens ( 3446.70 ms per token, 0.29 tokens per second) 11.12.591.198 I slot print_timing: id 0 | task 7816 | total time = 7593.25 ms / 816 tokens 11.12.591.199 I slot print_timing: id 0 | task 7816 | graphs reused = 6355 11.12.591.199 I slot print_timing: id 0 | task 7816 | graph reallocs = 0 / 0 (same size) / (changed size) 11.12.591.366 I slot release: id 0 | task 7816 | stop processing: n_tokens = 824, truncated = 0 11.12.591.405 I slot print_timing: id 1 | task 7821 | prompt processing, n_tokens = 1643, progress = 1.00, t = 5.99 s / 274.31 tokens per second 11.12.594.601 I slot print_timing: id 2 | task 7824 | prompt processing, n_tokens = 1086, progress = 0.68, t = 3.34 s / 324.67 tokens per second 11.12.596.629 I slot print_timing: id 3 | task 7825 | prompt processing, n_tokens = 706, progress = 0.44, t = 3.34 s / 211.08 tokens per second 11.13.867.030 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 319776115149 11.13.874.983 I slot launch_slot_: id 0 | task 7828 | processing task, is_child = 0 11.13.875.211 I slot print_timing: id 2 | task 7824 | prompt processing, n_tokens = 1388, progress = 0.87, t = 4.62 s / 300.39 tokens per second 11.13.876.964 I slot print_timing: id 3 | task 7825 | prompt processing, n_tokens = 1114, progress = 0.69, t = 4.62 s / 241.10 tokens per second 11.16.594.176 I slot print_timing: id 1 | task 7821 | prompt eval time = 7266.62 ms / 1647 tokens ( 4.41 ms per token, 226.65 tokens per second) 11.16.594.183 I slot print_timing: id 1 | task 7821 | eval time = 2727.14 ms / 2 tokens ( 2727.14 ms per token, 0.37 tokens per second) 11.16.594.184 I slot print_timing: id 1 | task 7821 | total time = 9993.76 ms / 1649 tokens 11.16.594.185 I slot print_timing: id 1 | task 7821 | graphs reused = 6355 11.16.594.186 I slot print_timing: id 1 | task 7821 | graph reallocs = 0 / 0 (same size) / (changed size) 11.16.594.578 I slot release: id 1 | task 7821 | stop processing: n_tokens = 1657, truncated = 0 11.16.598.709 I slot print_timing: id 2 | task 7824 | prompt processing, n_tokens = 1598, progress = 1.00, t = 7.35 s / 217.54 tokens per second 11.16.602.980 I slot print_timing: id 3 | task 7825 | prompt processing, n_tokens = 1388, progress = 0.85, t = 7.35 s / 188.96 tokens per second 11.17.509.115 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.814 (> 0.100 thold), f_keep = 0.859 11.17.509.532 I slot launch_slot_: id 1 | task 7831 | processing task, is_child = 0 11.17.509.572 I slot print_timing: id 0 | task 7828 | prompt processing, n_tokens = 1388, progress = 0.84, t = 3.63 s / 382.36 tokens per second 11.17.538.318 I slot print_timing: id 3 | task 7825 | prompt processing, n_tokens = 1626, progress = 1.00, t = 8.26 s / 196.86 tokens per second 11.18.625.144 I slot print_timing: id 0 | task 7828 | prompt processing, n_tokens = 1652, progress = 1.00, t = 4.74 s / 348.32 tokens per second 11.18.707.627 I slot print_timing: id 2 | task 7824 | prompt eval time = 8263.93 ms / 1602 tokens ( 5.16 ms per token, 193.85 tokens per second) 11.18.707.642 I slot print_timing: id 2 | task 7824 | eval time = 1198.54 ms / 3 tokens ( 599.27 ms per token, 1.67 tokens per second) 11.18.707.643 I slot print_timing: id 2 | task 7824 | total time = 9462.47 ms / 1605 tokens 11.18.707.644 I slot print_timing: id 2 | task 7824 | graphs reused = 6355 11.18.707.654 I slot print_timing: id 2 | task 7824 | graph reallocs = 0 / 0 (same size) / (changed size) 11.18.707.915 I slot release: id 2 | task 7824 | stop processing: n_tokens = 1613, truncated = 0 11.18.709.889 I slot print_timing: id 3 | task 7825 | prompt eval time = 9379.68 ms / 1630 tokens ( 5.75 ms per token, 173.78 tokens per second) 11.18.709.897 I slot print_timing: id 3 | task 7825 | eval time = 84.80 ms / 2 tokens ( 84.80 ms per token, 11.79 tokens per second) 11.18.709.898 I slot print_timing: id 3 | task 7825 | total time = 9464.48 ms / 1632 tokens 11.18.709.898 I slot print_timing: id 3 | task 7825 | graphs reused = 6355 11.18.709.905 I slot print_timing: id 3 | task 7825 | graph reallocs = 0 / 0 (same size) / (changed size) 11.18.710.043 I slot release: id 3 | task 7825 | stop processing: n_tokens = 1640, truncated = 0 11.18.744.111 I slot print_timing: id 0 | task 7828 | prompt eval time = 4828.33 ms / 1656 tokens ( 2.92 ms per token, 342.98 tokens per second) 11.18.744.115 I slot print_timing: id 0 | task 7828 | eval time = 40.78 ms / 2 tokens ( 40.78 ms per token, 24.52 tokens per second) 11.18.744.116 I slot print_timing: id 0 | task 7828 | total time = 4869.11 ms / 1658 tokens 11.18.744.117 I slot print_timing: id 0 | task 7828 | graphs reused = 6355 11.18.744.117 I slot print_timing: id 0 | task 7828 | graph reallocs = 0 / 0 (same size) / (changed size) 11.18.744.234 I slot release: id 0 | task 7828 | stop processing: n_tokens = 1666, truncated = 0 11.18.746.013 I slot print_timing: id 1 | task 7831 | prompt eval time = 1171.28 ms / 325 tokens ( 3.60 ms per token, 277.47 tokens per second) 11.18.746.017 I slot print_timing: id 1 | task 7831 | eval time = 40.40 ms / 2 tokens ( 40.40 ms per token, 24.75 tokens per second) 11.18.746.017 I slot print_timing: id 1 | task 7831 | total time = 1211.68 ms / 327 tokens 11.18.746.018 I slot print_timing: id 1 | task 7831 | graphs reused = 6355 11.18.746.018 I slot print_timing: id 1 | task 7831 | graph reallocs = 0 / 0 (same size) / (changed size) 11.18.746.107 I slot release: id 1 | task 7831 | stop processing: n_tokens = 1750, truncated = 0 11.18.746.117 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1613, t_last = 319782231705 11.18.746.292 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 344.413 MiB) 11.18.761.661 I slot launch_slot_: id 2 | task 7835 | processing task, is_child = 0 11.18.761.818 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 343.183 MiB) 11.18.777.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 454.255 MiB) 11.18.801.802 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1640, t_last = 319782233833 11.18.802.000 I slot launch_slot_: id 3 | task 7836 | processing task, is_child = 0 11.18.802.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1666, t_last = 319782268018 11.18.802.366 I slot launch_slot_: id 0 | task 7837 | processing task, is_child = 0 11.18.802.473 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1750, t_last = 319782269891 11.18.802.612 I slot launch_slot_: id 1 | task 7838 | processing task, is_child = 0 11.23.431.991 I slot print_timing: id 0 | task 7837 | prompt processing, n_tokens = 714, progress = 0.85, t = 4.63 s / 154.23 tokens per second 11.23.508.316 I slot print_timing: id 1 | task 7838 | prompt processing, n_tokens = 714, progress = 0.83, t = 4.63 s / 154.24 tokens per second 11.23.512.017 I slot print_timing: id 2 | task 7835 | prompt processing, n_tokens = 721, progress = 0.86, t = 4.63 s / 155.77 tokens per second 11.23.513.738 I slot print_timing: id 3 | task 7836 | prompt processing, n_tokens = 721, progress = 0.84, t = 4.63 s / 155.78 tokens per second 11.24.406.073 I slot print_timing: id 0 | task 7837 | prompt processing, n_tokens = 836, progress = 1.00, t = 5.60 s / 149.19 tokens per second 11.24.483.891 I slot print_timing: id 1 | task 7838 | prompt processing, n_tokens = 855, progress = 1.00, t = 5.60 s / 152.59 tokens per second 11.24.487.353 I slot print_timing: id 2 | task 7835 | prompt processing, n_tokens = 831, progress = 1.00, t = 5.60 s / 148.32 tokens per second 11.24.489.107 I slot print_timing: id 3 | task 7836 | prompt processing, n_tokens = 858, progress = 1.00, t = 5.60 s / 153.15 tokens per second 11.24.585.731 I slot print_timing: id 0 | task 7837 | prompt eval time = 5746.26 ms / 840 tokens ( 6.84 ms per token, 146.18 tokens per second) 11.24.585.734 I slot print_timing: id 0 | task 7837 | eval time = 36.85 ms / 2 tokens ( 36.85 ms per token, 27.14 tokens per second) 11.24.585.734 I slot print_timing: id 0 | task 7837 | total time = 5783.11 ms / 842 tokens 11.24.585.735 I slot print_timing: id 0 | task 7837 | graphs reused = 6355 11.24.585.735 I slot print_timing: id 0 | task 7837 | graph reallocs = 0 / 0 (same size) / (changed size) 11.24.585.792 I slot release: id 0 | task 7837 | stop processing: n_tokens = 850, truncated = 0 11.24.586.891 I slot print_timing: id 1 | task 7838 | prompt eval time = 5747.42 ms / 859 tokens ( 6.69 ms per token, 149.46 tokens per second) 11.24.586.895 I slot print_timing: id 1 | task 7838 | eval time = 36.52 ms / 2 tokens ( 36.52 ms per token, 27.38 tokens per second) 11.24.586.895 I slot print_timing: id 1 | task 7838 | total time = 5783.95 ms / 861 tokens 11.24.586.896 I slot print_timing: id 1 | task 7838 | graphs reused = 6355 11.24.586.896 I slot print_timing: id 1 | task 7838 | graph reallocs = 0 / 0 (same size) / (changed size) 11.24.586.941 I slot release: id 1 | task 7838 | stop processing: n_tokens = 869, truncated = 0 11.24.588.043 I slot print_timing: id 2 | task 7835 | prompt eval time = 5748.26 ms / 835 tokens ( 6.88 ms per token, 145.26 tokens per second) 11.24.588.044 I slot print_timing: id 2 | task 7835 | eval time = 36.48 ms / 2 tokens ( 36.48 ms per token, 27.41 tokens per second) 11.24.588.045 I slot print_timing: id 2 | task 7835 | total time = 5784.74 ms / 837 tokens 11.24.588.045 I slot print_timing: id 2 | task 7835 | graphs reused = 6355 11.24.588.045 I slot print_timing: id 2 | task 7835 | graph reallocs = 0 / 0 (same size) / (changed size) 11.24.588.078 I slot release: id 2 | task 7835 | stop processing: n_tokens = 845, truncated = 0 11.24.589.196 I slot print_timing: id 3 | task 7836 | prompt eval time = 5749.19 ms / 862 tokens ( 6.67 ms per token, 149.93 tokens per second) 11.24.589.198 I slot print_timing: id 3 | task 7836 | eval time = 36.39 ms / 2 tokens ( 36.39 ms per token, 27.48 tokens per second) 11.24.589.199 I slot print_timing: id 3 | task 7836 | total time = 5785.58 ms / 864 tokens 11.24.589.199 I slot print_timing: id 3 | task 7836 | graphs reused = 6355 11.24.589.199 I slot print_timing: id 3 | task 7836 | graph reallocs = 0 / 0 (same size) / (changed size) 11.24.589.223 I slot release: id 3 | task 7836 | stop processing: n_tokens = 872, truncated = 0 11.24.594.411 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 319788109574 11.24.594.485 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 343.253 MiB) 11.24.615.018 I slot launch_slot_: id 0 | task 7844 | processing task, is_child = 0 11.24.615.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 346.629 MiB) 11.24.651.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.225 MiB) 11.24.680.336 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 319788110723 11.24.680.487 I slot launch_slot_: id 1 | task 7845 | processing task, is_child = 0 11.24.680.634 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 319788111860 11.24.680.737 I slot launch_slot_: id 2 | task 7846 | processing task, is_child = 0 11.24.680.802 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 872, t_last = 319788113005 11.24.683.029 I slot launch_slot_: id 3 | task 7847 | processing task, is_child = 0 11.27.868.877 I slot print_timing: id 0 | task 7844 | prompt processing, n_tokens = 565, progress = 0.82, t = 3.19 s / 177.35 tokens per second 11.27.944.250 I slot print_timing: id 1 | task 7845 | prompt processing, n_tokens = 613, progress = 0.81, t = 3.19 s / 192.43 tokens per second 11.27.945.941 I slot print_timing: id 2 | task 7846 | prompt processing, n_tokens = 613, progress = 0.84, t = 3.19 s / 192.43 tokens per second 11.27.947.634 I slot print_timing: id 3 | task 7847 | prompt processing, n_tokens = 167, progress = 1.00, t = 3.18 s / 52.44 tokens per second 11.28.675.166 I slot print_timing: id 0 | task 7844 | prompt processing, n_tokens = 684, progress = 0.99, t = 3.99 s / 171.39 tokens per second 11.28.677.242 I slot print_timing: id 1 | task 7845 | prompt processing, n_tokens = 758, progress = 0.99, t = 3.99 s / 189.94 tokens per second 11.28.679.104 I slot print_timing: id 2 | task 7846 | prompt processing, n_tokens = 729, progress = 0.99, t = 3.99 s / 182.68 tokens per second 11.28.762.824 I slot print_timing: id 3 | task 7847 | prompt eval time = 3990.75 ms / 171 tokens ( 23.34 ms per token, 42.85 tokens per second) 11.28.762.827 I slot print_timing: id 3 | task 7847 | eval time = 87.67 ms / 2 tokens ( 87.67 ms per token, 11.41 tokens per second) 11.28.762.828 I slot print_timing: id 3 | task 7847 | total time = 4078.43 ms / 173 tokens 11.28.762.828 I slot print_timing: id 3 | task 7847 | graphs reused = 6355 11.28.762.829 I slot print_timing: id 3 | task 7847 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.762.880 I slot release: id 3 | task 7847 | stop processing: n_tokens = 894, truncated = 0 11.28.794.844 I slot print_timing: id 0 | task 7844 | prompt eval time = 4076.28 ms / 688 tokens ( 5.92 ms per token, 168.78 tokens per second) 11.28.794.848 I slot print_timing: id 0 | task 7844 | eval time = 35.53 ms / 2 tokens ( 35.53 ms per token, 28.15 tokens per second) 11.28.794.848 I slot print_timing: id 0 | task 7844 | total time = 4111.80 ms / 690 tokens 11.28.794.849 I slot print_timing: id 0 | task 7844 | graphs reused = 6355 11.28.794.849 I slot print_timing: id 0 | task 7844 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.794.896 I slot release: id 0 | task 7844 | stop processing: n_tokens = 698, truncated = 0 11.28.796.002 I slot print_timing: id 1 | task 7845 | prompt eval time = 4077.32 ms / 762 tokens ( 5.35 ms per token, 186.89 tokens per second) 11.28.796.003 I slot print_timing: id 1 | task 7845 | eval time = 35.47 ms / 2 tokens ( 35.47 ms per token, 28.19 tokens per second) 11.28.796.004 I slot print_timing: id 1 | task 7845 | total time = 4112.79 ms / 764 tokens 11.28.796.004 I slot print_timing: id 1 | task 7845 | graphs reused = 6355 11.28.796.005 I slot print_timing: id 1 | task 7845 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.796.043 I slot release: id 1 | task 7845 | stop processing: n_tokens = 772, truncated = 0 11.28.797.134 I slot print_timing: id 2 | task 7846 | prompt eval time = 4078.40 ms / 733 tokens ( 5.56 ms per token, 179.73 tokens per second) 11.28.797.136 I slot print_timing: id 2 | task 7846 | eval time = 35.37 ms / 2 tokens ( 35.37 ms per token, 28.27 tokens per second) 11.28.797.137 I slot print_timing: id 2 | task 7846 | total time = 4113.77 ms / 735 tokens 11.28.797.137 I slot print_timing: id 2 | task 7846 | graphs reused = 6355 11.28.797.137 I slot print_timing: id 2 | task 7846 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.797.165 I slot release: id 2 | task 7846 | stop processing: n_tokens = 743, truncated = 0 11.28.797.171 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.839 (> 0.100 thold), f_keep = 0.861 11.28.797.232 I slot launch_slot_: id 0 | task 7853 | processing task, is_child = 0 11.28.809.390 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 397.084 MiB) 11.28.838.461 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 319792286662 11.28.838.609 I slot launch_slot_: id 3 | task 7854 | processing task, is_child = 0 11.30.247.532 I slot print_timing: id 0 | task 7853 | prompt eval time = 1159.68 ms / 115 tokens ( 10.08 ms per token, 99.16 tokens per second) 11.30.247.537 I slot print_timing: id 0 | task 7853 | eval time = 249.10 ms / 2 tokens ( 249.10 ms per token, 4.01 tokens per second) 11.30.247.538 I slot print_timing: id 0 | task 7853 | total time = 1408.78 ms / 117 tokens 11.30.247.538 I slot print_timing: id 0 | task 7853 | graphs reused = 6355 11.30.247.539 I slot print_timing: id 0 | task 7853 | graph reallocs = 0 / 0 (same size) / (changed size) 11.30.247.606 I slot release: id 0 | task 7853 | stop processing: n_tokens = 717, truncated = 0 11.30.311.942 I slot print_timing: id 3 | task 7854 | prompt eval time = 1442.68 ms / 673 tokens ( 2.14 ms per token, 466.49 tokens per second) 11.30.311.945 I slot print_timing: id 3 | task 7854 | eval time = 28.84 ms / 2 tokens ( 28.84 ms per token, 34.68 tokens per second) 11.30.311.945 I slot print_timing: id 3 | task 7854 | total time = 1471.52 ms / 675 tokens 11.30.311.946 I slot print_timing: id 3 | task 7854 | graphs reused = 6355 11.30.311.946 I slot print_timing: id 3 | task 7854 | graph reallocs = 0 / 0 (same size) / (changed size) 11.30.311.977 I slot release: id 3 | task 7854 | stop processing: n_tokens = 683, truncated = 0 11.33.314.851 I srv operator(): operator(): cleaning up before exit...