/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/a235d23638cc/LFM2.5-24B-A2B-UD-Q4_K_XL.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.043.071 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.043.132 I srv llama_server: initializing ... 0.00.043.137 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.043.223 I srv init_listene: The UI is disabled 0.00.043.226 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.043.266 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) 0.00.044.915 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/a235d23638cc/LFM2.5-24B-A2B-UD-Q4_K_XL.gguf' 0.01.056.713 I cmn init: llama threadpool init, n_threads = 8 0.01.121.137 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.01.124.129 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.124.148 I srv llama_server: model loaded 0.01.124.154 I srv llama_server: listening on http://127.0.0.1:8091 0.31.102.117 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.102.140 I slot launch_slot_: id 0 | task 1 | processing task, is_child = 0 0.31.102.141 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.102.152 I slot launch_slot_: id 1 | task 0 | processing task, is_child = 0 0.31.102.152 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.102.161 I slot launch_slot_: id 2 | task 3 | processing task, is_child = 0 0.31.102.161 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.102.170 I slot launch_slot_: id 3 | task 2 | processing task, is_child = 0 0.32.143.515 I slot print_timing: id 0 | task 1 | prompt eval time = 998.97 ms / 117 tokens ( 8.54 ms per token, 117.12 tokens per second) 0.32.143.521 I slot print_timing: id 0 | task 1 | eval time = 42.36 ms / 2 tokens ( 42.36 ms per token, 23.60 tokens per second) 0.32.143.521 I slot print_timing: id 0 | task 1 | total time = 1041.34 ms / 119 tokens 0.32.143.521 I slot print_timing: id 0 | task 1 | graphs reused = 1 0.32.143.522 I slot print_timing: id 0 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.143.541 I slot release: id 0 | task 1 | stop processing: n_tokens = 118, truncated = 0 0.32.143.903 I slot print_timing: id 1 | task 0 | prompt eval time = 999.40 ms / 123 tokens ( 8.13 ms per token, 123.07 tokens per second) 0.32.143.905 I slot print_timing: id 1 | task 0 | eval time = 42.32 ms / 2 tokens ( 42.32 ms per token, 23.63 tokens per second) 0.32.143.905 I slot print_timing: id 1 | task 0 | total time = 1041.72 ms / 125 tokens 0.32.143.906 I slot print_timing: id 1 | task 0 | graphs reused = 1 0.32.143.906 I slot print_timing: id 1 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.143.917 I slot release: id 1 | task 0 | stop processing: n_tokens = 124, truncated = 0 0.32.144.205 I slot print_timing: id 2 | task 3 | prompt eval time = 999.81 ms / 131 tokens ( 7.63 ms per token, 131.02 tokens per second) 0.32.144.207 I slot print_timing: id 2 | task 3 | eval time = 42.21 ms / 2 tokens ( 42.21 ms per token, 23.69 tokens per second) 0.32.144.207 I slot print_timing: id 2 | task 3 | total time = 1042.02 ms / 133 tokens 0.32.144.208 I slot print_timing: id 2 | task 3 | graphs reused = 1 0.32.144.208 I slot print_timing: id 2 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.144.230 I slot release: id 2 | task 3 | stop processing: n_tokens = 132, truncated = 0 0.32.144.598 I slot print_timing: id 3 | task 2 | prompt eval time = 1000.37 ms / 112 tokens ( 8.93 ms per token, 111.96 tokens per second) 0.32.144.601 I slot print_timing: id 3 | task 2 | eval time = 42.04 ms / 2 tokens ( 42.04 ms per token, 23.79 tokens per second) 0.32.144.601 I slot print_timing: id 3 | task 2 | total time = 1042.41 ms / 114 tokens 0.32.144.601 I slot print_timing: id 3 | task 2 | graphs reused = 1 0.32.144.602 I slot print_timing: id 3 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.144.623 I slot release: id 3 | task 2 | stop processing: n_tokens = 113, truncated = 0 0.32.150.640 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.254 0.32.150.894 I slot launch_slot_: id 0 | task 7 | processing task, is_child = 0 0.32.151.988 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.242 0.32.152.022 I slot launch_slot_: id 1 | task 8 | processing task, is_child = 0 0.32.152.054 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.220 0.32.152.084 I slot launch_slot_: id 2 | task 10 | processing task, is_child = 0 0.32.152.101 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.257 0.32.152.128 I slot launch_slot_: id 3 | task 9 | processing task, is_child = 0 0.33.363.656 I slot print_timing: id 0 | task 7 | prompt eval time = 1170.60 ms / 110 tokens ( 10.64 ms per token, 93.97 tokens per second) 0.33.363.658 I slot print_timing: id 0 | task 7 | eval time = 40.92 ms / 2 tokens ( 40.92 ms per token, 24.44 tokens per second) 0.33.363.659 I slot print_timing: id 0 | task 7 | total time = 1211.52 ms / 112 tokens 0.33.363.659 I slot print_timing: id 0 | task 7 | graphs reused = 1 0.33.363.659 I slot print_timing: id 0 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.363.677 I slot release: id 0 | task 7 | stop processing: n_tokens = 111, truncated = 0 0.33.363.961 I slot print_timing: id 1 | task 8 | prompt eval time = 1170.88 ms / 161 tokens ( 7.27 ms per token, 137.50 tokens per second) 0.33.363.969 I slot print_timing: id 1 | task 8 | eval time = 40.94 ms / 2 tokens ( 40.94 ms per token, 24.43 tokens per second) 0.33.363.969 I slot print_timing: id 1 | task 8 | total time = 1211.81 ms / 163 tokens 0.33.363.969 I slot print_timing: id 1 | task 8 | graphs reused = 1 0.33.363.970 I slot print_timing: id 1 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.363.987 I slot release: id 1 | task 8 | stop processing: n_tokens = 162, truncated = 0 0.33.364.282 I slot print_timing: id 2 | task 10 | prompt eval time = 1171.16 ms / 199 tokens ( 5.89 ms per token, 169.92 tokens per second) 0.33.364.284 I slot print_timing: id 2 | task 10 | eval time = 40.96 ms / 2 tokens ( 40.96 ms per token, 24.42 tokens per second) 0.33.364.284 I slot print_timing: id 2 | task 10 | total time = 1212.12 ms / 201 tokens 0.33.364.284 I slot print_timing: id 2 | task 10 | graphs reused = 1 0.33.364.285 I slot print_timing: id 2 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.364.303 I slot release: id 2 | task 10 | stop processing: n_tokens = 200, truncated = 0 0.33.364.604 I slot print_timing: id 3 | task 9 | prompt eval time = 1171.48 ms / 161 tokens ( 7.28 ms per token, 137.43 tokens per second) 0.33.364.607 I slot print_timing: id 3 | task 9 | eval time = 40.95 ms / 2 tokens ( 40.95 ms per token, 24.42 tokens per second) 0.33.364.607 I slot print_timing: id 3 | task 9 | total time = 1212.43 ms / 163 tokens 0.33.364.607 I slot print_timing: id 3 | task 9 | graphs reused = 1 0.33.364.608 I slot print_timing: id 3 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.364.627 I slot release: id 3 | task 9 | stop processing: n_tokens = 162, truncated = 0 0.33.368.773 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.270 0.33.369.175 I slot launch_slot_: id 0 | task 14 | processing task, is_child = 0 0.33.370.388 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.179 0.33.370.427 I slot launch_slot_: id 1 | task 15 | processing task, is_child = 0 0.33.370.465 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.145 0.33.370.494 I slot launch_slot_: id 2 | task 16 | processing task, is_child = 0 0.33.370.515 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.179 0.33.370.542 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 0.34.447.022 I slot print_timing: id 0 | task 14 | prompt eval time = 1035.37 ms / 119 tokens ( 8.70 ms per token, 114.94 tokens per second) 0.34.447.024 I slot print_timing: id 0 | task 14 | eval time = 41.11 ms / 2 tokens ( 41.11 ms per token, 24.33 tokens per second) 0.34.447.024 I slot print_timing: id 0 | task 14 | total time = 1076.47 ms / 121 tokens 0.34.447.025 I slot print_timing: id 0 | task 14 | graphs reused = 1 0.34.447.025 I slot print_timing: id 0 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.447.042 I slot release: id 0 | task 14 | stop processing: n_tokens = 120, truncated = 0 0.34.447.319 I slot print_timing: id 1 | task 15 | prompt eval time = 1035.63 ms / 151 tokens ( 6.86 ms per token, 145.80 tokens per second) 0.34.447.322 I slot print_timing: id 1 | task 15 | eval time = 41.13 ms / 2 tokens ( 41.13 ms per token, 24.32 tokens per second) 0.34.447.323 I slot print_timing: id 1 | task 15 | total time = 1076.76 ms / 153 tokens 0.34.447.323 I slot print_timing: id 1 | task 15 | graphs reused = 1 0.34.447.323 I slot print_timing: id 1 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.447.337 I slot release: id 1 | task 15 | stop processing: n_tokens = 152, truncated = 0 0.34.447.615 I slot print_timing: id 2 | task 16 | prompt eval time = 1035.91 ms / 127 tokens ( 8.16 ms per token, 122.60 tokens per second) 0.34.447.617 I slot print_timing: id 2 | task 16 | eval time = 41.13 ms / 2 tokens ( 41.13 ms per token, 24.31 tokens per second) 0.34.447.618 I slot print_timing: id 2 | task 16 | total time = 1077.04 ms / 129 tokens 0.34.447.618 I slot print_timing: id 2 | task 16 | graphs reused = 1 0.34.447.618 I slot print_timing: id 2 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.447.630 I slot release: id 2 | task 16 | stop processing: n_tokens = 128, truncated = 0 0.34.448.031 I slot print_timing: id 3 | task 17 | prompt eval time = 1036.30 ms / 116 tokens ( 8.93 ms per token, 111.94 tokens per second) 0.34.448.033 I slot print_timing: id 3 | task 17 | eval time = 41.14 ms / 2 tokens ( 41.14 ms per token, 24.31 tokens per second) 0.34.448.035 I slot print_timing: id 3 | task 17 | total time = 1077.43 ms / 118 tokens 0.34.448.035 I slot print_timing: id 3 | task 17 | graphs reused = 1 0.34.448.035 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.448.055 I slot release: id 3 | task 17 | stop processing: n_tokens = 117, truncated = 0 0.34.452.435 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.242 0.34.452.909 I slot launch_slot_: id 0 | task 21 | processing task, is_child = 0 0.34.454.033 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.191 0.34.454.066 I slot launch_slot_: id 1 | task 23 | processing task, is_child = 0 0.34.454.098 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.227 0.34.454.127 I slot launch_slot_: id 2 | task 22 | processing task, is_child = 0 0.34.454.145 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.248 0.34.454.172 I slot launch_slot_: id 3 | task 24 | processing task, is_child = 0 0.35.674.764 I slot print_timing: id 0 | task 21 | prompt eval time = 1179.55 ms / 143 tokens ( 8.25 ms per token, 121.23 tokens per second) 0.35.674.766 I slot print_timing: id 0 | task 21 | eval time = 41.03 ms / 2 tokens ( 41.03 ms per token, 24.37 tokens per second) 0.35.674.766 I slot print_timing: id 0 | task 21 | total time = 1220.58 ms / 145 tokens 0.35.674.766 I slot print_timing: id 0 | task 21 | graphs reused = 1 0.35.674.767 I slot print_timing: id 0 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.674.787 I slot release: id 0 | task 21 | stop processing: n_tokens = 144, truncated = 0 0.35.675.055 I slot print_timing: id 1 | task 23 | prompt eval time = 1179.82 ms / 135 tokens ( 8.74 ms per token, 114.42 tokens per second) 0.35.675.059 I slot print_timing: id 1 | task 23 | eval time = 41.04 ms / 2 tokens ( 41.04 ms per token, 24.37 tokens per second) 0.35.675.060 I slot print_timing: id 1 | task 23 | total time = 1220.86 ms / 137 tokens 0.35.675.060 I slot print_timing: id 1 | task 23 | graphs reused = 1 0.35.675.060 I slot print_timing: id 1 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.675.075 I slot release: id 1 | task 23 | stop processing: n_tokens = 136, truncated = 0 0.35.675.339 I slot print_timing: id 2 | task 22 | prompt eval time = 1180.10 ms / 184 tokens ( 6.41 ms per token, 155.92 tokens per second) 0.35.675.341 I slot print_timing: id 2 | task 22 | eval time = 41.04 ms / 2 tokens ( 41.04 ms per token, 24.37 tokens per second) 0.35.675.341 I slot print_timing: id 2 | task 22 | total time = 1221.14 ms / 186 tokens 0.35.675.342 I slot print_timing: id 2 | task 22 | graphs reused = 1 0.35.675.342 I slot print_timing: id 2 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.675.366 I slot release: id 2 | task 22 | stop processing: n_tokens = 185, truncated = 0 0.35.675.674 I slot print_timing: id 3 | task 24 | prompt eval time = 1180.43 ms / 120 tokens ( 9.84 ms per token, 101.66 tokens per second) 0.35.675.676 I slot print_timing: id 3 | task 24 | eval time = 41.03 ms / 2 tokens ( 41.03 ms per token, 24.37 tokens per second) 0.35.675.677 I slot print_timing: id 3 | task 24 | total time = 1221.46 ms / 122 tokens 0.35.675.677 I slot print_timing: id 3 | task 24 | graphs reused = 1 0.35.675.677 I slot print_timing: id 3 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.675.689 I slot release: id 3 | task 24 | stop processing: n_tokens = 121, truncated = 0 0.35.679.787 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.201 0.35.680.282 I slot launch_slot_: id 0 | task 28 | processing task, is_child = 0 0.35.681.410 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.213 0.35.681.568 I slot launch_slot_: id 1 | task 30 | processing task, is_child = 0 0.35.681.603 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.157 0.35.681.749 I slot launch_slot_: id 2 | task 29 | processing task, is_child = 0 0.35.681.766 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.240 0.35.681.796 I slot launch_slot_: id 3 | task 31 | processing task, is_child = 0 0.36.816.472 I slot print_timing: id 0 | task 28 | prompt eval time = 1093.52 ms / 141 tokens ( 7.76 ms per token, 128.94 tokens per second) 0.36.816.474 I slot print_timing: id 0 | task 28 | eval time = 41.15 ms / 2 tokens ( 41.15 ms per token, 24.30 tokens per second) 0.36.816.475 I slot print_timing: id 0 | task 28 | total time = 1134.67 ms / 143 tokens 0.36.816.475 I slot print_timing: id 0 | task 28 | graphs reused = 1 0.36.816.475 I slot print_timing: id 0 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.816.498 I slot release: id 0 | task 28 | stop processing: n_tokens = 142, truncated = 0 0.36.816.776 I slot print_timing: id 1 | task 30 | prompt eval time = 1093.80 ms / 131 tokens ( 8.35 ms per token, 119.77 tokens per second) 0.36.816.781 I slot print_timing: id 1 | task 30 | eval time = 41.16 ms / 2 tokens ( 41.16 ms per token, 24.30 tokens per second) 0.36.816.781 I slot print_timing: id 1 | task 30 | total time = 1134.96 ms / 133 tokens 0.36.816.781 I slot print_timing: id 1 | task 30 | graphs reused = 1 0.36.816.782 I slot print_timing: id 1 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.816.794 I slot release: id 1 | task 30 | stop processing: n_tokens = 132, truncated = 0 0.36.817.066 I slot print_timing: id 2 | task 29 | prompt eval time = 1094.07 ms / 125 tokens ( 8.75 ms per token, 114.25 tokens per second) 0.36.817.068 I slot print_timing: id 2 | task 29 | eval time = 41.17 ms / 2 tokens ( 41.17 ms per token, 24.29 tokens per second) 0.36.817.069 I slot print_timing: id 2 | task 29 | total time = 1135.24 ms / 127 tokens 0.36.817.069 I slot print_timing: id 2 | task 29 | graphs reused = 1 0.36.817.069 I slot print_timing: id 2 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.817.083 I slot release: id 2 | task 29 | stop processing: n_tokens = 126, truncated = 0 0.36.817.387 I slot print_timing: id 3 | task 31 | prompt eval time = 1094.51 ms / 179 tokens ( 6.11 ms per token, 163.54 tokens per second) 0.36.817.390 I slot print_timing: id 3 | task 31 | eval time = 41.04 ms / 2 tokens ( 41.04 ms per token, 24.36 tokens per second) 0.36.817.390 I slot print_timing: id 3 | task 31 | total time = 1135.55 ms / 181 tokens 0.36.817.391 I slot print_timing: id 3 | task 31 | graphs reused = 1 0.36.817.391 I slot print_timing: id 3 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.817.407 I slot release: id 3 | task 31 | stop processing: n_tokens = 180, truncated = 0 0.36.821.691 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.227 0.36.821.910 I slot launch_slot_: id 1 | task 35 | processing task, is_child = 0 0.36.823.076 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.204 0.36.823.113 I slot launch_slot_: id 0 | task 36 | processing task, is_child = 0 0.36.823.150 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.167 0.36.823.179 I slot launch_slot_: id 3 | task 37 | processing task, is_child = 0 0.36.823.199 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.230 0.36.823.226 I slot launch_slot_: id 2 | task 38 | processing task, is_child = 0 0.37.991.088 I slot print_timing: id 0 | task 36 | prompt eval time = 1126.82 ms / 143 tokens ( 7.88 ms per token, 126.91 tokens per second) 0.37.991.090 I slot print_timing: id 0 | task 36 | eval time = 41.03 ms / 2 tokens ( 41.03 ms per token, 24.37 tokens per second) 0.37.991.090 I slot print_timing: id 0 | task 36 | total time = 1167.86 ms / 145 tokens 0.37.991.091 I slot print_timing: id 0 | task 36 | graphs reused = 1 0.37.991.091 I slot print_timing: id 0 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.991.111 I slot release: id 0 | task 36 | stop processing: n_tokens = 144, truncated = 0 0.37.991.387 I slot print_timing: id 1 | task 35 | prompt eval time = 1127.09 ms / 122 tokens ( 9.24 ms per token, 108.24 tokens per second) 0.37.991.390 I slot print_timing: id 1 | task 35 | eval time = 41.06 ms / 2 tokens ( 41.06 ms per token, 24.36 tokens per second) 0.37.991.391 I slot print_timing: id 1 | task 35 | total time = 1168.14 ms / 124 tokens 0.37.991.391 I slot print_timing: id 1 | task 35 | graphs reused = 1 0.37.991.391 I slot print_timing: id 1 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.991.404 I slot release: id 1 | task 35 | stop processing: n_tokens = 123, truncated = 0 0.37.991.686 I slot print_timing: id 2 | task 38 | prompt eval time = 1127.35 ms / 113 tokens ( 9.98 ms per token, 100.24 tokens per second) 0.37.991.688 I slot print_timing: id 2 | task 38 | eval time = 41.08 ms / 2 tokens ( 41.08 ms per token, 24.35 tokens per second) 0.37.991.688 I slot print_timing: id 2 | task 38 | total time = 1168.42 ms / 115 tokens 0.37.991.689 I slot print_timing: id 2 | task 38 | graphs reused = 1 0.37.991.689 I slot print_timing: id 2 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.991.700 I slot release: id 2 | task 38 | stop processing: n_tokens = 114, truncated = 0 0.37.991.996 I slot print_timing: id 3 | task 37 | prompt eval time = 1127.73 ms / 145 tokens ( 7.78 ms per token, 128.58 tokens per second) 0.37.991.999 I slot print_timing: id 3 | task 37 | eval time = 41.00 ms / 2 tokens ( 41.00 ms per token, 24.39 tokens per second) 0.37.991.999 I slot print_timing: id 3 | task 37 | total time = 1168.73 ms / 147 tokens 0.37.992.000 I slot print_timing: id 3 | task 37 | graphs reused = 1 0.37.992.000 I slot print_timing: id 3 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.992.020 I slot release: id 3 | task 37 | stop processing: n_tokens = 146, truncated = 0 0.37.995.964 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.201 0.37.996.416 I slot launch_slot_: id 0 | task 43 | processing task, is_child = 0 0.37.997.468 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.244 0.37.997.500 I slot launch_slot_: id 1 | task 42 | processing task, is_child = 0 0.37.997.532 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.254 0.37.997.560 I slot launch_slot_: id 2 | task 44 | processing task, is_child = 0 0.37.997.579 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.199 0.37.997.608 I slot launch_slot_: id 3 | task 45 | processing task, is_child = 0 0.39.031.332 I slot print_timing: id 0 | task 43 | prompt eval time = 992.96 ms / 123 tokens ( 8.07 ms per token, 123.87 tokens per second) 0.39.031.335 I slot print_timing: id 0 | task 43 | eval time = 40.75 ms / 2 tokens ( 40.75 ms per token, 24.54 tokens per second) 0.39.031.335 I slot print_timing: id 0 | task 43 | total time = 1033.72 ms / 125 tokens 0.39.031.336 I slot print_timing: id 0 | task 43 | graphs reused = 1 0.39.031.336 I slot print_timing: id 0 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.031.359 I slot release: id 0 | task 43 | stop processing: n_tokens = 124, truncated = 0 0.39.031.624 I slot print_timing: id 1 | task 42 | prompt eval time = 993.22 ms / 115 tokens ( 8.64 ms per token, 115.78 tokens per second) 0.39.031.626 I slot print_timing: id 1 | task 42 | eval time = 40.77 ms / 2 tokens ( 40.77 ms per token, 24.53 tokens per second) 0.39.031.627 I slot print_timing: id 1 | task 42 | total time = 1034.00 ms / 117 tokens 0.39.031.627 I slot print_timing: id 1 | task 42 | graphs reused = 1 0.39.031.627 I slot print_timing: id 1 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.031.640 I slot release: id 1 | task 42 | stop processing: n_tokens = 116, truncated = 0 0.39.031.912 I slot print_timing: id 2 | task 44 | prompt eval time = 993.50 ms / 110 tokens ( 9.03 ms per token, 110.72 tokens per second) 0.39.031.914 I slot print_timing: id 2 | task 44 | eval time = 40.78 ms / 2 tokens ( 40.78 ms per token, 24.52 tokens per second) 0.39.031.915 I slot print_timing: id 2 | task 44 | total time = 1034.28 ms / 112 tokens 0.39.031.915 I slot print_timing: id 2 | task 44 | graphs reused = 1 0.39.031.915 I slot print_timing: id 2 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.031.926 I slot release: id 2 | task 44 | stop processing: n_tokens = 111, truncated = 0 0.39.032.326 I slot print_timing: id 3 | task 45 | prompt eval time = 993.88 ms / 146 tokens ( 6.81 ms per token, 146.90 tokens per second) 0.39.032.328 I slot print_timing: id 3 | task 45 | eval time = 40.79 ms / 2 tokens ( 40.79 ms per token, 24.51 tokens per second) 0.39.032.328 I slot print_timing: id 3 | task 45 | total time = 1034.68 ms / 148 tokens 0.39.032.328 I slot print_timing: id 3 | task 45 | graphs reused = 1 0.39.032.329 I slot print_timing: id 3 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.032.339 I slot release: id 3 | task 45 | stop processing: n_tokens = 147, truncated = 0 0.39.036.290 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.234 0.39.036.701 I slot launch_slot_: id 0 | task 50 | processing task, is_child = 0 0.39.037.637 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.250 0.39.037.670 I slot launch_slot_: id 1 | task 51 | processing task, is_child = 0 0.39.037.702 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.261 0.39.037.865 I slot launch_slot_: id 2 | task 49 | processing task, is_child = 0 0.39.037.884 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.197 0.39.038.047 I slot launch_slot_: id 3 | task 52 | processing task, is_child = 0 0.40.184.958 I slot print_timing: id 0 | task 50 | prompt eval time = 1106.00 ms / 137 tokens ( 8.07 ms per token, 123.87 tokens per second) 0.40.184.960 I slot print_timing: id 0 | task 50 | eval time = 40.90 ms / 2 tokens ( 40.90 ms per token, 24.45 tokens per second) 0.40.184.961 I slot print_timing: id 0 | task 50 | total time = 1146.90 ms / 139 tokens 0.40.184.961 I slot print_timing: id 0 | task 50 | graphs reused = 1 0.40.184.961 I slot print_timing: id 0 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.184.983 I slot release: id 0 | task 50 | stop processing: n_tokens = 138, truncated = 0 0.40.185.237 I slot print_timing: id 1 | task 51 | prompt eval time = 1106.25 ms / 103 tokens ( 10.74 ms per token, 93.11 tokens per second) 0.40.185.239 I slot print_timing: id 1 | task 51 | eval time = 40.92 ms / 2 tokens ( 40.92 ms per token, 24.44 tokens per second) 0.40.185.239 I slot print_timing: id 1 | task 51 | total time = 1147.17 ms / 105 tokens 0.40.185.239 I slot print_timing: id 1 | task 51 | graphs reused = 1 0.40.185.240 I slot print_timing: id 1 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.185.254 I slot release: id 1 | task 51 | stop processing: n_tokens = 104, truncated = 0 0.40.185.534 I slot print_timing: id 2 | task 49 | prompt eval time = 1106.54 ms / 131 tokens ( 8.45 ms per token, 118.39 tokens per second) 0.40.185.536 I slot print_timing: id 2 | task 49 | eval time = 40.92 ms / 2 tokens ( 40.92 ms per token, 24.44 tokens per second) 0.40.185.536 I slot print_timing: id 2 | task 49 | total time = 1147.46 ms / 133 tokens 0.40.185.537 I slot print_timing: id 2 | task 49 | graphs reused = 1 0.40.185.537 I slot print_timing: id 2 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.185.549 I slot release: id 2 | task 49 | stop processing: n_tokens = 132, truncated = 0 0.40.185.849 I slot print_timing: id 3 | task 52 | prompt eval time = 1106.86 ms / 114 tokens ( 9.71 ms per token, 102.99 tokens per second) 0.40.185.853 I slot print_timing: id 3 | task 52 | eval time = 40.91 ms / 2 tokens ( 40.91 ms per token, 24.45 tokens per second) 0.40.185.854 I slot print_timing: id 3 | task 52 | total time = 1147.76 ms / 116 tokens 0.40.185.855 I slot print_timing: id 3 | task 52 | graphs reused = 1 0.40.185.855 I slot print_timing: id 3 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.185.864 I slot release: id 3 | task 52 | stop processing: n_tokens = 115, truncated = 0 0.40.189.798 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.210 0.40.190.309 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.40.191.020 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.279 0.40.191.050 I slot launch_slot_: id 1 | task 57 | processing task, is_child = 0 0.40.191.082 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.220 0.40.191.110 I slot launch_slot_: id 2 | task 58 | processing task, is_child = 0 0.40.191.128 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.252 0.40.191.155 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 0.41.496.934 I slot print_timing: id 0 | task 56 | prompt eval time = 1264.93 ms / 186 tokens ( 6.80 ms per token, 147.04 tokens per second) 0.41.496.938 I slot print_timing: id 0 | task 56 | eval time = 40.84 ms / 2 tokens ( 40.84 ms per token, 24.49 tokens per second) 0.41.496.938 I slot print_timing: id 0 | task 56 | total time = 1305.77 ms / 188 tokens 0.41.496.939 I slot print_timing: id 0 | task 56 | graphs reused = 1 0.41.496.939 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.496.962 I slot release: id 0 | task 56 | stop processing: n_tokens = 187, truncated = 0 0.41.497.236 I slot print_timing: id 1 | task 57 | prompt eval time = 1265.20 ms / 132 tokens ( 9.58 ms per token, 104.33 tokens per second) 0.41.497.238 I slot print_timing: id 1 | task 57 | eval time = 40.86 ms / 2 tokens ( 40.86 ms per token, 24.47 tokens per second) 0.41.497.239 I slot print_timing: id 1 | task 57 | total time = 1306.06 ms / 134 tokens 0.41.497.239 I slot print_timing: id 1 | task 57 | graphs reused = 1 0.41.497.239 I slot print_timing: id 1 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.497.254 I slot release: id 1 | task 57 | stop processing: n_tokens = 133, truncated = 0 0.41.497.537 I slot print_timing: id 2 | task 58 | prompt eval time = 1265.49 ms / 168 tokens ( 7.53 ms per token, 132.76 tokens per second) 0.41.497.539 I slot print_timing: id 2 | task 58 | eval time = 40.87 ms / 2 tokens ( 40.87 ms per token, 24.47 tokens per second) 0.41.497.540 I slot print_timing: id 2 | task 58 | total time = 1306.36 ms / 170 tokens 0.41.497.540 I slot print_timing: id 2 | task 58 | graphs reused = 1 0.41.497.540 I slot print_timing: id 2 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.497.557 I slot release: id 2 | task 58 | stop processing: n_tokens = 169, truncated = 0 0.41.497.861 I slot print_timing: id 3 | task 59 | prompt eval time = 1265.80 ms / 178 tokens ( 7.11 ms per token, 140.62 tokens per second) 0.41.497.863 I slot print_timing: id 3 | task 59 | eval time = 40.87 ms / 2 tokens ( 40.87 ms per token, 24.47 tokens per second) 0.41.497.864 I slot print_timing: id 3 | task 59 | total time = 1306.67 ms / 180 tokens 0.41.497.864 I slot print_timing: id 3 | task 59 | graphs reused = 1 0.41.497.864 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.497.879 I slot release: id 3 | task 59 | stop processing: n_tokens = 179, truncated = 0 0.41.502.863 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.155 0.41.503.376 I slot launch_slot_: id 0 | task 66 | processing task, is_child = 0 0.41.504.620 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.218 0.41.504.770 I slot launch_slot_: id 1 | task 63 | processing task, is_child = 0 0.41.504.806 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.172 0.41.504.836 I slot launch_slot_: id 2 | task 64 | processing task, is_child = 0 0.41.504.855 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.162 0.41.504.886 I slot launch_slot_: id 3 | task 65 | processing task, is_child = 0 0.42.721.748 I slot print_timing: id 0 | task 66 | prompt eval time = 1175.92 ms / 168 tokens ( 7.00 ms per token, 142.87 tokens per second) 0.42.721.750 I slot print_timing: id 0 | task 66 | eval time = 40.94 ms / 2 tokens ( 40.94 ms per token, 24.43 tokens per second) 0.42.721.751 I slot print_timing: id 0 | task 66 | total time = 1216.86 ms / 170 tokens 0.42.721.752 I slot print_timing: id 0 | task 66 | graphs reused = 1 0.42.721.752 I slot print_timing: id 0 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.721.775 I slot release: id 0 | task 66 | stop processing: n_tokens = 169, truncated = 0 0.42.722.057 I slot print_timing: id 1 | task 63 | prompt eval time = 1176.19 ms / 141 tokens ( 8.34 ms per token, 119.88 tokens per second) 0.42.722.061 I slot print_timing: id 1 | task 63 | eval time = 40.96 ms / 2 tokens ( 40.96 ms per token, 24.41 tokens per second) 0.42.722.062 I slot print_timing: id 1 | task 63 | total time = 1217.15 ms / 143 tokens 0.42.722.062 I slot print_timing: id 1 | task 63 | graphs reused = 1 0.42.722.062 I slot print_timing: id 1 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.722.077 I slot release: id 1 | task 63 | stop processing: n_tokens = 142, truncated = 0 0.42.722.354 I slot print_timing: id 2 | task 64 | prompt eval time = 1176.45 ms / 150 tokens ( 7.84 ms per token, 127.50 tokens per second) 0.42.722.356 I slot print_timing: id 2 | task 64 | eval time = 40.98 ms / 2 tokens ( 40.98 ms per token, 24.40 tokens per second) 0.42.722.356 I slot print_timing: id 2 | task 64 | total time = 1217.44 ms / 152 tokens 0.42.722.356 I slot print_timing: id 2 | task 64 | graphs reused = 1 0.42.722.357 I slot print_timing: id 2 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.722.368 I slot release: id 2 | task 64 | stop processing: n_tokens = 151, truncated = 0 0.42.722.687 I slot print_timing: id 3 | task 65 | prompt eval time = 1176.74 ms / 124 tokens ( 9.49 ms per token, 105.38 tokens per second) 0.42.722.690 I slot print_timing: id 3 | task 65 | eval time = 41.02 ms / 2 tokens ( 41.02 ms per token, 24.38 tokens per second) 0.42.722.690 I slot print_timing: id 3 | task 65 | total time = 1217.76 ms / 126 tokens 0.42.722.690 I slot print_timing: id 3 | task 65 | graphs reused = 1 0.42.722.691 I slot print_timing: id 3 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.722.701 I slot release: id 3 | task 65 | stop processing: n_tokens = 125, truncated = 0 0.42.727.110 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.240 0.42.727.514 I slot launch_slot_: id 3 | task 70 | processing task, is_child = 0 0.42.728.699 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.172 0.42.728.735 I slot launch_slot_: id 0 | task 71 | processing task, is_child = 0 0.42.728.769 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.211 0.42.728.801 I slot launch_slot_: id 1 | task 72 | processing task, is_child = 0 0.42.728.818 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.192 0.42.728.850 I slot launch_slot_: id 2 | task 73 | processing task, is_child = 0 0.43.875.906 I slot print_timing: id 0 | task 71 | prompt eval time = 1105.62 ms / 131 tokens ( 8.44 ms per token, 118.49 tokens per second) 0.43.875.908 I slot print_timing: id 0 | task 71 | eval time = 41.43 ms / 2 tokens ( 41.43 ms per token, 24.14 tokens per second) 0.43.875.908 I slot print_timing: id 0 | task 71 | total time = 1147.05 ms / 133 tokens 0.43.875.909 I slot print_timing: id 0 | task 71 | graphs reused = 1 0.43.875.909 I slot print_timing: id 0 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.875.932 I slot release: id 0 | task 71 | stop processing: n_tokens = 132, truncated = 0 0.43.876.206 I slot print_timing: id 1 | task 72 | prompt eval time = 1105.88 ms / 111 tokens ( 9.96 ms per token, 100.37 tokens per second) 0.43.876.209 I slot print_timing: id 1 | task 72 | eval time = 41.45 ms / 2 tokens ( 41.45 ms per token, 24.12 tokens per second) 0.43.876.210 I slot print_timing: id 1 | task 72 | total time = 1147.33 ms / 113 tokens 0.43.876.210 I slot print_timing: id 1 | task 72 | graphs reused = 1 0.43.876.210 I slot print_timing: id 1 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.876.221 I slot release: id 1 | task 72 | stop processing: n_tokens = 112, truncated = 0 0.43.876.504 I slot print_timing: id 2 | task 73 | prompt eval time = 1106.15 ms / 160 tokens ( 6.91 ms per token, 144.65 tokens per second) 0.43.876.506 I slot print_timing: id 2 | task 73 | eval time = 41.46 ms / 2 tokens ( 41.46 ms per token, 24.12 tokens per second) 0.43.876.507 I slot print_timing: id 2 | task 73 | total time = 1147.62 ms / 162 tokens 0.43.876.507 I slot print_timing: id 2 | task 73 | graphs reused = 1 0.43.876.507 I slot print_timing: id 2 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.876.528 I slot release: id 2 | task 73 | stop processing: n_tokens = 161, truncated = 0 0.43.876.856 I slot print_timing: id 3 | task 70 | prompt eval time = 1106.60 ms / 164 tokens ( 6.75 ms per token, 148.20 tokens per second) 0.43.876.860 I slot print_timing: id 3 | task 70 | eval time = 41.35 ms / 2 tokens ( 41.35 ms per token, 24.18 tokens per second) 0.43.876.860 I slot print_timing: id 3 | task 70 | total time = 1147.95 ms / 166 tokens 0.43.876.861 I slot print_timing: id 3 | task 70 | graphs reused = 1 0.43.876.861 I slot print_timing: id 3 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.876.883 I slot release: id 3 | task 70 | stop processing: n_tokens = 165, truncated = 0 0.43.881.284 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.186 0.43.881.794 I slot launch_slot_: id 2 | task 77 | processing task, is_child = 0 0.43.882.792 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.220 0.43.882.828 I slot launch_slot_: id 0 | task 78 | processing task, is_child = 0 0.43.882.862 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.259 0.43.882.892 I slot launch_slot_: id 1 | task 79 | processing task, is_child = 0 0.43.882.911 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.182 0.43.882.942 I slot launch_slot_: id 3 | task 80 | processing task, is_child = 0 0.45.061.180 I slot print_timing: id 0 | task 78 | prompt eval time = 1137.25 ms / 112 tokens ( 10.15 ms per token, 98.48 tokens per second) 0.45.061.182 I slot print_timing: id 0 | task 78 | eval time = 40.98 ms / 2 tokens ( 40.98 ms per token, 24.40 tokens per second) 0.45.061.182 I slot print_timing: id 0 | task 78 | total time = 1178.23 ms / 114 tokens 0.45.061.183 I slot print_timing: id 0 | task 78 | graphs reused = 1 0.45.061.183 I slot print_timing: id 0 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.061.201 I slot release: id 0 | task 78 | stop processing: n_tokens = 113, truncated = 0 0.45.061.482 I slot print_timing: id 1 | task 79 | prompt eval time = 1137.53 ms / 166 tokens ( 6.85 ms per token, 145.93 tokens per second) 0.45.061.484 I slot print_timing: id 1 | task 79 | eval time = 40.99 ms / 2 tokens ( 40.99 ms per token, 24.39 tokens per second) 0.45.061.484 I slot print_timing: id 1 | task 79 | total time = 1178.52 ms / 168 tokens 0.45.061.485 I slot print_timing: id 1 | task 79 | graphs reused = 1 0.45.061.485 I slot print_timing: id 1 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.061.499 I slot release: id 1 | task 79 | stop processing: n_tokens = 167, truncated = 0 0.45.061.794 I slot print_timing: id 2 | task 77 | prompt eval time = 1137.80 ms / 111 tokens ( 10.25 ms per token, 97.56 tokens per second) 0.45.061.796 I slot print_timing: id 2 | task 77 | eval time = 41.02 ms / 2 tokens ( 41.02 ms per token, 24.38 tokens per second) 0.45.061.797 I slot print_timing: id 2 | task 77 | total time = 1178.82 ms / 113 tokens 0.45.061.797 I slot print_timing: id 2 | task 77 | graphs reused = 1 0.45.061.797 I slot print_timing: id 2 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.061.808 I slot release: id 2 | task 77 | stop processing: n_tokens = 112, truncated = 0 0.45.062.108 I slot print_timing: id 3 | task 80 | prompt eval time = 1138.10 ms / 166 tokens ( 6.86 ms per token, 145.86 tokens per second) 0.45.062.111 I slot print_timing: id 3 | task 80 | eval time = 41.03 ms / 2 tokens ( 41.03 ms per token, 24.37 tokens per second) 0.45.062.111 I slot print_timing: id 3 | task 80 | total time = 1179.12 ms / 168 tokens 0.45.062.112 I slot print_timing: id 3 | task 80 | graphs reused = 1 0.45.062.112 I slot print_timing: id 3 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.062.127 I slot release: id 3 | task 80 | stop processing: n_tokens = 167, truncated = 0 0.45.066.455 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.257 0.45.066.670 I slot launch_slot_: id 0 | task 84 | processing task, is_child = 0 0.45.067.812 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.174 0.45.067.847 I slot launch_slot_: id 1 | task 85 | processing task, is_child = 0 0.45.067.881 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.259 0.45.067.909 I slot launch_slot_: id 2 | task 86 | processing task, is_child = 0 0.45.067.928 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.174 0.45.068.075 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 0.46.100.602 I slot print_timing: id 0 | task 84 | prompt eval time = 991.56 ms / 122 tokens ( 8.13 ms per token, 123.04 tokens per second) 0.46.100.604 I slot print_timing: id 0 | task 84 | eval time = 40.96 ms / 2 tokens ( 40.96 ms per token, 24.41 tokens per second) 0.46.100.604 I slot print_timing: id 0 | task 84 | total time = 1032.52 ms / 124 tokens 0.46.100.605 I slot print_timing: id 0 | task 84 | graphs reused = 1 0.46.100.605 I slot print_timing: id 0 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.100.626 I slot release: id 0 | task 84 | stop processing: n_tokens = 123, truncated = 0 0.46.100.908 I slot print_timing: id 1 | task 85 | prompt eval time = 991.83 ms / 133 tokens ( 7.46 ms per token, 134.10 tokens per second) 0.46.100.910 I slot print_timing: id 1 | task 85 | eval time = 40.98 ms / 2 tokens ( 40.98 ms per token, 24.40 tokens per second) 0.46.100.910 I slot print_timing: id 1 | task 85 | total time = 1032.82 ms / 135 tokens 0.46.100.910 I slot print_timing: id 1 | task 85 | graphs reused = 1 0.46.100.911 I slot print_timing: id 1 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.100.929 I slot release: id 1 | task 85 | stop processing: n_tokens = 134, truncated = 0 0.46.101.210 I slot print_timing: id 2 | task 86 | prompt eval time = 992.09 ms / 145 tokens ( 6.84 ms per token, 146.16 tokens per second) 0.46.101.212 I slot print_timing: id 2 | task 86 | eval time = 41.02 ms / 2 tokens ( 41.02 ms per token, 24.38 tokens per second) 0.46.101.212 I slot print_timing: id 2 | task 86 | total time = 1033.11 ms / 147 tokens 0.46.101.213 I slot print_timing: id 2 | task 86 | graphs reused = 1 0.46.101.213 I slot print_timing: id 2 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.101.232 I slot release: id 2 | task 86 | stop processing: n_tokens = 146, truncated = 0 0.46.101.536 I slot print_timing: id 3 | task 87 | prompt eval time = 992.37 ms / 127 tokens ( 7.81 ms per token, 127.98 tokens per second) 0.46.101.538 I slot print_timing: id 3 | task 87 | eval time = 41.05 ms / 2 tokens ( 41.05 ms per token, 24.36 tokens per second) 0.46.101.538 I slot print_timing: id 3 | task 87 | total time = 1033.42 ms / 129 tokens 0.46.101.538 I slot print_timing: id 3 | task 87 | graphs reused = 1 0.46.101.539 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.101.552 I slot release: id 3 | task 87 | stop processing: n_tokens = 128, truncated = 0 0.46.105.007 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.236 0.46.105.481 I slot launch_slot_: id 0 | task 91 | processing task, is_child = 0 0.46.106.494 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.234 0.46.106.525 I slot launch_slot_: id 3 | task 92 | processing task, is_child = 0 0.46.106.559 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.216 0.46.106.587 I slot launch_slot_: id 1 | task 93 | processing task, is_child = 0 0.46.106.605 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.199 0.46.106.744 I slot launch_slot_: id 2 | task 94 | processing task, is_child = 0 0.47.162.510 I slot print_timing: id 0 | task 91 | prompt eval time = 1014.54 ms / 140 tokens ( 7.25 ms per token, 137.99 tokens per second) 0.47.162.512 I slot print_timing: id 0 | task 91 | eval time = 41.21 ms / 2 tokens ( 41.21 ms per token, 24.26 tokens per second) 0.47.162.513 I slot print_timing: id 0 | task 91 | total time = 1055.76 ms / 142 tokens 0.47.162.513 I slot print_timing: id 0 | task 91 | graphs reused = 1 0.47.162.513 I slot print_timing: id 0 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.162.534 I slot release: id 0 | task 91 | stop processing: n_tokens = 141, truncated = 0 0.47.162.805 I slot print_timing: id 1 | task 93 | prompt eval time = 1014.81 ms / 126 tokens ( 8.05 ms per token, 124.16 tokens per second) 0.47.162.806 I slot print_timing: id 1 | task 93 | eval time = 41.24 ms / 2 tokens ( 41.24 ms per token, 24.25 tokens per second) 0.47.162.807 I slot print_timing: id 1 | task 93 | total time = 1056.05 ms / 128 tokens 0.47.162.807 I slot print_timing: id 1 | task 93 | graphs reused = 1 0.47.162.807 I slot print_timing: id 1 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.162.823 I slot release: id 1 | task 93 | stop processing: n_tokens = 127, truncated = 0 0.47.163.192 I slot print_timing: id 2 | task 94 | prompt eval time = 1015.17 ms / 133 tokens ( 7.63 ms per token, 131.01 tokens per second) 0.47.163.194 I slot print_timing: id 2 | task 94 | eval time = 41.26 ms / 2 tokens ( 41.26 ms per token, 24.24 tokens per second) 0.47.163.194 I slot print_timing: id 2 | task 94 | total time = 1056.42 ms / 135 tokens 0.47.163.195 I slot print_timing: id 2 | task 94 | graphs reused = 1 0.47.163.195 I slot print_timing: id 2 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.163.209 I slot release: id 2 | task 94 | stop processing: n_tokens = 134, truncated = 0 0.47.163.507 I slot print_timing: id 3 | task 92 | prompt eval time = 1015.48 ms / 146 tokens ( 6.96 ms per token, 143.77 tokens per second) 0.47.163.510 I slot print_timing: id 3 | task 92 | eval time = 41.25 ms / 2 tokens ( 41.25 ms per token, 24.24 tokens per second) 0.47.163.510 I slot print_timing: id 3 | task 92 | total time = 1056.73 ms / 148 tokens 0.47.163.510 I slot print_timing: id 3 | task 92 | graphs reused = 1 0.47.163.510 I slot print_timing: id 3 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.163.531 I slot release: id 3 | task 92 | stop processing: n_tokens = 147, truncated = 0 0.47.167.933 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.206 0.47.168.355 I slot launch_slot_: id 0 | task 98 | processing task, is_child = 0 0.47.169.293 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.224 0.47.169.327 I slot launch_slot_: id 2 | task 101 | processing task, is_child = 0 0.47.169.361 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.204 0.47.169.394 I slot launch_slot_: id 3 | task 100 | processing task, is_child = 0 0.47.169.413 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.170 (> 0.100 thold), f_keep = 0.228 0.47.169.444 I slot launch_slot_: id 1 | task 99 | processing task, is_child = 0 0.48.337.731 I slot print_timing: id 0 | task 98 | prompt eval time = 1127.35 ms / 123 tokens ( 9.17 ms per token, 109.11 tokens per second) 0.48.337.734 I slot print_timing: id 0 | task 98 | eval time = 40.93 ms / 2 tokens ( 40.93 ms per token, 24.43 tokens per second) 0.48.337.734 I slot print_timing: id 0 | task 98 | total time = 1168.28 ms / 125 tokens 0.48.337.735 I slot print_timing: id 0 | task 98 | graphs reused = 1 0.48.337.735 I slot print_timing: id 0 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.337.752 I slot release: id 0 | task 98 | stop processing: n_tokens = 124, truncated = 0 0.48.338.038 I slot print_timing: id 1 | task 99 | prompt eval time = 1127.62 ms / 171 tokens ( 6.59 ms per token, 151.65 tokens per second) 0.48.338.042 I slot print_timing: id 1 | task 99 | eval time = 40.95 ms / 2 tokens ( 40.95 ms per token, 24.42 tokens per second) 0.48.338.042 I slot print_timing: id 1 | task 99 | total time = 1168.58 ms / 173 tokens 0.48.338.042 I slot print_timing: id 1 | task 99 | graphs reused = 1 0.48.338.043 I slot print_timing: id 1 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.338.057 I slot release: id 1 | task 99 | stop processing: n_tokens = 172, truncated = 0 0.48.338.330 I slot print_timing: id 2 | task 101 | prompt eval time = 1127.90 ms / 110 tokens ( 10.25 ms per token, 97.53 tokens per second) 0.48.338.333 I slot print_timing: id 2 | task 101 | eval time = 40.96 ms / 2 tokens ( 40.96 ms per token, 24.41 tokens per second) 0.48.338.333 I slot print_timing: id 2 | task 101 | total time = 1168.86 ms / 112 tokens 0.48.338.333 I slot print_timing: id 2 | task 101 | graphs reused = 1 0.48.338.334 I slot print_timing: id 2 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.338.344 I slot release: id 2 | task 101 | stop processing: n_tokens = 111, truncated = 0 0.48.338.630 I slot print_timing: id 3 | task 100 | prompt eval time = 1128.18 ms / 120 tokens ( 9.40 ms per token, 106.37 tokens per second) 0.48.338.633 I slot print_timing: id 3 | task 100 | eval time = 40.97 ms / 2 tokens ( 40.97 ms per token, 24.41 tokens per second) 0.48.338.633 I slot print_timing: id 3 | task 100 | total time = 1169.15 ms / 122 tokens 0.48.338.633 I slot print_timing: id 3 | task 100 | graphs reused = 1 0.48.338.634 I slot print_timing: id 3 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.338.645 I slot release: id 3 | task 100 | stop processing: n_tokens = 121, truncated = 0 0.48.343.020 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.270 0.48.343.302 I slot launch_slot_: id 2 | task 106 | processing task, is_child = 0 0.48.344.429 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.256 (> 0.100 thold), f_keep = 0.248 0.48.344.462 I slot launch_slot_: id 3 | task 105 | processing task, is_child = 0 0.48.344.496 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.125 (> 0.100 thold), f_keep = 0.234 0.48.344.526 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.48.344.545 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.169 0.48.344.575 I slot launch_slot_: id 1 | task 108 | processing task, is_child = 0 0.49.777.037 I slot print_timing: id 0 | task 107 | prompt eval time = 1391.43 ms / 232 tokens ( 6.00 ms per token, 166.73 tokens per second) 0.49.777.040 I slot print_timing: id 0 | task 107 | eval time = 41.02 ms / 2 tokens ( 41.02 ms per token, 24.38 tokens per second) 0.49.777.040 I slot print_timing: id 0 | task 107 | total time = 1432.45 ms / 234 tokens 0.49.777.041 I slot print_timing: id 0 | task 107 | graphs reused = 1 0.49.777.041 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.777.065 I slot release: id 0 | task 107 | stop processing: n_tokens = 233, truncated = 0 0.49.777.342 I slot print_timing: id 1 | task 108 | prompt eval time = 1391.71 ms / 176 tokens ( 7.91 ms per token, 126.46 tokens per second) 0.49.777.343 I slot print_timing: id 1 | task 108 | eval time = 41.04 ms / 2 tokens ( 41.04 ms per token, 24.37 tokens per second) 0.49.777.344 I slot print_timing: id 1 | task 108 | total time = 1432.75 ms / 178 tokens 0.49.777.344 I slot print_timing: id 1 | task 108 | graphs reused = 1 0.49.777.344 I slot print_timing: id 1 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.777.365 I slot release: id 1 | task 108 | stop processing: n_tokens = 177, truncated = 0 0.49.777.644 I slot print_timing: id 2 | task 106 | prompt eval time = 1391.98 ms / 138 tokens ( 10.09 ms per token, 99.14 tokens per second) 0.49.777.646 I slot print_timing: id 2 | task 106 | eval time = 41.06 ms / 2 tokens ( 41.06 ms per token, 24.36 tokens per second) 0.49.777.647 I slot print_timing: id 2 | task 106 | total time = 1433.04 ms / 140 tokens 0.49.777.647 I slot print_timing: id 2 | task 106 | graphs reused = 1 0.49.777.647 I slot print_timing: id 2 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.777.662 I slot release: id 2 | task 106 | stop processing: n_tokens = 139, truncated = 0 0.49.777.937 I slot print_timing: id 3 | task 105 | prompt eval time = 1392.33 ms / 117 tokens ( 11.90 ms per token, 84.03 tokens per second) 0.49.777.941 I slot print_timing: id 3 | task 105 | eval time = 40.99 ms / 2 tokens ( 40.99 ms per token, 24.40 tokens per second) 0.49.777.941 I slot print_timing: id 3 | task 105 | total time = 1433.32 ms / 119 tokens 0.49.777.941 I slot print_timing: id 3 | task 105 | graphs reused = 1 0.49.777.942 I slot print_timing: id 3 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.777.956 I slot release: id 3 | task 105 | stop processing: n_tokens = 118, truncated = 0 0.49.781.894 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.263 0.49.782.308 I slot launch_slot_: id 3 | task 112 | processing task, is_child = 0 0.49.783.656 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.124 0.49.783.690 I slot launch_slot_: id 0 | task 113 | processing task, is_child = 0 0.49.783.725 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.216 0.49.783.863 I slot launch_slot_: id 2 | task 114 | processing task, is_child = 0 0.49.783.882 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.164 0.49.783.912 I slot launch_slot_: id 1 | task 115 | processing task, is_child = 0 0.51.293.352 I slot print_timing: id 0 | task 113 | prompt eval time = 1468.11 ms / 158 tokens ( 9.29 ms per token, 107.62 tokens per second) 0.51.293.354 I slot print_timing: id 0 | task 113 | eval time = 41.32 ms / 2 tokens ( 41.32 ms per token, 24.20 tokens per second) 0.51.293.354 I slot print_timing: id 0 | task 113 | total time = 1509.43 ms / 160 tokens 0.51.293.355 I slot print_timing: id 0 | task 113 | graphs reused = 1 0.51.293.355 I slot print_timing: id 0 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.293.376 I slot release: id 0 | task 113 | stop processing: n_tokens = 159, truncated = 0 0.51.293.654 I slot print_timing: id 1 | task 115 | prompt eval time = 1468.37 ms / 227 tokens ( 6.47 ms per token, 154.59 tokens per second) 0.51.293.658 I slot print_timing: id 1 | task 115 | eval time = 41.35 ms / 2 tokens ( 41.35 ms per token, 24.19 tokens per second) 0.51.293.658 I slot print_timing: id 1 | task 115 | total time = 1509.72 ms / 229 tokens 0.51.293.659 I slot print_timing: id 1 | task 115 | graphs reused = 1 0.51.293.659 I slot print_timing: id 1 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.293.679 I slot release: id 1 | task 115 | stop processing: n_tokens = 228, truncated = 0 0.51.293.975 I slot print_timing: id 2 | task 114 | prompt eval time = 1468.66 ms / 143 tokens ( 10.27 ms per token, 97.37 tokens per second) 0.51.293.977 I slot print_timing: id 2 | task 114 | eval time = 41.37 ms / 2 tokens ( 41.37 ms per token, 24.17 tokens per second) 0.51.293.977 I slot print_timing: id 2 | task 114 | total time = 1510.03 ms / 145 tokens 0.51.293.977 I slot print_timing: id 2 | task 114 | graphs reused = 1 0.51.293.978 I slot print_timing: id 2 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.294.004 I slot release: id 2 | task 114 | stop processing: n_tokens = 144, truncated = 0 0.51.294.402 I slot print_timing: id 3 | task 112 | prompt eval time = 1469.07 ms / 156 tokens ( 9.42 ms per token, 106.19 tokens per second) 0.51.294.406 I slot print_timing: id 3 | task 112 | eval time = 41.38 ms / 2 tokens ( 41.38 ms per token, 24.17 tokens per second) 0.51.294.406 I slot print_timing: id 3 | task 112 | total time = 1510.45 ms / 158 tokens 0.51.294.406 I slot print_timing: id 3 | task 112 | graphs reused = 1 0.51.294.407 I slot print_timing: id 3 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.294.418 I slot release: id 3 | task 112 | stop processing: n_tokens = 157, truncated = 0 0.51.298.651 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.299 (> 0.100 thold), f_keep = 0.222 0.51.299.079 I slot launch_slot_: id 2 | task 119 | processing task, is_child = 0 0.51.300.272 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.256 (> 0.100 thold), f_keep = 0.191 0.51.300.304 I slot launch_slot_: id 3 | task 121 | processing task, is_child = 0 0.51.300.341 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.182 0.51.300.371 I slot launch_slot_: id 0 | task 120 | processing task, is_child = 0 0.51.300.392 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.127 0.51.300.539 I slot launch_slot_: id 1 | task 122 | processing task, is_child = 0 0.52.523.326 I slot print_timing: id 0 | task 120 | prompt eval time = 1181.62 ms / 143 tokens ( 8.26 ms per token, 121.02 tokens per second) 0.52.523.328 I slot print_timing: id 0 | task 120 | eval time = 41.16 ms / 2 tokens ( 41.16 ms per token, 24.30 tokens per second) 0.52.523.329 I slot print_timing: id 0 | task 120 | total time = 1222.78 ms / 145 tokens 0.52.523.329 I slot print_timing: id 0 | task 120 | graphs reused = 1 0.52.523.330 I slot print_timing: id 0 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.523.358 I slot release: id 0 | task 120 | stop processing: n_tokens = 144, truncated = 0 0.52.523.628 I slot print_timing: id 1 | task 122 | prompt eval time = 1181.88 ms / 189 tokens ( 6.25 ms per token, 159.91 tokens per second) 0.52.523.630 I slot print_timing: id 1 | task 122 | eval time = 41.19 ms / 2 tokens ( 41.19 ms per token, 24.28 tokens per second) 0.52.523.631 I slot print_timing: id 1 | task 122 | total time = 1223.07 ms / 191 tokens 0.52.523.631 I slot print_timing: id 1 | task 122 | graphs reused = 1 0.52.523.631 I slot print_timing: id 1 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.523.648 I slot release: id 1 | task 122 | stop processing: n_tokens = 190, truncated = 0 0.52.523.923 I slot print_timing: id 2 | task 119 | prompt eval time = 1182.16 ms / 107 tokens ( 11.05 ms per token, 90.51 tokens per second) 0.52.523.925 I slot print_timing: id 2 | task 119 | eval time = 41.20 ms / 2 tokens ( 41.20 ms per token, 24.27 tokens per second) 0.52.523.926 I slot print_timing: id 2 | task 119 | total time = 1223.36 ms / 109 tokens 0.52.523.926 I slot print_timing: id 2 | task 119 | graphs reused = 1 0.52.523.926 I slot print_timing: id 2 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.523.937 I slot release: id 2 | task 119 | stop processing: n_tokens = 108, truncated = 0 0.52.524.238 I slot print_timing: id 3 | task 121 | prompt eval time = 1182.51 ms / 117 tokens ( 10.11 ms per token, 98.94 tokens per second) 0.52.524.240 I slot print_timing: id 3 | task 121 | eval time = 41.15 ms / 2 tokens ( 41.15 ms per token, 24.30 tokens per second) 0.52.524.241 I slot print_timing: id 3 | task 121 | total time = 1223.66 ms / 119 tokens 0.52.524.241 I slot print_timing: id 3 | task 121 | graphs reused = 1 0.52.524.241 I slot print_timing: id 3 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.524.253 I slot release: id 3 | task 121 | stop processing: n_tokens = 118, truncated = 0 0.52.528.311 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.201 0.52.528.760 I slot launch_slot_: id 0 | task 126 | processing task, is_child = 0 0.52.529.585 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.153 0.52.529.620 I slot launch_slot_: id 1 | task 127 | processing task, is_child = 0 0.52.529.653 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.244 (> 0.100 thold), f_keep = 0.278 0.52.529.682 I slot launch_slot_: id 2 | task 128 | processing task, is_child = 0 0.52.529.700 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.254 0.52.529.729 I slot launch_slot_: id 3 | task 129 | processing task, is_child = 0 0.53.825.033 I slot print_timing: id 0 | task 126 | prompt eval time = 1254.20 ms / 138 tokens ( 9.09 ms per token, 110.03 tokens per second) 0.53.825.035 I slot print_timing: id 0 | task 126 | eval time = 41.10 ms / 2 tokens ( 41.10 ms per token, 24.33 tokens per second) 0.53.825.036 I slot print_timing: id 0 | task 126 | total time = 1295.29 ms / 140 tokens 0.53.825.037 I slot print_timing: id 0 | task 126 | graphs reused = 1 0.53.825.037 I slot print_timing: id 0 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.825.060 I slot release: id 0 | task 126 | stop processing: n_tokens = 139, truncated = 0 0.53.825.342 I slot print_timing: id 1 | task 127 | prompt eval time = 1254.48 ms / 173 tokens ( 7.25 ms per token, 137.91 tokens per second) 0.53.825.344 I slot print_timing: id 1 | task 127 | eval time = 41.11 ms / 2 tokens ( 41.11 ms per token, 24.32 tokens per second) 0.53.825.344 I slot print_timing: id 1 | task 127 | total time = 1295.59 ms / 175 tokens 0.53.825.345 I slot print_timing: id 1 | task 127 | graphs reused = 1 0.53.825.345 I slot print_timing: id 1 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.825.359 I slot release: id 1 | task 127 | stop processing: n_tokens = 174, truncated = 0 0.53.825.639 I slot print_timing: id 2 | task 128 | prompt eval time = 1254.76 ms / 123 tokens ( 10.20 ms per token, 98.03 tokens per second) 0.53.825.642 I slot print_timing: id 2 | task 128 | eval time = 41.11 ms / 2 tokens ( 41.11 ms per token, 24.32 tokens per second) 0.53.825.642 I slot print_timing: id 2 | task 128 | total time = 1295.88 ms / 125 tokens 0.53.825.642 I slot print_timing: id 2 | task 128 | graphs reused = 1 0.53.825.642 I slot print_timing: id 2 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.825.655 I slot release: id 2 | task 128 | stop processing: n_tokens = 124, truncated = 0 0.53.825.939 I slot print_timing: id 3 | task 129 | prompt eval time = 1255.09 ms / 110 tokens ( 11.41 ms per token, 87.64 tokens per second) 0.53.825.941 I slot print_timing: id 3 | task 129 | eval time = 41.08 ms / 2 tokens ( 41.08 ms per token, 24.34 tokens per second) 0.53.825.942 I slot print_timing: id 3 | task 129 | total time = 1296.17 ms / 112 tokens 0.53.825.942 I slot print_timing: id 3 | task 129 | graphs reused = 1 0.53.825.942 I slot print_timing: id 3 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.825.954 I slot release: id 3 | task 129 | stop processing: n_tokens = 111, truncated = 0 0.53.829.876 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.242 0.53.830.220 I slot launch_slot_: id 2 | task 135 | processing task, is_child = 0 0.53.831.130 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.209 0.53.831.173 I slot launch_slot_: id 0 | task 133 | processing task, is_child = 0 0.53.831.207 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.167 0.53.831.243 I slot launch_slot_: id 1 | task 134 | processing task, is_child = 0 0.53.831.260 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.261 0.53.831.291 I slot launch_slot_: id 3 | task 136 | processing task, is_child = 0 0.55.021.869 I slot print_timing: id 0 | task 133 | prompt eval time = 1149.15 ms / 134 tokens ( 8.58 ms per token, 116.61 tokens per second) 0.55.021.871 I slot print_timing: id 0 | task 133 | eval time = 41.42 ms / 2 tokens ( 41.42 ms per token, 24.14 tokens per second) 0.55.021.871 I slot print_timing: id 0 | task 133 | total time = 1190.57 ms / 136 tokens 0.55.021.871 I slot print_timing: id 0 | task 133 | graphs reused = 1 0.55.021.872 I slot print_timing: id 0 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.021.891 I slot release: id 0 | task 133 | stop processing: n_tokens = 135, truncated = 0 0.55.022.179 I slot print_timing: id 1 | task 134 | prompt eval time = 1149.43 ms / 161 tokens ( 7.14 ms per token, 140.07 tokens per second) 0.55.022.181 I slot print_timing: id 1 | task 134 | eval time = 41.44 ms / 2 tokens ( 41.44 ms per token, 24.13 tokens per second) 0.55.022.182 I slot print_timing: id 1 | task 134 | total time = 1190.87 ms / 163 tokens 0.55.022.182 I slot print_timing: id 1 | task 134 | graphs reused = 1 0.55.022.182 I slot print_timing: id 1 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.022.199 I slot release: id 1 | task 134 | stop processing: n_tokens = 162, truncated = 0 0.55.022.499 I slot print_timing: id 2 | task 135 | prompt eval time = 1149.71 ms / 122 tokens ( 9.42 ms per token, 106.11 tokens per second) 0.55.022.501 I slot print_timing: id 2 | task 135 | eval time = 41.46 ms / 2 tokens ( 41.46 ms per token, 24.12 tokens per second) 0.55.022.502 I slot print_timing: id 2 | task 135 | total time = 1191.17 ms / 124 tokens 0.55.022.502 I slot print_timing: id 2 | task 135 | graphs reused = 1 0.55.022.502 I slot print_timing: id 2 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.022.517 I slot release: id 2 | task 135 | stop processing: n_tokens = 123, truncated = 0 0.55.022.819 I slot print_timing: id 3 | task 136 | prompt eval time = 1150.15 ms / 136 tokens ( 8.46 ms per token, 118.25 tokens per second) 0.55.022.821 I slot print_timing: id 3 | task 136 | eval time = 41.33 ms / 2 tokens ( 41.33 ms per token, 24.19 tokens per second) 0.55.022.822 I slot print_timing: id 3 | task 136 | total time = 1191.49 ms / 138 tokens 0.55.022.822 I slot print_timing: id 3 | task 136 | graphs reused = 1 0.55.022.822 I slot print_timing: id 3 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.022.833 I slot release: id 3 | task 136 | stop processing: n_tokens = 137, truncated = 0 0.55.026.566 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.215 0.55.026.998 I slot launch_slot_: id 0 | task 141 | processing task, is_child = 0 0.55.028.132 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.170 (> 0.100 thold), f_keep = 0.179 0.55.028.169 I slot launch_slot_: id 1 | task 143 | processing task, is_child = 0 0.55.028.203 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.236 0.55.028.237 I slot launch_slot_: id 2 | task 142 | processing task, is_child = 0 0.55.028.256 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.212 0.55.028.286 I slot launch_slot_: id 3 | task 140 | processing task, is_child = 0 0.56.206.749 I slot print_timing: id 0 | task 141 | prompt eval time = 1137.27 ms / 131 tokens ( 8.68 ms per token, 115.19 tokens per second) 0.56.206.751 I slot print_timing: id 0 | task 141 | eval time = 41.19 ms / 2 tokens ( 41.19 ms per token, 24.28 tokens per second) 0.56.206.752 I slot print_timing: id 0 | task 141 | total time = 1178.46 ms / 133 tokens 0.56.206.752 I slot print_timing: id 0 | task 141 | graphs reused = 1 0.56.206.752 I slot print_timing: id 0 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.206.773 I slot release: id 0 | task 141 | stop processing: n_tokens = 132, truncated = 0 0.56.207.063 I slot print_timing: id 1 | task 143 | prompt eval time = 1137.54 ms / 171 tokens ( 6.65 ms per token, 150.32 tokens per second) 0.56.207.066 I slot print_timing: id 1 | task 143 | eval time = 41.22 ms / 2 tokens ( 41.22 ms per token, 24.26 tokens per second) 0.56.207.066 I slot print_timing: id 1 | task 143 | total time = 1178.76 ms / 173 tokens 0.56.207.067 I slot print_timing: id 1 | task 143 | graphs reused = 1 0.56.207.067 I slot print_timing: id 1 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.207.086 I slot release: id 1 | task 143 | stop processing: n_tokens = 172, truncated = 0 0.56.207.394 I slot print_timing: id 2 | task 142 | prompt eval time = 1137.85 ms / 175 tokens ( 6.50 ms per token, 153.80 tokens per second) 0.56.207.397 I slot print_timing: id 2 | task 142 | eval time = 41.22 ms / 2 tokens ( 41.22 ms per token, 24.26 tokens per second) 0.56.207.397 I slot print_timing: id 2 | task 142 | total time = 1179.08 ms / 177 tokens 0.56.207.397 I slot print_timing: id 2 | task 142 | graphs reused = 1 0.56.207.398 I slot print_timing: id 2 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.207.412 I slot release: id 2 | task 142 | stop processing: n_tokens = 176, truncated = 0 0.56.207.708 I slot print_timing: id 3 | task 140 | prompt eval time = 1138.15 ms / 181 tokens ( 6.29 ms per token, 159.03 tokens per second) 0.56.207.715 I slot print_timing: id 3 | task 140 | eval time = 41.23 ms / 2 tokens ( 41.23 ms per token, 24.25 tokens per second) 0.56.207.715 I slot print_timing: id 3 | task 140 | total time = 1179.38 ms / 183 tokens 0.56.207.715 I slot print_timing: id 3 | task 140 | graphs reused = 1 0.56.207.716 I slot print_timing: id 3 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.207.733 I slot release: id 3 | task 140 | stop processing: n_tokens = 182, truncated = 0 0.56.212.521 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.220 0.56.213.183 I slot launch_slot_: id 0 | task 148 | processing task, is_child = 0 0.56.214.466 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.169 0.56.214.502 I slot launch_slot_: id 1 | task 149 | processing task, is_child = 0 0.56.214.540 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.165 0.56.214.571 I slot launch_slot_: id 2 | task 147 | processing task, is_child = 0 0.56.214.591 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.159 0.56.214.739 I slot launch_slot_: id 3 | task 150 | processing task, is_child = 0 0.57.096.196 I slot print_timing: id 0 | task 148 | prompt eval time = 840.29 ms / 116 tokens ( 7.24 ms per token, 138.05 tokens per second) 0.57.096.198 I slot print_timing: id 0 | task 148 | eval time = 41.16 ms / 2 tokens ( 41.16 ms per token, 24.29 tokens per second) 0.57.096.199 I slot print_timing: id 0 | task 148 | total time = 881.45 ms / 118 tokens 0.57.096.199 I slot print_timing: id 0 | task 148 | graphs reused = 1 0.57.096.200 I slot print_timing: id 0 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.096.219 I slot release: id 0 | task 148 | stop processing: n_tokens = 117, truncated = 0 0.57.096.492 I slot print_timing: id 1 | task 149 | prompt eval time = 840.55 ms / 115 tokens ( 7.31 ms per token, 136.81 tokens per second) 0.57.096.494 I slot print_timing: id 1 | task 149 | eval time = 41.19 ms / 2 tokens ( 41.19 ms per token, 24.28 tokens per second) 0.57.096.495 I slot print_timing: id 1 | task 149 | total time = 881.74 ms / 117 tokens 0.57.096.495 I slot print_timing: id 1 | task 149 | graphs reused = 1 0.57.096.495 I slot print_timing: id 1 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.096.506 I slot release: id 1 | task 149 | stop processing: n_tokens = 116, truncated = 0 0.57.096.775 I slot print_timing: id 2 | task 147 | prompt eval time = 840.83 ms / 125 tokens ( 6.73 ms per token, 148.66 tokens per second) 0.57.096.777 I slot print_timing: id 2 | task 147 | eval time = 41.18 ms / 2 tokens ( 41.18 ms per token, 24.28 tokens per second) 0.57.096.777 I slot print_timing: id 2 | task 147 | total time = 882.01 ms / 127 tokens 0.57.096.777 I slot print_timing: id 2 | task 147 | graphs reused = 1 0.57.096.777 I slot print_timing: id 2 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.096.787 I slot release: id 2 | task 147 | stop processing: n_tokens = 126, truncated = 0 0.57.097.075 I slot print_timing: id 3 | task 150 | prompt eval time = 841.18 ms / 123 tokens ( 6.84 ms per token, 146.22 tokens per second) 0.57.097.078 I slot print_timing: id 3 | task 150 | eval time = 41.12 ms / 2 tokens ( 41.12 ms per token, 24.32 tokens per second) 0.57.097.078 I slot print_timing: id 3 | task 150 | total time = 882.30 ms / 125 tokens 0.57.097.079 I slot print_timing: id 3 | task 150 | graphs reused = 1 0.57.097.079 I slot print_timing: id 3 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.097.091 I slot release: id 3 | task 150 | stop processing: n_tokens = 124, truncated = 0 0.57.101.359 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.248 0.57.101.577 I slot launch_slot_: id 0 | task 154 | processing task, is_child = 0 0.57.102.448 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.250 0.57.102.483 I slot launch_slot_: id 1 | task 155 | processing task, is_child = 0 0.57.102.516 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.230 0.57.102.657 I slot launch_slot_: id 2 | task 156 | processing task, is_child = 0 0.57.102.676 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.242 0.57.102.821 I slot launch_slot_: id 3 | task 157 | processing task, is_child = 0 0.58.007.770 I slot print_timing: id 0 | task 154 | prompt eval time = 863.86 ms / 143 tokens ( 6.04 ms per token, 165.54 tokens per second) 0.58.007.773 I slot print_timing: id 0 | task 154 | eval time = 41.08 ms / 2 tokens ( 41.08 ms per token, 24.34 tokens per second) 0.58.007.773 I slot print_timing: id 0 | task 154 | total time = 904.94 ms / 145 tokens 0.58.007.774 I slot print_timing: id 0 | task 154 | graphs reused = 1 0.58.007.774 I slot print_timing: id 0 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.007.793 I slot release: id 0 | task 154 | stop processing: n_tokens = 144, truncated = 0 0.58.008.073 I slot print_timing: id 1 | task 155 | prompt eval time = 864.13 ms / 130 tokens ( 6.65 ms per token, 150.44 tokens per second) 0.58.008.077 I slot print_timing: id 1 | task 155 | eval time = 41.11 ms / 2 tokens ( 41.11 ms per token, 24.33 tokens per second) 0.58.008.077 I slot print_timing: id 1 | task 155 | total time = 905.24 ms / 132 tokens 0.58.008.078 I slot print_timing: id 1 | task 155 | graphs reused = 1 0.58.008.078 I slot print_timing: id 1 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.008.091 I slot release: id 1 | task 155 | stop processing: n_tokens = 131, truncated = 0 0.58.008.380 I slot print_timing: id 2 | task 156 | prompt eval time = 864.41 ms / 130 tokens ( 6.65 ms per token, 150.39 tokens per second) 0.58.008.382 I slot print_timing: id 2 | task 156 | eval time = 41.12 ms / 2 tokens ( 41.12 ms per token, 24.32 tokens per second) 0.58.008.382 I slot print_timing: id 2 | task 156 | total time = 905.53 ms / 132 tokens 0.58.008.383 I slot print_timing: id 2 | task 156 | graphs reused = 1 0.58.008.383 I slot print_timing: id 2 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.008.394 I slot release: id 2 | task 156 | stop processing: n_tokens = 131, truncated = 0 0.58.008.778 I slot print_timing: id 3 | task 157 | prompt eval time = 864.82 ms / 129 tokens ( 6.70 ms per token, 149.16 tokens per second) 0.58.008.781 I slot print_timing: id 3 | task 157 | eval time = 41.11 ms / 2 tokens ( 41.11 ms per token, 24.33 tokens per second) 0.58.008.781 I slot print_timing: id 3 | task 157 | total time = 905.92 ms / 131 tokens 0.58.008.781 I slot print_timing: id 3 | task 157 | graphs reused = 1 0.58.008.782 I slot print_timing: id 3 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.008.804 I slot release: id 3 | task 157 | stop processing: n_tokens = 130, truncated = 0 0.58.012.571 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.286 (> 0.100 thold), f_keep = 0.231 0.58.012.960 I slot launch_slot_: id 3 | task 161 | processing task, is_child = 0 0.58.014.043 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.201 0.58.014.077 I slot launch_slot_: id 0 | task 162 | processing task, is_child = 0 0.58.014.110 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.225 (> 0.100 thold), f_keep = 0.221 0.58.014.140 I slot launch_slot_: id 1 | task 163 | processing task, is_child = 0 0.58.014.159 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.221 0.58.014.188 I slot launch_slot_: id 2 | task 164 | processing task, is_child = 0 0.59.170.101 I slot print_timing: id 0 | task 162 | prompt eval time = 1114.96 ms / 124 tokens ( 8.99 ms per token, 111.21 tokens per second) 0.59.170.103 I slot print_timing: id 0 | task 162 | eval time = 40.94 ms / 2 tokens ( 40.94 ms per token, 24.43 tokens per second) 0.59.170.103 I slot print_timing: id 0 | task 162 | total time = 1155.91 ms / 126 tokens 0.59.170.104 I slot print_timing: id 0 | task 162 | graphs reused = 1 0.59.170.104 I slot print_timing: id 0 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.170.125 I slot release: id 0 | task 162 | stop processing: n_tokens = 125, truncated = 0 0.59.170.388 I slot print_timing: id 1 | task 163 | prompt eval time = 1115.22 ms / 129 tokens ( 8.65 ms per token, 115.67 tokens per second) 0.59.170.390 I slot print_timing: id 1 | task 163 | eval time = 40.96 ms / 2 tokens ( 40.96 ms per token, 24.41 tokens per second) 0.59.170.391 I slot print_timing: id 1 | task 163 | total time = 1156.18 ms / 131 tokens 0.59.170.391 I slot print_timing: id 1 | task 163 | graphs reused = 1 0.59.170.391 I slot print_timing: id 1 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.170.406 I slot release: id 1 | task 163 | stop processing: n_tokens = 130, truncated = 0 0.59.170.699 I slot print_timing: id 2 | task 164 | prompt eval time = 1115.51 ms / 161 tokens ( 6.93 ms per token, 144.33 tokens per second) 0.59.170.700 I slot print_timing: id 2 | task 164 | eval time = 40.97 ms / 2 tokens ( 40.97 ms per token, 24.41 tokens per second) 0.59.170.701 I slot print_timing: id 2 | task 164 | total time = 1156.48 ms / 163 tokens 0.59.170.701 I slot print_timing: id 2 | task 164 | graphs reused = 1 0.59.170.701 I slot print_timing: id 2 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.170.715 I slot release: id 2 | task 164 | stop processing: n_tokens = 162, truncated = 0 0.59.171.010 I slot print_timing: id 3 | task 161 | prompt eval time = 1115.80 ms / 105 tokens ( 10.63 ms per token, 94.10 tokens per second) 0.59.171.014 I slot print_timing: id 3 | task 161 | eval time = 40.98 ms / 2 tokens ( 40.98 ms per token, 24.40 tokens per second) 0.59.171.014 I slot print_timing: id 3 | task 161 | total time = 1156.78 ms / 107 tokens 0.59.171.014 I slot print_timing: id 3 | task 161 | graphs reused = 1 0.59.171.014 I slot print_timing: id 3 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.171.025 I slot release: id 3 | task 161 | stop processing: n_tokens = 106, truncated = 0 0.59.175.002 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.232 0.59.175.461 I slot launch_slot_: id 0 | task 169 | processing task, is_child = 0 0.59.176.320 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.223 0.59.176.355 I slot launch_slot_: id 1 | task 168 | processing task, is_child = 0 0.59.176.389 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.179 0.59.176.526 I slot launch_slot_: id 2 | task 170 | processing task, is_child = 0 0.59.176.543 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.283 0.59.176.576 I slot launch_slot_: id 3 | task 171 | processing task, is_child = 0 1.00.401.703 I slot print_timing: id 0 | task 169 | prompt eval time = 1183.95 ms / 155 tokens ( 7.64 ms per token, 130.92 tokens per second) 1.00.401.706 I slot print_timing: id 0 | task 169 | eval time = 41.17 ms / 2 tokens ( 41.17 ms per token, 24.29 tokens per second) 1.00.401.706 I slot print_timing: id 0 | task 169 | total time = 1225.12 ms / 157 tokens 1.00.401.707 I slot print_timing: id 0 | task 169 | graphs reused = 1 1.00.401.707 I slot print_timing: id 0 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.401.727 I slot release: id 0 | task 169 | stop processing: n_tokens = 156, truncated = 0 1.00.402.001 I slot print_timing: id 1 | task 168 | prompt eval time = 1184.21 ms / 169 tokens ( 7.01 ms per token, 142.71 tokens per second) 1.00.402.004 I slot print_timing: id 1 | task 168 | eval time = 41.20 ms / 2 tokens ( 41.20 ms per token, 24.27 tokens per second) 1.00.402.004 I slot print_timing: id 1 | task 168 | total time = 1225.41 ms / 171 tokens 1.00.402.005 I slot print_timing: id 1 | task 168 | graphs reused = 1 1.00.402.005 I slot print_timing: id 1 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.402.025 I slot release: id 1 | task 168 | stop processing: n_tokens = 170, truncated = 0 1.00.402.317 I slot print_timing: id 2 | task 170 | prompt eval time = 1184.49 ms / 143 tokens ( 8.28 ms per token, 120.73 tokens per second) 1.00.402.319 I slot print_timing: id 2 | task 170 | eval time = 41.23 ms / 2 tokens ( 41.23 ms per token, 24.25 tokens per second) 1.00.402.320 I slot print_timing: id 2 | task 170 | total time = 1225.72 ms / 145 tokens 1.00.402.320 I slot print_timing: id 2 | task 170 | graphs reused = 1 1.00.402.320 I slot print_timing: id 2 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.402.333 I slot release: id 2 | task 170 | stop processing: n_tokens = 144, truncated = 0 1.00.402.636 I slot print_timing: id 3 | task 171 | prompt eval time = 1184.80 ms / 113 tokens ( 10.48 ms per token, 95.37 tokens per second) 1.00.402.640 I slot print_timing: id 3 | task 171 | eval time = 41.22 ms / 2 tokens ( 41.22 ms per token, 24.26 tokens per second) 1.00.402.641 I slot print_timing: id 3 | task 171 | total time = 1226.02 ms / 115 tokens 1.00.402.641 I slot print_timing: id 3 | task 171 | graphs reused = 1 1.00.402.642 I slot print_timing: id 3 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.402.656 I slot release: id 3 | task 171 | stop processing: n_tokens = 114, truncated = 0 1.00.407.160 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.263 1.00.407.446 I slot launch_slot_: id 3 | task 178 | processing task, is_child = 0 1.00.408.661 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.186 1.00.408.698 I slot launch_slot_: id 0 | task 175 | processing task, is_child = 0 1.00.408.734 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.171 1.00.408.765 I slot launch_slot_: id 1 | task 177 | processing task, is_child = 0 1.00.408.784 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.201 1.00.408.815 I slot launch_slot_: id 2 | task 176 | processing task, is_child = 0 1.01.461.078 I slot print_timing: id 0 | task 175 | prompt eval time = 1011.25 ms / 111 tokens ( 9.11 ms per token, 109.77 tokens per second) 1.01.461.081 I slot print_timing: id 0 | task 175 | eval time = 41.01 ms / 2 tokens ( 41.01 ms per token, 24.39 tokens per second) 1.01.461.081 I slot print_timing: id 0 | task 175 | total time = 1052.25 ms / 113 tokens 1.01.461.082 I slot print_timing: id 0 | task 175 | graphs reused = 1 1.01.461.082 I slot print_timing: id 0 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.461.099 I slot release: id 0 | task 175 | stop processing: n_tokens = 112, truncated = 0 1.01.461.370 I slot print_timing: id 1 | task 177 | prompt eval time = 1011.51 ms / 150 tokens ( 6.74 ms per token, 148.29 tokens per second) 1.01.461.372 I slot print_timing: id 1 | task 177 | eval time = 41.02 ms / 2 tokens ( 41.02 ms per token, 24.38 tokens per second) 1.01.461.372 I slot print_timing: id 1 | task 177 | total time = 1052.53 ms / 152 tokens 1.01.461.373 I slot print_timing: id 1 | task 177 | graphs reused = 1 1.01.461.373 I slot print_timing: id 1 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.461.391 I slot release: id 1 | task 177 | stop processing: n_tokens = 151, truncated = 0 1.01.461.690 I slot print_timing: id 2 | task 176 | prompt eval time = 1011.78 ms / 138 tokens ( 7.33 ms per token, 136.39 tokens per second) 1.01.461.692 I slot print_timing: id 2 | task 176 | eval time = 41.06 ms / 2 tokens ( 41.06 ms per token, 24.36 tokens per second) 1.01.461.692 I slot print_timing: id 2 | task 176 | total time = 1052.84 ms / 140 tokens 1.01.461.693 I slot print_timing: id 2 | task 176 | graphs reused = 1 1.01.461.693 I slot print_timing: id 2 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.461.712 I slot release: id 2 | task 176 | stop processing: n_tokens = 139, truncated = 0 1.01.461.994 I slot print_timing: id 3 | task 178 | prompt eval time = 1012.07 ms / 113 tokens ( 8.96 ms per token, 111.65 tokens per second) 1.01.461.996 I slot print_timing: id 3 | task 178 | eval time = 41.06 ms / 2 tokens ( 41.06 ms per token, 24.36 tokens per second) 1.01.462.000 I slot print_timing: id 3 | task 178 | total time = 1053.13 ms / 115 tokens 1.01.462.000 I slot print_timing: id 3 | task 178 | graphs reused = 1 1.01.462.001 I slot print_timing: id 3 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.462.010 I slot release: id 3 | task 178 | stop processing: n_tokens = 114, truncated = 0 1.01.465.565 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.259 1.01.465.792 I slot launch_slot_: id 0 | task 182 | processing task, is_child = 0 1.01.466.801 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.263 (> 0.100 thold), f_keep = 0.263 1.01.466.836 I slot launch_slot_: id 3 | task 183 | processing task, is_child = 0 1.01.466.871 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.192 1.01.466.901 I slot launch_slot_: id 1 | task 184 | processing task, is_child = 0 1.01.466.919 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.209 1.01.467.079 I slot launch_slot_: id 2 | task 185 | processing task, is_child = 0 1.02.594.522 I slot print_timing: id 0 | task 182 | prompt eval time = 1086.11 ms / 153 tokens ( 7.10 ms per token, 140.87 tokens per second) 1.02.594.524 I slot print_timing: id 0 | task 182 | eval time = 41.33 ms / 2 tokens ( 41.33 ms per token, 24.20 tokens per second) 1.02.594.524 I slot print_timing: id 0 | task 182 | total time = 1127.44 ms / 155 tokens 1.02.594.525 I slot print_timing: id 0 | task 182 | graphs reused = 1 1.02.594.525 I slot print_timing: id 0 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.594.545 I slot release: id 0 | task 182 | stop processing: n_tokens = 154, truncated = 0 1.02.594.806 I slot print_timing: id 1 | task 184 | prompt eval time = 1086.36 ms / 126 tokens ( 8.62 ms per token, 115.98 tokens per second) 1.02.594.808 I slot print_timing: id 1 | task 184 | eval time = 41.35 ms / 2 tokens ( 41.35 ms per token, 24.18 tokens per second) 1.02.594.808 I slot print_timing: id 1 | task 184 | total time = 1127.71 ms / 128 tokens 1.02.594.808 I slot print_timing: id 1 | task 184 | graphs reused = 1 1.02.594.809 I slot print_timing: id 1 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.594.822 I slot release: id 1 | task 184 | stop processing: n_tokens = 127, truncated = 0 1.02.595.100 I slot print_timing: id 2 | task 185 | prompt eval time = 1086.72 ms / 131 tokens ( 8.30 ms per token, 120.55 tokens per second) 1.02.595.102 I slot print_timing: id 2 | task 185 | eval time = 41.27 ms / 2 tokens ( 41.27 ms per token, 24.23 tokens per second) 1.02.595.102 I slot print_timing: id 2 | task 185 | total time = 1127.99 ms / 133 tokens 1.02.595.102 I slot print_timing: id 2 | task 185 | graphs reused = 1 1.02.595.103 I slot print_timing: id 2 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.595.118 I slot release: id 2 | task 185 | stop processing: n_tokens = 132, truncated = 0 1.02.595.415 I slot print_timing: id 3 | task 183 | prompt eval time = 1087.01 ms / 114 tokens ( 9.54 ms per token, 104.87 tokens per second) 1.02.595.419 I slot print_timing: id 3 | task 183 | eval time = 41.28 ms / 2 tokens ( 41.28 ms per token, 24.22 tokens per second) 1.02.595.419 I slot print_timing: id 3 | task 183 | total time = 1128.29 ms / 116 tokens 1.02.595.420 I slot print_timing: id 3 | task 183 | graphs reused = 1 1.02.595.420 I slot print_timing: id 3 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.595.430 I slot release: id 3 | task 183 | stop processing: n_tokens = 115, truncated = 0 1.02.600.274 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.227 1.02.600.698 I slot launch_slot_: id 2 | task 189 | processing task, is_child = 0 1.02.601.711 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.261 1.02.601.744 I slot launch_slot_: id 3 | task 190 | processing task, is_child = 0 1.02.601.785 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.185 (> 0.100 thold), f_keep = 0.188 1.02.601.819 I slot launch_slot_: id 0 | task 191 | processing task, is_child = 0 1.02.601.837 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.228 1.02.601.867 I slot launch_slot_: id 1 | task 192 | processing task, is_child = 0 1.03.832.357 I slot print_timing: id 0 | task 191 | prompt eval time = 1189.20 ms / 157 tokens ( 7.57 ms per token, 132.02 tokens per second) 1.03.832.360 I slot print_timing: id 0 | task 191 | eval time = 41.28 ms / 2 tokens ( 41.28 ms per token, 24.22 tokens per second) 1.03.832.360 I slot print_timing: id 0 | task 191 | total time = 1230.48 ms / 159 tokens 1.03.832.361 I slot print_timing: id 0 | task 191 | graphs reused = 1 1.03.832.361 I slot print_timing: id 0 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.832.384 I slot release: id 0 | task 191 | stop processing: n_tokens = 158, truncated = 0 1.03.832.669 I slot print_timing: id 1 | task 192 | prompt eval time = 1189.61 ms / 170 tokens ( 7.00 ms per token, 142.90 tokens per second) 1.03.832.671 I slot print_timing: id 1 | task 192 | eval time = 41.18 ms / 2 tokens ( 41.18 ms per token, 24.29 tokens per second) 1.03.832.672 I slot print_timing: id 1 | task 192 | total time = 1230.78 ms / 172 tokens 1.03.832.672 I slot print_timing: id 1 | task 192 | graphs reused = 1 1.03.832.672 I slot print_timing: id 1 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.832.691 I slot release: id 1 | task 192 | stop processing: n_tokens = 171, truncated = 0 1.03.832.965 I slot print_timing: id 2 | task 189 | prompt eval time = 1190.00 ms / 130 tokens ( 9.15 ms per token, 109.24 tokens per second) 1.03.832.968 I slot print_timing: id 2 | task 189 | eval time = 41.07 ms / 2 tokens ( 41.07 ms per token, 24.35 tokens per second) 1.03.832.968 I slot print_timing: id 2 | task 189 | total time = 1231.06 ms / 132 tokens 1.03.832.969 I slot print_timing: id 2 | task 189 | graphs reused = 1 1.03.832.969 I slot print_timing: id 2 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.832.980 I slot release: id 2 | task 189 | stop processing: n_tokens = 131, truncated = 0 1.03.833.281 I slot print_timing: id 3 | task 190 | prompt eval time = 1190.52 ms / 119 tokens ( 10.00 ms per token, 99.96 tokens per second) 1.03.833.284 I slot print_timing: id 3 | task 190 | eval time = 40.85 ms / 2 tokens ( 40.85 ms per token, 24.48 tokens per second) 1.03.833.284 I slot print_timing: id 3 | task 190 | total time = 1231.37 ms / 121 tokens 1.03.833.284 I slot print_timing: id 3 | task 190 | graphs reused = 1 1.03.833.285 I slot print_timing: id 3 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.833.299 I slot release: id 3 | task 190 | stop processing: n_tokens = 120, truncated = 0 1.03.837.391 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.184 1.03.838.035 I slot launch_slot_: id 0 | task 196 | processing task, is_child = 0 1.03.838.967 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.170 1.03.839.001 I slot launch_slot_: id 1 | task 197 | processing task, is_child = 0 1.03.839.035 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.221 1.03.839.069 I slot launch_slot_: id 2 | task 198 | processing task, is_child = 0 1.03.839.088 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.242 1.03.839.118 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 1.05.170.571 I slot print_timing: id 0 | task 196 | prompt eval time = 1290.36 ms / 135 tokens ( 9.56 ms per token, 104.62 tokens per second) 1.05.170.573 I slot print_timing: id 0 | task 196 | eval time = 41.09 ms / 2 tokens ( 41.09 ms per token, 24.34 tokens per second) 1.05.170.574 I slot print_timing: id 0 | task 196 | total time = 1331.44 ms / 137 tokens 1.05.170.574 I slot print_timing: id 0 | task 196 | graphs reused = 1 1.05.170.574 I slot print_timing: id 0 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.170.599 I slot release: id 0 | task 196 | stop processing: n_tokens = 136, truncated = 0 1.05.170.895 I slot print_timing: id 1 | task 197 | prompt eval time = 1290.64 ms / 182 tokens ( 7.09 ms per token, 141.01 tokens per second) 1.05.170.896 I slot print_timing: id 1 | task 197 | eval time = 41.11 ms / 2 tokens ( 41.11 ms per token, 24.32 tokens per second) 1.05.170.897 I slot print_timing: id 1 | task 197 | total time = 1331.76 ms / 184 tokens 1.05.170.897 I slot print_timing: id 1 | task 197 | graphs reused = 1 1.05.170.897 I slot print_timing: id 1 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.170.916 I slot release: id 1 | task 197 | stop processing: n_tokens = 183, truncated = 0 1.05.171.208 I slot print_timing: id 2 | task 198 | prompt eval time = 1290.94 ms / 155 tokens ( 8.33 ms per token, 120.07 tokens per second) 1.05.171.209 I slot print_timing: id 2 | task 198 | eval time = 41.12 ms / 2 tokens ( 41.12 ms per token, 24.32 tokens per second) 1.05.171.210 I slot print_timing: id 2 | task 198 | total time = 1332.06 ms / 157 tokens 1.05.171.210 I slot print_timing: id 2 | task 198 | graphs reused = 1 1.05.171.210 I slot print_timing: id 2 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.171.232 I slot release: id 2 | task 198 | stop processing: n_tokens = 156, truncated = 0 1.05.171.543 I slot print_timing: id 3 | task 199 | prompt eval time = 1291.26 ms / 110 tokens ( 11.74 ms per token, 85.19 tokens per second) 1.05.171.546 I slot print_timing: id 3 | task 199 | eval time = 41.13 ms / 2 tokens ( 41.13 ms per token, 24.31 tokens per second) 1.05.171.546 I slot print_timing: id 3 | task 199 | total time = 1332.38 ms / 112 tokens 1.05.171.546 I slot print_timing: id 3 | task 199 | graphs reused = 1 1.05.171.547 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.171.567 I slot release: id 3 | task 199 | stop processing: n_tokens = 111, truncated = 0 1.05.176.375 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.213 1.05.176.972 I slot launch_slot_: id 0 | task 203 | processing task, is_child = 0 1.05.177.973 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.158 1.05.178.013 I slot launch_slot_: id 1 | task 204 | processing task, is_child = 0 1.05.178.047 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.186 1.05.178.078 I slot launch_slot_: id 2 | task 206 | processing task, is_child = 0 1.05.178.095 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.261 1.05.178.123 I slot launch_slot_: id 3 | task 205 | processing task, is_child = 0 1.06.321.983 I slot print_timing: id 0 | task 203 | prompt eval time = 1102.53 ms / 117 tokens ( 9.42 ms per token, 106.12 tokens per second) 1.06.321.985 I slot print_timing: id 0 | task 203 | eval time = 41.32 ms / 2 tokens ( 41.32 ms per token, 24.20 tokens per second) 1.06.321.986 I slot print_timing: id 0 | task 203 | total time = 1143.85 ms / 119 tokens 1.06.321.986 I slot print_timing: id 0 | task 203 | graphs reused = 1 1.06.321.987 I slot print_timing: id 0 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.322.009 I slot release: id 0 | task 203 | stop processing: n_tokens = 118, truncated = 0 1.06.322.363 I slot print_timing: id 1 | task 204 | prompt eval time = 1102.87 ms / 134 tokens ( 8.23 ms per token, 121.50 tokens per second) 1.06.322.365 I slot print_timing: id 1 | task 204 | eval time = 41.35 ms / 2 tokens ( 41.35 ms per token, 24.18 tokens per second) 1.06.322.365 I slot print_timing: id 1 | task 204 | total time = 1144.22 ms / 136 tokens 1.06.322.366 I slot print_timing: id 1 | task 204 | graphs reused = 1 1.06.322.366 I slot print_timing: id 1 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.322.381 I slot release: id 1 | task 204 | stop processing: n_tokens = 135, truncated = 0 1.06.322.658 I slot print_timing: id 2 | task 206 | prompt eval time = 1103.14 ms / 160 tokens ( 6.89 ms per token, 145.04 tokens per second) 1.06.322.660 I slot print_timing: id 2 | task 206 | eval time = 41.35 ms / 2 tokens ( 41.35 ms per token, 24.18 tokens per second) 1.06.322.661 I slot print_timing: id 2 | task 206 | total time = 1144.50 ms / 162 tokens 1.06.322.661 I slot print_timing: id 2 | task 206 | graphs reused = 1 1.06.322.661 I slot print_timing: id 2 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.322.684 I slot release: id 2 | task 206 | stop processing: n_tokens = 161, truncated = 0 1.06.323.006 I slot print_timing: id 3 | task 205 | prompt eval time = 1103.64 ms / 136 tokens ( 8.12 ms per token, 123.23 tokens per second) 1.06.323.016 I slot print_timing: id 3 | task 205 | eval time = 41.19 ms / 2 tokens ( 41.19 ms per token, 24.28 tokens per second) 1.06.323.017 I slot print_timing: id 3 | task 205 | total time = 1144.83 ms / 138 tokens 1.06.323.017 I slot print_timing: id 3 | task 205 | graphs reused = 1 1.06.323.017 I slot print_timing: id 3 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.323.037 I slot release: id 3 | task 205 | stop processing: n_tokens = 137, truncated = 0 1.06.327.350 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.246 1.06.327.756 I slot launch_slot_: id 0 | task 211 | processing task, is_child = 0 1.06.328.987 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.215 1.06.329.152 I slot launch_slot_: id 1 | task 212 | processing task, is_child = 0 1.06.329.190 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.180 1.06.329.337 I slot launch_slot_: id 2 | task 210 | processing task, is_child = 0 1.06.329.357 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.212 1.06.329.388 I slot launch_slot_: id 3 | task 213 | processing task, is_child = 0 1.07.507.243 I slot print_timing: id 0 | task 211 | prompt eval time = 1136.62 ms / 151 tokens ( 7.53 ms per token, 132.85 tokens per second) 1.07.507.246 I slot print_timing: id 0 | task 211 | eval time = 41.23 ms / 2 tokens ( 41.23 ms per token, 24.26 tokens per second) 1.07.507.247 I slot print_timing: id 0 | task 211 | total time = 1177.84 ms / 153 tokens 1.07.507.247 I slot print_timing: id 0 | task 211 | graphs reused = 1 1.07.507.247 I slot print_timing: id 0 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.507.268 I slot release: id 0 | task 211 | stop processing: n_tokens = 152, truncated = 0 1.07.507.555 I slot print_timing: id 1 | task 212 | prompt eval time = 1136.90 ms / 118 tokens ( 9.63 ms per token, 103.79 tokens per second) 1.07.507.558 I slot print_timing: id 1 | task 212 | eval time = 41.25 ms / 2 tokens ( 41.25 ms per token, 24.24 tokens per second) 1.07.507.558 I slot print_timing: id 1 | task 212 | total time = 1178.15 ms / 120 tokens 1.07.507.558 I slot print_timing: id 1 | task 212 | graphs reused = 1 1.07.507.559 I slot print_timing: id 1 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.507.571 I slot release: id 1 | task 212 | stop processing: n_tokens = 119, truncated = 0 1.07.507.838 I slot print_timing: id 2 | task 210 | prompt eval time = 1137.16 ms / 124 tokens ( 9.17 ms per token, 109.04 tokens per second) 1.07.507.841 I slot print_timing: id 2 | task 210 | eval time = 41.26 ms / 2 tokens ( 41.26 ms per token, 24.24 tokens per second) 1.07.507.841 I slot print_timing: id 2 | task 210 | total time = 1178.42 ms / 126 tokens 1.07.507.841 I slot print_timing: id 2 | task 210 | graphs reused = 1 1.07.507.841 I slot print_timing: id 2 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.507.861 I slot release: id 2 | task 210 | stop processing: n_tokens = 125, truncated = 0 1.07.508.131 I slot print_timing: id 3 | task 213 | prompt eval time = 1137.44 ms / 156 tokens ( 7.29 ms per token, 137.15 tokens per second) 1.07.508.133 I slot print_timing: id 3 | task 213 | eval time = 41.26 ms / 2 tokens ( 41.26 ms per token, 24.24 tokens per second) 1.07.508.134 I slot print_timing: id 3 | task 213 | total time = 1178.70 ms / 158 tokens 1.07.508.134 I slot print_timing: id 3 | task 213 | graphs reused = 1 1.07.508.134 I slot print_timing: id 3 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.508.154 I slot release: id 3 | task 213 | stop processing: n_tokens = 157, truncated = 0 1.07.512.700 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.191 1.07.513.155 I slot launch_slot_: id 0 | task 219 | processing task, is_child = 0 1.07.514.245 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.244 1.07.514.280 I slot launch_slot_: id 1 | task 217 | processing task, is_child = 0 1.07.514.318 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.232 1.07.514.349 I slot launch_slot_: id 2 | task 218 | processing task, is_child = 0 1.07.514.370 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.185 1.07.514.402 I slot launch_slot_: id 3 | task 220 | processing task, is_child = 0 1.08.715.577 I slot print_timing: id 0 | task 219 | prompt eval time = 1159.97 ms / 149 tokens ( 7.79 ms per token, 128.45 tokens per second) 1.08.715.579 I slot print_timing: id 0 | task 219 | eval time = 41.20 ms / 2 tokens ( 41.20 ms per token, 24.27 tokens per second) 1.08.715.580 I slot print_timing: id 0 | task 219 | total time = 1201.17 ms / 151 tokens 1.08.715.580 I slot print_timing: id 0 | task 219 | graphs reused = 1 1.08.715.580 I slot print_timing: id 0 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.715.601 I slot release: id 0 | task 219 | stop processing: n_tokens = 150, truncated = 0 1.08.715.875 I slot print_timing: id 1 | task 217 | prompt eval time = 1160.24 ms / 154 tokens ( 7.53 ms per token, 132.73 tokens per second) 1.08.715.877 I slot print_timing: id 1 | task 217 | eval time = 41.21 ms / 2 tokens ( 41.21 ms per token, 24.26 tokens per second) 1.08.715.878 I slot print_timing: id 1 | task 217 | total time = 1201.45 ms / 156 tokens 1.08.715.878 I slot print_timing: id 1 | task 217 | graphs reused = 1 1.08.715.878 I slot print_timing: id 1 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.715.899 I slot release: id 1 | task 217 | stop processing: n_tokens = 155, truncated = 0 1.08.716.173 I slot print_timing: id 2 | task 218 | prompt eval time = 1160.52 ms / 162 tokens ( 7.16 ms per token, 139.59 tokens per second) 1.08.716.175 I slot print_timing: id 2 | task 218 | eval time = 41.22 ms / 2 tokens ( 41.22 ms per token, 24.26 tokens per second) 1.08.716.176 I slot print_timing: id 2 | task 218 | total time = 1201.74 ms / 164 tokens 1.08.716.176 I slot print_timing: id 2 | task 218 | graphs reused = 1 1.08.716.176 I slot print_timing: id 2 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.716.189 I slot release: id 2 | task 218 | stop processing: n_tokens = 163, truncated = 0 1.08.716.489 I slot print_timing: id 3 | task 220 | prompt eval time = 1160.81 ms / 156 tokens ( 7.44 ms per token, 134.39 tokens per second) 1.08.716.493 I slot print_timing: id 3 | task 220 | eval time = 41.23 ms / 2 tokens ( 41.23 ms per token, 24.25 tokens per second) 1.08.716.493 I slot print_timing: id 3 | task 220 | total time = 1202.04 ms / 158 tokens 1.08.716.493 I slot print_timing: id 3 | task 220 | graphs reused = 1 1.08.716.494 I slot print_timing: id 3 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.716.506 I slot release: id 3 | task 220 | stop processing: n_tokens = 157, truncated = 0 1.08.720.639 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.193 1.08.721.100 I slot launch_slot_: id 0 | task 224 | processing task, is_child = 0 1.08.722.296 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.187 1.08.722.334 I slot launch_slot_: id 1 | task 225 | processing task, is_child = 0 1.08.722.371 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.178 1.08.722.404 I slot launch_slot_: id 2 | task 226 | processing task, is_child = 0 1.08.722.424 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.185 1.08.722.566 I slot launch_slot_: id 3 | task 227 | processing task, is_child = 0 1.09.813.725 I slot print_timing: id 0 | task 224 | prompt eval time = 1049.78 ms / 186 tokens ( 5.64 ms per token, 177.18 tokens per second) 1.09.813.726 I slot print_timing: id 0 | task 224 | eval time = 41.37 ms / 2 tokens ( 41.37 ms per token, 24.17 tokens per second) 1.09.813.727 I slot print_timing: id 0 | task 224 | total time = 1091.15 ms / 188 tokens 1.09.813.727 I slot print_timing: id 0 | task 224 | graphs reused = 1 1.09.813.728 I slot print_timing: id 0 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.813.750 I slot release: id 0 | task 224 | stop processing: n_tokens = 187, truncated = 0 1.09.814.125 I slot print_timing: id 1 | task 225 | prompt eval time = 1050.13 ms / 108 tokens ( 9.72 ms per token, 102.84 tokens per second) 1.09.814.127 I slot print_timing: id 1 | task 225 | eval time = 41.41 ms / 2 tokens ( 41.41 ms per token, 24.15 tokens per second) 1.09.814.127 I slot print_timing: id 1 | task 225 | total time = 1091.54 ms / 110 tokens 1.09.814.127 I slot print_timing: id 1 | task 225 | graphs reused = 1 1.09.814.128 I slot print_timing: id 1 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.814.145 I slot release: id 1 | task 225 | stop processing: n_tokens = 109, truncated = 0 1.09.814.447 I slot print_timing: id 2 | task 226 | prompt eval time = 1050.44 ms / 115 tokens ( 9.13 ms per token, 109.48 tokens per second) 1.09.814.450 I slot print_timing: id 2 | task 226 | eval time = 41.40 ms / 2 tokens ( 41.40 ms per token, 24.15 tokens per second) 1.09.814.451 I slot print_timing: id 2 | task 226 | total time = 1091.84 ms / 117 tokens 1.09.814.451 I slot print_timing: id 2 | task 226 | graphs reused = 1 1.09.814.451 I slot print_timing: id 2 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.814.471 I slot release: id 2 | task 226 | stop processing: n_tokens = 116, truncated = 0 1.09.814.824 I slot print_timing: id 3 | task 227 | prompt eval time = 1050.83 ms / 103 tokens ( 10.20 ms per token, 98.02 tokens per second) 1.09.814.827 I slot print_timing: id 3 | task 227 | eval time = 41.38 ms / 2 tokens ( 41.38 ms per token, 24.16 tokens per second) 1.09.814.827 I slot print_timing: id 3 | task 227 | total time = 1092.21 ms / 105 tokens 1.09.814.828 I slot print_timing: id 3 | task 227 | graphs reused = 1 1.09.814.828 I slot print_timing: id 3 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.814.846 I slot release: id 3 | task 227 | stop processing: n_tokens = 104, truncated = 0 1.09.818.685 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.155 1.09.819.243 I slot launch_slot_: id 0 | task 231 | processing task, is_child = 0 1.09.819.740 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.288 1.09.819.791 I slot launch_slot_: id 3 | task 232 | processing task, is_child = 0 1.09.819.826 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.266 1.09.819.857 I slot launch_slot_: id 1 | task 234 | processing task, is_child = 0 1.09.819.876 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.250 1.09.819.907 I slot launch_slot_: id 2 | task 233 | processing task, is_child = 0 1.10.998.766 I slot print_timing: id 0 | task 231 | prompt eval time = 1137.35 ms / 122 tokens ( 9.32 ms per token, 107.27 tokens per second) 1.10.998.768 I slot print_timing: id 0 | task 231 | eval time = 41.50 ms / 2 tokens ( 41.50 ms per token, 24.10 tokens per second) 1.10.998.768 I slot print_timing: id 0 | task 231 | total time = 1178.85 ms / 124 tokens 1.10.998.769 I slot print_timing: id 0 | task 231 | graphs reused = 1 1.10.998.769 I slot print_timing: id 0 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.998.788 I slot release: id 0 | task 231 | stop processing: n_tokens = 123, truncated = 0 1.10.999.061 I slot print_timing: id 1 | task 234 | prompt eval time = 1137.62 ms / 128 tokens ( 8.89 ms per token, 112.52 tokens per second) 1.10.999.064 I slot print_timing: id 1 | task 234 | eval time = 41.52 ms / 2 tokens ( 41.52 ms per token, 24.09 tokens per second) 1.10.999.065 I slot print_timing: id 1 | task 234 | total time = 1179.13 ms / 130 tokens 1.10.999.065 I slot print_timing: id 1 | task 234 | graphs reused = 1 1.10.999.065 I slot print_timing: id 1 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.999.082 I slot release: id 1 | task 234 | stop processing: n_tokens = 129, truncated = 0 1.10.999.368 I slot print_timing: id 2 | task 233 | prompt eval time = 1137.91 ms / 163 tokens ( 6.98 ms per token, 143.24 tokens per second) 1.10.999.370 I slot print_timing: id 2 | task 233 | eval time = 41.52 ms / 2 tokens ( 41.52 ms per token, 24.09 tokens per second) 1.10.999.371 I slot print_timing: id 2 | task 233 | total time = 1179.43 ms / 165 tokens 1.10.999.371 I slot print_timing: id 2 | task 233 | graphs reused = 1 1.10.999.371 I slot print_timing: id 2 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.999.387 I slot release: id 2 | task 233 | stop processing: n_tokens = 164, truncated = 0 1.10.999.681 I slot print_timing: id 3 | task 232 | prompt eval time = 1138.22 ms / 113 tokens ( 10.07 ms per token, 99.28 tokens per second) 1.10.999.683 I slot print_timing: id 3 | task 232 | eval time = 41.51 ms / 2 tokens ( 41.51 ms per token, 24.09 tokens per second) 1.10.999.684 I slot print_timing: id 3 | task 232 | total time = 1179.73 ms / 115 tokens 1.10.999.684 I slot print_timing: id 3 | task 232 | graphs reused = 1 1.10.999.684 I slot print_timing: id 3 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.999.694 I slot release: id 3 | task 232 | stop processing: n_tokens = 114, truncated = 0 1.11.003.853 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.263 1.11.004.260 I slot launch_slot_: id 3 | task 238 | processing task, is_child = 0 1.11.005.363 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.236 1.11.005.400 I slot launch_slot_: id 0 | task 239 | processing task, is_child = 0 1.11.005.437 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.225 1.11.005.469 I slot launch_slot_: id 1 | task 240 | processing task, is_child = 0 1.11.005.489 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.177 1.11.005.643 I slot launch_slot_: id 2 | task 241 | processing task, is_child = 0 1.12.046.794 I slot print_timing: id 0 | task 239 | prompt eval time = 999.91 ms / 121 tokens ( 8.26 ms per token, 121.01 tokens per second) 1.12.046.797 I slot print_timing: id 0 | task 239 | eval time = 41.23 ms / 2 tokens ( 41.23 ms per token, 24.25 tokens per second) 1.12.046.798 I slot print_timing: id 0 | task 239 | total time = 1041.14 ms / 123 tokens 1.12.046.798 I slot print_timing: id 0 | task 239 | graphs reused = 1 1.12.046.799 I slot print_timing: id 0 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.046.819 I slot release: id 0 | task 239 | stop processing: n_tokens = 122, truncated = 0 1.12.047.101 I slot print_timing: id 1 | task 240 | prompt eval time = 1000.19 ms / 127 tokens ( 7.88 ms per token, 126.98 tokens per second) 1.12.047.103 I slot print_timing: id 1 | task 240 | eval time = 41.25 ms / 2 tokens ( 41.25 ms per token, 24.24 tokens per second) 1.12.047.103 I slot print_timing: id 1 | task 240 | total time = 1041.44 ms / 129 tokens 1.12.047.103 I slot print_timing: id 1 | task 240 | graphs reused = 1 1.12.047.104 I slot print_timing: id 1 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.047.116 I slot release: id 1 | task 240 | stop processing: n_tokens = 128, truncated = 0 1.12.047.411 I slot print_timing: id 2 | task 241 | prompt eval time = 1000.51 ms / 139 tokens ( 7.20 ms per token, 138.93 tokens per second) 1.12.047.413 I slot print_timing: id 2 | task 241 | eval time = 41.23 ms / 2 tokens ( 41.23 ms per token, 24.25 tokens per second) 1.12.047.413 I slot print_timing: id 2 | task 241 | total time = 1041.74 ms / 141 tokens 1.12.047.413 I slot print_timing: id 2 | task 241 | graphs reused = 1 1.12.047.413 I slot print_timing: id 2 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.047.426 I slot release: id 2 | task 241 | stop processing: n_tokens = 140, truncated = 0 1.12.047.720 I slot print_timing: id 3 | task 238 | prompt eval time = 1000.83 ms / 136 tokens ( 7.36 ms per token, 135.89 tokens per second) 1.12.047.723 I slot print_timing: id 3 | task 238 | eval time = 41.21 ms / 2 tokens ( 41.21 ms per token, 24.26 tokens per second) 1.12.047.724 I slot print_timing: id 3 | task 238 | total time = 1042.04 ms / 138 tokens 1.12.047.724 I slot print_timing: id 3 | task 238 | graphs reused = 1 1.12.047.724 I slot print_timing: id 3 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.047.754 I slot release: id 3 | task 238 | stop processing: n_tokens = 137, truncated = 0 1.12.052.238 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.238 1.12.052.701 I slot launch_slot_: id 0 | task 245 | processing task, is_child = 0 1.12.053.842 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.227 1.12.053.996 I slot launch_slot_: id 1 | task 246 | processing task, is_child = 0 1.12.054.037 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.207 1.12.054.070 I slot launch_slot_: id 2 | task 248 | processing task, is_child = 0 1.12.054.090 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.212 1.12.054.122 I slot launch_slot_: id 3 | task 247 | processing task, is_child = 0 1.13.290.609 I slot print_timing: id 0 | task 245 | prompt eval time = 1195.02 ms / 142 tokens ( 8.42 ms per token, 118.83 tokens per second) 1.13.290.611 I slot print_timing: id 0 | task 245 | eval time = 41.46 ms / 2 tokens ( 41.46 ms per token, 24.12 tokens per second) 1.13.290.612 I slot print_timing: id 0 | task 245 | total time = 1236.48 ms / 144 tokens 1.13.290.612 I slot print_timing: id 0 | task 245 | graphs reused = 1 1.13.290.613 I slot print_timing: id 0 | task 245 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.290.636 I slot release: id 0 | task 245 | stop processing: n_tokens = 143, truncated = 0 1.13.290.932 I slot print_timing: id 1 | task 246 | prompt eval time = 1195.31 ms / 159 tokens ( 7.52 ms per token, 133.02 tokens per second) 1.13.290.934 I slot print_timing: id 1 | task 246 | eval time = 41.48 ms / 2 tokens ( 41.48 ms per token, 24.11 tokens per second) 1.13.290.934 I slot print_timing: id 1 | task 246 | total time = 1236.79 ms / 161 tokens 1.13.290.935 I slot print_timing: id 1 | task 246 | graphs reused = 1 1.13.290.935 I slot print_timing: id 1 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.290.948 I slot release: id 1 | task 246 | stop processing: n_tokens = 160, truncated = 0 1.13.291.228 I slot print_timing: id 2 | task 248 | prompt eval time = 1195.60 ms / 170 tokens ( 7.03 ms per token, 142.19 tokens per second) 1.13.291.230 I slot print_timing: id 2 | task 248 | eval time = 41.48 ms / 2 tokens ( 41.48 ms per token, 24.11 tokens per second) 1.13.291.230 I slot print_timing: id 2 | task 248 | total time = 1237.08 ms / 172 tokens 1.13.291.230 I slot print_timing: id 2 | task 248 | graphs reused = 1 1.13.291.231 I slot print_timing: id 2 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.291.244 I slot release: id 2 | task 248 | stop processing: n_tokens = 171, truncated = 0 1.13.291.517 I slot print_timing: id 3 | task 247 | prompt eval time = 1195.94 ms / 120 tokens ( 9.97 ms per token, 100.34 tokens per second) 1.13.291.520 I slot print_timing: id 3 | task 247 | eval time = 41.41 ms / 2 tokens ( 41.41 ms per token, 24.15 tokens per second) 1.13.291.520 I slot print_timing: id 3 | task 247 | total time = 1237.36 ms / 122 tokens 1.13.291.520 I slot print_timing: id 3 | task 247 | graphs reused = 1 1.13.291.521 I slot print_timing: id 3 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.291.531 I slot release: id 3 | task 247 | stop processing: n_tokens = 121, truncated = 0 1.13.296.423 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.203 1.13.296.861 I slot launch_slot_: id 0 | task 252 | processing task, is_child = 0 1.13.298.147 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.181 1.13.298.330 I slot launch_slot_: id 1 | task 253 | processing task, is_child = 0 1.13.298.370 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.256 1.13.298.401 I slot launch_slot_: id 3 | task 254 | processing task, is_child = 0 1.13.298.420 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.170 1.13.298.454 I slot launch_slot_: id 2 | task 255 | processing task, is_child = 0 1.14.616.722 I slot print_timing: id 0 | task 252 | prompt eval time = 1276.81 ms / 103 tokens ( 12.40 ms per token, 80.67 tokens per second) 1.14.616.724 I slot print_timing: id 0 | task 252 | eval time = 41.45 ms / 2 tokens ( 41.45 ms per token, 24.13 tokens per second) 1.14.616.725 I slot print_timing: id 0 | task 252 | total time = 1318.25 ms / 105 tokens 1.14.616.725 I slot print_timing: id 0 | task 252 | graphs reused = 1 1.14.616.725 I slot print_timing: id 0 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.616.748 I slot release: id 0 | task 252 | stop processing: n_tokens = 104, truncated = 0 1.14.617.037 I slot print_timing: id 1 | task 253 | prompt eval time = 1277.09 ms / 134 tokens ( 9.53 ms per token, 104.93 tokens per second) 1.14.617.040 I slot print_timing: id 1 | task 253 | eval time = 41.47 ms / 2 tokens ( 41.47 ms per token, 24.12 tokens per second) 1.14.617.040 I slot print_timing: id 1 | task 253 | total time = 1318.56 ms / 136 tokens 1.14.617.040 I slot print_timing: id 1 | task 253 | graphs reused = 1 1.14.617.041 I slot print_timing: id 1 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.617.060 I slot release: id 1 | task 253 | stop processing: n_tokens = 135, truncated = 0 1.14.617.336 I slot print_timing: id 2 | task 255 | prompt eval time = 1277.38 ms / 158 tokens ( 8.08 ms per token, 123.69 tokens per second) 1.14.617.338 I slot print_timing: id 2 | task 255 | eval time = 41.46 ms / 2 tokens ( 41.46 ms per token, 24.12 tokens per second) 1.14.617.339 I slot print_timing: id 2 | task 255 | total time = 1318.84 ms / 160 tokens 1.14.617.339 I slot print_timing: id 2 | task 255 | graphs reused = 1 1.14.617.339 I slot print_timing: id 2 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.617.361 I slot release: id 2 | task 255 | stop processing: n_tokens = 159, truncated = 0 1.14.617.651 I slot print_timing: id 3 | task 254 | prompt eval time = 1277.88 ms / 184 tokens ( 6.95 ms per token, 143.99 tokens per second) 1.14.617.654 I slot print_timing: id 3 | task 254 | eval time = 41.26 ms / 2 tokens ( 41.26 ms per token, 24.24 tokens per second) 1.14.617.655 I slot print_timing: id 3 | task 254 | total time = 1319.14 ms / 186 tokens 1.14.617.655 I slot print_timing: id 3 | task 254 | graphs reused = 1 1.14.617.655 I slot print_timing: id 3 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.617.684 I slot release: id 3 | task 254 | stop processing: n_tokens = 185, truncated = 0 1.14.621.695 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.279 1.14.621.905 I slot launch_slot_: id 0 | task 259 | processing task, is_child = 0 1.14.623.142 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.215 1.14.623.187 I slot launch_slot_: id 1 | task 260 | processing task, is_child = 0 1.15.222.153 I slot print_timing: id 0 | task 259 | prompt eval time = 573.66 ms / 125 tokens ( 4.59 ms per token, 217.90 tokens per second) 1.15.222.157 I slot print_timing: id 0 | task 259 | eval time = 25.26 ms / 2 tokens ( 25.26 ms per token, 39.58 tokens per second) 1.15.222.158 I slot print_timing: id 0 | task 259 | total time = 598.92 ms / 127 tokens 1.15.222.159 I slot print_timing: id 0 | task 259 | graphs reused = 1 1.15.222.159 I slot print_timing: id 0 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.222.176 I slot release: id 0 | task 259 | stop processing: n_tokens = 126, truncated = 0 1.15.222.460 I slot print_timing: id 1 | task 260 | prompt eval time = 574.02 ms / 145 tokens ( 3.96 ms per token, 252.60 tokens per second) 1.15.222.461 I slot print_timing: id 1 | task 260 | eval time = 25.19 ms / 2 tokens ( 25.19 ms per token, 39.69 tokens per second) 1.15.222.462 I slot print_timing: id 1 | task 260 | total time = 599.22 ms / 147 tokens 1.15.222.462 I slot print_timing: id 1 | task 260 | graphs reused = 1 1.15.222.462 I slot print_timing: id 1 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.222.478 I slot release: id 1 | task 260 | stop processing: n_tokens = 146, truncated = 0 1.15.235.252 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 159, t_last = 335461985345 1.15.235.355 I slot launch_slot_: id 2 | task 264 | processing task, is_child = 0 1.15.236.057 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 185, t_last = 335461985667 1.15.236.093 I slot launch_slot_: id 3 | task 267 | processing task, is_child = 0 1.15.236.133 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 126, t_last = 335462590159 1.15.236.165 I slot launch_slot_: id 0 | task 266 | processing task, is_child = 0 1.15.236.184 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 146, t_last = 335462590461 1.15.236.217 I slot launch_slot_: id 1 | task 265 | processing task, is_child = 0 1.20.612.411 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 1149, progress = 1.00, t = 5.38 s / 213.72 tokens per second 1.20.835.954 I slot print_timing: id 1 | task 265 | prompt processing, n_tokens = 1129, progress = 1.00, t = 5.38 s / 210.00 tokens per second 1.20.836.152 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 1144, progress = 1.00, t = 5.38 s / 212.79 tokens per second 1.20.836.358 I slot print_timing: id 3 | task 267 | prompt processing, n_tokens = 643, progress = 0.55, t = 5.38 s / 119.60 tokens per second 1.21.602.085 I slot print_timing: id 3 | task 267 | prompt processing, n_tokens = 1155, progress = 1.00, t = 6.36 s / 181.46 tokens per second 1.25.738.961 I slot print_timing: id 0 | task 266 | n_gen = 100, tg = 23.93 t/s, tg_3s = 24.17 t/s 1.25.739.489 I slot print_timing: id 1 | task 265 | n_gen = 100, tg = 23.93 t/s, tg_3s = 24.17 t/s 1.25.740.071 I slot print_timing: id 2 | task 264 | n_gen = 100, tg = 23.92 t/s, tg_3s = 24.17 t/s 1.25.782.248 I slot print_timing: id 3 | task 267 | n_gen = 100, tg = 24.10 t/s, tg_3s = 24.34 t/s 1.28.775.268 I slot print_timing: id 0 | task 266 | n_gen = 173, tg = 23.98 t/s, tg_3s = 24.04 t/s 1.28.775.924 I slot print_timing: id 1 | task 265 | n_gen = 173, tg = 23.97 t/s, tg_3s = 24.04 t/s 1.28.776.581 I slot print_timing: id 2 | task 264 | n_gen = 173, tg = 23.97 t/s, tg_3s = 24.04 t/s 1.28.818.867 I slot print_timing: id 3 | task 267 | n_gen = 173, tg = 24.07 t/s, tg_3s = 24.04 t/s 1.31.815.401 I slot print_timing: id 0 | task 266 | n_gen = 246, tg = 23.99 t/s, tg_3s = 24.01 t/s 1.31.816.034 I slot print_timing: id 1 | task 265 | n_gen = 246, tg = 23.99 t/s, tg_3s = 24.01 t/s 1.31.816.724 I slot print_timing: id 2 | task 264 | n_gen = 246, tg = 23.99 t/s, tg_3s = 24.01 t/s 1.31.858.988 I slot print_timing: id 3 | task 267 | n_gen = 246, tg = 24.06 t/s, tg_3s = 24.01 t/s 1.33.442.795 I slot print_timing: id 2 | task 264 | prompt eval time = 6365.81 ms / 1148 tokens ( 5.55 ms per token, 180.34 tokens per second) 1.33.442.799 I slot print_timing: id 2 | task 264 | eval time = 11840.73 ms / 285 tokens ( 41.69 ms per token, 23.99 tokens per second) 1.33.442.800 I slot print_timing: id 2 | task 264 | total time = 18206.54 ms / 1433 tokens 1.33.442.801 I slot print_timing: id 2 | task 264 | graphs reused = 284 1.33.442.801 I slot print_timing: id 2 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.442.906 I slot release: id 2 | task 264 | stop processing: n_tokens = 1432, truncated = 0 1.33.486.282 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.746 1.33.486.319 I slot launch_slot_: id 2 | task 556 | processing task, is_child = 0 1.34.826.567 I slot print_timing: id 0 | task 266 | n_gen = 298, tg = 22.46 t/s, tg_3s = 17.27 t/s 1.34.827.254 I slot print_timing: id 1 | task 265 | n_gen = 298, tg = 22.46 t/s, tg_3s = 17.27 t/s 1.34.870.686 I slot print_timing: id 3 | task 267 | n_gen = 298, tg = 22.51 t/s, tg_3s = 17.27 t/s 1.37.036.188 I slot print_timing: id 1 | task 265 | prompt eval time = 6365.53 ms / 1133 tokens ( 5.62 ms per token, 177.99 tokens per second) 1.37.036.194 I slot print_timing: id 1 | task 265 | eval time = 15434.41 ms / 351 tokens ( 44.10 ms per token, 22.68 tokens per second) 1.37.036.195 I slot print_timing: id 1 | task 265 | total time = 21799.94 ms / 1484 tokens 1.37.036.195 I slot print_timing: id 1 | task 265 | graphs reused = 345 1.37.036.196 I slot print_timing: id 1 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.036.316 I slot release: id 1 | task 265 | stop processing: n_tokens = 1483, truncated = 0 1.37.081.197 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.720 1.37.081.240 I slot launch_slot_: id 1 | task 623 | processing task, is_child = 0 1.38.030.627 I slot print_timing: id 0 | task 266 | n_gen = 354, tg = 21.49 t/s, tg_3s = 17.48 t/s 1.38.031.191 I slot print_timing: id 3 | task 267 | n_gen = 353, tg = 21.52 t/s, tg_3s = 17.40 t/s 1.39.490.600 I slot print_timing: id 2 | task 556 | n_gen = 100, tg = 19.66 t/s, tg_3s = 19.86 t/s 1.41.070.349 I slot print_timing: id 0 | task 266 | n_gen = 426, tg = 21.83 t/s, tg_3s = 23.69 t/s 1.41.072.137 I slot print_timing: id 3 | task 267 | n_gen = 425, tg = 21.86 t/s, tg_3s = 23.68 t/s 1.42.237.668 I slot print_timing: id 1 | task 623 | n_gen = 100, tg = 23.99 t/s, tg_3s = 24.23 t/s 1.42.530.343 I slot print_timing: id 2 | task 556 | n_gen = 173, tg = 21.30 t/s, tg_3s = 24.02 t/s 1.44.109.373 I slot print_timing: id 0 | task 266 | n_gen = 499, tg = 22.13 t/s, tg_3s = 24.02 t/s 1.44.111.048 I slot print_timing: id 3 | task 267 | n_gen = 498, tg = 22.15 t/s, tg_3s = 24.02 t/s 1.45.238.011 I slot print_timing: id 1 | task 623 | n_gen = 172, tg = 23.99 t/s, tg_3s = 24.00 t/s 1.45.531.289 I slot print_timing: id 2 | task 556 | n_gen = 245, tg = 22.03 t/s, tg_3s = 23.99 t/s 1.47.113.870 I slot print_timing: id 0 | task 266 | n_gen = 571, tg = 22.34 t/s, tg_3s = 23.96 t/s 1.47.115.747 I slot print_timing: id 3 | task 267 | n_gen = 570, tg = 22.37 t/s, tg_3s = 23.96 t/s 1.48.239.715 I slot print_timing: id 1 | task 623 | n_gen = 244, tg = 23.99 t/s, tg_3s = 23.99 t/s 1.48.531.418 I slot print_timing: id 2 | task 556 | n_gen = 317, tg = 22.45 t/s, tg_3s = 24.00 t/s 1.49.654.152 I slot print_timing: id 0 | task 266 | prompt eval time = 6365.25 ms / 1153 tokens ( 5.52 ms per token, 181.14 tokens per second) 1.49.654.156 I slot print_timing: id 0 | task 266 | eval time = 28052.67 ms / 632 tokens ( 44.46 ms per token, 22.49 tokens per second) 1.49.654.156 I slot print_timing: id 0 | task 266 | total time = 34417.92 ms / 1785 tokens 1.49.654.157 I slot print_timing: id 0 | task 266 | graphs reused = 620 1.49.654.158 I slot print_timing: id 0 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.654.256 I slot release: id 0 | task 266 | stop processing: n_tokens = 1784, truncated = 0 1.49.691.704 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.599 1.49.691.743 I slot launch_slot_: id 0 | task 905 | processing task, is_child = 0 1.50.585.930 I slot print_timing: id 3 | task 267 | n_gen = 634, tg = 21.89 t/s, tg_3s = 18.44 t/s 1.51.277.746 I slot print_timing: id 1 | task 623 | n_gen = 297, tg = 22.48 t/s, tg_3s = 17.45 t/s 1.51.570.742 I slot print_timing: id 2 | task 556 | n_gen = 370, tg = 21.56 t/s, tg_3s = 17.44 t/s 1.53.613.706 I slot print_timing: id 3 | task 267 | n_gen = 706, tg = 22.07 t/s, tg_3s = 23.78 t/s 1.54.279.194 I slot print_timing: id 1 | task 623 | n_gen = 369, tg = 22.76 t/s, tg_3s = 23.99 t/s 1.54.571.168 I slot print_timing: id 2 | task 556 | n_gen = 442, tg = 21.92 t/s, tg_3s = 24.00 t/s 1.54.778.573 I slot print_timing: id 0 | task 905 | n_gen = 100, tg = 24.01 t/s, tg_3s = 24.26 t/s 1.56.651.911 I slot print_timing: id 3 | task 267 | n_gen = 779, tg = 22.24 t/s, tg_3s = 24.03 t/s 1.57.316.913 I slot print_timing: id 1 | task 623 | n_gen = 442, tg = 22.96 t/s, tg_3s = 24.03 t/s 1.57.609.310 I slot print_timing: id 2 | task 556 | n_gen = 515, tg = 22.20 t/s, tg_3s = 24.03 t/s 1.57.816.656 I slot print_timing: id 0 | task 905 | n_gen = 173, tg = 24.02 t/s, tg_3s = 24.03 t/s 1.58.359.124 I slot print_timing: id 2 | task 556 | prompt eval time = 968.97 ms / 539 tokens ( 1.80 ms per token, 556.26 tokens per second) 1.58.359.131 I slot print_timing: id 2 | task 556 | eval time = 23903.83 ms / 533 tokens ( 44.93 ms per token, 22.26 tokens per second) 1.58.359.132 I slot print_timing: id 2 | task 556 | total time = 24872.80 ms / 1072 tokens 1.58.359.133 I slot print_timing: id 2 | task 556 | graphs reused = 805 1.58.359.134 I slot print_timing: id 2 | task 556 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.359.234 I slot release: id 2 | task 556 | stop processing: n_tokens = 1703, truncated = 0 1.58.402.588 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.627 1.58.402.638 I slot launch_slot_: id 2 | task 1095 | processing task, is_child = 0 1.59.662.172 I slot print_timing: id 3 | task 267 | n_gen = 835, tg = 21.95 t/s, tg_3s = 18.60 t/s 2.00.329.411 I slot print_timing: id 1 | task 623 | n_gen = 498, tg = 22.37 t/s, tg_3s = 18.59 t/s 2.00.828.748 I slot print_timing: id 0 | task 905 | n_gen = 229, tg = 22.41 t/s, tg_3s = 18.59 t/s 2.02.671.643 I slot print_timing: id 3 | task 267 | n_gen = 906, tg = 22.07 t/s, tg_3s = 23.59 t/s 2.03.337.153 I slot print_timing: id 1 | task 623 | n_gen = 569, tg = 22.52 t/s, tg_3s = 23.61 t/s 2.03.337.846 I slot print_timing: id 2 | task 1095 | n_gen = 100, tg = 23.73 t/s, tg_3s = 23.97 t/s 2.03.837.510 I slot print_timing: id 0 | task 905 | n_gen = 300, tg = 22.68 t/s, tg_3s = 23.60 t/s 2.05.679.524 I slot print_timing: id 3 | task 267 | n_gen = 978, tg = 22.20 t/s, tg_3s = 23.94 t/s 2.06.346.268 I slot print_timing: id 1 | task 623 | n_gen = 641, tg = 22.67 t/s, tg_3s = 23.93 t/s 2.06.346.888 I slot print_timing: id 2 | task 1095 | n_gen = 172, tg = 23.81 t/s, tg_3s = 23.93 t/s 2.06.847.681 I slot print_timing: id 0 | task 905 | n_gen = 372, tg = 22.91 t/s, tg_3s = 23.92 t/s 2.07.603.626 I slot print_timing: id 3 | task 267 | prompt eval time = 6438.17 ms / 1159 tokens ( 5.55 ms per token, 180.02 tokens per second) 2.07.603.633 I slot print_timing: id 3 | task 267 | eval time = 45929.18 ms / 1024 tokens ( 44.90 ms per token, 22.27 tokens per second) 2.07.603.634 I slot print_timing: id 3 | task 267 | total time = 52367.35 ms / 2183 tokens 2.07.603.635 I slot print_timing: id 3 | task 267 | graphs reused = 1004 2.07.603.635 I slot print_timing: id 3 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.603.735 I slot release: id 3 | task 267 | stop processing: n_tokens = 2182, truncated = 0 2.07.639.900 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.489 2.07.645.555 I slot launch_slot_: id 3 | task 1300 | processing task, is_child = 0 2.09.363.148 I slot print_timing: id 1 | task 623 | n_gen = 693, tg = 22.14 t/s, tg_3s = 17.24 t/s 2.09.363.698 I slot print_timing: id 2 | task 1095 | n_gen = 224, tg = 21.87 t/s, tg_3s = 17.24 t/s 2.09.862.162 I slot print_timing: id 0 | task 905 | n_gen = 424, tg = 22.02 t/s, tg_3s = 17.25 t/s 2.12.364.225 I slot print_timing: id 1 | task 623 | n_gen = 765, tg = 22.30 t/s, tg_3s = 23.99 t/s 2.12.364.786 I slot print_timing: id 2 | task 1095 | n_gen = 296, tg = 22.35 t/s, tg_3s = 23.99 t/s 2.12.740.854 I slot print_timing: id 3 | task 1300 | n_gen = 100, tg = 24.01 t/s, tg_3s = 24.25 t/s 2.12.864.542 I slot print_timing: id 0 | task 905 | n_gen = 496, tg = 22.29 t/s, tg_3s = 23.98 t/s 2.15.365.213 I slot print_timing: id 1 | task 623 | n_gen = 837, tg = 22.44 t/s, tg_3s = 23.99 t/s 2.15.365.773 I slot print_timing: id 2 | task 1095 | n_gen = 368, tg = 22.66 t/s, tg_3s = 23.99 t/s 2.15.782.242 I slot print_timing: id 3 | task 1300 | n_gen = 173, tg = 24.00 t/s, tg_3s = 24.00 t/s 2.15.905.883 I slot print_timing: id 0 | task 905 | n_gen = 569, tg = 22.50 t/s, tg_3s = 24.00 t/s 2.16.825.205 I slot print_timing: id 0 | task 905 | prompt eval time = 964.24 ms / 544 tokens ( 1.77 ms per token, 564.17 tokens per second) 2.16.825.212 I slot print_timing: id 0 | task 905 | eval time = 26169.21 ms / 591 tokens ( 44.35 ms per token, 22.55 tokens per second) 2.16.825.213 I slot print_timing: id 0 | task 905 | total time = 27133.45 ms / 1135 tokens 2.16.825.214 I slot print_timing: id 0 | task 905 | graphs reused = 1199 2.16.825.214 I slot print_timing: id 0 | task 905 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.825.322 I slot release: id 0 | task 905 | stop processing: n_tokens = 1771, truncated = 0 2.16.862.456 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.603 2.16.862.486 I slot launch_slot_: id 0 | task 1502 | processing task, is_child = 0 2.18.370.545 I slot print_timing: id 1 | task 623 | n_gen = 889, tg = 22.06 t/s, tg_3s = 17.30 t/s 2.18.370.852 I slot print_timing: id 2 | task 1095 | n_gen = 420, tg = 21.82 t/s, tg_3s = 17.30 t/s 2.18.791.431 I slot print_timing: id 3 | task 1300 | n_gen = 225, tg = 22.02 t/s, tg_3s = 17.28 t/s 2.21.384.817 I slot print_timing: id 1 | task 623 | n_gen = 961, tg = 22.18 t/s, tg_3s = 23.89 t/s 2.21.385.316 I slot print_timing: id 2 | task 1095 | n_gen = 492, tg = 22.10 t/s, tg_3s = 23.88 t/s 2.21.801.651 I slot print_timing: id 3 | task 1300 | n_gen = 297, tg = 22.45 t/s, tg_3s = 23.92 t/s 2.21.967.299 I slot print_timing: id 0 | task 1502 | n_gen = 100, tg = 23.97 t/s, tg_3s = 24.21 t/s 2.23.759.466 I slot print_timing: id 2 | task 1095 | prompt eval time = 763.70 ms / 500 tokens ( 1.53 ms per token, 654.71 tokens per second) 2.23.759.473 I slot print_timing: id 2 | task 1095 | eval time = 24593.12 ms / 549 tokens ( 44.88 ms per token, 22.28 tokens per second) 2.23.759.474 I slot print_timing: id 2 | task 1095 | total time = 25356.82 ms / 1049 tokens 2.23.759.474 I slot print_timing: id 2 | task 1095 | graphs reused = 1341 2.23.759.475 I slot print_timing: id 2 | task 1095 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.759.608 I slot release: id 2 | task 1095 | stop processing: n_tokens = 1703, truncated = 0 2.23.803.348 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.627 2.23.803.391 I slot launch_slot_: id 2 | task 1649 | processing task, is_child = 0 2.24.498.143 I slot print_timing: id 1 | task 623 | n_gen = 1020, tg = 21.97 t/s, tg_3s = 18.95 t/s 2.24.700.778 I slot print_timing: id 1 | task 623 | prompt eval time = 1029.84 ms / 563 tokens ( 1.83 ms per token, 546.69 tokens per second) 2.24.700.783 I slot print_timing: id 1 | task 623 | eval time = 46589.69 ms / 1024 tokens ( 45.54 ms per token, 21.96 tokens per second) 2.24.700.783 I slot print_timing: id 1 | task 623 | total time = 47619.53 ms / 1587 tokens 2.24.700.784 I slot print_timing: id 1 | task 623 | graphs reused = 1343 2.24.700.784 I slot print_timing: id 1 | task 623 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.700.847 I slot release: id 1 | task 623 | stop processing: n_tokens = 2203, truncated = 0 2.24.742.860 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.485 2.24.747.666 I slot launch_slot_: id 1 | task 1656 | processing task, is_child = 0 2.25.408.176 I slot print_timing: id 0 | task 1502 | n_gen = 151, tg = 19.81 t/s, tg_3s = 14.82 t/s 2.25.408.777 I slot print_timing: id 3 | task 1300 | n_gen = 352, tg = 20.90 t/s, tg_3s = 15.25 t/s 2.28.437.331 I slot print_timing: id 0 | task 1502 | n_gen = 223, tg = 20.94 t/s, tg_3s = 23.77 t/s 2.28.438.879 I slot print_timing: id 3 | task 1300 | n_gen = 424, tg = 21.34 t/s, tg_3s = 23.76 t/s 2.29.346.381 I slot print_timing: id 2 | task 1649 | n_gen = 100, tg = 20.76 t/s, tg_3s = 20.97 t/s 2.29.594.206 I slot print_timing: id 1 | task 1656 | n_gen = 100, tg = 24.11 t/s, tg_3s = 24.35 t/s 2.31.465.740 I slot print_timing: id 0 | task 1502 | n_gen = 296, tg = 21.64 t/s, tg_3s = 24.11 t/s 2.31.467.458 I slot print_timing: id 3 | task 1300 | n_gen = 497, tg = 21.71 t/s, tg_3s = 24.10 t/s 2.32.382.638 I slot print_timing: id 2 | task 1649 | n_gen = 173, tg = 22.04 t/s, tg_3s = 24.04 t/s 2.32.632.413 I slot print_timing: id 1 | task 1656 | n_gen = 173, tg = 24.08 t/s, tg_3s = 24.03 t/s 2.34.502.705 I slot print_timing: id 0 | task 1502 | n_gen = 369, tg = 22.08 t/s, tg_3s = 24.04 t/s 2.34.504.322 I slot print_timing: id 3 | task 1300 | n_gen = 570, tg = 21.98 t/s, tg_3s = 24.04 t/s 2.35.419.735 I slot print_timing: id 2 | task 1649 | n_gen = 246, tg = 22.60 t/s, tg_3s = 24.04 t/s 2.35.669.239 I slot print_timing: id 1 | task 1656 | n_gen = 246, tg = 24.06 t/s, tg_3s = 24.04 t/s 2.37.505.825 I slot print_timing: id 0 | task 1502 | n_gen = 441, tg = 22.37 t/s, tg_3s = 23.98 t/s 2.37.507.549 I slot print_timing: id 3 | task 1300 | n_gen = 642, tg = 22.19 t/s, tg_3s = 23.97 t/s 2.38.421.928 I slot print_timing: id 2 | task 1649 | n_gen = 318, tg = 22.90 t/s, tg_3s = 23.98 t/s 2.38.671.992 I slot print_timing: id 1 | task 1656 | n_gen = 318, tg = 24.04 t/s, tg_3s = 23.98 t/s 2.40.545.361 I slot print_timing: id 0 | task 1502 | n_gen = 514, tg = 22.59 t/s, tg_3s = 24.02 t/s 2.40.547.057 I slot print_timing: id 3 | task 1300 | n_gen = 715, tg = 22.36 t/s, tg_3s = 24.02 t/s 2.41.424.204 I slot print_timing: id 2 | task 1649 | n_gen = 390, tg = 23.09 t/s, tg_3s = 23.98 t/s 2.41.675.464 I slot print_timing: id 1 | task 1656 | n_gen = 390, tg = 24.03 t/s, tg_3s = 23.97 t/s 2.43.551.374 I slot print_timing: id 0 | task 1502 | n_gen = 586, tg = 22.75 t/s, tg_3s = 23.95 t/s 2.43.552.992 I slot print_timing: id 3 | task 1300 | n_gen = 787, tg = 22.50 t/s, tg_3s = 23.95 t/s 2.44.429.351 I slot print_timing: id 2 | task 1649 | n_gen = 462, tg = 23.22 t/s, tg_3s = 23.96 t/s 2.44.679.219 I slot print_timing: id 1 | task 1656 | n_gen = 462, tg = 24.02 t/s, tg_3s = 23.97 t/s 2.46.553.144 I slot print_timing: id 0 | task 1502 | n_gen = 658, tg = 22.88 t/s, tg_3s = 23.99 t/s 2.46.554.806 I slot print_timing: id 3 | task 1300 | n_gen = 859, tg = 22.62 t/s, tg_3s = 23.99 t/s 2.47.430.671 I slot print_timing: id 2 | task 1649 | n_gen = 534, tg = 23.32 t/s, tg_3s = 23.99 t/s 2.47.681.324 I slot print_timing: id 1 | task 1656 | n_gen = 534, tg = 24.02 t/s, tg_3s = 23.98 t/s 2.48.350.857 I slot print_timing: id 0 | task 1502 | prompt eval time = 974.20 ms / 546 tokens ( 1.78 ms per token, 560.46 tokens per second) 2.48.350.864 I slot print_timing: id 0 | task 1502 | eval time = 30514.16 ms / 701 tokens ( 43.59 ms per token, 22.94 tokens per second) 2.48.350.865 I slot print_timing: id 0 | task 1502 | total time = 31488.36 ms / 1247 tokens 2.48.350.865 I slot print_timing: id 0 | task 1502 | graphs reused = 1889 2.48.350.866 I slot print_timing: id 0 | task 1502 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.350.974 I slot release: id 0 | task 1502 | stop processing: n_tokens = 1911, truncated = 0 2.48.389.316 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.559 2.48.389.360 I slot launch_slot_: id 0 | task 2209 | processing task, is_child = 0 2.49.566.390 I slot print_timing: id 3 | task 1300 | n_gen = 917, tg = 22.37 t/s, tg_3s = 19.26 t/s 2.49.648.146 I slot print_timing: id 2 | task 1649 | prompt eval time = 773.90 ms / 513 tokens ( 1.51 ms per token, 662.88 tokens per second) 2.49.648.153 I slot print_timing: id 2 | task 1649 | eval time = 25070.85 ms / 573 tokens ( 43.83 ms per token, 22.82 tokens per second) 2.49.648.154 I slot print_timing: id 2 | task 1649 | total time = 25844.75 ms / 1086 tokens 2.49.648.155 I slot print_timing: id 2 | task 1649 | graphs reused = 1903 2.49.648.156 I slot print_timing: id 2 | task 1649 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.648.273 I slot release: id 2 | task 1649 | stop processing: n_tokens = 1740, truncated = 0 2.49.694.152 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.614 2.49.694.225 I slot launch_slot_: id 2 | task 2227 | processing task, is_child = 0 2.50.701.014 I slot print_timing: id 1 | task 1656 | n_gen = 576, tg = 22.81 t/s, tg_3s = 13.91 t/s 2.52.037.244 I slot print_timing: id 3 | task 1300 | prompt eval time = 971.22 ms / 543 tokens ( 1.79 ms per token, 559.09 tokens per second) 2.52.037.251 I slot print_timing: id 3 | task 1300 | eval time = 43420.45 ms / 960 tokens ( 45.28 ms per token, 22.09 tokens per second) 2.52.037.252 I slot print_timing: id 3 | task 1300 | total time = 44391.68 ms / 1503 tokens 2.52.037.253 I slot print_timing: id 3 | task 1300 | graphs reused = 1940 2.52.037.253 I slot print_timing: id 3 | task 1300 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.037.392 I slot release: id 3 | task 1300 | stop processing: n_tokens = 2145, truncated = 0 2.52.073.544 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.498 2.52.079.120 I slot launch_slot_: id 3 | task 2269 | processing task, is_child = 0 2.53.741.812 I slot print_timing: id 1 | task 1656 | n_gen = 633, tg = 22.37 t/s, tg_3s = 18.75 t/s 2.54.532.236 I slot print_timing: id 0 | task 2209 | n_gen = 100, tg = 18.14 t/s, tg_3s = 18.32 t/s 2.55.241.328 I slot print_timing: id 2 | task 2227 | n_gen = 100, tg = 20.65 t/s, tg_3s = 20.86 t/s 2.56.782.676 I slot print_timing: id 1 | task 1656 | n_gen = 706, tg = 22.53 t/s, tg_3s = 24.01 t/s 2.56.950.197 I slot print_timing: id 3 | task 2269 | n_gen = 100, tg = 24.03 t/s, tg_3s = 24.27 t/s 2.57.571.628 I slot print_timing: id 0 | task 2209 | n_gen = 173, tg = 20.24 t/s, tg_3s = 24.02 t/s 2.57.904.615 I slot print_timing: id 1 | task 1656 | prompt eval time = 740.47 ms / 481 tokens ( 1.54 ms per token, 649.58 tokens per second) 2.57.904.624 I slot print_timing: id 1 | task 1656 | eval time = 32416.47 ms / 733 tokens ( 44.28 ms per token, 22.58 tokens per second) 2.57.904.625 I slot print_timing: id 1 | task 1656 | total time = 33156.94 ms / 1214 tokens 2.57.904.626 I slot print_timing: id 1 | task 1656 | graphs reused = 2060 2.57.904.626 I slot print_timing: id 1 | task 1656 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.904.752 I slot release: id 1 | task 1656 | stop processing: n_tokens = 1877, truncated = 0 2.57.948.846 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.569 2.57.948.892 I slot launch_slot_: id 1 | task 2395 | processing task, is_child = 0 2.58.772.139 I slot print_timing: id 2 | task 2227 | n_gen = 167, tg = 19.94 t/s, tg_3s = 18.98 t/s 2.59.979.838 I slot print_timing: id 3 | task 2269 | n_gen = 154, tg = 21.40 t/s, tg_3s = 17.82 t/s 3.00.602.886 I slot print_timing: id 0 | task 2209 | n_gen = 227, tg = 19.60 t/s, tg_3s = 17.81 t/s 3.01.812.269 I slot print_timing: id 2 | task 2227 | n_gen = 239, tg = 20.94 t/s, tg_3s = 23.68 t/s 3.02.978.998 I slot print_timing: id 1 | task 2395 | n_gen = 100, tg = 23.98 t/s, tg_3s = 24.23 t/s 3.02.980.167 I slot print_timing: id 3 | task 2269 | n_gen = 226, tg = 22.17 t/s, tg_3s = 24.00 t/s 3.03.644.244 I slot print_timing: id 0 | task 2209 | n_gen = 300, tg = 20.52 t/s, tg_3s = 24.00 t/s 3.04.813.969 I slot print_timing: id 2 | task 2227 | n_gen = 311, tg = 21.58 t/s, tg_3s = 23.99 t/s 3.05.979.135 I slot print_timing: id 1 | task 2395 | n_gen = 172, tg = 23.99 t/s, tg_3s = 24.00 t/s 3.05.980.233 I slot print_timing: id 3 | task 2269 | n_gen = 298, tg = 22.58 t/s, tg_3s = 24.00 t/s 3.06.644.754 I slot print_timing: id 0 | task 2209 | n_gen = 372, tg = 21.11 t/s, tg_3s = 24.00 t/s 3.07.855.621 I slot print_timing: id 2 | task 2227 | n_gen = 384, tg = 22.00 t/s, tg_3s = 24.00 t/s 3.08.981.289 I slot print_timing: id 1 | task 2395 | n_gen = 244, tg = 23.99 t/s, tg_3s = 23.98 t/s 3.08.982.478 I slot print_timing: id 3 | task 2269 | n_gen = 370, tg = 22.84 t/s, tg_3s = 23.98 t/s 3.09.645.462 I slot print_timing: id 0 | task 2209 | n_gen = 444, tg = 21.53 t/s, tg_3s = 23.99 t/s 3.10.895.697 I slot print_timing: id 2 | task 2227 | n_gen = 457, tg = 22.30 t/s, tg_3s = 24.01 t/s 3.11.767.879 I slot print_timing: id 3 | task 2269 | prompt eval time = 750.62 ms / 496 tokens ( 1.51 ms per token, 660.78 tokens per second) 3.11.767.886 I slot print_timing: id 3 | task 2269 | eval time = 18938.12 ms / 437 tokens ( 43.44 ms per token, 23.02 tokens per second) 3.11.767.887 I slot print_timing: id 3 | task 2269 | total time = 19688.74 ms / 933 tokens 3.11.767.888 I slot print_timing: id 3 | task 2269 | graphs reused = 2368 3.11.767.889 I slot print_timing: id 3 | task 2269 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.768.016 I slot release: id 3 | task 2269 | stop processing: n_tokens = 1602, truncated = 0 3.11.804.255 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.667 3.11.804.304 I slot launch_slot_: id 3 | task 2710 | processing task, is_child = 0 3.12.444.737 I slot print_timing: id 1 | task 2395 | n_gen = 313, tg = 22.95 t/s, tg_3s = 19.92 t/s 3.12.681.395 I slot print_timing: id 0 | task 2209 | n_gen = 502, tg = 21.22 t/s, tg_3s = 19.10 t/s 3.13.925.073 I slot print_timing: id 2 | task 2227 | n_gen = 515, tg = 21.89 t/s, tg_3s = 19.15 t/s 3.15.462.498 I slot print_timing: id 1 | task 2395 | n_gen = 385, tg = 23.12 t/s, tg_3s = 23.86 t/s 3.15.712.182 I slot print_timing: id 0 | task 2209 | n_gen = 575, tg = 21.55 t/s, tg_3s = 24.09 t/s 3.16.254.509 I slot print_timing: id 2 | task 2227 | prompt eval time = 753.42 ms / 482 tokens ( 1.56 ms per token, 639.75 tokens per second) 3.16.254.516 I slot print_timing: id 2 | task 2227 | eval time = 25806.83 ms / 571 tokens ( 45.28 ms per token, 22.09 tokens per second) 3.16.254.517 I slot print_timing: id 2 | task 2227 | total time = 26560.25 ms / 1053 tokens 3.16.254.518 I slot print_timing: id 2 | task 2227 | graphs reused = 2457 3.16.254.518 I slot print_timing: id 2 | task 2227 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.254.645 I slot release: id 2 | task 2227 | stop processing: n_tokens = 1707, truncated = 0 3.16.298.395 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.626 3.16.298.430 I slot launch_slot_: id 2 | task 2804 | processing task, is_child = 0 3.17.320.250 I slot print_timing: id 3 | task 2710 | n_gen = 100, tg = 20.61 t/s, tg_3s = 20.82 t/s 3.18.487.420 I slot print_timing: id 1 | task 2395 | n_gen = 441, tg = 22.41 t/s, tg_3s = 18.51 t/s 3.18.739.117 I slot print_timing: id 0 | task 2209 | n_gen = 631, tg = 21.24 t/s, tg_3s = 18.50 t/s 3.20.327.811 I slot print_timing: id 3 | task 2710 | n_gen = 172, tg = 21.89 t/s, tg_3s = 23.94 t/s 3.21.204.069 I slot print_timing: id 2 | task 2804 | n_gen = 100, tg = 23.97 t/s, tg_3s = 24.21 t/s 3.21.494.940 I slot print_timing: id 1 | task 2395 | n_gen = 513, tg = 22.61 t/s, tg_3s = 23.94 t/s 3.21.744.237 I slot print_timing: id 0 | task 2209 | n_gen = 703, tg = 21.49 t/s, tg_3s = 23.96 t/s 3.23.369.424 I slot print_timing: id 3 | task 2710 | n_gen = 245, tg = 22.48 t/s, tg_3s = 24.00 t/s 3.24.243.886 I slot print_timing: id 2 | task 2804 | n_gen = 173, tg = 23.99 t/s, tg_3s = 24.01 t/s 3.24.535.154 I slot print_timing: id 1 | task 2395 | n_gen = 586, tg = 22.78 t/s, tg_3s = 24.01 t/s 3.24.785.254 I slot print_timing: id 0 | task 2209 | n_gen = 776, tg = 21.70 t/s, tg_3s = 24.01 t/s 3.26.375.543 I slot print_timing: id 3 | task 2710 | n_gen = 317, tg = 22.80 t/s, tg_3s = 23.95 t/s 3.27.250.702 I slot print_timing: id 2 | task 2804 | n_gen = 245, tg = 23.98 t/s, tg_3s = 23.95 t/s 3.27.541.242 I slot print_timing: id 1 | task 2395 | n_gen = 658, tg = 22.90 t/s, tg_3s = 23.95 t/s 3.27.790.600 I slot print_timing: id 0 | task 2209 | n_gen = 848, tg = 21.88 t/s, tg_3s = 23.96 t/s 3.29.379.519 I slot print_timing: id 3 | task 2710 | n_gen = 389, tg = 23.01 t/s, tg_3s = 23.97 t/s 3.30.258.951 I slot print_timing: id 2 | task 2804 | n_gen = 317, tg = 23.97 t/s, tg_3s = 23.93 t/s 3.30.551.393 I slot print_timing: id 1 | task 2395 | n_gen = 730, tg = 23.00 t/s, tg_3s = 23.92 t/s 3.30.801.117 I slot print_timing: id 0 | task 2209 | n_gen = 920, tg = 22.02 t/s, tg_3s = 23.92 t/s 3.32.388.820 I slot print_timing: id 3 | task 2710 | n_gen = 461, tg = 23.15 t/s, tg_3s = 23.93 t/s 3.33.265.681 I slot print_timing: id 2 | task 2804 | n_gen = 389, tg = 23.96 t/s, tg_3s = 23.95 t/s 3.33.557.507 I slot print_timing: id 1 | task 2395 | n_gen = 802, tg = 23.08 t/s, tg_3s = 23.95 t/s 3.33.808.556 I slot print_timing: id 0 | task 2209 | n_gen = 992, tg = 22.15 t/s, tg_3s = 23.94 t/s 3.35.152.811 I slot print_timing: id 0 | task 2209 | prompt eval time = 684.47 ms / 448 tokens ( 1.53 ms per token, 654.52 tokens per second) 3.35.152.815 I slot print_timing: id 0 | task 2209 | eval time = 46078.97 ms / 1024 tokens ( 45.04 ms per token, 22.20 tokens per second) 3.35.152.816 I slot print_timing: id 0 | task 2209 | total time = 46763.44 ms / 1472 tokens 3.35.152.817 I slot print_timing: id 0 | task 2209 | graphs reused = 2887 3.35.152.818 I slot print_timing: id 0 | task 2209 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.152.916 I slot release: id 0 | task 2209 | stop processing: n_tokens = 2166, truncated = 0 3.35.190.789 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.493 3.35.196.619 I slot launch_slot_: id 0 | task 3241 | processing task, is_child = 0 3.35.809.425 I slot print_timing: id 3 | task 2710 | n_gen = 529, tg = 22.67 t/s, tg_3s = 19.88 t/s 3.36.288.466 I slot print_timing: id 2 | task 2804 | n_gen = 447, tg = 23.21 t/s, tg_3s = 19.19 t/s 3.36.577.186 I slot print_timing: id 1 | task 2395 | n_gen = 860, tg = 22.77 t/s, tg_3s = 19.21 t/s 3.38.834.285 I slot print_timing: id 3 | task 2710 | n_gen = 601, tg = 22.80 t/s, tg_3s = 23.80 t/s 3.38.875.860 I slot print_timing: id 3 | task 2710 | prompt eval time = 713.35 ms / 458 tokens ( 1.56 ms per token, 642.04 tokens per second) 3.38.875.868 I slot print_timing: id 3 | task 2710 | eval time = 26358.20 ms / 602 tokens ( 43.86 ms per token, 22.80 tokens per second) 3.38.875.869 I slot print_timing: id 3 | task 2710 | total time = 27071.55 ms / 1060 tokens 3.38.875.869 I slot print_timing: id 3 | task 2710 | graphs reused = 2958 3.38.875.870 I slot print_timing: id 3 | task 2710 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.875.987 I slot release: id 3 | task 2710 | stop processing: n_tokens = 1729, truncated = 0 3.38.911.970 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.618 3.38.912.006 I slot launch_slot_: id 3 | task 3317 | processing task, is_child = 0 3.39.552.097 I slot print_timing: id 2 | task 2804 | n_gen = 511, tg = 22.69 t/s, tg_3s = 19.61 t/s 3.39.624.262 I slot print_timing: id 1 | task 2395 | n_gen = 918, tg = 22.49 t/s, tg_3s = 19.03 t/s 3.39.953.598 I slot print_timing: id 2 | task 2804 | prompt eval time = 775.58 ms / 515 tokens ( 1.51 ms per token, 664.02 tokens per second) 3.39.953.604 I slot print_timing: id 2 | task 2804 | eval time = 22879.58 ms / 520 tokens ( 44.08 ms per token, 22.68 tokens per second) 3.39.953.605 I slot print_timing: id 2 | task 2804 | total time = 23655.16 ms / 1035 tokens 3.39.953.606 I slot print_timing: id 2 | task 2804 | graphs reused = 2965 3.39.953.606 I slot print_timing: id 2 | task 2804 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.953.706 I slot release: id 2 | task 2804 | stop processing: n_tokens = 1689, truncated = 0 3.39.996.662 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.632 3.39.996.716 I slot launch_slot_: id 2 | task 3329 | processing task, is_child = 0 3.41.312.493 I slot print_timing: id 0 | task 3241 | n_gen = 100, tg = 18.22 t/s, tg_3s = 18.41 t/s 3.42.648.606 I slot print_timing: id 1 | task 2395 | n_gen = 974, tg = 22.22 t/s, tg_3s = 18.52 t/s 3.44.313.842 I slot print_timing: id 0 | task 3241 | n_gen = 172, tg = 20.27 t/s, tg_3s = 23.99 t/s 3.44.440.360 I slot print_timing: id 3 | task 3317 | n_gen = 100, tg = 20.56 t/s, tg_3s = 20.77 t/s 3.44.730.454 I slot print_timing: id 1 | task 2395 | prompt eval time = 902.49 ms / 527 tokens ( 1.71 ms per token, 583.94 tokens per second) 3.44.730.462 I slot print_timing: id 1 | task 2395 | eval time = 45879.07 ms / 1024 tokens ( 44.85 ms per token, 22.30 tokens per second) 3.44.730.465 I slot print_timing: id 1 | task 2395 | total time = 46781.56 ms / 1551 tokens 3.44.730.466 I slot print_timing: id 1 | task 2395 | graphs reused = 3059 3.44.730.466 I slot print_timing: id 1 | task 2395 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.730.600 I slot release: id 1 | task 2395 | stop processing: n_tokens = 2214, truncated = 0 3.44.775.070 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.482 3.44.781.770 I slot launch_slot_: id 1 | task 3428 | processing task, is_child = 0 3.45.553.724 I slot print_timing: id 2 | task 3329 | n_gen = 100, tg = 20.69 t/s, tg_3s = 20.90 t/s 3.47.335.319 I slot print_timing: id 0 | task 3241 | n_gen = 229, tg = 19.90 t/s, tg_3s = 18.86 t/s 3.47.462.460 I slot print_timing: id 3 | task 3317 | n_gen = 157, tg = 19.90 t/s, tg_3s = 18.86 t/s 3.48.586.261 I slot print_timing: id 2 | task 3329 | n_gen = 173, tg = 22.00 t/s, tg_3s = 24.07 t/s 3.49.626.552 I slot print_timing: id 1 | task 3428 | n_gen = 100, tg = 24.06 t/s, tg_3s = 24.30 t/s 3.50.375.417 I slot print_timing: id 0 | task 3241 | n_gen = 302, tg = 20.76 t/s, tg_3s = 24.01 t/s 3.50.502.802 I slot print_timing: id 3 | task 3317 | n_gen = 230, tg = 21.05 t/s, tg_3s = 24.01 t/s 3.51.626.275 I slot print_timing: id 2 | task 3329 | n_gen = 246, tg = 22.56 t/s, tg_3s = 24.01 t/s 3.52.667.274 I slot print_timing: id 1 | task 3428 | n_gen = 173, tg = 24.04 t/s, tg_3s = 24.01 t/s 3.53.416.463 I slot print_timing: id 0 | task 3241 | n_gen = 375, tg = 21.33 t/s, tg_3s = 24.00 t/s 3.53.543.577 I slot print_timing: id 3 | task 3317 | n_gen = 303, tg = 21.70 t/s, tg_3s = 24.01 t/s 3.54.627.967 I slot print_timing: id 2 | task 3329 | n_gen = 318, tg = 22.87 t/s, tg_3s = 23.99 t/s 3.55.668.498 I slot print_timing: id 1 | task 3428 | n_gen = 245, tg = 24.02 t/s, tg_3s = 23.99 t/s 3.56.417.535 I slot print_timing: id 0 | task 3241 | n_gen = 447, tg = 21.72 t/s, tg_3s = 23.99 t/s 3.56.544.345 I slot print_timing: id 3 | task 3317 | n_gen = 375, tg = 22.10 t/s, tg_3s = 23.99 t/s 3.57.668.459 I slot print_timing: id 2 | task 3329 | n_gen = 391, tg = 23.08 t/s, tg_3s = 24.01 t/s 3.58.710.355 I slot print_timing: id 1 | task 3428 | n_gen = 318, tg = 24.02 t/s, tg_3s = 24.00 t/s 3.59.420.282 I slot print_timing: id 0 | task 3241 | n_gen = 519, tg = 22.00 t/s, tg_3s = 23.98 t/s 3.59.546.644 I slot print_timing: id 3 | task 3317 | n_gen = 447, tg = 22.39 t/s, tg_3s = 23.98 t/s 4.00.670.450 I slot print_timing: id 2 | task 3329 | n_gen = 463, tg = 23.21 t/s, tg_3s = 23.98 t/s 4.01.711.129 I slot print_timing: id 1 | task 3428 | n_gen = 390, tg = 24.01 t/s, tg_3s = 23.99 t/s 4.02.458.402 I slot print_timing: id 0 | task 3241 | n_gen = 592, tg = 22.24 t/s, tg_3s = 24.03 t/s 4.02.585.779 I slot print_timing: id 3 | task 3317 | n_gen = 520, tg = 22.60 t/s, tg_3s = 24.02 t/s 4.03.710.591 I slot print_timing: id 2 | task 3329 | n_gen = 536, tg = 23.32 t/s, tg_3s = 24.01 t/s 4.04.543.152 I slot print_timing: id 3 | task 3317 | prompt eval time = 712.94 ms / 458 tokens ( 1.56 ms per token, 642.41 tokens per second) 4.04.543.159 I slot print_timing: id 3 | task 3317 | eval time = 24918.20 ms / 567 tokens ( 44.03 ms per token, 22.71 tokens per second) 4.04.543.160 I slot print_timing: id 3 | task 3317 | total time = 25631.14 ms / 1025 tokens 4.04.543.161 I slot print_timing: id 3 | task 3317 | graphs reused = 3514 4.04.543.161 I slot print_timing: id 3 | task 3317 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.543.259 I slot release: id 3 | task 3317 | stop processing: n_tokens = 1694, truncated = 0 4.04.579.010 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.630 4.04.579.041 I slot launch_slot_: id 3 | task 3889 | processing task, is_child = 0 4.05.265.935 I slot print_timing: id 1 | task 3428 | n_gen = 460, tg = 23.24 t/s, tg_3s = 19.69 t/s 4.05.461.271 I slot print_timing: id 0 | task 3241 | n_gen = 648, tg = 21.87 t/s, tg_3s = 18.65 t/s 4.06.719.645 I slot print_timing: id 2 | task 3329 | n_gen = 592, tg = 22.77 t/s, tg_3s = 18.61 t/s 4.08.307.558 I slot print_timing: id 1 | task 3428 | n_gen = 532, tg = 23.29 t/s, tg_3s = 23.67 t/s 4.08.349.219 I slot print_timing: id 1 | task 3428 | prompt eval time = 729.98 ms / 463 tokens ( 1.58 ms per token, 634.26 tokens per second) 4.08.349.224 I slot print_timing: id 1 | task 3428 | eval time = 22837.46 ms / 533 tokens ( 42.93 ms per token, 23.30 tokens per second) 4.08.349.225 I slot print_timing: id 1 | task 3428 | total time = 23567.44 ms / 996 tokens 4.08.349.225 I slot print_timing: id 1 | task 3428 | graphs reused = 3584 4.08.349.226 I slot print_timing: id 1 | task 3428 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.349.358 I slot release: id 1 | task 3428 | stop processing: n_tokens = 1670, truncated = 0 4.08.393.435 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.640 4.08.393.473 I slot launch_slot_: id 1 | task 3965 | processing task, is_child = 0 4.09.039.769 I slot print_timing: id 0 | task 3241 | n_gen = 719, tg = 21.65 t/s, tg_3s = 19.84 t/s 4.09.746.649 I slot print_timing: id 2 | task 3329 | n_gen = 649, tg = 22.36 t/s, tg_3s = 18.83 t/s 4.10.123.116 I slot print_timing: id 3 | task 3889 | n_gen = 100, tg = 20.69 t/s, tg_3s = 20.90 t/s 4.11.832.979 I slot print_timing: id 2 | task 3329 | prompt eval time = 771.62 ms / 490 tokens ( 1.57 ms per token, 635.02 tokens per second) 4.11.832.987 I slot print_timing: id 2 | task 3329 | eval time = 31064.63 ms / 699 tokens ( 44.51 ms per token, 22.47 tokens per second) 4.11.832.988 I slot print_timing: id 2 | task 3329 | total time = 31836.25 ms / 1189 tokens 4.11.832.988 I slot print_timing: id 2 | task 3329 | graphs reused = 3648 4.11.832.989 I slot print_timing: id 2 | task 3329 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.833.095 I slot release: id 2 | task 3329 | stop processing: n_tokens = 1843, truncated = 0 4.11.876.556 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.579 4.11.876.594 I slot launch_slot_: id 2 | task 4034 | processing task, is_child = 0 4.12.539.231 I slot print_timing: id 0 | task 3241 | n_gen = 787, tg = 21.44 t/s, tg_3s = 19.43 t/s 4.13.156.255 I slot print_timing: id 3 | task 3889 | n_gen = 157, tg = 19.96 t/s, tg_3s = 18.79 t/s 4.13.906.226 I slot print_timing: id 1 | task 3965 | n_gen = 100, tg = 20.68 t/s, tg_3s = 20.89 t/s 4.15.568.162 I slot print_timing: id 0 | task 3241 | n_gen = 859, tg = 21.62 t/s, tg_3s = 23.77 t/s 4.16.194.430 I slot print_timing: id 3 | task 3889 | n_gen = 230, tg = 21.10 t/s, tg_3s = 24.03 t/s 4.16.737.479 I slot print_timing: id 2 | task 4034 | n_gen = 100, tg = 24.03 t/s, tg_3s = 24.28 t/s 4.16.945.262 I slot print_timing: id 1 | task 3965 | n_gen = 173, tg = 21.98 t/s, tg_3s = 24.02 t/s 4.17.611.278 I slot print_timing: id 0 | task 3241 | prompt eval time = 682.64 ms / 447 tokens ( 1.53 ms per token, 654.81 tokens per second) 4.17.611.285 I slot print_timing: id 0 | task 3241 | eval time = 41732.00 ms / 908 tokens ( 46.01 ms per token, 21.73 tokens per second) 4.17.611.286 I slot print_timing: id 0 | task 3241 | total time = 42414.65 ms / 1355 tokens 4.17.611.287 I slot print_timing: id 0 | task 3241 | graphs reused = 3766 4.17.611.287 I slot print_timing: id 0 | task 3241 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.611.384 I slot release: id 0 | task 3241 | stop processing: n_tokens = 2049, truncated = 0 4.17.648.431 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.521 4.17.648.470 I slot launch_slot_: id 0 | task 4158 | processing task, is_child = 0 4.19.230.640 I slot print_timing: id 3 | task 3889 | n_gen = 289, tg = 20.73 t/s, tg_3s = 19.43 t/s 4.19.771.743 I slot print_timing: id 2 | task 4034 | n_gen = 159, tg = 22.09 t/s, tg_3s = 19.44 t/s 4.19.979.862 I slot print_timing: id 1 | task 3965 | n_gen = 232, tg = 21.27 t/s, tg_3s = 19.44 t/s 4.22.262.986 I slot print_timing: id 3 | task 3889 | n_gen = 362, tg = 21.33 t/s, tg_3s = 24.07 t/s 4.22.426.368 I slot print_timing: id 0 | task 4158 | n_gen = 100, tg = 24.12 t/s, tg_3s = 24.36 t/s 4.22.800.748 I slot print_timing: id 2 | task 4034 | n_gen = 232, tg = 22.69 t/s, tg_3s = 24.10 t/s 4.23.008.902 I slot print_timing: id 1 | task 3965 | n_gen = 305, tg = 21.89 t/s, tg_3s = 24.10 t/s 4.25.300.011 I slot print_timing: id 3 | task 3889 | n_gen = 435, tg = 21.74 t/s, tg_3s = 24.04 t/s 4.25.464.658 I slot print_timing: id 0 | task 4158 | n_gen = 173, tg = 24.08 t/s, tg_3s = 24.03 t/s 4.25.842.286 I slot print_timing: id 2 | task 4034 | n_gen = 305, tg = 22.99 t/s, tg_3s = 24.00 t/s 4.26.009.196 I slot print_timing: id 1 | task 3965 | n_gen = 377, tg = 22.26 t/s, tg_3s = 24.00 t/s 4.28.305.443 I slot print_timing: id 3 | task 3889 | n_gen = 507, tg = 22.03 t/s, tg_3s = 23.96 t/s 4.28.470.965 I slot print_timing: id 0 | task 4158 | n_gen = 245, tg = 24.04 t/s, tg_3s = 23.95 t/s 4.28.848.235 I slot print_timing: id 2 | task 4034 | n_gen = 377, tg = 23.17 t/s, tg_3s = 23.95 t/s 4.29.014.613 I slot print_timing: id 1 | task 3965 | n_gen = 449, tg = 22.52 t/s, tg_3s = 23.96 t/s 4.31.313.703 I slot print_timing: id 3 | task 3889 | n_gen = 579, tg = 22.25 t/s, tg_3s = 23.93 t/s 4.31.478.463 I slot print_timing: id 0 | task 4158 | n_gen = 317, tg = 24.02 t/s, tg_3s = 23.94 t/s 4.31.853.564 I slot print_timing: id 2 | task 4034 | n_gen = 449, tg = 23.29 t/s, tg_3s = 23.96 t/s 4.32.019.152 I slot print_timing: id 1 | task 3965 | n_gen = 521, tg = 22.71 t/s, tg_3s = 23.96 t/s 4.34.314.786 I slot print_timing: id 3 | task 3889 | n_gen = 651, tg = 22.43 t/s, tg_3s = 23.99 t/s 4.34.480.083 I slot print_timing: id 0 | task 4158 | n_gen = 389, tg = 24.01 t/s, tg_3s = 23.99 t/s 4.34.858.495 I slot print_timing: id 2 | task 4034 | n_gen = 521, tg = 23.38 t/s, tg_3s = 23.96 t/s 4.35.025.853 I slot print_timing: id 1 | task 3965 | n_gen = 593, tg = 22.85 t/s, tg_3s = 23.95 t/s 4.37.318.302 I slot print_timing: id 3 | task 3889 | n_gen = 723, tg = 22.58 t/s, tg_3s = 23.97 t/s 4.37.483.133 I slot print_timing: id 0 | task 4158 | n_gen = 461, tg = 24.01 t/s, tg_3s = 23.98 t/s 4.37.858.670 I slot print_timing: id 2 | task 4034 | n_gen = 593, tg = 23.45 t/s, tg_3s = 24.00 t/s 4.38.066.599 I slot print_timing: id 1 | task 3965 | n_gen = 666, tg = 22.97 t/s, tg_3s = 24.01 t/s 4.39.064.539 I slot print_timing: id 0 | task 4158 | prompt eval time = 673.50 ms / 435 tokens ( 1.55 ms per token, 645.88 tokens per second) 4.39.064.546 I slot print_timing: id 0 | task 4158 | eval time = 20742.56 ms / 499 tokens ( 41.65 ms per token, 24.01 tokens per second) 4.39.064.547 I slot print_timing: id 0 | task 4158 | total time = 21416.06 ms / 934 tokens 4.39.064.548 I slot print_timing: id 0 | task 4158 | graphs reused = 4262 4.39.064.549 I slot print_timing: id 0 | task 4158 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.064.649 I slot release: id 0 | task 4158 | stop processing: n_tokens = 1628, truncated = 0 4.39.102.153 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.656 4.39.102.191 I slot launch_slot_: id 0 | task 4660 | processing task, is_child = 0 4.40.359.182 I slot print_timing: id 3 | task 3889 | n_gen = 781, tg = 22.27 t/s, tg_3s = 19.07 t/s 4.40.609.321 I slot print_timing: id 1 | task 3965 | prompt eval time = 725.68 ms / 458 tokens ( 1.58 ms per token, 631.13 tokens per second) 4.40.609.342 I slot print_timing: id 1 | task 3965 | eval time = 31490.16 ms / 712 tokens ( 44.29 ms per token, 22.58 tokens per second) 4.40.609.343 I slot print_timing: id 1 | task 3965 | total time = 32215.84 ms / 1170 tokens 4.40.609.343 I slot print_timing: id 1 | task 3965 | graphs reused = 4281 4.40.609.344 I slot print_timing: id 1 | task 3965 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.609.450 I slot release: id 1 | task 3965 | stop processing: n_tokens = 1844, truncated = 0 4.40.653.486 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.579 4.40.653.524 I slot launch_slot_: id 1 | task 4683 | processing task, is_child = 0 4.41.342.090 I slot print_timing: id 2 | task 4034 | n_gen = 646, tg = 22.46 t/s, tg_3s = 15.21 t/s 4.43.372.099 I slot print_timing: id 3 | task 3889 | n_gen = 837, tg = 21.98 t/s, tg_3s = 18.59 t/s 4.44.371.842 I slot print_timing: id 2 | task 4034 | n_gen = 718, tg = 22.58 t/s, tg_3s = 23.76 t/s 4.44.620.521 I slot print_timing: id 0 | task 4660 | n_gen = 100, tg = 20.62 t/s, tg_3s = 20.82 t/s 4.45.545.681 I slot print_timing: id 1 | task 4683 | n_gen = 100, tg = 24.01 t/s, tg_3s = 24.25 t/s 4.46.384.787 I slot print_timing: id 3 | task 3889 | n_gen = 909, tg = 22.12 t/s, tg_3s = 23.90 t/s 4.47.390.168 I slot print_timing: id 2 | task 4034 | n_gen = 790, tg = 22.69 t/s, tg_3s = 23.85 t/s 4.47.639.912 I slot print_timing: id 0 | task 4660 | n_gen = 172, tg = 21.86 t/s, tg_3s = 23.85 t/s 4.48.563.525 I slot print_timing: id 1 | task 4683 | n_gen = 172, tg = 23.94 t/s, tg_3s = 23.86 t/s 4.49.404.847 I slot print_timing: id 3 | task 3889 | n_gen = 981, tg = 22.24 t/s, tg_3s = 23.84 t/s 4.50.408.525 I slot print_timing: id 2 | task 4034 | n_gen = 862, tg = 22.78 t/s, tg_3s = 23.85 t/s 4.50.658.552 I slot print_timing: id 0 | task 4660 | n_gen = 244, tg = 22.42 t/s, tg_3s = 23.85 t/s 4.51.206.762 I slot print_timing: id 3 | task 3889 | prompt eval time = 759.80 ms / 510 tokens ( 1.49 ms per token, 671.23 tokens per second) 4.51.206.770 I slot print_timing: id 3 | task 3889 | eval time = 45867.91 ms / 1024 tokens ( 44.84 ms per token, 22.30 tokens per second) 4.51.206.771 I slot print_timing: id 3 | task 3889 | total time = 46627.71 ms / 1534 tokens 4.51.206.771 I slot print_timing: id 3 | task 3889 | graphs reused = 4513 4.51.206.772 I slot print_timing: id 3 | task 3889 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.206.901 I slot release: id 3 | task 3889 | stop processing: n_tokens = 2203, truncated = 0 4.51.243.421 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.485 4.51.249.403 I slot launch_slot_: id 3 | task 4921 | processing task, is_child = 0 4.52.007.314 I slot print_timing: id 1 | task 4683 | n_gen = 238, tg = 22.39 t/s, tg_3s = 19.16 t/s 4.53.418.615 I slot print_timing: id 2 | task 4034 | n_gen = 917, tg = 22.45 t/s, tg_3s = 18.27 t/s 4.53.668.530 I slot print_timing: id 0 | task 4660 | n_gen = 299, tg = 21.52 t/s, tg_3s = 18.27 t/s 4.53.877.381 I slot print_timing: id 2 | task 4034 | prompt eval time = 741.68 ms / 482 tokens ( 1.54 ms per token, 649.88 tokens per second) 4.53.877.385 I slot print_timing: id 2 | task 4034 | eval time = 41259.10 ms / 928 tokens ( 44.51 ms per token, 22.47 tokens per second) 4.53.877.386 I slot print_timing: id 2 | task 4034 | total time = 42000.78 ms / 1410 tokens 4.53.877.387 I slot print_timing: id 2 | task 4034 | graphs reused = 4554 4.53.877.388 I slot print_timing: id 2 | task 4034 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.877.489 I slot release: id 2 | task 4034 | stop processing: n_tokens = 2064, truncated = 0 4.53.921.002 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.517 4.53.921.057 I slot launch_slot_: id 2 | task 4969 | processing task, is_child = 0 4.55.032.688 I slot print_timing: id 1 | task 4683 | n_gen = 294, tg = 21.53 t/s, tg_3s = 18.51 t/s 4.56.699.138 I slot print_timing: id 0 | task 4660 | n_gen = 356, tg = 21.03 t/s, tg_3s = 18.81 t/s 4.56.867.162 I slot print_timing: id 3 | task 4921 | n_gen = 100, tg = 20.68 t/s, tg_3s = 20.89 t/s 4.58.068.240 I slot print_timing: id 1 | task 4683 | n_gen = 367, tg = 21.99 t/s, tg_3s = 24.05 t/s 4.58.776.281 I slot print_timing: id 2 | task 4969 | n_gen = 100, tg = 24.07 t/s, tg_3s = 24.32 t/s 4.59.731.621 I slot print_timing: id 0 | task 4660 | n_gen = 429, tg = 21.49 t/s, tg_3s = 24.07 t/s 4.59.899.403 I slot print_timing: id 3 | task 4921 | n_gen = 173, tg = 22.00 t/s, tg_3s = 24.07 t/s 5.01.104.797 I slot print_timing: id 1 | task 4683 | n_gen = 440, tg = 22.30 t/s, tg_3s = 24.04 t/s 5.01.811.026 I slot print_timing: id 2 | task 4969 | n_gen = 173, tg = 24.06 t/s, tg_3s = 24.05 t/s 5.02.767.126 I slot print_timing: id 0 | task 4660 | n_gen = 502, tg = 21.83 t/s, tg_3s = 24.05 t/s 5.02.936.469 I slot print_timing: id 3 | task 4921 | n_gen = 246, tg = 22.57 t/s, tg_3s = 24.04 t/s 5.04.142.204 I slot print_timing: id 1 | task 4683 | n_gen = 513, tg = 22.53 t/s, tg_3s = 24.03 t/s 5.04.851.235 I slot print_timing: id 2 | task 4969 | n_gen = 246, tg = 24.05 t/s, tg_3s = 24.01 t/s 5.05.807.877 I slot print_timing: id 0 | task 4660 | n_gen = 575, tg = 22.09 t/s, tg_3s = 24.01 t/s 5.05.975.588 I slot print_timing: id 3 | task 4921 | n_gen = 319, tg = 22.89 t/s, tg_3s = 24.02 t/s 5.07.142.950 I slot print_timing: id 1 | task 4683 | n_gen = 585, tg = 22.70 t/s, tg_3s = 23.99 t/s 5.07.855.346 I slot print_timing: id 2 | task 4969 | n_gen = 318, tg = 24.03 t/s, tg_3s = 23.97 t/s 5.08.817.364 I slot print_timing: id 0 | task 4660 | n_gen = 647, tg = 22.28 t/s, tg_3s = 23.92 t/s 5.08.985.950 I slot print_timing: id 3 | task 4921 | n_gen = 391, tg = 23.07 t/s, tg_3s = 23.92 t/s 5.10.155.970 I slot print_timing: id 1 | task 4683 | n_gen = 657, tg = 22.83 t/s, tg_3s = 23.90 t/s 5.10.866.977 I slot print_timing: id 2 | task 4969 | n_gen = 390, tg = 24.01 t/s, tg_3s = 23.91 t/s 5.11.825.544 I slot print_timing: id 0 | task 4660 | n_gen = 719, tg = 22.43 t/s, tg_3s = 23.93 t/s 5.11.996.080 I slot print_timing: id 3 | task 4921 | n_gen = 463, tg = 23.20 t/s, tg_3s = 23.92 t/s 5.12.789.582 I slot print_timing: id 2 | task 4969 | prompt eval time = 742.63 ms / 482 tokens ( 1.54 ms per token, 649.05 tokens per second) 5.12.789.591 I slot print_timing: id 2 | task 4969 | eval time = 18125.88 ms / 436 tokens ( 41.67 ms per token, 24.00 tokens per second) 5.12.789.592 I slot print_timing: id 2 | task 4969 | total time = 18868.51 ms / 918 tokens 5.12.789.592 I slot print_timing: id 2 | task 4969 | graphs reused = 4986 5.12.789.593 I slot print_timing: id 2 | task 4969 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.789.730 I slot release: id 2 | task 4969 | stop processing: n_tokens = 1572, truncated = 0 5.12.833.953 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.679 5.12.833.999 I slot launch_slot_: id 2 | task 5408 | processing task, is_child = 0 5.13.491.540 I slot print_timing: id 1 | task 4683 | n_gen = 722, tg = 22.48 t/s, tg_3s = 19.49 t/s 5.14.865.697 I slot print_timing: id 0 | task 4660 | n_gen = 776, tg = 22.11 t/s, tg_3s = 18.75 t/s 5.15.034.121 I slot print_timing: id 3 | task 4921 | n_gen = 520, tg = 22.61 t/s, tg_3s = 18.76 t/s 5.16.532.764 I slot print_timing: id 1 | task 4683 | n_gen = 794, tg = 22.59 t/s, tg_3s = 23.67 t/s 5.17.702.063 I slot print_timing: id 2 | task 5408 | n_gen = 100, tg = 23.97 t/s, tg_3s = 24.21 t/s 5.17.868.094 I slot print_timing: id 0 | task 4660 | n_gen = 848, tg = 22.26 t/s, tg_3s = 23.98 t/s 5.18.037.345 I slot print_timing: id 3 | task 4921 | n_gen = 592, tg = 22.77 t/s, tg_3s = 23.97 t/s 5.19.544.281 I slot print_timing: id 1 | task 4683 | n_gen = 866, tg = 22.69 t/s, tg_3s = 23.91 t/s 5.20.723.239 I slot print_timing: id 2 | task 5408 | n_gen = 172, tg = 23.91 t/s, tg_3s = 23.83 t/s 5.20.890.583 I slot print_timing: id 0 | task 4660 | n_gen = 920, tg = 22.38 t/s, tg_3s = 23.82 t/s 5.21.060.915 I slot print_timing: id 3 | task 4921 | n_gen = 664, tg = 22.88 t/s, tg_3s = 23.81 t/s 5.22.573.087 I slot print_timing: id 1 | task 4683 | n_gen = 938, tg = 22.77 t/s, tg_3s = 23.77 t/s 5.23.747.912 I slot print_timing: id 2 | task 5408 | n_gen = 244, tg = 23.88 t/s, tg_3s = 23.80 t/s 5.23.914.127 I slot print_timing: id 0 | task 4660 | n_gen = 992, tg = 22.47 t/s, tg_3s = 23.81 t/s 5.24.083.945 I slot print_timing: id 3 | task 4921 | n_gen = 736, tg = 22.97 t/s, tg_3s = 23.82 t/s 5.25.259.051 I slot print_timing: id 0 | task 4660 | prompt eval time = 716.24 ms / 478 tokens ( 1.50 ms per token, 667.38 tokens per second) 5.25.259.059 I slot print_timing: id 0 | task 4660 | eval time = 45440.61 ms / 1024 tokens ( 44.42 ms per token, 22.51 tokens per second) 5.25.259.059 I slot print_timing: id 0 | task 4660 | total time = 46156.85 ms / 1502 tokens 5.25.259.060 I slot print_timing: id 0 | task 4660 | graphs reused = 5263 5.25.259.061 I slot print_timing: id 0 | task 4660 | graph reallocs = 0 / 0 (same size) / (changed size) 5.25.259.165 I slot release: id 0 | task 4660 | stop processing: n_tokens = 2196, truncated = 0 5.25.297.002 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.486 5.25.302.851 I slot launch_slot_: id 0 | task 5691 | processing task, is_child = 0 5.25.914.258 I slot print_timing: id 1 | task 4683 | n_gen = 1004, tg = 22.54 t/s, tg_3s = 19.75 t/s 5.26.773.023 I slot print_timing: id 1 | task 4683 | prompt eval time = 768.16 ms / 501 tokens ( 1.53 ms per token, 652.21 tokens per second) 5.26.773.030 I slot print_timing: id 1 | task 4683 | eval time = 45351.33 ms / 1024 tokens ( 44.33 ms per token, 22.56 tokens per second) 5.26.773.031 I slot print_timing: id 1 | task 4683 | total time = 46119.49 ms / 1525 tokens 5.26.773.031 I slot print_timing: id 1 | task 4683 | graphs reused = 5282 5.26.773.032 I slot print_timing: id 1 | task 4683 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.773.137 I slot release: id 1 | task 4683 | stop processing: n_tokens = 2199, truncated = 0 5.26.773.712 I slot print_timing: id 2 | task 5408 | n_gen = 302, tg = 22.80 t/s, tg_3s = 19.17 t/s 5.26.817.361 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.486 5.26.823.765 I slot launch_slot_: id 1 | task 5714 | processing task, is_child = 0 5.27.480.699 I slot print_timing: id 3 | task 4921 | n_gen = 788, tg = 22.23 t/s, tg_3s = 15.31 t/s 5.28.891.707 I slot print_timing: id 2 | task 5408 | prompt eval time = 737.05 ms / 476 tokens ( 1.55 ms per token, 645.82 tokens per second) 5.28.891.716 I slot print_timing: id 2 | task 5408 | eval time = 15320.65 ms / 337 tokens ( 45.60 ms per token, 21.93 tokens per second) 5.28.891.717 I slot print_timing: id 2 | task 5408 | total time = 16057.70 ms / 813 tokens 5.28.891.717 I slot print_timing: id 2 | task 5408 | graphs reused = 5313 5.28.891.718 I slot print_timing: id 2 | task 5408 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.891.843 I slot release: id 2 | task 5408 | stop processing: n_tokens = 1467, truncated = 0 5.28.935.542 I slot print_timing: id 3 | task 4921 | prompt eval time = 830.73 ms / 519 tokens ( 1.60 ms per token, 624.75 tokens per second) 5.28.935.547 I slot print_timing: id 3 | task 4921 | eval time = 36855.39 ms / 822 tokens ( 44.89 ms per token, 22.28 tokens per second) 5.28.935.548 I slot print_timing: id 3 | task 4921 | total time = 37686.13 ms / 1341 tokens 5.28.935.549 I slot print_timing: id 3 | task 4921 | graphs reused = 5313 5.28.935.550 I slot print_timing: id 3 | task 4921 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.935.652 I slot release: id 3 | task 4921 | stop processing: n_tokens = 2010, truncated = 0 5.28.935.664 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.729 5.28.935.697 I slot launch_slot_: id 2 | task 5750 | processing task, is_child = 0 5.29.611.075 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.531 5.29.611.111 I slot launch_slot_: id 3 | task 5752 | processing task, is_child = 0 5.32.107.515 I slot print_timing: id 0 | task 5691 | n_gen = 100, tg = 16.17 t/s, tg_3s = 16.33 t/s 5.33.023.896 I slot print_timing: id 1 | task 5714 | n_gen = 100, tg = 18.12 t/s, tg_3s = 18.30 t/s 5.34.483.798 I slot print_timing: id 2 | task 5750 | n_gen = 100, tg = 23.85 t/s, tg_3s = 24.09 t/s 5.34.526.095 I slot print_timing: id 3 | task 5752 | n_gen = 100, tg = 24.02 t/s, tg_3s = 24.26 t/s 5.35.148.865 I slot print_timing: id 0 | task 5691 | n_gen = 173, tg = 18.77 t/s, tg_3s = 24.00 t/s 5.36.058.556 I slot print_timing: id 1 | task 5714 | n_gen = 173, tg = 20.24 t/s, tg_3s = 24.06 t/s 5.37.517.135 I slot print_timing: id 2 | task 5750 | n_gen = 173, tg = 23.94 t/s, tg_3s = 24.07 t/s 5.37.559.050 I slot print_timing: id 3 | task 5752 | n_gen = 173, tg = 24.04 t/s, tg_3s = 24.07 t/s 5.38.179.657 I slot print_timing: id 0 | task 5691 | n_gen = 246, tg = 20.09 t/s, tg_3s = 24.09 t/s 5.39.093.473 I slot print_timing: id 1 | task 5714 | n_gen = 246, tg = 21.24 t/s, tg_3s = 24.05 t/s 5.40.549.988 I slot print_timing: id 2 | task 5750 | n_gen = 246, tg = 23.98 t/s, tg_3s = 24.07 t/s 5.40.591.908 I slot print_timing: id 3 | task 5752 | n_gen = 246, tg = 24.05 t/s, tg_3s = 24.07 t/s 5.41.211.599 I slot print_timing: id 0 | task 5691 | n_gen = 319, tg = 20.88 t/s, tg_3s = 24.08 t/s 5.42.130.222 I slot print_timing: id 1 | task 5714 | n_gen = 319, tg = 21.82 t/s, tg_3s = 24.04 t/s 5.43.551.105 I slot print_timing: id 2 | task 5750 | n_gen = 318, tg = 23.98 t/s, tg_3s = 23.99 t/s 5.43.593.427 I slot print_timing: id 3 | task 5752 | n_gen = 318, tg = 24.04 t/s, tg_3s = 23.99 t/s 5.44.219.112 I slot print_timing: id 0 | task 5691 | n_gen = 391, tg = 21.39 t/s, tg_3s = 23.94 t/s 5.45.141.406 I slot print_timing: id 1 | task 5714 | n_gen = 391, tg = 22.18 t/s, tg_3s = 23.91 t/s 5.46.553.372 I slot print_timing: id 2 | task 5750 | n_gen = 390, tg = 23.98 t/s, tg_3s = 23.98 t/s 5.46.596.086 I slot print_timing: id 3 | task 5752 | n_gen = 390, tg = 24.02 t/s, tg_3s = 23.98 t/s 5.47.012.657 I slot print_timing: id 2 | task 5750 | prompt eval time = 1390.62 ms / 498 tokens ( 2.79 ms per token, 358.11 tokens per second) 5.47.012.664 I slot print_timing: id 2 | task 5750 | eval time = 16680.59 ms / 401 tokens ( 41.70 ms per token, 23.98 tokens per second) 5.47.012.665 I slot print_timing: id 2 | task 5750 | total time = 18071.21 ms / 899 tokens 5.47.012.666 I slot print_timing: id 2 | task 5750 | graphs reused = 5709 5.47.012.666 I slot print_timing: id 2 | task 5750 | graph reallocs = 0 / 0 (same size) / (changed size) 5.47.012.775 I slot release: id 2 | task 5750 | stop processing: n_tokens = 1553, truncated = 0 5.47.056.477 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.688 5.47.056.512 I slot launch_slot_: id 2 | task 6155 | processing task, is_child = 0 5.47.720.039 I slot print_timing: id 0 | task 5691 | n_gen = 460, tg = 21.12 t/s, tg_3s = 19.71 t/s 5.48.167.634 I slot print_timing: id 1 | task 5714 | n_gen = 448, tg = 21.69 t/s, tg_3s = 18.84 t/s 5.49.629.658 I slot print_timing: id 3 | task 5752 | n_gen = 447, tg = 23.20 t/s, tg_3s = 18.79 t/s 5.50.714.018 I slot print_timing: id 3 | task 5752 | prompt eval time = 793.20 ms / 493 tokens ( 1.61 ms per token, 621.53 tokens per second) 5.50.714.024 I slot print_timing: id 3 | task 5752 | eval time = 20309.50 ms / 473 tokens ( 43.03 ms per token, 23.24 tokens per second) 5.50.714.025 I slot print_timing: id 3 | task 5752 | total time = 21102.71 ms / 966 tokens 5.50.714.027 I slot print_timing: id 3 | task 5752 | graphs reused = 5778 5.50.714.028 I slot print_timing: id 3 | task 5752 | graph reallocs = 0 / 0 (same size) / (changed size) 5.50.714.162 I slot release: id 3 | task 5752 | stop processing: n_tokens = 1638, truncated = 0 5.50.749.423 I slot print_timing: id 0 | task 5691 | n_gen = 532, tg = 21.44 t/s, tg_3s = 23.77 t/s 5.50.750.479 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.652 5.50.750.510 I slot launch_slot_: id 3 | task 6229 | processing task, is_child = 0 5.51.408.391 I slot print_timing: id 1 | task 5714 | n_gen = 511, tg = 21.38 t/s, tg_3s = 19.44 t/s 5.51.604.158 I slot print_timing: id 1 | task 5714 | prompt eval time = 735.75 ms / 473 tokens ( 1.56 ms per token, 642.88 tokens per second) 5.51.604.163 I slot print_timing: id 1 | task 5714 | eval time = 24044.63 ms / 515 tokens ( 46.78 ms per token, 21.38 tokens per second) 5.51.604.165 I slot print_timing: id 1 | task 5714 | total time = 24780.39 ms / 988 tokens 5.51.604.166 I slot print_timing: id 1 | task 5714 | graphs reused = 5780 5.51.604.166 I slot print_timing: id 1 | task 5714 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.604.233 I slot release: id 1 | task 5714 | stop processing: n_tokens = 1662, truncated = 0 5.51.647.222 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.643 5.51.647.259 I slot launch_slot_: id 1 | task 6236 | processing task, is_child = 0 5.53.269.348 I slot print_timing: id 2 | task 6155 | n_gen = 100, tg = 18.10 t/s, tg_3s = 18.28 t/s 5.53.767.446 I slot print_timing: id 0 | task 5691 | n_gen = 572, tg = 20.55 t/s, tg_3s = 13.25 t/s 5.56.270.722 I slot print_timing: id 2 | task 6155 | n_gen = 172, tg = 20.19 t/s, tg_3s = 23.99 t/s 5.56.312.696 I slot print_timing: id 3 | task 6229 | n_gen = 100, tg = 20.49 t/s, tg_3s = 20.70 t/s 5.56.560.166 I slot print_timing: id 1 | task 6236 | n_gen = 100, tg = 23.98 t/s, tg_3s = 24.22 t/s 5.56.768.654 I slot print_timing: id 0 | task 5691 | n_gen = 644, tg = 20.89 t/s, tg_3s = 23.99 t/s 5.59.311.580 I slot print_timing: id 2 | task 6155 | n_gen = 245, tg = 21.19 t/s, tg_3s = 24.01 t/s 5.59.353.942 I slot print_timing: id 3 | task 6229 | n_gen = 173, tg = 21.85 t/s, tg_3s = 24.00 t/s 5.59.561.282 I slot print_timing: id 1 | task 6236 | n_gen = 172, tg = 23.99 t/s, tg_3s = 23.99 t/s 5.59.769.264 I slot print_timing: id 0 | task 5691 | n_gen = 716, tg = 21.16 t/s, tg_3s = 24.00 t/s 6.02.312.859 I slot print_timing: id 2 | task 6155 | n_gen = 317, tg = 21.77 t/s, tg_3s = 23.99 t/s 6.02.354.811 I slot print_timing: id 3 | task 6229 | n_gen = 245, tg = 22.44 t/s, tg_3s = 23.99 t/s 6.02.562.263 I slot print_timing: id 1 | task 6236 | n_gen = 244, tg = 23.99 t/s, tg_3s = 23.99 t/s 6.02.770.070 I slot print_timing: id 0 | task 5691 | n_gen = 788, tg = 21.39 t/s, tg_3s = 23.99 t/s 6.05.349.884 I slot print_timing: id 2 | task 6155 | n_gen = 390, tg = 22.16 t/s, tg_3s = 24.04 t/s 6.05.392.828 I slot print_timing: id 3 | task 6229 | n_gen = 318, tg = 22.79 t/s, tg_3s = 24.03 t/s 6.05.600.543 I slot print_timing: id 1 | task 6236 | n_gen = 317, tg = 24.00 t/s, tg_3s = 24.03 t/s 6.05.807.584 I slot print_timing: id 0 | task 5691 | n_gen = 861, tg = 21.60 t/s, tg_3s = 24.03 t/s 6.08.355.159 I slot print_timing: id 2 | task 6155 | n_gen = 462, tg = 22.43 t/s, tg_3s = 23.96 t/s 6.08.397.265 I slot print_timing: id 3 | task 6229 | n_gen = 390, tg = 23.00 t/s, tg_3s = 23.96 t/s 6.08.605.035 I slot print_timing: id 1 | task 6236 | n_gen = 389, tg = 23.99 t/s, tg_3s = 23.96 t/s 6.08.812.913 I slot print_timing: id 0 | task 5691 | n_gen = 933, tg = 21.76 t/s, tg_3s = 23.96 t/s 6.10.196.588 I slot print_timing: id 0 | task 5691 | prompt eval time = 681.39 ms / 448 tokens ( 1.52 ms per token, 657.48 tokens per second) 6.10.196.592 I slot print_timing: id 0 | task 5691 | eval time = 44212.34 ms / 966 tokens ( 45.82 ms per token, 21.83 tokens per second) 6.10.196.593 I slot print_timing: id 0 | task 5691 | total time = 44893.72 ms / 1414 tokens 6.10.196.594 I slot print_timing: id 0 | task 5691 | graphs reused = 6203 6.10.196.595 I slot print_timing: id 0 | task 5691 | graph reallocs = 0 / 0 (same size) / (changed size) 6.10.196.708 I slot release: id 0 | task 5691 | stop processing: n_tokens = 2108, truncated = 0 6.10.235.111 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.507 6.10.235.149 I slot launch_slot_: id 0 | task 6666 | processing task, is_child = 0 6.11.362.249 I slot print_timing: id 2 | task 6155 | n_gen = 519, tg = 21.98 t/s, tg_3s = 18.96 t/s 6.11.405.587 I slot print_timing: id 3 | task 6229 | n_gen = 447, tg = 22.38 t/s, tg_3s = 18.95 t/s 6.11.614.954 I slot print_timing: id 1 | task 6236 | n_gen = 446, tg = 23.20 t/s, tg_3s = 18.94 t/s 6.14.366.087 I slot print_timing: id 2 | task 6155 | n_gen = 591, tg = 22.21 t/s, tg_3s = 23.97 t/s 6.14.407.919 I slot print_timing: id 3 | task 6229 | n_gen = 519, tg = 22.59 t/s, tg_3s = 23.98 t/s 6.14.656.424 I slot print_timing: id 1 | task 6236 | n_gen = 519, tg = 23.31 t/s, tg_3s = 24.00 t/s 6.14.741.991 I slot print_timing: id 3 | task 6229 | prompt eval time = 730.72 ms / 482 tokens ( 1.52 ms per token, 659.63 tokens per second) 6.14.741.995 I slot print_timing: id 3 | task 6229 | eval time = 23260.76 ms / 527 tokens ( 44.22 ms per token, 22.61 tokens per second) 6.14.741.996 I slot print_timing: id 3 | task 6229 | total time = 23991.47 ms / 1009 tokens 6.14.741.997 I slot print_timing: id 3 | task 6229 | graphs reused = 6294 6.14.741.997 I slot print_timing: id 3 | task 6229 | graph reallocs = 0 / 0 (same size) / (changed size) 6.14.742.122 I slot release: id 3 | task 6229 | stop processing: n_tokens = 1681, truncated = 0 6.14.778.534 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.635 6.14.778.564 I slot launch_slot_: id 3 | task 6761 | processing task, is_child = 0 6.15.725.623 I slot print_timing: id 0 | task 6666 | n_gen = 100, tg = 20.74 t/s, tg_3s = 20.95 t/s 6.17.397.685 I slot print_timing: id 2 | task 6155 | n_gen = 648, tg = 21.86 t/s, tg_3s = 18.80 t/s 6.17.689.668 I slot print_timing: id 1 | task 6236 | n_gen = 576, tg = 22.77 t/s, tg_3s = 18.79 t/s 6.18.733.710 I slot print_timing: id 0 | task 6666 | n_gen = 172, tg = 21.98 t/s, tg_3s = 23.94 t/s 6.19.651.672 I slot print_timing: id 3 | task 6761 | n_gen = 100, tg = 23.96 t/s, tg_3s = 24.21 t/s 6.20.400.636 I slot print_timing: id 2 | task 6155 | n_gen = 720, tg = 22.05 t/s, tg_3s = 23.98 t/s 6.20.690.560 I slot print_timing: id 1 | task 6236 | n_gen = 648, tg = 22.90 t/s, tg_3s = 23.99 t/s 6.21.772.482 I slot print_timing: id 0 | task 6666 | n_gen = 245, tg = 22.55 t/s, tg_3s = 24.02 t/s 6.22.689.438 I slot print_timing: id 3 | task 6761 | n_gen = 173, tg = 23.99 t/s, tg_3s = 24.03 t/s 6.23.439.537 I slot print_timing: id 2 | task 6155 | n_gen = 793, tg = 22.22 t/s, tg_3s = 24.02 t/s 6.23.730.339 I slot print_timing: id 1 | task 6236 | n_gen = 721, tg = 23.00 t/s, tg_3s = 24.01 t/s 6.24.814.153 I slot print_timing: id 0 | task 6666 | n_gen = 318, tg = 22.87 t/s, tg_3s = 24.00 t/s 6.25.689.919 I slot print_timing: id 3 | task 6761 | n_gen = 245, tg = 23.99 t/s, tg_3s = 24.00 t/s 6.26.479.614 I slot print_timing: id 2 | task 6155 | n_gen = 866, tg = 22.36 t/s, tg_3s = 24.01 t/s 6.26.769.874 I slot print_timing: id 1 | task 6236 | n_gen = 794, tg = 23.09 t/s, tg_3s = 24.02 t/s 6.27.852.105 I slot print_timing: id 0 | task 6666 | n_gen = 391, tg = 23.08 t/s, tg_3s = 24.03 t/s 6.27.978.276 I slot print_timing: id 1 | task 6236 | prompt eval time = 784.77 ms / 514 tokens ( 1.53 ms per token, 654.97 tokens per second) 6.27.978.281 I slot print_timing: id 1 | task 6236 | eval time = 35546.24 ms / 823 tokens ( 43.24 ms per token, 23.12 tokens per second) 6.27.978.282 I slot print_timing: id 1 | task 6236 | total time = 36331.01 ms / 1337 tokens 6.27.978.283 I slot print_timing: id 1 | task 6236 | graphs reused = 6591 6.27.978.283 I slot print_timing: id 1 | task 6236 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.978.420 I slot release: id 1 | task 6236 | stop processing: n_tokens = 2011, truncated = 0 6.28.022.942 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.531 6.28.022.980 I slot launch_slot_: id 1 | task 7064 | processing task, is_child = 0 6.28.707.755 I slot print_timing: id 3 | task 6761 | n_gen = 302, tg = 22.82 t/s, tg_3s = 18.89 t/s 6.29.503.077 I slot print_timing: id 2 | task 6155 | n_gen = 922, tg = 22.08 t/s, tg_3s = 18.52 t/s 6.30.887.013 I slot print_timing: id 0 | task 6666 | n_gen = 447, tg = 22.37 t/s, tg_3s = 18.45 t/s 6.31.729.115 I slot print_timing: id 3 | task 6761 | n_gen = 373, tg = 22.95 t/s, tg_3s = 23.50 t/s 6.32.522.309 I slot print_timing: id 2 | task 6155 | n_gen = 994, tg = 22.20 t/s, tg_3s = 23.85 t/s 6.32.939.011 I slot print_timing: id 1 | task 7064 | n_gen = 100, tg = 23.84 t/s, tg_3s = 24.08 t/s 6.33.693.902 I slot print_timing: id 2 | task 6155 | prompt eval time = 742.67 ms / 482 tokens ( 1.54 ms per token, 649.01 tokens per second) 6.33.693.909 I slot print_timing: id 2 | task 6155 | eval time = 45894.71 ms / 1022 tokens ( 44.95 ms per token, 22.25 tokens per second) 6.33.693.910 I slot print_timing: id 2 | task 6155 | total time = 46637.38 ms / 1504 tokens 6.33.693.911 I slot print_timing: id 2 | task 6155 | graphs reused = 6706 6.33.693.911 I slot print_timing: id 2 | task 6155 | graph reallocs = 0 / 0 (same size) / (changed size) 6.33.694.007 I slot release: id 2 | task 6155 | stop processing: n_tokens = 2158, truncated = 0 6.33.737.555 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.495 6.33.743.560 I slot launch_slot_: id 2 | task 7185 | processing task, is_child = 0 6.34.548.165 I slot print_timing: id 0 | task 6666 | n_gen = 517, tg = 21.87 t/s, tg_3s = 19.12 t/s 6.34.750.567 I slot print_timing: id 3 | task 6761 | n_gen = 427, tg = 22.15 t/s, tg_3s = 17.87 t/s 6.35.959.541 I slot print_timing: id 1 | task 7064 | n_gen = 154, tg = 21.33 t/s, tg_3s = 17.88 t/s 6.37.587.976 I slot print_timing: id 0 | task 6666 | n_gen = 589, tg = 22.08 t/s, tg_3s = 23.69 t/s 6.37.756.078 I slot print_timing: id 3 | task 6761 | n_gen = 499, tg = 22.40 t/s, tg_3s = 23.96 t/s 6.38.754.963 I slot print_timing: id 2 | task 7185 | n_gen = 100, tg = 23.99 t/s, tg_3s = 24.23 t/s 6.38.965.517 I slot print_timing: id 1 | task 7064 | n_gen = 226, tg = 22.11 t/s, tg_3s = 23.95 t/s 6.40.628.535 I slot print_timing: id 0 | task 6666 | n_gen = 662, tg = 22.27 t/s, tg_3s = 24.01 t/s 6.40.797.328 I slot print_timing: id 3 | task 6761 | n_gen = 572, tg = 22.59 t/s, tg_3s = 24.00 t/s 6.41.755.770 I slot print_timing: id 2 | task 7185 | n_gen = 172, tg = 23.99 t/s, tg_3s = 23.99 t/s 6.42.004.685 I slot print_timing: id 1 | task 7064 | n_gen = 299, tg = 22.55 t/s, tg_3s = 24.02 t/s 6.42.879.943 I slot print_timing: id 3 | task 6761 | prompt eval time = 741.87 ms / 486 tokens ( 1.53 ms per token, 655.10 tokens per second) 6.42.879.951 I slot print_timing: id 3 | task 6761 | eval time = 27359.50 ms / 622 tokens ( 44.06 ms per token, 22.70 tokens per second) 6.42.879.952 I slot print_timing: id 3 | task 6761 | total time = 28101.37 ms / 1108 tokens 6.42.879.953 I slot print_timing: id 3 | task 6761 | graphs reused = 6902 6.42.879.954 I slot print_timing: id 3 | task 6761 | graph reallocs = 0 / 0 (same size) / (changed size) 6.42.880.077 I slot release: id 3 | task 6761 | stop processing: n_tokens = 1780, truncated = 0 6.42.916.023 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.600 6.42.916.058 I slot launch_slot_: id 3 | task 7388 | processing task, is_child = 0 6.43.633.977 I slot print_timing: id 0 | task 6666 | n_gen = 719, tg = 21.97 t/s, tg_3s = 18.97 t/s 6.43.798.374 I slot print_timing: id 0 | task 6666 | prompt eval time = 716.99 ms / 478 tokens ( 1.50 ms per token, 666.67 tokens per second) 6.43.798.379 I slot print_timing: id 0 | task 6666 | eval time = 32846.22 ms / 723 tokens ( 45.49 ms per token, 21.98 tokens per second) 6.43.798.379 I slot print_timing: id 0 | task 6666 | total time = 33563.22 ms / 1201 tokens 6.43.798.380 I slot print_timing: id 0 | task 6666 | graphs reused = 6905 6.43.798.380 I slot print_timing: id 0 | task 6666 | graph reallocs = 0 / 0 (same size) / (changed size) 6.43.798.437 I slot release: id 0 | task 6666 | stop processing: n_tokens = 1895, truncated = 0 6.43.833.222 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.564 6.43.833.249 I slot launch_slot_: id 0 | task 7396 | processing task, is_child = 0 6.44.775.789 I slot print_timing: id 2 | task 7185 | n_gen = 215, tg = 21.09 t/s, tg_3s = 14.24 t/s 6.45.018.093 I slot print_timing: id 1 | task 7064 | n_gen = 342, tg = 21.01 t/s, tg_3s = 14.27 t/s 6.47.807.138 I slot print_timing: id 2 | task 7185 | n_gen = 288, tg = 21.78 t/s, tg_3s = 24.08 t/s 6.48.055.317 I slot print_timing: id 1 | task 7064 | n_gen = 415, tg = 21.49 t/s, tg_3s = 24.04 t/s 6.48.347.325 I slot print_timing: id 3 | task 7388 | n_gen = 100, tg = 21.01 t/s, tg_3s = 21.22 t/s 6.48.637.737 I slot print_timing: id 0 | task 7396 | n_gen = 100, tg = 24.10 t/s, tg_3s = 24.34 t/s 6.50.846.576 I slot print_timing: id 2 | task 7185 | n_gen = 361, tg = 22.20 t/s, tg_3s = 24.02 t/s 6.51.097.471 I slot print_timing: id 1 | task 7064 | n_gen = 488, tg = 21.83 t/s, tg_3s = 24.00 t/s 6.51.349.164 I slot print_timing: id 3 | task 7388 | n_gen = 172, tg = 22.17 t/s, tg_3s = 23.99 t/s 6.51.638.166 I slot print_timing: id 0 | task 7396 | n_gen = 172, tg = 24.06 t/s, tg_3s = 24.00 t/s 6.53.851.595 I slot print_timing: id 2 | task 7185 | n_gen = 433, tg = 22.47 t/s, tg_3s = 23.96 t/s 6.54.099.913 I slot print_timing: id 1 | task 7064 | n_gen = 560, tg = 22.08 t/s, tg_3s = 23.98 t/s 6.54.352.496 I slot print_timing: id 3 | task 7388 | n_gen = 244, tg = 22.67 t/s, tg_3s = 23.97 t/s 6.54.642.294 I slot print_timing: id 0 | task 7396 | n_gen = 244, tg = 24.03 t/s, tg_3s = 23.97 t/s 6.56.855.040 I slot print_timing: id 2 | task 7185 | n_gen = 505, tg = 22.68 t/s, tg_3s = 23.97 t/s 6.57.103.685 I slot print_timing: id 1 | task 7064 | n_gen = 632, tg = 22.28 t/s, tg_3s = 23.97 t/s 6.57.353.261 I slot print_timing: id 3 | task 7388 | n_gen = 316, tg = 22.96 t/s, tg_3s = 23.99 t/s 6.57.643.162 I slot print_timing: id 0 | task 7396 | n_gen = 316, tg = 24.02 t/s, tg_3s = 23.99 t/s 6.58.018.832 I slot print_timing: id 2 | task 7185 | prompt eval time = 884.37 ms / 525 tokens ( 1.68 ms per token, 593.64 tokens per second) 6.58.018.836 I slot print_timing: id 2 | task 7185 | eval time = 23390.89 ms / 533 tokens ( 43.97 ms per token, 22.74 tokens per second) 6.58.018.836 I slot print_timing: id 2 | task 7185 | total time = 24275.26 ms / 1058 tokens 6.58.018.837 I slot print_timing: id 2 | task 7185 | graphs reused = 7227 6.58.018.837 I slot print_timing: id 2 | task 7185 | graph reallocs = 0 / 0 (same size) / (changed size) 6.58.018.954 I slot release: id 2 | task 7185 | stop processing: n_tokens = 1712, truncated = 0 6.58.062.078 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.624 6.58.062.116 I slot launch_slot_: id 2 | task 7724 | processing task, is_child = 0 7.00.105.871 I slot print_timing: id 1 | task 7064 | n_gen = 688, tg = 21.94 t/s, tg_3s = 18.65 t/s 7.00.358.078 I slot print_timing: id 3 | task 7388 | n_gen = 372, tg = 22.18 t/s, tg_3s = 18.64 t/s 7.00.647.717 I slot print_timing: id 0 | task 7396 | n_gen = 372, tg = 23.02 t/s, tg_3s = 18.64 t/s 7.02.944.184 I slot print_timing: id 2 | task 7724 | n_gen = 100, tg = 23.89 t/s, tg_3s = 24.14 t/s 7.03.110.070 I slot print_timing: id 1 | task 7064 | n_gen = 760, tg = 22.11 t/s, tg_3s = 23.97 t/s 7.03.361.840 I slot print_timing: id 3 | task 7388 | n_gen = 444, tg = 22.46 t/s, tg_3s = 23.97 t/s 7.03.653.060 I slot print_timing: id 0 | task 7396 | n_gen = 444, tg = 23.17 t/s, tg_3s = 23.96 t/s 7.03.947.699 I slot print_timing: id 3 | task 7388 | prompt eval time = 718.81 ms / 466 tokens ( 1.54 ms per token, 648.29 tokens per second) 7.03.947.707 I slot print_timing: id 3 | task 7388 | eval time = 20312.82 ms / 458 tokens ( 44.45 ms per token, 22.50 tokens per second) 7.03.947.708 I slot print_timing: id 3 | task 7388 | total time = 21031.63 ms / 924 tokens 7.03.947.708 I slot print_timing: id 3 | task 7388 | graphs reused = 7349 7.03.947.709 I slot print_timing: id 3 | task 7388 | graph reallocs = 0 / 0 (same size) / (changed size) 7.03.947.814 I slot release: id 3 | task 7388 | stop processing: n_tokens = 1596, truncated = 0 7.03.983.401 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.669 7.03.983.436 I slot launch_slot_: id 3 | task 7851 | processing task, is_child = 0 7.05.961.732 I slot print_timing: id 2 | task 7724 | n_gen = 157, tg = 21.79 t/s, tg_3s = 18.89 t/s 7.06.128.428 I slot print_timing: id 1 | task 7064 | n_gen = 817, tg = 21.85 t/s, tg_3s = 18.88 t/s 7.06.668.807 I slot print_timing: id 0 | task 7396 | n_gen = 501, tg = 22.58 t/s, tg_3s = 18.90 t/s 7.08.840.240 I slot print_timing: id 3 | task 7851 | n_gen = 100, tg = 23.94 t/s, tg_3s = 24.19 t/s 7.08.965.151 I slot print_timing: id 2 | task 7724 | n_gen = 229, tg = 22.43 t/s, tg_3s = 23.97 t/s 7.09.132.278 I slot print_timing: id 1 | task 7064 | n_gen = 889, tg = 22.01 t/s, tg_3s = 23.97 t/s 7.09.675.990 I slot print_timing: id 0 | task 7396 | n_gen = 573, tg = 22.75 t/s, tg_3s = 23.94 t/s 7.11.859.745 I slot print_timing: id 3 | task 7851 | n_gen = 172, tg = 23.90 t/s, tg_3s = 23.84 t/s 7.11.984.838 I slot print_timing: id 2 | task 7724 | n_gen = 301, tg = 22.76 t/s, tg_3s = 23.84 t/s 7.12.152.188 I slot print_timing: id 1 | task 7064 | n_gen = 961, tg = 22.14 t/s, tg_3s = 23.84 t/s 7.12.697.075 I slot print_timing: id 0 | task 7396 | n_gen = 645, tg = 22.86 t/s, tg_3s = 23.83 t/s 7.14.793.842 I slot print_timing: id 1 | task 7064 | prompt eval time = 763.84 ms / 496 tokens ( 1.54 ms per token, 649.35 tokens per second) 7.14.793.850 I slot print_timing: id 1 | task 7064 | eval time = 46007.01 ms / 1024 tokens ( 44.97 ms per token, 22.24 tokens per second) 7.14.793.851 I slot print_timing: id 1 | task 7064 | total time = 46770.85 ms / 1520 tokens 7.14.793.852 I slot print_timing: id 1 | task 7064 | graphs reused = 7588 7.14.793.853 I slot print_timing: id 1 | task 7064 | graph reallocs = 0 / 0 (same size) / (changed size) 7.14.794.009 I slot release: id 1 | task 7064 | stop processing: n_tokens = 2194, truncated = 0 7.14.838.721 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.487 7.14.845.373 I slot launch_slot_: id 1 | task 8096 | processing task, is_child = 0 7.15.503.876 I slot print_timing: id 2 | task 7724 | n_gen = 370, tg = 22.09 t/s, tg_3s = 19.61 t/s 7.15.504.164 I slot print_timing: id 3 | task 7851 | n_gen = 244, tg = 22.50 t/s, tg_3s = 19.76 t/s 7.15.706.300 I slot print_timing: id 0 | task 7396 | n_gen = 701, tg = 22.45 t/s, tg_3s = 18.61 t/s 7.18.497.891 I slot print_timing: id 2 | task 7724 | prompt eval time = 738.88 ms / 478 tokens ( 1.55 ms per token, 646.93 tokens per second) 7.18.497.898 I slot print_timing: id 2 | task 7724 | eval time = 19696.89 ms / 441 tokens ( 44.77 ms per token, 22.34 tokens per second) 7.18.497.899 I slot print_timing: id 2 | task 7724 | total time = 20435.77 ms / 919 tokens 7.18.497.899 I slot print_timing: id 2 | task 7724 | graphs reused = 7657 7.18.497.900 I slot print_timing: id 2 | task 7724 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.498.019 I slot release: id 2 | task 7724 | stop processing: n_tokens = 1582, truncated = 0 7.18.541.004 I slot print_timing: id 3 | task 7851 | n_gen = 316, tg = 22.77 t/s, tg_3s = 23.71 t/s 7.18.541.012 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.675 7.18.541.048 I slot launch_slot_: id 2 | task 8170 | processing task, is_child = 0 7.19.229.756 I slot print_timing: id 0 | task 7396 | n_gen = 770, tg = 22.16 t/s, tg_3s = 19.58 t/s 7.19.931.231 I slot print_timing: id 0 | task 7396 | prompt eval time = 696.34 ms / 453 tokens ( 1.54 ms per token, 650.55 tokens per second) 7.19.931.239 I slot print_timing: id 0 | task 7396 | eval time = 35401.64 ms / 786 tokens ( 45.10 ms per token, 22.17 tokens per second) 7.19.931.241 I slot print_timing: id 0 | task 7396 | total time = 36097.98 ms / 1239 tokens 7.19.931.242 I slot print_timing: id 0 | task 7396 | graphs reused = 7671 7.19.931.243 I slot print_timing: id 0 | task 7396 | graph reallocs = 0 / 0 (same size) / (changed size) 7.19.931.358 I slot release: id 0 | task 7396 | stop processing: n_tokens = 1933, truncated = 0 7.19.969.467 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.553 7.19.969.504 I slot launch_slot_: id 0 | task 8189 | processing task, is_child = 0 7.21.007.079 I slot print_timing: id 1 | task 8096 | n_gen = 100, tg = 18.25 t/s, tg_3s = 18.44 t/s 7.21.556.924 I slot print_timing: id 3 | task 7851 | n_gen = 357, tg = 21.13 t/s, tg_3s = 13.59 t/s 7.24.011.149 I slot print_timing: id 1 | task 8096 | n_gen = 172, tg = 20.29 t/s, tg_3s = 23.97 t/s 7.24.053.026 I slot print_timing: id 2 | task 8170 | n_gen = 100, tg = 20.87 t/s, tg_3s = 21.08 t/s 7.24.594.352 I slot print_timing: id 3 | task 7851 | prompt eval time = 722.06 ms / 470 tokens ( 1.54 ms per token, 650.92 tokens per second) 7.24.594.359 I slot print_timing: id 3 | task 7851 | eval time = 19888.85 ms / 430 tokens ( 46.36 ms per token, 21.57 tokens per second) 7.24.594.361 I slot print_timing: id 3 | task 7851 | total time = 20610.91 ms / 900 tokens 7.24.594.362 I slot print_timing: id 3 | task 7851 | graphs reused = 7764 7.24.594.363 I slot print_timing: id 3 | task 7851 | graph reallocs = 0 / 0 (same size) / (changed size) 7.24.594.458 I slot release: id 3 | task 7851 | stop processing: n_tokens = 1572, truncated = 0 7.24.630.267 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.679 7.24.630.298 I slot launch_slot_: id 3 | task 8287 | processing task, is_child = 0 7.25.439.777 I slot print_timing: id 0 | task 8189 | n_gen = 100, tg = 20.80 t/s, tg_3s = 21.01 t/s 7.27.022.286 I slot print_timing: id 1 | task 8096 | n_gen = 229, tg = 19.93 t/s, tg_3s = 18.93 t/s 7.27.064.402 I slot print_timing: id 2 | task 8170 | n_gen = 157, tg = 20.12 t/s, tg_3s = 18.93 t/s 7.28.479.384 I slot print_timing: id 0 | task 8189 | n_gen = 173, tg = 22.06 t/s, tg_3s = 24.02 t/s 7.29.480.627 I slot print_timing: id 3 | task 8287 | n_gen = 100, tg = 24.01 t/s, tg_3s = 24.26 t/s 7.30.061.643 I slot print_timing: id 1 | task 8096 | n_gen = 302, tg = 20.79 t/s, tg_3s = 24.02 t/s 7.30.103.816 I slot print_timing: id 2 | task 8170 | n_gen = 230, tg = 21.21 t/s, tg_3s = 24.02 t/s 7.31.517.974 I slot print_timing: id 0 | task 8189 | n_gen = 246, tg = 22.61 t/s, tg_3s = 24.02 t/s 7.32.518.752 I slot print_timing: id 3 | task 8287 | n_gen = 173, tg = 24.02 t/s, tg_3s = 24.03 t/s 7.33.099.831 I slot print_timing: id 1 | task 8096 | n_gen = 375, tg = 21.35 t/s, tg_3s = 24.03 t/s 7.33.141.994 I slot print_timing: id 2 | task 8170 | n_gen = 303, tg = 21.83 t/s, tg_3s = 24.03 t/s 7.34.518.241 I slot print_timing: id 0 | task 8189 | n_gen = 318, tg = 22.91 t/s, tg_3s = 24.00 t/s 7.35.558.246 I slot print_timing: id 3 | task 8287 | n_gen = 246, tg = 24.02 t/s, tg_3s = 24.02 t/s 7.36.139.647 I slot print_timing: id 1 | task 8096 | n_gen = 448, tg = 21.75 t/s, tg_3s = 24.01 t/s 7.36.182.225 I slot print_timing: id 2 | task 8170 | n_gen = 376, tg = 22.22 t/s, tg_3s = 24.01 t/s 7.37.555.741 I slot print_timing: id 0 | task 8189 | n_gen = 391, tg = 23.11 t/s, tg_3s = 24.03 t/s 7.38.598.751 I slot print_timing: id 3 | task 8287 | n_gen = 319, tg = 24.02 t/s, tg_3s = 24.01 t/s 7.39.139.756 I slot print_timing: id 1 | task 8096 | n_gen = 520, tg = 22.03 t/s, tg_3s = 24.00 t/s 7.39.223.415 I slot print_timing: id 2 | task 8170 | n_gen = 449, tg = 22.50 t/s, tg_3s = 24.00 t/s 7.40.098.090 I slot print_timing: id 1 | task 8096 | prompt eval time = 738.22 ms / 476 tokens ( 1.55 ms per token, 644.80 tokens per second) 7.40.098.095 I slot print_timing: id 1 | task 8096 | eval time = 24514.48 ms / 543 tokens ( 45.23 ms per token, 22.11 tokens per second) 7.40.098.096 I slot print_timing: id 1 | task 8096 | total time = 25252.70 ms / 1019 tokens 7.40.098.097 I slot print_timing: id 1 | task 8096 | graphs reused = 8116 7.40.098.098 I slot print_timing: id 1 | task 8096 | graph reallocs = 0 / 0 (same size) / (changed size) 7.40.098.221 I slot release: id 1 | task 8096 | stop processing: n_tokens = 1693, truncated = 0 7.40.142.550 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.631 7.40.142.592 I slot launch_slot_: id 1 | task 8645 | processing task, is_child = 0 7.40.787.199 I slot print_timing: id 0 | task 8189 | n_gen = 454, tg = 22.53 t/s, tg_3s = 19.50 t/s 7.41.618.135 I slot print_timing: id 3 | task 8287 | n_gen = 376, tg = 23.06 t/s, tg_3s = 18.88 t/s 7.41.659.424 I slot print_timing: id 2 | task 8170 | prompt eval time = 768.13 ms / 502 tokens ( 1.53 ms per token, 653.54 tokens per second) 7.41.659.432 I slot print_timing: id 2 | task 8170 | eval time = 22350.24 ms / 492 tokens ( 45.52 ms per token, 21.97 tokens per second) 7.41.659.433 I slot print_timing: id 2 | task 8170 | total time = 23118.37 ms / 994 tokens 7.41.659.434 I slot print_timing: id 2 | task 8170 | graphs reused = 8134 7.41.659.435 I slot print_timing: id 2 | task 8170 | graph reallocs = 0 / 0 (same size) / (changed size) 7.41.659.570 I slot release: id 2 | task 8170 | stop processing: n_tokens = 1657, truncated = 0 7.41.703.465 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.645 7.41.703.497 I slot launch_slot_: id 2 | task 8668 | processing task, is_child = 0 7.43.788.538 I slot print_timing: id 0 | task 8189 | n_gen = 509, tg = 21.98 t/s, tg_3s = 18.33 t/s 7.44.623.615 I slot print_timing: id 3 | task 8287 | n_gen = 432, tg = 22.37 t/s, tg_3s = 18.63 t/s 7.45.663.308 I slot print_timing: id 1 | task 8645 | n_gen = 100, tg = 20.64 t/s, tg_3s = 20.85 t/s 7.46.579.412 I slot print_timing: id 2 | task 8668 | n_gen = 100, tg = 24.02 t/s, tg_3s = 24.26 t/s 7.46.827.972 I slot print_timing: id 0 | task 8189 | n_gen = 582, tg = 22.22 t/s, tg_3s = 24.02 t/s 7.47.663.400 I slot print_timing: id 3 | task 8287 | n_gen = 505, tg = 22.60 t/s, tg_3s = 24.01 t/s 7.48.704.486 I slot print_timing: id 1 | task 8645 | n_gen = 173, tg = 21.95 t/s, tg_3s = 24.00 t/s 7.48.705.500 I slot print_timing: id 3 | task 8287 | prompt eval time = 727.62 ms / 476 tokens ( 1.53 ms per token, 654.18 tokens per second) 7.48.705.507 I slot print_timing: id 3 | task 8287 | eval time = 23347.57 ms / 530 tokens ( 44.14 ms per token, 22.66 tokens per second) 7.48.705.508 I slot print_timing: id 3 | task 8287 | total time = 24075.19 ms / 1006 tokens 7.48.705.509 I slot print_timing: id 3 | task 8287 | graphs reused = 8283 7.48.705.510 I slot print_timing: id 3 | task 8287 | graph reallocs = 0 / 0 (same size) / (changed size) 7.48.705.618 I slot release: id 3 | task 8287 | stop processing: n_tokens = 1678, truncated = 0 7.48.741.423 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.636 7.48.741.467 I slot launch_slot_: id 3 | task 8822 | processing task, is_child = 0 7.49.581.917 I slot print_timing: id 2 | task 8668 | n_gen = 157, tg = 21.90 t/s, tg_3s = 18.98 t/s 7.49.866.281 I slot print_timing: id 0 | task 8189 | n_gen = 640, tg = 21.89 t/s, tg_3s = 19.09 t/s 7.51.742.005 I slot print_timing: id 1 | task 8645 | n_gen = 231, tg = 21.15 t/s, tg_3s = 19.09 t/s 7.52.617.508 I slot print_timing: id 2 | task 8668 | n_gen = 230, tg = 22.54 t/s, tg_3s = 24.05 t/s 7.52.907.849 I slot print_timing: id 0 | task 8189 | n_gen = 713, tg = 22.09 t/s, tg_3s = 24.00 t/s 7.53.576.611 I slot print_timing: id 3 | task 8822 | n_gen = 100, tg = 24.04 t/s, tg_3s = 24.29 t/s 7.54.744.884 I slot print_timing: id 1 | task 8645 | n_gen = 303, tg = 21.76 t/s, tg_3s = 23.98 t/s 7.55.621.027 I slot print_timing: id 2 | task 8668 | n_gen = 302, tg = 22.87 t/s, tg_3s = 23.97 t/s 7.55.912.659 I slot print_timing: id 0 | task 8189 | n_gen = 785, tg = 22.25 t/s, tg_3s = 23.96 t/s 7.56.581.382 I slot print_timing: id 3 | task 8822 | n_gen = 172, tg = 24.01 t/s, tg_3s = 23.96 t/s 7.57.783.156 I slot print_timing: id 1 | task 8645 | n_gen = 376, tg = 22.17 t/s, tg_3s = 24.03 t/s 7.58.659.051 I slot print_timing: id 2 | task 8668 | n_gen = 375, tg = 23.09 t/s, tg_3s = 24.03 t/s 7.58.947.779 I slot print_timing: id 0 | task 8189 | n_gen = 858, tg = 22.40 t/s, tg_3s = 24.05 t/s 7.59.618.098 I slot print_timing: id 3 | task 8822 | n_gen = 245, tg = 24.02 t/s, tg_3s = 24.04 t/s 7.59.906.810 I slot print_timing: id 0 | task 8189 | prompt eval time = 711.42 ms / 471 tokens ( 1.51 ms per token, 662.05 tokens per second) 7.59.906.815 I slot print_timing: id 0 | task 8189 | eval time = 39225.88 ms / 881 tokens ( 44.57 ms per token, 22.43 tokens per second) 7.59.906.816 I slot print_timing: id 0 | task 8189 | total time = 39937.30 ms / 1352 tokens 7.59.906.817 I slot print_timing: id 0 | task 8189 | graphs reused = 8533 7.59.906.817 I slot print_timing: id 0 | task 8189 | graph reallocs = 0 / 0 (same size) / (changed size) 7.59.906.920 I slot release: id 0 | task 8189 | stop processing: n_tokens = 2046, truncated = 0 7.59.944.451 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.522 7.59.944.488 I slot launch_slot_: id 0 | task 9077 | processing task, is_child = 0 8.00.787.581 I slot print_timing: id 1 | task 8645 | n_gen = 434, tg = 21.74 t/s, tg_3s = 19.30 t/s 8.01.691.141 I slot print_timing: id 2 | task 8668 | n_gen = 434, tg = 22.51 t/s, tg_3s = 19.46 t/s 8.02.649.296 I slot print_timing: id 3 | task 8822 | n_gen = 304, tg = 22.97 t/s, tg_3s = 19.46 t/s 8.03.814.825 I slot print_timing: id 1 | task 8645 | prompt eval time = 724.41 ms / 455 tokens ( 1.59 ms per token, 628.10 tokens per second) 8.03.814.829 I slot print_timing: id 1 | task 8645 | eval time = 22947.81 ms / 507 tokens ( 45.35 ms per token, 22.05 tokens per second) 8.03.814.830 I slot print_timing: id 1 | task 8645 | total time = 23672.22 ms / 962 tokens 8.03.814.831 I slot print_timing: id 1 | task 8645 | graphs reused = 8610 8.03.814.831 I slot print_timing: id 1 | task 8645 | graph reallocs = 0 / 0 (same size) / (changed size) 8.03.814.940 I slot release: id 1 | task 8645 | stop processing: n_tokens = 1636, truncated = 0 8.03.858.782 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.653 8.03.858.818 I slot launch_slot_: id 1 | task 9158 | processing task, is_child = 0 8.04.703.137 I slot print_timing: id 2 | task 8668 | n_gen = 490, tg = 21.98 t/s, tg_3s = 18.59 t/s 8.05.407.206 I slot print_timing: id 0 | task 9077 | n_gen = 100, tg = 20.69 t/s, tg_3s = 20.90 t/s 8.05.657.107 I slot print_timing: id 3 | task 8822 | n_gen = 360, tg = 22.16 t/s, tg_3s = 18.62 t/s 8.07.277.191 I slot print_timing: id 3 | task 8822 | prompt eval time = 717.78 ms / 466 tokens ( 1.54 ms per token, 649.22 tokens per second) 8.07.277.196 I slot print_timing: id 3 | task 8822 | eval time = 17817.93 ms / 399 tokens ( 44.77 ms per token, 22.34 tokens per second) 8.07.277.198 I slot print_timing: id 3 | task 8822 | total time = 18535.72 ms / 865 tokens 8.07.277.199 I slot print_timing: id 3 | task 8822 | graphs reused = 8673 8.07.277.200 I slot print_timing: id 3 | task 8822 | graph reallocs = 0 / 0 (same size) / (changed size) 8.07.277.304 I slot release: id 3 | task 8822 | stop processing: n_tokens = 1537, truncated = 0 8.07.312.728 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.695 8.07.312.768 I slot launch_slot_: id 3 | task 9226 | processing task, is_child = 0 8.07.964.672 I slot print_timing: id 2 | task 8668 | n_gen = 554, tg = 21.68 t/s, tg_3s = 19.62 t/s 8.08.453.486 I slot print_timing: id 0 | task 9077 | n_gen = 158, tg = 20.05 t/s, tg_3s = 19.04 t/s 8.09.371.484 I slot print_timing: id 1 | task 9158 | n_gen = 100, tg = 20.84 t/s, tg_3s = 21.05 t/s 8.10.999.438 I slot print_timing: id 2 | task 8668 | n_gen = 626, tg = 21.90 t/s, tg_3s = 23.73 t/s 8.11.455.865 I slot print_timing: id 0 | task 9077 | n_gen = 230, tg = 21.14 t/s, tg_3s = 23.98 t/s 8.12.169.719 I slot print_timing: id 3 | task 9226 | n_gen = 100, tg = 23.95 t/s, tg_3s = 24.20 t/s 8.12.376.451 I slot print_timing: id 1 | task 9158 | n_gen = 172, tg = 22.05 t/s, tg_3s = 23.96 t/s 8.13.706.687 I slot print_timing: id 2 | task 8668 | prompt eval time = 754.57 ms / 487 tokens ( 1.55 ms per token, 645.40 tokens per second) 8.13.706.694 I slot print_timing: id 2 | task 8668 | eval time = 31248.61 ms / 691 tokens ( 45.29 ms per token, 22.08 tokens per second) 8.13.706.695 I slot print_timing: id 2 | task 8668 | total time = 32003.18 ms / 1178 tokens 8.13.706.696 I slot print_timing: id 2 | task 8668 | graphs reused = 8807 8.13.706.696 I slot print_timing: id 2 | task 8668 | graph reallocs = 0 / 0 (same size) / (changed size) 8.13.706.801 I slot release: id 2 | task 8668 | stop processing: n_tokens = 1841, truncated = 0 8.13.750.344 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.580 8.13.750.384 I slot launch_slot_: id 2 | task 9366 | processing task, is_child = 0 8.14.484.451 I slot print_timing: id 0 | task 9077 | n_gen = 287, tg = 20.63 t/s, tg_3s = 18.82 t/s 8.15.195.357 I slot print_timing: id 3 | task 9226 | n_gen = 157, tg = 21.79 t/s, tg_3s = 18.84 t/s 8.15.402.069 I slot print_timing: id 1 | task 9158 | n_gen = 229, tg = 21.15 t/s, tg_3s = 18.84 t/s 8.16.442.342 I slot print_timing: id 0 | task 9077 | prompt eval time = 677.99 ms / 439 tokens ( 1.54 ms per token, 647.50 tokens per second) 8.16.442.349 I slot print_timing: id 0 | task 9077 | eval time = 15819.85 ms / 334 tokens ( 47.51 ms per token, 21.05 tokens per second) 8.16.442.349 I slot print_timing: id 0 | task 9077 | total time = 16497.85 ms / 773 tokens 8.16.442.350 I slot print_timing: id 0 | task 9077 | graphs reused = 8853 8.16.442.351 I slot print_timing: id 0 | task 9077 | graph reallocs = 0 / 0 (same size) / (changed size) 8.16.442.444 I slot release: id 0 | task 9077 | stop processing: n_tokens = 1467, truncated = 0 8.16.479.853 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.728 8.16.479.898 I slot launch_slot_: id 0 | task 9417 | processing task, is_child = 0 8.18.206.911 I slot print_timing: id 3 | task 9226 | n_gen = 214, tg = 20.94 t/s, tg_3s = 18.93 t/s 8.18.413.412 I slot print_timing: id 1 | task 9158 | n_gen = 286, tg = 20.66 t/s, tg_3s = 18.93 t/s 8.19.244.967 I slot print_timing: id 2 | task 9366 | n_gen = 100, tg = 20.80 t/s, tg_3s = 21.01 t/s 8.21.244.494 I slot print_timing: id 3 | task 9226 | n_gen = 287, tg = 21.65 t/s, tg_3s = 24.03 t/s 8.21.325.832 I slot print_timing: id 0 | task 9417 | n_gen = 100, tg = 24.07 t/s, tg_3s = 24.31 t/s 8.21.452.307 I slot print_timing: id 1 | task 9158 | n_gen = 359, tg = 21.27 t/s, tg_3s = 24.02 t/s 8.22.246.382 I slot print_timing: id 2 | task 9366 | n_gen = 172, tg = 22.03 t/s, tg_3s = 23.99 t/s 8.24.285.765 I slot print_timing: id 3 | task 9226 | n_gen = 360, tg = 22.09 t/s, tg_3s = 24.00 t/s 8.24.326.018 I slot print_timing: id 0 | task 9417 | n_gen = 172, tg = 24.04 t/s, tg_3s = 24.00 t/s 8.24.492.927 I slot print_timing: id 1 | task 9158 | n_gen = 432, tg = 21.69 t/s, tg_3s = 24.01 t/s 8.25.282.691 I slot print_timing: id 2 | task 9366 | n_gen = 245, tg = 22.60 t/s, tg_3s = 24.04 t/s 8.27.323.470 I slot print_timing: id 3 | task 9226 | n_gen = 433, tg = 22.40 t/s, tg_3s = 24.03 t/s 8.27.363.343 I slot print_timing: id 0 | task 9417 | n_gen = 245, tg = 24.04 t/s, tg_3s = 24.03 t/s 8.27.530.610 I slot print_timing: id 1 | task 9158 | n_gen = 505, tg = 22.00 t/s, tg_3s = 24.03 t/s 8.28.075.078 I slot print_timing: id 1 | task 9158 | prompt eval time = 761.15 ms / 492 tokens ( 1.55 ms per token, 646.39 tokens per second) 8.28.075.086 I slot print_timing: id 1 | task 9158 | eval time = 23455.10 ms / 518 tokens ( 45.37 ms per token, 22.04 tokens per second) 8.28.075.087 I slot print_timing: id 1 | task 9158 | total time = 24216.25 ms / 1010 tokens 8.28.075.088 I slot print_timing: id 1 | task 9158 | graphs reused = 9113 8.28.075.088 I slot print_timing: id 1 | task 9158 | graph reallocs = 0 / 0 (same size) / (changed size) 8.28.075.191 I slot release: id 1 | task 9158 | stop processing: n_tokens = 1684, truncated = 0 8.28.119.490 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.634 8.28.119.532 I slot launch_slot_: id 1 | task 9682 | processing task, is_child = 0 8.28.784.269 I slot print_timing: id 2 | task 9366 | n_gen = 314, tg = 21.89 t/s, tg_3s = 19.71 t/s 8.29.615.284 I slot print_timing: id 3 | task 9226 | prompt eval time = 724.01 ms / 476 tokens ( 1.52 ms per token, 657.45 tokens per second) 8.29.615.290 I slot print_timing: id 3 | task 9226 | eval time = 21578.50 ms / 472 tokens ( 45.81 ms per token, 21.83 tokens per second) 8.29.615.291 I slot print_timing: id 3 | task 9226 | total time = 22302.51 ms / 948 tokens 8.29.615.292 I slot print_timing: id 3 | task 9226 | graphs reused = 9130 8.29.615.292 I slot print_timing: id 3 | task 9226 | graph reallocs = 0 / 0 (same size) / (changed size) 8.29.615.405 I slot release: id 3 | task 9226 | stop processing: n_tokens = 1620, truncated = 0 8.29.651.402 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.659 8.29.651.442 I slot launch_slot_: id 3 | task 9704 | processing task, is_child = 0 8.30.473.070 I slot print_timing: id 0 | task 9417 | n_gen = 286, tg = 21.49 t/s, tg_3s = 13.18 t/s 8.31.798.171 I slot print_timing: id 2 | task 9366 | n_gen = 367, tg = 21.14 t/s, tg_3s = 17.59 t/s 8.33.506.381 I slot print_timing: id 0 | task 9417 | n_gen = 358, tg = 21.91 t/s, tg_3s = 23.74 t/s 8.33.756.202 I slot print_timing: id 1 | task 9682 | n_gen = 100, tg = 20.24 t/s, tg_3s = 20.44 t/s 8.34.673.935 I slot print_timing: id 3 | task 9704 | n_gen = 100, tg = 23.98 t/s, tg_3s = 24.22 t/s 8.34.798.894 I slot print_timing: id 2 | task 9366 | n_gen = 439, tg = 21.56 t/s, tg_3s = 23.99 t/s 8.36.546.530 I slot print_timing: id 0 | task 9417 | n_gen = 431, tg = 22.24 t/s, tg_3s = 24.01 t/s 8.36.795.310 I slot print_timing: id 1 | task 9682 | n_gen = 173, tg = 21.69 t/s, tg_3s = 24.02 t/s 8.37.713.583 I slot print_timing: id 3 | task 9704 | n_gen = 173, tg = 24.00 t/s, tg_3s = 24.02 t/s 8.37.838.101 I slot print_timing: id 2 | task 9366 | n_gen = 512, tg = 21.88 t/s, tg_3s = 24.02 t/s 8.39.585.770 I slot print_timing: id 0 | task 9417 | n_gen = 504, tg = 22.48 t/s, tg_3s = 24.02 t/s 8.39.836.035 I slot print_timing: id 1 | task 9682 | n_gen = 246, tg = 22.33 t/s, tg_3s = 24.01 t/s 8.40.753.127 I slot print_timing: id 3 | task 9704 | n_gen = 246, tg = 24.00 t/s, tg_3s = 24.02 t/s 8.40.878.003 I slot print_timing: id 2 | task 9366 | n_gen = 585, tg = 22.13 t/s, tg_3s = 24.01 t/s 8.42.627.104 I slot print_timing: id 0 | task 9417 | n_gen = 577, tg = 22.66 t/s, tg_3s = 24.00 t/s 8.42.836.239 I slot print_timing: id 1 | task 9682 | n_gen = 318, tg = 22.69 t/s, tg_3s = 24.00 t/s 8.43.757.504 I slot print_timing: id 3 | task 9704 | n_gen = 318, tg = 23.99 t/s, tg_3s = 23.97 t/s 8.43.881.940 I slot print_timing: id 2 | task 9366 | n_gen = 657, tg = 22.32 t/s, tg_3s = 23.97 t/s 8.45.632.610 I slot print_timing: id 0 | task 9417 | n_gen = 649, tg = 22.80 t/s, tg_3s = 23.96 t/s 8.45.841.409 I slot print_timing: id 1 | task 9682 | n_gen = 390, tg = 22.91 t/s, tg_3s = 23.96 t/s 8.46.554.162 I slot print_timing: id 2 | task 9366 | prompt eval time = 734.66 ms / 471 tokens ( 1.56 ms per token, 641.11 tokens per second) 8.46.554.169 I slot print_timing: id 2 | task 9366 | eval time = 32069.11 ms / 721 tokens ( 44.54 ms per token, 22.45 tokens per second) 8.46.554.170 I slot print_timing: id 2 | task 9366 | total time = 32803.77 ms / 1192 tokens 8.46.554.171 I slot print_timing: id 2 | task 9366 | graphs reused = 9511 8.46.554.172 I slot print_timing: id 2 | task 9366 | graph reallocs = 0 / 0 (same size) / (changed size) 8.46.554.272 I slot release: id 2 | task 9366 | stop processing: n_tokens = 1855, truncated = 0 8.46.597.694 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.576 8.46.597.729 I slot launch_slot_: id 2 | task 10093 | processing task, is_child = 0 8.47.282.788 I slot print_timing: id 3 | task 9704 | n_gen = 387, tg = 23.06 t/s, tg_3s = 19.57 t/s 8.48.656.339 I slot print_timing: id 0 | task 9417 | n_gen = 705, tg = 22.39 t/s, tg_3s = 18.52 t/s 8.48.866.534 I slot print_timing: id 1 | task 9682 | n_gen = 446, tg = 22.25 t/s, tg_3s = 18.51 t/s 8.50.283.853 I slot print_timing: id 3 | task 9704 | n_gen = 458, tg = 23.15 t/s, tg_3s = 23.66 t/s 8.51.492.941 I slot print_timing: id 2 | task 10093 | n_gen = 100, tg = 23.96 t/s, tg_3s = 24.21 t/s 8.51.658.083 I slot print_timing: id 0 | task 9417 | n_gen = 777, tg = 22.53 t/s, tg_3s = 23.99 t/s 8.51.908.049 I slot print_timing: id 1 | task 9682 | n_gen = 519, tg = 22.48 t/s, tg_3s = 24.00 t/s 8.53.286.727 I slot print_timing: id 3 | task 9704 | n_gen = 530, tg = 23.26 t/s, tg_3s = 23.98 t/s 8.54.494.485 I slot print_timing: id 2 | task 10093 | n_gen = 172, tg = 23.97 t/s, tg_3s = 23.99 t/s 8.54.660.042 I slot print_timing: id 0 | task 9417 | n_gen = 849, tg = 22.65 t/s, tg_3s = 23.98 t/s 8.54.910.448 I slot print_timing: id 1 | task 9682 | n_gen = 591, tg = 22.65 t/s, tg_3s = 23.98 t/s 8.56.297.122 I slot print_timing: id 3 | task 9704 | n_gen = 602, tg = 23.34 t/s, tg_3s = 23.92 t/s 8.57.510.701 I slot print_timing: id 2 | task 10093 | n_gen = 244, tg = 23.94 t/s, tg_3s = 23.87 t/s 8.57.676.978 I slot print_timing: id 0 | task 9417 | n_gen = 921, tg = 22.74 t/s, tg_3s = 23.87 t/s 8.57.929.406 I slot print_timing: id 1 | task 9682 | n_gen = 663, tg = 22.78 t/s, tg_3s = 23.85 t/s 8.59.317.625 I slot print_timing: id 3 | task 9704 | n_gen = 674, tg = 23.39 t/s, tg_3s = 23.84 t/s 9.00.537.938 I slot print_timing: id 2 | task 10093 | n_gen = 316, tg = 23.91 t/s, tg_3s = 23.78 t/s 9.00.704.492 I slot print_timing: id 0 | task 9417 | n_gen = 993, tg = 22.81 t/s, tg_3s = 23.78 t/s 9.00.956.656 I slot print_timing: id 1 | task 9682 | n_gen = 735, tg = 22.87 t/s, tg_3s = 23.78 t/s 9.02.000.166 I slot print_timing: id 0 | task 9417 | prompt eval time = 732.77 ms / 489 tokens ( 1.50 ms per token, 667.33 tokens per second) 9.02.000.171 I slot print_timing: id 0 | task 9417 | eval time = 44787.48 ms / 1024 tokens ( 43.78 ms per token, 22.84 tokens per second) 9.02.000.172 I slot print_timing: id 0 | task 9417 | total time = 45520.26 ms / 1513 tokens 9.02.000.172 I slot print_timing: id 0 | task 9417 | graphs reused = 9859 9.02.000.173 I slot print_timing: id 0 | task 9417 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.000.283 I slot release: id 0 | task 9417 | stop processing: n_tokens = 2207, truncated = 0 9.02.037.755 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.484 9.02.045.786 I slot launch_slot_: id 0 | task 10447 | processing task, is_child = 0 9.02.816.916 I slot print_timing: id 3 | task 9704 | n_gen = 741, tg = 22.93 t/s, tg_3s = 19.15 t/s 9.03.553.855 I slot print_timing: id 2 | task 10093 | n_gen = 371, tg = 22.85 t/s, tg_3s = 18.24 t/s 9.03.969.888 I slot print_timing: id 1 | task 9682 | n_gen = 790, tg = 22.47 t/s, tg_3s = 18.25 t/s 9.05.854.435 I slot print_timing: id 3 | task 9704 | n_gen = 813, tg = 23.00 t/s, tg_3s = 23.70 t/s 9.06.565.653 I slot print_timing: id 2 | task 10093 | n_gen = 443, tg = 23.02 t/s, tg_3s = 23.91 t/s 9.06.980.826 I slot print_timing: id 1 | task 9682 | n_gen = 862, tg = 22.59 t/s, tg_3s = 23.91 t/s 9.07.021.805 I slot print_timing: id 0 | task 10447 | n_gen = 100, tg = 23.94 t/s, tg_3s = 24.18 t/s 9.08.030.917 I slot print_timing: id 2 | task 10093 | prompt eval time = 764.18 ms / 499 tokens ( 1.53 ms per token, 652.99 tokens per second) 9.08.030.923 I slot print_timing: id 2 | task 10093 | eval time = 20669.00 ms / 478 tokens ( 43.33 ms per token, 23.08 tokens per second) 9.08.030.924 I slot print_timing: id 2 | task 10093 | total time = 21433.18 ms / 977 tokens 9.08.030.925 I slot print_timing: id 2 | task 10093 | graphs reused = 9981 9.08.030.926 I slot print_timing: id 2 | task 10093 | graph reallocs = 0 / 0 (same size) / (changed size) 9.08.031.024 I slot release: id 2 | task 10093 | stop processing: n_tokens = 1640, truncated = 0 9.08.074.581 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.651 9.08.074.622 I slot launch_slot_: id 2 | task 10575 | processing task, is_child = 0 9.08.883.606 I slot print_timing: id 3 | task 9704 | n_gen = 870, tg = 22.67 t/s, tg_3s = 18.82 t/s 9.10.014.340 I slot print_timing: id 1 | task 9682 | n_gen = 919, tg = 22.31 t/s, tg_3s = 18.79 t/s 9.10.055.701 I slot print_timing: id 0 | task 10447 | n_gen = 157, tg = 21.76 t/s, tg_3s = 18.79 t/s 9.11.895.984 I slot print_timing: id 3 | task 9704 | n_gen = 942, tg = 22.76 t/s, tg_3s = 23.90 t/s 9.12.021.002 I slot print_timing: id 1 | task 9682 | prompt eval time = 744.23 ms / 481 tokens ( 1.55 ms per token, 646.30 tokens per second) 9.12.021.008 I slot print_timing: id 1 | task 9682 | eval time = 43157.23 ms / 967 tokens ( 44.68 ms per token, 22.38 tokens per second) 9.12.021.009 I slot print_timing: id 1 | task 9682 | total time = 43901.46 ms / 1448 tokens 9.12.021.010 I slot print_timing: id 1 | task 9682 | graphs reused = 10057 9.12.021.011 I slot print_timing: id 1 | task 9682 | graph reallocs = 0 / 0 (same size) / (changed size) 9.12.021.119 I slot release: id 1 | task 9682 | stop processing: n_tokens = 2122, truncated = 0 9.12.065.514 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.503 9.12.065.553 I slot launch_slot_: id 1 | task 10656 | processing task, is_child = 0 9.13.089.184 I slot print_timing: id 0 | task 10447 | n_gen = 214, tg = 20.88 t/s, tg_3s = 18.79 t/s 9.13.594.661 I slot print_timing: id 2 | task 10575 | n_gen = 100, tg = 20.65 t/s, tg_3s = 20.86 t/s 9.14.934.067 I slot print_timing: id 3 | task 9704 | n_gen = 999, tg = 22.48 t/s, tg_3s = 18.76 t/s 9.15.978.189 I slot print_timing: id 3 | task 9704 | prompt eval time = 894.50 ms / 530 tokens ( 1.69 ms per token, 592.51 tokens per second) 9.15.978.194 I slot print_timing: id 3 | task 9704 | eval time = 45432.23 ms / 1024 tokens ( 44.41 ms per token, 22.52 tokens per second) 9.15.978.195 I slot print_timing: id 3 | task 9704 | total time = 46326.73 ms / 1554 tokens 9.15.978.196 I slot print_timing: id 3 | task 9704 | graphs reused = 10132 9.15.978.197 I slot print_timing: id 3 | task 9704 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.978.322 I slot release: id 3 | task 9704 | stop processing: n_tokens = 2226, truncated = 0 9.16.013.946 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.480 9.16.020.258 I slot launch_slot_: id 3 | task 10736 | processing task, is_child = 0 9.16.675.115 I slot print_timing: id 0 | task 10447 | n_gen = 285, tg = 20.60 t/s, tg_3s = 19.80 t/s 9.16.675.680 I slot print_timing: id 2 | task 10575 | n_gen = 159, tg = 20.06 t/s, tg_3s = 19.15 t/s 9.17.575.103 I slot print_timing: id 1 | task 10656 | n_gen = 100, tg = 20.74 t/s, tg_3s = 20.95 t/s 9.19.700.710 I slot print_timing: id 0 | task 10447 | n_gen = 357, tg = 21.17 t/s, tg_3s = 23.80 t/s 9.19.701.941 I slot print_timing: id 2 | task 10575 | n_gen = 231, tg = 21.10 t/s, tg_3s = 23.79 t/s 9.20.580.424 I slot print_timing: id 1 | task 10656 | n_gen = 172, tg = 21.98 t/s, tg_3s = 23.96 t/s 9.20.872.166 I slot print_timing: id 3 | task 10736 | n_gen = 100, tg = 24.00 t/s, tg_3s = 24.24 t/s 9.22.740.482 I slot print_timing: id 0 | task 10447 | n_gen = 430, tg = 21.61 t/s, tg_3s = 24.01 t/s 9.22.741.654 I slot print_timing: id 2 | task 10575 | n_gen = 304, tg = 21.73 t/s, tg_3s = 24.02 t/s 9.23.615.461 I slot print_timing: id 1 | task 10656 | n_gen = 245, tg = 22.56 t/s, tg_3s = 24.05 t/s 9.23.907.757 I slot print_timing: id 3 | task 10736 | n_gen = 173, tg = 24.02 t/s, tg_3s = 24.05 t/s 9.25.779.460 I slot print_timing: id 0 | task 10447 | n_gen = 503, tg = 21.93 t/s, tg_3s = 24.02 t/s 9.25.780.559 I slot print_timing: id 2 | task 10575 | n_gen = 377, tg = 22.14 t/s, tg_3s = 24.02 t/s 9.26.653.024 I slot print_timing: id 1 | task 10656 | n_gen = 318, tg = 22.89 t/s, tg_3s = 24.03 t/s 9.26.946.153 I slot print_timing: id 3 | task 10736 | n_gen = 246, tg = 24.02 t/s, tg_3s = 24.03 t/s 9.28.817.398 I slot print_timing: id 0 | task 10447 | n_gen = 576, tg = 22.17 t/s, tg_3s = 24.03 t/s 9.28.818.538 I slot print_timing: id 2 | task 10575 | n_gen = 450, tg = 22.43 t/s, tg_3s = 24.03 t/s 9.29.692.328 I slot print_timing: id 1 | task 10656 | n_gen = 391, tg = 23.09 t/s, tg_3s = 24.02 t/s 9.29.985.583 I slot print_timing: id 3 | task 10736 | n_gen = 319, tg = 24.02 t/s, tg_3s = 24.02 t/s 9.31.821.543 I slot print_timing: id 0 | task 10447 | n_gen = 648, tg = 22.36 t/s, tg_3s = 23.97 t/s 9.31.822.683 I slot print_timing: id 2 | task 10575 | n_gen = 522, tg = 22.63 t/s, tg_3s = 23.97 t/s 9.32.700.158 I slot print_timing: id 1 | task 10656 | n_gen = 463, tg = 23.22 t/s, tg_3s = 23.94 t/s 9.32.992.540 I slot print_timing: id 3 | task 10736 | n_gen = 391, tg = 24.01 t/s, tg_3s = 23.94 t/s 9.33.493.364 I slot print_timing: id 2 | task 10575 | prompt eval time = 726.10 ms / 460 tokens ( 1.58 ms per token, 633.52 tokens per second) 9.33.493.371 I slot print_timing: id 2 | task 10575 | eval time = 24692.63 ms / 562 tokens ( 44.02 ms per token, 22.72 tokens per second) 9.33.493.372 I slot print_timing: id 2 | task 10575 | total time = 25418.73 ms / 1022 tokens 9.33.493.372 I slot print_timing: id 2 | task 10575 | graphs reused = 10531 9.33.493.373 I slot print_timing: id 2 | task 10575 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.493.472 I slot release: id 2 | task 10575 | stop processing: n_tokens = 1685, truncated = 0 9.33.537.253 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.634 9.33.537.290 I slot launch_slot_: id 2 | task 11142 | processing task, is_child = 0 9.34.855.590 I slot print_timing: id 0 | task 10447 | n_gen = 705, tg = 22.02 t/s, tg_3s = 18.79 t/s 9.35.734.469 I slot print_timing: id 1 | task 10656 | n_gen = 520, tg = 22.63 t/s, tg_3s = 18.79 t/s 9.36.028.121 I slot print_timing: id 3 | task 10736 | n_gen = 448, tg = 23.18 t/s, tg_3s = 18.78 t/s 9.37.859.642 I slot print_timing: id 0 | task 10447 | n_gen = 777, tg = 22.19 t/s, tg_3s = 23.97 t/s 9.38.401.902 I slot print_timing: id 2 | task 11142 | n_gen = 100, tg = 24.01 t/s, tg_3s = 24.25 t/s 9.38.735.069 I slot print_timing: id 1 | task 10656 | n_gen = 592, tg = 22.79 t/s, tg_3s = 24.00 t/s 9.38.736.214 I slot print_timing: id 3 | task 10736 | prompt eval time = 727.33 ms / 479 tokens ( 1.52 ms per token, 658.58 tokens per second) 9.38.736.218 I slot print_timing: id 3 | task 10736 | eval time = 21988.62 ms / 513 tokens ( 42.95 ms per token, 23.28 tokens per second) 9.38.736.220 I slot print_timing: id 3 | task 10736 | total time = 22715.94 ms / 992 tokens 9.38.736.221 I slot print_timing: id 3 | task 10736 | graphs reused = 10637 9.38.736.221 I slot print_timing: id 3 | task 10736 | graph reallocs = 0 / 0 (same size) / (changed size) 9.38.736.374 I slot release: id 3 | task 10736 | stop processing: n_tokens = 1678, truncated = 0 9.38.772.552 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.636 9.38.772.583 I slot launch_slot_: id 3 | task 11253 | processing task, is_child = 0 9.40.872.148 I slot print_timing: id 0 | task 10447 | n_gen = 834, tg = 21.93 t/s, tg_3s = 18.92 t/s 9.41.414.525 I slot print_timing: id 2 | task 11142 | n_gen = 157, tg = 21.86 t/s, tg_3s = 18.92 t/s 9.41.748.082 I slot print_timing: id 1 | task 10656 | n_gen = 649, tg = 22.39 t/s, tg_3s = 18.92 t/s 9.43.629.974 I slot print_timing: id 3 | task 11253 | n_gen = 100, tg = 23.97 t/s, tg_3s = 24.22 t/s 9.43.878.838 I slot print_timing: id 0 | task 10447 | n_gen = 906, tg = 22.08 t/s, tg_3s = 23.95 t/s 9.44.425.643 I slot print_timing: id 2 | task 11142 | n_gen = 229, tg = 22.47 t/s, tg_3s = 23.91 t/s 9.44.761.086 I slot print_timing: id 1 | task 10656 | n_gen = 721, tg = 22.53 t/s, tg_3s = 23.90 t/s 9.46.643.387 I slot print_timing: id 3 | task 11253 | n_gen = 172, tg = 23.94 t/s, tg_3s = 23.89 t/s 9.46.891.789 I slot print_timing: id 0 | task 10447 | n_gen = 978, tg = 22.20 t/s, tg_3s = 23.90 t/s 9.47.438.216 I slot print_timing: id 2 | task 11142 | n_gen = 301, tg = 22.80 t/s, tg_3s = 23.90 t/s 9.47.773.938 I slot print_timing: id 1 | task 10656 | n_gen = 793, tg = 22.65 t/s, tg_3s = 23.90 t/s 9.48.818.696 I slot print_timing: id 0 | task 10447 | prompt eval time = 840.88 ms / 523 tokens ( 1.61 ms per token, 621.97 tokens per second) 9.48.818.701 I slot print_timing: id 0 | task 10447 | eval time = 45932.02 ms / 1024 tokens ( 44.90 ms per token, 22.27 tokens per second) 9.48.818.702 I slot print_timing: id 0 | task 10447 | total time = 46772.90 ms / 1547 tokens 9.48.818.702 I slot print_timing: id 0 | task 10447 | graphs reused = 10858 9.48.818.703 I slot print_timing: id 0 | task 10447 | graph reallocs = 0 / 0 (same size) / (changed size) 9.48.818.809 I slot release: id 0 | task 10447 | stop processing: n_tokens = 2189, truncated = 0 9.48.855.810 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.488 9.48.861.228 I slot launch_slot_: id 0 | task 11480 | processing task, is_child = 0 9.49.654.223 I slot print_timing: id 3 | task 11253 | n_gen = 228, tg = 22.36 t/s, tg_3s = 18.60 t/s 9.50.469.564 I slot print_timing: id 2 | task 11142 | n_gen = 358, tg = 22.05 t/s, tg_3s = 18.80 t/s 9.50.798.124 I slot print_timing: id 1 | task 10656 | n_gen = 850, tg = 22.34 t/s, tg_3s = 18.85 t/s 9.52.671.842 I slot print_timing: id 3 | task 11253 | n_gen = 301, tg = 22.78 t/s, tg_3s = 24.19 t/s 9.53.509.121 I slot print_timing: id 2 | task 11142 | n_gen = 431, tg = 22.36 t/s, tg_3s = 24.02 t/s 9.53.717.366 I slot print_timing: id 0 | task 11480 | n_gen = 100, tg = 24.11 t/s, tg_3s = 24.36 t/s 9.53.801.777 I slot print_timing: id 1 | task 10656 | n_gen = 922, tg = 22.46 t/s, tg_3s = 23.97 t/s 9.55.681.897 I slot print_timing: id 3 | task 11253 | n_gen = 373, tg = 22.99 t/s, tg_3s = 23.92 t/s 9.56.512.764 I slot print_timing: id 2 | task 11142 | n_gen = 503, tg = 22.58 t/s, tg_3s = 23.97 t/s 9.56.720.446 I slot print_timing: id 0 | task 11480 | n_gen = 172, tg = 24.05 t/s, tg_3s = 23.98 t/s 9.56.803.525 I slot print_timing: id 1 | task 10656 | n_gen = 994, tg = 22.57 t/s, tg_3s = 23.99 t/s 9.57.387.721 I slot print_timing: id 3 | task 11253 | prompt eval time = 727.84 ms / 478 tokens ( 1.52 ms per token, 656.74 tokens per second) 9.57.387.726 I slot print_timing: id 3 | task 11253 | eval time = 17887.28 ms / 414 tokens ( 43.31 ms per token, 23.09 tokens per second) 9.57.387.727 I slot print_timing: id 3 | task 11253 | total time = 18615.13 ms / 892 tokens 9.57.387.728 I slot print_timing: id 3 | task 11253 | graphs reused = 11044 9.57.387.729 I slot print_timing: id 3 | task 11253 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.387.839 I slot release: id 3 | task 11253 | stop processing: n_tokens = 1578, truncated = 0 9.57.423.584 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.677 9.57.423.621 I slot launch_slot_: id 3 | task 11671 | processing task, is_child = 0 9.58.673.655 I slot print_timing: id 1 | task 10656 | prompt eval time = 736.66 ms / 472 tokens ( 1.56 ms per token, 640.73 tokens per second) 9.58.673.659 I slot print_timing: id 1 | task 10656 | eval time = 45871.44 ms / 1024 tokens ( 44.84 ms per token, 22.30 tokens per second) 9.58.673.660 I slot print_timing: id 1 | task 10656 | total time = 46608.10 ms / 1496 tokens 9.58.673.660 I slot print_timing: id 1 | task 10656 | graphs reused = 11056 9.58.673.661 I slot print_timing: id 1 | task 10656 | graph reallocs = 0 / 0 (same size) / (changed size) 9.58.673.722 I slot release: id 1 | task 10656 | stop processing: n_tokens = 2170, truncated = 0 9.58.715.146 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.492 9.58.718.439 I slot launch_slot_: id 1 | task 11688 | processing task, is_child = 0 9.59.544.345 I slot print_timing: id 2 | task 11142 | n_gen = 546, tg = 21.57 t/s, tg_3s = 14.18 t/s 9.59.746.325 I slot print_timing: id 0 | task 11480 | n_gen = 215, tg = 21.12 t/s, tg_3s = 14.21 t/s 10.02.581.704 I slot print_timing: id 2 | task 11142 | n_gen = 619, tg = 21.83 t/s, tg_3s = 24.03 t/s 10.02.747.034 I slot print_timing: id 0 | task 11480 | n_gen = 287, tg = 21.77 t/s, tg_3s = 23.99 t/s 10.02.873.290 I slot print_timing: id 3 | task 11671 | n_gen = 100, tg = 20.92 t/s, tg_3s = 21.14 t/s 10.03.538.917 I slot print_timing: id 1 | task 11688 | n_gen = 100, tg = 24.04 t/s, tg_3s = 24.29 t/s 10.05.582.172 I slot print_timing: id 2 | task 11142 | n_gen = 691, tg = 22.04 t/s, tg_3s = 24.00 t/s 10.05.747.684 I slot print_timing: id 0 | task 11480 | n_gen = 359, tg = 22.19 t/s, tg_3s = 23.99 t/s 10.05.874.725 I slot print_timing: id 3 | task 11671 | n_gen = 172, tg = 22.11 t/s, tg_3s = 23.99 t/s 10.06.540.588 I slot print_timing: id 1 | task 11688 | n_gen = 172, tg = 24.02 t/s, tg_3s = 23.99 t/s 10.08.622.933 I slot print_timing: id 2 | task 11142 | n_gen = 764, tg = 22.22 t/s, tg_3s = 24.01 t/s 10.08.788.023 I slot print_timing: id 0 | task 11480 | n_gen = 432, tg = 22.48 t/s, tg_3s = 24.01 t/s 10.08.914.356 I slot print_timing: id 3 | task 11671 | n_gen = 245, tg = 22.65 t/s, tg_3s = 24.02 t/s 10.09.579.905 I slot print_timing: id 1 | task 11688 | n_gen = 245, tg = 24.02 t/s, tg_3s = 24.02 t/s 10.11.663.386 I slot print_timing: id 2 | task 11142 | n_gen = 837, tg = 22.36 t/s, tg_3s = 24.01 t/s 10.11.829.056 I slot print_timing: id 0 | task 11480 | n_gen = 505, tg = 22.68 t/s, tg_3s = 24.00 t/s 10.11.955.739 I slot print_timing: id 3 | task 11671 | n_gen = 318, tg = 22.95 t/s, tg_3s = 24.00 t/s 10.12.620.575 I slot print_timing: id 1 | task 11688 | n_gen = 318, tg = 24.02 t/s, tg_3s = 24.01 t/s 10.14.666.308 I slot print_timing: id 2 | task 11142 | n_gen = 909, tg = 22.48 t/s, tg_3s = 23.98 t/s 10.14.832.110 I slot print_timing: id 0 | task 11480 | n_gen = 577, tg = 22.84 t/s, tg_3s = 23.98 t/s 10.14.958.463 I slot print_timing: id 3 | task 11671 | n_gen = 390, tg = 23.13 t/s, tg_3s = 23.98 t/s 10.15.623.225 I slot print_timing: id 1 | task 11688 | n_gen = 390, tg = 24.01 t/s, tg_3s = 23.98 t/s 10.15.789.150 I slot print_timing: id 0 | task 11480 | prompt eval time = 750.36 ms / 514 tokens ( 1.46 ms per token, 685.00 tokens per second) 10.15.789.166 I slot print_timing: id 0 | task 11480 | eval time = 26177.55 ms / 600 tokens ( 43.70 ms per token, 22.88 tokens per second) 10.15.789.169 I slot print_timing: id 0 | task 11480 | total time = 26927.91 ms / 1114 tokens 10.15.789.170 I slot print_timing: id 0 | task 11480 | graphs reused = 11446 10.15.789.171 I slot print_timing: id 0 | task 11480 | graph reallocs = 0 / 0 (same size) / (changed size) 10.15.789.270 I slot release: id 0 | task 11480 | stop processing: n_tokens = 1763, truncated = 0 10.15.825.850 I slot print_timing: id 1 | task 11688 | prompt eval time = 702.86 ms / 445 tokens ( 1.58 ms per token, 633.12 tokens per second) 10.15.825.854 I slot print_timing: id 1 | task 11688 | eval time = 16404.54 ms / 395 tokens ( 41.64 ms per token, 24.02 tokens per second) 10.15.825.855 I slot print_timing: id 1 | task 11688 | total time = 17107.40 ms / 840 tokens 10.15.825.856 I slot print_timing: id 1 | task 11688 | graphs reused = 11446 10.15.825.856 I slot print_timing: id 1 | task 11688 | graph reallocs = 0 / 0 (same size) / (changed size) 10.15.825.944 I slot release: id 1 | task 11688 | stop processing: n_tokens = 1534, truncated = 0 10.15.826.984 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.606 10.15.827.018 I slot launch_slot_: id 0 | task 12085 | processing task, is_child = 0 10.16.050.763 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.696 10.16.050.790 I slot launch_slot_: id 1 | task 12087 | processing task, is_child = 0 10.17.667.870 I slot print_timing: id 2 | task 11142 | n_gen = 943, tg = 21.71 t/s, tg_3s = 11.33 t/s 10.17.997.033 I slot print_timing: id 3 | task 11671 | n_gen = 425, tg = 21.35 t/s, tg_3s = 11.52 t/s 10.20.682.249 I slot print_timing: id 2 | task 11142 | n_gen = 1015, tg = 21.85 t/s, tg_3s = 23.89 t/s 10.21.015.110 I slot print_timing: id 3 | task 11671 | n_gen = 497, tg = 21.68 t/s, tg_3s = 23.86 t/s 10.21.056.605 I slot print_timing: id 2 | task 11142 | prompt eval time = 740.82 ms / 480 tokens ( 1.54 ms per token, 647.93 tokens per second) 10.21.056.611 I slot print_timing: id 2 | task 11142 | eval time = 46778.49 ms / 1024 tokens ( 45.73 ms per token, 21.87 tokens per second) 10.21.056.612 I slot print_timing: id 2 | task 11142 | total time = 47519.31 ms / 1504 tokens 10.21.056.613 I slot print_timing: id 2 | task 11142 | graphs reused = 11529 10.21.056.614 I slot print_timing: id 2 | task 11142 | graph reallocs = 0 / 0 (same size) / (changed size) 10.21.056.740 I slot release: id 2 | task 11142 | stop processing: n_tokens = 2167, truncated = 0 10.21.100.242 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.493 10.21.106.783 I slot launch_slot_: id 2 | task 12175 | processing task, is_child = 0 10.22.324.559 I slot print_timing: id 0 | task 12085 | n_gen = 100, tg = 20.71 t/s, tg_3s = 20.92 t/s 10.22.325.059 I slot print_timing: id 1 | task 12087 | n_gen = 100, tg = 20.71 t/s, tg_3s = 20.92 t/s 10.23.068.094 I slot print_timing: id 3 | task 11671 | prompt eval time = 718.45 ms / 465 tokens ( 1.55 ms per token, 647.22 tokens per second) 10.23.068.099 I slot print_timing: id 3 | task 11671 | eval time = 24926.01 ms / 531 tokens ( 47.03 ms per token, 21.26 tokens per second) 10.23.068.101 I slot print_timing: id 3 | task 11671 | total time = 25644.47 ms / 996 tokens 10.23.068.101 I slot print_timing: id 3 | task 11671 | graphs reused = 11558 10.23.068.102 I slot print_timing: id 3 | task 11671 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.068.200 I slot release: id 3 | task 11671 | stop processing: n_tokens = 1682, truncated = 0 10.23.103.953 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.636 10.23.103.986 I slot launch_slot_: id 3 | task 12209 | processing task, is_child = 0 10.25.341.096 I slot print_timing: id 0 | task 12085 | n_gen = 158, tg = 20.14 t/s, tg_3s = 19.23 t/s 10.25.341.685 I slot print_timing: id 1 | task 12087 | n_gen = 158, tg = 20.14 t/s, tg_3s = 19.23 t/s 10.26.547.547 I slot print_timing: id 2 | task 12175 | n_gen = 100, tg = 21.00 t/s, tg_3s = 21.21 t/s 10.27.919.676 I slot print_timing: id 3 | task 12209 | n_gen = 100, tg = 24.18 t/s, tg_3s = 24.43 t/s 10.28.376.690 I slot print_timing: id 0 | task 12085 | n_gen = 231, tg = 21.23 t/s, tg_3s = 24.05 t/s 10.28.377.408 I slot print_timing: id 1 | task 12087 | n_gen = 231, tg = 21.23 t/s, tg_3s = 24.05 t/s 10.29.584.773 I slot print_timing: id 2 | task 12175 | n_gen = 173, tg = 22.19 t/s, tg_3s = 24.04 t/s 10.30.920.072 I slot print_timing: id 3 | task 12209 | n_gen = 172, tg = 24.10 t/s, tg_3s = 24.00 t/s 10.31.378.339 I slot print_timing: id 0 | task 12085 | n_gen = 303, tg = 21.83 t/s, tg_3s = 23.99 t/s 10.31.378.883 I slot print_timing: id 1 | task 12087 | n_gen = 303, tg = 21.83 t/s, tg_3s = 23.99 t/s 10.32.591.756 I slot print_timing: id 2 | task 12175 | n_gen = 245, tg = 22.68 t/s, tg_3s = 23.94 t/s 10.33.255.789 I slot print_timing: id 0 | task 12085 | prompt eval time = 1715.23 ms / 562 tokens ( 3.05 ms per token, 327.65 tokens per second) 10.33.255.795 I slot print_timing: id 0 | task 12085 | eval time = 15711.81 ms / 348 tokens ( 45.28 ms per token, 22.09 tokens per second) 10.33.255.796 I slot print_timing: id 0 | task 12085 | total time = 17427.04 ms / 910 tokens 10.33.255.797 I slot print_timing: id 0 | task 12085 | graphs reused = 11783 10.33.255.798 I slot print_timing: id 0 | task 12085 | graph reallocs = 0 / 0 (same size) / (changed size) 10.33.255.923 I slot release: id 0 | task 12085 | stop processing: n_tokens = 1559, truncated = 0 10.33.293.911 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.685 10.33.293.955 I slot launch_slot_: id 0 | task 12440 | processing task, is_child = 0 10.33.976.591 I slot print_timing: id 3 | task 12209 | n_gen = 231, tg = 22.66 t/s, tg_3s = 19.30 t/s 10.34.382.592 I slot print_timing: id 1 | task 12087 | n_gen = 361, tg = 21.38 t/s, tg_3s = 19.31 t/s 10.35.596.654 I slot print_timing: id 2 | task 12175 | n_gen = 303, tg = 21.94 t/s, tg_3s = 19.30 t/s 10.37.016.297 I slot print_timing: id 3 | task 12209 | n_gen = 304, tg = 22.97 t/s, tg_3s = 24.02 t/s 10.37.389.366 I slot print_timing: id 1 | task 12087 | n_gen = 433, tg = 21.77 t/s, tg_3s = 23.95 t/s 10.38.096.815 I slot print_timing: id 0 | task 12440 | n_gen = 100, tg = 24.02 t/s, tg_3s = 24.27 t/s 10.38.598.807 I slot print_timing: id 2 | task 12175 | n_gen = 375, tg = 22.31 t/s, tg_3s = 23.98 t/s 10.40.053.680 I slot print_timing: id 3 | task 12209 | n_gen = 377, tg = 23.17 t/s, tg_3s = 24.03 t/s 10.40.427.279 I slot print_timing: id 1 | task 12087 | n_gen = 506, tg = 22.07 t/s, tg_3s = 24.03 t/s 10.41.136.735 I slot print_timing: id 0 | task 12440 | n_gen = 173, tg = 24.02 t/s, tg_3s = 24.01 t/s 10.41.639.553 I slot print_timing: id 2 | task 12175 | n_gen = 448, tg = 22.57 t/s, tg_3s = 24.01 t/s 10.42.143.270 I slot print_timing: id 1 | task 12087 | prompt eval time = 1493.52 ms / 440 tokens ( 3.39 ms per token, 294.61 tokens per second) 10.42.143.277 I slot print_timing: id 1 | task 12087 | eval time = 24598.90 ms / 547 tokens ( 45.05 ms per token, 22.20 tokens per second) 10.42.143.278 I slot print_timing: id 1 | task 12087 | total time = 26092.42 ms / 987 tokens 10.42.143.279 I slot print_timing: id 1 | task 12087 | graphs reused = 11978 10.42.143.280 I slot print_timing: id 1 | task 12087 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.143.396 I slot release: id 1 | task 12087 | stop processing: n_tokens = 1681, truncated = 0 10.42.187.953 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.635 10.42.187.998 I slot launch_slot_: id 1 | task 12640 | processing task, is_child = 0 10.43.074.442 I slot print_timing: id 3 | task 12209 | n_gen = 434, tg = 22.49 t/s, tg_3s = 18.87 t/s 10.44.168.488 I slot print_timing: id 0 | task 12440 | n_gen = 230, tg = 22.47 t/s, tg_3s = 18.80 t/s 10.44.670.845 I slot print_timing: id 2 | task 12175 | n_gen = 505, tg = 22.07 t/s, tg_3s = 18.80 t/s 10.46.086.831 I slot print_timing: id 3 | task 12209 | n_gen = 506, tg = 22.69 t/s, tg_3s = 23.90 t/s 10.47.043.259 I slot print_timing: id 1 | task 12640 | n_gen = 100, tg = 23.95 t/s, tg_3s = 24.19 t/s 10.47.209.834 I slot print_timing: id 0 | task 12440 | n_gen = 303, tg = 22.82 t/s, tg_3s = 24.00 t/s 10.47.709.898 I slot print_timing: id 2 | task 12175 | n_gen = 578, tg = 22.30 t/s, tg_3s = 24.02 t/s 10.49.124.710 I slot print_timing: id 3 | task 12209 | n_gen = 579, tg = 22.85 t/s, tg_3s = 24.03 t/s 10.50.081.401 I slot print_timing: id 1 | task 12640 | n_gen = 173, tg = 23.98 t/s, tg_3s = 24.03 t/s 10.50.248.316 I slot print_timing: id 0 | task 12440 | n_gen = 376, tg = 23.04 t/s, tg_3s = 24.03 t/s 10.50.748.785 I slot print_timing: id 2 | task 12175 | n_gen = 651, tg = 22.48 t/s, tg_3s = 24.02 t/s 10.52.130.755 I slot print_timing: id 3 | task 12209 | n_gen = 651, tg = 22.96 t/s, tg_3s = 23.95 t/s 10.53.089.408 I slot print_timing: id 1 | task 12640 | n_gen = 245, tg = 23.97 t/s, tg_3s = 23.94 t/s 10.53.255.617 I slot print_timing: id 0 | task 12440 | n_gen = 448, tg = 23.18 t/s, tg_3s = 23.94 t/s 10.53.756.037 I slot print_timing: id 2 | task 12175 | n_gen = 723, tg = 22.62 t/s, tg_3s = 23.94 t/s 10.54.590.141 I slot print_timing: id 3 | task 12209 | prompt eval time = 721.52 ms / 469 tokens ( 1.54 ms per token, 650.01 tokens per second) 10.54.590.150 I slot print_timing: id 3 | task 12209 | eval time = 30764.62 ms / 710 tokens ( 43.39 ms per token, 23.05 tokens per second) 10.54.590.151 I slot print_timing: id 3 | task 12209 | total time = 31486.14 ms / 1179 tokens 10.54.590.152 I slot print_timing: id 3 | task 12209 | graphs reused = 12256 10.54.590.153 I slot print_timing: id 3 | task 12209 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.590.278 I slot release: id 3 | task 12209 | stop processing: n_tokens = 1865, truncated = 0 10.54.626.314 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.573 10.54.626.355 I slot launch_slot_: id 3 | task 12924 | processing task, is_child = 0 10.56.121.982 I slot print_timing: id 1 | task 12640 | n_gen = 303, tg = 22.86 t/s, tg_3s = 19.13 t/s 10.56.288.263 I slot print_timing: id 0 | task 12440 | n_gen = 506, tg = 22.63 t/s, tg_3s = 19.13 t/s 10.56.789.312 I slot print_timing: id 2 | task 12175 | n_gen = 781, tg = 22.31 t/s, tg_3s = 19.12 t/s 10.58.329.979 I slot print_timing: id 2 | task 12175 | prompt eval time = 725.37 ms / 460 tokens ( 1.58 ms per token, 634.16 tokens per second) 10.58.329.990 I slot print_timing: id 2 | task 12175 | eval time = 36497.82 ms / 818 tokens ( 44.67 ms per token, 22.38 tokens per second) 10.58.329.992 I slot print_timing: id 2 | task 12175 | total time = 37223.19 ms / 1278 tokens 10.58.329.992 I slot print_timing: id 2 | task 12175 | graphs reused = 12327 10.58.329.993 I slot print_timing: id 2 | task 12175 | graph reallocs = 0 / 0 (same size) / (changed size) 10.58.330.089 I slot release: id 2 | task 12175 | stop processing: n_tokens = 1941, truncated = 0 10.58.373.270 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.550 10.58.373.320 I slot launch_slot_: id 2 | task 13000 | processing task, is_child = 0 10.59.132.430 I slot print_timing: id 1 | task 12640 | n_gen = 359, tg = 22.07 t/s, tg_3s = 18.60 t/s 10.59.299.754 I slot print_timing: id 0 | task 12440 | n_gen = 562, tg = 22.15 t/s, tg_3s = 18.60 t/s 10.59.758.621 I slot print_timing: id 0 | task 12440 | prompt eval time = 681.80 ms / 446 tokens ( 1.53 ms per token, 654.15 tokens per second) 10.59.758.628 I slot print_timing: id 0 | task 12440 | eval time = 25782.86 ms / 573 tokens ( 45.07 ms per token, 22.19 tokens per second) 10.59.758.629 I slot print_timing: id 0 | task 12440 | total time = 26464.66 ms / 1019 tokens 10.59.758.630 I slot print_timing: id 0 | task 12440 | graphs reused = 12341 10.59.758.631 I slot print_timing: id 0 | task 12440 | graph reallocs = 0 / 0 (same size) / (changed size) 10.59.758.726 I slot release: id 0 | task 12440 | stop processing: n_tokens = 1714, truncated = 0 10.59.795.971 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.623 10.59.796.002 I slot launch_slot_: id 0 | task 13019 | processing task, is_child = 0 11.00.745.023 I slot print_timing: id 3 | task 12924 | n_gen = 100, tg = 18.30 t/s, tg_3s = 18.48 t/s 11.02.162.462 I slot print_timing: id 1 | task 12640 | n_gen = 417, tg = 21.61 t/s, tg_3s = 19.14 t/s 11.03.747.586 I slot print_timing: id 3 | task 12924 | n_gen = 172, tg = 20.32 t/s, tg_3s = 23.98 t/s 11.03.871.435 I slot print_timing: id 2 | task 13000 | n_gen = 100, tg = 20.89 t/s, tg_3s = 21.10 t/s 11.04.618.195 I slot print_timing: id 0 | task 13019 | n_gen = 100, tg = 24.04 t/s, tg_3s = 24.28 t/s 11.05.201.529 I slot print_timing: id 1 | task 12640 | n_gen = 490, tg = 21.94 t/s, tg_3s = 24.02 t/s 11.06.783.738 I slot print_timing: id 3 | task 12924 | n_gen = 245, tg = 21.31 t/s, tg_3s = 24.04 t/s 11.06.906.862 I slot print_timing: id 2 | task 13000 | n_gen = 173, tg = 22.12 t/s, tg_3s = 24.05 t/s 11.07.651.119 I slot print_timing: id 0 | task 13019 | n_gen = 173, tg = 24.05 t/s, tg_3s = 24.07 t/s 11.08.233.681 I slot print_timing: id 1 | task 12640 | n_gen = 563, tg = 22.19 t/s, tg_3s = 24.08 t/s 11.09.813.464 I slot print_timing: id 3 | task 12924 | n_gen = 318, tg = 21.89 t/s, tg_3s = 24.09 t/s 11.09.938.178 I slot print_timing: id 2 | task 13000 | n_gen = 246, tg = 22.67 t/s, tg_3s = 24.08 t/s 11.10.687.542 I slot print_timing: id 0 | task 13019 | n_gen = 246, tg = 24.05 t/s, tg_3s = 24.04 t/s 11.11.271.810 I slot print_timing: id 1 | task 12640 | n_gen = 636, tg = 22.39 t/s, tg_3s = 24.03 t/s 11.12.855.000 I slot print_timing: id 3 | task 12924 | n_gen = 391, tg = 22.26 t/s, tg_3s = 24.00 t/s 11.12.979.535 I slot print_timing: id 2 | task 13000 | n_gen = 319, tg = 22.97 t/s, tg_3s = 24.00 t/s 11.13.727.203 I slot print_timing: id 0 | task 13019 | n_gen = 319, tg = 24.04 t/s, tg_3s = 24.02 t/s 11.14.310.613 I slot print_timing: id 1 | task 12640 | n_gen = 709, tg = 22.55 t/s, tg_3s = 24.02 t/s 11.15.894.618 I slot print_timing: id 3 | task 12924 | n_gen = 464, tg = 22.52 t/s, tg_3s = 24.02 t/s 11.16.018.097 I slot print_timing: id 2 | task 13000 | n_gen = 392, tg = 23.16 t/s, tg_3s = 24.02 t/s 11.16.767.838 I slot print_timing: id 0 | task 13019 | n_gen = 392, tg = 24.03 t/s, tg_3s = 24.01 t/s 11.17.350.915 I slot print_timing: id 1 | task 12640 | n_gen = 782, tg = 22.68 t/s, tg_3s = 24.01 t/s 11.18.901.042 I slot print_timing: id 3 | task 12924 | n_gen = 536, tg = 22.70 t/s, tg_3s = 23.95 t/s 11.19.025.206 I slot print_timing: id 2 | task 13000 | n_gen = 464, tg = 23.28 t/s, tg_3s = 23.94 t/s 11.19.776.366 I slot print_timing: id 0 | task 13019 | n_gen = 464, tg = 24.02 t/s, tg_3s = 23.93 t/s 11.20.363.261 I slot print_timing: id 1 | task 12640 | n_gen = 854, tg = 22.77 t/s, tg_3s = 23.90 t/s 11.20.825.155 I slot print_timing: id 2 | task 13000 | prompt eval time = 759.43 ms / 491 tokens ( 1.55 ms per token, 646.54 tokens per second) 11.20.825.163 I slot print_timing: id 2 | task 13000 | eval time = 21692.40 ms / 507 tokens ( 42.87 ms per token, 23.33 tokens per second) 11.20.825.164 I slot print_timing: id 2 | task 13000 | total time = 22451.83 ms / 998 tokens 11.20.825.165 I slot print_timing: id 2 | task 13000 | graphs reused = 12827 11.20.825.166 I slot print_timing: id 2 | task 13000 | graph reallocs = 0 / 0 (same size) / (changed size) 11.20.825.284 I slot release: id 2 | task 13000 | stop processing: n_tokens = 1661, truncated = 0 11.20.868.517 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.643 11.20.868.558 I slot launch_slot_: id 2 | task 13511 | processing task, is_child = 0 11.21.930.492 I slot print_timing: id 3 | task 12924 | n_gen = 592, tg = 22.22 t/s, tg_3s = 18.49 t/s 11.22.812.061 I slot print_timing: id 0 | task 13019 | n_gen = 520, tg = 23.26 t/s, tg_3s = 18.45 t/s 11.23.400.106 I slot print_timing: id 1 | task 12640 | n_gen = 910, tg = 22.45 t/s, tg_3s = 18.44 t/s 11.24.945.455 I slot print_timing: id 3 | task 12924 | n_gen = 664, tg = 22.39 t/s, tg_3s = 23.88 t/s 11.25.778.953 I slot print_timing: id 2 | task 13511 | n_gen = 100, tg = 23.94 t/s, tg_3s = 24.18 t/s 11.25.819.821 I slot print_timing: id 0 | task 13019 | n_gen = 592, tg = 23.34 t/s, tg_3s = 23.94 t/s 11.26.403.362 I slot print_timing: id 1 | task 12640 | n_gen = 982, tg = 22.56 t/s, tg_3s = 23.97 t/s 11.27.067.401 I slot print_timing: id 0 | task 13019 | prompt eval time = 703.29 ms / 462 tokens ( 1.52 ms per token, 656.91 tokens per second) 11.27.067.410 I slot print_timing: id 0 | task 13019 | eval time = 26568.10 ms / 622 tokens ( 42.78 ms per token, 23.37 tokens per second) 11.27.067.411 I slot print_timing: id 0 | task 13019 | total time = 27271.39 ms / 1084 tokens 11.27.067.411 I slot print_timing: id 0 | task 13019 | graphs reused = 12955 11.27.067.412 I slot print_timing: id 0 | task 13019 | graph reallocs = 0 / 0 (same size) / (changed size) 11.27.067.526 I slot release: id 0 | task 13019 | stop processing: n_tokens = 1779, truncated = 0 11.27.105.458 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.600 11.27.105.496 I slot launch_slot_: id 0 | task 13645 | processing task, is_child = 0 11.27.974.975 I slot print_timing: id 3 | task 12924 | n_gen = 722, tg = 22.09 t/s, tg_3s = 19.14 t/s 11.28.546.229 I slot print_timing: id 3 | task 12924 | prompt eval time = 707.66 ms / 454 tokens ( 1.56 ms per token, 641.55 tokens per second) 11.28.546.234 I slot print_timing: id 3 | task 12924 | eval time = 33212.21 ms / 736 tokens ( 45.19 ms per token, 22.13 tokens per second) 11.28.546.234 I slot print_timing: id 3 | task 12924 | total time = 33919.87 ms / 1190 tokens 11.28.546.235 I slot print_timing: id 3 | task 12924 | graphs reused = 12973 11.28.546.235 I slot print_timing: id 3 | task 12924 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.546.314 I slot release: id 3 | task 12924 | stop processing: n_tokens = 1876, truncated = 0 11.28.580.617 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.569 11.28.580.644 I slot launch_slot_: id 3 | task 13667 | processing task, is_child = 0 11.29.225.167 I slot print_timing: id 2 | task 13511 | n_gen = 154, tg = 20.18 t/s, tg_3s = 15.67 t/s 11.29.380.206 I slot print_timing: id 1 | task 12640 | prompt eval time = 721.71 ms / 454 tokens ( 1.59 ms per token, 629.06 tokens per second) 11.29.380.209 I slot print_timing: id 1 | task 12640 | eval time = 46470.49 ms / 1024 tokens ( 45.43 ms per token, 22.01 tokens per second) 11.29.380.209 I slot print_timing: id 1 | task 12640 | total time = 47192.20 ms / 1478 tokens 11.29.380.210 I slot print_timing: id 1 | task 12640 | graphs reused = 12974 11.29.380.210 I slot print_timing: id 1 | task 12640 | graph reallocs = 0 / 0 (same size) / (changed size) 11.29.380.272 I slot release: id 1 | task 12640 | stop processing: n_tokens = 2172, truncated = 0 11.29.421.422 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.492 11.29.427.219 I slot launch_slot_: id 1 | task 13673 | processing task, is_child = 0 11.32.235.875 I slot print_timing: id 2 | task 13511 | n_gen = 210, tg = 19.73 t/s, tg_3s = 18.60 t/s 11.33.192.256 I slot print_timing: id 0 | task 13645 | n_gen = 100, tg = 18.39 t/s, tg_3s = 18.58 t/s 11.34.066.726 I slot print_timing: id 3 | task 13667 | n_gen = 100, tg = 20.76 t/s, tg_3s = 20.97 t/s 11.34.273.396 I slot print_timing: id 1 | task 13673 | n_gen = 100, tg = 24.06 t/s, tg_3s = 24.30 t/s 11.35.274.103 I slot print_timing: id 2 | task 13511 | n_gen = 283, tg = 20.69 t/s, tg_3s = 24.03 t/s 11.36.228.935 I slot print_timing: id 0 | task 13645 | n_gen = 173, tg = 20.43 t/s, tg_3s = 24.04 t/s 11.37.103.006 I slot print_timing: id 3 | task 13667 | n_gen = 173, tg = 22.04 t/s, tg_3s = 24.04 t/s 11.37.309.916 I slot print_timing: id 1 | task 13673 | n_gen = 173, tg = 24.05 t/s, tg_3s = 24.04 t/s 11.38.311.175 I slot print_timing: id 2 | task 13511 | n_gen = 356, tg = 21.30 t/s, tg_3s = 24.04 t/s 11.39.268.313 I slot print_timing: id 0 | task 13645 | n_gen = 246, tg = 21.38 t/s, tg_3s = 24.02 t/s 11.40.144.644 I slot print_timing: id 3 | task 13667 | n_gen = 246, tg = 22.59 t/s, tg_3s = 24.00 t/s 11.40.310.846 I slot print_timing: id 1 | task 13673 | n_gen = 245, tg = 24.03 t/s, tg_3s = 23.99 t/s 11.41.312.779 I slot print_timing: id 2 | task 13511 | n_gen = 428, tg = 21.71 t/s, tg_3s = 23.99 t/s 11.42.269.638 I slot print_timing: id 0 | task 13645 | n_gen = 318, tg = 21.92 t/s, tg_3s = 23.99 t/s 11.43.146.136 I slot print_timing: id 3 | task 13667 | n_gen = 318, tg = 22.89 t/s, tg_3s = 23.99 t/s 11.43.311.459 I slot print_timing: id 1 | task 13673 | n_gen = 317, tg = 24.03 t/s, tg_3s = 24.00 t/s 11.44.353.769 I slot print_timing: id 2 | task 13511 | n_gen = 501, tg = 22.02 t/s, tg_3s = 24.01 t/s 11.45.270.187 I slot print_timing: id 0 | task 13645 | n_gen = 390, tg = 22.28 t/s, tg_3s = 24.00 t/s 11.46.149.592 I slot print_timing: id 3 | task 13667 | n_gen = 390, tg = 23.08 t/s, tg_3s = 23.97 t/s 11.46.315.136 I slot print_timing: id 1 | task 13673 | n_gen = 389, tg = 24.02 t/s, tg_3s = 23.97 t/s 11.47.023.437 I slot print_timing: id 3 | task 13667 | prompt eval time = 717.30 ms / 465 tokens ( 1.54 ms per token, 648.26 tokens per second) 11.47.023.442 I slot print_timing: id 3 | task 13667 | eval time = 17725.48 ms / 411 tokens ( 43.23 ms per token, 23.13 tokens per second) 11.47.023.442 I slot print_timing: id 3 | task 13667 | total time = 18442.78 ms / 876 tokens 11.47.023.443 I slot print_timing: id 3 | task 13667 | graphs reused = 13377 11.47.023.444 I slot print_timing: id 3 | task 13667 | graph reallocs = 0 / 0 (same size) / (changed size) 11.47.023.544 I slot release: id 3 | task 13667 | stop processing: n_tokens = 1562, truncated = 0 11.47.059.335 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.684 11.47.059.367 I slot launch_slot_: id 3 | task 14082 | processing task, is_child = 0 11.47.682.982 I slot print_timing: id 2 | task 13511 | n_gen = 567, tg = 21.74 t/s, tg_3s = 19.82 t/s 11.48.285.687 I slot print_timing: id 0 | task 13645 | n_gen = 448, tg = 21.83 t/s, tg_3s = 19.23 t/s 11.49.323.831 I slot print_timing: id 1 | task 13673 | n_gen = 447, tg = 23.27 t/s, tg_3s = 19.28 t/s 11.50.705.438 I slot print_timing: id 2 | task 13511 | n_gen = 639, tg = 21.95 t/s, tg_3s = 23.82 t/s 11.51.289.241 I slot print_timing: id 0 | task 13645 | n_gen = 520, tg = 22.10 t/s, tg_3s = 23.97 t/s 11.51.876.856 I slot print_timing: id 3 | task 14082 | n_gen = 100, tg = 24.02 t/s, tg_3s = 24.27 t/s 11.52.336.885 I slot print_timing: id 1 | task 13673 | n_gen = 519, tg = 23.36 t/s, tg_3s = 23.90 t/s 11.53.088.369 I slot print_timing: id 1 | task 13673 | prompt eval time = 731.44 ms / 467 tokens ( 1.57 ms per token, 638.46 tokens per second) 11.53.088.377 I slot print_timing: id 1 | task 13673 | eval time = 22929.69 ms / 537 tokens ( 42.78 ms per token, 23.38 tokens per second) 11.53.088.379 I slot print_timing: id 1 | task 13673 | total time = 23661.13 ms / 1004 tokens 11.53.088.380 I slot print_timing: id 1 | task 13673 | graphs reused = 13503 11.53.088.381 I slot print_timing: id 1 | task 13673 | graph reallocs = 0 / 0 (same size) / (changed size) 11.53.088.521 I slot release: id 1 | task 13673 | stop processing: n_tokens = 1678, truncated = 0 11.53.132.829 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.636 11.53.132.873 I slot launch_slot_: id 1 | task 14214 | processing task, is_child = 0 11.53.813.899 I slot print_timing: id 2 | task 13511 | n_gen = 698, tg = 21.67 t/s, tg_3s = 18.98 t/s 11.54.302.569 I slot print_timing: id 0 | task 13645 | n_gen = 576, tg = 21.70 t/s, tg_3s = 18.58 t/s 11.54.898.274 I slot print_timing: id 3 | task 14082 | n_gen = 156, tg = 21.70 t/s, tg_3s = 18.53 t/s 11.56.815.839 I slot print_timing: id 2 | task 13511 | n_gen = 769, tg = 21.84 t/s, tg_3s = 23.65 t/s 11.57.147.312 I slot print_timing: id 2 | task 13511 | prompt eval time = 774.98 ms / 514 tokens ( 1.51 ms per token, 663.24 tokens per second) 11.57.147.318 I slot print_timing: id 2 | task 13511 | eval time = 35503.76 ms / 777 tokens ( 45.75 ms per token, 21.86 tokens per second) 11.57.147.319 I slot print_timing: id 2 | task 13511 | total time = 36278.74 ms / 1291 tokens 11.57.147.320 I slot print_timing: id 2 | task 13511 | graphs reused = 13580 11.57.147.321 I slot print_timing: id 2 | task 13511 | graph reallocs = 0 / 0 (same size) / (changed size) 11.57.147.433 I slot release: id 2 | task 13511 | stop processing: n_tokens = 1954, truncated = 0 11.57.190.784 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.547 11.57.190.830 I slot launch_slot_: id 2 | task 14296 | processing task, is_child = 0 11.57.418.295 I slot print_timing: id 0 | task 13645 | n_gen = 646, tg = 21.78 t/s, tg_3s = 22.47 t/s 11.58.116.647 I slot print_timing: id 3 | task 14082 | n_gen = 213, tg = 20.46 t/s, tg_3s = 17.71 t/s 11.58.899.815 I slot print_timing: id 1 | task 14214 | n_gen = 100, tg = 19.78 t/s, tg_3s = 19.97 t/s 12.00.442.911 I slot print_timing: id 0 | task 13645 | n_gen = 702, tg = 21.48 t/s, tg_3s = 18.51 t/s 12.01.149.516 I slot print_timing: id 3 | task 14082 | n_gen = 285, tg = 21.20 t/s, tg_3s = 23.74 t/s 12.01.936.652 I slot print_timing: id 1 | task 14214 | n_gen = 173, tg = 21.38 t/s, tg_3s = 24.04 t/s 12.02.309.764 I slot print_timing: id 2 | task 14296 | n_gen = 100, tg = 24.06 t/s, tg_3s = 24.31 t/s 12.03.224.517 I slot print_timing: id 0 | task 13645 | prompt eval time = 703.70 ms / 462 tokens ( 1.52 ms per token, 656.53 tokens per second) 12.03.224.524 I slot print_timing: id 0 | task 13645 | eval time = 35415.31 ms / 769 tokens ( 46.11 ms per token, 21.69 tokens per second) 12.03.224.525 I slot print_timing: id 0 | task 13645 | total time = 36119.01 ms / 1231 tokens 12.03.224.526 I slot print_timing: id 0 | task 13645 | graphs reused = 13700 12.03.224.527 I slot print_timing: id 0 | task 13645 | graph reallocs = 0 / 0 (same size) / (changed size) 12.03.224.640 I slot release: id 0 | task 13645 | stop processing: n_tokens = 1926, truncated = 0 12.03.262.274 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.555 12.03.262.317 I slot launch_slot_: id 0 | task 14422 | processing task, is_child = 0 12.04.169.834 I slot print_timing: id 3 | task 14082 | n_gen = 343, tg = 20.84 t/s, tg_3s = 19.20 t/s 12.04.958.046 I slot print_timing: id 1 | task 14214 | n_gen = 231, tg = 20.79 t/s, tg_3s = 19.20 t/s 12.05.333.539 I slot print_timing: id 2 | task 14296 | n_gen = 158, tg = 22.00 t/s, tg_3s = 19.18 t/s 12.07.204.679 I slot print_timing: id 3 | task 14082 | n_gen = 416, tg = 21.34 t/s, tg_3s = 24.05 t/s 12.07.994.989 I slot print_timing: id 1 | task 14214 | n_gen = 304, tg = 21.49 t/s, tg_3s = 24.04 t/s 12.08.077.477 I slot print_timing: id 0 | task 14422 | n_gen = 100, tg = 24.07 t/s, tg_3s = 24.31 t/s 12.08.370.109 I slot print_timing: id 2 | task 14296 | n_gen = 231, tg = 22.61 t/s, tg_3s = 24.04 t/s 12.10.243.668 I slot print_timing: id 3 | task 14082 | n_gen = 489, tg = 21.70 t/s, tg_3s = 24.02 t/s 12.11.030.797 I slot print_timing: id 1 | task 14214 | n_gen = 377, tg = 21.94 t/s, tg_3s = 24.05 t/s 12.11.113.644 I slot print_timing: id 0 | task 14422 | n_gen = 173, tg = 24.06 t/s, tg_3s = 24.04 t/s 12.11.407.297 I slot print_timing: id 2 | task 14296 | n_gen = 304, tg = 22.93 t/s, tg_3s = 24.04 t/s 12.13.280.630 I slot print_timing: id 3 | task 14082 | n_gen = 562, tg = 21.98 t/s, tg_3s = 24.04 t/s 12.14.063.689 I slot print_timing: id 1 | task 14214 | n_gen = 450, tg = 22.26 t/s, tg_3s = 24.07 t/s 12.14.144.663 I slot print_timing: id 0 | task 14422 | n_gen = 246, tg = 24.07 t/s, tg_3s = 24.08 t/s 12.14.437.240 I slot print_timing: id 2 | task 14296 | n_gen = 377, tg = 23.15 t/s, tg_3s = 24.09 t/s 12.16.313.518 I slot print_timing: id 3 | task 14082 | n_gen = 635, tg = 22.20 t/s, tg_3s = 24.07 t/s 12.17.104.006 I slot print_timing: id 1 | task 14214 | n_gen = 523, tg = 22.49 t/s, tg_3s = 24.01 t/s 12.17.145.141 I slot print_timing: id 0 | task 14422 | n_gen = 318, tg = 24.05 t/s, tg_3s = 24.00 t/s 12.17.442.187 I slot print_timing: id 2 | task 14296 | n_gen = 449, tg = 23.28 t/s, tg_3s = 23.96 t/s 12.19.320.142 I slot print_timing: id 3 | task 14082 | n_gen = 707, tg = 22.37 t/s, tg_3s = 23.95 t/s 12.20.112.388 I slot print_timing: id 1 | task 14214 | n_gen = 595, tg = 22.66 t/s, tg_3s = 23.93 t/s 12.20.153.812 I slot print_timing: id 0 | task 14422 | n_gen = 390, tg = 24.03 t/s, tg_3s = 23.93 t/s 12.20.447.904 I slot print_timing: id 2 | task 14296 | n_gen = 521, tg = 23.37 t/s, tg_3s = 23.95 t/s 12.22.328.685 I slot print_timing: id 3 | task 14082 | n_gen = 779, tg = 22.50 t/s, tg_3s = 23.93 t/s 12.23.121.090 I slot print_timing: id 1 | task 14214 | n_gen = 667, tg = 22.79 t/s, tg_3s = 23.93 t/s 12.23.162.645 I slot print_timing: id 0 | task 14422 | n_gen = 462, tg = 24.01 t/s, tg_3s = 23.93 t/s 12.23.456.205 I slot print_timing: id 2 | task 14296 | n_gen = 593, tg = 23.44 t/s, tg_3s = 23.93 t/s 12.25.339.780 I slot print_timing: id 3 | task 14082 | n_gen = 851, tg = 22.62 t/s, tg_3s = 23.91 t/s 12.26.132.028 I slot print_timing: id 1 | task 14214 | n_gen = 739, tg = 22.89 t/s, tg_3s = 23.91 t/s 12.26.172.989 I slot print_timing: id 0 | task 14422 | n_gen = 534, tg = 24.00 t/s, tg_3s = 23.92 t/s 12.26.465.738 I slot print_timing: id 2 | task 14296 | n_gen = 665, tg = 23.49 t/s, tg_3s = 23.92 t/s 12.28.346.574 I slot print_timing: id 3 | task 14082 | n_gen = 923, tg = 22.71 t/s, tg_3s = 23.95 t/s 12.29.145.789 I slot print_timing: id 1 | task 14214 | n_gen = 811, tg = 22.98 t/s, tg_3s = 23.89 t/s 12.29.186.932 I slot print_timing: id 0 | task 14422 | n_gen = 606, tg = 23.99 t/s, tg_3s = 23.89 t/s 12.29.481.657 I slot print_timing: id 2 | task 14296 | n_gen = 737, tg = 23.52 t/s, tg_3s = 23.87 t/s 12.31.376.477 I slot print_timing: id 3 | task 14082 | n_gen = 995, tg = 22.79 t/s, tg_3s = 23.76 t/s 12.32.171.615 I slot print_timing: id 1 | task 14214 | n_gen = 883, tg = 23.04 t/s, tg_3s = 23.80 t/s 12.32.213.102 I slot print_timing: id 0 | task 14422 | n_gen = 678, tg = 23.97 t/s, tg_3s = 23.79 t/s 12.32.507.601 I slot print_timing: id 2 | task 14296 | n_gen = 809, tg = 23.55 t/s, tg_3s = 23.79 t/s 12.32.592.273 I slot print_timing: id 3 | task 14082 | prompt eval time = 696.46 ms / 451 tokens ( 1.54 ms per token, 647.56 tokens per second) 12.32.592.282 I slot print_timing: id 3 | task 14082 | eval time = 44836.43 ms / 1024 tokens ( 43.83 ms per token, 22.82 tokens per second) 12.32.592.283 I slot print_timing: id 3 | task 14082 | total time = 45532.90 ms / 1475 tokens 12.32.592.284 I slot print_timing: id 3 | task 14082 | graphs reused = 14383 12.32.592.285 I slot print_timing: id 3 | task 14082 | graph reallocs = 0 / 0 (same size) / (changed size) 12.32.592.409 I slot release: id 3 | task 14082 | stop processing: n_tokens = 2161, truncated = 0 12.32.629.268 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.494 12.32.631.517 I slot launch_slot_: id 3 | task 15112 | processing task, is_child = 0 12.35.100.535 I slot print_timing: id 1 | task 14214 | prompt eval time = 760.64 ms / 492 tokens ( 1.55 ms per token, 646.83 tokens per second) 12.35.100.542 I slot print_timing: id 1 | task 14214 | eval time = 41207.02 ms / 938 tokens ( 43.98 ms per token, 22.74 tokens per second) 12.35.100.543 I slot print_timing: id 1 | task 14214 | total time = 41967.65 ms / 1430 tokens 12.35.100.543 I slot print_timing: id 1 | task 14214 | graphs reused = 14424 12.35.100.544 I slot print_timing: id 1 | task 14214 | graph reallocs = 0 / 0 (same size) / (changed size) 12.35.100.644 I slot release: id 1 | task 14214 | stop processing: n_tokens = 2104, truncated = 0 12.35.145.059 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.508 12.35.145.100 I slot launch_slot_: id 1 | task 15158 | processing task, is_child = 0 12.35.804.602 I slot print_timing: id 0 | task 14422 | n_gen = 734, tg = 23.02 t/s, tg_3s = 15.59 t/s 12.35.804.915 I slot print_timing: id 2 | task 14296 | n_gen = 858, tg = 22.79 t/s, tg_3s = 14.86 t/s 12.38.146.278 I slot print_timing: id 3 | task 15112 | n_gen = 100, tg = 20.62 t/s, tg_3s = 20.83 t/s 12.38.817.346 I slot print_timing: id 0 | task 14422 | n_gen = 805, tg = 23.07 t/s, tg_3s = 23.57 t/s 12.38.818.684 I slot print_timing: id 2 | task 14296 | n_gen = 929, tg = 22.84 t/s, tg_3s = 23.56 t/s 12.40.029.046 I slot print_timing: id 1 | task 15158 | n_gen = 100, tg = 23.89 t/s, tg_3s = 24.13 t/s 12.41.155.284 I slot print_timing: id 0 | task 14422 | prompt eval time = 702.40 ms / 462 tokens ( 1.52 ms per token, 657.75 tokens per second) 12.41.155.290 I slot print_timing: id 0 | task 14422 | eval time = 37190.56 ms / 861 tokens ( 43.24 ms per token, 23.12 tokens per second) 12.41.155.291 I slot print_timing: id 0 | task 14422 | total time = 37892.96 ms / 1323 tokens 12.41.155.292 I slot print_timing: id 0 | task 14422 | graphs reused = 14549 12.41.155.292 I slot print_timing: id 0 | task 14422 | graph reallocs = 0 / 0 (same size) / (changed size) 12.41.155.393 I slot release: id 0 | task 14422 | stop processing: n_tokens = 2018, truncated = 0 12.41.157.072 I slot print_timing: id 3 | task 15112 | n_gen = 172, tg = 21.89 t/s, tg_3s = 23.91 t/s 12.41.192.769 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.529 12.41.192.807 I slot launch_slot_: id 0 | task 15288 | processing task, is_child = 0 12.41.841.557 I slot print_timing: id 2 | task 14296 | n_gen = 987, tg = 22.59 t/s, tg_3s = 19.19 t/s 12.43.038.954 I slot print_timing: id 1 | task 15158 | n_gen = 157, tg = 21.81 t/s, tg_3s = 18.94 t/s 12.43.418.115 I slot print_timing: id 2 | task 14296 | prompt eval time = 1004.82 ms / 545 tokens ( 1.84 ms per token, 542.38 tokens per second) 12.43.418.123 I slot print_timing: id 2 | task 14296 | eval time = 45222.46 ms / 1024 tokens ( 44.21 ms per token, 22.62 tokens per second) 12.43.418.123 I slot print_timing: id 2 | task 14296 | total time = 46227.28 ms / 1569 tokens 12.43.418.124 I slot print_timing: id 2 | task 14296 | graphs reused = 14585 12.43.418.125 I slot print_timing: id 2 | task 14296 | graph reallocs = 0 / 0 (same size) / (changed size) 12.43.418.241 I slot release: id 2 | task 14296 | stop processing: n_tokens = 2232, truncated = 0 12.43.461.553 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.478 12.43.468.264 I slot launch_slot_: id 2 | task 15328 | processing task, is_child = 0 12.44.193.373 I slot print_timing: id 3 | task 15112 | n_gen = 214, tg = 19.64 t/s, tg_3s = 13.83 t/s 12.46.053.723 I slot print_timing: id 1 | task 15158 | n_gen = 214, tg = 20.95 t/s, tg_3s = 18.91 t/s 12.46.678.243 I slot print_timing: id 0 | task 15288 | n_gen = 100, tg = 20.77 t/s, tg_3s = 20.98 t/s 12.47.220.890 I slot print_timing: id 3 | task 15112 | n_gen = 287, tg = 20.61 t/s, tg_3s = 24.11 t/s 12.48.300.079 I slot print_timing: id 2 | task 15328 | n_gen = 100, tg = 24.11 t/s, tg_3s = 24.35 t/s 12.49.090.978 I slot print_timing: id 1 | task 15158 | n_gen = 287, tg = 21.66 t/s, tg_3s = 24.03 t/s 12.49.714.330 I slot print_timing: id 0 | task 15288 | n_gen = 173, tg = 22.04 t/s, tg_3s = 24.04 t/s 12.50.258.156 I slot print_timing: id 3 | task 15112 | n_gen = 360, tg = 21.23 t/s, tg_3s = 24.03 t/s 12.51.340.288 I slot print_timing: id 2 | task 15328 | n_gen = 173, tg = 24.07 t/s, tg_3s = 24.01 t/s 12.52.093.756 I slot print_timing: id 1 | task 15158 | n_gen = 359, tg = 22.09 t/s, tg_3s = 23.98 t/s 12.52.718.439 I slot print_timing: id 0 | task 15288 | n_gen = 245, tg = 22.58 t/s, tg_3s = 23.97 t/s 12.53.260.962 I slot print_timing: id 3 | task 15112 | n_gen = 432, tg = 21.64 t/s, tg_3s = 23.98 t/s 12.54.342.262 I slot print_timing: id 2 | task 15328 | n_gen = 245, tg = 24.04 t/s, tg_3s = 23.98 t/s 12.55.133.222 I slot print_timing: id 1 | task 15158 | n_gen = 432, tg = 22.39 t/s, tg_3s = 24.02 t/s 12.55.757.393 I slot print_timing: id 0 | task 15288 | n_gen = 318, tg = 22.89 t/s, tg_3s = 24.02 t/s 12.56.302.226 I slot print_timing: id 3 | task 15112 | n_gen = 505, tg = 21.95 t/s, tg_3s = 24.00 t/s 12.57.343.948 I slot print_timing: id 2 | task 15328 | n_gen = 317, tg = 24.03 t/s, tg_3s = 23.99 t/s 12.58.134.217 I slot print_timing: id 1 | task 15158 | n_gen = 504, tg = 22.61 t/s, tg_3s = 23.99 t/s 12.58.717.912 I slot print_timing: id 2 | task 15328 | prompt eval time = 724.78 ms / 457 tokens ( 1.59 ms per token, 630.54 tokens per second) 12.58.717.920 I slot print_timing: id 2 | task 15328 | eval time = 14524.86 ms / 350 tokens ( 41.62 ms per token, 24.03 tokens per second) 12.58.717.921 I slot print_timing: id 2 | task 15328 | total time = 15249.64 ms / 807 tokens 12.58.717.921 I slot print_timing: id 2 | task 15328 | graphs reused = 14932 12.58.717.922 I slot print_timing: id 2 | task 15328 | graph reallocs = 0 / 0 (same size) / (changed size) 12.58.718.036 I slot release: id 2 | task 15328 | stop processing: n_tokens = 1499, truncated = 0 12.58.760.522 I slot print_timing: id 0 | task 15288 | n_gen = 390, tg = 23.09 t/s, tg_3s = 23.97 t/s 12.58.761.616 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.712 12.58.761.663 I slot launch_slot_: id 2 | task 15681 | processing task, is_child = 0 12.59.413.771 I slot print_timing: id 3 | task 15112 | n_gen = 565, tg = 21.64 t/s, tg_3s = 19.28 t/s 13.01.155.313 I slot print_timing: id 1 | task 15158 | n_gen = 561, tg = 22.16 t/s, tg_3s = 18.87 t/s 13.01.738.368 I slot print_timing: id 3 | task 15112 | prompt eval time = 714.20 ms / 457 tokens ( 1.56 ms per token, 639.88 tokens per second) 13.01.738.373 I slot print_timing: id 3 | task 15112 | eval time = 28392.64 ms / 620 tokens ( 45.87 ms per token, 21.80 tokens per second) 13.01.738.374 I slot print_timing: id 3 | task 15112 | total time = 29106.84 ms / 1077 tokens 13.01.738.374 I slot print_timing: id 3 | task 15112 | graphs reused = 14985 13.01.738.375 I slot print_timing: id 3 | task 15112 | graph reallocs = 0 / 0 (same size) / (changed size) 13.01.738.477 I slot release: id 3 | task 15112 | stop processing: n_tokens = 1763, truncated = 0 13.01.772.972 I slot print_timing: id 0 | task 15288 | n_gen = 447, tg = 22.46 t/s, tg_3s = 18.92 t/s 13.01.773.862 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.606 13.01.773.897 I slot launch_slot_: id 3 | task 15739 | processing task, is_child = 0 13.04.162.178 I slot print_timing: id 1 | task 15158 | prompt eval time = 739.60 ms / 475 tokens ( 1.56 ms per token, 642.24 tokens per second) 13.04.162.185 I slot print_timing: id 1 | task 15158 | eval time = 28277.47 ms / 618 tokens ( 45.83 ms per token, 21.82 tokens per second) 13.04.162.186 I slot print_timing: id 1 | task 15158 | total time = 29017.07 ms / 1093 tokens 13.04.162.187 I slot print_timing: id 1 | task 15158 | graphs reused = 15024 13.04.162.187 I slot print_timing: id 1 | task 15158 | graph reallocs = 0 / 0 (same size) / (changed size) 13.04.162.286 I slot release: id 1 | task 15158 | stop processing: n_tokens = 1767, truncated = 0 13.04.205.635 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.604 13.04.205.673 I slot launch_slot_: id 1 | task 15783 | processing task, is_child = 0 13.04.882.235 I slot print_timing: id 0 | task 15288 | n_gen = 491, tg = 21.33 t/s, tg_3s = 14.15 t/s 13.04.882.504 I slot print_timing: id 2 | task 15681 | n_gen = 100, tg = 18.37 t/s, tg_3s = 18.55 t/s 13.07.281.746 I slot print_timing: id 3 | task 15739 | n_gen = 100, tg = 20.70 t/s, tg_3s = 20.91 t/s 13.07.904.609 I slot print_timing: id 0 | task 15288 | n_gen = 563, tg = 21.62 t/s, tg_3s = 23.82 t/s 13.07.905.603 I slot print_timing: id 2 | task 15681 | n_gen = 172, tg = 20.33 t/s, tg_3s = 23.82 t/s 13.09.071.347 I slot print_timing: id 1 | task 15783 | n_gen = 100, tg = 24.09 t/s, tg_3s = 24.33 t/s 13.10.283.245 I slot print_timing: id 3 | task 15739 | n_gen = 172, tg = 21.97 t/s, tg_3s = 23.99 t/s 13.10.906.667 I slot print_timing: id 0 | task 15288 | n_gen = 635, tg = 21.87 t/s, tg_3s = 23.98 t/s 13.10.907.747 I slot print_timing: id 2 | task 15681 | n_gen = 244, tg = 21.29 t/s, tg_3s = 23.98 t/s 13.12.072.434 I slot print_timing: id 1 | task 15783 | n_gen = 172, tg = 24.05 t/s, tg_3s = 23.99 t/s 13.13.284.722 I slot print_timing: id 3 | task 15739 | n_gen = 244, tg = 22.53 t/s, tg_3s = 23.99 t/s 13.13.908.678 I slot print_timing: id 0 | task 15288 | n_gen = 707, tg = 22.06 t/s, tg_3s = 23.98 t/s 13.13.909.704 I slot print_timing: id 2 | task 15681 | n_gen = 316, tg = 21.85 t/s, tg_3s = 23.98 t/s 13.15.074.923 I slot print_timing: id 1 | task 15783 | n_gen = 244, tg = 24.03 t/s, tg_3s = 23.98 t/s 13.16.325.699 I slot print_timing: id 3 | task 15739 | n_gen = 317, tg = 22.85 t/s, tg_3s = 24.01 t/s 13.16.948.974 I slot print_timing: id 0 | task 15288 | n_gen = 780, tg = 22.23 t/s, tg_3s = 24.01 t/s 13.16.950.056 I slot print_timing: id 2 | task 15681 | n_gen = 389, tg = 22.23 t/s, tg_3s = 24.01 t/s 13.18.114.874 I slot print_timing: id 1 | task 15783 | n_gen = 317, tg = 24.02 t/s, tg_3s = 24.01 t/s 13.19.366.579 I slot print_timing: id 3 | task 15739 | n_gen = 390, tg = 23.06 t/s, tg_3s = 24.01 t/s 13.19.949.274 I slot print_timing: id 0 | task 15288 | n_gen = 852, tg = 22.37 t/s, tg_3s = 24.00 t/s 13.19.950.409 I slot print_timing: id 2 | task 15681 | n_gen = 461, tg = 22.49 t/s, tg_3s = 24.00 t/s 13.21.124.203 I slot print_timing: id 1 | task 15783 | n_gen = 389, tg = 24.01 t/s, tg_3s = 23.93 t/s 13.22.383.701 I slot print_timing: id 3 | task 15739 | n_gen = 462, tg = 23.18 t/s, tg_3s = 23.86 t/s 13.22.968.667 I slot print_timing: id 0 | task 15288 | n_gen = 924, tg = 22.48 t/s, tg_3s = 23.85 t/s 13.22.969.815 I slot print_timing: id 2 | task 15681 | n_gen = 533, tg = 22.66 t/s, tg_3s = 23.85 t/s 13.24.144.968 I slot print_timing: id 1 | task 15783 | n_gen = 461, tg = 23.98 t/s, tg_3s = 23.84 t/s 13.25.403.481 I slot print_timing: id 3 | task 15739 | n_gen = 534, tg = 23.27 t/s, tg_3s = 23.84 t/s 13.25.987.353 I slot print_timing: id 0 | task 15288 | n_gen = 996, tg = 22.57 t/s, tg_3s = 23.85 t/s 13.25.988.559 I slot print_timing: id 2 | task 15681 | n_gen = 605, tg = 22.80 t/s, tg_3s = 23.85 t/s 13.27.163.516 I slot print_timing: id 0 | task 15288 | prompt eval time = 718.69 ms / 483 tokens ( 1.49 ms per token, 672.06 tokens per second) 13.27.163.522 I slot print_timing: id 0 | task 15288 | eval time = 45252.01 ms / 1024 tokens ( 44.23 ms per token, 22.61 tokens per second) 13.27.163.524 I slot print_timing: id 0 | task 15288 | total time = 45970.70 ms / 1507 tokens 13.27.163.525 I slot print_timing: id 0 | task 15288 | graphs reused = 15553 13.27.163.525 I slot print_timing: id 0 | task 15288 | graph reallocs = 0 / 0 (same size) / (changed size) 13.27.163.635 I slot release: id 0 | task 15288 | stop processing: n_tokens = 2202, truncated = 0 13.27.164.251 I slot print_timing: id 1 | task 15783 | n_gen = 533, tg = 23.96 t/s, tg_3s = 23.85 t/s 13.27.201.706 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.485 13.27.207.935 I slot launch_slot_: id 0 | task 16319 | processing task, is_child = 0 13.28.423.354 I slot print_timing: id 3 | task 15739 | n_gen = 592, tg = 22.80 t/s, tg_3s = 19.21 t/s 13.28.996.569 I slot print_timing: id 2 | task 15681 | n_gen = 663, tg = 22.44 t/s, tg_3s = 19.28 t/s 13.30.172.349 I slot print_timing: id 1 | task 15783 | n_gen = 591, tg = 23.40 t/s, tg_3s = 19.28 t/s 13.31.426.545 I slot print_timing: id 3 | task 15739 | n_gen = 664, tg = 22.92 t/s, tg_3s = 23.97 t/s 13.32.007.269 I slot print_timing: id 0 | task 16319 | n_gen = 100, tg = 24.05 t/s, tg_3s = 24.30 t/s 13.32.008.265 I slot print_timing: id 2 | task 15681 | n_gen = 735, tg = 22.57 t/s, tg_3s = 23.91 t/s 13.33.175.575 I slot print_timing: id 1 | task 15783 | n_gen = 663, tg = 23.46 t/s, tg_3s = 23.97 t/s 13.33.759.295 I slot print_timing: id 3 | task 15739 | prompt eval time = 725.36 ms / 475 tokens ( 1.53 ms per token, 654.85 tokens per second) 13.33.759.300 I slot print_timing: id 3 | task 15739 | eval time = 31260.03 ms / 720 tokens ( 43.48 ms per token, 23.00 tokens per second) 13.33.759.301 I slot print_timing: id 3 | task 15739 | total time = 31985.39 ms / 1195 tokens 13.33.759.302 I slot print_timing: id 3 | task 15739 | graphs reused = 15694 13.33.759.303 I slot print_timing: id 3 | task 15739 | graph reallocs = 0 / 0 (same size) / (changed size) 13.33.759.412 I slot release: id 3 | task 15739 | stop processing: n_tokens = 1881, truncated = 0 13.33.795.438 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.568 13.33.795.477 I slot launch_slot_: id 3 | task 16464 | processing task, is_child = 0 13.35.009.785 I slot print_timing: id 0 | task 16319 | n_gen = 157, tg = 21.91 t/s, tg_3s = 18.98 t/s 13.35.010.314 I slot print_timing: id 2 | task 15681 | n_gen = 792, tg = 22.27 t/s, tg_3s = 18.99 t/s 13.36.217.084 I slot print_timing: id 1 | task 15783 | n_gen = 721, tg = 23.04 t/s, tg_3s = 19.07 t/s 13.36.425.897 I slot print_timing: id 2 | task 15681 | prompt eval time = 731.01 ms / 467 tokens ( 1.57 ms per token, 638.84 tokens per second) 13.36.425.904 I slot print_timing: id 2 | task 15681 | eval time = 36933.21 ms / 826 tokens ( 44.77 ms per token, 22.34 tokens per second) 13.36.425.905 I slot print_timing: id 2 | task 15681 | total time = 37664.22 ms / 1293 tokens 13.36.425.906 I slot print_timing: id 2 | task 15681 | graphs reused = 15739 13.36.425.906 I slot print_timing: id 2 | task 15681 | graph reallocs = 0 / 0 (same size) / (changed size) 13.36.426.019 I slot release: id 2 | task 15681 | stop processing: n_tokens = 1985, truncated = 0 13.36.469.379 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.538 13.36.469.416 I slot launch_slot_: id 2 | task 16514 | processing task, is_child = 0 13.38.024.532 I slot print_timing: id 0 | task 16319 | n_gen = 214, tg = 21.02 t/s, tg_3s = 18.91 t/s 13.39.234.123 I slot print_timing: id 1 | task 15783 | n_gen = 778, tg = 22.67 t/s, tg_3s = 18.89 t/s 13.39.276.408 I slot print_timing: id 3 | task 16464 | n_gen = 100, tg = 20.82 t/s, tg_3s = 21.03 t/s 13.41.065.327 I slot print_timing: id 0 | task 16319 | n_gen = 287, tg = 21.71 t/s, tg_3s = 24.01 t/s 13.41.065.862 I slot print_timing: id 1 | task 15783 | prompt eval time = 755.90 ms / 487 tokens ( 1.55 ms per token, 644.26 tokens per second) 13.41.065.864 I slot print_timing: id 1 | task 15783 | eval time = 36104.28 ms / 822 tokens ( 43.98 ms per token, 22.74 tokens per second) 13.41.065.865 I slot print_timing: id 1 | task 15783 | total time = 36860.18 ms / 1309 tokens 13.41.065.866 I slot print_timing: id 1 | task 15783 | graphs reused = 15831 13.41.065.867 I slot print_timing: id 1 | task 15783 | graph reallocs = 0 / 0 (same size) / (changed size) 13.41.065.982 I slot release: id 1 | task 15783 | stop processing: n_tokens = 1983, truncated = 0 13.41.110.242 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.539 13.41.110.281 I slot launch_slot_: id 1 | task 16611 | processing task, is_child = 0 13.41.966.997 I slot print_timing: id 2 | task 16514 | n_gen = 100, tg = 20.75 t/s, tg_3s = 20.96 t/s 13.42.301.461 I slot print_timing: id 3 | task 16464 | n_gen = 157, tg = 20.05 t/s, tg_3s = 18.84 t/s 13.44.090.324 I slot print_timing: id 0 | task 16319 | n_gen = 344, tg = 21.17 t/s, tg_3s = 18.84 t/s 13.45.007.364 I slot print_timing: id 2 | task 16514 | n_gen = 173, tg = 22.02 t/s, tg_3s = 24.01 t/s 13.45.341.155 I slot print_timing: id 3 | task 16464 | n_gen = 230, tg = 21.16 t/s, tg_3s = 24.02 t/s 13.45.965.710 I slot print_timing: id 1 | task 16611 | n_gen = 100, tg = 24.02 t/s, tg_3s = 24.26 t/s 13.47.092.462 I slot print_timing: id 0 | task 16319 | n_gen = 416, tg = 21.61 t/s, tg_3s = 23.98 t/s 13.48.010.999 I slot print_timing: id 0 | task 16319 | prompt eval time = 683.33 ms / 449 tokens ( 1.52 ms per token, 657.07 tokens per second) 13.48.011.005 I slot print_timing: id 0 | task 16319 | eval time = 20119.72 ms / 438 tokens ( 46.04 ms per token, 21.72 tokens per second) 13.48.011.006 I slot print_timing: id 0 | task 16319 | total time = 20803.05 ms / 887 tokens 13.48.011.007 I slot print_timing: id 0 | task 16319 | graphs reused = 15977 13.48.011.008 I slot print_timing: id 0 | task 16319 | graph reallocs = 0 / 0 (same size) / (changed size) 13.48.011.115 I slot release: id 0 | task 16319 | stop processing: n_tokens = 1582, truncated = 0 13.48.012.227 I slot print_timing: id 2 | task 16514 | n_gen = 245, tg = 22.56 t/s, tg_3s = 23.96 t/s 13.48.048.645 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.675 13.48.048.691 I slot launch_slot_: id 0 | task 16763 | processing task, is_child = 0 13.48.659.293 I slot print_timing: id 3 | task 16464 | n_gen = 296, tg = 20.86 t/s, tg_3s = 19.89 t/s 13.48.975.350 I slot print_timing: id 1 | task 16611 | n_gen = 158, tg = 22.01 t/s, tg_3s = 19.27 t/s 13.50.769.902 I slot print_timing: id 2 | task 16514 | prompt eval time = 725.66 ms / 459 tokens ( 1.58 ms per token, 632.53 tokens per second) 13.50.769.909 I slot print_timing: id 2 | task 16514 | eval time = 13574.81 ms / 297 tokens ( 45.86 ms per token, 21.81 tokens per second) 13.50.769.910 I slot print_timing: id 2 | task 16514 | total time = 14300.47 ms / 756 tokens 13.50.769.911 I slot print_timing: id 2 | task 16514 | graphs reused = 16026 13.50.769.912 I slot print_timing: id 2 | task 16514 | graph reallocs = 0 / 0 (same size) / (changed size) 13.50.770.048 I slot release: id 2 | task 16514 | stop processing: n_tokens = 1448, truncated = 0 13.50.813.936 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.738 13.50.813.971 I slot launch_slot_: id 2 | task 16816 | processing task, is_child = 0 13.51.671.517 I slot print_timing: id 3 | task 16464 | n_gen = 351, tg = 20.41 t/s, tg_3s = 18.26 t/s 13.51.996.664 I slot print_timing: id 1 | task 16611 | n_gen = 214, tg = 20.98 t/s, tg_3s = 18.53 t/s 13.53.539.505 I slot print_timing: id 0 | task 16763 | n_gen = 100, tg = 20.58 t/s, tg_3s = 20.79 t/s 13.54.705.617 I slot print_timing: id 3 | task 16464 | n_gen = 424, tg = 20.96 t/s, tg_3s = 24.06 t/s 13.55.037.364 I slot print_timing: id 1 | task 16611 | n_gen = 287, tg = 21.68 t/s, tg_3s = 24.01 t/s 13.55.702.777 I slot print_timing: id 2 | task 16816 | n_gen = 100, tg = 24.06 t/s, tg_3s = 24.31 t/s 13.56.573.880 I slot print_timing: id 0 | task 16763 | n_gen = 173, tg = 21.93 t/s, tg_3s = 24.06 t/s 13.57.738.149 I slot print_timing: id 3 | task 16464 | n_gen = 497, tg = 21.36 t/s, tg_3s = 24.07 t/s 13.58.070.895 I slot print_timing: id 1 | task 16611 | n_gen = 360, tg = 22.12 t/s, tg_3s = 24.06 t/s 13.58.737.261 I slot print_timing: id 2 | task 16816 | n_gen = 173, tg = 24.06 t/s, tg_3s = 24.06 t/s 13.58.821.297 I slot print_timing: id 3 | task 16464 | prompt eval time = 724.83 ms / 475 tokens ( 1.53 ms per token, 655.33 tokens per second) 13.58.821.305 I slot print_timing: id 3 | task 16464 | eval time = 24300.98 ms / 523 tokens ( 46.55 ms per token, 21.48 tokens per second) 13.58.821.306 I slot print_timing: id 3 | task 16464 | total time = 25025.81 ms / 998 tokens 13.58.821.307 I slot print_timing: id 3 | task 16464 | graphs reused = 16198 13.58.821.307 I slot print_timing: id 3 | task 16464 | graph reallocs = 0 / 0 (same size) / (changed size) 13.58.821.425 I slot release: id 3 | task 16464 | stop processing: n_tokens = 1684, truncated = 0 13.58.857.147 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.634 13.58.857.182 I slot launch_slot_: id 3 | task 16994 | processing task, is_child = 0 13.59.576.668 I slot print_timing: id 0 | task 16763 | n_gen = 230, tg = 21.11 t/s, tg_3s = 18.98 t/s 14.01.075.496 I slot print_timing: id 1 | task 16611 | n_gen = 417, tg = 21.63 t/s, tg_3s = 18.97 t/s 14.01.742.678 I slot print_timing: id 2 | task 16816 | n_gen = 230, tg = 22.55 t/s, tg_3s = 18.97 t/s 14.02.614.579 I slot print_timing: id 0 | task 16763 | n_gen = 303, tg = 21.75 t/s, tg_3s = 24.03 t/s 14.03.698.784 I slot print_timing: id 3 | task 16994 | n_gen = 100, tg = 24.02 t/s, tg_3s = 24.26 t/s 14.04.113.998 I slot print_timing: id 1 | task 16611 | n_gen = 490, tg = 21.96 t/s, tg_3s = 24.02 t/s 14.04.611.832 I slot print_timing: id 1 | task 16611 | prompt eval time = 733.50 ms / 467 tokens ( 1.57 ms per token, 636.68 tokens per second) 14.04.611.840 I slot print_timing: id 1 | task 16611 | eval time = 22768.04 ms / 502 tokens ( 45.45 ms per token, 22.00 tokens per second) 14.04.611.840 I slot print_timing: id 1 | task 16611 | total time = 23501.54 ms / 969 tokens 14.04.611.841 I slot print_timing: id 1 | task 16611 | graphs reused = 16317 14.04.611.842 I slot print_timing: id 1 | task 16611 | graph reallocs = 0 / 0 (same size) / (changed size) 14.04.611.967 I slot release: id 1 | task 16611 | stop processing: n_tokens = 1643, truncated = 0 14.04.656.416 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.650 14.04.656.458 I slot launch_slot_: id 1 | task 17119 | processing task, is_child = 0 14.05.324.123 I slot print_timing: id 2 | task 16816 | n_gen = 301, tg = 21.84 t/s, tg_3s = 19.82 t/s 14.05.648.861 I slot print_timing: id 0 | task 16763 | n_gen = 360, tg = 21.22 t/s, tg_3s = 18.79 t/s 14.06.738.775 I slot print_timing: id 3 | task 16994 | n_gen = 157, tg = 21.78 t/s, tg_3s = 18.75 t/s 14.08.324.618 I slot print_timing: id 2 | task 16816 | n_gen = 372, tg = 22.17 t/s, tg_3s = 23.66 t/s 14.08.658.274 I slot print_timing: id 0 | task 16763 | n_gen = 432, tg = 21.63 t/s, tg_3s = 23.92 t/s 14.09.533.346 I slot print_timing: id 1 | task 17119 | n_gen = 100, tg = 23.97 t/s, tg_3s = 24.22 t/s 14.09.742.372 I slot print_timing: id 3 | task 16994 | n_gen = 229, tg = 22.43 t/s, tg_3s = 23.97 t/s 14.11.364.366 I slot print_timing: id 2 | task 16816 | n_gen = 445, tg = 22.45 t/s, tg_3s = 24.02 t/s 14.11.695.932 I slot print_timing: id 0 | task 16763 | n_gen = 505, tg = 21.94 t/s, tg_3s = 24.03 t/s 14.12.571.573 I slot print_timing: id 1 | task 17119 | n_gen = 173, tg = 24.00 t/s, tg_3s = 24.03 t/s 14.12.781.143 I slot print_timing: id 3 | task 16994 | n_gen = 302, tg = 22.80 t/s, tg_3s = 24.02 t/s 14.14.402.645 I slot print_timing: id 2 | task 16816 | n_gen = 518, tg = 22.66 t/s, tg_3s = 24.03 t/s 14.14.733.926 I slot print_timing: id 0 | task 16763 | n_gen = 578, tg = 22.19 t/s, tg_3s = 24.03 t/s 14.15.572.293 I slot print_timing: id 1 | task 17119 | n_gen = 245, tg = 24.00 t/s, tg_3s = 23.99 t/s 14.15.782.720 I slot print_timing: id 3 | task 16994 | n_gen = 374, tg = 23.02 t/s, tg_3s = 23.99 t/s 14.16.073.595 I slot print_timing: id 0 | task 16763 | prompt eval time = 680.44 ms / 443 tokens ( 1.54 ms per token, 651.05 tokens per second) 14.16.073.602 I slot print_timing: id 0 | task 16763 | eval time = 27344.45 ms / 610 tokens ( 44.90 ms per token, 22.27 tokens per second) 14.16.073.604 I slot print_timing: id 0 | task 16763 | total time = 28024.90 ms / 1053 tokens 14.16.073.605 I slot print_timing: id 0 | task 16763 | graphs reused = 16571 14.16.073.605 I slot print_timing: id 0 | task 16763 | graph reallocs = 0 / 0 (same size) / (changed size) 14.16.073.712 I slot release: id 0 | task 16763 | stop processing: n_tokens = 1748, truncated = 0 14.16.110.904 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.611 14.16.110.946 I slot launch_slot_: id 0 | task 17379 | processing task, is_child = 0 14.17.412.490 I slot print_timing: id 2 | task 16816 | n_gen = 576, tg = 22.27 t/s, tg_3s = 19.27 t/s 14.18.594.488 I slot print_timing: id 1 | task 17119 | n_gen = 303, tg = 22.90 t/s, tg_3s = 19.19 t/s 14.18.803.989 I slot print_timing: id 3 | task 16994 | n_gen = 432, tg = 22.42 t/s, tg_3s = 19.20 t/s 14.20.427.526 I slot print_timing: id 2 | task 16816 | n_gen = 648, tg = 22.43 t/s, tg_3s = 23.88 t/s 14.20.927.270 I slot print_timing: id 0 | task 17379 | n_gen = 100, tg = 23.97 t/s, tg_3s = 24.21 t/s 14.21.596.895 I slot print_timing: id 1 | task 17119 | n_gen = 375, tg = 23.10 t/s, tg_3s = 23.98 t/s 14.21.805.920 I slot print_timing: id 3 | task 16994 | n_gen = 504, tg = 22.63 t/s, tg_3s = 23.98 t/s 14.23.429.283 I slot print_timing: id 2 | task 16816 | n_gen = 720, tg = 22.58 t/s, tg_3s = 23.99 t/s 14.23.928.291 I slot print_timing: id 0 | task 17379 | n_gen = 172, tg = 23.98 t/s, tg_3s = 23.99 t/s 14.24.638.589 I slot print_timing: id 1 | task 17119 | n_gen = 448, tg = 23.24 t/s, tg_3s = 24.00 t/s 14.24.807.461 I slot print_timing: id 3 | task 16994 | n_gen = 576, tg = 22.79 t/s, tg_3s = 23.99 t/s 14.26.436.715 I slot print_timing: id 2 | task 16816 | n_gen = 792, tg = 22.70 t/s, tg_3s = 23.94 t/s 14.26.937.557 I slot print_timing: id 0 | task 17379 | n_gen = 244, tg = 23.96 t/s, tg_3s = 23.93 t/s 14.27.648.731 I slot print_timing: id 1 | task 17119 | n_gen = 520, tg = 23.33 t/s, tg_3s = 23.92 t/s 14.27.816.514 I slot print_timing: id 3 | task 16994 | n_gen = 648, tg = 22.91 t/s, tg_3s = 23.93 t/s 14.29.448.481 I slot print_timing: id 2 | task 16816 | n_gen = 864, tg = 22.79 t/s, tg_3s = 23.91 t/s 14.29.950.725 I slot print_timing: id 0 | task 17379 | n_gen = 316, tg = 23.95 t/s, tg_3s = 23.90 t/s 14.30.665.667 I slot print_timing: id 1 | task 17119 | n_gen = 592, tg = 23.40 t/s, tg_3s = 23.87 t/s 14.30.834.756 I slot print_timing: id 3 | task 16994 | n_gen = 720, tg = 23.00 t/s, tg_3s = 23.85 t/s 14.32.470.792 I slot print_timing: id 2 | task 16816 | n_gen = 936, tg = 22.87 t/s, tg_3s = 23.82 t/s 14.32.971.674 I slot print_timing: id 0 | task 17379 | n_gen = 388, tg = 23.93 t/s, tg_3s = 23.83 t/s 14.33.686.280 I slot print_timing: id 1 | task 17119 | n_gen = 664, tg = 23.44 t/s, tg_3s = 23.84 t/s 14.33.855.705 I slot print_timing: id 3 | task 16994 | n_gen = 792, tg = 23.08 t/s, tg_3s = 23.83 t/s 14.35.488.140 I slot print_timing: id 2 | task 16816 | n_gen = 1008, tg = 22.94 t/s, tg_3s = 23.86 t/s 14.35.990.032 I slot print_timing: id 0 | task 17379 | n_gen = 460, tg = 23.91 t/s, tg_3s = 23.85 t/s 14.36.158.998 I slot print_timing: id 2 | task 16816 | prompt eval time = 774.50 ms / 511 tokens ( 1.52 ms per token, 659.78 tokens per second) 14.36.159.003 I slot print_timing: id 2 | task 16816 | eval time = 44570.52 ms / 1024 tokens ( 43.57 ms per token, 22.95 tokens per second) 14.36.159.003 I slot print_timing: id 2 | task 16816 | total time = 45345.02 ms / 1535 tokens 14.36.159.004 I slot print_timing: id 2 | task 16816 | graphs reused = 17032 14.36.159.005 I slot print_timing: id 2 | task 16816 | graph reallocs = 0 / 0 (same size) / (changed size) 14.36.159.127 I slot release: id 2 | task 16816 | stop processing: n_tokens = 2227, truncated = 0 14.36.202.961 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.480 14.36.209.446 I slot launch_slot_: id 2 | task 17846 | processing task, is_child = 0 14.36.862.442 I slot print_timing: id 1 | task 17119 | n_gen = 725, tg = 23.01 t/s, tg_3s = 19.21 t/s 14.36.862.733 I slot print_timing: id 3 | task 16994 | n_gen = 849, tg = 22.74 t/s, tg_3s = 18.96 t/s 14.38.992.135 I slot print_timing: id 0 | task 17379 | n_gen = 516, tg = 23.20 t/s, tg_3s = 18.65 t/s 14.39.873.031 I slot print_timing: id 1 | task 17119 | n_gen = 796, tg = 23.06 t/s, tg_3s = 23.58 t/s 14.39.874.073 I slot print_timing: id 3 | task 16994 | n_gen = 920, tg = 22.81 t/s, tg_3s = 23.58 t/s 14.41.092.263 I slot print_timing: id 2 | task 17846 | n_gen = 100, tg = 23.85 t/s, tg_3s = 24.09 t/s 14.42.013.007 I slot print_timing: id 0 | task 17379 | n_gen = 588, tg = 23.28 t/s, tg_3s = 23.83 t/s 14.42.894.520 I slot print_timing: id 1 | task 17119 | n_gen = 868, tg = 23.13 t/s, tg_3s = 23.83 t/s 14.42.895.664 I slot print_timing: id 3 | task 16994 | n_gen = 992, tg = 22.88 t/s, tg_3s = 23.83 t/s 14.43.816.660 I slot print_timing: id 0 | task 17379 | prompt eval time = 685.99 ms / 451 tokens ( 1.52 ms per token, 657.44 tokens per second) 14.43.816.667 I slot print_timing: id 0 | task 17379 | eval time = 27019.71 ms / 631 tokens ( 42.89 ms per token, 23.32 tokens per second) 14.43.816.668 I slot print_timing: id 0 | task 17379 | total time = 27705.71 ms / 1082 tokens 14.43.816.669 I slot print_timing: id 0 | task 17379 | graphs reused = 17194 14.43.816.670 I slot print_timing: id 0 | task 17379 | graph reallocs = 0 / 0 (same size) / (changed size) 14.43.816.782 I slot release: id 0 | task 17379 | stop processing: n_tokens = 1777, truncated = 0 14.43.854.914 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.601 14.43.854.952 I slot launch_slot_: id 0 | task 18014 | processing task, is_child = 0 14.44.458.386 I slot print_timing: id 2 | task 17846 | n_gen = 167, tg = 22.08 t/s, tg_3s = 19.90 t/s 14.44.817.928 I slot print_timing: id 3 | task 16994 | prompt eval time = 720.35 ms / 471 tokens ( 1.53 ms per token, 653.85 tokens per second) 14.44.817.933 I slot print_timing: id 3 | task 16994 | eval time = 45240.39 ms / 1024 tokens ( 44.22 ms per token, 22.61 tokens per second) 14.44.817.934 I slot print_timing: id 3 | task 16994 | total time = 45960.74 ms / 1495 tokens 14.44.817.934 I slot print_timing: id 3 | task 16994 | graphs reused = 17201 14.44.817.935 I slot print_timing: id 3 | task 16994 | graph reallocs = 0 / 0 (same size) / (changed size) 14.44.818.025 I slot release: id 3 | task 16994 | stop processing: n_tokens = 2181, truncated = 0 14.44.852.347 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.490 14.44.857.731 I slot launch_slot_: id 3 | task 18025 | processing task, is_child = 0 14.45.907.375 I slot print_timing: id 1 | task 17119 | n_gen = 911, tg = 22.47 t/s, tg_3s = 14.27 t/s 14.47.498.380 I slot print_timing: id 2 | task 17846 | n_gen = 224, tg = 21.12 t/s, tg_3s = 18.75 t/s 14.48.919.709 I slot print_timing: id 1 | task 17119 | n_gen = 983, tg = 22.57 t/s, tg_3s = 23.90 t/s 14.49.296.319 I slot print_timing: id 0 | task 18014 | n_gen = 100, tg = 20.76 t/s, tg_3s = 20.97 t/s 14.49.714.609 I slot print_timing: id 3 | task 18025 | n_gen = 100, tg = 23.94 t/s, tg_3s = 24.19 t/s 14.50.505.451 I slot print_timing: id 2 | task 17846 | n_gen = 296, tg = 21.75 t/s, tg_3s = 23.94 t/s 14.50.629.916 I slot print_timing: id 1 | task 17119 | prompt eval time = 747.45 ms / 484 tokens ( 1.54 ms per token, 647.53 tokens per second) 14.50.629.923 I slot print_timing: id 1 | task 17119 | eval time = 45226.00 ms / 1024 tokens ( 44.21 ms per token, 22.62 tokens per second) 14.50.629.924 I slot print_timing: id 1 | task 17119 | total time = 45973.45 ms / 1508 tokens 14.50.629.925 I slot print_timing: id 1 | task 17119 | graphs reused = 17321 14.50.629.926 I slot print_timing: id 1 | task 17119 | graph reallocs = 0 / 0 (same size) / (changed size) 14.50.630.029 I slot release: id 1 | task 17119 | stop processing: n_tokens = 2182, truncated = 0 14.50.673.963 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.489 14.50.680.280 I slot launch_slot_: id 1 | task 18150 | processing task, is_child = 0 14.52.312.088 I slot print_timing: id 0 | task 18014 | n_gen = 157, tg = 20.04 t/s, tg_3s = 18.90 t/s 14.52.730.231 I slot print_timing: id 3 | task 18025 | n_gen = 157, tg = 21.82 t/s, tg_3s = 18.90 t/s 14.53.520.715 I slot print_timing: id 2 | task 17846 | n_gen = 353, tg = 21.23 t/s, tg_3s = 18.90 t/s 14.53.770.617 I slot print_timing: id 2 | task 17846 | prompt eval time = 732.25 ms / 467 tokens ( 1.57 ms per token, 637.76 tokens per second) 14.53.770.625 I slot print_timing: id 2 | task 17846 | eval time = 16828.90 ms / 359 tokens ( 47.01 ms per token, 21.27 tokens per second) 14.53.770.627 I slot print_timing: id 2 | task 17846 | total time = 17561.15 ms / 826 tokens 14.53.770.628 I slot print_timing: id 2 | task 17846 | graphs reused = 17377 14.53.770.629 I slot print_timing: id 2 | task 17846 | graph reallocs = 0 / 0 (same size) / (changed size) 14.53.770.743 I slot release: id 2 | task 17846 | stop processing: n_tokens = 1518, truncated = 0 14.53.814.239 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.704 14.53.814.276 I slot launch_slot_: id 2 | task 18211 | processing task, is_child = 0 14.55.326.095 I slot print_timing: id 0 | task 18014 | n_gen = 213, tg = 19.63 t/s, tg_3s = 18.58 t/s 14.55.743.907 I slot print_timing: id 3 | task 18025 | n_gen = 213, tg = 20.86 t/s, tg_3s = 18.58 t/s 14.56.200.971 I slot print_timing: id 1 | task 18150 | n_gen = 100, tg = 20.64 t/s, tg_3s = 20.84 t/s 14.58.365.155 I slot print_timing: id 0 | task 18014 | n_gen = 286, tg = 20.60 t/s, tg_3s = 24.02 t/s 14.58.699.356 I slot print_timing: id 2 | task 18211 | n_gen = 100, tg = 24.04 t/s, tg_3s = 24.29 t/s 14.58.783.127 I slot print_timing: id 3 | task 18025 | n_gen = 286, tg = 21.59 t/s, tg_3s = 24.02 t/s 14.59.241.401 I slot print_timing: id 1 | task 18150 | n_gen = 173, tg = 21.94 t/s, tg_3s = 24.01 t/s 15.01.366.336 I slot print_timing: id 0 | task 18014 | n_gen = 358, tg = 21.20 t/s, tg_3s = 23.99 t/s 15.01.700.440 I slot print_timing: id 2 | task 18211 | n_gen = 172, tg = 24.02 t/s, tg_3s = 23.99 t/s 15.01.784.215 I slot print_timing: id 3 | task 18025 | n_gen = 358, tg = 22.03 t/s, tg_3s = 23.99 t/s 15.02.244.358 I slot print_timing: id 1 | task 18150 | n_gen = 245, tg = 22.51 t/s, tg_3s = 23.98 t/s 15.04.367.857 I slot print_timing: id 0 | task 18014 | n_gen = 430, tg = 21.62 t/s, tg_3s = 23.99 t/s 15.04.702.503 I slot print_timing: id 2 | task 18211 | n_gen = 244, tg = 24.01 t/s, tg_3s = 23.98 t/s 15.04.786.482 I slot print_timing: id 3 | task 18025 | n_gen = 430, tg = 22.34 t/s, tg_3s = 23.98 t/s 15.05.283.999 I slot print_timing: id 1 | task 18150 | n_gen = 318, tg = 22.84 t/s, tg_3s = 24.02 t/s 15.07.368.153 I slot print_timing: id 0 | task 18014 | n_gen = 502, tg = 21.94 t/s, tg_3s = 24.00 t/s 15.07.702.794 I slot print_timing: id 2 | task 18211 | n_gen = 316, tg = 24.01 t/s, tg_3s = 24.00 t/s 15.07.787.036 I slot print_timing: id 3 | task 18025 | n_gen = 502, tg = 22.56 t/s, tg_3s = 24.00 t/s 15.08.286.235 I slot print_timing: id 1 | task 18150 | n_gen = 390, tg = 23.04 t/s, tg_3s = 23.98 t/s 15.08.746.198 I slot print_timing: id 1 | task 18150 | prompt eval time = 723.28 ms / 456 tokens ( 1.59 ms per token, 630.46 tokens per second) 15.08.746.205 I slot print_timing: id 1 | task 18150 | eval time = 17342.63 ms / 401 tokens ( 43.36 ms per token, 23.06 tokens per second) 15.08.746.206 I slot print_timing: id 1 | task 18150 | total time = 18065.91 ms / 857 tokens 15.08.746.206 I slot print_timing: id 1 | task 18150 | graphs reused = 17715 15.08.746.207 I slot print_timing: id 1 | task 18150 | graph reallocs = 0 / 0 (same size) / (changed size) 15.08.746.314 I slot release: id 1 | task 18150 | stop processing: n_tokens = 1531, truncated = 0 15.08.790.989 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.698 15.08.791.031 I slot launch_slot_: id 1 | task 18555 | processing task, is_child = 0 15.10.408.881 I slot print_timing: id 0 | task 18014 | n_gen = 559, tg = 21.56 t/s, tg_3s = 18.75 t/s 15.10.743.047 I slot print_timing: id 2 | task 18211 | n_gen = 373, tg = 23.02 t/s, tg_3s = 18.75 t/s 15.10.826.829 I slot print_timing: id 3 | task 18025 | n_gen = 559, tg = 22.10 t/s, tg_3s = 18.75 t/s 15.13.324.705 I slot print_timing: id 0 | task 18014 | prompt eval time = 673.70 ms / 433 tokens ( 1.56 ms per token, 642.72 tokens per second) 15.13.324.710 I slot print_timing: id 0 | task 18014 | eval time = 28796.04 ms / 629 tokens ( 45.85 ms per token, 21.81 tokens per second) 15.13.324.711 I slot print_timing: id 0 | task 18014 | total time = 29469.75 ms / 1062 tokens 15.13.324.711 I slot print_timing: id 0 | task 18014 | graphs reused = 17805 15.13.324.712 I slot print_timing: id 0 | task 18014 | graph reallocs = 0 / 0 (same size) / (changed size) 15.13.324.809 I slot release: id 0 | task 18014 | stop processing: n_tokens = 1757, truncated = 0 15.13.362.516 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.608 15.13.362.567 I slot launch_slot_: id 0 | task 18650 | processing task, is_child = 0 15.13.991.054 I slot print_timing: id 2 | task 18211 | n_gen = 437, tg = 22.46 t/s, tg_3s = 19.70 t/s 15.13.991.378 I slot print_timing: id 3 | task 18025 | n_gen = 621, tg = 21.82 t/s, tg_3s = 19.59 t/s 15.14.266.459 I slot print_timing: id 1 | task 18555 | n_gen = 100, tg = 20.92 t/s, tg_3s = 21.13 t/s 15.17.013.178 I slot print_timing: id 2 | task 18211 | n_gen = 509, tg = 22.65 t/s, tg_3s = 23.82 t/s 15.17.013.694 I slot print_timing: id 3 | task 18025 | n_gen = 693, tg = 22.01 t/s, tg_3s = 23.82 t/s 15.17.303.926 I slot print_timing: id 1 | task 18555 | n_gen = 173, tg = 22.14 t/s, tg_3s = 24.03 t/s 15.18.180.440 I slot print_timing: id 0 | task 18650 | n_gen = 100, tg = 24.03 t/s, tg_3s = 24.28 t/s 15.20.013.739 I slot print_timing: id 2 | task 18211 | n_gen = 581, tg = 22.81 t/s, tg_3s = 24.00 t/s 15.20.014.393 I slot print_timing: id 3 | task 18025 | n_gen = 765, tg = 22.19 t/s, tg_3s = 23.99 t/s 15.20.305.232 I slot print_timing: id 1 | task 18555 | n_gen = 245, tg = 22.65 t/s, tg_3s = 23.99 t/s 15.20.388.862 I slot print_timing: id 2 | task 18211 | prompt eval time = 767.68 ms / 505 tokens ( 1.52 ms per token, 657.82 tokens per second) 15.20.388.870 I slot print_timing: id 2 | task 18211 | eval time = 25806.90 ms / 590 tokens ( 43.81 ms per token, 22.82 tokens per second) 15.20.388.871 I slot print_timing: id 2 | task 18211 | total time = 26574.58 ms / 1095 tokens 15.20.388.872 I slot print_timing: id 2 | task 18211 | graphs reused = 17957 15.20.388.873 I slot print_timing: id 2 | task 18211 | graph reallocs = 0 / 0 (same size) / (changed size) 15.20.388.980 I slot release: id 2 | task 18211 | stop processing: n_tokens = 1787, truncated = 0 15.20.432.446 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.598 15.20.432.489 I slot launch_slot_: id 2 | task 18806 | processing task, is_child = 0 15.21.217.699 I slot print_timing: id 0 | task 18650 | n_gen = 157, tg = 21.80 t/s, tg_3s = 18.77 t/s 15.23.046.511 I slot print_timing: id 3 | task 18025 | n_gen = 822, tg = 21.91 t/s, tg_3s = 18.80 t/s 15.23.335.796 I slot print_timing: id 1 | task 18555 | n_gen = 302, tg = 21.81 t/s, tg_3s = 18.81 t/s 15.24.251.578 I slot print_timing: id 0 | task 18650 | n_gen = 230, tg = 22.47 t/s, tg_3s = 24.06 t/s 15.25.292.565 I slot print_timing: id 2 | task 18806 | n_gen = 100, tg = 24.05 t/s, tg_3s = 24.30 t/s 15.26.050.034 I slot print_timing: id 3 | task 18025 | n_gen = 894, tg = 22.07 t/s, tg_3s = 23.97 t/s 15.26.343.121 I slot print_timing: id 1 | task 18555 | n_gen = 374, tg = 22.19 t/s, tg_3s = 23.94 t/s 15.27.265.254 I slot print_timing: id 0 | task 18650 | n_gen = 302, tg = 22.80 t/s, tg_3s = 23.89 t/s 15.28.315.304 I slot print_timing: id 2 | task 18806 | n_gen = 172, tg = 23.95 t/s, tg_3s = 23.82 t/s 15.28.650.199 I slot print_timing: id 1 | task 18555 | prompt eval time = 743.58 ms / 485 tokens ( 1.53 ms per token, 652.25 tokens per second) 15.28.650.205 I slot print_timing: id 1 | task 18555 | eval time = 19115.58 ms / 429 tokens ( 44.66 ms per token, 22.39 tokens per second) 15.28.650.206 I slot print_timing: id 1 | task 18555 | total time = 19859.16 ms / 914 tokens 15.28.650.207 I slot print_timing: id 1 | task 18555 | graphs reused = 18134 15.28.650.207 I slot print_timing: id 1 | task 18555 | graph reallocs = 0 / 0 (same size) / (changed size) 15.28.650.317 I slot release: id 1 | task 18555 | stop processing: n_tokens = 1588, truncated = 0 15.28.694.645 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.673 15.28.694.688 I slot launch_slot_: id 1 | task 18989 | processing task, is_child = 0 15.29.342.765 I slot print_timing: id 3 | task 18025 | n_gen = 958, tg = 21.87 t/s, tg_3s = 19.44 t/s 15.30.280.748 I slot print_timing: id 0 | task 18650 | n_gen = 359, tg = 22.07 t/s, tg_3s = 18.90 t/s 15.31.329.350 I slot print_timing: id 2 | task 18806 | n_gen = 229, tg = 22.46 t/s, tg_3s = 18.91 t/s 15.32.124.823 I slot print_timing: id 3 | task 18025 | prompt eval time = 722.37 ms / 476 tokens ( 1.52 ms per token, 658.94 tokens per second) 15.32.124.827 I slot print_timing: id 3 | task 18025 | eval time = 46544.71 ms / 1024 tokens ( 45.50 ms per token, 21.98 tokens per second) 15.32.124.828 I slot print_timing: id 3 | task 18025 | total time = 47267.08 ms / 1500 tokens 15.32.124.829 I slot print_timing: id 3 | task 18025 | graphs reused = 18198 15.32.124.829 I slot print_timing: id 3 | task 18025 | graph reallocs = 0 / 0 (same size) / (changed size) 15.32.124.934 I slot release: id 3 | task 18025 | stop processing: n_tokens = 2194, truncated = 0 15.32.160.851 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.487 15.32.166.803 I slot launch_slot_: id 3 | task 19058 | processing task, is_child = 0 15.33.295.282 I slot print_timing: id 0 | task 18650 | n_gen = 416, tg = 21.58 t/s, tg_3s = 18.91 t/s 15.34.172.397 I slot print_timing: id 1 | task 18989 | n_gen = 100, tg = 20.84 t/s, tg_3s = 21.05 t/s 15.34.339.707 I slot print_timing: id 2 | task 18806 | n_gen = 286, tg = 21.65 t/s, tg_3s = 18.93 t/s 15.36.337.052 I slot print_timing: id 0 | task 18650 | n_gen = 489, tg = 21.91 t/s, tg_3s = 24.00 t/s 15.37.002.275 I slot print_timing: id 3 | task 19058 | n_gen = 100, tg = 24.06 t/s, tg_3s = 24.30 t/s 15.37.209.935 I slot print_timing: id 1 | task 18989 | n_gen = 173, tg = 22.09 t/s, tg_3s = 24.03 t/s 15.37.376.211 I slot print_timing: id 2 | task 18806 | n_gen = 359, tg = 22.10 t/s, tg_3s = 24.04 t/s 15.39.373.738 I slot print_timing: id 0 | task 18650 | n_gen = 562, tg = 22.16 t/s, tg_3s = 24.04 t/s 15.40.041.246 I slot print_timing: id 3 | task 19058 | n_gen = 173, tg = 24.04 t/s, tg_3s = 24.02 t/s 15.40.247.745 I slot print_timing: id 1 | task 18989 | n_gen = 246, tg = 22.63 t/s, tg_3s = 24.03 t/s 15.40.415.159 I slot print_timing: id 2 | task 18806 | n_gen = 432, tg = 22.40 t/s, tg_3s = 24.02 t/s 15.42.039.318 I slot print_timing: id 1 | task 18989 | prompt eval time = 727.31 ms / 459 tokens ( 1.58 ms per token, 631.10 tokens per second) 15.42.039.321 I slot print_timing: id 1 | task 18989 | eval time = 12617.32 ms / 289 tokens ( 43.81 ms per token, 22.83 tokens per second) 15.42.039.322 I slot print_timing: id 1 | task 18989 | total time = 13344.62 ms / 748 tokens 15.42.039.323 I slot print_timing: id 1 | task 18989 | graphs reused = 18417 15.42.039.324 I slot print_timing: id 1 | task 18989 | graph reallocs = 0 / 0 (same size) / (changed size) 15.42.039.429 I slot release: id 1 | task 18989 | stop processing: n_tokens = 1422, truncated = 0 15.42.083.622 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.751 15.42.083.661 I slot launch_slot_: id 1 | task 19282 | processing task, is_child = 0 15.42.769.975 I slot print_timing: id 0 | task 18650 | n_gen = 628, tg = 21.84 t/s, tg_3s = 19.43 t/s 15.43.055.739 I slot print_timing: id 3 | task 19058 | n_gen = 229, tg = 22.42 t/s, tg_3s = 18.58 t/s 15.43.433.499 I slot print_timing: id 2 | task 18806 | n_gen = 488, tg = 21.88 t/s, tg_3s = 18.55 t/s 15.45.770.000 I slot print_timing: id 0 | task 18650 | n_gen = 699, tg = 22.01 t/s, tg_3s = 23.67 t/s 15.46.063.695 I slot print_timing: id 3 | task 19058 | n_gen = 301, tg = 22.77 t/s, tg_3s = 23.94 t/s 15.46.438.165 I slot print_timing: id 2 | task 18806 | n_gen = 560, tg = 22.13 t/s, tg_3s = 23.96 t/s 15.46.979.117 I slot print_timing: id 1 | task 19282 | n_gen = 100, tg = 23.98 t/s, tg_3s = 24.22 t/s 15.47.146.059 I slot print_timing: id 0 | task 18650 | prompt eval time = 698.72 ms / 456 tokens ( 1.53 ms per token, 652.62 tokens per second) 15.47.146.067 I slot print_timing: id 0 | task 18650 | eval time = 33084.76 ms / 732 tokens ( 45.26 ms per token, 22.09 tokens per second) 15.47.146.068 I slot print_timing: id 0 | task 18650 | total time = 33783.48 ms / 1188 tokens 15.47.146.068 I slot print_timing: id 0 | task 18650 | graphs reused = 18518 15.47.146.069 I slot print_timing: id 0 | task 18650 | graph reallocs = 0 / 0 (same size) / (changed size) 15.47.146.179 I slot release: id 0 | task 18650 | stop processing: n_tokens = 1883, truncated = 0 15.47.183.337 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.567 15.47.183.371 I slot launch_slot_: id 0 | task 19389 | processing task, is_child = 0 15.49.075.429 I slot print_timing: id 3 | task 19058 | n_gen = 359, tg = 22.12 t/s, tg_3s = 19.26 t/s 15.49.451.876 I slot print_timing: id 2 | task 18806 | n_gen = 618, tg = 21.82 t/s, tg_3s = 19.25 t/s 15.49.991.187 I slot print_timing: id 1 | task 19282 | n_gen = 158, tg = 21.99 t/s, tg_3s = 19.26 t/s 15.51.988.910 I slot print_timing: id 0 | task 19389 | n_gen = 100, tg = 23.98 t/s, tg_3s = 24.23 t/s 15.52.115.716 I slot print_timing: id 3 | task 19058 | n_gen = 432, tg = 22.41 t/s, tg_3s = 24.01 t/s 15.52.489.741 I slot print_timing: id 2 | task 18806 | n_gen = 691, tg = 22.04 t/s, tg_3s = 24.03 t/s 15.53.029.673 I slot print_timing: id 1 | task 19282 | n_gen = 231, tg = 22.59 t/s, tg_3s = 24.03 t/s 15.54.991.675 I slot print_timing: id 0 | task 19389 | n_gen = 172, tg = 23.98 t/s, tg_3s = 23.98 t/s 15.55.120.088 I slot print_timing: id 3 | task 19058 | n_gen = 504, tg = 22.62 t/s, tg_3s = 23.97 t/s 15.55.497.363 I slot print_timing: id 2 | task 18806 | n_gen = 763, tg = 22.20 t/s, tg_3s = 23.94 t/s 15.56.040.930 I slot print_timing: id 1 | task 19282 | n_gen = 303, tg = 22.89 t/s, tg_3s = 23.91 t/s 15.57.999.665 I slot print_timing: id 0 | task 19389 | n_gen = 244, tg = 23.97 t/s, tg_3s = 23.94 t/s 15.58.125.702 I slot print_timing: id 3 | task 19058 | n_gen = 576, tg = 22.78 t/s, tg_3s = 23.96 t/s 15.58.501.181 I slot print_timing: id 2 | task 18806 | n_gen = 835, tg = 22.34 t/s, tg_3s = 23.97 t/s 15.59.041.049 I slot print_timing: id 1 | task 19282 | n_gen = 375, tg = 23.10 t/s, tg_3s = 24.00 t/s 16.00.042.321 I slot print_timing: id 3 | task 19058 | prompt eval time = 720.56 ms / 470 tokens ( 1.53 ms per token, 652.27 tokens per second) 16.00.042.328 I slot print_timing: id 3 | task 19058 | eval time = 27154.95 ms / 622 tokens ( 43.73 ms per token, 22.87 tokens per second) 16.00.042.329 I slot print_timing: id 3 | task 19058 | total time = 27875.50 ms / 1092 tokens 16.00.042.330 I slot print_timing: id 3 | task 19058 | graphs reused = 18808 16.00.042.331 I slot print_timing: id 3 | task 19058 | graph reallocs = 0 / 0 (same size) / (changed size) 16.00.042.429 I slot release: id 3 | task 19058 | stop processing: n_tokens = 1786, truncated = 0 16.00.078.218 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.598 16.00.078.253 I slot launch_slot_: id 3 | task 19685 | processing task, is_child = 0 16.01.018.345 I slot print_timing: id 0 | task 19389 | n_gen = 302, tg = 22.88 t/s, tg_3s = 19.21 t/s 16.01.523.825 I slot print_timing: id 2 | task 18806 | n_gen = 893, tg = 22.11 t/s, tg_3s = 19.19 t/s 16.02.068.626 I slot print_timing: id 1 | task 19282 | n_gen = 433, tg = 22.48 t/s, tg_3s = 19.16 t/s 16.04.038.263 I slot print_timing: id 0 | task 19389 | n_gen = 374, tg = 23.06 t/s, tg_3s = 23.84 t/s 16.04.542.013 I slot print_timing: id 2 | task 18806 | n_gen = 965, tg = 22.23 t/s, tg_3s = 23.86 t/s 16.04.921.670 I slot print_timing: id 3 | task 19685 | n_gen = 100, tg = 23.86 t/s, tg_3s = 24.10 t/s 16.05.088.623 I slot print_timing: id 1 | task 19282 | n_gen = 505, tg = 22.66 t/s, tg_3s = 23.84 t/s 16.07.012.614 I slot print_timing: id 2 | task 18806 | prompt eval time = 744.06 ms / 485 tokens ( 1.53 ms per token, 651.83 tokens per second) 16.07.012.620 I slot print_timing: id 2 | task 18806 | eval time = 45836.06 ms / 1024 tokens ( 44.81 ms per token, 22.32 tokens per second) 16.07.012.621 I slot print_timing: id 2 | task 18806 | total time = 46580.12 ms / 1509 tokens 16.07.012.622 I slot print_timing: id 2 | task 18806 | graphs reused = 18956 16.07.012.623 I slot print_timing: id 2 | task 18806 | graph reallocs = 0 / 0 (same size) / (changed size) 16.07.012.748 I slot release: id 2 | task 18806 | stop processing: n_tokens = 2201, truncated = 0 16.07.055.672 I slot print_timing: id 0 | task 19389 | n_gen = 446, tg = 23.18 t/s, tg_3s = 23.86 t/s 16.07.056.786 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.485 16.07.063.209 I slot launch_slot_: id 2 | task 19838 | processing task, is_child = 0 16.07.959.067 I slot print_timing: id 3 | task 19685 | n_gen = 157, tg = 21.71 t/s, tg_3s = 18.77 t/s 16.08.120.888 I slot print_timing: id 1 | task 19282 | n_gen = 562, tg = 22.20 t/s, tg_3s = 18.80 t/s 16.10.075.521 I slot print_timing: id 0 | task 19389 | n_gen = 503, tg = 22.60 t/s, tg_3s = 18.88 t/s 16.10.994.691 I slot print_timing: id 3 | task 19685 | n_gen = 230, tg = 22.40 t/s, tg_3s = 24.05 t/s 16.11.160.477 I slot print_timing: id 1 | task 19282 | n_gen = 635, tg = 22.39 t/s, tg_3s = 24.02 t/s 16.11.909.421 I slot print_timing: id 2 | task 19838 | n_gen = 100, tg = 24.06 t/s, tg_3s = 24.30 t/s 16.12.868.955 I slot print_timing: id 0 | task 19389 | prompt eval time = 677.60 ms / 440 tokens ( 1.54 ms per token, 649.35 tokens per second) 16.12.868.962 I slot print_timing: id 0 | task 19389 | eval time = 25007.98 ms / 570 tokens ( 43.95 ms per token, 22.75 tokens per second) 16.12.868.963 I slot print_timing: id 0 | task 19389 | total time = 25685.57 ms / 1010 tokens 16.12.868.964 I slot print_timing: id 0 | task 19389 | graphs reused = 19076 16.12.868.965 I slot print_timing: id 0 | task 19389 | graph reallocs = 0 / 0 (same size) / (changed size) 16.12.869.075 I slot release: id 0 | task 19389 | stop processing: n_tokens = 1705, truncated = 0 16.12.906.504 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.626 16.12.906.539 I slot launch_slot_: id 0 | task 19964 | processing task, is_child = 0 16.14.028.725 I slot print_timing: id 3 | task 19685 | n_gen = 288, tg = 21.65 t/s, tg_3s = 19.12 t/s 16.14.194.883 I slot print_timing: id 1 | task 19282 | n_gen = 693, tg = 22.08 t/s, tg_3s = 19.11 t/s 16.14.944.826 I slot print_timing: id 2 | task 19838 | n_gen = 158, tg = 21.96 t/s, tg_3s = 19.11 t/s 16.17.069.761 I slot print_timing: id 3 | task 19685 | n_gen = 361, tg = 22.09 t/s, tg_3s = 24.00 t/s 16.17.235.365 I slot print_timing: id 1 | task 19282 | n_gen = 766, tg = 22.25 t/s, tg_3s = 24.01 t/s 16.17.735.352 I slot print_timing: id 0 | task 19964 | n_gen = 100, tg = 24.04 t/s, tg_3s = 24.28 t/s 16.17.945.124 I slot print_timing: id 2 | task 19838 | n_gen = 230, tg = 22.56 t/s, tg_3s = 24.00 t/s 16.20.075.715 I slot print_timing: id 3 | task 19685 | n_gen = 433, tg = 22.38 t/s, tg_3s = 23.95 t/s 16.20.240.353 I slot print_timing: id 1 | task 19282 | n_gen = 838, tg = 22.39 t/s, tg_3s = 23.96 t/s 16.20.366.624 I slot print_timing: id 3 | task 19685 | prompt eval time = 693.93 ms / 444 tokens ( 1.56 ms per token, 639.83 tokens per second) 16.20.366.629 I slot print_timing: id 3 | task 19685 | eval time = 19594.43 ms / 440 tokens ( 44.63 ms per token, 22.40 tokens per second) 16.20.366.630 I slot print_timing: id 3 | task 19685 | total time = 20288.36 ms / 884 tokens 16.20.366.631 I slot print_timing: id 3 | task 19685 | graphs reused = 19238 16.20.366.631 I slot print_timing: id 3 | task 19685 | graph reallocs = 0 / 0 (same size) / (changed size) 16.20.366.741 I slot release: id 3 | task 19685 | stop processing: n_tokens = 1578, truncated = 0 16.20.402.784 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.677 16.20.402.830 I slot launch_slot_: id 3 | task 20130 | processing task, is_child = 0 16.21.025.113 I slot print_timing: id 0 | task 19964 | n_gen = 165, tg = 22.14 t/s, tg_3s = 19.76 t/s 16.21.025.678 I slot print_timing: id 2 | task 19838 | n_gen = 290, tg = 21.84 t/s, tg_3s = 19.48 t/s 16.23.256.897 I slot print_timing: id 1 | task 19282 | n_gen = 896, tg = 22.15 t/s, tg_3s = 19.23 t/s 16.24.050.671 I slot print_timing: id 0 | task 19964 | n_gen = 237, tg = 22.62 t/s, tg_3s = 23.80 t/s 16.24.051.913 I slot print_timing: id 2 | task 19838 | n_gen = 362, tg = 22.21 t/s, tg_3s = 23.79 t/s 16.25.227.066 I slot print_timing: id 3 | task 20130 | n_gen = 100, tg = 23.98 t/s, tg_3s = 24.22 t/s 16.26.271.761 I slot print_timing: id 1 | task 19282 | n_gen = 968, tg = 22.27 t/s, tg_3s = 23.88 t/s 16.27.066.588 I slot print_timing: id 0 | task 19964 | n_gen = 309, tg = 22.90 t/s, tg_3s = 23.87 t/s 16.27.067.806 I slot print_timing: id 2 | task 19838 | n_gen = 434, tg = 22.47 t/s, tg_3s = 23.87 t/s 16.28.240.727 I slot print_timing: id 3 | task 20130 | n_gen = 172, tg = 23.94 t/s, tg_3s = 23.89 t/s 16.28.618.612 I slot print_timing: id 1 | task 19282 | prompt eval time = 766.29 ms / 500 tokens ( 1.53 ms per token, 652.49 tokens per second) 16.28.618.617 I slot print_timing: id 1 | task 19282 | eval time = 45768.64 ms / 1024 tokens ( 44.74 ms per token, 22.35 tokens per second) 16.28.618.618 I slot print_timing: id 1 | task 19282 | total time = 46534.94 ms / 1524 tokens 16.28.618.619 I slot print_timing: id 1 | task 19282 | graphs reused = 19416 16.28.618.619 I slot print_timing: id 1 | task 19282 | graph reallocs = 0 / 0 (same size) / (changed size) 16.28.618.741 I slot release: id 1 | task 19282 | stop processing: n_tokens = 2198, truncated = 0 16.28.663.102 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.486 16.28.669.606 I slot launch_slot_: id 1 | task 20314 | processing task, is_child = 0 16.30.103.631 I slot print_timing: id 0 | task 19964 | n_gen = 365, tg = 22.08 t/s, tg_3s = 18.44 t/s 16.30.104.750 I slot print_timing: id 2 | task 19838 | n_gen = 490, tg = 21.92 t/s, tg_3s = 18.44 t/s 16.31.270.116 I slot print_timing: id 3 | task 20130 | n_gen = 228, tg = 22.32 t/s, tg_3s = 18.49 t/s 16.33.140.184 I slot print_timing: id 0 | task 19964 | n_gen = 438, tg = 22.38 t/s, tg_3s = 24.04 t/s 16.33.141.253 I slot print_timing: id 2 | task 19838 | n_gen = 563, tg = 22.17 t/s, tg_3s = 24.04 t/s 16.33.556.716 I slot print_timing: id 1 | task 20314 | n_gen = 100, tg = 24.02 t/s, tg_3s = 24.26 t/s 16.34.307.748 I slot print_timing: id 3 | task 20130 | n_gen = 301, tg = 22.71 t/s, tg_3s = 24.03 t/s 16.36.142.322 I slot print_timing: id 0 | task 19964 | n_gen = 510, tg = 22.60 t/s, tg_3s = 23.98 t/s 16.36.143.312 I slot print_timing: id 2 | task 19838 | n_gen = 635, tg = 22.36 t/s, tg_3s = 23.98 t/s 16.36.561.329 I slot print_timing: id 1 | task 20314 | n_gen = 172, tg = 23.99 t/s, tg_3s = 23.96 t/s 16.37.311.841 I slot print_timing: id 3 | task 20130 | n_gen = 373, tg = 22.94 t/s, tg_3s = 23.97 t/s 16.39.150.715 I slot print_timing: id 0 | task 19964 | n_gen = 582, tg = 22.75 t/s, tg_3s = 23.93 t/s 16.39.151.924 I slot print_timing: id 2 | task 19838 | n_gen = 707, tg = 22.51 t/s, tg_3s = 23.93 t/s 16.39.569.981 I slot print_timing: id 1 | task 20314 | n_gen = 244, tg = 23.98 t/s, tg_3s = 23.93 t/s 16.40.322.699 I slot print_timing: id 3 | task 20130 | n_gen = 445, tg = 23.10 t/s, tg_3s = 23.91 t/s 16.42.154.626 I slot print_timing: id 0 | task 19964 | n_gen = 654, tg = 22.88 t/s, tg_3s = 23.97 t/s 16.42.155.753 I slot print_timing: id 2 | task 19838 | n_gen = 779, tg = 22.64 t/s, tg_3s = 23.97 t/s 16.42.570.863 I slot print_timing: id 1 | task 20314 | n_gen = 316, tg = 23.98 t/s, tg_3s = 23.99 t/s 16.43.361.346 I slot print_timing: id 3 | task 20130 | n_gen = 518, tg = 23.22 t/s, tg_3s = 24.02 t/s 16.45.190.653 I slot print_timing: id 0 | task 19964 | n_gen = 727, tg = 22.99 t/s, tg_3s = 24.04 t/s 16.45.191.936 I slot print_timing: id 2 | task 19838 | n_gen = 852, tg = 22.76 t/s, tg_3s = 24.04 t/s 16.45.276.299 I slot print_timing: id 3 | task 20130 | prompt eval time = 695.53 ms / 449 tokens ( 1.55 ms per token, 645.55 tokens per second) 16.45.276.307 I slot print_timing: id 3 | task 20130 | eval time = 24177.93 ms / 564 tokens ( 42.94 ms per token, 23.29 tokens per second) 16.45.276.308 I slot print_timing: id 3 | task 20130 | total time = 24873.46 ms / 1013 tokens 16.45.276.309 I slot print_timing: id 3 | task 20130 | graphs reused = 19794 16.45.276.309 I slot print_timing: id 3 | task 20130 | graph reallocs = 0 / 0 (same size) / (changed size) 16.45.276.427 I slot release: id 3 | task 20130 | stop processing: n_tokens = 1707, truncated = 0 16.45.312.397 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.626 16.45.312.449 I slot launch_slot_: id 3 | task 20698 | processing task, is_child = 0 16.45.969.379 I slot print_timing: id 1 | task 20314 | n_gen = 383, tg = 23.10 t/s, tg_3s = 19.71 t/s 16.46.124.773 I slot print_timing: id 0 | task 19964 | prompt eval time = 710.78 ms / 473 tokens ( 1.50 ms per token, 665.47 tokens per second) 16.46.124.778 I slot print_timing: id 0 | task 19964 | eval time = 32507.45 ms / 734 tokens ( 44.35 ms per token, 22.55 tokens per second) 16.46.124.779 I slot print_timing: id 0 | task 19964 | total time = 33218.23 ms / 1207 tokens 16.46.124.779 I slot print_timing: id 0 | task 19964 | graphs reused = 19795 16.46.124.780 I slot print_timing: id 0 | task 19964 | graph reallocs = 0 / 0 (same size) / (changed size) 16.46.124.839 I slot release: id 0 | task 19964 | stop processing: n_tokens = 1902, truncated = 0 16.46.159.989 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.562 16.46.160.021 I slot launch_slot_: id 0 | task 20704 | processing task, is_child = 0 16.48.207.155 I slot print_timing: id 2 | task 19838 | n_gen = 894, tg = 22.10 t/s, tg_3s = 13.93 t/s 16.49.002.110 I slot print_timing: id 1 | task 20314 | n_gen = 440, tg = 22.44 t/s, tg_3s = 18.79 t/s 16.50.802.765 I slot print_timing: id 3 | task 20698 | n_gen = 100, tg = 20.80 t/s, tg_3s = 21.01 t/s 16.51.009.735 I slot print_timing: id 0 | task 20704 | n_gen = 100, tg = 23.92 t/s, tg_3s = 24.16 t/s 16.51.219.554 I slot print_timing: id 2 | task 19838 | n_gen = 966, tg = 22.22 t/s, tg_3s = 23.90 t/s 16.52.014.085 I slot print_timing: id 1 | task 20314 | n_gen = 512, tg = 22.63 t/s, tg_3s = 23.90 t/s 16.53.645.613 I slot print_timing: id 2 | task 19838 | prompt eval time = 731.74 ms / 467 tokens ( 1.57 ms per token, 638.20 tokens per second) 16.53.645.620 I slot print_timing: id 2 | task 19838 | eval time = 45850.65 ms / 1024 tokens ( 44.82 ms per token, 22.31 tokens per second) 16.53.645.621 I slot print_timing: id 2 | task 19838 | total time = 46582.39 ms / 1491 tokens 16.53.645.622 I slot print_timing: id 2 | task 19838 | graphs reused = 19956 16.53.645.623 I slot print_timing: id 2 | task 19838 | graph reallocs = 0 / 0 (same size) / (changed size) 16.53.645.731 I slot release: id 2 | task 19838 | stop processing: n_tokens = 2183, truncated = 0 16.53.689.008 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.489 16.53.695.105 I slot launch_slot_: id 2 | task 20870 | processing task, is_child = 0 16.54.347.297 I slot print_timing: id 0 | task 20704 | n_gen = 165, tg = 21.93 t/s, tg_3s = 19.48 t/s 16.54.347.838 I slot print_timing: id 3 | task 20698 | n_gen = 170, tg = 20.35 t/s, tg_3s = 19.75 t/s 16.55.019.465 I slot print_timing: id 1 | task 20314 | n_gen = 568, tg = 22.16 t/s, tg_3s = 18.63 t/s 16.57.351.916 I slot print_timing: id 0 | task 20704 | n_gen = 236, tg = 22.42 t/s, tg_3s = 23.63 t/s 16.57.353.520 I slot print_timing: id 3 | task 20698 | n_gen = 241, tg = 21.22 t/s, tg_3s = 23.62 t/s 16.58.060.388 I slot print_timing: id 1 | task 20314 | n_gen = 641, tg = 22.36 t/s, tg_3s = 24.01 t/s 16.58.560.311 I slot print_timing: id 2 | task 20870 | n_gen = 100, tg = 23.95 t/s, tg_3s = 24.19 t/s 17.00.390.189 I slot print_timing: id 0 | task 20704 | n_gen = 309, tg = 22.78 t/s, tg_3s = 24.03 t/s 17.00.392.097 I slot print_timing: id 3 | task 20698 | n_gen = 314, tg = 21.81 t/s, tg_3s = 24.02 t/s 17.01.100.197 I slot print_timing: id 1 | task 20314 | n_gen = 714, tg = 22.52 t/s, tg_3s = 24.01 t/s 17.01.600.961 I slot print_timing: id 2 | task 20870 | n_gen = 173, tg = 23.97 t/s, tg_3s = 24.01 t/s 17.03.391.364 I slot print_timing: id 0 | task 20704 | n_gen = 381, tg = 23.00 t/s, tg_3s = 23.99 t/s 17.03.393.010 I slot print_timing: id 3 | task 20698 | n_gen = 386, tg = 22.19 t/s, tg_3s = 23.99 t/s 17.04.141.599 I slot print_timing: id 1 | task 20314 | n_gen = 787, tg = 22.65 t/s, tg_3s = 24.00 t/s 17.04.601.972 I slot print_timing: id 2 | task 20870 | n_gen = 245, tg = 23.98 t/s, tg_3s = 23.99 t/s 17.04.851.349 I slot print_timing: id 1 | task 20314 | prompt eval time = 765.15 ms / 486 tokens ( 1.57 ms per token, 635.17 tokens per second) 17.04.851.353 I slot print_timing: id 1 | task 20314 | eval time = 35416.58 ms / 804 tokens ( 44.11 ms per token, 22.67 tokens per second) 17.04.851.354 I slot print_timing: id 1 | task 20314 | total time = 36181.73 ms / 1290 tokens 17.04.851.355 I slot print_timing: id 1 | task 20314 | graphs reused = 20204 17.04.851.356 I slot print_timing: id 1 | task 20314 | graph reallocs = 0 / 0 (same size) / (changed size) 17.04.851.484 I slot release: id 1 | task 20314 | stop processing: n_tokens = 1964, truncated = 0 17.04.895.973 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.544 17.04.896.015 I slot launch_slot_: id 1 | task 21124 | processing task, is_child = 0 17.06.421.220 I slot print_timing: id 0 | task 20704 | n_gen = 438, tg = 22.35 t/s, tg_3s = 18.81 t/s 17.06.422.983 I slot print_timing: id 3 | task 20698 | n_gen = 443, tg = 21.69 t/s, tg_3s = 18.81 t/s 17.07.630.119 I slot print_timing: id 2 | task 20870 | n_gen = 302, tg = 22.80 t/s, tg_3s = 18.82 t/s 17.09.421.315 I slot print_timing: id 0 | task 20704 | n_gen = 510, tg = 22.57 t/s, tg_3s = 24.00 t/s 17.09.464.541 I slot print_timing: id 3 | task 20698 | n_gen = 516, tg = 21.99 t/s, tg_3s = 24.00 t/s 17.09.755.464 I slot print_timing: id 1 | task 21124 | n_gen = 100, tg = 24.00 t/s, tg_3s = 24.24 t/s 17.10.671.208 I slot print_timing: id 2 | task 20870 | n_gen = 375, tg = 23.02 t/s, tg_3s = 24.00 t/s 17.12.459.094 I slot print_timing: id 0 | task 20704 | n_gen = 583, tg = 22.74 t/s, tg_3s = 24.03 t/s 17.12.502.640 I slot print_timing: id 3 | task 20698 | n_gen = 589, tg = 22.22 t/s, tg_3s = 24.03 t/s 17.12.792.848 I slot print_timing: id 1 | task 21124 | n_gen = 173, tg = 24.01 t/s, tg_3s = 24.03 t/s 17.13.126.460 I slot print_timing: id 0 | task 20704 | prompt eval time = 710.44 ms / 471 tokens ( 1.51 ms per token, 662.97 tokens per second) 17.13.126.467 I slot print_timing: id 0 | task 20704 | eval time = 26255.99 ms / 599 tokens ( 43.91 ms per token, 22.78 tokens per second) 17.13.126.468 I slot print_timing: id 0 | task 20704 | total time = 26966.43 ms / 1070 tokens 17.13.126.469 I slot print_timing: id 0 | task 20704 | graphs reused = 20383 17.13.126.470 I slot print_timing: id 0 | task 20704 | graph reallocs = 0 / 0 (same size) / (changed size) 17.13.126.585 I slot release: id 0 | task 20704 | stop processing: n_tokens = 1765, truncated = 0 17.13.164.451 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.605 17.13.164.490 I slot launch_slot_: id 0 | task 21308 | processing task, is_child = 0 17.13.772.990 I slot print_timing: id 2 | task 20870 | n_gen = 436, tg = 22.49 t/s, tg_3s = 19.67 t/s 17.15.541.280 I slot print_timing: id 3 | task 20698 | n_gen = 648, tg = 21.93 t/s, tg_3s = 19.42 t/s 17.15.830.268 I slot print_timing: id 1 | task 21124 | n_gen = 232, tg = 22.65 t/s, tg_3s = 19.42 t/s 17.16.788.882 I slot print_timing: id 2 | task 20870 | n_gen = 508, tg = 22.67 t/s, tg_3s = 23.87 t/s 17.17.954.056 I slot print_timing: id 0 | task 21308 | n_gen = 100, tg = 24.08 t/s, tg_3s = 24.32 t/s 17.18.580.077 I slot print_timing: id 3 | task 20698 | n_gen = 721, tg = 22.13 t/s, tg_3s = 24.02 t/s 17.18.871.273 I slot print_timing: id 1 | task 21124 | n_gen = 305, tg = 22.96 t/s, tg_3s = 24.01 t/s 17.19.828.612 I slot print_timing: id 2 | task 20870 | n_gen = 581, tg = 22.83 t/s, tg_3s = 24.02 t/s 17.20.954.290 I slot print_timing: id 0 | task 21308 | n_gen = 172, tg = 24.05 t/s, tg_3s = 24.00 t/s 17.21.580.584 I slot print_timing: id 3 | task 20698 | n_gen = 793, tg = 22.29 t/s, tg_3s = 24.00 t/s 17.21.746.404 I slot print_timing: id 1 | task 21124 | prompt eval time = 733.66 ms / 469 tokens ( 1.56 ms per token, 639.26 tokens per second) 17.21.746.407 I slot print_timing: id 1 | task 21124 | eval time = 16116.72 ms / 374 tokens ( 43.21 ms per token, 23.14 tokens per second) 17.21.746.408 I slot print_timing: id 1 | task 21124 | total time = 16850.38 ms / 843 tokens 17.21.746.409 I slot print_timing: id 1 | task 21124 | graphs reused = 20572 17.21.746.410 I slot print_timing: id 1 | task 21124 | graph reallocs = 0 / 0 (same size) / (changed size) 17.21.746.509 I slot release: id 1 | task 21124 | stop processing: n_tokens = 1517, truncated = 0 17.21.790.884 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.704 17.21.790.926 I slot launch_slot_: id 1 | task 21502 | processing task, is_child = 0 17.22.868.335 I slot print_timing: id 2 | task 20870 | n_gen = 637, tg = 22.36 t/s, tg_3s = 18.42 t/s 17.23.991.632 I slot print_timing: id 0 | task 21308 | n_gen = 228, tg = 22.37 t/s, tg_3s = 18.44 t/s 17.24.618.153 I slot print_timing: id 3 | task 20698 | n_gen = 849, tg = 21.98 t/s, tg_3s = 18.44 t/s 17.25.869.173 I slot print_timing: id 2 | task 20870 | n_gen = 709, tg = 22.52 t/s, tg_3s = 23.99 t/s 17.26.742.279 I slot print_timing: id 1 | task 21502 | n_gen = 100, tg = 24.03 t/s, tg_3s = 24.27 t/s 17.27.033.408 I slot print_timing: id 0 | task 21308 | n_gen = 301, tg = 22.74 t/s, tg_3s = 24.00 t/s 17.27.620.740 I slot print_timing: id 3 | task 20698 | n_gen = 921, tg = 22.13 t/s, tg_3s = 23.98 t/s 17.28.747.373 I slot print_timing: id 2 | task 20870 | prompt eval time = 731.69 ms / 466 tokens ( 1.57 ms per token, 636.89 tokens per second) 17.28.747.380 I slot print_timing: id 2 | task 20870 | eval time = 34320.57 ms / 778 tokens ( 44.17 ms per token, 22.64 tokens per second) 17.28.747.382 I slot print_timing: id 2 | task 20870 | total time = 35052.26 ms / 1244 tokens 17.28.747.383 I slot print_timing: id 2 | task 20870 | graphs reused = 20717 17.28.747.384 I slot print_timing: id 2 | task 20870 | graph reallocs = 0 / 0 (same size) / (changed size) 17.28.747.485 I slot release: id 2 | task 20870 | stop processing: n_tokens = 1936, truncated = 0 17.28.790.968 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.552 17.28.791.006 I slot launch_slot_: id 2 | task 21654 | processing task, is_child = 0 17.29.777.677 I slot print_timing: id 1 | task 21502 | n_gen = 158, tg = 21.94 t/s, tg_3s = 19.11 t/s 17.30.034.383 I slot print_timing: id 0 | task 21308 | n_gen = 358, tg = 22.05 t/s, tg_3s = 18.99 t/s 17.30.622.698 I slot print_timing: id 3 | task 20698 | n_gen = 978, tg = 21.92 t/s, tg_3s = 18.99 t/s 17.32.545.049 I slot print_timing: id 3 | task 20698 | prompt eval time = 729.83 ms / 480 tokens ( 1.52 ms per token, 657.68 tokens per second) 17.32.545.056 I slot print_timing: id 3 | task 20698 | eval time = 46502.76 ms / 1024 tokens ( 45.46 ms per token, 22.00 tokens per second) 17.32.545.057 I slot print_timing: id 3 | task 20698 | total time = 47232.59 ms / 1504 tokens 17.32.545.057 I slot print_timing: id 3 | task 20698 | graphs reused = 20789 17.32.545.058 I slot print_timing: id 3 | task 20698 | graph reallocs = 0 / 0 (same size) / (changed size) 17.32.545.159 I slot release: id 3 | task 20698 | stop processing: n_tokens = 2198, truncated = 0 17.32.580.296 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.486 17.32.586.431 I slot launch_slot_: id 3 | task 21731 | processing task, is_child = 0 17.33.208.068 I slot print_timing: id 0 | task 21308 | n_gen = 420, tg = 21.64 t/s, tg_3s = 19.54 t/s 17.33.208.383 I slot print_timing: id 1 | task 21502 | n_gen = 226, tg = 21.25 t/s, tg_3s = 19.82 t/s 17.34.236.573 I slot print_timing: id 2 | task 21654 | n_gen = 100, tg = 20.86 t/s, tg_3s = 21.07 t/s 17.36.235.660 I slot print_timing: id 0 | task 21308 | n_gen = 492, tg = 21.93 t/s, tg_3s = 23.78 t/s 17.36.236.353 I slot print_timing: id 1 | task 21502 | n_gen = 298, tg = 21.82 t/s, tg_3s = 23.78 t/s 17.37.278.093 I slot print_timing: id 2 | task 21654 | n_gen = 173, tg = 22.09 t/s, tg_3s = 24.00 t/s 17.37.403.905 I slot print_timing: id 3 | task 21731 | n_gen = 100, tg = 24.01 t/s, tg_3s = 24.25 t/s 17.39.276.196 I slot print_timing: id 0 | task 21308 | n_gen = 565, tg = 22.18 t/s, tg_3s = 24.01 t/s 17.39.276.743 I slot print_timing: id 1 | task 21502 | n_gen = 371, tg = 22.22 t/s, tg_3s = 24.01 t/s 17.40.317.204 I slot print_timing: id 2 | task 21654 | n_gen = 246, tg = 22.63 t/s, tg_3s = 24.02 t/s 17.40.442.440 I slot print_timing: id 3 | task 21731 | n_gen = 173, tg = 24.02 t/s, tg_3s = 24.02 t/s 17.42.312.194 I slot print_timing: id 0 | task 21308 | prompt eval time = 678.17 ms / 442 tokens ( 1.53 ms per token, 651.76 tokens per second) 17.42.312.200 I slot print_timing: id 0 | task 21308 | eval time = 28469.53 ms / 638 tokens ( 44.69 ms per token, 22.37 tokens per second) 17.42.312.201 I slot print_timing: id 0 | task 21308 | total time = 29147.70 ms / 1080 tokens 17.42.312.202 I slot print_timing: id 0 | task 21308 | graphs reused = 21005 17.42.312.203 I slot print_timing: id 0 | task 21308 | graph reallocs = 0 / 0 (same size) / (changed size) 17.42.312.302 I slot release: id 0 | task 21308 | stop processing: n_tokens = 1775, truncated = 0 17.42.312.779 I slot print_timing: id 1 | task 21502 | n_gen = 444, tg = 22.50 t/s, tg_3s = 24.04 t/s 17.42.349.388 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.602 17.42.349.423 I slot launch_slot_: id 0 | task 21952 | processing task, is_child = 0 17.43.327.210 I slot print_timing: id 2 | task 21654 | n_gen = 304, tg = 21.90 t/s, tg_3s = 19.27 t/s 17.43.453.292 I slot print_timing: id 3 | task 21731 | n_gen = 231, tg = 22.61 t/s, tg_3s = 19.26 t/s 17.45.079.331 I slot print_timing: id 2 | task 21654 | prompt eval time = 699.89 ms / 437 tokens ( 1.60 ms per token, 624.38 tokens per second) 17.45.079.339 I slot print_timing: id 2 | task 21654 | eval time = 15588.42 ms / 346 tokens ( 45.18 ms per token, 22.13 tokens per second) 17.45.079.340 I slot print_timing: id 2 | task 21654 | total time = 16288.32 ms / 783 tokens 17.45.079.341 I slot print_timing: id 2 | task 21654 | graphs reused = 21054 17.45.079.342 I slot print_timing: id 2 | task 21654 | graph reallocs = 0 / 0 (same size) / (changed size) 17.45.079.448 I slot release: id 2 | task 21654 | stop processing: n_tokens = 1475, truncated = 0 17.45.123.435 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.724 17.45.123.492 I slot launch_slot_: id 2 | task 22005 | processing task, is_child = 0 17.45.774.262 I slot print_timing: id 1 | task 21502 | n_gen = 498, tg = 21.47 t/s, tg_3s = 15.60 t/s 17.46.477.559 I slot print_timing: id 3 | task 21731 | n_gen = 288, tg = 21.75 t/s, tg_3s = 18.85 t/s 17.47.806.367 I slot print_timing: id 0 | task 21952 | n_gen = 100, tg = 20.72 t/s, tg_3s = 20.93 t/s 17.48.806.558 I slot print_timing: id 1 | task 21502 | n_gen = 570, tg = 21.73 t/s, tg_3s = 23.74 t/s 17.49.516.313 I slot print_timing: id 3 | task 21731 | n_gen = 361, tg = 22.17 t/s, tg_3s = 24.02 t/s 17.49.974.991 I slot print_timing: id 2 | task 22005 | n_gen = 100, tg = 24.02 t/s, tg_3s = 24.26 t/s 17.50.810.781 I slot print_timing: id 0 | task 21952 | n_gen = 172, tg = 21.97 t/s, tg_3s = 23.96 t/s 17.51.816.657 I slot print_timing: id 1 | task 21502 | n_gen = 642, tg = 21.96 t/s, tg_3s = 23.92 t/s 17.52.525.246 I slot print_timing: id 3 | task 21731 | n_gen = 433, tg = 22.45 t/s, tg_3s = 23.93 t/s 17.52.982.779 I slot print_timing: id 2 | task 22005 | n_gen = 172, tg = 23.99 t/s, tg_3s = 23.94 t/s 17.53.814.926 I slot print_timing: id 0 | task 21952 | n_gen = 244, tg = 22.53 t/s, tg_3s = 23.97 t/s 17.54.856.403 I slot print_timing: id 1 | task 21502 | n_gen = 715, tg = 22.15 t/s, tg_3s = 24.02 t/s 17.55.564.932 I slot print_timing: id 3 | task 21731 | n_gen = 506, tg = 22.66 t/s, tg_3s = 24.02 t/s 17.56.022.650 I slot print_timing: id 2 | task 22005 | n_gen = 245, tg = 23.99 t/s, tg_3s = 24.01 t/s 17.56.854.826 I slot print_timing: id 0 | task 21952 | n_gen = 317, tg = 22.86 t/s, tg_3s = 24.01 t/s 17.57.773.473 I slot print_timing: id 0 | task 21952 | prompt eval time = 679.67 ms / 442 tokens ( 1.54 ms per token, 650.31 tokens per second) 17.57.773.479 I slot print_timing: id 0 | task 21952 | eval time = 14744.37 ms / 339 tokens ( 43.62 ms per token, 22.92 tokens per second) 17.57.773.480 I slot print_timing: id 0 | task 21952 | total time = 15424.04 ms / 781 tokens 17.57.773.481 I slot print_timing: id 0 | task 21952 | graphs reused = 21338 17.57.773.482 I slot print_timing: id 0 | task 21952 | graph reallocs = 0 / 0 (same size) / (changed size) 17.57.773.587 I slot release: id 0 | task 21952 | stop processing: n_tokens = 1476, truncated = 0 17.57.811.407 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.724 17.57.811.446 I slot launch_slot_: id 0 | task 22295 | processing task, is_child = 0 17.58.449.433 I slot print_timing: id 1 | task 21502 | n_gen = 787, tg = 21.94 t/s, tg_3s = 20.04 t/s 17.58.603.886 I slot print_timing: id 3 | task 21731 | n_gen = 564, tg = 22.23 t/s, tg_3s = 19.09 t/s 17.59.050.930 I slot print_timing: id 2 | task 22005 | n_gen = 303, tg = 22.88 t/s, tg_3s = 19.15 t/s 18.01.484.402 I slot print_timing: id 1 | task 21502 | n_gen = 859, tg = 22.08 t/s, tg_3s = 23.72 t/s 18.01.610.659 I slot print_timing: id 3 | task 21731 | n_gen = 636, tg = 22.41 t/s, tg_3s = 23.95 t/s 18.02.069.180 I slot print_timing: id 2 | task 22005 | n_gen = 375, tg = 23.06 t/s, tg_3s = 23.85 t/s 18.02.652.597 I slot print_timing: id 0 | task 22295 | n_gen = 100, tg = 23.96 t/s, tg_3s = 24.20 t/s 18.04.494.991 I slot print_timing: id 1 | task 21502 | n_gen = 931, tg = 22.21 t/s, tg_3s = 23.92 t/s 18.04.620.994 I slot print_timing: id 3 | task 21731 | n_gen = 708, tg = 22.56 t/s, tg_3s = 23.92 t/s 18.05.081.197 I slot print_timing: id 2 | task 22005 | n_gen = 447, tg = 23.20 t/s, tg_3s = 23.90 t/s 18.05.662.948 I slot print_timing: id 0 | task 22295 | n_gen = 172, tg = 23.94 t/s, tg_3s = 23.92 t/s 18.07.504.134 I slot print_timing: id 1 | task 21502 | n_gen = 1003, tg = 22.33 t/s, tg_3s = 23.93 t/s 18.07.631.182 I slot print_timing: id 3 | task 21731 | n_gen = 780, tg = 22.68 t/s, tg_3s = 23.92 t/s 18.08.090.883 I slot print_timing: id 2 | task 22005 | n_gen = 519, tg = 23.29 t/s, tg_3s = 23.92 t/s 18.08.382.006 I slot print_timing: id 1 | task 21502 | prompt eval time = 831.24 ms / 517 tokens ( 1.61 ms per token, 621.96 tokens per second) 18.08.382.016 I slot print_timing: id 1 | task 21502 | eval time = 45759.83 ms / 1024 tokens ( 44.73 ms per token, 22.36 tokens per second) 18.08.382.016 I slot print_timing: id 1 | task 21502 | total time = 46591.07 ms / 1541 tokens 18.08.382.017 I slot print_timing: id 1 | task 21502 | graphs reused = 21573 18.08.382.018 I slot print_timing: id 1 | task 21502 | graph reallocs = 0 / 0 (same size) / (changed size) 18.08.382.130 I slot release: id 1 | task 21502 | stop processing: n_tokens = 2215, truncated = 0 18.08.425.918 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.482 18.08.432.560 I slot launch_slot_: id 1 | task 22535 | processing task, is_child = 0 18.09.079.793 I slot print_timing: id 0 | task 22295 | n_gen = 239, tg = 22.54 t/s, tg_3s = 19.61 t/s 18.10.663.031 I slot print_timing: id 3 | task 21731 | n_gen = 837, tg = 22.36 t/s, tg_3s = 18.80 t/s 18.11.121.311 I slot print_timing: id 2 | task 22005 | n_gen = 576, tg = 22.76 t/s, tg_3s = 18.81 t/s 18.11.454.215 I slot print_timing: id 2 | task 22005 | prompt eval time = 730.16 ms / 464 tokens ( 1.57 ms per token, 635.47 tokens per second) 18.11.454.219 I slot print_timing: id 2 | task 22005 | eval time = 25600.55 ms / 584 tokens ( 43.91 ms per token, 22.77 tokens per second) 18.11.454.220 I slot print_timing: id 2 | task 22005 | total time = 26330.71 ms / 1048 tokens 18.11.454.221 I slot print_timing: id 2 | task 22005 | graphs reused = 21627 18.11.454.222 I slot print_timing: id 2 | task 22005 | graph reallocs = 0 / 0 (same size) / (changed size) 18.11.454.331 I slot release: id 2 | task 22005 | stop processing: n_tokens = 1740, truncated = 0 18.11.497.841 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.614 18.11.497.880 I slot launch_slot_: id 2 | task 22594 | processing task, is_child = 0 18.12.279.819 I slot print_timing: id 0 | task 22295 | n_gen = 298, tg = 21.58 t/s, tg_3s = 18.44 t/s 18.13.696.107 I slot print_timing: id 3 | task 21731 | n_gen = 892, tg = 22.05 t/s, tg_3s = 18.13 t/s 18.14.028.535 I slot print_timing: id 1 | task 22535 | n_gen = 100, tg = 20.33 t/s, tg_3s = 20.54 t/s 18.15.285.930 I slot print_timing: id 0 | task 22295 | n_gen = 369, tg = 21.95 t/s, tg_3s = 23.62 t/s 18.16.505.907 I slot print_timing: id 2 | task 22594 | n_gen = 100, tg = 23.88 t/s, tg_3s = 24.12 t/s 18.16.714.632 I slot print_timing: id 3 | task 21731 | n_gen = 964, tg = 22.17 t/s, tg_3s = 23.85 t/s 18.17.047.110 I slot print_timing: id 1 | task 22535 | n_gen = 172, tg = 21.68 t/s, tg_3s = 23.85 t/s 18.18.301.687 I slot print_timing: id 0 | task 22295 | n_gen = 441, tg = 22.24 t/s, tg_3s = 23.87 t/s 18.19.226.032 I slot print_timing: id 3 | task 21731 | prompt eval time = 694.49 ms / 448 tokens ( 1.55 ms per token, 645.08 tokens per second) 18.19.226.037 I slot print_timing: id 3 | task 21731 | eval time = 45945.10 ms / 1024 tokens ( 44.91 ms per token, 22.27 tokens per second) 18.19.226.038 I slot print_timing: id 3 | task 21731 | total time = 46639.59 ms / 1472 tokens 18.19.226.039 I slot print_timing: id 3 | task 21731 | graphs reused = 21789 18.19.226.040 I slot print_timing: id 3 | task 21731 | graph reallocs = 0 / 0 (same size) / (changed size) 18.19.226.149 I slot release: id 3 | task 21731 | stop processing: n_tokens = 2166, truncated = 0 18.19.262.373 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.493 18.19.264.853 I slot launch_slot_: id 3 | task 22763 | processing task, is_child = 0 18.19.903.467 I slot print_timing: id 2 | task 22594 | n_gen = 167, tg = 22.00 t/s, tg_3s = 19.72 t/s 18.20.058.772 I slot print_timing: id 1 | task 22535 | n_gen = 229, tg = 20.92 t/s, tg_3s = 18.93 t/s 18.21.310.162 I slot print_timing: id 0 | task 22295 | n_gen = 498, tg = 21.81 t/s, tg_3s = 18.95 t/s 18.22.942.255 I slot print_timing: id 2 | task 22594 | n_gen = 239, tg = 22.49 t/s, tg_3s = 23.69 t/s 18.23.066.775 I slot print_timing: id 1 | task 22535 | n_gen = 301, tg = 21.57 t/s, tg_3s = 23.94 t/s 18.24.108.662 I slot print_timing: id 3 | task 22763 | n_gen = 100, tg = 23.96 t/s, tg_3s = 24.20 t/s 18.24.315.506 I slot print_timing: id 0 | task 22295 | n_gen = 570, tg = 22.06 t/s, tg_3s = 23.96 t/s 18.25.984.326 I slot print_timing: id 2 | task 22594 | n_gen = 312, tg = 22.83 t/s, tg_3s = 24.00 t/s 18.26.066.925 I slot print_timing: id 1 | task 22535 | n_gen = 373, tg = 22.00 t/s, tg_3s = 24.00 t/s 18.27.112.597 I slot print_timing: id 3 | task 22763 | n_gen = 172, tg = 23.96 t/s, tg_3s = 23.97 t/s 18.27.319.641 I slot print_timing: id 0 | task 22295 | n_gen = 642, tg = 22.26 t/s, tg_3s = 23.97 t/s 18.28.984.807 I slot print_timing: id 2 | task 22594 | n_gen = 384, tg = 23.04 t/s, tg_3s = 24.00 t/s 18.29.067.371 I slot print_timing: id 1 | task 22535 | n_gen = 445, tg = 22.30 t/s, tg_3s = 24.00 t/s 18.30.151.100 I slot print_timing: id 3 | task 22763 | n_gen = 245, tg = 23.98 t/s, tg_3s = 24.02 t/s 18.30.357.430 I slot print_timing: id 0 | task 22295 | n_gen = 715, tg = 22.43 t/s, tg_3s = 24.03 t/s 18.31.987.404 I slot print_timing: id 2 | task 22594 | n_gen = 456, tg = 23.18 t/s, tg_3s = 23.98 t/s 18.32.070.455 I slot print_timing: id 1 | task 22535 | n_gen = 517, tg = 22.52 t/s, tg_3s = 23.98 t/s 18.33.159.204 I slot print_timing: id 3 | task 22763 | n_gen = 317, tg = 23.97 t/s, tg_3s = 23.94 t/s 18.33.366.593 I slot print_timing: id 0 | task 22295 | n_gen = 787, tg = 22.56 t/s, tg_3s = 23.93 t/s 18.34.999.941 I slot print_timing: id 2 | task 22594 | n_gen = 528, tg = 23.28 t/s, tg_3s = 23.90 t/s 18.35.082.925 I slot print_timing: id 1 | task 22535 | n_gen = 589, tg = 22.68 t/s, tg_3s = 23.90 t/s 18.36.168.444 I slot print_timing: id 3 | task 22763 | n_gen = 389, tg = 23.96 t/s, tg_3s = 23.93 t/s 18.36.376.311 I slot print_timing: id 0 | task 22295 | n_gen = 859, tg = 22.66 t/s, tg_3s = 23.92 t/s 18.38.007.805 I slot print_timing: id 2 | task 22594 | n_gen = 600, tg = 23.35 t/s, tg_3s = 23.94 t/s 18.38.090.579 I slot print_timing: id 1 | task 22535 | n_gen = 661, tg = 22.81 t/s, tg_3s = 23.94 t/s 18.39.178.224 I slot print_timing: id 3 | task 22763 | n_gen = 461, tg = 23.96 t/s, tg_3s = 23.92 t/s 18.39.386.275 I slot print_timing: id 0 | task 22295 | n_gen = 931, tg = 22.76 t/s, tg_3s = 23.92 t/s 18.41.027.695 I slot print_timing: id 2 | task 22594 | n_gen = 672, tg = 23.41 t/s, tg_3s = 23.84 t/s 18.41.111.422 I slot print_timing: id 1 | task 22535 | n_gen = 733, tg = 22.91 t/s, tg_3s = 23.83 t/s 18.42.200.726 I slot print_timing: id 3 | task 22763 | n_gen = 533, tg = 23.94 t/s, tg_3s = 23.82 t/s 18.42.408.749 I slot print_timing: id 0 | task 22295 | n_gen = 1003, tg = 22.83 t/s, tg_3s = 23.82 t/s 18.43.289.673 I slot print_timing: id 0 | task 22295 | prompt eval time = 708.65 ms / 469 tokens ( 1.51 ms per token, 661.82 tokens per second) 18.43.289.677 I slot print_timing: id 0 | task 22295 | eval time = 44769.57 ms / 1024 tokens ( 43.76 ms per token, 22.85 tokens per second) 18.43.289.678 I slot print_timing: id 0 | task 22295 | total time = 45478.22 ms / 1493 tokens 18.43.289.679 I slot print_timing: id 0 | task 22295 | graphs reused = 22344 18.43.289.679 I slot print_timing: id 0 | task 22295 | graph reallocs = 0 / 0 (same size) / (changed size) 18.43.289.786 I slot release: id 0 | task 22295 | stop processing: n_tokens = 2188, truncated = 0 18.43.327.978 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.488 18.43.334.197 I slot launch_slot_: id 0 | task 23325 | processing task, is_child = 0 18.44.072.686 I slot print_timing: id 2 | task 22594 | n_gen = 729, tg = 22.96 t/s, tg_3s = 18.72 t/s 18.44.114.553 I slot print_timing: id 1 | task 22535 | n_gen = 789, tg = 22.54 t/s, tg_3s = 18.65 t/s 18.44.523.412 I slot print_timing: id 1 | task 22535 | prompt eval time = 726.81 ms / 458 tokens ( 1.59 ms per token, 630.15 tokens per second) 18.44.523.417 I slot print_timing: id 1 | task 22535 | eval time = 35364.03 ms / 799 tokens ( 44.32 ms per token, 22.57 tokens per second) 18.44.523.418 I slot print_timing: id 1 | task 22535 | total time = 36090.84 ms / 1257 tokens 18.44.523.418 I slot print_timing: id 1 | task 22535 | graphs reused = 22355 18.44.523.419 I slot print_timing: id 1 | task 22535 | graph reallocs = 0 / 0 (same size) / (changed size) 18.44.523.475 I slot release: id 1 | task 22535 | stop processing: n_tokens = 1932, truncated = 0 18.44.564.942 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.553 18.44.564.969 I slot launch_slot_: id 1 | task 23340 | processing task, is_child = 0 18.45.224.265 I slot print_timing: id 3 | task 22763 | n_gen = 575, tg = 22.73 t/s, tg_3s = 13.89 t/s 18.47.103.465 I slot print_timing: id 2 | task 22594 | n_gen = 786, tg = 22.59 t/s, tg_3s = 18.81 t/s 18.48.233.143 I slot print_timing: id 3 | task 22763 | n_gen = 646, tg = 22.83 t/s, tg_3s = 23.60 t/s 18.48.860.753 I slot print_timing: id 0 | task 23325 | n_gen = 100, tg = 20.67 t/s, tg_3s = 20.88 t/s 18.49.447.874 I slot print_timing: id 1 | task 23340 | n_gen = 100, tg = 23.89 t/s, tg_3s = 24.13 t/s 18.50.119.991 I slot print_timing: id 2 | task 22594 | n_gen = 858, tg = 22.70 t/s, tg_3s = 23.87 t/s 18.51.251.075 I slot print_timing: id 3 | task 22763 | n_gen = 718, tg = 22.93 t/s, tg_3s = 23.86 t/s 18.51.876.656 I slot print_timing: id 0 | task 23325 | n_gen = 172, tg = 21.91 t/s, tg_3s = 23.87 t/s 18.52.465.684 I slot print_timing: id 1 | task 23340 | n_gen = 172, tg = 23.88 t/s, tg_3s = 23.86 t/s 18.53.139.874 I slot print_timing: id 2 | task 22594 | n_gen = 930, tg = 22.78 t/s, tg_3s = 23.84 t/s 18.54.275.129 I slot print_timing: id 3 | task 22763 | n_gen = 790, tg = 23.00 t/s, tg_3s = 23.81 t/s 18.54.901.462 I slot print_timing: id 0 | task 23325 | n_gen = 244, tg = 22.44 t/s, tg_3s = 23.80 t/s 18.55.489.583 I slot print_timing: id 1 | task 23340 | n_gen = 244, tg = 23.86 t/s, tg_3s = 23.81 t/s 18.56.160.207 I slot print_timing: id 2 | task 22594 | n_gen = 1002, tg = 22.85 t/s, tg_3s = 23.84 t/s 18.57.084.167 I slot print_timing: id 2 | task 22594 | prompt eval time = 861.70 ms / 521 tokens ( 1.65 ms per token, 604.62 tokens per second) 18.57.084.174 I slot print_timing: id 2 | task 22594 | eval time = 44724.57 ms / 1024 tokens ( 43.72 ms per token, 22.87 tokens per second) 18.57.084.175 I slot print_timing: id 2 | task 22594 | total time = 45586.27 ms / 1545 tokens 18.57.084.175 I slot print_timing: id 2 | task 22594 | graphs reused = 22634 18.57.084.176 I slot print_timing: id 2 | task 22594 | graph reallocs = 0 / 0 (same size) / (changed size) 18.57.084.280 I slot release: id 2 | task 22594 | stop processing: n_tokens = 2237, truncated = 0 18.57.127.825 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.477 18.57.134.385 I slot launch_slot_: id 2 | task 23625 | processing task, is_child = 0 18.57.798.806 I slot print_timing: id 3 | task 22763 | n_gen = 859, tg = 22.68 t/s, tg_3s = 19.58 t/s 18.57.918.714 I slot print_timing: id 0 | task 23325 | n_gen = 300, tg = 21.59 t/s, tg_3s = 18.56 t/s 18.58.509.918 I slot print_timing: id 1 | task 23340 | n_gen = 300, tg = 22.64 t/s, tg_3s = 18.54 t/s 19.00.808.036 I slot print_timing: id 3 | task 22763 | n_gen = 930, tg = 22.75 t/s, tg_3s = 23.59 t/s 19.00.932.331 I slot print_timing: id 0 | task 23325 | n_gen = 372, tg = 22.00 t/s, tg_3s = 23.89 t/s 19.01.518.562 I slot print_timing: id 1 | task 23340 | n_gen = 372, tg = 22.88 t/s, tg_3s = 23.93 t/s 19.02.021.637 I slot print_timing: id 2 | task 23625 | n_gen = 100, tg = 23.89 t/s, tg_3s = 24.13 t/s 19.03.829.801 I slot print_timing: id 3 | task 22763 | n_gen = 1002, tg = 22.83 t/s, tg_3s = 23.83 t/s 19.03.953.714 I slot print_timing: id 0 | task 23325 | n_gen = 444, tg = 22.28 t/s, tg_3s = 23.83 t/s 19.04.541.472 I slot print_timing: id 1 | task 23340 | n_gen = 444, tg = 23.03 t/s, tg_3s = 23.82 t/s 19.04.750.526 I slot print_timing: id 3 | task 22763 | prompt eval time = 711.32 ms / 456 tokens ( 1.56 ms per token, 641.07 tokens per second) 19.04.750.532 I slot print_timing: id 3 | task 22763 | eval time = 44774.35 ms / 1024 tokens ( 43.77 ms per token, 22.85 tokens per second) 19.04.750.533 I slot print_timing: id 3 | task 22763 | total time = 45485.66 ms / 1480 tokens 19.04.750.533 I slot print_timing: id 3 | task 22763 | graphs reused = 22796 19.04.750.534 I slot print_timing: id 3 | task 22763 | graph reallocs = 0 / 0 (same size) / (changed size) 19.04.750.631 I slot release: id 3 | task 22763 | stop processing: n_tokens = 2174, truncated = 0 19.04.786.109 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.491 19.04.791.857 I slot launch_slot_: id 3 | task 23793 | processing task, is_child = 0 19.05.432.059 I slot print_timing: id 2 | task 23625 | n_gen = 167, tg = 21.97 t/s, tg_3s = 19.65 t/s 19.06.961.882 I slot print_timing: id 0 | task 23325 | n_gen = 501, tg = 21.84 t/s, tg_3s = 18.95 t/s 19.07.543.225 I slot print_timing: id 1 | task 23340 | n_gen = 501, tg = 22.48 t/s, tg_3s = 18.99 t/s 19.08.375.902 I slot print_timing: id 1 | task 23340 | prompt eval time = 738.57 ms / 476 tokens ( 1.55 ms per token, 644.49 tokens per second) 19.08.375.909 I slot print_timing: id 1 | task 23340 | eval time = 23072.36 ms / 521 tokens ( 44.37 ms per token, 22.54 tokens per second) 19.08.375.911 I slot print_timing: id 1 | task 23340 | total time = 23810.92 ms / 997 tokens 19.08.375.912 I slot print_timing: id 1 | task 23340 | graphs reused = 22864 19.08.375.912 I slot print_timing: id 1 | task 23340 | graph reallocs = 0 / 0 (same size) / (changed size) 19.08.376.035 I slot release: id 1 | task 23340 | stop processing: n_tokens = 1672, truncated = 0 19.08.420.465 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.639 19.08.420.510 I slot launch_slot_: id 1 | task 23866 | processing task, is_child = 0 19.09.106.295 I slot print_timing: id 2 | task 23625 | n_gen = 239, tg = 21.19 t/s, tg_3s = 19.60 t/s 19.09.978.779 I slot print_timing: id 0 | task 23325 | n_gen = 557, tg = 21.46 t/s, tg_3s = 18.56 t/s 19.10.313.275 I slot print_timing: id 3 | task 23793 | n_gen = 100, tg = 20.59 t/s, tg_3s = 20.80 t/s 19.12.146.102 I slot print_timing: id 2 | task 23625 | n_gen = 311, tg = 21.73 t/s, tg_3s = 23.69 t/s 19.13.018.719 I slot print_timing: id 0 | task 23325 | n_gen = 630, tg = 21.73 t/s, tg_3s = 24.01 t/s 19.13.311.076 I slot print_timing: id 1 | task 23866 | n_gen = 100, tg = 24.00 t/s, tg_3s = 24.24 t/s 19.13.354.079 I slot print_timing: id 3 | task 23793 | n_gen = 173, tg = 21.91 t/s, tg_3s = 24.01 t/s 19.15.183.001 I slot print_timing: id 2 | task 23625 | n_gen = 384, tg = 22.13 t/s, tg_3s = 24.04 t/s 19.16.056.454 I slot print_timing: id 0 | task 23325 | n_gen = 703, tg = 21.95 t/s, tg_3s = 24.03 t/s 19.16.348.970 I slot print_timing: id 1 | task 23866 | n_gen = 173, tg = 24.01 t/s, tg_3s = 24.03 t/s 19.16.391.404 I slot print_timing: id 3 | task 23793 | n_gen = 246, tg = 22.50 t/s, tg_3s = 24.03 t/s 19.18.221.380 I slot print_timing: id 2 | task 23625 | n_gen = 457, tg = 22.41 t/s, tg_3s = 24.03 t/s 19.19.096.242 I slot print_timing: id 0 | task 23325 | n_gen = 776, tg = 22.13 t/s, tg_3s = 24.01 t/s 19.19.388.327 I slot print_timing: id 1 | task 23866 | n_gen = 246, tg = 24.01 t/s, tg_3s = 24.02 t/s 19.19.430.594 I slot print_timing: id 3 | task 23793 | n_gen = 319, tg = 22.83 t/s, tg_3s = 24.02 t/s 19.21.261.349 I slot print_timing: id 2 | task 23625 | n_gen = 530, tg = 22.62 t/s, tg_3s = 24.01 t/s 19.22.136.396 I slot print_timing: id 0 | task 23325 | n_gen = 849, tg = 22.28 t/s, tg_3s = 24.01 t/s 19.22.428.555 I slot print_timing: id 1 | task 23866 | n_gen = 319, tg = 24.01 t/s, tg_3s = 24.01 t/s 19.22.471.722 I slot print_timing: id 3 | task 23793 | n_gen = 392, tg = 23.04 t/s, tg_3s = 24.00 t/s 19.24.270.123 I slot print_timing: id 2 | task 23625 | n_gen = 602, tg = 22.77 t/s, tg_3s = 23.93 t/s 19.25.151.001 I slot print_timing: id 0 | task 23325 | n_gen = 921, tg = 22.40 t/s, tg_3s = 23.88 t/s 19.25.444.075 I slot print_timing: id 1 | task 23866 | n_gen = 391, tg = 23.99 t/s, tg_3s = 23.88 t/s 19.25.486.934 I slot print_timing: id 3 | task 23793 | n_gen = 464, tg = 23.17 t/s, tg_3s = 23.88 t/s 19.27.280.790 I slot print_timing: id 2 | task 23625 | n_gen = 674, tg = 22.89 t/s, tg_3s = 23.91 t/s 19.28.161.454 I slot print_timing: id 0 | task 23325 | n_gen = 993, tg = 22.50 t/s, tg_3s = 23.92 t/s 19.28.457.747 I slot print_timing: id 1 | task 23866 | n_gen = 463, tg = 23.97 t/s, tg_3s = 23.89 t/s 19.28.500.908 I slot print_timing: id 3 | task 23793 | n_gen = 536, tg = 23.26 t/s, tg_3s = 23.89 t/s 19.29.463.200 I slot print_timing: id 0 | task 23325 | prompt eval time = 737.91 ms / 496 tokens ( 1.49 ms per token, 672.17 tokens per second) 19.29.463.206 I slot print_timing: id 0 | task 23325 | eval time = 45391.08 ms / 1024 tokens ( 44.37 ms per token, 22.54 tokens per second) 19.29.463.207 I slot print_timing: id 0 | task 23325 | total time = 46128.99 ms / 1520 tokens 19.29.463.208 I slot print_timing: id 0 | task 23325 | graphs reused = 23347 19.29.463.208 I slot print_timing: id 0 | task 23325 | graph reallocs = 0 / 0 (same size) / (changed size) 19.29.463.314 I slot release: id 0 | task 23325 | stop processing: n_tokens = 2215, truncated = 0 19.29.501.034 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.482 19.29.509.102 I slot launch_slot_: id 0 | task 24356 | processing task, is_child = 0 19.30.299.324 I slot print_timing: id 2 | task 23625 | n_gen = 730, tg = 22.48 t/s, tg_3s = 18.55 t/s 19.31.467.527 I slot print_timing: id 1 | task 23866 | n_gen = 519, tg = 23.25 t/s, tg_3s = 18.61 t/s 19.31.511.223 I slot print_timing: id 3 | task 23793 | n_gen = 592, tg = 22.72 t/s, tg_3s = 18.60 t/s 19.33.303.118 I slot print_timing: id 2 | task 23625 | n_gen = 802, tg = 22.61 t/s, tg_3s = 23.97 t/s 19.34.390.198 I slot print_timing: id 0 | task 24356 | n_gen = 100, tg = 23.95 t/s, tg_3s = 24.19 t/s 19.34.475.056 I slot print_timing: id 1 | task 23866 | n_gen = 591, tg = 23.33 t/s, tg_3s = 23.94 t/s 19.34.518.381 I slot print_timing: id 3 | task 23793 | n_gen = 664, tg = 22.85 t/s, tg_3s = 23.94 t/s 19.36.322.554 I slot print_timing: id 2 | task 23625 | n_gen = 874, tg = 22.71 t/s, tg_3s = 23.85 t/s 19.37.412.901 I slot print_timing: id 0 | task 24356 | n_gen = 172, tg = 23.89 t/s, tg_3s = 23.82 t/s 19.37.497.038 I slot print_timing: id 1 | task 23866 | n_gen = 663, tg = 23.38 t/s, tg_3s = 23.83 t/s 19.37.540.101 I slot print_timing: id 3 | task 23793 | n_gen = 736, tg = 22.94 t/s, tg_3s = 23.83 t/s 19.39.346.086 I slot print_timing: id 2 | task 23625 | n_gen = 946, tg = 22.79 t/s, tg_3s = 23.81 t/s 19.40.434.050 I slot print_timing: id 0 | task 24356 | n_gen = 244, tg = 23.88 t/s, tg_3s = 23.83 t/s 19.40.518.102 I slot print_timing: id 1 | task 23866 | n_gen = 735, tg = 23.43 t/s, tg_3s = 23.83 t/s 19.40.561.170 I slot print_timing: id 3 | task 23793 | n_gen = 808, tg = 23.02 t/s, tg_3s = 23.83 t/s 19.42.362.811 I slot print_timing: id 2 | task 23625 | n_gen = 1018, tg = 22.86 t/s, tg_3s = 23.87 t/s 19.42.613.984 I slot print_timing: id 2 | task 23625 | prompt eval time = 742.62 ms / 484 tokens ( 1.53 ms per token, 651.74 tokens per second) 19.42.613.992 I slot print_timing: id 2 | task 23625 | eval time = 44736.96 ms / 1024 tokens ( 43.73 ms per token, 22.87 tokens per second) 19.42.613.993 I slot print_timing: id 2 | task 23625 | total time = 45479.59 ms / 1508 tokens 19.42.613.994 I slot print_timing: id 2 | task 23625 | graphs reused = 23641 19.42.613.994 I slot print_timing: id 2 | task 23625 | graph reallocs = 0 / 0 (same size) / (changed size) 19.42.614.123 I slot release: id 2 | task 23625 | stop processing: n_tokens = 2205, truncated = 0 19.42.658.358 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.484 19.42.664.913 I slot launch_slot_: id 2 | task 24655 | processing task, is_child = 0 19.43.449.297 I slot print_timing: id 0 | task 24356 | n_gen = 301, tg = 22.74 t/s, tg_3s = 18.90 t/s 19.43.531.251 I slot print_timing: id 1 | task 23866 | n_gen = 792, tg = 23.03 t/s, tg_3s = 18.92 t/s 19.43.572.945 I slot print_timing: id 3 | task 23793 | n_gen = 865, tg = 22.70 t/s, tg_3s = 18.93 t/s 19.46.469.777 I slot print_timing: id 0 | task 24356 | n_gen = 373, tg = 22.94 t/s, tg_3s = 23.84 t/s 19.46.554.052 I slot print_timing: id 1 | task 23866 | n_gen = 864, tg = 23.09 t/s, tg_3s = 23.82 t/s 19.46.596.950 I slot print_timing: id 3 | task 23793 | n_gen = 937, tg = 22.78 t/s, tg_3s = 23.81 t/s 19.47.516.597 I slot print_timing: id 2 | task 24655 | n_gen = 100, tg = 23.86 t/s, tg_3s = 24.10 t/s 19.47.642.911 I slot print_timing: id 3 | task 23793 | prompt eval time = 712.65 ms / 457 tokens ( 1.56 ms per token, 641.27 tokens per second) 19.47.642.918 I slot print_timing: id 3 | task 23793 | eval time = 42138.39 ms / 962 tokens ( 43.85 ms per token, 22.81 tokens per second) 19.47.642.919 I slot print_timing: id 3 | task 23793 | total time = 42851.04 ms / 1419 tokens 19.47.642.920 I slot print_timing: id 3 | task 23793 | graphs reused = 23741 19.47.642.921 I slot print_timing: id 3 | task 23793 | graph reallocs = 0 / 0 (same size) / (changed size) 19.47.643.044 I slot release: id 3 | task 23793 | stop processing: n_tokens = 2113, truncated = 0 19.47.679.737 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.505 19.47.679.769 I slot launch_slot_: id 3 | task 24761 | processing task, is_child = 0 19.49.471.175 I slot print_timing: id 0 | task 24356 | n_gen = 430, tg = 22.33 t/s, tg_3s = 18.99 t/s 19.49.555.896 I slot print_timing: id 1 | task 23866 | n_gen = 921, tg = 22.79 t/s, tg_3s = 18.99 t/s 19.50.518.826 I slot print_timing: id 2 | task 24655 | n_gen = 157, tg = 21.81 t/s, tg_3s = 18.99 t/s 19.52.489.933 I slot print_timing: id 0 | task 24356 | n_gen = 502, tg = 22.53 t/s, tg_3s = 23.85 t/s 19.52.533.116 I slot print_timing: id 3 | task 24761 | n_gen = 100, tg = 23.91 t/s, tg_3s = 24.15 t/s 19.52.574.020 I slot print_timing: id 1 | task 23866 | n_gen = 993, tg = 22.86 t/s, tg_3s = 23.86 t/s 19.53.535.881 I slot print_timing: id 2 | task 24655 | n_gen = 229, tg = 22.42 t/s, tg_3s = 23.86 t/s 19.53.870.380 I slot print_timing: id 1 | task 23866 | prompt eval time = 765.28 ms / 498 tokens ( 1.54 ms per token, 650.75 tokens per second) 19.53.870.385 I slot print_timing: id 1 | task 23866 | eval time = 44684.58 ms / 1024 tokens ( 43.68 ms per token, 22.89 tokens per second) 19.53.870.386 I slot print_timing: id 1 | task 23866 | total time = 45449.86 ms / 1522 tokens 19.53.870.386 I slot print_timing: id 1 | task 23866 | graphs reused = 23871 19.53.870.387 I slot print_timing: id 1 | task 23866 | graph reallocs = 0 / 0 (same size) / (changed size) 19.53.870.505 I slot release: id 1 | task 23866 | stop processing: n_tokens = 2197, truncated = 0 19.53.914.591 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.486 19.53.922.616 I slot launch_slot_: id 1 | task 24896 | processing task, is_child = 0 19.55.515.777 I slot print_timing: id 0 | task 24356 | n_gen = 559, tg = 22.09 t/s, tg_3s = 18.84 t/s 19.55.559.049 I slot print_timing: id 3 | task 24761 | n_gen = 157, tg = 21.77 t/s, tg_3s = 18.84 t/s 19.56.560.690 I slot print_timing: id 2 | task 24655 | n_gen = 286, tg = 21.60 t/s, tg_3s = 18.84 t/s 19.58.557.529 I slot print_timing: id 0 | task 24356 | n_gen = 632, tg = 22.30 t/s, tg_3s = 24.00 t/s 19.58.559.096 I slot print_timing: id 3 | task 24761 | n_gen = 229, tg = 22.43 t/s, tg_3s = 24.00 t/s 19.58.769.243 I slot print_timing: id 1 | task 24896 | n_gen = 100, tg = 24.02 t/s, tg_3s = 24.26 t/s 19.59.562.477 I slot print_timing: id 2 | task 24655 | n_gen = 358, tg = 22.04 t/s, tg_3s = 23.99 t/s 20.00.395.669 I slot print_timing: id 2 | task 24655 | prompt eval time = 702.42 ms / 441 tokens ( 1.59 ms per token, 627.83 tokens per second) 20.00.395.677 I slot print_timing: id 2 | task 24655 | eval time = 17028.33 ms / 378 tokens ( 45.17 ms per token, 22.14 tokens per second) 20.00.395.677 I slot print_timing: id 2 | task 24655 | total time = 17730.74 ms / 819 tokens 20.00.395.678 I slot print_timing: id 2 | task 24655 | graphs reused = 24007 20.00.395.679 I slot print_timing: id 2 | task 24655 | graph reallocs = 0 / 0 (same size) / (changed size) 20.00.395.795 I slot release: id 2 | task 24655 | stop processing: n_tokens = 1516, truncated = 0 20.00.439.649 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.704 20.00.439.694 I slot launch_slot_: id 2 | task 25038 | processing task, is_child = 0 20.01.597.428 I slot print_timing: id 0 | task 24356 | n_gen = 690, tg = 21.98 t/s, tg_3s = 19.08 t/s 20.01.599.859 I slot print_timing: id 3 | task 24761 | n_gen = 287, tg = 21.65 t/s, tg_3s = 19.07 t/s 20.01.810.806 I slot print_timing: id 1 | task 24896 | n_gen = 158, tg = 21.92 t/s, tg_3s = 19.07 t/s 20.04.602.293 I slot print_timing: id 0 | task 24356 | n_gen = 762, tg = 22.16 t/s, tg_3s = 23.96 t/s 20.04.603.997 I slot print_timing: id 3 | task 24761 | n_gen = 359, tg = 22.08 t/s, tg_3s = 23.97 t/s 20.04.851.633 I slot print_timing: id 1 | task 24896 | n_gen = 231, tg = 22.54 t/s, tg_3s = 24.01 t/s 20.05.101.979 I slot print_timing: id 0 | task 24356 | prompt eval time = 747.24 ms / 509 tokens ( 1.47 ms per token, 681.17 tokens per second) 20.05.101.985 I slot print_timing: id 0 | task 24356 | eval time = 34845.62 ms / 774 tokens ( 45.08 ms per token, 22.18 tokens per second) 20.05.101.986 I slot print_timing: id 0 | task 24356 | total time = 35592.86 ms / 1283 tokens 20.05.101.987 I slot print_timing: id 0 | task 24356 | graphs reused = 24101 20.05.101.988 I slot print_timing: id 0 | task 24356 | graph reallocs = 0 / 0 (same size) / (changed size) 20.05.102.107 I slot release: id 0 | task 24356 | stop processing: n_tokens = 1932, truncated = 0 20.05.140.142 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.553 20.05.140.181 I slot launch_slot_: id 0 | task 25137 | processing task, is_child = 0 20.06.119.847 I slot print_timing: id 2 | task 25038 | n_gen = 100, tg = 19.92 t/s, tg_3s = 20.12 t/s 20.07.608.195 I slot print_timing: id 3 | task 24761 | n_gen = 411, tg = 21.34 t/s, tg_3s = 17.31 t/s 20.07.857.535 I slot print_timing: id 1 | task 24896 | n_gen = 283, tg = 21.35 t/s, tg_3s = 17.30 t/s 20.09.148.414 I slot print_timing: id 2 | task 25038 | n_gen = 173, tg = 21.50 t/s, tg_3s = 24.10 t/s 20.10.230.807 I slot print_timing: id 0 | task 25137 | n_gen = 100, tg = 24.08 t/s, tg_3s = 24.32 t/s 20.10.649.459 I slot print_timing: id 3 | task 24761 | n_gen = 484, tg = 21.70 t/s, tg_3s = 24.00 t/s 20.10.898.332 I slot print_timing: id 1 | task 24896 | n_gen = 356, tg = 21.84 t/s, tg_3s = 24.01 t/s 20.12.154.160 I slot print_timing: id 2 | task 25038 | n_gen = 245, tg = 22.17 t/s, tg_3s = 23.95 t/s 20.13.243.590 I slot print_timing: id 0 | task 25137 | n_gen = 172, tg = 24.00 t/s, tg_3s = 23.90 t/s 20.13.664.984 I slot print_timing: id 3 | task 24761 | n_gen = 556, tg = 21.96 t/s, tg_3s = 23.88 t/s 20.13.915.329 I slot print_timing: id 1 | task 24896 | n_gen = 428, tg = 22.16 t/s, tg_3s = 23.86 t/s 20.15.170.916 I slot print_timing: id 2 | task 25038 | n_gen = 317, tg = 22.54 t/s, tg_3s = 23.87 t/s 20.16.252.713 I slot print_timing: id 0 | task 25137 | n_gen = 244, tg = 23.98 t/s, tg_3s = 23.93 t/s 20.16.670.969 I slot print_timing: id 3 | task 24761 | n_gen = 628, tg = 22.17 t/s, tg_3s = 23.95 t/s 20.16.919.992 I slot print_timing: id 1 | task 24896 | n_gen = 500, tg = 22.40 t/s, tg_3s = 23.96 t/s 20.18.178.924 I slot print_timing: id 2 | task 25038 | n_gen = 389, tg = 22.78 t/s, tg_3s = 23.94 t/s 20.19.263.803 I slot print_timing: id 0 | task 25137 | n_gen = 316, tg = 23.96 t/s, tg_3s = 23.91 t/s 20.19.684.415 I slot print_timing: id 3 | task 24761 | n_gen = 700, tg = 22.34 t/s, tg_3s = 23.89 t/s 20.19.933.326 I slot print_timing: id 1 | task 24896 | n_gen = 572, tg = 22.58 t/s, tg_3s = 23.89 t/s 20.21.184.319 I slot print_timing: id 2 | task 25038 | n_gen = 461, tg = 22.96 t/s, tg_3s = 23.96 t/s 20.22.268.673 I slot print_timing: id 0 | task 25137 | n_gen = 388, tg = 23.96 t/s, tg_3s = 23.96 t/s 20.22.686.565 I slot print_timing: id 3 | task 24761 | n_gen = 772, tg = 22.48 t/s, tg_3s = 23.98 t/s 20.22.934.818 I slot print_timing: id 1 | task 24896 | n_gen = 644, tg = 22.73 t/s, tg_3s = 23.99 t/s 20.23.144.152 I slot print_timing: id 1 | task 24896 | prompt eval time = 724.47 ms / 456 tokens ( 1.59 ms per token, 629.43 tokens per second) 20.23.144.159 I slot print_timing: id 1 | task 24896 | eval time = 28497.05 ms / 649 tokens ( 43.98 ms per token, 22.74 tokens per second) 20.23.144.160 I slot print_timing: id 1 | task 24896 | total time = 29221.52 ms / 1105 tokens 20.23.144.160 I slot print_timing: id 1 | task 24896 | graphs reused = 24507 20.23.144.161 I slot print_timing: id 1 | task 24896 | graph reallocs = 0 / 0 (same size) / (changed size) 20.23.144.270 I slot release: id 1 | task 24896 | stop processing: n_tokens = 1791, truncated = 0 20.23.188.273 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.596 20.23.188.307 I slot launch_slot_: id 1 | task 25550 | processing task, is_child = 0 20.24.220.252 I slot print_timing: id 2 | task 25038 | n_gen = 518, tg = 22.41 t/s, tg_3s = 18.78 t/s 20.25.301.882 I slot print_timing: id 0 | task 25137 | n_gen = 445, tg = 23.15 t/s, tg_3s = 18.79 t/s 20.25.720.880 I slot print_timing: id 3 | task 24761 | n_gen = 829, tg = 22.18 t/s, tg_3s = 18.79 t/s 20.26.677.938 I slot print_timing: id 2 | task 25038 | prompt eval time = 709.89 ms / 452 tokens ( 1.57 ms per token, 636.72 tokens per second) 20.26.677.943 I slot print_timing: id 2 | task 25038 | eval time = 25528.33 ms / 577 tokens ( 44.32 ms per token, 22.56 tokens per second) 20.26.677.943 I slot print_timing: id 2 | task 25038 | total time = 26238.22 ms / 1029 tokens 20.26.677.944 I slot print_timing: id 2 | task 25038 | graphs reused = 24572 20.26.677.945 I slot print_timing: id 2 | task 25038 | graph reallocs = 0 / 0 (same size) / (changed size) 20.26.678.068 I slot release: id 2 | task 25038 | stop processing: n_tokens = 1726, truncated = 0 20.26.721.836 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.619 20.26.721.874 I slot launch_slot_: id 2 | task 25620 | processing task, is_child = 0 20.28.321.666 I slot print_timing: id 0 | task 25137 | n_gen = 502, tg = 22.57 t/s, tg_3s = 18.88 t/s 20.28.696.769 I slot print_timing: id 1 | task 25550 | n_gen = 100, tg = 20.74 t/s, tg_3s = 20.95 t/s 20.28.739.717 I slot print_timing: id 3 | task 24761 | n_gen = 886, tg = 21.93 t/s, tg_3s = 18.88 t/s 20.31.332.361 I slot print_timing: id 0 | task 25137 | n_gen = 574, tg = 22.73 t/s, tg_3s = 23.91 t/s 20.31.583.932 I slot print_timing: id 2 | task 25620 | n_gen = 100, tg = 23.98 t/s, tg_3s = 24.22 t/s 20.31.708.391 I slot print_timing: id 1 | task 25550 | n_gen = 172, tg = 21.96 t/s, tg_3s = 23.91 t/s 20.31.751.122 I slot print_timing: id 3 | task 24761 | n_gen = 958, tg = 22.07 t/s, tg_3s = 23.91 t/s 20.34.344.159 I slot print_timing: id 0 | task 25137 | n_gen = 646, tg = 22.85 t/s, tg_3s = 23.91 t/s 20.34.513.048 I slot print_timing: id 3 | task 24761 | prompt eval time = 712.36 ms / 459 tokens ( 1.55 ms per token, 644.34 tokens per second) 20.34.513.056 I slot print_timing: id 3 | task 24761 | eval time = 46120.92 ms / 1024 tokens ( 45.08 ms per token, 22.18 tokens per second) 20.34.513.057 I slot print_timing: id 3 | task 24761 | total time = 46833.27 ms / 1483 tokens 20.34.513.057 I slot print_timing: id 3 | task 24761 | graphs reused = 24739 20.34.513.058 I slot print_timing: id 3 | task 24761 | graph reallocs = 0 / 0 (same size) / (changed size) 20.34.513.173 I slot release: id 3 | task 24761 | stop processing: n_tokens = 2177, truncated = 0 20.34.549.330 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.491 20.34.551.532 I slot launch_slot_: id 3 | task 25793 | processing task, is_child = 0 20.35.170.051 I slot print_timing: id 1 | task 25550 | n_gen = 241, tg = 21.34 t/s, tg_3s = 19.93 t/s 20.35.170.333 I slot print_timing: id 2 | task 25620 | n_gen = 172, tg = 22.16 t/s, tg_3s = 20.08 t/s 20.37.358.473 I slot print_timing: id 0 | task 25137 | n_gen = 704, tg = 22.50 t/s, tg_3s = 19.24 t/s 20.38.192.136 I slot print_timing: id 1 | task 25550 | n_gen = 313, tg = 21.86 t/s, tg_3s = 23.82 t/s 20.38.192.708 I slot print_timing: id 2 | task 25620 | n_gen = 244, tg = 22.63 t/s, tg_3s = 23.82 t/s 20.39.355.047 I slot print_timing: id 3 | task 25793 | n_gen = 100, tg = 24.08 t/s, tg_3s = 24.32 t/s 20.40.396.480 I slot print_timing: id 0 | task 25137 | n_gen = 777, tg = 22.64 t/s, tg_3s = 24.03 t/s 20.41.231.653 I slot print_timing: id 1 | task 25550 | n_gen = 386, tg = 22.24 t/s, tg_3s = 24.02 t/s 20.41.232.242 I slot print_timing: id 2 | task 25620 | n_gen = 317, tg = 22.94 t/s, tg_3s = 24.02 t/s 20.42.362.701 I slot print_timing: id 3 | task 25793 | n_gen = 172, tg = 24.02 t/s, tg_3s = 23.94 t/s 20.43.406.916 I slot print_timing: id 0 | task 25137 | n_gen = 849, tg = 22.74 t/s, tg_3s = 23.92 t/s 20.43.866.087 I slot print_timing: id 1 | task 25550 | prompt eval time = 734.14 ms / 468 tokens ( 1.57 ms per token, 637.48 tokens per second) 20.43.866.091 I slot print_timing: id 1 | task 25550 | eval time = 19943.63 ms / 449 tokens ( 44.52 ms per token, 22.46 tokens per second) 20.43.866.092 I slot print_timing: id 1 | task 25550 | total time = 20677.77 ms / 917 tokens 20.43.866.093 I slot print_timing: id 1 | task 25550 | graphs reused = 24944 20.43.866.093 I slot print_timing: id 1 | task 25550 | graph reallocs = 0 / 0 (same size) / (changed size) 20.43.866.201 I slot release: id 1 | task 25550 | stop processing: n_tokens = 1603, truncated = 0 20.43.909.717 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.666 20.43.909.760 I slot launch_slot_: id 1 | task 26004 | processing task, is_child = 0 20.44.595.807 I slot print_timing: id 2 | task 25620 | n_gen = 382, tg = 22.23 t/s, tg_3s = 19.32 t/s 20.45.387.721 I slot print_timing: id 3 | task 25793 | n_gen = 228, tg = 22.38 t/s, tg_3s = 18.51 t/s 20.45.554.951 I slot print_timing: id 2 | task 25620 | prompt eval time = 733.57 ms / 470 tokens ( 1.56 ms per token, 640.71 tokens per second) 20.45.554.956 I slot print_timing: id 2 | task 25620 | eval time = 18099.50 ms / 404 tokens ( 44.91 ms per token, 22.27 tokens per second) 20.45.554.957 I slot print_timing: id 2 | task 25620 | total time = 18833.07 ms / 874 tokens 20.45.554.958 I slot print_timing: id 2 | task 25620 | graphs reused = 24964 20.45.554.959 I slot print_timing: id 2 | task 25620 | graph reallocs = 0 / 0 (same size) / (changed size) 20.45.555.073 I slot release: id 2 | task 25620 | stop processing: n_tokens = 1571, truncated = 0 20.45.598.855 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.680 20.45.598.898 I slot launch_slot_: id 2 | task 26029 | processing task, is_child = 0 20.46.425.035 I slot print_timing: id 0 | task 25137 | n_gen = 890, tg = 22.06 t/s, tg_3s = 13.58 t/s 20.48.393.563 I slot print_timing: id 3 | task 25793 | n_gen = 285, tg = 21.60 t/s, tg_3s = 18.96 t/s 20.49.436.547 I slot print_timing: id 0 | task 25137 | n_gen = 962, tg = 22.19 t/s, tg_3s = 23.91 t/s 20.49.437.057 I slot print_timing: id 1 | task 26004 | n_gen = 100, tg = 20.79 t/s, tg_3s = 21.00 t/s 20.50.438.091 I slot print_timing: id 2 | task 26029 | n_gen = 100, tg = 23.94 t/s, tg_3s = 24.18 t/s 20.51.400.372 I slot print_timing: id 3 | task 25793 | n_gen = 357, tg = 22.03 t/s, tg_3s = 23.95 t/s 20.52.025.878 I slot print_timing: id 0 | task 25137 | prompt eval time = 979.10 ms / 561 tokens ( 1.75 ms per token, 572.98 tokens per second) 20.52.025.884 I slot print_timing: id 0 | task 25137 | eval time = 45906.59 ms / 1024 tokens ( 44.87 ms per token, 22.28 tokens per second) 20.52.025.885 I slot print_timing: id 0 | task 25137 | total time = 46885.69 ms / 1585 tokens 20.52.025.886 I slot print_timing: id 0 | task 25137 | graphs reused = 25100 20.52.025.887 I slot print_timing: id 0 | task 25137 | graph reallocs = 0 / 0 (same size) / (changed size) 20.52.025.993 I slot release: id 0 | task 25137 | stop processing: n_tokens = 2234, truncated = 0 20.52.456.435 I slot print_timing: id 1 | task 26004 | n_gen = 175, tg = 22.36 t/s, tg_3s = 24.84 t/s 20.53.445.256 I slot print_timing: id 2 | task 26029 | n_gen = 181, tg = 25.20 t/s, tg_3s = 26.94 t/s 20.54.038.215 I slot print_timing: id 3 | task 25793 | prompt eval time = 691.60 ms / 443 tokens ( 1.56 ms per token, 640.54 tokens per second) 20.54.038.221 I slot print_timing: id 3 | task 25793 | eval time = 18795.07 ms / 433 tokens ( 43.51 ms per token, 22.98 tokens per second) 20.54.038.221 I slot print_timing: id 3 | task 25793 | total time = 19486.67 ms / 876 tokens 20.54.038.222 I slot print_timing: id 3 | task 25793 | graphs reused = 25159 20.54.038.223 I slot print_timing: id 3 | task 25793 | graph reallocs = 0 / 0 (same size) / (changed size) 20.54.038.309 I slot release: id 3 | task 25793 | stop processing: n_tokens = 1570, truncated = 0 20.55.474.274 I slot print_timing: id 1 | task 26004 | n_gen = 282, tg = 26.02 t/s, tg_3s = 35.46 t/s 20.55.644.290 I slot print_timing: id 2 | task 26029 | prompt eval time = 703.01 ms / 441 tokens ( 1.59 ms per token, 627.30 tokens per second) 20.55.644.296 I slot print_timing: id 2 | task 26029 | eval time = 9342.37 ms / 265 tokens ( 35.39 ms per token, 28.26 tokens per second) 20.55.644.297 I slot print_timing: id 2 | task 26029 | total time = 10045.39 ms / 706 tokens 20.55.644.297 I slot print_timing: id 2 | task 26029 | graphs reused = 25224 20.55.644.298 I slot print_timing: id 2 | task 26029 | graph reallocs = 0 / 0 (same size) / (changed size) 20.55.644.373 I slot release: id 2 | task 26029 | stop processing: n_tokens = 1403, truncated = 0 20.58.282.528 I slot print_timing: id 1 | task 26004 | prompt eval time = 766.19 ms / 500 tokens ( 1.53 ms per token, 652.58 tokens per second) 20.58.282.531 I slot print_timing: id 1 | task 26004 | eval time = 13606.57 ms / 465 tokens ( 29.32 ms per token, 34.10 tokens per second) 20.58.282.532 I slot print_timing: id 1 | task 26004 | total time = 14372.76 ms / 965 tokens 20.58.282.532 I slot print_timing: id 1 | task 26004 | graphs reused = 25398 20.58.282.533 I slot print_timing: id 1 | task 26004 | graph reallocs = 0 / 0 (same size) / (changed size) 20.58.282.602 I slot release: id 1 | task 26004 | stop processing: n_tokens = 1651, truncated = 0 20.58.298.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2234, t_last = 336639393976 20.58.302.835 I slot launch_slot_: id 0 | task 26472 | processing task, is_child = 0 20.58.310.001 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1570, t_last = 336641406292 20.58.310.131 I slot launch_slot_: id 3 | task 26473 | processing task, is_child = 0 20.58.310.304 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1403, t_last = 336643012356 20.58.310.407 I slot launch_slot_: id 2 | task 26474 | processing task, is_child = 0 20.58.310.500 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1651, t_last = 336645650585 20.58.310.614 I slot launch_slot_: id 1 | task 26475 | processing task, is_child = 0 21.02.248.071 I slot print_timing: id 0 | task 26472 | prompt processing, n_tokens = 754, progress = 0.99, t = 3.94 s / 191.50 tokens per second 21.02.894.705 I slot print_timing: id 1 | task 26475 | prompt processing, n_tokens = 940, progress = 1.00, t = 3.94 s / 238.75 tokens per second 21.02.894.886 I slot print_timing: id 2 | task 26474 | prompt processing, n_tokens = 760, progress = 0.99, t = 3.94 s / 193.04 tokens per second 21.02.895.048 I slot print_timing: id 3 | task 26473 | prompt processing, n_tokens = 942, progress = 1.00, t = 3.94 s / 239.27 tokens per second 21.03.054.747 I slot print_timing: id 0 | task 26472 | prompt eval time = 4702.50 ms / 758 tokens ( 6.20 ms per token, 161.19 tokens per second) 21.03.054.749 I slot print_timing: id 0 | task 26472 | eval time = 41.62 ms / 2 tokens ( 41.62 ms per token, 24.03 tokens per second) 21.03.054.750 I slot print_timing: id 0 | task 26472 | total time = 4744.12 ms / 760 tokens 21.03.054.750 I slot print_timing: id 0 | task 26472 | graphs reused = 25400 21.03.054.750 I slot print_timing: id 0 | task 26472 | graph reallocs = 0 / 0 (same size) / (changed size) 21.03.054.792 I slot release: id 0 | task 26472 | stop processing: n_tokens = 759, truncated = 0 21.03.055.064 I slot print_timing: id 1 | task 26475 | prompt eval time = 4702.60 ms / 944 tokens ( 4.98 ms per token, 200.74 tokens per second) 21.03.055.067 I slot print_timing: id 1 | task 26475 | eval time = 41.64 ms / 2 tokens ( 41.64 ms per token, 24.01 tokens per second) 21.03.055.068 I slot print_timing: id 1 | task 26475 | total time = 4744.24 ms / 946 tokens 21.03.055.068 I slot print_timing: id 1 | task 26475 | graphs reused = 25400 21.03.055.068 I slot print_timing: id 1 | task 26475 | graph reallocs = 0 / 0 (same size) / (changed size) 21.03.055.116 I slot release: id 1 | task 26475 | stop processing: n_tokens = 945, truncated = 0 21.03.055.414 I slot print_timing: id 2 | task 26474 | prompt eval time = 4702.75 ms / 764 tokens ( 6.16 ms per token, 162.46 tokens per second) 21.03.055.416 I slot print_timing: id 2 | task 26474 | eval time = 41.69 ms / 2 tokens ( 41.69 ms per token, 23.99 tokens per second) 21.03.055.416 I slot print_timing: id 2 | task 26474 | total time = 4744.44 ms / 766 tokens 21.03.055.417 I slot print_timing: id 2 | task 26474 | graphs reused = 25400 21.03.055.417 I slot print_timing: id 2 | task 26474 | graph reallocs = 0 / 0 (same size) / (changed size) 21.03.055.451 I slot release: id 2 | task 26474 | stop processing: n_tokens = 765, truncated = 0 21.03.055.742 I slot print_timing: id 3 | task 26473 | prompt eval time = 4702.98 ms / 946 tokens ( 4.97 ms per token, 201.15 tokens per second) 21.03.055.749 I slot print_timing: id 3 | task 26473 | eval time = 41.68 ms / 2 tokens ( 41.68 ms per token, 23.99 tokens per second) 21.03.055.749 I slot print_timing: id 3 | task 26473 | total time = 4744.66 ms / 948 tokens 21.03.055.749 I slot print_timing: id 3 | task 26473 | graphs reused = 25400 21.03.055.750 I slot print_timing: id 3 | task 26473 | graph reallocs = 0 / 0 (same size) / (changed size) 21.03.055.791 I slot release: id 3 | task 26473 | stop processing: n_tokens = 947, truncated = 0 21.03.062.128 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 759, t_last = 336650422775 21.03.063.767 I slot launch_slot_: id 0 | task 26481 | processing task, is_child = 0 21.03.068.858 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 336650423099 21.03.068.926 I slot launch_slot_: id 1 | task 26480 | processing task, is_child = 0 21.03.069.014 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 765, t_last = 336650423434 21.03.069.068 I slot launch_slot_: id 2 | task 26483 | processing task, is_child = 0 21.03.069.113 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 947, t_last = 336650423774 21.03.069.173 I slot launch_slot_: id 3 | task 26482 | processing task, is_child = 0 21.06.572.811 I slot print_timing: id 0 | task 26481 | prompt processing, n_tokens = 768, progress = 0.99, t = 3.50 s / 219.20 tokens per second 21.07.216.917 I slot print_timing: id 1 | task 26480 | prompt processing, n_tokens = 772, progress = 0.99, t = 3.50 s / 220.35 tokens per second 21.07.217.065 I slot print_timing: id 2 | task 26483 | prompt processing, n_tokens = 821, progress = 1.00, t = 3.50 s / 234.34 tokens per second 21.07.217.218 I slot print_timing: id 3 | task 26482 | prompt processing, n_tokens = 816, progress = 1.00, t = 3.50 s / 232.91 tokens per second 21.07.377.372 I slot print_timing: id 0 | task 26481 | prompt eval time = 4266.84 ms / 772 tokens ( 5.53 ms per token, 180.93 tokens per second) 21.07.377.376 I slot print_timing: id 0 | task 26481 | eval time = 41.35 ms / 2 tokens ( 41.35 ms per token, 24.18 tokens per second) 21.07.377.377 I slot print_timing: id 0 | task 26481 | total time = 4308.19 ms / 774 tokens 21.07.377.377 I slot print_timing: id 0 | task 26481 | graphs reused = 25401 21.07.377.378 I slot print_timing: id 0 | task 26481 | graph reallocs = 0 / 0 (same size) / (changed size) 21.07.377.432 I slot release: id 0 | task 26481 | stop processing: n_tokens = 773, truncated = 0 21.07.377.693 I slot print_timing: id 1 | task 26480 | prompt eval time = 4267.06 ms / 776 tokens ( 5.50 ms per token, 181.86 tokens per second) 21.07.377.695 I slot print_timing: id 1 | task 26480 | eval time = 41.40 ms / 2 tokens ( 41.40 ms per token, 24.16 tokens per second) 21.07.377.696 I slot print_timing: id 1 | task 26480 | total time = 4308.46 ms / 778 tokens 21.07.377.696 I slot print_timing: id 1 | task 26480 | graphs reused = 25401 21.07.377.696 I slot print_timing: id 1 | task 26480 | graph reallocs = 0 / 0 (same size) / (changed size) 21.07.377.727 I slot release: id 1 | task 26480 | stop processing: n_tokens = 777, truncated = 0 21.07.378.007 I slot print_timing: id 2 | task 26483 | prompt eval time = 4267.30 ms / 825 tokens ( 5.17 ms per token, 193.33 tokens per second) 21.07.378.009 I slot print_timing: id 2 | task 26483 | eval time = 41.41 ms / 2 tokens ( 41.41 ms per token, 24.15 tokens per second) 21.07.378.009 I slot print_timing: id 2 | task 26483 | total time = 4308.71 ms / 827 tokens 21.07.378.009 I slot print_timing: id 2 | task 26483 | graphs reused = 25401 21.07.378.010 I slot print_timing: id 2 | task 26483 | graph reallocs = 0 / 0 (same size) / (changed size) 21.07.378.043 I slot release: id 2 | task 26483 | stop processing: n_tokens = 826, truncated = 0 21.07.378.343 I slot print_timing: id 3 | task 26482 | prompt eval time = 4267.58 ms / 820 tokens ( 5.20 ms per token, 192.15 tokens per second) 21.07.378.344 I slot print_timing: id 3 | task 26482 | eval time = 41.42 ms / 2 tokens ( 41.42 ms per token, 24.14 tokens per second) 21.07.378.345 I slot print_timing: id 3 | task 26482 | total time = 4309.00 ms / 822 tokens 21.07.378.345 I slot print_timing: id 3 | task 26482 | graphs reused = 25401 21.07.378.345 I slot print_timing: id 3 | task 26482 | graph reallocs = 0 / 0 (same size) / (changed size) 21.07.378.376 I slot release: id 3 | task 26482 | stop processing: n_tokens = 821, truncated = 0 21.07.384.985 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 336654745415 21.07.386.497 I slot launch_slot_: id 0 | task 26488 | processing task, is_child = 0 21.07.391.107 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 777, t_last = 336654745710 21.07.391.176 I slot launch_slot_: id 1 | task 26489 | processing task, is_child = 0 21.07.391.265 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.845 21.07.391.284 I slot launch_slot_: id 2 | task 26490 | processing task, is_child = 0 21.07.391.327 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 821, t_last = 336654746359 21.07.391.387 I slot launch_slot_: id 3 | task 26491 | processing task, is_child = 0 21.11.757.203 I slot print_timing: id 0 | task 26488 | prompt processing, n_tokens = 852, progress = 1.00, t = 4.37 s / 195.17 tokens per second 21.11.757.366 I slot print_timing: id 1 | task 26489 | prompt processing, n_tokens = 845, progress = 1.00, t = 4.37 s / 193.57 tokens per second 21.11.757.515 I slot print_timing: id 3 | task 26491 | prompt processing, n_tokens = 927, progress = 1.00, t = 4.37 s / 212.36 tokens per second 21.11.875.004 I slot print_timing: id 2 | task 26490 | prompt eval time = 4365.65 ms / 488 tokens ( 8.95 ms per token, 111.78 tokens per second) 21.11.875.007 I slot print_timing: id 2 | task 26490 | eval time = 117.81 ms / 2 tokens ( 117.81 ms per token, 8.49 tokens per second) 21.11.875.007 I slot print_timing: id 2 | task 26490 | total time = 4483.47 ms / 490 tokens 21.11.875.008 I slot print_timing: id 2 | task 26490 | graphs reused = 25401 21.11.875.008 I slot print_timing: id 2 | task 26490 | graph reallocs = 0 / 0 (same size) / (changed size) 21.11.875.056 I slot release: id 2 | task 26490 | stop processing: n_tokens = 798, truncated = 0 21.11.915.105 I slot print_timing: id 0 | task 26488 | prompt eval time = 4483.03 ms / 856 tokens ( 5.24 ms per token, 190.94 tokens per second) 21.11.915.107 I slot print_timing: id 0 | task 26488 | eval time = 40.68 ms / 2 tokens ( 40.68 ms per token, 24.58 tokens per second) 21.11.915.108 I slot print_timing: id 0 | task 26488 | total time = 4523.71 ms / 858 tokens 21.11.915.108 I slot print_timing: id 0 | task 26488 | graphs reused = 25401 21.11.915.108 I slot print_timing: id 0 | task 26488 | graph reallocs = 0 / 0 (same size) / (changed size) 21.11.915.179 I slot release: id 0 | task 26488 | stop processing: n_tokens = 857, truncated = 0 21.11.915.470 I slot print_timing: id 1 | task 26489 | prompt eval time = 4483.25 ms / 849 tokens ( 5.28 ms per token, 189.37 tokens per second) 21.11.915.472 I slot print_timing: id 1 | task 26489 | eval time = 40.76 ms / 2 tokens ( 40.76 ms per token, 24.53 tokens per second) 21.11.915.473 I slot print_timing: id 1 | task 26489 | total time = 4524.01 ms / 851 tokens 21.11.915.473 I slot print_timing: id 1 | task 26489 | graphs reused = 25401 21.11.915.473 I slot print_timing: id 1 | task 26489 | graph reallocs = 0 / 0 (same size) / (changed size) 21.11.915.512 I slot release: id 1 | task 26489 | stop processing: n_tokens = 850, truncated = 0 21.11.915.793 I slot print_timing: id 3 | task 26491 | prompt eval time = 4483.82 ms / 931 tokens ( 4.82 ms per token, 207.64 tokens per second) 21.11.915.795 I slot print_timing: id 3 | task 26491 | eval time = 40.32 ms / 2 tokens ( 40.32 ms per token, 24.80 tokens per second) 21.11.915.795 I slot print_timing: id 3 | task 26491 | total time = 4524.15 ms / 933 tokens 21.11.915.796 I slot print_timing: id 3 | task 26491 | graphs reused = 25401 21.11.915.796 I slot print_timing: id 3 | task 26491 | graph reallocs = 0 / 0 (same size) / (changed size) 21.11.915.840 I slot release: id 3 | task 26491 | stop processing: n_tokens = 932, truncated = 0 21.11.915.844 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 798, t_last = 336659243039 21.11.917.773 I slot launch_slot_: id 2 | task 26496 | processing task, is_child = 0 21.11.922.762 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 857, t_last = 336659283162 21.11.922.838 I slot launch_slot_: id 0 | task 26497 | processing task, is_child = 0 21.11.922.930 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 336659283495 21.11.922.989 I slot launch_slot_: id 1 | task 26498 | processing task, is_child = 0 21.11.923.033 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 336659283823 21.11.923.091 I slot launch_slot_: id 3 | task 26499 | processing task, is_child = 0 21.17.150.174 I slot print_timing: id 0 | task 26497 | prompt processing, n_tokens = 887, progress = 1.00, t = 5.23 s / 169.69 tokens per second 21.17.442.484 I slot print_timing: id 1 | task 26498 | prompt processing, n_tokens = 985, progress = 1.00, t = 5.23 s / 188.44 tokens per second 21.17.442.659 I slot print_timing: id 2 | task 26496 | prompt processing, n_tokens = 950, progress = 1.00, t = 5.23 s / 181.75 tokens per second 21.17.442.823 I slot print_timing: id 3 | task 26499 | prompt processing, n_tokens = 1226, progress = 0.70, t = 5.23 s / 234.56 tokens per second 21.18.219.098 I slot print_timing: id 3 | task 26499 | prompt processing, n_tokens = 1738, progress = 1.00, t = 6.29 s / 276.10 tokens per second 21.18.290.379 I slot print_timing: id 0 | task 26497 | prompt eval time = 6295.40 ms / 891 tokens ( 7.07 ms per token, 141.53 tokens per second) 21.18.290.383 I slot print_timing: id 0 | task 26497 | eval time = 71.88 ms / 2 tokens ( 71.88 ms per token, 13.91 tokens per second) 21.18.290.384 I slot print_timing: id 0 | task 26497 | total time = 6367.28 ms / 893 tokens 21.18.290.384 I slot print_timing: id 0 | task 26497 | graphs reused = 25402 21.18.290.385 I slot print_timing: id 0 | task 26497 | graph reallocs = 0 / 0 (same size) / (changed size) 21.18.290.439 I slot release: id 0 | task 26497 | stop processing: n_tokens = 892, truncated = 0 21.18.290.721 I slot print_timing: id 1 | task 26498 | prompt eval time = 6295.63 ms / 989 tokens ( 6.37 ms per token, 157.09 tokens per second) 21.18.290.723 I slot print_timing: id 1 | task 26498 | eval time = 71.93 ms / 2 tokens ( 71.93 ms per token, 13.90 tokens per second) 21.18.290.724 I slot print_timing: id 1 | task 26498 | total time = 6367.55 ms / 991 tokens 21.18.290.724 I slot print_timing: id 1 | task 26498 | graphs reused = 25402 21.18.290.724 I slot print_timing: id 1 | task 26498 | graph reallocs = 0 / 0 (same size) / (changed size) 21.18.290.776 I slot release: id 1 | task 26498 | stop processing: n_tokens = 990, truncated = 0 21.18.291.053 I slot print_timing: id 2 | task 26496 | prompt eval time = 6295.85 ms / 954 tokens ( 6.60 ms per token, 151.53 tokens per second) 21.18.291.055 I slot print_timing: id 2 | task 26496 | eval time = 71.96 ms / 2 tokens ( 71.96 ms per token, 13.90 tokens per second) 21.18.291.055 I slot print_timing: id 2 | task 26496 | total time = 6367.81 ms / 956 tokens 21.18.291.056 I slot print_timing: id 2 | task 26496 | graphs reused = 25402 21.18.291.056 I slot print_timing: id 2 | task 26496 | graph reallocs = 0 / 0 (same size) / (changed size) 21.18.291.090 I slot release: id 2 | task 26496 | stop processing: n_tokens = 955, truncated = 0 21.18.308.136 I slot print_timing: id 3 | task 26499 | prompt eval time = 6368.21 ms / 1742 tokens ( 3.66 ms per token, 273.55 tokens per second) 21.18.308.138 I slot print_timing: id 3 | task 26499 | eval time = 16.62 ms / 2 tokens ( 16.62 ms per token, 60.18 tokens per second) 21.18.308.138 I slot print_timing: id 3 | task 26499 | total time = 6384.83 ms / 1744 tokens 21.18.308.139 I slot print_timing: id 3 | task 26499 | graphs reused = 25402 21.18.308.139 I slot print_timing: id 3 | task 26499 | graph reallocs = 0 / 0 (same size) / (changed size) 21.18.308.229 I slot release: id 3 | task 26499 | stop processing: n_tokens = 1743, truncated = 0 21.18.308.235 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 892, t_last = 336665658423 21.18.310.195 I slot launch_slot_: id 0 | task 26505 | processing task, is_child = 0 21.18.317.530 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 990, t_last = 336665658759 21.18.317.600 I slot launch_slot_: id 1 | task 26506 | processing task, is_child = 0 21.18.317.715 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.828 (> 0.100 thold), f_keep = 0.431 21.18.317.805 I slot launch_slot_: id 3 | task 26507 | processing task, is_child = 0 21.18.317.850 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 955, t_last = 336665659073 21.18.317.913 I slot launch_slot_: id 2 | task 26508 | processing task, is_child = 0 21.22.086.486 I slot print_timing: id 0 | task 26505 | prompt processing, n_tokens = 858, progress = 1.00, t = 3.77 s / 227.67 tokens per second 21.22.730.172 I slot print_timing: id 1 | task 26506 | prompt processing, n_tokens = 723, progress = 0.99, t = 3.77 s / 191.85 tokens per second 21.22.730.330 I slot print_timing: id 2 | task 26508 | prompt processing, n_tokens = 696, progress = 0.99, t = 3.77 s / 184.69 tokens per second 21.22.730.463 I slot print_timing: id 3 | task 26507 | prompt processing, n_tokens = 904, progress = 1.00, t = 3.77 s / 239.89 tokens per second 21.22.890.814 I slot print_timing: id 0 | task 26505 | prompt eval time = 4531.38 ms / 862 tokens ( 5.26 ms per token, 190.23 tokens per second) 21.22.890.816 I slot print_timing: id 0 | task 26505 | eval time = 41.52 ms / 2 tokens ( 41.52 ms per token, 24.09 tokens per second) 21.22.890.816 I slot print_timing: id 0 | task 26505 | total time = 4572.89 ms / 864 tokens 21.22.890.817 I slot print_timing: id 0 | task 26505 | graphs reused = 25404 21.22.890.817 I slot print_timing: id 0 | task 26505 | graph reallocs = 0 / 0 (same size) / (changed size) 21.22.890.868 I slot release: id 0 | task 26505 | stop processing: n_tokens = 863, truncated = 0 21.22.891.139 I slot print_timing: id 1 | task 26506 | prompt eval time = 4531.59 ms / 727 tokens ( 6.23 ms per token, 160.43 tokens per second) 21.22.891.141 I slot print_timing: id 1 | task 26506 | eval time = 41.56 ms / 2 tokens ( 41.56 ms per token, 24.06 tokens per second) 21.22.891.141 I slot print_timing: id 1 | task 26506 | total time = 4573.15 ms / 729 tokens 21.22.891.141 I slot print_timing: id 1 | task 26506 | graphs reused = 25404 21.22.891.142 I slot print_timing: id 1 | task 26506 | graph reallocs = 0 / 0 (same size) / (changed size) 21.22.891.175 I slot release: id 1 | task 26506 | stop processing: n_tokens = 728, truncated = 0 21.22.891.448 I slot print_timing: id 2 | task 26508 | prompt eval time = 4531.80 ms / 700 tokens ( 6.47 ms per token, 154.46 tokens per second) 21.22.891.449 I slot print_timing: id 2 | task 26508 | eval time = 41.59 ms / 2 tokens ( 41.59 ms per token, 24.04 tokens per second) 21.22.891.450 I slot print_timing: id 2 | task 26508 | total time = 4573.39 ms / 702 tokens 21.22.891.451 I slot print_timing: id 2 | task 26508 | graphs reused = 25404 21.22.891.451 I slot print_timing: id 2 | task 26508 | graph reallocs = 0 / 0 (same size) / (changed size) 21.22.891.483 I slot release: id 2 | task 26508 | stop processing: n_tokens = 701, truncated = 0 21.22.891.775 I slot print_timing: id 3 | task 26507 | prompt eval time = 4532.19 ms / 908 tokens ( 4.99 ms per token, 200.34 tokens per second) 21.22.891.777 I slot print_timing: id 3 | task 26507 | eval time = 41.47 ms / 2 tokens ( 41.47 ms per token, 24.11 tokens per second) 21.22.891.778 I slot print_timing: id 3 | task 26507 | total time = 4573.66 ms / 910 tokens 21.22.891.778 I slot print_timing: id 3 | task 26507 | graphs reused = 25404 21.22.891.778 I slot print_timing: id 3 | task 26507 | graph reallocs = 0 / 0 (same size) / (changed size) 21.22.891.838 I slot release: id 3 | task 26507 | stop processing: n_tokens = 909, truncated = 0 21.22.898.249 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.848 21.22.898.277 I slot launch_slot_: id 1 | task 26514 | processing task, is_child = 0 21.22.902.713 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.880 21.22.902.733 I slot launch_slot_: id 2 | task 26513 | processing task, is_child = 0 21.22.902.817 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 336670258852 21.22.902.876 I slot launch_slot_: id 0 | task 26515 | processing task, is_child = 0 21.22.902.920 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 909, t_last = 336670259823 21.22.903.424 I slot launch_slot_: id 3 | task 26516 | processing task, is_child = 0 21.26.350.684 I slot print_timing: id 0 | task 26515 | prompt processing, n_tokens = 824, progress = 1.00, t = 3.45 s / 239.05 tokens per second 21.26.350.847 I slot print_timing: id 2 | task 26513 | prompt processing, n_tokens = 520, progress = 0.99, t = 3.45 s / 150.87 tokens per second 21.26.350.981 I slot print_timing: id 3 | task 26516 | prompt processing, n_tokens = 518, progress = 0.99, t = 3.45 s / 150.29 tokens per second 21.26.469.581 I slot print_timing: id 1 | task 26514 | prompt eval time = 3447.18 ms / 493 tokens ( 6.99 ms per token, 143.02 tokens per second) 21.26.469.584 I slot print_timing: id 1 | task 26514 | eval time = 118.91 ms / 2 tokens ( 118.91 ms per token, 8.41 tokens per second) 21.26.469.584 I slot print_timing: id 1 | task 26514 | total time = 3566.09 ms / 495 tokens 21.26.469.584 I slot print_timing: id 1 | task 26514 | graphs reused = 25404 21.26.469.585 I slot print_timing: id 1 | task 26514 | graph reallocs = 0 / 0 (same size) / (changed size) 21.26.469.630 I slot release: id 1 | task 26514 | stop processing: n_tokens = 705, truncated = 0 21.26.510.229 I slot print_timing: id 0 | task 26515 | prompt eval time = 3565.89 ms / 828 tokens ( 4.31 ms per token, 232.20 tokens per second) 21.26.510.231 I slot print_timing: id 0 | task 26515 | eval time = 40.90 ms / 2 tokens ( 40.90 ms per token, 24.45 tokens per second) 21.26.510.231 I slot print_timing: id 0 | task 26515 | total time = 3606.79 ms / 830 tokens 21.26.510.231 I slot print_timing: id 0 | task 26515 | graphs reused = 25404 21.26.510.232 I slot print_timing: id 0 | task 26515 | graph reallocs = 0 / 0 (same size) / (changed size) 21.26.510.275 I slot release: id 0 | task 26515 | stop processing: n_tokens = 829, truncated = 0 21.26.510.529 I slot print_timing: id 2 | task 26513 | prompt eval time = 3566.30 ms / 524 tokens ( 6.81 ms per token, 146.93 tokens per second) 21.26.510.536 I slot print_timing: id 2 | task 26513 | eval time = 40.62 ms / 2 tokens ( 40.62 ms per token, 24.62 tokens per second) 21.26.510.536 I slot print_timing: id 2 | task 26513 | total time = 3606.92 ms / 526 tokens 21.26.510.536 I slot print_timing: id 2 | task 26513 | graphs reused = 25404 21.26.510.537 I slot print_timing: id 2 | task 26513 | graph reallocs = 0 / 0 (same size) / (changed size) 21.26.510.579 I slot release: id 2 | task 26513 | stop processing: n_tokens = 709, truncated = 0 21.26.510.858 I slot print_timing: id 3 | task 26516 | prompt eval time = 3566.53 ms / 522 tokens ( 6.83 ms per token, 146.36 tokens per second) 21.26.510.860 I slot print_timing: id 3 | task 26516 | eval time = 40.65 ms / 2 tokens ( 40.65 ms per token, 24.60 tokens per second) 21.26.510.861 I slot print_timing: id 3 | task 26516 | total time = 3607.18 ms / 524 tokens 21.26.510.861 I slot print_timing: id 3 | task 26516 | graphs reused = 25404 21.26.510.861 I slot print_timing: id 3 | task 26516 | graph reallocs = 0 / 0 (same size) / (changed size) 21.26.510.895 I slot release: id 3 | task 26516 | stop processing: n_tokens = 707, truncated = 0 21.26.510.898 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 705, t_last = 336673837613 21.26.512.490 I slot launch_slot_: id 1 | task 26521 | processing task, is_child = 0 21.26.517.205 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 829, t_last = 336673878258 21.26.517.283 I slot launch_slot_: id 0 | task 26522 | processing task, is_child = 0 21.26.517.359 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 709, t_last = 336673878562 21.26.517.420 I slot launch_slot_: id 2 | task 26523 | processing task, is_child = 0 21.26.517.458 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 336673878878 21.26.517.510 I slot launch_slot_: id 3 | task 26524 | processing task, is_child = 0 21.30.841.672 I slot print_timing: id 0 | task 26522 | prompt processing, n_tokens = 958, progress = 1.00, t = 4.32 s / 221.55 tokens per second 21.31.489.236 I slot print_timing: id 1 | task 26521 | prompt processing, n_tokens = 913, progress = 1.00, t = 4.32 s / 211.14 tokens per second 21.31.489.411 I slot print_timing: id 2 | task 26523 | prompt processing, n_tokens = 922, progress = 1.00, t = 4.32 s / 213.23 tokens per second 21.31.489.577 I slot print_timing: id 3 | task 26524 | prompt processing, n_tokens = 932, progress = 1.00, t = 4.32 s / 215.54 tokens per second 21.31.650.000 I slot print_timing: id 0 | task 26522 | prompt eval time = 5090.90 ms / 962 tokens ( 5.29 ms per token, 188.96 tokens per second) 21.31.650.002 I slot print_timing: id 0 | task 26522 | eval time = 41.59 ms / 2 tokens ( 41.59 ms per token, 24.04 tokens per second) 21.31.650.003 I slot print_timing: id 0 | task 26522 | total time = 5132.48 ms / 964 tokens 21.31.650.003 I slot print_timing: id 0 | task 26522 | graphs reused = 25406 21.31.650.004 I slot print_timing: id 0 | task 26522 | graph reallocs = 0 / 0 (same size) / (changed size) 21.31.650.057 I slot release: id 0 | task 26522 | stop processing: n_tokens = 963, truncated = 0 21.31.650.330 I slot print_timing: id 1 | task 26521 | prompt eval time = 5091.10 ms / 917 tokens ( 5.55 ms per token, 180.12 tokens per second) 21.31.650.332 I slot print_timing: id 1 | task 26521 | eval time = 41.65 ms / 2 tokens ( 41.65 ms per token, 24.01 tokens per second) 21.31.650.333 I slot print_timing: id 1 | task 26521 | total time = 5132.74 ms / 919 tokens 21.31.650.333 I slot print_timing: id 1 | task 26521 | graphs reused = 25406 21.31.650.333 I slot print_timing: id 1 | task 26521 | graph reallocs = 0 / 0 (same size) / (changed size) 21.31.650.377 I slot release: id 1 | task 26521 | stop processing: n_tokens = 918, truncated = 0 21.31.650.666 I slot print_timing: id 2 | task 26523 | prompt eval time = 5091.35 ms / 926 tokens ( 5.50 ms per token, 181.88 tokens per second) 21.31.650.667 I slot print_timing: id 2 | task 26523 | eval time = 41.68 ms / 2 tokens ( 41.68 ms per token, 23.99 tokens per second) 21.31.650.668 I slot print_timing: id 2 | task 26523 | total time = 5133.03 ms / 928 tokens 21.31.650.668 I slot print_timing: id 2 | task 26523 | graphs reused = 25406 21.31.650.668 I slot print_timing: id 2 | task 26523 | graph reallocs = 0 / 0 (same size) / (changed size) 21.31.650.703 I slot release: id 2 | task 26523 | stop processing: n_tokens = 927, truncated = 0 21.31.650.991 I slot print_timing: id 3 | task 26524 | prompt eval time = 5091.69 ms / 936 tokens ( 5.44 ms per token, 183.83 tokens per second) 21.31.650.997 I slot print_timing: id 3 | task 26524 | eval time = 41.61 ms / 2 tokens ( 41.61 ms per token, 24.03 tokens per second) 21.31.650.998 I slot print_timing: id 3 | task 26524 | total time = 5133.30 ms / 938 tokens 21.31.650.998 I slot print_timing: id 3 | task 26524 | graphs reused = 25406 21.31.650.998 I slot print_timing: id 3 | task 26524 | graph reallocs = 0 / 0 (same size) / (changed size) 21.31.651.037 I slot release: id 3 | task 26524 | stop processing: n_tokens = 937, truncated = 0 21.31.657.583 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 963, t_last = 336679018040 21.31.659.498 I slot launch_slot_: id 0 | task 26529 | processing task, is_child = 0 21.31.664.805 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.898 21.31.664.826 I slot launch_slot_: id 1 | task 26530 | processing task, is_child = 0 21.31.664.913 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 927, t_last = 336679018686 21.31.664.975 I slot launch_slot_: id 2 | task 26531 | processing task, is_child = 0 21.31.665.020 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 937, t_last = 336679019020 21.31.665.083 I slot launch_slot_: id 3 | task 26532 | processing task, is_child = 0 21.35.461.002 I slot print_timing: id 0 | task 26529 | prompt processing, n_tokens = 817, progress = 1.00, t = 3.80 s / 215.23 tokens per second 21.36.106.555 I slot print_timing: id 1 | task 26530 | prompt processing, n_tokens = 519, progress = 1.00, t = 3.80 s / 136.73 tokens per second 21.36.106.729 I slot print_timing: id 2 | task 26531 | prompt processing, n_tokens = 882, progress = 1.00, t = 3.80 s / 232.36 tokens per second 21.36.106.892 I slot print_timing: id 3 | task 26532 | prompt processing, n_tokens = 996, progress = 1.00, t = 3.80 s / 262.40 tokens per second 21.36.267.206 I slot print_timing: id 0 | task 26529 | prompt eval time = 4560.71 ms / 821 tokens ( 5.56 ms per token, 180.02 tokens per second) 21.36.267.208 I slot print_timing: id 0 | task 26529 | eval time = 41.40 ms / 2 tokens ( 41.40 ms per token, 24.15 tokens per second) 21.36.267.208 I slot print_timing: id 0 | task 26529 | total time = 4602.11 ms / 823 tokens 21.36.267.209 I slot print_timing: id 0 | task 26529 | graphs reused = 25408 21.36.267.209 I slot print_timing: id 0 | task 26529 | graph reallocs = 0 / 0 (same size) / (changed size) 21.36.267.255 I slot release: id 0 | task 26529 | stop processing: n_tokens = 822, truncated = 0 21.36.267.515 I slot print_timing: id 1 | task 26530 | prompt eval time = 4560.93 ms / 523 tokens ( 8.72 ms per token, 114.67 tokens per second) 21.36.267.517 I slot print_timing: id 1 | task 26530 | eval time = 41.44 ms / 2 tokens ( 41.44 ms per token, 24.13 tokens per second) 21.36.267.517 I slot print_timing: id 1 | task 26530 | total time = 4602.36 ms / 525 tokens 21.36.267.518 I slot print_timing: id 1 | task 26530 | graphs reused = 25408 21.36.267.518 I slot print_timing: id 1 | task 26530 | graph reallocs = 0 / 0 (same size) / (changed size) 21.36.267.561 I slot release: id 1 | task 26530 | stop processing: n_tokens = 925, truncated = 0 21.36.267.827 I slot print_timing: id 2 | task 26531 | prompt eval time = 4561.13 ms / 886 tokens ( 5.15 ms per token, 194.25 tokens per second) 21.36.267.829 I slot print_timing: id 2 | task 26531 | eval time = 41.47 ms / 2 tokens ( 41.47 ms per token, 24.11 tokens per second) 21.36.267.830 I slot print_timing: id 2 | task 26531 | total time = 4602.60 ms / 888 tokens 21.36.267.830 I slot print_timing: id 2 | task 26531 | graphs reused = 25408 21.36.267.830 I slot print_timing: id 2 | task 26531 | graph reallocs = 0 / 0 (same size) / (changed size) 21.36.267.869 I slot release: id 2 | task 26531 | stop processing: n_tokens = 887, truncated = 0 21.36.268.145 I slot print_timing: id 3 | task 26532 | prompt eval time = 4561.48 ms / 1000 tokens ( 4.56 ms per token, 219.23 tokens per second) 21.36.268.147 I slot print_timing: id 3 | task 26532 | eval time = 41.38 ms / 2 tokens ( 41.38 ms per token, 24.17 tokens per second) 21.36.268.147 I slot print_timing: id 3 | task 26532 | total time = 4602.86 ms / 1002 tokens 21.36.268.147 I slot print_timing: id 3 | task 26532 | graphs reused = 25408 21.36.268.147 I slot print_timing: id 3 | task 26532 | graph reallocs = 0 / 0 (same size) / (changed size) 21.36.268.195 I slot release: id 3 | task 26532 | stop processing: n_tokens = 1001, truncated = 0 21.36.274.721 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.892 21.36.274.747 I slot launch_slot_: id 2 | task 26537 | processing task, is_child = 0 21.36.280.226 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.790 21.36.280.254 I slot launch_slot_: id 3 | task 26538 | processing task, is_child = 0 21.36.280.341 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 822, t_last = 336683635238 21.36.281.115 I slot launch_slot_: id 0 | task 26539 | processing task, is_child = 0 21.36.281.169 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 336683635545 21.36.281.236 I slot launch_slot_: id 1 | task 26540 | processing task, is_child = 0 21.39.639.492 I slot print_timing: id 1 | task 26540 | prompt processing, n_tokens = 868, progress = 1.00, t = 3.36 s / 258.52 tokens per second 21.39.639.651 I slot print_timing: id 2 | task 26537 | prompt processing, n_tokens = 514, progress = 1.00, t = 3.36 s / 153.09 tokens per second 21.39.737.094 I slot print_timing: id 0 | task 26539 | prompt eval time = 3357.94 ms / 506 tokens ( 6.64 ms per token, 150.69 tokens per second) 21.39.737.096 I slot print_timing: id 0 | task 26539 | eval time = 97.91 ms / 2 tokens ( 97.91 ms per token, 10.21 tokens per second) 21.39.737.097 I slot print_timing: id 0 | task 26539 | total time = 3455.85 ms / 508 tokens 21.39.737.097 I slot print_timing: id 0 | task 26539 | graphs reused = 25408 21.39.737.098 I slot print_timing: id 0 | task 26539 | graph reallocs = 0 / 0 (same size) / (changed size) 21.39.737.156 I slot release: id 0 | task 26539 | stop processing: n_tokens = 991, truncated = 0 21.39.738.209 I slot print_timing: id 3 | task 26538 | prompt eval time = 3358.00 ms / 477 tokens ( 7.04 ms per token, 142.05 tokens per second) 21.39.738.211 I slot print_timing: id 3 | task 26538 | eval time = 98.73 ms / 2 tokens ( 98.73 ms per token, 10.13 tokens per second) 21.39.738.211 I slot print_timing: id 3 | task 26538 | total time = 3456.72 ms / 479 tokens 21.39.738.211 I slot print_timing: id 3 | task 26538 | graphs reused = 25408 21.39.738.212 I slot print_timing: id 3 | task 26538 | graph reallocs = 0 / 0 (same size) / (changed size) 21.39.738.269 I slot release: id 3 | task 26538 | stop processing: n_tokens = 962, truncated = 0 21.39.762.918 I slot print_timing: id 1 | task 26540 | prompt eval time = 3456.10 ms / 872 tokens ( 3.96 ms per token, 252.31 tokens per second) 21.39.762.921 I slot print_timing: id 1 | task 26540 | eval time = 25.46 ms / 2 tokens ( 25.46 ms per token, 39.27 tokens per second) 21.39.762.922 I slot print_timing: id 1 | task 26540 | total time = 3481.57 ms / 874 tokens 21.39.762.922 I slot print_timing: id 1 | task 26540 | graphs reused = 25408 21.39.762.923 I slot print_timing: id 1 | task 26540 | graph reallocs = 0 / 0 (same size) / (changed size) 21.39.762.963 I slot release: id 1 | task 26540 | stop processing: n_tokens = 873, truncated = 0 21.39.763.236 I slot print_timing: id 2 | task 26537 | prompt eval time = 3456.47 ms / 518 tokens ( 6.67 ms per token, 149.86 tokens per second) 21.39.763.238 I slot print_timing: id 2 | task 26537 | eval time = 25.36 ms / 2 tokens ( 25.36 ms per token, 39.43 tokens per second) 21.39.763.238 I slot print_timing: id 2 | task 26537 | total time = 3481.83 ms / 520 tokens 21.39.763.239 I slot print_timing: id 2 | task 26537 | graphs reused = 25408 21.39.763.239 I slot print_timing: id 2 | task 26537 | graph reallocs = 0 / 0 (same size) / (changed size) 21.39.763.279 I slot release: id 2 | task 26537 | stop processing: n_tokens = 889, truncated = 0 21.39.763.283 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 336687105140 21.39.764.208 I slot launch_slot_: id 0 | task 26545 | processing task, is_child = 0 21.39.769.935 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 336687106253 21.39.770.015 I slot launch_slot_: id 3 | task 26546 | processing task, is_child = 0 21.39.770.104 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 336687130947 21.39.770.166 I slot launch_slot_: id 1 | task 26547 | processing task, is_child = 0 21.39.770.210 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 336687131262 21.39.770.272 I slot launch_slot_: id 2 | task 26548 | processing task, is_child = 0 21.44.407.182 I slot print_timing: id 0 | task 26545 | prompt processing, n_tokens = 865, progress = 1.00, t = 4.64 s / 186.55 tokens per second 21.45.056.189 I slot print_timing: id 1 | task 26547 | prompt processing, n_tokens = 899, progress = 1.00, t = 4.64 s / 193.88 tokens per second 21.45.056.402 I slot print_timing: id 2 | task 26548 | prompt processing, n_tokens = 1276, progress = 1.00, t = 4.64 s / 275.19 tokens per second 21.45.056.673 I slot print_timing: id 3 | task 26546 | prompt processing, n_tokens = 906, progress = 1.00, t = 4.64 s / 195.40 tokens per second 21.45.217.580 I slot print_timing: id 0 | task 26545 | prompt eval time = 5405.29 ms / 869 tokens ( 6.22 ms per token, 160.77 tokens per second) 21.45.217.583 I slot print_timing: id 0 | task 26545 | eval time = 42.01 ms / 2 tokens ( 42.01 ms per token, 23.80 tokens per second) 21.45.217.583 I slot print_timing: id 0 | task 26545 | total time = 5447.30 ms / 871 tokens 21.45.217.584 I slot print_timing: id 0 | task 26545 | graphs reused = 25410 21.45.217.584 I slot print_timing: id 0 | task 26545 | graph reallocs = 0 / 0 (same size) / (changed size) 21.45.217.639 I slot release: id 0 | task 26545 | stop processing: n_tokens = 870, truncated = 0 21.45.217.927 I slot print_timing: id 1 | task 26547 | prompt eval time = 5405.58 ms / 903 tokens ( 5.99 ms per token, 167.05 tokens per second) 21.45.217.929 I slot print_timing: id 1 | task 26547 | eval time = 41.99 ms / 2 tokens ( 41.99 ms per token, 23.82 tokens per second) 21.45.217.930 I slot print_timing: id 1 | task 26547 | total time = 5447.57 ms / 905 tokens 21.45.217.930 I slot print_timing: id 1 | task 26547 | graphs reused = 25410 21.45.217.930 I slot print_timing: id 1 | task 26547 | graph reallocs = 0 / 0 (same size) / (changed size) 21.45.217.979 I slot release: id 1 | task 26547 | stop processing: n_tokens = 904, truncated = 0 21.45.218.260 I slot print_timing: id 2 | task 26548 | prompt eval time = 5405.96 ms / 1280 tokens ( 4.22 ms per token, 236.78 tokens per second) 21.45.218.262 I slot print_timing: id 2 | task 26548 | eval time = 41.88 ms / 2 tokens ( 41.88 ms per token, 23.88 tokens per second) 21.45.218.263 I slot print_timing: id 2 | task 26548 | total time = 5447.84 ms / 1282 tokens 21.45.218.263 I slot print_timing: id 2 | task 26548 | graphs reused = 25410 21.45.218.263 I slot print_timing: id 2 | task 26548 | graph reallocs = 0 / 0 (same size) / (changed size) 21.45.218.320 I slot release: id 2 | task 26548 | stop processing: n_tokens = 1281, truncated = 0 21.45.218.596 I slot print_timing: id 3 | task 26546 | prompt eval time = 5406.38 ms / 910 tokens ( 5.94 ms per token, 168.32 tokens per second) 21.45.218.599 I slot print_timing: id 3 | task 26546 | eval time = 41.73 ms / 2 tokens ( 41.73 ms per token, 23.96 tokens per second) 21.45.218.600 I slot print_timing: id 3 | task 26546 | total time = 5448.11 ms / 912 tokens 21.45.218.600 I slot print_timing: id 3 | task 26546 | graphs reused = 25410 21.45.218.600 I slot print_timing: id 3 | task 26546 | graph reallocs = 0 / 0 (same size) / (changed size) 21.45.218.634 I slot release: id 3 | task 26546 | stop processing: n_tokens = 911, truncated = 0 21.45.225.279 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 870, t_last = 336692585622 21.45.227.026 I slot launch_slot_: id 0 | task 26553 | processing task, is_child = 0 21.45.232.615 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.877 21.45.232.636 I slot launch_slot_: id 2 | task 26555 | processing task, is_child = 0 21.45.232.723 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 336692585962 21.45.233.576 I slot launch_slot_: id 1 | task 26554 | processing task, is_child = 0 21.45.233.626 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 336692586617 21.45.233.688 I slot launch_slot_: id 3 | task 26556 | processing task, is_child = 0 21.49.473.830 I slot print_timing: id 0 | task 26553 | prompt processing, n_tokens = 763, progress = 0.99, t = 4.24 s / 179.97 tokens per second 21.49.473.987 I slot print_timing: id 3 | task 26556 | prompt processing, n_tokens = 1283, progress = 1.00, t = 4.24 s / 302.65 tokens per second 21.49.573.685 I slot print_timing: id 1 | task 26554 | prompt eval time = 4239.75 ms / 439 tokens ( 9.66 ms per token, 103.54 tokens per second) 21.49.573.687 I slot print_timing: id 1 | task 26554 | eval time = 100.18 ms / 2 tokens ( 100.18 ms per token, 9.98 tokens per second) 21.49.573.687 I slot print_timing: id 1 | task 26554 | total time = 4339.93 ms / 441 tokens 21.49.573.688 I slot print_timing: id 1 | task 26554 | graphs reused = 25410 21.49.573.688 I slot print_timing: id 1 | task 26554 | graph reallocs = 0 / 0 (same size) / (changed size) 21.49.573.752 I slot release: id 1 | task 26554 | stop processing: n_tokens = 1204, truncated = 0 21.49.574.028 I slot print_timing: id 2 | task 26555 | prompt eval time = 4239.95 ms / 476 tokens ( 8.91 ms per token, 112.27 tokens per second) 21.49.574.038 I slot print_timing: id 2 | task 26555 | eval time = 100.21 ms / 2 tokens ( 100.21 ms per token, 9.98 tokens per second) 21.49.574.039 I slot print_timing: id 2 | task 26555 | total time = 4340.16 ms / 478 tokens 21.49.574.039 I slot print_timing: id 2 | task 26555 | graphs reused = 25410 21.49.574.039 I slot print_timing: id 2 | task 26555 | graph reallocs = 0 / 0 (same size) / (changed size) 21.49.574.090 I slot release: id 2 | task 26555 | stop processing: n_tokens = 1241, truncated = 0 21.49.606.294 I slot print_timing: id 0 | task 26553 | prompt eval time = 4339.73 ms / 767 tokens ( 5.66 ms per token, 176.74 tokens per second) 21.49.606.296 I slot print_timing: id 0 | task 26553 | eval time = 32.87 ms / 2 tokens ( 32.87 ms per token, 30.43 tokens per second) 21.49.606.297 I slot print_timing: id 0 | task 26553 | total time = 4372.60 ms / 769 tokens 21.49.606.297 I slot print_timing: id 0 | task 26553 | graphs reused = 25410 21.49.606.297 I slot print_timing: id 0 | task 26553 | graph reallocs = 0 / 0 (same size) / (changed size) 21.49.606.343 I slot release: id 0 | task 26553 | stop processing: n_tokens = 768, truncated = 0 21.49.606.624 I slot print_timing: id 3 | task 26556 | prompt eval time = 4340.56 ms / 1287 tokens ( 3.37 ms per token, 296.51 tokens per second) 21.49.606.627 I slot print_timing: id 3 | task 26556 | eval time = 32.10 ms / 2 tokens ( 32.10 ms per token, 31.15 tokens per second) 21.49.606.627 I slot print_timing: id 3 | task 26556 | total time = 4372.66 ms / 1289 tokens 21.49.606.627 I slot print_timing: id 3 | task 26556 | graphs reused = 25410 21.49.606.628 I slot print_timing: id 3 | task 26556 | graph reallocs = 0 / 0 (same size) / (changed size) 21.49.606.678 I slot release: id 3 | task 26556 | stop processing: n_tokens = 1288, truncated = 0 21.49.606.682 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.872 (> 0.100 thold), f_keep = 0.889 21.49.606.706 I slot launch_slot_: id 0 | task 26561 | processing task, is_child = 0 21.49.612.736 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1204, t_last = 336696941736 21.49.612.828 I slot launch_slot_: id 1 | task 26562 | processing task, is_child = 0 21.49.612.942 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1241, t_last = 336696942073 21.49.613.020 I slot launch_slot_: id 2 | task 26563 | processing task, is_child = 0 21.49.613.076 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1288, t_last = 336696974661 21.49.613.150 I slot launch_slot_: id 3 | task 26564 | processing task, is_child = 0 21.53.235.349 I slot print_timing: id 0 | task 26561 | prompt processing, n_tokens = 528, progress = 0.99, t = 3.62 s / 145.77 tokens per second 21.53.883.622 I slot print_timing: id 1 | task 26562 | prompt processing, n_tokens = 870, progress = 1.00, t = 3.62 s / 240.19 tokens per second 21.53.883.775 I slot print_timing: id 2 | task 26563 | prompt processing, n_tokens = 766, progress = 0.99, t = 3.62 s / 211.49 tokens per second 21.53.883.913 I slot print_timing: id 3 | task 26564 | prompt processing, n_tokens = 840, progress = 1.00, t = 3.62 s / 231.92 tokens per second 21.54.044.303 I slot print_timing: id 0 | task 26561 | prompt eval time = 4389.52 ms / 532 tokens ( 8.25 ms per token, 121.20 tokens per second) 21.54.044.305 I slot print_timing: id 0 | task 26561 | eval time = 41.63 ms / 2 tokens ( 41.63 ms per token, 24.02 tokens per second) 21.54.044.306 I slot print_timing: id 0 | task 26561 | total time = 4431.15 ms / 534 tokens 21.54.044.306 I slot print_timing: id 0 | task 26561 | graphs reused = 25411 21.54.044.307 I slot print_timing: id 0 | task 26561 | graph reallocs = 0 / 0 (same size) / (changed size) 21.54.044.358 I slot release: id 0 | task 26561 | stop processing: n_tokens = 784, truncated = 0 21.54.044.626 I slot print_timing: id 1 | task 26562 | prompt eval time = 4389.71 ms / 874 tokens ( 5.02 ms per token, 199.10 tokens per second) 21.54.044.628 I slot print_timing: id 1 | task 26562 | eval time = 41.67 ms / 2 tokens ( 41.67 ms per token, 24.00 tokens per second) 21.54.044.629 I slot print_timing: id 1 | task 26562 | total time = 4431.38 ms / 876 tokens 21.54.044.629 I slot print_timing: id 1 | task 26562 | graphs reused = 25411 21.54.044.629 I slot print_timing: id 1 | task 26562 | graph reallocs = 0 / 0 (same size) / (changed size) 21.54.044.675 I slot release: id 1 | task 26562 | stop processing: n_tokens = 875, truncated = 0 21.54.044.976 I slot print_timing: id 2 | task 26563 | prompt eval time = 4389.92 ms / 770 tokens ( 5.70 ms per token, 175.40 tokens per second) 21.54.044.979 I slot print_timing: id 2 | task 26563 | eval time = 41.72 ms / 2 tokens ( 41.72 ms per token, 23.97 tokens per second) 21.54.044.979 I slot print_timing: id 2 | task 26563 | total time = 4431.64 ms / 772 tokens 21.54.044.979 I slot print_timing: id 2 | task 26563 | graphs reused = 25411 21.54.044.980 I slot print_timing: id 2 | task 26563 | graph reallocs = 0 / 0 (same size) / (changed size) 21.54.045.030 I slot release: id 2 | task 26563 | stop processing: n_tokens = 771, truncated = 0 21.54.045.320 I slot print_timing: id 3 | task 26564 | prompt eval time = 4390.15 ms / 844 tokens ( 5.20 ms per token, 192.25 tokens per second) 21.54.045.323 I slot print_timing: id 3 | task 26564 | eval time = 41.75 ms / 2 tokens ( 41.75 ms per token, 23.95 tokens per second) 21.54.045.323 I slot print_timing: id 3 | task 26564 | total time = 4431.90 ms / 846 tokens 21.54.045.324 I slot print_timing: id 3 | task 26564 | graphs reused = 25411 21.54.045.324 I slot print_timing: id 3 | task 26564 | graph reallocs = 0 / 0 (same size) / (changed size) 21.54.045.368 I slot release: id 3 | task 26564 | stop processing: n_tokens = 845, truncated = 0 21.54.052.390 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.811 (> 0.100 thold), f_keep = 0.860 21.54.052.416 I slot launch_slot_: id 2 | task 26569 | processing task, is_child = 0 21.54.057.311 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 784, t_last = 336701412341 21.54.057.379 I slot launch_slot_: id 0 | task 26570 | processing task, is_child = 0 21.54.057.468 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 336701412658 21.54.057.527 I slot launch_slot_: id 1 | task 26571 | processing task, is_child = 0 21.54.057.569 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 336701413351 21.54.057.629 I slot launch_slot_: id 3 | task 26572 | processing task, is_child = 0 21.57.314.603 I slot print_timing: id 0 | task 26570 | prompt processing, n_tokens = 746, progress = 0.99, t = 3.26 s / 229.05 tokens per second 21.57.959.002 I slot print_timing: id 1 | task 26571 | prompt processing, n_tokens = 775, progress = 0.99, t = 3.26 s / 237.96 tokens per second 21.57.959.149 I slot print_timing: id 2 | task 26569 | prompt processing, n_tokens = 560, progress = 1.00, t = 3.26 s / 171.95 tokens per second 21.57.959.285 I slot print_timing: id 3 | task 26572 | prompt processing, n_tokens = 752, progress = 0.99, t = 3.26 s / 230.90 tokens per second 21.58.119.711 I slot print_timing: id 0 | task 26570 | prompt eval time = 4020.23 ms / 750 tokens ( 5.36 ms per token, 186.56 tokens per second) 21.58.119.716 I slot print_timing: id 0 | task 26570 | eval time = 41.85 ms / 2 tokens ( 41.85 ms per token, 23.90 tokens per second) 21.58.119.718 I slot print_timing: id 0 | task 26570 | total time = 4062.07 ms / 752 tokens 21.58.119.718 I slot print_timing: id 0 | task 26570 | graphs reused = 25412 21.58.119.718 I slot print_timing: id 0 | task 26570 | graph reallocs = 0 / 0 (same size) / (changed size) 21.58.119.772 I slot release: id 0 | task 26570 | stop processing: n_tokens = 751, truncated = 0 21.58.120.045 I slot print_timing: id 1 | task 26571 | prompt eval time = 4020.49 ms / 779 tokens ( 5.16 ms per token, 193.76 tokens per second) 21.58.120.049 I slot print_timing: id 1 | task 26571 | eval time = 41.86 ms / 2 tokens ( 41.86 ms per token, 23.89 tokens per second) 21.58.120.049 I slot print_timing: id 1 | task 26571 | total time = 4062.35 ms / 781 tokens 21.58.120.049 I slot print_timing: id 1 | task 26571 | graphs reused = 25412 21.58.120.050 I slot print_timing: id 1 | task 26571 | graph reallocs = 0 / 0 (same size) / (changed size) 21.58.120.084 I slot release: id 1 | task 26571 | stop processing: n_tokens = 780, truncated = 0 21.58.120.359 I slot print_timing: id 2 | task 26569 | prompt eval time = 4020.81 ms / 564 tokens ( 7.13 ms per token, 140.27 tokens per second) 21.58.120.361 I slot print_timing: id 2 | task 26569 | eval time = 41.80 ms / 2 tokens ( 41.80 ms per token, 23.92 tokens per second) 21.58.120.362 I slot print_timing: id 2 | task 26569 | total time = 4062.62 ms / 566 tokens 21.58.120.362 I slot print_timing: id 2 | task 26569 | graphs reused = 25412 21.58.120.362 I slot print_timing: id 2 | task 26569 | graph reallocs = 0 / 0 (same size) / (changed size) 21.58.120.398 I slot release: id 2 | task 26569 | stop processing: n_tokens = 819, truncated = 0 21.58.120.694 I slot print_timing: id 3 | task 26572 | prompt eval time = 4021.29 ms / 756 tokens ( 5.32 ms per token, 188.00 tokens per second) 21.58.120.699 I slot print_timing: id 3 | task 26572 | eval time = 41.58 ms / 2 tokens ( 41.58 ms per token, 24.05 tokens per second) 21.58.120.699 I slot print_timing: id 3 | task 26572 | total time = 4062.88 ms / 758 tokens 21.58.120.700 I slot print_timing: id 3 | task 26572 | graphs reused = 25412 21.58.120.700 I slot print_timing: id 3 | task 26572 | graph reallocs = 0 / 0 (same size) / (changed size) 21.58.120.736 I slot release: id 3 | task 26572 | stop processing: n_tokens = 757, truncated = 0 21.58.127.379 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 336705487755 21.58.128.803 I slot launch_slot_: id 0 | task 26578 | processing task, is_child = 0 21.58.133.163 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 336705488067 21.58.133.232 I slot launch_slot_: id 1 | task 26579 | processing task, is_child = 0 21.58.133.314 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 819, t_last = 336705488381 21.58.133.377 I slot launch_slot_: id 2 | task 26577 | processing task, is_child = 0 21.58.133.423 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 336705488719 21.58.133.483 I slot launch_slot_: id 3 | task 26580 | processing task, is_child = 0 22.02.134.905 I slot print_timing: id 0 | task 26578 | prompt processing, n_tokens = 881, progress = 1.00, t = 4.00 s / 220.17 tokens per second 22.02.779.613 I slot print_timing: id 1 | task 26579 | prompt processing, n_tokens = 899, progress = 1.00, t = 4.00 s / 224.67 tokens per second 22.02.779.771 I slot print_timing: id 2 | task 26577 | prompt processing, n_tokens = 877, progress = 1.00, t = 4.00 s / 219.18 tokens per second 22.02.779.931 I slot print_timing: id 3 | task 26580 | prompt processing, n_tokens = 893, progress = 1.00, t = 4.00 s / 223.18 tokens per second 22.02.939.610 I slot print_timing: id 0 | task 26578 | prompt eval time = 4765.07 ms / 885 tokens ( 5.38 ms per token, 185.73 tokens per second) 22.02.939.615 I slot print_timing: id 0 | task 26578 | eval time = 41.04 ms / 2 tokens ( 41.04 ms per token, 24.36 tokens per second) 22.02.939.616 I slot print_timing: id 0 | task 26578 | total time = 4806.11 ms / 887 tokens 22.02.939.617 I slot print_timing: id 0 | task 26578 | graphs reused = 25414 22.02.939.617 I slot print_timing: id 0 | task 26578 | graph reallocs = 0 / 0 (same size) / (changed size) 22.02.939.671 I slot release: id 0 | task 26578 | stop processing: n_tokens = 886, truncated = 0 22.02.939.955 I slot print_timing: id 1 | task 26579 | prompt eval time = 4765.39 ms / 903 tokens ( 5.28 ms per token, 189.49 tokens per second) 22.02.939.957 I slot print_timing: id 1 | task 26579 | eval time = 41.01 ms / 2 tokens ( 41.01 ms per token, 24.38 tokens per second) 22.02.939.958 I slot print_timing: id 1 | task 26579 | total time = 4806.40 ms / 905 tokens 22.02.939.958 I slot print_timing: id 1 | task 26579 | graphs reused = 25414 22.02.939.958 I slot print_timing: id 1 | task 26579 | graph reallocs = 0 / 0 (same size) / (changed size) 22.02.939.995 I slot release: id 1 | task 26579 | stop processing: n_tokens = 904, truncated = 0 22.02.940.271 I slot print_timing: id 2 | task 26577 | prompt eval time = 4765.64 ms / 881 tokens ( 5.41 ms per token, 184.87 tokens per second) 22.02.940.274 I slot print_timing: id 2 | task 26577 | eval time = 41.02 ms / 2 tokens ( 41.02 ms per token, 24.38 tokens per second) 22.02.940.274 I slot print_timing: id 2 | task 26577 | total time = 4806.66 ms / 883 tokens 22.02.940.274 I slot print_timing: id 2 | task 26577 | graphs reused = 25414 22.02.940.275 I slot print_timing: id 2 | task 26577 | graph reallocs = 0 / 0 (same size) / (changed size) 22.02.940.306 I slot release: id 2 | task 26577 | stop processing: n_tokens = 882, truncated = 0 22.02.940.587 I slot print_timing: id 3 | task 26580 | prompt eval time = 4765.88 ms / 897 tokens ( 5.31 ms per token, 188.21 tokens per second) 22.02.940.590 I slot print_timing: id 3 | task 26580 | eval time = 41.04 ms / 2 tokens ( 41.04 ms per token, 24.37 tokens per second) 22.02.940.591 I slot print_timing: id 3 | task 26580 | total time = 4806.92 ms / 899 tokens 22.02.940.591 I slot print_timing: id 3 | task 26580 | graphs reused = 25414 22.02.940.592 I slot print_timing: id 3 | task 26580 | graph reallocs = 0 / 0 (same size) / (changed size) 22.02.940.622 I slot release: id 3 | task 26580 | stop processing: n_tokens = 898, truncated = 0 22.02.946.951 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 336710307654 22.02.948.580 I slot launch_slot_: id 0 | task 26585 | processing task, is_child = 0 22.02.953.401 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 336710307978 22.02.953.467 I slot launch_slot_: id 1 | task 26586 | processing task, is_child = 0 22.02.953.556 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.912 22.02.953.571 I slot launch_slot_: id 2 | task 26587 | processing task, is_child = 0 22.02.953.616 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 898, t_last = 336710308606 22.02.953.678 I slot launch_slot_: id 3 | task 26588 | processing task, is_child = 0 22.06.251.300 I slot print_timing: id 0 | task 26585 | prompt processing, n_tokens = 773, progress = 0.99, t = 3.30 s / 234.41 tokens per second 22.06.898.474 I slot print_timing: id 1 | task 26586 | prompt processing, n_tokens = 773, progress = 0.99, t = 3.30 s / 234.42 tokens per second 22.06.898.619 I slot print_timing: id 2 | task 26587 | prompt processing, n_tokens = 529, progress = 1.00, t = 3.30 s / 160.43 tokens per second 22.06.898.773 I slot print_timing: id 3 | task 26588 | prompt processing, n_tokens = 941, progress = 1.00, t = 3.30 s / 285.38 tokens per second 22.07.058.717 I slot print_timing: id 0 | task 26585 | prompt eval time = 4063.57 ms / 777 tokens ( 5.23 ms per token, 191.21 tokens per second) 22.07.058.720 I slot print_timing: id 0 | task 26585 | eval time = 41.46 ms / 2 tokens ( 41.46 ms per token, 24.12 tokens per second) 22.07.058.720 I slot print_timing: id 0 | task 26585 | total time = 4105.03 ms / 779 tokens 22.07.058.721 I slot print_timing: id 0 | task 26585 | graphs reused = 25416 22.07.058.721 I slot print_timing: id 0 | task 26585 | graph reallocs = 0 / 0 (same size) / (changed size) 22.07.058.768 I slot release: id 0 | task 26585 | stop processing: n_tokens = 778, truncated = 0 22.07.059.043 I slot print_timing: id 1 | task 26586 | prompt eval time = 4063.81 ms / 777 tokens ( 5.23 ms per token, 191.20 tokens per second) 22.07.059.045 I slot print_timing: id 1 | task 26586 | eval time = 41.49 ms / 2 tokens ( 41.49 ms per token, 24.10 tokens per second) 22.07.059.046 I slot print_timing: id 1 | task 26586 | total time = 4105.30 ms / 779 tokens 22.07.059.046 I slot print_timing: id 1 | task 26586 | graphs reused = 25416 22.07.059.046 I slot print_timing: id 1 | task 26586 | graph reallocs = 0 / 0 (same size) / (changed size) 22.07.059.081 I slot release: id 1 | task 26586 | stop processing: n_tokens = 778, truncated = 0 22.07.059.351 I slot print_timing: id 2 | task 26587 | prompt eval time = 4064.04 ms / 533 tokens ( 7.62 ms per token, 131.15 tokens per second) 22.07.059.353 I slot print_timing: id 2 | task 26587 | eval time = 41.51 ms / 2 tokens ( 41.51 ms per token, 24.09 tokens per second) 22.07.059.354 I slot print_timing: id 2 | task 26587 | total time = 4105.56 ms / 535 tokens 22.07.059.354 I slot print_timing: id 2 | task 26587 | graphs reused = 25416 22.07.059.355 I slot print_timing: id 2 | task 26587 | graph reallocs = 0 / 0 (same size) / (changed size) 22.07.059.403 I slot release: id 2 | task 26587 | stop processing: n_tokens = 899, truncated = 0 22.07.059.680 I slot print_timing: id 3 | task 26588 | prompt eval time = 4064.27 ms / 945 tokens ( 4.30 ms per token, 232.51 tokens per second) 22.07.059.683 I slot print_timing: id 3 | task 26588 | eval time = 41.53 ms / 2 tokens ( 41.53 ms per token, 24.08 tokens per second) 22.07.059.684 I slot print_timing: id 3 | task 26588 | total time = 4105.81 ms / 947 tokens 22.07.059.684 I slot print_timing: id 3 | task 26588 | graphs reused = 25416 22.07.059.684 I slot print_timing: id 3 | task 26588 | graph reallocs = 0 / 0 (same size) / (changed size) 22.07.059.736 I slot release: id 3 | task 26588 | stop processing: n_tokens = 946, truncated = 0 22.07.066.541 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.871 22.07.066.561 I slot launch_slot_: id 3 | task 26593 | processing task, is_child = 0 22.07.071.567 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 336714426751 22.07.071.633 I slot launch_slot_: id 0 | task 26594 | processing task, is_child = 0 22.07.071.732 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 336714427064 22.07.071.789 I slot launch_slot_: id 1 | task 26595 | processing task, is_child = 0 22.07.071.835 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 336714427386 22.07.071.896 I slot launch_slot_: id 2 | task 26596 | processing task, is_child = 0 22.11.661.126 I slot print_timing: id 0 | task 26594 | prompt processing, n_tokens = 925, progress = 1.00, t = 4.59 s / 201.57 tokens per second 22.11.661.288 I slot print_timing: id 1 | task 26595 | prompt processing, n_tokens = 876, progress = 1.00, t = 4.59 s / 190.90 tokens per second 22.11.661.450 I slot print_timing: id 2 | task 26596 | prompt processing, n_tokens = 908, progress = 1.00, t = 4.59 s / 197.87 tokens per second 22.11.769.197 I slot print_timing: id 3 | task 26593 | prompt eval time = 4589.04 ms / 494 tokens ( 9.29 ms per token, 107.65 tokens per second) 22.11.769.201 I slot print_timing: id 3 | task 26593 | eval time = 108.08 ms / 2 tokens ( 108.08 ms per token, 9.25 tokens per second) 22.11.769.202 I slot print_timing: id 3 | task 26593 | total time = 4697.12 ms / 496 tokens 22.11.769.202 I slot print_timing: id 3 | task 26593 | graphs reused = 25417 22.11.769.203 I slot print_timing: id 3 | task 26593 | graph reallocs = 0 / 0 (same size) / (changed size) 22.11.769.272 I slot release: id 3 | task 26593 | stop processing: n_tokens = 924, truncated = 0 22.11.802.037 I slot print_timing: id 0 | task 26594 | prompt eval time = 4696.41 ms / 929 tokens ( 5.06 ms per token, 197.81 tokens per second) 22.11.802.040 I slot print_timing: id 0 | task 26594 | eval time = 33.73 ms / 2 tokens ( 33.73 ms per token, 29.65 tokens per second) 22.11.802.040 I slot print_timing: id 0 | task 26594 | total time = 4730.13 ms / 931 tokens 22.11.802.041 I slot print_timing: id 0 | task 26594 | graphs reused = 25417 22.11.802.041 I slot print_timing: id 0 | task 26594 | graph reallocs = 0 / 0 (same size) / (changed size) 22.11.802.085 I slot release: id 0 | task 26594 | stop processing: n_tokens = 930, truncated = 0 22.11.802.354 I slot print_timing: id 1 | task 26595 | prompt eval time = 4696.66 ms / 880 tokens ( 5.34 ms per token, 187.37 tokens per second) 22.11.802.356 I slot print_timing: id 1 | task 26595 | eval time = 33.74 ms / 2 tokens ( 33.74 ms per token, 29.64 tokens per second) 22.11.802.357 I slot print_timing: id 1 | task 26595 | total time = 4730.40 ms / 882 tokens 22.11.802.357 I slot print_timing: id 1 | task 26595 | graphs reused = 25417 22.11.802.357 I slot print_timing: id 1 | task 26595 | graph reallocs = 0 / 0 (same size) / (changed size) 22.11.802.398 I slot release: id 1 | task 26595 | stop processing: n_tokens = 881, truncated = 0 22.11.802.690 I slot print_timing: id 2 | task 26596 | prompt eval time = 4696.90 ms / 912 tokens ( 5.15 ms per token, 194.17 tokens per second) 22.11.802.692 I slot print_timing: id 2 | task 26596 | eval time = 33.78 ms / 2 tokens ( 33.78 ms per token, 29.61 tokens per second) 22.11.802.692 I slot print_timing: id 2 | task 26596 | total time = 4730.67 ms / 914 tokens 22.11.802.692 I slot print_timing: id 2 | task 26596 | graphs reused = 25417 22.11.802.693 I slot print_timing: id 2 | task 26596 | graph reallocs = 0 / 0 (same size) / (changed size) 22.11.802.734 I slot release: id 2 | task 26596 | stop processing: n_tokens = 913, truncated = 0 22.11.802.739 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.894 22.11.802.764 I slot launch_slot_: id 1 | task 26601 | processing task, is_child = 0 22.11.807.963 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.863 22.11.807.986 I slot launch_slot_: id 2 | task 26602 | processing task, is_child = 0 22.11.808.079 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 336719137255 22.11.808.723 I slot launch_slot_: id 3 | task 26603 | processing task, is_child = 0 22.11.808.776 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 930, t_last = 336719170068 22.11.808.841 I slot launch_slot_: id 0 | task 26604 | processing task, is_child = 0 22.15.531.761 I slot print_timing: id 0 | task 26604 | prompt processing, n_tokens = 1168, progress = 1.00, t = 3.72 s / 313.78 tokens per second 22.15.531.966 I slot print_timing: id 1 | task 26601 | prompt processing, n_tokens = 516, progress = 1.00, t = 3.72 s / 138.63 tokens per second 22.15.620.094 I slot print_timing: id 2 | task 26602 | prompt eval time = 3722.44 ms / 474 tokens ( 7.85 ms per token, 127.34 tokens per second) 22.15.620.096 I slot print_timing: id 2 | task 26602 | eval time = 88.65 ms / 2 tokens ( 88.65 ms per token, 11.28 tokens per second) 22.15.620.096 I slot print_timing: id 2 | task 26602 | total time = 3811.09 ms / 476 tokens 22.15.620.097 I slot print_timing: id 2 | task 26602 | graphs reused = 25417 22.15.620.097 I slot print_timing: id 2 | task 26602 | graph reallocs = 0 / 0 (same size) / (changed size) 22.15.620.168 I slot release: id 2 | task 26602 | stop processing: n_tokens = 871, truncated = 0 22.15.620.485 I slot print_timing: id 3 | task 26603 | prompt eval time = 3722.65 ms / 486 tokens ( 7.66 ms per token, 130.55 tokens per second) 22.15.620.488 I slot print_timing: id 3 | task 26603 | eval time = 88.73 ms / 2 tokens ( 88.73 ms per token, 11.27 tokens per second) 22.15.620.489 I slot print_timing: id 3 | task 26603 | total time = 3811.38 ms / 488 tokens 22.15.620.489 I slot print_timing: id 3 | task 26603 | graphs reused = 25417 22.15.620.490 I slot print_timing: id 3 | task 26603 | graph reallocs = 0 / 0 (same size) / (changed size) 22.15.620.539 I slot release: id 3 | task 26603 | stop processing: n_tokens = 883, truncated = 0 22.15.645.934 I slot print_timing: id 0 | task 26604 | prompt eval time = 3810.57 ms / 1172 tokens ( 3.25 ms per token, 307.57 tokens per second) 22.15.645.939 I slot print_timing: id 0 | task 26604 | eval time = 26.52 ms / 2 tokens ( 26.52 ms per token, 37.71 tokens per second) 22.15.645.940 I slot print_timing: id 0 | task 26604 | total time = 3837.09 ms / 1174 tokens 22.15.645.940 I slot print_timing: id 0 | task 26604 | graphs reused = 25417 22.15.645.941 I slot print_timing: id 0 | task 26604 | graph reallocs = 0 / 0 (same size) / (changed size) 22.15.646.006 I slot release: id 0 | task 26604 | stop processing: n_tokens = 1173, truncated = 0 22.15.646.291 I slot print_timing: id 1 | task 26601 | prompt eval time = 3810.89 ms / 520 tokens ( 7.33 ms per token, 136.45 tokens per second) 22.15.646.295 I slot print_timing: id 1 | task 26601 | eval time = 26.49 ms / 2 tokens ( 26.49 ms per token, 37.76 tokens per second) 22.15.646.295 I slot print_timing: id 1 | task 26601 | total time = 3837.37 ms / 522 tokens 22.15.646.295 I slot print_timing: id 1 | task 26601 | graphs reused = 25417 22.15.646.296 I slot print_timing: id 1 | task 26601 | graph reallocs = 0 / 0 (same size) / (changed size) 22.15.646.342 I slot release: id 1 | task 26601 | stop processing: n_tokens = 885, truncated = 0 22.15.646.346 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.835 (> 0.100 thold), f_keep = 0.883 22.15.646.369 I slot launch_slot_: id 0 | task 26609 | processing task, is_child = 0 22.15.651.054 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 336722988151 22.15.651.130 I slot launch_slot_: id 2 | task 26610 | processing task, is_child = 0 22.16.513.181 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 336722988522 22.16.513.278 I slot launch_slot_: id 3 | task 26612 | processing task, is_child = 0 22.16.513.331 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 336723014325 22.16.513.398 I slot launch_slot_: id 1 | task 26613 | processing task, is_child = 0 22.18.751.817 I slot print_timing: id 0 | task 26609 | prompt processing, n_tokens = 580, progress = 1.00, t = 3.10 s / 187.06 tokens per second 22.22.313.472 I slot print_timing: id 1 | task 26613 | prompt processing, n_tokens = 2076, progress = 0.80, t = 5.50 s / 377.26 tokens per second 22.22.313.526 I slot print_timing: id 2 | task 26610 | prompt processing, n_tokens = 1175, progress = 1.00, t = 6.66 s / 176.38 tokens per second 22.24.411.392 I slot print_timing: id 0 | task 26609 | prompt eval time = 6662.23 ms / 584 tokens ( 11.41 ms per token, 87.66 tokens per second) 22.24.411.394 I slot print_timing: id 0 | task 26609 | eval time = 2097.93 ms / 2 tokens ( 2097.93 ms per token, 0.48 tokens per second) 22.24.411.395 I slot print_timing: id 0 | task 26609 | total time = 8760.16 ms / 586 tokens 22.24.411.395 I slot print_timing: id 0 | task 26609 | graphs reused = 25417 22.24.411.396 I slot print_timing: id 0 | task 26609 | graph reallocs = 0 / 0 (same size) / (changed size) 22.24.411.467 I slot release: id 0 | task 26609 | stop processing: n_tokens = 1241, truncated = 0 22.24.411.816 I slot print_timing: id 1 | task 26613 | prompt processing, n_tokens = 2588, progress = 1.00, t = 7.60 s / 340.49 tokens per second 22.24.412.296 I slot print_timing: id 3 | task 26612 | prompt processing, n_tokens = 1983, progress = 0.79, t = 5.01 s / 396.05 tokens per second 22.25.144.357 I slot print_timing: id 2 | task 26610 | prompt eval time = 8760.50 ms / 1179 tokens ( 7.43 ms per token, 134.58 tokens per second) 22.25.144.359 I slot print_timing: id 2 | task 26610 | eval time = 732.55 ms / 2 tokens ( 732.55 ms per token, 1.37 tokens per second) 22.25.144.360 I slot print_timing: id 2 | task 26610 | total time = 9493.05 ms / 1181 tokens 22.25.144.360 I slot print_timing: id 2 | task 26610 | graphs reused = 25417 22.25.144.361 I slot print_timing: id 2 | task 26610 | graph reallocs = 0 / 0 (same size) / (changed size) 22.25.144.431 I slot release: id 2 | task 26610 | stop processing: n_tokens = 1180, truncated = 0 22.25.144.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1241, t_last = 336731779450 22.25.149.458 I slot launch_slot_: id 0 | task 26618 | processing task, is_child = 0 22.25.152.978 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1180, t_last = 336732512414 22.25.153.089 I slot launch_slot_: id 2 | task 26619 | processing task, is_child = 0 22.27.774.123 I slot print_timing: id 1 | task 26613 | prompt eval time = 8333.69 ms / 2592 tokens ( 3.22 ms per token, 311.03 tokens per second) 22.27.774.127 I slot print_timing: id 1 | task 26613 | eval time = 2630.09 ms / 2 tokens ( 2630.09 ms per token, 0.38 tokens per second) 22.27.774.128 I slot print_timing: id 1 | task 26613 | total time = 10963.77 ms / 2594 tokens 22.27.774.128 I slot print_timing: id 1 | task 26613 | graphs reused = 25417 22.27.774.129 I slot print_timing: id 1 | task 26613 | graph reallocs = 0 / 0 (same size) / (changed size) 22.27.774.270 I slot release: id 1 | task 26613 | stop processing: n_tokens = 2593, truncated = 0 22.30.045.956 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2593, t_last = 336735142254 22.30.527.524 I slot launch_slot_: id 1 | task 26622 | processing task, is_child = 0 22.30.527.542 I slot print_timing: id 0 | task 26618 | prompt processing, n_tokens = 2230, progress = 0.81, t = 4.89 s / 455.77 tokens per second 22.30.527.770 I slot print_timing: id 3 | task 26612 | prompt processing, n_tokens = 2495, progress = 1.00, t = 5.74 s / 434.71 tokens per second 22.33.397.959 I slot print_timing: id 0 | task 26618 | prompt processing, n_tokens = 2742, progress = 1.00, t = 8.24 s / 332.58 tokens per second 22.33.398.399 I slot print_timing: id 2 | task 26619 | prompt processing, n_tokens = 2126, progress = 0.80, t = 5.62 s / 378.07 tokens per second 22.34.834.289 I slot print_timing: id 3 | task 26612 | prompt eval time = 13993.74 ms / 2499 tokens ( 5.60 ms per token, 178.58 tokens per second) 22.34.834.292 I slot print_timing: id 3 | task 26612 | eval time = 1436.34 ms / 2 tokens ( 1436.34 ms per token, 0.70 tokens per second) 22.34.834.293 I slot print_timing: id 3 | task 26612 | total time = 15430.08 ms / 2501 tokens 22.34.834.293 I slot print_timing: id 3 | task 26612 | graphs reused = 25417 22.34.834.294 I slot print_timing: id 3 | task 26612 | graph reallocs = 0 / 0 (same size) / (changed size) 22.34.834.427 I slot release: id 3 | task 26612 | stop processing: n_tokens = 2500, truncated = 0 22.34.834.441 I slot print_timing: id 1 | task 26622 | prompt processing, n_tokens = 1755, progress = 1.00, t = 4.31 s / 407.57 tokens per second 22.34.834.802 I slot print_timing: id 2 | task 26619 | prompt processing, n_tokens = 2638, progress = 1.00, t = 7.06 s / 373.69 tokens per second 22.34.919.870 I slot print_timing: id 0 | task 26618 | prompt eval time = 9680.90 ms / 2746 tokens ( 3.53 ms per token, 283.65 tokens per second) 22.34.919.872 I slot print_timing: id 0 | task 26618 | eval time = 85.87 ms / 2 tokens ( 85.87 ms per token, 11.65 tokens per second) 22.34.919.873 I slot print_timing: id 0 | task 26618 | total time = 9766.77 ms / 2748 tokens 22.34.919.873 I slot print_timing: id 0 | task 26618 | graphs reused = 25417 22.34.919.874 I slot print_timing: id 0 | task 26618 | graph reallocs = 0 / 0 (same size) / (changed size) 22.34.920.005 I slot release: id 0 | task 26618 | stop processing: n_tokens = 2747, truncated = 0 22.34.920.870 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2500, t_last = 336742202410 22.34.928.909 I slot launch_slot_: id 3 | task 26626 | processing task, is_child = 0 22.34.936.928 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2747, t_last = 336742287990 22.34.937.061 I slot launch_slot_: id 0 | task 26627 | processing task, is_child = 0 22.37.693.712 I slot print_timing: id 1 | task 26622 | prompt eval time = 4392.81 ms / 1759 tokens ( 2.50 ms per token, 400.43 tokens per second) 22.37.693.714 I slot print_timing: id 1 | task 26622 | eval time = 2773.31 ms / 2 tokens ( 2773.31 ms per token, 0.36 tokens per second) 22.37.693.714 I slot print_timing: id 1 | task 26622 | total time = 7166.12 ms / 1761 tokens 22.37.693.715 I slot print_timing: id 1 | task 26622 | graphs reused = 25417 22.37.693.715 I slot print_timing: id 1 | task 26622 | graph reallocs = 0 / 0 (same size) / (changed size) 22.37.693.817 I slot release: id 1 | task 26622 | stop processing: n_tokens = 1760, truncated = 0 22.37.694.251 I slot print_timing: id 2 | task 26619 | prompt eval time = 7146.57 ms / 2642 tokens ( 2.70 ms per token, 369.69 tokens per second) 22.37.694.254 I slot print_timing: id 2 | task 26619 | eval time = 2773.38 ms / 2 tokens ( 2773.38 ms per token, 0.36 tokens per second) 22.37.694.254 I slot print_timing: id 2 | task 26619 | total time = 9919.95 ms / 2644 tokens 22.37.694.255 I slot print_timing: id 2 | task 26619 | graphs reused = 25417 22.37.694.255 I slot print_timing: id 2 | task 26619 | graph reallocs = 0 / 0 (same size) / (changed size) 22.37.694.421 I slot release: id 2 | task 26619 | stop processing: n_tokens = 2643, truncated = 0 22.39.006.235 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.798 (> 0.100 thold), f_keep = 0.830 22.39.006.275 I slot launch_slot_: id 1 | task 26630 | processing task, is_child = 0 22.39.386.668 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2643, t_last = 336745062405 22.39.386.837 I slot launch_slot_: id 2 | task 26631 | processing task, is_child = 0 22.39.386.850 I slot print_timing: id 0 | task 26627 | prompt processing, n_tokens = 2001, progress = 1.00, t = 4.07 s / 491.75 tokens per second 22.39.387.435 I slot print_timing: id 3 | task 26626 | prompt processing, n_tokens = 1295, progress = 0.72, t = 4.07 s / 318.26 tokens per second 22.42.184.406 I slot print_timing: id 3 | task 26626 | prompt processing, n_tokens = 1807, progress = 1.00, t = 7.25 s / 249.36 tokens per second 22.43.611.817 I slot print_timing: id 0 | task 26627 | prompt eval time = 7247.23 ms / 2005 tokens ( 3.61 ms per token, 276.66 tokens per second) 22.43.611.820 I slot print_timing: id 0 | task 26627 | eval time = 1427.52 ms / 2 tokens ( 1427.52 ms per token, 0.70 tokens per second) 22.43.611.821 I slot print_timing: id 0 | task 26627 | total time = 8674.74 ms / 2007 tokens 22.43.611.821 I slot print_timing: id 0 | task 26627 | graphs reused = 25417 22.43.611.822 I slot print_timing: id 0 | task 26627 | graph reallocs = 0 / 0 (same size) / (changed size) 22.43.611.933 I slot release: id 0 | task 26627 | stop processing: n_tokens = 2006, truncated = 0 22.43.612.278 I slot print_timing: id 1 | task 26630 | prompt processing, n_tokens = 582, progress = 1.00, t = 4.22 s / 137.77 tokens per second 22.43.612.625 I slot print_timing: id 2 | task 26631 | prompt processing, n_tokens = 1904, progress = 1.00, t = 4.22 s / 450.73 tokens per second 22.43.692.440 I slot print_timing: id 3 | task 26626 | prompt eval time = 8675.00 ms / 1811 tokens ( 4.79 ms per token, 208.76 tokens per second) 22.43.692.444 I slot print_timing: id 3 | task 26626 | eval time = 80.17 ms / 2 tokens ( 80.17 ms per token, 12.47 tokens per second) 22.43.692.444 I slot print_timing: id 3 | task 26626 | total time = 8755.17 ms / 1813 tokens 22.43.692.445 I slot print_timing: id 3 | task 26626 | graphs reused = 25417 22.43.692.445 I slot print_timing: id 3 | task 26626 | graph reallocs = 0 / 0 (same size) / (changed size) 22.43.692.551 I slot release: id 3 | task 26626 | stop processing: n_tokens = 1812, truncated = 0 22.43.692.560 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.728 22.43.692.588 I slot launch_slot_: id 0 | task 26635 | processing task, is_child = 0 22.45.358.554 I slot print_timing: id 1 | task 26630 | prompt eval time = 4304.58 ms / 586 tokens ( 7.35 ms per token, 136.13 tokens per second) 22.45.358.557 I slot print_timing: id 1 | task 26630 | eval time = 1666.80 ms / 2 tokens ( 1666.80 ms per token, 0.60 tokens per second) 22.45.358.557 I slot print_timing: id 1 | task 26630 | total time = 5971.38 ms / 588 tokens 22.45.358.558 I slot print_timing: id 1 | task 26630 | graphs reused = 25417 22.45.358.558 I slot print_timing: id 1 | task 26630 | graph reallocs = 0 / 0 (same size) / (changed size) 22.45.358.662 I slot release: id 1 | task 26630 | stop processing: n_tokens = 1830, truncated = 0 22.45.359.115 I slot print_timing: id 2 | task 26631 | prompt eval time = 4304.87 ms / 1908 tokens ( 2.26 ms per token, 443.22 tokens per second) 22.45.359.119 I slot print_timing: id 2 | task 26631 | eval time = 1666.98 ms / 2 tokens ( 1666.98 ms per token, 0.60 tokens per second) 22.45.359.119 I slot print_timing: id 2 | task 26631 | total time = 5971.85 ms / 1910 tokens 22.45.359.120 I slot print_timing: id 2 | task 26631 | graphs reused = 25417 22.45.359.120 I slot print_timing: id 2 | task 26631 | graph reallocs = 0 / 0 (same size) / (changed size) 22.45.359.213 I slot release: id 2 | task 26631 | stop processing: n_tokens = 1909, truncated = 0 22.45.359.220 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1812, t_last = 336751060535 22.45.359.455 I slot launch_slot_: id 3 | task 26637 | processing task, is_child = 0 22.45.372.061 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1830, t_last = 336752726647 22.45.372.170 I slot launch_slot_: id 1 | task 26638 | processing task, is_child = 0 22.45.372.247 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1909, t_last = 336752727197 22.45.372.347 I slot launch_slot_: id 2 | task 26639 | processing task, is_child = 0 22.47.103.337 I slot print_timing: id 0 | task 26635 | prompt processing, n_tokens = 1743, progress = 1.00, t = 3.40 s / 511.93 tokens per second 22.49.253.203 I slot print_timing: id 1 | task 26638 | prompt processing, n_tokens = 729, progress = 0.99, t = 3.88 s / 187.86 tokens per second 22.49.253.376 I slot print_timing: id 2 | task 26639 | prompt processing, n_tokens = 740, progress = 0.99, t = 3.88 s / 190.71 tokens per second 22.49.253.508 I slot print_timing: id 3 | task 26637 | prompt processing, n_tokens = 707, progress = 0.99, t = 3.88 s / 182.21 tokens per second 22.49.365.897 I slot print_timing: id 0 | task 26635 | prompt eval time = 5554.63 ms / 1747 tokens ( 3.18 ms per token, 314.51 tokens per second) 22.49.365.899 I slot print_timing: id 0 | task 26635 | eval time = 112.71 ms / 2 tokens ( 112.71 ms per token, 8.87 tokens per second) 22.49.365.899 I slot print_timing: id 0 | task 26635 | total time = 5667.34 ms / 1749 tokens 22.49.365.900 I slot print_timing: id 0 | task 26635 | graphs reused = 25417 22.49.365.900 I slot print_timing: id 0 | task 26635 | graph reallocs = 0 / 0 (same size) / (changed size) 22.49.365.998 I slot release: id 0 | task 26635 | stop processing: n_tokens = 1748, truncated = 0 22.49.399.945 I slot print_timing: id 1 | task 26638 | prompt eval time = 3993.91 ms / 733 tokens ( 5.45 ms per token, 183.53 tokens per second) 22.49.399.948 I slot print_timing: id 1 | task 26638 | eval time = 33.64 ms / 2 tokens ( 33.64 ms per token, 29.73 tokens per second) 22.49.399.950 I slot print_timing: id 1 | task 26638 | total time = 4027.55 ms / 735 tokens 22.49.399.950 I slot print_timing: id 1 | task 26638 | graphs reused = 25417 22.49.399.951 I slot print_timing: id 1 | task 26638 | graph reallocs = 0 / 0 (same size) / (changed size) 22.49.399.997 I slot release: id 1 | task 26638 | stop processing: n_tokens = 734, truncated = 0 22.49.400.283 I slot print_timing: id 2 | task 26639 | prompt eval time = 3994.20 ms / 744 tokens ( 5.37 ms per token, 186.27 tokens per second) 22.49.400.285 I slot print_timing: id 2 | task 26639 | eval time = 33.55 ms / 2 tokens ( 33.55 ms per token, 29.80 tokens per second) 22.49.400.285 I slot print_timing: id 2 | task 26639 | total time = 4027.75 ms / 746 tokens 22.49.400.286 I slot print_timing: id 2 | task 26639 | graphs reused = 25417 22.49.400.286 I slot print_timing: id 2 | task 26639 | graph reallocs = 0 / 0 (same size) / (changed size) 22.49.400.330 I slot release: id 2 | task 26639 | stop processing: n_tokens = 745, truncated = 0 22.49.400.621 I slot print_timing: id 3 | task 26637 | prompt eval time = 3994.60 ms / 711 tokens ( 5.62 ms per token, 177.99 tokens per second) 22.49.400.623 I slot print_timing: id 3 | task 26637 | eval time = 33.37 ms / 2 tokens ( 33.37 ms per token, 29.97 tokens per second) 22.49.400.624 I slot print_timing: id 3 | task 26637 | total time = 4027.97 ms / 713 tokens 22.49.400.624 I slot print_timing: id 3 | task 26637 | graphs reused = 25417 22.49.400.624 I slot print_timing: id 3 | task 26637 | graph reallocs = 0 / 0 (same size) / (changed size) 22.49.400.656 I slot release: id 3 | task 26637 | stop processing: n_tokens = 712, truncated = 0 22.49.400.661 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.854 22.49.400.686 I slot launch_slot_: id 1 | task 26644 | processing task, is_child = 0 22.49.410.552 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.842 22.49.410.577 I slot launch_slot_: id 2 | task 26645 | processing task, is_child = 0 22.49.410.692 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1748, t_last = 336756733981 22.49.410.785 I slot launch_slot_: id 0 | task 26646 | processing task, is_child = 0 22.49.410.823 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 712, t_last = 336756768639 22.49.410.880 I slot launch_slot_: id 3 | task 26647 | processing task, is_child = 0 22.53.501.573 I slot print_timing: id 0 | task 26646 | prompt processing, n_tokens = 1036, progress = 1.00, t = 4.09 s / 253.30 tokens per second 22.53.501.803 I slot print_timing: id 3 | task 26647 | prompt processing, n_tokens = 785, progress = 0.99, t = 4.09 s / 191.95 tokens per second 22.53.601.089 I slot print_timing: id 1 | task 26644 | prompt eval time = 4090.23 ms / 493 tokens ( 8.30 ms per token, 120.53 tokens per second) 22.53.601.092 I slot print_timing: id 1 | task 26644 | eval time = 99.84 ms / 2 tokens ( 99.84 ms per token, 10.02 tokens per second) 22.53.601.092 I slot print_timing: id 1 | task 26644 | total time = 4190.07 ms / 495 tokens 22.53.601.093 I slot print_timing: id 1 | task 26644 | graphs reused = 25417 22.53.601.093 I slot print_timing: id 1 | task 26644 | graph reallocs = 0 / 0 (same size) / (changed size) 22.53.601.142 I slot release: id 1 | task 26644 | stop processing: n_tokens = 711, truncated = 0 22.53.601.459 I slot print_timing: id 2 | task 26645 | prompt eval time = 4090.43 ms / 498 tokens ( 8.21 ms per token, 121.75 tokens per second) 22.53.601.462 I slot print_timing: id 2 | task 26645 | eval time = 99.90 ms / 2 tokens ( 99.90 ms per token, 10.01 tokens per second) 22.53.601.462 I slot print_timing: id 2 | task 26645 | total time = 4190.33 ms / 500 tokens 22.53.601.463 I slot print_timing: id 2 | task 26645 | graphs reused = 25417 22.53.601.463 I slot print_timing: id 2 | task 26645 | graph reallocs = 0 / 0 (same size) / (changed size) 22.53.601.500 I slot release: id 2 | task 26645 | stop processing: n_tokens = 727, truncated = 0 22.53.633.844 I slot print_timing: id 0 | task 26646 | prompt eval time = 4189.94 ms / 1040 tokens ( 4.03 ms per token, 248.21 tokens per second) 22.53.633.846 I slot print_timing: id 0 | task 26646 | eval time = 33.02 ms / 2 tokens ( 33.02 ms per token, 30.28 tokens per second) 22.53.633.846 I slot print_timing: id 0 | task 26646 | total time = 4222.96 ms / 1042 tokens 22.53.633.847 I slot print_timing: id 0 | task 26646 | graphs reused = 25417 22.53.633.847 I slot print_timing: id 0 | task 26646 | graph reallocs = 0 / 0 (same size) / (changed size) 22.53.633.902 I slot release: id 0 | task 26646 | stop processing: n_tokens = 1041, truncated = 0 22.53.634.171 I slot print_timing: id 3 | task 26647 | prompt eval time = 4190.72 ms / 789 tokens ( 5.31 ms per token, 188.27 tokens per second) 22.53.634.173 I slot print_timing: id 3 | task 26647 | eval time = 32.22 ms / 2 tokens ( 32.22 ms per token, 31.04 tokens per second) 22.53.634.173 I slot print_timing: id 3 | task 26647 | total time = 4222.94 ms / 791 tokens 22.53.634.174 I slot print_timing: id 3 | task 26647 | graphs reused = 25417 22.53.634.174 I slot print_timing: id 3 | task 26647 | graph reallocs = 0 / 0 (same size) / (changed size) 22.53.634.215 I slot release: id 3 | task 26647 | stop processing: n_tokens = 790, truncated = 0 22.53.634.219 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 336760969125 22.53.636.385 I slot launch_slot_: id 1 | task 26652 | processing task, is_child = 0 22.53.642.858 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 336760969483 22.53.642.928 I slot launch_slot_: id 2 | task 26653 | processing task, is_child = 0 22.53.643.020 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 336761001885 22.53.643.088 I slot launch_slot_: id 0 | task 26654 | processing task, is_child = 0 22.53.643.128 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 336761002198 22.53.643.186 I slot launch_slot_: id 3 | task 26655 | processing task, is_child = 0 22.57.433.022 I slot print_timing: id 0 | task 26654 | prompt processing, n_tokens = 821, progress = 1.00, t = 3.79 s / 216.63 tokens per second 22.58.076.631 I slot print_timing: id 1 | task 26652 | prompt processing, n_tokens = 772, progress = 0.99, t = 3.79 s / 203.71 tokens per second 22.58.076.777 I slot print_timing: id 2 | task 26653 | prompt processing, n_tokens = 780, progress = 0.99, t = 3.79 s / 205.82 tokens per second 22.58.076.943 I slot print_timing: id 3 | task 26655 | prompt processing, n_tokens = 827, progress = 1.00, t = 3.79 s / 218.23 tokens per second 22.58.236.847 I slot print_timing: id 0 | task 26654 | prompt eval time = 4552.15 ms / 825 tokens ( 5.52 ms per token, 181.23 tokens per second) 22.58.236.850 I slot print_timing: id 0 | task 26654 | eval time = 41.50 ms / 2 tokens ( 41.50 ms per token, 24.09 tokens per second) 22.58.236.851 I slot print_timing: id 0 | task 26654 | total time = 4593.65 ms / 827 tokens 22.58.236.852 I slot print_timing: id 0 | task 26654 | graphs reused = 25418 22.58.236.852 I slot print_timing: id 0 | task 26654 | graph reallocs = 0 / 0 (same size) / (changed size) 22.58.236.903 I slot release: id 0 | task 26654 | stop processing: n_tokens = 826, truncated = 0 22.58.237.168 I slot print_timing: id 1 | task 26652 | prompt eval time = 4552.36 ms / 776 tokens ( 5.87 ms per token, 170.46 tokens per second) 22.58.237.170 I slot print_timing: id 1 | task 26652 | eval time = 41.53 ms / 2 tokens ( 41.53 ms per token, 24.08 tokens per second) 22.58.237.171 I slot print_timing: id 1 | task 26652 | total time = 4593.90 ms / 778 tokens 22.58.237.171 I slot print_timing: id 1 | task 26652 | graphs reused = 25418 22.58.237.172 I slot print_timing: id 1 | task 26652 | graph reallocs = 0 / 0 (same size) / (changed size) 22.58.237.217 I slot release: id 1 | task 26652 | stop processing: n_tokens = 777, truncated = 0 22.58.237.487 I slot print_timing: id 2 | task 26653 | prompt eval time = 4552.73 ms / 784 tokens ( 5.81 ms per token, 172.20 tokens per second) 22.58.237.490 I slot print_timing: id 2 | task 26653 | eval time = 41.44 ms / 2 tokens ( 41.44 ms per token, 24.13 tokens per second) 22.58.237.490 I slot print_timing: id 2 | task 26653 | total time = 4594.17 ms / 786 tokens 22.58.237.490 I slot print_timing: id 2 | task 26653 | graphs reused = 25418 22.58.237.490 I slot print_timing: id 2 | task 26653 | graph reallocs = 0 / 0 (same size) / (changed size) 22.58.237.521 I slot release: id 2 | task 26653 | stop processing: n_tokens = 785, truncated = 0 22.58.237.808 I slot print_timing: id 3 | task 26655 | prompt eval time = 4553.17 ms / 831 tokens ( 5.48 ms per token, 182.51 tokens per second) 22.58.237.812 I slot print_timing: id 3 | task 26655 | eval time = 41.27 ms / 2 tokens ( 41.27 ms per token, 24.23 tokens per second) 22.58.237.812 I slot print_timing: id 3 | task 26655 | total time = 4594.44 ms / 833 tokens 22.58.237.812 I slot print_timing: id 3 | task 26655 | graphs reused = 25418 22.58.237.813 I slot print_timing: id 3 | task 26655 | graph reallocs = 0 / 0 (same size) / (changed size) 22.58.237.846 I slot release: id 3 | task 26655 | stop processing: n_tokens = 832, truncated = 0 22.58.243.898 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.832 (> 0.100 thold), f_keep = 0.891 22.58.243.922 I slot launch_slot_: id 0 | task 26660 | processing task, is_child = 0 22.58.249.999 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 777, t_last = 336765605200 22.58.250.070 I slot launch_slot_: id 1 | task 26661 | processing task, is_child = 0 22.58.250.153 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.825 (> 0.100 thold), f_keep = 0.885 22.58.250.170 I slot launch_slot_: id 3 | task 26662 | processing task, is_child = 0 22.58.250.213 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 785, t_last = 336765605504 22.58.251.043 I slot launch_slot_: id 2 | task 26663 | processing task, is_child = 0 23.01.879.167 I slot print_timing: id 0 | task 26660 | prompt eval time = 3586.58 ms / 576 tokens ( 6.23 ms per token, 160.60 tokens per second) 23.01.879.169 I slot print_timing: id 0 | task 26660 | eval time = 41.54 ms / 2 tokens ( 41.54 ms per token, 24.07 tokens per second) 23.01.879.170 I slot print_timing: id 0 | task 26660 | total time = 3628.11 ms / 578 tokens 23.01.879.171 I slot print_timing: id 0 | task 26660 | graphs reused = 25419 23.01.879.171 I slot print_timing: id 0 | task 26660 | graph reallocs = 0 / 0 (same size) / (changed size) 23.01.879.222 I slot release: id 0 | task 26660 | stop processing: n_tokens = 886, truncated = 0 23.01.879.499 I slot print_timing: id 1 | task 26661 | prompt eval time = 3586.79 ms / 677 tokens ( 5.30 ms per token, 188.75 tokens per second) 23.01.879.501 I slot print_timing: id 1 | task 26661 | eval time = 41.56 ms / 2 tokens ( 41.56 ms per token, 24.06 tokens per second) 23.01.879.502 I slot print_timing: id 1 | task 26661 | total time = 3628.36 ms / 679 tokens 23.01.879.502 I slot print_timing: id 1 | task 26661 | graphs reused = 25419 23.01.879.502 I slot print_timing: id 1 | task 26661 | graph reallocs = 0 / 0 (same size) / (changed size) 23.01.879.537 I slot release: id 1 | task 26661 | stop processing: n_tokens = 678, truncated = 0 23.01.879.821 I slot print_timing: id 2 | task 26663 | prompt eval time = 3587.08 ms / 533 tokens ( 6.73 ms per token, 148.59 tokens per second) 23.01.879.823 I slot print_timing: id 2 | task 26663 | eval time = 41.54 ms / 2 tokens ( 41.54 ms per token, 24.07 tokens per second) 23.01.879.823 I slot print_timing: id 2 | task 26663 | total time = 3628.62 ms / 535 tokens 23.01.879.823 I slot print_timing: id 2 | task 26663 | graphs reused = 25419 23.01.879.824 I slot print_timing: id 2 | task 26663 | graph reallocs = 0 / 0 (same size) / (changed size) 23.01.879.874 I slot release: id 2 | task 26663 | stop processing: n_tokens = 849, truncated = 0 23.01.880.168 I slot print_timing: id 3 | task 26662 | prompt eval time = 3587.37 ms / 577 tokens ( 6.22 ms per token, 160.84 tokens per second) 23.01.880.170 I slot print_timing: id 3 | task 26662 | eval time = 41.53 ms / 2 tokens ( 41.53 ms per token, 24.08 tokens per second) 23.01.880.171 I slot print_timing: id 3 | task 26662 | total time = 3628.90 ms / 579 tokens 23.01.880.171 I slot print_timing: id 3 | task 26662 | graphs reused = 25419 23.01.880.172 I slot print_timing: id 3 | task 26662 | graph reallocs = 0 / 0 (same size) / (changed size) 23.01.880.213 I slot release: id 3 | task 26662 | stop processing: n_tokens = 893, truncated = 0 23.01.887.135 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 336769247205 23.01.889.599 I slot launch_slot_: id 0 | task 26668 | processing task, is_child = 0 23.01.896.157 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 336769247520 23.01.896.232 I slot launch_slot_: id 1 | task 26669 | processing task, is_child = 0 23.01.896.326 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 849, t_last = 336769247857 23.01.896.397 I slot launch_slot_: id 2 | task 26670 | processing task, is_child = 0 23.01.896.444 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 893, t_last = 336769248196 23.01.896.513 I slot launch_slot_: id 3 | task 26671 | processing task, is_child = 0 23.05.542.986 I slot print_timing: id 0 | task 26668 | prompt processing, n_tokens = 736, progress = 0.99, t = 3.65 s / 201.84 tokens per second 23.06.186.714 I slot print_timing: id 1 | task 26669 | prompt processing, n_tokens = 809, progress = 1.00, t = 3.65 s / 221.86 tokens per second 23.06.186.891 I slot print_timing: id 2 | task 26670 | prompt processing, n_tokens = 715, progress = 0.99, t = 3.65 s / 196.09 tokens per second 23.06.187.019 I slot print_timing: id 3 | task 26671 | prompt processing, n_tokens = 788, progress = 0.99, t = 3.65 s / 216.11 tokens per second 23.06.347.606 I slot print_timing: id 0 | task 26668 | prompt eval time = 4409.12 ms / 740 tokens ( 5.96 ms per token, 167.83 tokens per second) 23.06.347.611 I slot print_timing: id 0 | task 26668 | eval time = 41.96 ms / 2 tokens ( 41.96 ms per token, 23.83 tokens per second) 23.06.347.612 I slot print_timing: id 0 | task 26668 | total time = 4451.09 ms / 742 tokens 23.06.347.612 I slot print_timing: id 0 | task 26668 | graphs reused = 25420 23.06.347.613 I slot print_timing: id 0 | task 26668 | graph reallocs = 0 / 0 (same size) / (changed size) 23.06.347.661 I slot release: id 0 | task 26668 | stop processing: n_tokens = 741, truncated = 0 23.06.347.942 I slot print_timing: id 1 | task 26669 | prompt eval time = 4409.33 ms / 813 tokens ( 5.42 ms per token, 184.38 tokens per second) 23.06.347.944 I slot print_timing: id 1 | task 26669 | eval time = 42.01 ms / 2 tokens ( 42.01 ms per token, 23.80 tokens per second) 23.06.347.946 I slot print_timing: id 1 | task 26669 | total time = 4451.34 ms / 815 tokens 23.06.347.946 I slot print_timing: id 1 | task 26669 | graphs reused = 25420 23.06.347.946 I slot print_timing: id 1 | task 26669 | graph reallocs = 0 / 0 (same size) / (changed size) 23.06.347.991 I slot release: id 1 | task 26669 | stop processing: n_tokens = 814, truncated = 0 23.06.348.267 I slot print_timing: id 2 | task 26670 | prompt eval time = 4409.67 ms / 719 tokens ( 6.13 ms per token, 163.05 tokens per second) 23.06.348.269 I slot print_timing: id 2 | task 26670 | eval time = 41.94 ms / 2 tokens ( 41.94 ms per token, 23.85 tokens per second) 23.06.348.270 I slot print_timing: id 2 | task 26670 | total time = 4451.61 ms / 721 tokens 23.06.348.270 I slot print_timing: id 2 | task 26670 | graphs reused = 25420 23.06.348.270 I slot print_timing: id 2 | task 26670 | graph reallocs = 0 / 0 (same size) / (changed size) 23.06.348.299 I slot release: id 2 | task 26670 | stop processing: n_tokens = 720, truncated = 0 23.06.348.584 I slot print_timing: id 3 | task 26671 | prompt eval time = 4410.11 ms / 792 tokens ( 5.57 ms per token, 179.59 tokens per second) 23.06.348.588 I slot print_timing: id 3 | task 26671 | eval time = 41.76 ms / 2 tokens ( 41.76 ms per token, 23.94 tokens per second) 23.06.348.588 I slot print_timing: id 3 | task 26671 | total time = 4451.87 ms / 794 tokens 23.06.348.588 I slot print_timing: id 3 | task 26671 | graphs reused = 25420 23.06.348.589 I slot print_timing: id 3 | task 26671 | graph reallocs = 0 / 0 (same size) / (changed size) 23.06.348.631 I slot release: id 3 | task 26671 | stop processing: n_tokens = 793, truncated = 0 23.06.355.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 336773715644 23.06.356.990 I slot launch_slot_: id 0 | task 26676 | processing task, is_child = 0 23.06.362.662 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 814, t_last = 336773715974 23.06.362.728 I slot launch_slot_: id 1 | task 26677 | processing task, is_child = 0 23.06.362.813 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 336773716282 23.06.362.872 I slot launch_slot_: id 2 | task 26678 | processing task, is_child = 0 23.06.362.913 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 336773716614 23.06.362.970 I slot launch_slot_: id 3 | task 26679 | processing task, is_child = 0 23.09.379.729 I slot print_timing: id 0 | task 26676 | prompt processing, n_tokens = 690, progress = 0.99, t = 3.02 s / 228.72 tokens per second 23.10.021.382 I slot print_timing: id 1 | task 26677 | prompt processing, n_tokens = 714, progress = 0.99, t = 3.02 s / 236.68 tokens per second 23.10.021.561 I slot print_timing: id 2 | task 26678 | prompt processing, n_tokens = 690, progress = 0.99, t = 3.02 s / 228.73 tokens per second 23.10.021.686 I slot print_timing: id 3 | task 26679 | prompt processing, n_tokens = 689, progress = 0.99, t = 3.02 s / 228.40 tokens per second 23.10.181.912 I slot print_timing: id 0 | task 26676 | prompt eval time = 3777.52 ms / 694 tokens ( 5.44 ms per token, 183.72 tokens per second) 23.10.181.914 I slot print_timing: id 0 | task 26676 | eval time = 41.42 ms / 2 tokens ( 41.42 ms per token, 24.14 tokens per second) 23.10.181.915 I slot print_timing: id 0 | task 26676 | total time = 3818.94 ms / 696 tokens 23.10.181.915 I slot print_timing: id 0 | task 26676 | graphs reused = 25422 23.10.181.916 I slot print_timing: id 0 | task 26676 | graph reallocs = 0 / 0 (same size) / (changed size) 23.10.181.958 I slot release: id 0 | task 26676 | stop processing: n_tokens = 695, truncated = 0 23.10.182.229 I slot print_timing: id 1 | task 26677 | prompt eval time = 3777.87 ms / 718 tokens ( 5.26 ms per token, 190.05 tokens per second) 23.10.182.234 I slot print_timing: id 1 | task 26677 | eval time = 41.32 ms / 2 tokens ( 41.32 ms per token, 24.20 tokens per second) 23.10.182.235 I slot print_timing: id 1 | task 26677 | total time = 3819.19 ms / 720 tokens 23.10.182.235 I slot print_timing: id 1 | task 26677 | graphs reused = 25422 23.10.182.235 I slot print_timing: id 1 | task 26677 | graph reallocs = 0 / 0 (same size) / (changed size) 23.10.182.272 I slot release: id 1 | task 26677 | stop processing: n_tokens = 719, truncated = 0 23.10.182.571 I slot print_timing: id 2 | task 26678 | prompt eval time = 3778.15 ms / 694 tokens ( 5.44 ms per token, 183.69 tokens per second) 23.10.182.574 I slot print_timing: id 2 | task 26678 | eval time = 41.33 ms / 2 tokens ( 41.33 ms per token, 24.20 tokens per second) 23.10.182.574 I slot print_timing: id 2 | task 26678 | total time = 3819.48 ms / 696 tokens 23.10.182.574 I slot print_timing: id 2 | task 26678 | graphs reused = 25422 23.10.182.575 I slot print_timing: id 2 | task 26678 | graph reallocs = 0 / 0 (same size) / (changed size) 23.10.182.603 I slot release: id 2 | task 26678 | stop processing: n_tokens = 695, truncated = 0 23.10.182.908 I slot print_timing: id 3 | task 26679 | prompt eval time = 3778.55 ms / 693 tokens ( 5.45 ms per token, 183.40 tokens per second) 23.10.182.912 I slot print_timing: id 3 | task 26679 | eval time = 41.22 ms / 2 tokens ( 41.22 ms per token, 24.26 tokens per second) 23.10.182.912 I slot print_timing: id 3 | task 26679 | total time = 3819.77 ms / 695 tokens 23.10.182.913 I slot print_timing: id 3 | task 26679 | graphs reused = 25422 23.10.182.913 I slot print_timing: id 3 | task 26679 | graph reallocs = 0 / 0 (same size) / (changed size) 23.10.182.941 I slot release: id 3 | task 26679 | stop processing: n_tokens = 694, truncated = 0 23.10.188.720 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.881 23.10.188.743 I slot launch_slot_: id 0 | task 26684 | processing task, is_child = 0 23.10.194.016 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.885 23.10.194.044 I slot launch_slot_: id 3 | task 26686 | processing task, is_child = 0 23.10.194.124 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.851 23.10.194.141 I slot launch_slot_: id 1 | task 26685 | processing task, is_child = 0 23.10.194.183 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.881 23.10.194.202 I slot launch_slot_: id 2 | task 26687 | processing task, is_child = 0 23.13.241.417 I slot print_timing: id 1 | task 26685 | prompt eval time = 2947.18 ms / 488 tokens ( 6.04 ms per token, 165.58 tokens per second) 23.13.241.419 I slot print_timing: id 1 | task 26685 | eval time = 99.93 ms / 2 tokens ( 99.93 ms per token, 10.01 tokens per second) 23.13.241.420 I slot print_timing: id 1 | task 26685 | total time = 3047.11 ms / 490 tokens 23.13.241.420 I slot print_timing: id 1 | task 26685 | graphs reused = 25422 23.13.241.420 I slot print_timing: id 1 | task 26685 | graph reallocs = 0 / 0 (same size) / (changed size) 23.13.241.463 I slot release: id 1 | task 26685 | stop processing: n_tokens = 691, truncated = 0 23.13.241.857 I slot print_timing: id 2 | task 26687 | prompt eval time = 2947.47 ms / 510 tokens ( 5.78 ms per token, 173.03 tokens per second) 23.13.241.860 I slot print_timing: id 2 | task 26687 | eval time = 99.99 ms / 2 tokens ( 99.99 ms per token, 10.00 tokens per second) 23.13.241.861 I slot print_timing: id 2 | task 26687 | total time = 3047.45 ms / 512 tokens 23.13.241.861 I slot print_timing: id 2 | task 26687 | graphs reused = 25422 23.13.241.862 I slot print_timing: id 2 | task 26687 | graph reallocs = 0 / 0 (same size) / (changed size) 23.13.241.901 I slot release: id 2 | task 26687 | stop processing: n_tokens = 689, truncated = 0 23.13.274.187 I slot print_timing: id 0 | task 26684 | prompt eval time = 3046.85 ms / 518 tokens ( 5.88 ms per token, 170.01 tokens per second) 23.13.274.189 I slot print_timing: id 0 | task 26684 | eval time = 33.12 ms / 2 tokens ( 33.12 ms per token, 30.19 tokens per second) 23.13.274.190 I slot print_timing: id 0 | task 26684 | total time = 3079.97 ms / 520 tokens 23.13.274.190 I slot print_timing: id 0 | task 26684 | graphs reused = 25422 23.13.274.190 I slot print_timing: id 0 | task 26684 | graph reallocs = 0 / 0 (same size) / (changed size) 23.13.274.231 I slot release: id 0 | task 26684 | stop processing: n_tokens = 697, truncated = 0 23.13.274.502 I slot print_timing: id 3 | task 26686 | prompt eval time = 3047.98 ms / 524 tokens ( 5.82 ms per token, 171.92 tokens per second) 23.13.274.504 I slot print_timing: id 3 | task 26686 | eval time = 32.02 ms / 2 tokens ( 32.02 ms per token, 31.23 tokens per second) 23.13.274.505 I slot print_timing: id 3 | task 26686 | total time = 3080.00 ms / 526 tokens 23.13.274.505 I slot print_timing: id 3 | task 26686 | graphs reused = 25422 23.13.274.505 I slot print_timing: id 3 | task 26686 | graph reallocs = 0 / 0 (same size) / (changed size) 23.13.274.543 I slot release: id 3 | task 26686 | stop processing: n_tokens = 702, truncated = 0 23.13.274.548 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.890 23.13.274.574 I slot launch_slot_: id 2 | task 26692 | processing task, is_child = 0 23.13.281.325 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.837 (> 0.100 thold), f_keep = 0.878 23.13.281.352 I slot launch_slot_: id 0 | task 26693 | processing task, is_child = 0 23.13.281.433 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.886 23.13.281.449 I slot launch_slot_: id 1 | task 26694 | processing task, is_child = 0 23.13.281.487 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 702, t_last = 336780642526 23.13.281.543 I slot launch_slot_: id 3 | task 26695 | processing task, is_child = 0 23.16.718.596 I slot print_timing: id 0 | task 26693 | prompt processing, n_tokens = 547, progress = 0.99, t = 3.44 s / 159.17 tokens per second 23.16.718.764 I slot print_timing: id 2 | task 26692 | prompt processing, n_tokens = 516, progress = 0.99, t = 3.44 s / 150.16 tokens per second 23.16.718.910 I slot print_timing: id 3 | task 26695 | prompt processing, n_tokens = 870, progress = 1.00, t = 3.44 s / 253.18 tokens per second 23.16.837.982 I slot print_timing: id 1 | task 26694 | prompt eval time = 3436.94 ms / 489 tokens ( 7.03 ms per token, 142.28 tokens per second) 23.16.837.984 I slot print_timing: id 1 | task 26694 | eval time = 119.40 ms / 2 tokens ( 119.40 ms per token, 8.38 tokens per second) 23.16.837.985 I slot print_timing: id 1 | task 26694 | total time = 3556.34 ms / 491 tokens 23.16.837.986 I slot print_timing: id 1 | task 26694 | graphs reused = 25422 23.16.837.986 I slot print_timing: id 1 | task 26694 | graph reallocs = 0 / 0 (same size) / (changed size) 23.16.838.034 I slot release: id 1 | task 26694 | stop processing: n_tokens = 692, truncated = 0 23.16.878.806 I slot print_timing: id 0 | task 26693 | prompt eval time = 3556.14 ms / 551 tokens ( 6.45 ms per token, 154.94 tokens per second) 23.16.878.809 I slot print_timing: id 0 | task 26693 | eval time = 41.12 ms / 2 tokens ( 41.12 ms per token, 24.32 tokens per second) 23.16.878.809 I slot print_timing: id 0 | task 26693 | total time = 3597.26 ms / 553 tokens 23.16.878.810 I slot print_timing: id 0 | task 26693 | graphs reused = 25422 23.16.878.810 I slot print_timing: id 0 | task 26693 | graph reallocs = 0 / 0 (same size) / (changed size) 23.16.878.853 I slot release: id 0 | task 26693 | stop processing: n_tokens = 732, truncated = 0 23.16.879.185 I slot print_timing: id 2 | task 26692 | prompt eval time = 3556.67 ms / 520 tokens ( 6.84 ms per token, 146.20 tokens per second) 23.16.879.189 I slot print_timing: id 2 | task 26692 | eval time = 40.75 ms / 2 tokens ( 40.75 ms per token, 24.54 tokens per second) 23.16.879.190 I slot print_timing: id 2 | task 26692 | total time = 3597.42 ms / 522 tokens 23.16.879.190 I slot print_timing: id 2 | task 26692 | graphs reused = 25422 23.16.879.191 I slot print_timing: id 2 | task 26692 | graph reallocs = 0 / 0 (same size) / (changed size) 23.16.879.221 I slot release: id 2 | task 26692 | stop processing: n_tokens = 699, truncated = 0 23.16.879.493 I slot print_timing: id 3 | task 26695 | prompt eval time = 3557.22 ms / 874 tokens ( 4.07 ms per token, 245.70 tokens per second) 23.16.879.495 I slot print_timing: id 3 | task 26695 | eval time = 40.43 ms / 2 tokens ( 40.43 ms per token, 24.73 tokens per second) 23.16.879.495 I slot print_timing: id 3 | task 26695 | total time = 3597.65 ms / 876 tokens 23.16.879.496 I slot print_timing: id 3 | task 26695 | graphs reused = 25422 23.16.879.496 I slot print_timing: id 3 | task 26695 | graph reallocs = 0 / 0 (same size) / (changed size) 23.16.879.545 I slot release: id 3 | task 26695 | stop processing: n_tokens = 875, truncated = 0 23.16.879.552 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.880 23.16.879.589 I slot launch_slot_: id 3 | task 26700 | processing task, is_child = 0 23.16.889.597 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 336784206017 23.16.889.673 I slot launch_slot_: id 1 | task 26702 | processing task, is_child = 0 23.16.889.758 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 336784246836 23.16.889.820 I slot launch_slot_: id 0 | task 26703 | processing task, is_child = 0 23.16.889.862 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 699, t_last = 336784247204 23.16.889.925 I slot launch_slot_: id 2 | task 26704 | processing task, is_child = 0 23.20.018.211 I slot print_timing: id 0 | task 26703 | prompt processing, n_tokens = 582, progress = 0.53, t = 3.13 s / 186.07 tokens per second 23.20.018.263 I slot print_timing: id 1 | task 26702 | prompt processing, n_tokens = 580, progress = 0.53, t = 3.13 s / 185.43 tokens per second 23.20.018.300 I slot print_timing: id 2 | task 26704 | prompt processing, n_tokens = 589, progress = 0.53, t = 3.13 s / 188.31 tokens per second 23.22.064.972 I slot print_timing: id 3 | task 26700 | prompt eval time = 3132.30 ms / 503 tokens ( 6.23 ms per token, 160.58 tokens per second) 23.22.064.975 I slot print_timing: id 3 | task 26700 | eval time = 2046.77 ms / 2 tokens ( 2046.77 ms per token, 0.49 tokens per second) 23.22.064.975 I slot print_timing: id 3 | task 26700 | total time = 5179.07 ms / 505 tokens 23.22.064.976 I slot print_timing: id 3 | task 26700 | graphs reused = 25422 23.22.064.976 I slot print_timing: id 3 | task 26700 | graph reallocs = 0 / 0 (same size) / (changed size) 23.22.065.029 I slot release: id 3 | task 26700 | stop processing: n_tokens = 862, truncated = 0 23.22.065.041 I slot print_timing: id 0 | task 26703 | prompt processing, n_tokens = 1094, progress = 1.00, t = 5.17 s / 211.41 tokens per second 23.22.065.258 I slot print_timing: id 1 | task 26702 | prompt processing, n_tokens = 1092, progress = 1.00, t = 5.17 s / 211.03 tokens per second 23.22.065.463 I slot print_timing: id 2 | task 26704 | prompt processing, n_tokens = 1101, progress = 1.00, t = 5.17 s / 212.77 tokens per second 23.22.157.734 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 336789433012 23.22.161.680 I slot launch_slot_: id 3 | task 26708 | processing task, is_child = 0 23.23.048.270 I slot print_timing: id 0 | task 26703 | prompt eval time = 5267.20 ms / 1098 tokens ( 4.80 ms per token, 208.46 tokens per second) 23.23.048.273 I slot print_timing: id 0 | task 26703 | eval time = 891.14 ms / 2 tokens ( 891.14 ms per token, 1.12 tokens per second) 23.23.048.273 I slot print_timing: id 0 | task 26703 | total time = 6158.34 ms / 1100 tokens 23.23.048.274 I slot print_timing: id 0 | task 26703 | graphs reused = 25422 23.23.048.274 I slot print_timing: id 0 | task 26703 | graph reallocs = 0 / 0 (same size) / (changed size) 23.23.048.335 I slot release: id 0 | task 26703 | stop processing: n_tokens = 1099, truncated = 0 23.23.048.654 I slot print_timing: id 1 | task 26702 | prompt eval time = 5267.44 ms / 1096 tokens ( 4.81 ms per token, 208.07 tokens per second) 23.23.048.657 I slot print_timing: id 1 | task 26702 | eval time = 891.23 ms / 2 tokens ( 891.23 ms per token, 1.12 tokens per second) 23.23.048.657 I slot print_timing: id 1 | task 26702 | total time = 6158.66 ms / 1098 tokens 23.23.048.658 I slot print_timing: id 1 | task 26702 | graphs reused = 25422 23.23.048.658 I slot print_timing: id 1 | task 26702 | graph reallocs = 0 / 0 (same size) / (changed size) 23.23.048.697 I slot release: id 1 | task 26702 | stop processing: n_tokens = 1097, truncated = 0 23.23.049.027 I slot print_timing: id 2 | task 26704 | prompt eval time = 5267.69 ms / 1105 tokens ( 4.77 ms per token, 209.77 tokens per second) 23.23.049.040 I slot print_timing: id 2 | task 26704 | eval time = 891.29 ms / 2 tokens ( 891.29 ms per token, 1.12 tokens per second) 23.23.049.041 I slot print_timing: id 2 | task 26704 | total time = 6158.99 ms / 1107 tokens 23.23.049.041 I slot print_timing: id 2 | task 26704 | graphs reused = 25422 23.23.049.043 I slot print_timing: id 2 | task 26704 | graph reallocs = 0 / 0 (same size) / (changed size) 23.23.049.110 I slot release: id 2 | task 26704 | stop processing: n_tokens = 1106, truncated = 0 23.23.736.792 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.897 23.23.736.821 I slot launch_slot_: id 0 | task 26712 | processing task, is_child = 0 23.23.744.399 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.892 23.23.744.427 I slot launch_slot_: id 2 | task 26713 | processing task, is_child = 0 23.23.744.480 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.898 23.23.744.497 I slot launch_slot_: id 1 | task 26714 | processing task, is_child = 0 23.25.787.775 I slot print_timing: id 3 | task 26708 | prompt eval time = 1575.10 ms / 1086 tokens ( 1.45 ms per token, 689.48 tokens per second) 23.25.787.777 I slot print_timing: id 3 | task 26708 | eval time = 2050.98 ms / 2 tokens ( 2050.98 ms per token, 0.49 tokens per second) 23.25.787.778 I slot print_timing: id 3 | task 26708 | total time = 3626.08 ms / 1088 tokens 23.25.787.778 I slot print_timing: id 3 | task 26708 | graphs reused = 25422 23.25.787.778 I slot print_timing: id 3 | task 26708 | graph reallocs = 0 / 0 (same size) / (changed size) 23.25.787.837 I slot release: id 3 | task 26708 | stop processing: n_tokens = 1087, truncated = 0 23.25.880.635 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.907 23.25.880.667 I slot launch_slot_: id 3 | task 26717 | processing task, is_child = 0 23.25.977.258 I slot print_timing: id 0 | task 26712 | prompt eval time = 2135.47 ms / 504 tokens ( 4.24 ms per token, 236.01 tokens per second) 23.25.977.262 I slot print_timing: id 0 | task 26712 | eval time = 97.28 ms / 2 tokens ( 97.28 ms per token, 10.28 tokens per second) 23.25.977.263 I slot print_timing: id 0 | task 26712 | total time = 2232.76 ms / 506 tokens 23.25.977.263 I slot print_timing: id 0 | task 26712 | graphs reused = 25422 23.25.977.264 I slot print_timing: id 0 | task 26712 | graph reallocs = 0 / 0 (same size) / (changed size) 23.25.977.314 I slot release: id 0 | task 26712 | stop processing: n_tokens = 1087, truncated = 0 23.25.977.577 I slot print_timing: id 1 | task 26714 | prompt eval time = 2135.61 ms / 515 tokens ( 4.15 ms per token, 241.15 tokens per second) 23.25.977.579 I slot print_timing: id 1 | task 26714 | eval time = 97.34 ms / 2 tokens ( 97.34 ms per token, 10.27 tokens per second) 23.25.977.579 I slot print_timing: id 1 | task 26714 | total time = 2232.95 ms / 517 tokens 23.25.977.579 I slot print_timing: id 1 | task 26714 | graphs reused = 25422 23.25.977.579 I slot print_timing: id 1 | task 26714 | graph reallocs = 0 / 0 (same size) / (changed size) 23.25.977.626 I slot release: id 1 | task 26714 | stop processing: n_tokens = 1096, truncated = 0 23.25.977.925 I slot print_timing: id 2 | task 26713 | prompt eval time = 2135.89 ms / 505 tokens ( 4.23 ms per token, 236.44 tokens per second) 23.25.977.928 I slot print_timing: id 2 | task 26713 | eval time = 97.30 ms / 2 tokens ( 97.30 ms per token, 10.28 tokens per second) 23.25.977.929 I slot print_timing: id 2 | task 26713 | total time = 2233.18 ms / 507 tokens 23.25.977.929 I slot print_timing: id 2 | task 26713 | graphs reused = 25422 23.25.977.929 I slot print_timing: id 2 | task 26713 | graph reallocs = 0 / 0 (same size) / (changed size) 23.25.977.967 I slot release: id 2 | task 26713 | stop processing: n_tokens = 1095, truncated = 0 23.26.664.310 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.907 23.26.664.338 I slot launch_slot_: id 0 | task 26721 | processing task, is_child = 0 23.26.672.880 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.900 23.26.672.901 I slot launch_slot_: id 1 | task 26722 | processing task, is_child = 0 23.26.672.954 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.900 23.26.672.972 I slot launch_slot_: id 2 | task 26723 | processing task, is_child = 0 23.28.103.482 I slot print_timing: id 3 | task 26717 | prompt eval time = 783.63 ms / 525 tokens ( 1.49 ms per token, 669.96 tokens per second) 23.28.103.487 I slot print_timing: id 3 | task 26717 | eval time = 1439.17 ms / 2 tokens ( 1439.17 ms per token, 0.69 tokens per second) 23.28.103.488 I slot print_timing: id 3 | task 26717 | total time = 2222.80 ms / 527 tokens 23.28.103.489 I slot print_timing: id 3 | task 26717 | graphs reused = 25422 23.28.103.489 I slot print_timing: id 3 | task 26717 | graph reallocs = 0 / 0 (same size) / (changed size) 23.28.103.541 I slot release: id 3 | task 26717 | stop processing: n_tokens = 1096, truncated = 0 23.28.841.925 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.900 23.28.841.970 I slot launch_slot_: id 3 | task 26726 | processing task, is_child = 0 23.29.562.841 I slot print_timing: id 0 | task 26721 | prompt eval time = 2168.63 ms / 506 tokens ( 4.29 ms per token, 233.33 tokens per second) 23.29.562.844 I slot print_timing: id 0 | task 26721 | eval time = 721.23 ms / 2 tokens ( 721.23 ms per token, 1.39 tokens per second) 23.29.562.844 I slot print_timing: id 0 | task 26721 | total time = 2889.86 ms / 508 tokens 23.29.562.845 I slot print_timing: id 0 | task 26721 | graphs reused = 25422 23.29.562.845 I slot print_timing: id 0 | task 26721 | graph reallocs = 0 / 0 (same size) / (changed size) 23.29.562.902 I slot release: id 0 | task 26721 | stop processing: n_tokens = 1089, truncated = 0 23.29.563.611 I slot print_timing: id 2 | task 26723 | prompt eval time = 2168.74 ms / 507 tokens ( 4.28 ms per token, 233.78 tokens per second) 23.29.563.615 I slot print_timing: id 2 | task 26723 | eval time = 721.69 ms / 2 tokens ( 721.69 ms per token, 1.39 tokens per second) 23.29.563.615 I slot print_timing: id 2 | task 26723 | total time = 2890.43 ms / 509 tokens 23.29.563.616 I slot print_timing: id 2 | task 26723 | graphs reused = 25422 23.29.563.616 I slot print_timing: id 2 | task 26723 | graph reallocs = 0 / 0 (same size) / (changed size) 23.29.563.664 I slot release: id 2 | task 26723 | stop processing: n_tokens = 1097, truncated = 0 23.29.617.136 I slot print_timing: id 1 | task 26722 | prompt eval time = 2890.22 ms / 523 tokens ( 5.53 ms per token, 180.96 tokens per second) 23.29.617.141 I slot print_timing: id 1 | task 26722 | eval time = 53.81 ms / 2 tokens ( 53.81 ms per token, 18.58 tokens per second) 23.29.617.141 I slot print_timing: id 1 | task 26722 | total time = 2944.03 ms / 525 tokens 23.29.617.142 I slot print_timing: id 1 | task 26722 | graphs reused = 25422 23.29.617.142 I slot print_timing: id 1 | task 26722 | graph reallocs = 0 / 0 (same size) / (changed size) 23.29.617.196 I slot release: id 1 | task 26722 | stop processing: n_tokens = 1104, truncated = 0 23.29.617.574 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.905 23.29.617.607 I slot launch_slot_: id 0 | task 26729 | processing task, is_child = 0 23.29.624.662 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.893 23.29.624.701 I slot launch_slot_: id 1 | task 26730 | processing task, is_child = 0 23.29.624.760 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.899 23.29.624.779 I slot launch_slot_: id 2 | task 26731 | processing task, is_child = 0 23.31.667.482 I slot print_timing: id 3 | task 26726 | prompt eval time = 775.41 ms / 510 tokens ( 1.52 ms per token, 657.72 tokens per second) 23.31.667.485 I slot print_timing: id 3 | task 26726 | eval time = 2049.91 ms / 2 tokens ( 2049.91 ms per token, 0.49 tokens per second) 23.31.667.485 I slot print_timing: id 3 | task 26726 | total time = 2825.31 ms / 512 tokens 23.31.667.486 I slot print_timing: id 3 | task 26726 | graphs reused = 25422 23.31.667.486 I slot print_timing: id 3 | task 26726 | graph reallocs = 0 / 0 (same size) / (changed size) 23.31.667.543 I slot release: id 3 | task 26726 | stop processing: n_tokens = 1090, truncated = 0 23.31.760.625 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1090, t_last = 336799035527 23.31.765.263 I slot launch_slot_: id 3 | task 26734 | processing task, is_child = 0 23.32.403.757 I slot print_timing: id 0 | task 26729 | prompt eval time = 2135.11 ms / 510 tokens ( 4.19 ms per token, 238.86 tokens per second) 23.32.403.759 I slot print_timing: id 0 | task 26729 | eval time = 643.86 ms / 2 tokens ( 643.86 ms per token, 1.55 tokens per second) 23.32.403.760 I slot print_timing: id 0 | task 26729 | total time = 2778.97 ms / 512 tokens 23.32.403.760 I slot print_timing: id 0 | task 26729 | graphs reused = 25422 23.32.403.761 I slot print_timing: id 0 | task 26729 | graph reallocs = 0 / 0 (same size) / (changed size) 23.32.403.815 I slot release: id 0 | task 26729 | stop processing: n_tokens = 1093, truncated = 0 23.32.404.088 I slot print_timing: id 1 | task 26730 | prompt eval time = 2135.31 ms / 506 tokens ( 4.22 ms per token, 236.97 tokens per second) 23.32.404.090 I slot print_timing: id 1 | task 26730 | eval time = 643.85 ms / 2 tokens ( 643.85 ms per token, 1.55 tokens per second) 23.32.404.090 I slot print_timing: id 1 | task 26730 | total time = 2779.16 ms / 508 tokens 23.32.404.091 I slot print_timing: id 1 | task 26730 | graphs reused = 25422 23.32.404.091 I slot print_timing: id 1 | task 26730 | graph reallocs = 0 / 0 (same size) / (changed size) 23.32.404.138 I slot release: id 1 | task 26730 | stop processing: n_tokens = 1094, truncated = 0 23.32.404.546 I slot print_timing: id 2 | task 26731 | prompt eval time = 2135.58 ms / 502 tokens ( 4.25 ms per token, 235.07 tokens per second) 23.32.404.549 I slot print_timing: id 2 | task 26731 | eval time = 643.93 ms / 2 tokens ( 643.93 ms per token, 1.55 tokens per second) 23.32.404.550 I slot print_timing: id 2 | task 26731 | total time = 2779.51 ms / 504 tokens 23.32.404.550 I slot print_timing: id 2 | task 26731 | graphs reused = 25422 23.32.404.550 I slot print_timing: id 2 | task 26731 | graph reallocs = 0 / 0 (same size) / (changed size) 23.32.404.604 I slot release: id 2 | task 26731 | stop processing: n_tokens = 1092, truncated = 0 23.33.089.171 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1093, t_last = 336799771798 23.33.092.494 I slot launch_slot_: id 0 | task 26738 | processing task, is_child = 0 23.33.098.636 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1094, t_last = 336799772121 23.33.098.724 I slot launch_slot_: id 1 | task 26739 | processing task, is_child = 0 23.33.098.783 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1092, t_last = 336799772587 23.33.098.865 I slot launch_slot_: id 2 | task 26740 | processing task, is_child = 0 23.35.386.764 I slot print_timing: id 3 | task 26734 | prompt eval time = 1323.89 ms / 983 tokens ( 1.35 ms per token, 742.51 tokens per second) 23.35.386.766 I slot print_timing: id 3 | task 26734 | eval time = 2297.59 ms / 2 tokens ( 2297.59 ms per token, 0.44 tokens per second) 23.35.386.768 I slot print_timing: id 3 | task 26734 | total time = 3621.48 ms / 985 tokens 23.35.386.768 I slot print_timing: id 3 | task 26734 | graphs reused = 25422 23.35.386.768 I slot print_timing: id 3 | task 26734 | graph reallocs = 0 / 0 (same size) / (changed size) 23.35.386.833 I slot release: id 3 | task 26734 | stop processing: n_tokens = 984, truncated = 0 23.37.365.661 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.886 23.37.365.711 I slot launch_slot_: id 3 | task 26743 | processing task, is_child = 0 23.37.365.723 I slot print_timing: id 0 | task 26738 | prompt processing, n_tokens = 1062, progress = 1.00, t = 4.27 s / 248.90 tokens per second 23.37.414.595 I slot print_timing: id 1 | task 26739 | prompt processing, n_tokens = 992, progress = 1.00, t = 4.27 s / 232.50 tokens per second 23.37.414.760 I slot print_timing: id 2 | task 26740 | prompt processing, n_tokens = 1033, progress = 1.00, t = 4.27 s / 242.11 tokens per second 23.38.271.266 I slot print_timing: id 0 | task 26738 | prompt eval time = 4485.04 ms / 1066 tokens ( 4.21 ms per token, 237.68 tokens per second) 23.38.271.271 I slot print_timing: id 0 | task 26738 | eval time = 687.35 ms / 2 tokens ( 687.35 ms per token, 1.45 tokens per second) 23.38.271.271 I slot print_timing: id 0 | task 26738 | total time = 5172.39 ms / 1068 tokens 23.38.271.272 I slot print_timing: id 0 | task 26738 | graphs reused = 25422 23.38.271.272 I slot print_timing: id 0 | task 26738 | graph reallocs = 0 / 0 (same size) / (changed size) 23.38.271.338 I slot release: id 0 | task 26738 | stop processing: n_tokens = 1067, truncated = 0 23.38.271.677 I slot print_timing: id 1 | task 26739 | prompt eval time = 4485.29 ms / 996 tokens ( 4.50 ms per token, 222.06 tokens per second) 23.38.271.679 I slot print_timing: id 1 | task 26739 | eval time = 687.43 ms / 2 tokens ( 687.43 ms per token, 1.45 tokens per second) 23.38.271.680 I slot print_timing: id 1 | task 26739 | total time = 5172.72 ms / 998 tokens 23.38.271.680 I slot print_timing: id 1 | task 26739 | graphs reused = 25422 23.38.271.680 I slot print_timing: id 1 | task 26739 | graph reallocs = 0 / 0 (same size) / (changed size) 23.38.271.723 I slot release: id 1 | task 26739 | stop processing: n_tokens = 997, truncated = 0 23.38.272.061 I slot print_timing: id 2 | task 26740 | prompt eval time = 4485.54 ms / 1037 tokens ( 4.33 ms per token, 231.19 tokens per second) 23.38.272.065 I slot print_timing: id 2 | task 26740 | eval time = 687.49 ms / 2 tokens ( 687.49 ms per token, 1.45 tokens per second) 23.38.272.066 I slot print_timing: id 2 | task 26740 | total time = 5173.03 ms / 1039 tokens 23.38.272.066 I slot print_timing: id 2 | task 26740 | graphs reused = 25422 23.38.272.066 I slot print_timing: id 2 | task 26740 | graph reallocs = 0 / 0 (same size) / (changed size) 23.38.272.130 I slot release: id 2 | task 26740 | stop processing: n_tokens = 1038, truncated = 0 23.38.310.272 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.817 23.38.310.301 I slot launch_slot_: id 0 | task 26747 | processing task, is_child = 0 23.38.316.113 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 997, t_last = 336805639706 23.38.316.196 I slot launch_slot_: id 1 | task 26748 | processing task, is_child = 0 23.38.316.266 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1038, t_last = 336805640113 23.38.316.340 I slot launch_slot_: id 2 | task 26749 | processing task, is_child = 0 23.39.847.149 I slot print_timing: id 3 | task 26743 | prompt eval time = 895.34 ms / 527 tokens ( 1.70 ms per token, 588.61 tokens per second) 23.39.847.154 I slot print_timing: id 3 | task 26743 | eval time = 1536.87 ms / 2 tokens ( 1536.87 ms per token, 0.65 tokens per second) 23.39.847.154 I slot print_timing: id 3 | task 26743 | total time = 2432.21 ms / 529 tokens 23.39.847.155 I slot print_timing: id 3 | task 26743 | graphs reused = 25422 23.39.847.155 I slot print_timing: id 3 | task 26743 | graph reallocs = 0 / 0 (same size) / (changed size) 23.39.847.212 I slot release: id 3 | task 26743 | stop processing: n_tokens = 995, truncated = 0 23.41.217.794 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 336807215195 23.41.222.722 I slot launch_slot_: id 3 | task 26752 | processing task, is_child = 0 23.41.658.958 I slot print_timing: id 0 | task 26747 | prompt eval time = 2901.44 ms / 457 tokens ( 6.35 ms per token, 157.51 tokens per second) 23.41.658.963 I slot print_timing: id 0 | task 26747 | eval time = 441.17 ms / 2 tokens ( 441.17 ms per token, 2.27 tokens per second) 23.41.658.964 I slot print_timing: id 0 | task 26747 | total time = 3342.61 ms / 459 tokens 23.41.658.965 I slot print_timing: id 0 | task 26747 | graphs reused = 25422 23.41.658.965 I slot print_timing: id 0 | task 26747 | graph reallocs = 0 / 0 (same size) / (changed size) 23.41.659.026 I slot release: id 0 | task 26747 | stop processing: n_tokens = 1008, truncated = 0 23.42.334.788 I slot print_timing: id 1 | task 26748 | prompt eval time = 3342.86 ms / 731 tokens ( 4.57 ms per token, 218.67 tokens per second) 23.42.334.791 I slot print_timing: id 1 | task 26748 | eval time = 675.44 ms / 2 tokens ( 675.44 ms per token, 1.48 tokens per second) 23.42.334.791 I slot print_timing: id 1 | task 26748 | total time = 4018.30 ms / 733 tokens 23.42.334.792 I slot print_timing: id 1 | task 26748 | graphs reused = 25422 23.42.334.792 I slot print_timing: id 1 | task 26748 | graph reallocs = 0 / 0 (same size) / (changed size) 23.42.334.834 I slot release: id 1 | task 26748 | stop processing: n_tokens = 732, truncated = 0 23.42.335.175 I slot print_timing: id 2 | task 26749 | prompt eval time = 3343.22 ms / 774 tokens ( 4.32 ms per token, 231.51 tokens per second) 23.42.335.177 I slot print_timing: id 2 | task 26749 | eval time = 675.41 ms / 2 tokens ( 675.41 ms per token, 1.48 tokens per second) 23.42.335.177 I slot print_timing: id 2 | task 26749 | total time = 4018.63 ms / 776 tokens 23.42.335.178 I slot print_timing: id 2 | task 26749 | graphs reused = 25422 23.42.335.178 I slot print_timing: id 2 | task 26749 | graph reallocs = 0 / 0 (same size) / (changed size) 23.42.335.215 I slot release: id 2 | task 26749 | stop processing: n_tokens = 775, truncated = 0 23.42.335.220 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.865 23.42.335.245 I slot launch_slot_: id 1 | task 26755 | processing task, is_child = 0 23.42.342.449 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.814 23.42.342.475 I slot launch_slot_: id 2 | task 26756 | processing task, is_child = 0 23.42.342.530 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1008, t_last = 336809027010 23.42.343.407 I slot launch_slot_: id 0 | task 26757 | processing task, is_child = 0 23.44.632.454 I slot print_timing: id 3 | task 26752 | prompt eval time = 3301.07 ms / 706 tokens ( 4.68 ms per token, 213.87 tokens per second) 23.44.632.457 I slot print_timing: id 3 | task 26752 | eval time = 108.25 ms / 2 tokens ( 108.25 ms per token, 9.24 tokens per second) 23.44.632.457 I slot print_timing: id 3 | task 26752 | total time = 3409.32 ms / 708 tokens 23.44.632.458 I slot print_timing: id 3 | task 26752 | graphs reused = 25422 23.44.632.458 I slot print_timing: id 3 | task 26752 | graph reallocs = 0 / 0 (same size) / (changed size) 23.44.632.544 I slot release: id 3 | task 26752 | stop processing: n_tokens = 707, truncated = 0 23.44.665.334 I slot print_timing: id 0 | task 26757 | prompt eval time = 2288.00 ms / 457 tokens ( 5.01 ms per token, 199.74 tokens per second) 23.44.665.337 I slot print_timing: id 0 | task 26757 | eval time = 33.92 ms / 2 tokens ( 33.92 ms per token, 29.48 tokens per second) 23.44.665.338 I slot print_timing: id 0 | task 26757 | total time = 2321.91 ms / 459 tokens 23.44.665.338 I slot print_timing: id 0 | task 26757 | graphs reused = 25422 23.44.665.339 I slot print_timing: id 0 | task 26757 | graph reallocs = 0 / 0 (same size) / (changed size) 23.44.665.379 I slot release: id 0 | task 26757 | stop processing: n_tokens = 716, truncated = 0 23.44.665.643 I slot print_timing: id 1 | task 26755 | prompt eval time = 2288.17 ms / 506 tokens ( 4.52 ms per token, 221.14 tokens per second) 23.44.665.645 I slot print_timing: id 1 | task 26755 | eval time = 33.94 ms / 2 tokens ( 33.94 ms per token, 29.46 tokens per second) 23.44.665.646 I slot print_timing: id 1 | task 26755 | total time = 2322.11 ms / 508 tokens 23.44.665.646 I slot print_timing: id 1 | task 26755 | graphs reused = 25422 23.44.665.646 I slot print_timing: id 1 | task 26755 | graph reallocs = 0 / 0 (same size) / (changed size) 23.44.665.682 I slot release: id 1 | task 26755 | stop processing: n_tokens = 722, truncated = 0 23.44.665.959 I slot print_timing: id 2 | task 26756 | prompt eval time = 2288.49 ms / 465 tokens ( 4.92 ms per token, 203.19 tokens per second) 23.44.665.963 I slot print_timing: id 2 | task 26756 | eval time = 33.81 ms / 2 tokens ( 33.81 ms per token, 29.58 tokens per second) 23.44.665.963 I slot print_timing: id 2 | task 26756 | total time = 2322.30 ms / 467 tokens 23.44.665.963 I slot print_timing: id 2 | task 26756 | graphs reused = 25422 23.44.665.964 I slot print_timing: id 2 | task 26756 | graph reallocs = 0 / 0 (same size) / (changed size) 23.44.665.995 I slot release: id 2 | task 26756 | stop processing: n_tokens = 724, truncated = 0 23.44.666.000 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.881 23.44.666.024 I slot launch_slot_: id 0 | task 26761 | processing task, is_child = 0 23.44.674.835 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.874 23.44.674.858 I slot launch_slot_: id 1 | task 26763 | processing task, is_child = 0 23.44.674.940 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.872 23.44.674.953 I slot launch_slot_: id 2 | task 26764 | processing task, is_child = 0 23.44.674.993 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 336812000527 23.44.675.052 I slot launch_slot_: id 3 | task 26765 | processing task, is_child = 0 23.48.240.252 I slot print_timing: id 0 | task 26761 | prompt eval time = 2815.74 ms / 451 tokens ( 6.24 ms per token, 160.17 tokens per second) 23.48.240.257 I slot print_timing: id 0 | task 26761 | eval time = 753.18 ms / 2 tokens ( 753.18 ms per token, 1.33 tokens per second) 23.48.240.257 I slot print_timing: id 0 | task 26761 | total time = 3568.92 ms / 453 tokens 23.48.240.257 I slot print_timing: id 0 | task 26761 | graphs reused = 25422 23.48.240.258 I slot print_timing: id 0 | task 26761 | graph reallocs = 0 / 0 (same size) / (changed size) 23.48.240.299 I slot release: id 0 | task 26761 | stop processing: n_tokens = 710, truncated = 0 23.48.304.091 I slot print_timing: id 1 | task 26763 | prompt eval time = 2990.78 ms / 508 tokens ( 5.89 ms per token, 169.86 tokens per second) 23.48.304.093 I slot print_timing: id 1 | task 26763 | eval time = 63.46 ms / 2 tokens ( 63.46 ms per token, 15.76 tokens per second) 23.48.304.094 I slot print_timing: id 1 | task 26763 | total time = 3054.23 ms / 510 tokens 23.48.304.094 I slot print_timing: id 1 | task 26763 | graphs reused = 25422 23.48.304.095 I slot print_timing: id 1 | task 26763 | graph reallocs = 0 / 0 (same size) / (changed size) 23.48.304.136 I slot release: id 1 | task 26763 | stop processing: n_tokens = 724, truncated = 0 23.48.304.449 I slot print_timing: id 2 | task 26764 | prompt eval time = 2991.02 ms / 473 tokens ( 6.32 ms per token, 158.14 tokens per second) 23.48.304.451 I slot print_timing: id 2 | task 26764 | eval time = 63.45 ms / 2 tokens ( 63.45 ms per token, 15.76 tokens per second) 23.48.304.452 I slot print_timing: id 2 | task 26764 | total time = 3054.47 ms / 475 tokens 23.48.304.452 I slot print_timing: id 2 | task 26764 | graphs reused = 25422 23.48.304.453 I slot print_timing: id 2 | task 26764 | graph reallocs = 0 / 0 (same size) / (changed size) 23.48.304.490 I slot release: id 2 | task 26764 | stop processing: n_tokens = 732, truncated = 0 23.48.304.898 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 336815608282 23.48.307.250 I slot launch_slot_: id 0 | task 26769 | processing task, is_child = 0 23.48.311.547 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 724, t_last = 336815672119 23.48.311.629 I slot launch_slot_: id 1 | task 26770 | processing task, is_child = 0 23.48.311.670 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 336815672473 23.48.311.736 I slot launch_slot_: id 2 | task 26771 | processing task, is_child = 0 23.50.286.868 I slot print_timing: id 3 | task 26765 | prompt eval time = 3054.81 ms / 944 tokens ( 3.24 ms per token, 309.02 tokens per second) 23.50.286.871 I slot print_timing: id 3 | task 26765 | eval time = 1981.96 ms / 2 tokens ( 1981.96 ms per token, 0.50 tokens per second) 23.50.286.872 I slot print_timing: id 3 | task 26765 | total time = 5036.77 ms / 946 tokens 23.50.286.872 I slot print_timing: id 3 | task 26765 | graphs reused = 25422 23.50.286.873 I slot print_timing: id 3 | task 26765 | graph reallocs = 0 / 0 (same size) / (changed size) 23.50.286.931 I slot release: id 3 | task 26765 | stop processing: n_tokens = 945, truncated = 0 23.52.266.210 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 336817654914 23.52.316.889 I slot launch_slot_: id 3 | task 26774 | processing task, is_child = 0 23.52.316.930 I slot print_timing: id 0 | task 26769 | prompt processing, n_tokens = 926, progress = 1.00, t = 3.95 s / 234.17 tokens per second 23.52.317.136 I slot print_timing: id 1 | task 26770 | prompt processing, n_tokens = 995, progress = 1.00, t = 3.95 s / 251.62 tokens per second 23.52.317.360 I slot print_timing: id 2 | task 26771 | prompt processing, n_tokens = 910, progress = 1.00, t = 3.95 s / 230.13 tokens per second 23.53.891.233 I slot print_timing: id 0 | task 26769 | prompt eval time = 4891.45 ms / 930 tokens ( 5.26 ms per token, 190.13 tokens per second) 23.53.891.238 I slot print_timing: id 0 | task 26769 | eval time = 688.03 ms / 2 tokens ( 688.03 ms per token, 1.45 tokens per second) 23.53.891.238 I slot print_timing: id 0 | task 26769 | total time = 5579.48 ms / 932 tokens 23.53.891.239 I slot print_timing: id 0 | task 26769 | graphs reused = 25423 23.53.891.239 I slot print_timing: id 0 | task 26769 | graph reallocs = 0 / 0 (same size) / (changed size) 23.53.891.296 I slot release: id 0 | task 26769 | stop processing: n_tokens = 931, truncated = 0 23.53.891.653 I slot print_timing: id 1 | task 26770 | prompt eval time = 4891.74 ms / 999 tokens ( 4.90 ms per token, 204.22 tokens per second) 23.53.891.656 I slot print_timing: id 1 | task 26770 | eval time = 688.10 ms / 2 tokens ( 688.10 ms per token, 1.45 tokens per second) 23.53.891.656 I slot print_timing: id 1 | task 26770 | total time = 5579.84 ms / 1001 tokens 23.53.891.656 I slot print_timing: id 1 | task 26770 | graphs reused = 25423 23.53.891.657 I slot print_timing: id 1 | task 26770 | graph reallocs = 0 / 0 (same size) / (changed size) 23.53.891.707 I slot release: id 1 | task 26770 | stop processing: n_tokens = 1000, truncated = 0 23.53.892.133 I slot print_timing: id 2 | task 26771 | prompt eval time = 4892.14 ms / 914 tokens ( 5.35 ms per token, 186.83 tokens per second) 23.53.892.137 I slot print_timing: id 2 | task 26771 | eval time = 688.11 ms / 2 tokens ( 688.11 ms per token, 1.45 tokens per second) 23.53.892.138 I slot print_timing: id 2 | task 26771 | total time = 5580.24 ms / 916 tokens 23.53.892.138 I slot print_timing: id 2 | task 26771 | graphs reused = 25423 23.53.892.138 I slot print_timing: id 2 | task 26771 | graph reallocs = 0 / 0 (same size) / (changed size) 23.53.892.188 I slot release: id 2 | task 26771 | stop processing: n_tokens = 915, truncated = 0 23.53.930.731 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 336821259279 23.53.933.820 I slot launch_slot_: id 0 | task 26778 | processing task, is_child = 0 23.53.937.933 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 336821259690 23.53.938.016 I slot launch_slot_: id 1 | task 26779 | processing task, is_child = 0 23.53.938.065 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 915, t_last = 336821260171 23.53.938.134 I slot launch_slot_: id 2 | task 26780 | processing task, is_child = 0 23.56.674.242 I slot print_timing: id 3 | task 26774 | prompt eval time = 1613.16 ms / 1051 tokens ( 1.53 ms per token, 651.51 tokens per second) 23.56.674.245 I slot print_timing: id 3 | task 26774 | eval time = 2743.51 ms / 2 tokens ( 2743.51 ms per token, 0.36 tokens per second) 23.56.674.245 I slot print_timing: id 3 | task 26774 | total time = 4356.67 ms / 1053 tokens 23.56.674.246 I slot print_timing: id 3 | task 26774 | graphs reused = 25423 23.56.674.246 I slot print_timing: id 3 | task 26774 | graph reallocs = 0 / 0 (same size) / (changed size) 23.56.674.317 I slot release: id 3 | task 26774 | stop processing: n_tokens = 1052, truncated = 0 23.58.905.392 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1052, t_last = 336824042301 23.59.445.079 I slot launch_slot_: id 3 | task 26783 | processing task, is_child = 0 23.59.445.109 I slot print_timing: id 0 | task 26778 | prompt processing, n_tokens = 2081, progress = 1.00, t = 4.97 s / 418.94 tokens per second 23.59.445.474 I slot print_timing: id 1 | task 26779 | prompt processing, n_tokens = 538, progress = 0.51, t = 4.97 s / 108.31 tokens per second 24.02.294.126 I slot print_timing: id 1 | task 26779 | prompt processing, n_tokens = 1050, progress = 1.00, t = 8.36 s / 125.67 tokens per second 24.02.294.322 I slot print_timing: id 2 | task 26780 | prompt processing, n_tokens = 1555, progress = 0.75, t = 5.62 s / 276.72 tokens per second 24.03.295.180 I slot print_timing: id 0 | task 26778 | prompt eval time = 8355.97 ms / 2085 tokens ( 4.01 ms per token, 249.52 tokens per second) 24.03.295.183 I slot print_timing: id 0 | task 26778 | eval time = 1001.06 ms / 2 tokens ( 1001.06 ms per token, 1.00 tokens per second) 24.03.295.183 I slot print_timing: id 0 | task 26778 | total time = 9357.04 ms / 2087 tokens 24.03.295.184 I slot print_timing: id 0 | task 26778 | graphs reused = 25423 24.03.295.184 I slot print_timing: id 0 | task 26778 | graph reallocs = 0 / 0 (same size) / (changed size) 24.03.295.304 I slot release: id 0 | task 26778 | stop processing: n_tokens = 2086, truncated = 0 24.03.295.636 I slot print_timing: id 2 | task 26780 | prompt processing, n_tokens = 2067, progress = 1.00, t = 6.62 s / 312.21 tokens per second 24.03.295.996 I slot print_timing: id 3 | task 26783 | prompt processing, n_tokens = 1533, progress = 0.75, t = 3.85 s / 398.26 tokens per second 24.04.042.649 I slot print_timing: id 1 | task 26779 | prompt eval time = 9357.38 ms / 1054 tokens ( 8.88 ms per token, 112.64 tokens per second) 24.04.042.651 I slot print_timing: id 1 | task 26779 | eval time = 747.02 ms / 2 tokens ( 747.02 ms per token, 1.34 tokens per second) 24.04.042.651 I slot print_timing: id 1 | task 26779 | total time = 10104.40 ms / 1056 tokens 24.04.042.652 I slot print_timing: id 1 | task 26779 | graphs reused = 25423 24.04.042.652 I slot print_timing: id 1 | task 26779 | graph reallocs = 0 / 0 (same size) / (changed size) 24.04.042.714 I slot release: id 1 | task 26779 | stop processing: n_tokens = 1055, truncated = 0 24.04.043.113 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.850 24.04.043.158 I slot launch_slot_: id 0 | task 26787 | processing task, is_child = 0 24.04.047.666 I slot print_timing: id 3 | task 26783 | prompt processing, n_tokens = 2045, progress = 1.00, t = 4.60 s / 444.88 tokens per second 24.04.712.023 I slot print_timing: id 2 | task 26780 | prompt eval time = 7368.72 ms / 2071 tokens ( 3.56 ms per token, 281.05 tokens per second) 24.04.712.026 I slot print_timing: id 2 | task 26780 | eval time = 668.91 ms / 2 tokens ( 668.91 ms per token, 1.49 tokens per second) 24.04.712.026 I slot print_timing: id 2 | task 26780 | total time = 8037.63 ms / 2073 tokens 24.04.712.026 I slot print_timing: id 2 | task 26780 | graphs reused = 25423 24.04.712.027 I slot print_timing: id 2 | task 26780 | graph reallocs = 0 / 0 (same size) / (changed size) 24.04.712.152 I slot release: id 2 | task 26780 | stop processing: n_tokens = 2072, truncated = 0 24.04.712.587 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.856 24.04.712.626 I slot launch_slot_: id 2 | task 26789 | processing task, is_child = 0 24.04.931.691 I slot print_timing: id 3 | task 26783 | prompt eval time = 5267.02 ms / 2049 tokens ( 2.57 ms per token, 389.02 tokens per second) 24.04.931.693 I slot print_timing: id 3 | task 26783 | eval time = 219.11 ms / 2 tokens ( 219.11 ms per token, 4.56 tokens per second) 24.04.931.693 I slot print_timing: id 3 | task 26783 | total time = 5486.13 ms / 2051 tokens 24.04.931.694 I slot print_timing: id 3 | task 26783 | graphs reused = 25423 24.04.931.694 I slot print_timing: id 3 | task 26783 | graph reallocs = 0 / 0 (same size) / (changed size) 24.04.931.809 I slot release: id 3 | task 26783 | stop processing: n_tokens = 2050, truncated = 0 24.04.931.816 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.865 24.04.931.845 I slot launch_slot_: id 3 | task 26791 | processing task, is_child = 0 24.05.832.825 I slot print_timing: id 0 | task 26787 | prompt eval time = 883.86 ms / 457 tokens ( 1.93 ms per token, 517.05 tokens per second) 24.05.832.828 I slot print_timing: id 0 | task 26787 | eval time = 901.45 ms / 2 tokens ( 901.45 ms per token, 1.11 tokens per second) 24.05.832.828 I slot print_timing: id 0 | task 26787 | total time = 1785.31 ms / 459 tokens 24.05.832.829 I slot print_timing: id 0 | task 26787 | graphs reused = 25423 24.05.832.829 I slot print_timing: id 0 | task 26787 | graph reallocs = 0 / 0 (same size) / (changed size) 24.05.832.934 I slot release: id 0 | task 26787 | stop processing: n_tokens = 2027, truncated = 0 24.05.832.942 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.875 24.05.832.972 I slot launch_slot_: id 0 | task 26793 | processing task, is_child = 0 24.07.186.510 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1055, t_last = 336831410697 24.07.186.646 I slot launch_slot_: id 1 | task 26795 | processing task, is_child = 0 24.09.458.871 I slot print_timing: id 2 | task 26789 | prompt eval time = 2473.42 ms / 551 tokens ( 4.49 ms per token, 222.77 tokens per second) 24.09.458.874 I slot print_timing: id 2 | task 26789 | eval time = 2272.37 ms / 2 tokens ( 2272.37 ms per token, 0.44 tokens per second) 24.09.458.874 I slot print_timing: id 2 | task 26789 | total time = 4745.78 ms / 553 tokens 24.09.458.875 I slot print_timing: id 2 | task 26789 | graphs reused = 25423 24.09.458.875 I slot print_timing: id 2 | task 26789 | graph reallocs = 0 / 0 (same size) / (changed size) 24.09.458.992 I slot release: id 2 | task 26789 | stop processing: n_tokens = 2107, truncated = 0 24.10.163.584 I slot print_timing: id 0 | task 26793 | prompt eval time = 3625.50 ms / 478 tokens ( 7.58 ms per token, 131.84 tokens per second) 24.10.163.586 I slot print_timing: id 0 | task 26793 | eval time = 705.01 ms / 2 tokens ( 705.01 ms per token, 1.42 tokens per second) 24.10.163.587 I slot print_timing: id 0 | task 26793 | total time = 4330.52 ms / 480 tokens 24.10.163.587 I slot print_timing: id 0 | task 26793 | graphs reused = 25423 24.10.163.588 I slot print_timing: id 0 | task 26793 | graph reallocs = 0 / 0 (same size) / (changed size) 24.10.163.699 I slot release: id 0 | task 26793 | stop processing: n_tokens = 2048, truncated = 0 24.10.164.016 I slot print_timing: id 3 | task 26791 | prompt eval time = 4527.49 ms / 583 tokens ( 7.77 ms per token, 128.77 tokens per second) 24.10.164.018 I slot print_timing: id 3 | task 26791 | eval time = 704.57 ms / 2 tokens ( 704.57 ms per token, 1.42 tokens per second) 24.10.164.019 I slot print_timing: id 3 | task 26791 | total time = 5232.06 ms / 585 tokens 24.10.164.019 I slot print_timing: id 3 | task 26791 | graphs reused = 25423 24.10.164.019 I slot print_timing: id 3 | task 26791 | graph reallocs = 0 / 0 (same size) / (changed size) 24.10.164.110 I slot release: id 3 | task 26791 | stop processing: n_tokens = 2117, truncated = 0 24.10.164.117 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.805 (> 0.100 thold), f_keep = 0.842 24.10.164.151 I slot launch_slot_: id 2 | task 26798 | processing task, is_child = 0 24.10.177.386 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.838 24.10.177.425 I slot launch_slot_: id 3 | task 26799 | processing task, is_child = 0 24.10.177.521 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.866 24.10.177.539 I slot launch_slot_: id 0 | task 26800 | processing task, is_child = 0 24.12.377.385 I slot print_timing: id 1 | task 26795 | prompt eval time = 4405.84 ms / 2126 tokens ( 2.07 ms per token, 482.54 tokens per second) 24.12.377.388 I slot print_timing: id 1 | task 26795 | eval time = 784.58 ms / 2 tokens ( 784.58 ms per token, 1.27 tokens per second) 24.12.377.388 I slot print_timing: id 1 | task 26795 | total time = 5190.42 ms / 2128 tokens 24.12.377.389 I slot print_timing: id 1 | task 26795 | graphs reused = 25423 24.12.377.389 I slot print_timing: id 1 | task 26795 | graph reallocs = 0 / 0 (same size) / (changed size) 24.12.377.509 I slot release: id 1 | task 26795 | stop processing: n_tokens = 2127, truncated = 0 24.12.446.565 I slot print_timing: id 0 | task 26800 | prompt eval time = 2199.55 ms / 431 tokens ( 5.10 ms per token, 195.95 tokens per second) 24.12.446.568 I slot print_timing: id 0 | task 26800 | eval time = 69.47 ms / 2 tokens ( 69.47 ms per token, 14.39 tokens per second) 24.12.446.569 I slot print_timing: id 0 | task 26800 | total time = 2269.02 ms / 433 tokens 24.12.446.569 I slot print_timing: id 0 | task 26800 | graphs reused = 25423 24.12.446.570 I slot print_timing: id 0 | task 26800 | graph reallocs = 0 / 0 (same size) / (changed size) 24.12.446.691 I slot release: id 0 | task 26800 | stop processing: n_tokens = 2001, truncated = 0 24.12.447.539 I slot print_timing: id 3 | task 26799 | prompt eval time = 2199.84 ms / 355 tokens ( 6.20 ms per token, 161.38 tokens per second) 24.12.447.543 I slot print_timing: id 3 | task 26799 | eval time = 69.60 ms / 2 tokens ( 69.60 ms per token, 14.37 tokens per second) 24.12.447.543 I slot print_timing: id 3 | task 26799 | total time = 2269.44 ms / 357 tokens 24.12.447.544 I slot print_timing: id 3 | task 26799 | graphs reused = 25423 24.12.447.544 I slot print_timing: id 3 | task 26799 | graph reallocs = 0 / 0 (same size) / (changed size) 24.12.447.631 I slot release: id 3 | task 26799 | stop processing: n_tokens = 1956, truncated = 0 24.12.447.648 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.886 24.12.447.677 I slot launch_slot_: id 0 | task 26804 | processing task, is_child = 0 24.12.461.423 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.865 (> 0.100 thold), f_keep = 0.834 24.12.461.457 I slot launch_slot_: id 1 | task 26805 | processing task, is_child = 0 24.12.461.566 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.848 (> 0.100 thold), f_keep = 0.907 24.12.461.585 I slot launch_slot_: id 3 | task 26806 | processing task, is_child = 0 24.14.375.243 I slot print_timing: id 2 | task 26798 | prompt eval time = 2269.15 ms / 614 tokens ( 3.70 ms per token, 270.59 tokens per second) 24.14.375.246 I slot print_timing: id 2 | task 26798 | eval time = 1928.07 ms / 2 tokens ( 1928.07 ms per token, 0.52 tokens per second) 24.14.375.246 I slot print_timing: id 2 | task 26798 | total time = 4197.22 ms / 616 tokens 24.14.375.246 I slot print_timing: id 2 | task 26798 | graphs reused = 25423 24.14.375.247 I slot print_timing: id 2 | task 26798 | graph reallocs = 0 / 0 (same size) / (changed size) 24.14.375.371 I slot release: id 2 | task 26798 | stop processing: n_tokens = 2205, truncated = 0 24.14.478.567 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.804 24.14.478.630 I slot launch_slot_: id 2 | task 26809 | processing task, is_child = 0 24.14.940.789 I slot print_timing: id 0 | task 26804 | prompt eval time = 2016.12 ms / 428 tokens ( 4.71 ms per token, 212.29 tokens per second) 24.14.940.794 I slot print_timing: id 0 | task 26804 | eval time = 463.07 ms / 2 tokens ( 463.07 ms per token, 2.16 tokens per second) 24.14.940.795 I slot print_timing: id 0 | task 26804 | total time = 2479.20 ms / 430 tokens 24.14.940.795 I slot print_timing: id 0 | task 26804 | graphs reused = 25423 24.14.940.796 I slot print_timing: id 0 | task 26804 | graph reallocs = 0 / 0 (same size) / (changed size) 24.14.940.907 I slot release: id 0 | task 26804 | stop processing: n_tokens = 1998, truncated = 0 24.14.941.255 I slot print_timing: id 1 | task 26805 | prompt eval time = 2016.40 ms / 441 tokens ( 4.57 ms per token, 218.71 tokens per second) 24.14.941.259 I slot print_timing: id 1 | task 26805 | eval time = 463.12 ms / 2 tokens ( 463.12 ms per token, 2.16 tokens per second) 24.14.941.259 I slot print_timing: id 1 | task 26805 | total time = 2479.53 ms / 443 tokens 24.14.941.259 I slot print_timing: id 1 | task 26805 | graphs reused = 25423 24.14.941.260 I slot print_timing: id 1 | task 26805 | graph reallocs = 0 / 0 (same size) / (changed size) 24.14.941.345 I slot release: id 1 | task 26805 | stop processing: n_tokens = 2052, truncated = 0 24.14.941.705 I slot print_timing: id 3 | task 26806 | prompt eval time = 2016.70 ms / 491 tokens ( 4.11 ms per token, 243.47 tokens per second) 24.14.941.708 I slot print_timing: id 3 | task 26806 | eval time = 463.15 ms / 2 tokens ( 463.15 ms per token, 2.16 tokens per second) 24.14.941.709 I slot print_timing: id 3 | task 26806 | total time = 2479.85 ms / 493 tokens 24.14.941.709 I slot print_timing: id 3 | task 26806 | graphs reused = 25423 24.14.941.709 I slot print_timing: id 3 | task 26806 | graph reallocs = 0 / 0 (same size) / (changed size) 24.14.941.828 I slot release: id 3 | task 26806 | stop processing: n_tokens = 2092, truncated = 0 24.14.980.698 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.887 24.14.980.725 I slot launch_slot_: id 0 | task 26812 | processing task, is_child = 0 24.14.992.714 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.864 24.14.992.745 I slot launch_slot_: id 1 | task 26813 | processing task, is_child = 0 24.14.992.842 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.848 24.14.992.860 I slot launch_slot_: id 3 | task 26814 | processing task, is_child = 0 24.16.475.932 I slot print_timing: id 2 | task 26809 | prompt eval time = 502.05 ms / 270 tokens ( 1.86 ms per token, 537.79 tokens per second) 24.16.475.934 I slot print_timing: id 2 | task 26809 | eval time = 1495.24 ms / 2 tokens ( 1495.24 ms per token, 0.67 tokens per second) 24.16.475.935 I slot print_timing: id 2 | task 26809 | total time = 1997.29 ms / 272 tokens 24.16.475.935 I slot print_timing: id 2 | task 26809 | graphs reused = 25423 24.16.475.936 I slot print_timing: id 2 | task 26809 | graph reallocs = 0 / 0 (same size) / (changed size) 24.16.476.050 I slot release: id 2 | task 26809 | stop processing: n_tokens = 1959, truncated = 0 24.17.242.161 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.905 24.17.242.205 I slot launch_slot_: id 2 | task 26817 | processing task, is_child = 0 24.17.752.847 I slot print_timing: id 0 | task 26812 | prompt eval time = 2248.92 ms / 485 tokens ( 4.64 ms per token, 215.66 tokens per second) 24.17.752.853 I slot print_timing: id 0 | task 26812 | eval time = 511.06 ms / 2 tokens ( 511.06 ms per token, 1.96 tokens per second) 24.17.752.853 I slot print_timing: id 0 | task 26812 | total time = 2759.98 ms / 487 tokens 24.17.752.854 I slot print_timing: id 0 | task 26812 | graphs reused = 25423 24.17.752.854 I slot print_timing: id 0 | task 26812 | graph reallocs = 0 / 0 (same size) / (changed size) 24.17.752.977 I slot release: id 0 | task 26812 | stop processing: n_tokens = 2055, truncated = 0 24.17.753.614 I slot print_timing: id 3 | task 26814 | prompt eval time = 2249.08 ms / 506 tokens ( 4.44 ms per token, 224.98 tokens per second) 24.17.753.618 I slot print_timing: id 3 | task 26814 | eval time = 511.46 ms / 2 tokens ( 511.46 ms per token, 1.96 tokens per second) 24.17.753.619 I slot print_timing: id 3 | task 26814 | total time = 2760.54 ms / 508 tokens 24.17.753.619 I slot print_timing: id 3 | task 26814 | graphs reused = 25423 24.17.753.620 I slot print_timing: id 3 | task 26814 | graph reallocs = 0 / 0 (same size) / (changed size) 24.17.753.750 I slot release: id 3 | task 26814 | stop processing: n_tokens = 2107, truncated = 0 24.17.809.763 I slot print_timing: id 1 | task 26813 | prompt eval time = 2760.27 ms / 545 tokens ( 5.06 ms per token, 197.44 tokens per second) 24.17.809.767 I slot print_timing: id 1 | task 26813 | eval time = 56.48 ms / 2 tokens ( 56.48 ms per token, 17.70 tokens per second) 24.17.809.767 I slot print_timing: id 1 | task 26813 | total time = 2816.76 ms / 547 tokens 24.17.809.768 I slot print_timing: id 1 | task 26813 | graphs reused = 25423 24.17.809.768 I slot print_timing: id 1 | task 26813 | graph reallocs = 0 / 0 (same size) / (changed size) 24.17.809.879 I slot release: id 1 | task 26813 | stop processing: n_tokens = 2156, truncated = 0 24.17.810.276 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.863 24.17.810.304 I slot launch_slot_: id 0 | task 26820 | processing task, is_child = 0 24.17.823.095 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.820 (> 0.100 thold), f_keep = 0.842 24.17.823.120 I slot launch_slot_: id 3 | task 26821 | processing task, is_child = 0 24.17.823.214 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.822 24.17.823.236 I slot launch_slot_: id 1 | task 26822 | processing task, is_child = 0 24.19.285.932 I slot print_timing: id 2 | task 26817 | prompt eval time = 567.72 ms / 270 tokens ( 2.10 ms per token, 475.59 tokens per second) 24.19.285.937 I slot print_timing: id 2 | task 26817 | eval time = 1475.66 ms / 2 tokens ( 1475.66 ms per token, 0.68 tokens per second) 24.19.285.938 I slot print_timing: id 2 | task 26817 | total time = 2043.38 ms / 272 tokens 24.19.285.938 I slot print_timing: id 2 | task 26817 | graphs reused = 25423 24.19.285.939 I slot print_timing: id 2 | task 26817 | graph reallocs = 0 / 0 (same size) / (changed size) 24.19.286.048 I slot release: id 2 | task 26817 | stop processing: n_tokens = 1959, truncated = 0 24.20.014.956 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.906 24.20.014.994 I slot launch_slot_: id 2 | task 26825 | processing task, is_child = 0 24.20.564.336 I slot print_timing: id 0 | task 26820 | prompt eval time = 2191.28 ms / 450 tokens ( 4.87 ms per token, 205.36 tokens per second) 24.20.564.341 I slot print_timing: id 0 | task 26820 | eval time = 549.81 ms / 2 tokens ( 549.81 ms per token, 1.82 tokens per second) 24.20.564.341 I slot print_timing: id 0 | task 26820 | total time = 2741.09 ms / 452 tokens 24.20.564.342 I slot print_timing: id 0 | task 26820 | graphs reused = 25423 24.20.564.342 I slot print_timing: id 0 | task 26820 | graph reallocs = 0 / 0 (same size) / (changed size) 24.20.564.466 I slot release: id 0 | task 26820 | stop processing: n_tokens = 2020, truncated = 0 24.20.564.777 I slot print_timing: id 1 | task 26822 | prompt eval time = 2191.57 ms / 338 tokens ( 6.48 ms per token, 154.23 tokens per second) 24.20.564.779 I slot print_timing: id 1 | task 26822 | eval time = 549.82 ms / 2 tokens ( 549.82 ms per token, 1.82 tokens per second) 24.20.564.780 I slot print_timing: id 1 | task 26822 | total time = 2741.39 ms / 340 tokens 24.20.564.780 I slot print_timing: id 1 | task 26822 | graphs reused = 25423 24.20.564.780 I slot print_timing: id 1 | task 26822 | graph reallocs = 0 / 0 (same size) / (changed size) 24.20.564.872 I slot release: id 1 | task 26822 | stop processing: n_tokens = 1978, truncated = 0 24.20.619.053 I slot print_timing: id 3 | task 26821 | prompt eval time = 2741.74 ms / 563 tokens ( 4.87 ms per token, 205.34 tokens per second) 24.20.619.060 I slot print_timing: id 3 | task 26821 | eval time = 53.81 ms / 2 tokens ( 53.81 ms per token, 18.58 tokens per second) 24.20.619.061 I slot print_timing: id 3 | task 26821 | total time = 2795.55 ms / 565 tokens 24.20.619.061 I slot print_timing: id 3 | task 26821 | graphs reused = 25423 24.20.619.062 I slot print_timing: id 3 | task 26821 | graph reallocs = 0 / 0 (same size) / (changed size) 24.20.619.175 I slot release: id 3 | task 26821 | stop processing: n_tokens = 2164, truncated = 0 24.20.619.183 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.820 24.20.619.209 I slot launch_slot_: id 3 | task 26828 | processing task, is_child = 0 24.20.631.262 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.878 24.20.631.293 I slot launch_slot_: id 0 | task 26829 | processing task, is_child = 0 24.20.631.397 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.896 24.20.631.422 I slot launch_slot_: id 1 | task 26830 | processing task, is_child = 0 24.22.199.411 I slot print_timing: id 2 | task 26825 | prompt eval time = 603.75 ms / 316 tokens ( 1.91 ms per token, 523.39 tokens per second) 24.22.199.413 I slot print_timing: id 2 | task 26825 | eval time = 1580.65 ms / 2 tokens ( 1580.65 ms per token, 0.63 tokens per second) 24.22.199.414 I slot print_timing: id 2 | task 26825 | total time = 2184.40 ms / 318 tokens 24.22.199.414 I slot print_timing: id 2 | task 26825 | graphs reused = 25423 24.22.199.415 I slot print_timing: id 2 | task 26825 | graph reallocs = 0 / 0 (same size) / (changed size) 24.22.199.530 I slot release: id 2 | task 26825 | stop processing: n_tokens = 2005, truncated = 0 24.22.301.420 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2005, t_last = 336849567514 24.22.309.825 I slot launch_slot_: id 2 | task 26833 | processing task, is_child = 0 24.23.533.783 I slot print_timing: id 0 | task 26829 | prompt eval time = 1669.25 ms / 322 tokens ( 5.18 ms per token, 192.90 tokens per second) 24.23.533.785 I slot print_timing: id 0 | task 26829 | eval time = 1233.10 ms / 2 tokens ( 1233.10 ms per token, 0.81 tokens per second) 24.23.533.786 I slot print_timing: id 0 | task 26829 | total time = 2902.35 ms / 324 tokens 24.23.533.786 I slot print_timing: id 0 | task 26829 | graphs reused = 25423 24.23.533.787 I slot print_timing: id 0 | task 26829 | graph reallocs = 0 / 0 (same size) / (changed size) 24.23.533.903 I slot release: id 0 | task 26829 | stop processing: n_tokens = 1892, truncated = 0 24.23.534.256 I slot print_timing: id 1 | task 26830 | prompt eval time = 1669.43 ms / 297 tokens ( 5.62 ms per token, 177.91 tokens per second) 24.23.534.260 I slot print_timing: id 1 | task 26830 | eval time = 1233.25 ms / 2 tokens ( 1233.25 ms per token, 0.81 tokens per second) 24.23.534.260 I slot print_timing: id 1 | task 26830 | total time = 2902.68 ms / 299 tokens 24.23.534.261 I slot print_timing: id 1 | task 26830 | graphs reused = 25423 24.23.534.261 I slot print_timing: id 1 | task 26830 | graph reallocs = 0 / 0 (same size) / (changed size) 24.23.534.350 I slot release: id 1 | task 26830 | stop processing: n_tokens = 1937, truncated = 0 24.23.534.910 I slot print_timing: id 3 | task 26828 | prompt eval time = 1669.73 ms / 330 tokens ( 5.06 ms per token, 197.64 tokens per second) 24.23.534.915 I slot print_timing: id 3 | task 26828 | eval time = 1233.49 ms / 2 tokens ( 1233.49 ms per token, 0.81 tokens per second) 24.23.534.915 I slot print_timing: id 3 | task 26828 | total time = 2903.22 ms / 332 tokens 24.23.534.916 I slot print_timing: id 3 | task 26828 | graphs reused = 25423 24.23.534.916 I slot print_timing: id 3 | task 26828 | graph reallocs = 0 / 0 (same size) / (changed size) 24.23.535.003 I slot release: id 3 | task 26828 | stop processing: n_tokens = 1978, truncated = 0 24.23.542.549 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1892, t_last = 336850901887 24.24.192.380 I slot launch_slot_: id 0 | task 26836 | processing task, is_child = 0 24.24.204.288 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1937, t_last = 336850902334 24.24.204.404 I slot launch_slot_: id 1 | task 26837 | processing task, is_child = 0 24.24.204.494 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1978, t_last = 336850902986 24.24.204.610 I slot launch_slot_: id 3 | task 26838 | processing task, is_child = 0 24.29.018.849 I slot print_timing: id 2 | task 26833 | prompt eval time = 4728.27 ms / 1430 tokens ( 3.31 ms per token, 302.44 tokens per second) 24.29.018.851 I slot print_timing: id 2 | task 26833 | eval time = 1980.74 ms / 2 tokens ( 1980.74 ms per token, 0.50 tokens per second) 24.29.018.852 I slot print_timing: id 2 | task 26833 | total time = 6709.01 ms / 1432 tokens 24.29.018.852 I slot print_timing: id 2 | task 26833 | graphs reused = 25423 24.29.018.852 I slot print_timing: id 2 | task 26833 | graph reallocs = 0 / 0 (same size) / (changed size) 24.29.018.932 I slot release: id 2 | task 26833 | stop processing: n_tokens = 1431, truncated = 0 24.29.018.944 I slot print_timing: id 0 | task 26836 | prompt processing, n_tokens = 977, progress = 1.00, t = 4.81 s / 202.95 tokens per second 24.29.019.122 I slot print_timing: id 1 | task 26837 | prompt processing, n_tokens = 1623, progress = 1.00, t = 4.81 s / 337.16 tokens per second 24.29.019.407 I slot print_timing: id 3 | task 26838 | prompt processing, n_tokens = 982, progress = 0.66, t = 4.81 s / 204.01 tokens per second 24.29.733.509 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1431, t_last = 336856386916 24.29.740.315 I slot launch_slot_: id 2 | task 26842 | processing task, is_child = 0 24.29.740.441 I slot print_timing: id 3 | task 26838 | prompt processing, n_tokens = 1494, progress = 1.00, t = 5.53 s / 270.28 tokens per second 24.30.416.619 I slot print_timing: id 0 | task 26836 | prompt eval time = 5528.57 ms / 981 tokens ( 5.64 ms per token, 177.44 tokens per second) 24.30.416.622 I slot print_timing: id 0 | task 26836 | eval time = 683.42 ms / 2 tokens ( 683.42 ms per token, 1.46 tokens per second) 24.30.416.623 I slot print_timing: id 0 | task 26836 | total time = 6212.00 ms / 983 tokens 24.30.416.623 I slot print_timing: id 0 | task 26836 | graphs reused = 25423 24.30.416.624 I slot print_timing: id 0 | task 26836 | graph reallocs = 0 / 0 (same size) / (changed size) 24.30.416.698 I slot release: id 0 | task 26836 | stop processing: n_tokens = 982, truncated = 0 24.30.417.041 I slot print_timing: id 1 | task 26837 | prompt eval time = 5528.75 ms / 1627 tokens ( 3.40 ms per token, 294.28 tokens per second) 24.30.417.045 I slot print_timing: id 1 | task 26837 | eval time = 683.54 ms / 2 tokens ( 683.54 ms per token, 1.46 tokens per second) 24.30.417.046 I slot print_timing: id 1 | task 26837 | total time = 6212.28 ms / 1629 tokens 24.30.417.046 I slot print_timing: id 1 | task 26837 | graphs reused = 25423 24.30.417.046 I slot print_timing: id 1 | task 26837 | graph reallocs = 0 / 0 (same size) / (changed size) 24.30.417.127 I slot release: id 1 | task 26837 | stop processing: n_tokens = 1628, truncated = 0 24.31.079.629 I slot print_timing: id 3 | task 26838 | prompt eval time = 6212.38 ms / 1498 tokens ( 4.15 ms per token, 241.13 tokens per second) 24.31.079.632 I slot print_timing: id 3 | task 26838 | eval time = 662.13 ms / 2 tokens ( 662.13 ms per token, 1.51 tokens per second) 24.31.079.633 I slot print_timing: id 3 | task 26838 | total time = 6874.51 ms / 1500 tokens 24.31.079.633 I slot print_timing: id 3 | task 26838 | graphs reused = 25423 24.31.079.634 I slot print_timing: id 3 | task 26838 | graph reallocs = 0 / 0 (same size) / (changed size) 24.31.079.724 I slot release: id 3 | task 26838 | stop processing: n_tokens = 1499, truncated = 0 24.31.079.732 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.878 24.31.079.763 I slot launch_slot_: id 0 | task 26845 | processing task, is_child = 0 24.31.091.417 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1628, t_last = 336857785111 24.31.091.537 I slot launch_slot_: id 1 | task 26846 | processing task, is_child = 0 24.31.091.609 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1499, t_last = 336858447708 24.31.091.710 I slot launch_slot_: id 3 | task 26847 | processing task, is_child = 0 24.34.491.483 I slot print_timing: id 2 | task 26842 | prompt eval time = 3374.15 ms / 969 tokens ( 3.48 ms per token, 287.18 tokens per second) 24.34.491.488 I slot print_timing: id 2 | task 26842 | eval time = 1377.01 ms / 2 tokens ( 1377.01 ms per token, 0.73 tokens per second) 24.34.491.488 I slot print_timing: id 2 | task 26842 | total time = 4751.16 ms / 971 tokens 24.34.491.489 I slot print_timing: id 2 | task 26842 | graphs reused = 25423 24.34.491.489 I slot print_timing: id 2 | task 26842 | graph reallocs = 0 / 0 (same size) / (changed size) 24.34.491.546 I slot release: id 2 | task 26842 | stop processing: n_tokens = 970, truncated = 0 24.34.491.559 I slot print_timing: id 1 | task 26846 | prompt processing, n_tokens = 939, progress = 1.00, t = 3.40 s / 276.26 tokens per second 24.34.491.739 I slot print_timing: id 3 | task 26847 | prompt processing, n_tokens = 960, progress = 1.00, t = 3.40 s / 282.46 tokens per second 24.34.582.888 I slot print_timing: id 0 | task 26845 | prompt eval time = 3399.45 ms / 493 tokens ( 6.90 ms per token, 145.02 tokens per second) 24.34.582.891 I slot print_timing: id 0 | task 26845 | eval time = 91.72 ms / 2 tokens ( 91.72 ms per token, 10.90 tokens per second) 24.34.582.891 I slot print_timing: id 0 | task 26845 | total time = 3491.17 ms / 495 tokens 24.34.582.892 I slot print_timing: id 0 | task 26845 | graphs reused = 25423 24.34.582.892 I slot print_timing: id 0 | task 26845 | graph reallocs = 0 / 0 (same size) / (changed size) 24.34.582.947 I slot release: id 0 | task 26845 | stop processing: n_tokens = 959, truncated = 0 24.34.583.736 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.898 24.34.583.773 I slot launch_slot_: id 0 | task 26851 | processing task, is_child = 0 24.34.587.293 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.888 24.34.587.329 I slot launch_slot_: id 2 | task 26852 | processing task, is_child = 0 24.35.893.297 I slot print_timing: id 1 | task 26846 | prompt eval time = 3491.50 ms / 943 tokens ( 3.70 ms per token, 270.08 tokens per second) 24.35.893.299 I slot print_timing: id 1 | task 26846 | eval time = 1309.94 ms / 2 tokens ( 1309.94 ms per token, 0.76 tokens per second) 24.35.893.300 I slot print_timing: id 1 | task 26846 | total time = 4801.44 ms / 945 tokens 24.35.893.300 I slot print_timing: id 1 | task 26846 | graphs reused = 25423 24.35.893.300 I slot print_timing: id 1 | task 26846 | graph reallocs = 0 / 0 (same size) / (changed size) 24.35.893.357 I slot release: id 1 | task 26846 | stop processing: n_tokens = 944, truncated = 0 24.35.893.783 I slot print_timing: id 3 | task 26847 | prompt eval time = 3491.58 ms / 964 tokens ( 3.62 ms per token, 276.09 tokens per second) 24.35.893.787 I slot print_timing: id 3 | task 26847 | eval time = 1310.06 ms / 2 tokens ( 1310.06 ms per token, 0.76 tokens per second) 24.35.893.788 I slot print_timing: id 3 | task 26847 | total time = 4801.64 ms / 966 tokens 24.35.893.788 I slot print_timing: id 3 | task 26847 | graphs reused = 25423 24.35.893.788 I slot print_timing: id 3 | task 26847 | graph reallocs = 0 / 0 (same size) / (changed size) 24.35.893.835 I slot release: id 3 | task 26847 | stop processing: n_tokens = 965, truncated = 0 24.35.968.463 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 944, t_last = 336863261340 24.35.971.381 I slot launch_slot_: id 1 | task 26855 | processing task, is_child = 0 24.35.974.092 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 336863261818 24.35.974.178 I slot launch_slot_: id 3 | task 26856 | processing task, is_child = 0 24.37.949.454 I slot print_timing: id 0 | task 26851 | prompt eval time = 1380.78 ms / 488 tokens ( 2.83 ms per token, 353.42 tokens per second) 24.37.949.456 I slot print_timing: id 0 | task 26851 | eval time = 1981.33 ms / 2 tokens ( 1981.33 ms per token, 0.50 tokens per second) 24.37.949.457 I slot print_timing: id 0 | task 26851 | total time = 3362.11 ms / 490 tokens 24.37.949.458 I slot print_timing: id 0 | task 26851 | graphs reused = 25423 24.37.949.458 I slot print_timing: id 0 | task 26851 | graph reallocs = 0 / 0 (same size) / (changed size) 24.37.949.515 I slot release: id 0 | task 26851 | stop processing: n_tokens = 954, truncated = 0 24.37.949.851 I slot print_timing: id 2 | task 26852 | prompt eval time = 1380.98 ms / 504 tokens ( 2.74 ms per token, 364.96 tokens per second) 24.37.949.853 I slot print_timing: id 2 | task 26852 | eval time = 1981.39 ms / 2 tokens ( 1981.39 ms per token, 0.50 tokens per second) 24.37.949.853 I slot print_timing: id 2 | task 26852 | total time = 3362.37 ms / 506 tokens 24.37.949.854 I slot print_timing: id 2 | task 26852 | graphs reused = 25423 24.37.949.854 I slot print_timing: id 2 | task 26852 | graph reallocs = 0 / 0 (same size) / (changed size) 24.37.949.897 I slot release: id 2 | task 26852 | stop processing: n_tokens = 958, truncated = 0 24.38.598.193 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 336865317498 24.39.251.846 I slot launch_slot_: id 0 | task 26859 | processing task, is_child = 0 24.39.255.927 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 958, t_last = 336865317880 24.39.256.010 I slot launch_slot_: id 2 | task 26860 | processing task, is_child = 0 24.43.051.975 I slot print_timing: id 1 | task 26855 | prompt eval time = 6072.72 ms / 789 tokens ( 7.70 ms per token, 129.93 tokens per second) 24.43.051.978 I slot print_timing: id 1 | task 26855 | eval time = 1005.06 ms / 2 tokens ( 1005.06 ms per token, 0.99 tokens per second) 24.43.051.978 I slot print_timing: id 1 | task 26855 | total time = 7077.79 ms / 791 tokens 24.43.051.979 I slot print_timing: id 1 | task 26855 | graphs reused = 25423 24.43.051.979 I slot print_timing: id 1 | task 26855 | graph reallocs = 0 / 0 (same size) / (changed size) 24.43.052.027 I slot release: id 1 | task 26855 | stop processing: n_tokens = 790, truncated = 0 24.43.052.345 I slot print_timing: id 0 | task 26859 | prompt processing, n_tokens = 1574, progress = 1.00, t = 3.80 s / 414.69 tokens per second 24.43.052.601 I slot print_timing: id 2 | task 26860 | prompt processing, n_tokens = 1094, progress = 0.68, t = 3.80 s / 288.24 tokens per second 24.43.761.254 I slot print_timing: id 3 | task 26856 | prompt eval time = 7078.08 ms / 1623 tokens ( 4.36 ms per token, 229.30 tokens per second) 24.43.761.256 I slot print_timing: id 3 | task 26856 | eval time = 708.91 ms / 2 tokens ( 708.91 ms per token, 1.41 tokens per second) 24.43.761.257 I slot print_timing: id 3 | task 26856 | total time = 7786.99 ms / 1625 tokens 24.43.761.257 I slot print_timing: id 3 | task 26856 | graphs reused = 25423 24.43.761.258 I slot print_timing: id 3 | task 26856 | graph reallocs = 0 / 0 (same size) / (changed size) 24.43.761.353 I slot release: id 3 | task 26856 | stop processing: n_tokens = 1624, truncated = 0 24.43.761.364 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.857 (> 0.100 thold), f_keep = 0.861 24.43.761.403 I slot launch_slot_: id 3 | task 26864 | processing task, is_child = 0 24.43.764.288 I slot print_timing: id 2 | task 26860 | prompt processing, n_tokens = 1606, progress = 1.00, t = 4.50 s / 356.55 tokens per second 24.43.888.828 I slot print_timing: id 0 | task 26859 | prompt eval time = 4504.91 ms / 1578 tokens ( 2.85 ms per token, 350.28 tokens per second) 24.43.888.833 I slot print_timing: id 0 | task 26859 | eval time = 127.89 ms / 2 tokens ( 127.89 ms per token, 7.82 tokens per second) 24.43.888.833 I slot print_timing: id 0 | task 26859 | total time = 4632.81 ms / 1580 tokens 24.43.888.833 I slot print_timing: id 0 | task 26859 | graphs reused = 25423 24.43.888.834 I slot print_timing: id 0 | task 26859 | graph reallocs = 0 / 0 (same size) / (changed size) 24.43.888.926 I slot release: id 0 | task 26859 | stop processing: n_tokens = 1579, truncated = 0 24.43.889.335 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.812 (> 0.100 thold), f_keep = 0.886 24.43.889.364 I slot launch_slot_: id 0 | task 26866 | processing task, is_child = 0 24.44.858.328 I slot print_timing: id 2 | task 26860 | prompt eval time = 4633.09 ms / 1610 tokens ( 2.88 ms per token, 347.50 tokens per second) 24.44.858.330 I slot print_timing: id 2 | task 26860 | eval time = 968.99 ms / 2 tokens ( 968.99 ms per token, 1.03 tokens per second) 24.44.858.331 I slot print_timing: id 2 | task 26860 | total time = 5602.09 ms / 1612 tokens 24.44.858.331 I slot print_timing: id 2 | task 26860 | graphs reused = 25423 24.44.858.332 I slot print_timing: id 2 | task 26860 | graph reallocs = 0 / 0 (same size) / (changed size) 24.44.858.426 I slot release: id 2 | task 26860 | stop processing: n_tokens = 1611, truncated = 0 24.44.858.433 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 336870420010 24.44.858.535 I slot launch_slot_: id 1 | task 26868 | processing task, is_child = 0 24.44.864.906 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1611, t_last = 336872226410 24.44.865.022 I slot launch_slot_: id 2 | task 26869 | processing task, is_child = 0 24.48.112.764 I slot print_timing: id 3 | task 26864 | prompt eval time = 2959.36 ms / 526 tokens ( 5.63 ms per token, 177.74 tokens per second) 24.48.112.767 I slot print_timing: id 3 | task 26864 | eval time = 1388.85 ms / 2 tokens ( 1388.85 ms per token, 0.72 tokens per second) 24.48.112.767 I slot print_timing: id 3 | task 26864 | total time = 4348.21 ms / 528 tokens 24.48.112.768 I slot print_timing: id 3 | task 26864 | graphs reused = 25423 24.48.112.768 I slot print_timing: id 3 | task 26864 | graph reallocs = 0 / 0 (same size) / (changed size) 24.48.112.870 I slot release: id 3 | task 26864 | stop processing: n_tokens = 1634, truncated = 0 24.48.112.884 I slot print_timing: id 1 | task 26868 | prompt processing, n_tokens = 822, progress = 1.00, t = 3.25 s / 253.15 tokens per second 24.48.113.039 I slot print_timing: id 2 | task 26869 | prompt processing, n_tokens = 850, progress = 1.00, t = 3.25 s / 261.78 tokens per second 24.48.196.633 I slot print_timing: id 0 | task 26866 | prompt eval time = 4223.00 ms / 661 tokens ( 6.39 ms per token, 156.52 tokens per second) 24.48.196.636 I slot print_timing: id 0 | task 26866 | eval time = 84.19 ms / 2 tokens ( 84.19 ms per token, 11.88 tokens per second) 24.48.196.637 I slot print_timing: id 0 | task 26866 | total time = 4307.18 ms / 663 tokens 24.48.196.637 I slot print_timing: id 0 | task 26866 | graphs reused = 25423 24.48.196.638 I slot print_timing: id 0 | task 26866 | graph reallocs = 0 / 0 (same size) / (changed size) 24.48.196.734 I slot release: id 0 | task 26866 | stop processing: n_tokens = 1724, truncated = 0 24.48.197.623 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1634, t_last = 336875480854 24.48.204.294 I slot launch_slot_: id 3 | task 26873 | processing task, is_child = 0 24.48.209.671 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1724, t_last = 336875564718 24.48.209.785 I slot launch_slot_: id 0 | task 26874 | processing task, is_child = 0 24.49.148.751 I slot print_timing: id 1 | task 26868 | prompt eval time = 3332.07 ms / 826 tokens ( 4.03 ms per token, 247.89 tokens per second) 24.49.148.753 I slot print_timing: id 1 | task 26868 | eval time = 951.59 ms / 2 tokens ( 951.59 ms per token, 1.05 tokens per second) 24.49.148.753 I slot print_timing: id 1 | task 26868 | total time = 4283.66 ms / 828 tokens 24.49.148.754 I slot print_timing: id 1 | task 26868 | graphs reused = 25423 24.49.148.754 I slot print_timing: id 1 | task 26868 | graph reallocs = 0 / 0 (same size) / (changed size) 24.49.148.810 I slot release: id 1 | task 26868 | stop processing: n_tokens = 827, truncated = 0 24.49.149.283 I slot print_timing: id 2 | task 26869 | prompt eval time = 3332.47 ms / 854 tokens ( 3.90 ms per token, 256.27 tokens per second) 24.49.149.285 I slot print_timing: id 2 | task 26869 | eval time = 951.66 ms / 2 tokens ( 951.66 ms per token, 1.05 tokens per second) 24.49.149.286 I slot print_timing: id 2 | task 26869 | total time = 4284.14 ms / 856 tokens 24.49.149.286 I slot print_timing: id 2 | task 26869 | graphs reused = 25423 24.49.149.287 I slot print_timing: id 2 | task 26869 | graph reallocs = 0 / 0 (same size) / (changed size) 24.49.149.334 I slot release: id 2 | task 26869 | stop processing: n_tokens = 855, truncated = 0 24.49.793.386 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 827, t_last = 336876516793 24.50.434.148 I slot launch_slot_: id 1 | task 26877 | processing task, is_child = 0 24.50.437.988 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 336876517317 24.50.438.089 I slot launch_slot_: id 2 | task 26878 | processing task, is_child = 0 24.52.766.862 I slot print_timing: id 0 | task 26874 | prompt eval time = 3220.61 ms / 847 tokens ( 3.80 ms per token, 262.99 tokens per second) 24.52.766.864 I slot print_timing: id 0 | task 26874 | eval time = 1336.46 ms / 2 tokens ( 1336.46 ms per token, 0.75 tokens per second) 24.52.766.864 I slot print_timing: id 0 | task 26874 | total time = 4557.07 ms / 849 tokens 24.52.766.865 I slot print_timing: id 0 | task 26874 | graphs reused = 25423 24.52.766.865 I slot print_timing: id 0 | task 26874 | graph reallocs = 0 / 0 (same size) / (changed size) 24.52.766.920 I slot release: id 0 | task 26874 | stop processing: n_tokens = 848, truncated = 0 24.52.767.256 I slot print_timing: id 3 | task 26873 | prompt eval time = 3220.79 ms / 828 tokens ( 3.89 ms per token, 257.08 tokens per second) 24.52.767.259 I slot print_timing: id 3 | task 26873 | eval time = 1336.54 ms / 2 tokens ( 1336.54 ms per token, 0.75 tokens per second) 24.52.767.259 I slot print_timing: id 3 | task 26873 | total time = 4557.33 ms / 830 tokens 24.52.767.259 I slot print_timing: id 3 | task 26873 | graphs reused = 25423 24.52.767.260 I slot print_timing: id 3 | task 26873 | graph reallocs = 0 / 0 (same size) / (changed size) 24.52.767.305 I slot release: id 3 | task 26873 | stop processing: n_tokens = 829, truncated = 0 24.52.832.079 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 848, t_last = 336880134903 24.52.835.019 I slot launch_slot_: id 0 | task 26882 | processing task, is_child = 0 24.52.837.003 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 829, t_last = 336880135288 24.52.837.077 I slot launch_slot_: id 3 | task 26883 | processing task, is_child = 0 24.53.532.686 I slot print_timing: id 1 | task 26877 | prompt eval time = 2393.36 ms / 867 tokens ( 2.76 ms per token, 362.25 tokens per second) 24.53.532.691 I slot print_timing: id 1 | task 26877 | eval time = 700.97 ms / 2 tokens ( 700.97 ms per token, 1.43 tokens per second) 24.53.532.692 I slot print_timing: id 1 | task 26877 | total time = 3094.33 ms / 869 tokens 24.53.532.692 I slot print_timing: id 1 | task 26877 | graphs reused = 25423 24.53.532.692 I slot print_timing: id 1 | task 26877 | graph reallocs = 0 / 0 (same size) / (changed size) 24.53.532.747 I slot release: id 1 | task 26877 | stop processing: n_tokens = 868, truncated = 0 24.53.533.185 I slot print_timing: id 2 | task 26878 | prompt eval time = 2393.65 ms / 759 tokens ( 3.15 ms per token, 317.09 tokens per second) 24.53.533.187 I slot print_timing: id 2 | task 26878 | eval time = 701.11 ms / 2 tokens ( 701.11 ms per token, 1.43 tokens per second) 24.53.533.188 I slot print_timing: id 2 | task 26878 | total time = 3094.76 ms / 761 tokens 24.53.533.188 I slot print_timing: id 2 | task 26878 | graphs reused = 25423 24.53.533.188 I slot print_timing: id 2 | task 26878 | graph reallocs = 0 / 0 (same size) / (changed size) 24.53.533.226 I slot release: id 2 | task 26878 | stop processing: n_tokens = 760, truncated = 0 24.54.180.582 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 868, t_last = 336880900730 24.54.818.877 I slot launch_slot_: id 1 | task 26886 | processing task, is_child = 0 24.54.822.072 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 336880901209 24.54.822.166 I slot launch_slot_: id 2 | task 26887 | processing task, is_child = 0 24.56.854.142 I slot print_timing: id 0 | task 26882 | prompt eval time = 2692.77 ms / 728 tokens ( 3.70 ms per token, 270.35 tokens per second) 24.56.854.148 I slot print_timing: id 0 | task 26882 | eval time = 1324.29 ms / 2 tokens ( 1324.29 ms per token, 0.76 tokens per second) 24.56.854.149 I slot print_timing: id 0 | task 26882 | total time = 4017.06 ms / 730 tokens 24.56.854.149 I slot print_timing: id 0 | task 26882 | graphs reused = 25423 24.56.854.150 I slot print_timing: id 0 | task 26882 | graph reallocs = 0 / 0 (same size) / (changed size) 24.56.854.195 I slot release: id 0 | task 26882 | stop processing: n_tokens = 729, truncated = 0 24.56.854.516 I slot print_timing: id 3 | task 26883 | prompt eval time = 2693.05 ms / 682 tokens ( 3.95 ms per token, 253.24 tokens per second) 24.56.854.518 I slot print_timing: id 3 | task 26883 | eval time = 1324.31 ms / 2 tokens ( 1324.31 ms per token, 0.76 tokens per second) 24.56.854.519 I slot print_timing: id 3 | task 26883 | total time = 4017.37 ms / 684 tokens 24.56.854.519 I slot print_timing: id 3 | task 26883 | graphs reused = 25423 24.56.854.519 I slot print_timing: id 3 | task 26883 | graph reallocs = 0 / 0 (same size) / (changed size) 24.56.854.557 I slot release: id 3 | task 26883 | stop processing: n_tokens = 683, truncated = 0 24.56.943.991 I slot print_timing: id 1 | task 26886 | prompt eval time = 2096.29 ms / 665 tokens ( 3.15 ms per token, 317.23 tokens per second) 24.56.943.994 I slot print_timing: id 1 | task 26886 | eval time = 25.32 ms / 2 tokens ( 25.32 ms per token, 39.49 tokens per second) 24.56.943.995 I slot print_timing: id 1 | task 26886 | total time = 2121.62 ms / 667 tokens 24.56.943.995 I slot print_timing: id 1 | task 26886 | graphs reused = 25423 24.56.943.996 I slot print_timing: id 1 | task 26886 | graph reallocs = 0 / 0 (same size) / (changed size) 24.56.944.034 I slot release: id 1 | task 26886 | stop processing: n_tokens = 666, truncated = 0 24.56.944.309 I slot print_timing: id 2 | task 26887 | prompt eval time = 2096.57 ms / 700 tokens ( 3.00 ms per token, 333.88 tokens per second) 24.56.944.312 I slot print_timing: id 2 | task 26887 | eval time = 25.29 ms / 2 tokens ( 25.29 ms per token, 39.54 tokens per second) 24.56.944.313 I slot print_timing: id 2 | task 26887 | total time = 2121.86 ms / 702 tokens 24.56.944.313 I slot print_timing: id 2 | task 26887 | graphs reused = 25423 24.56.944.313 I slot print_timing: id 2 | task 26887 | graph reallocs = 0 / 0 (same size) / (changed size) 24.56.944.342 I slot release: id 2 | task 26887 | stop processing: n_tokens = 701, truncated = 0 25.00.061.364 I srv operator(): operator(): cleaning up before exit...