/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/8d1b680a697c/Spark-X2.6-4B-Q3_K_M.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.050.556 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.050.610 I srv llama_server: initializing ... 0.00.050.615 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.050.697 I srv init_listene: The UI is disabled 0.00.050.700 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.050.736 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) 0.00.052.371 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/8d1b680a697c/Spark-X2.6-4B-Q3_K_M.gguf' 0.00.460.691 I cmn init: llama threadpool init, n_threads = 8 0.00.558.846 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.00.567.948 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.567.960 I srv llama_server: model loaded 0.00.567.963 I srv llama_server: listening on http://127.0.0.1:8091 1.20.486.884 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 1.20.486.979 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 1.20.486.982 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 1.20.487.017 I slot launch_slot_: id 1 | task 1 | processing task, is_child = 0 1.20.487.020 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 1.20.487.046 I slot launch_slot_: id 2 | task 2 | processing task, is_child = 0 1.20.487.048 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 1.20.487.073 I slot launch_slot_: id 3 | task 3 | processing task, is_child = 0 1.21.761.184 I slot print_timing: id 0 | task 0 | prompt eval time = 1229.40 ms / 134 tokens ( 9.17 ms per token, 109.00 tokens per second) 1.21.761.188 I slot print_timing: id 0 | task 0 | eval time = 44.70 ms / 2 tokens ( 44.70 ms per token, 22.37 tokens per second) 1.21.761.189 I slot print_timing: id 0 | task 0 | total time = 1274.10 ms / 136 tokens 1.21.761.193 I slot print_timing: id 0 | task 0 | graphs reused = 1 1.21.761.193 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.761.220 I slot release: id 0 | task 0 | stop processing: n_tokens = 135, truncated = 0 1.21.763.018 I slot print_timing: id 1 | task 1 | prompt eval time = 1232.21 ms / 128 tokens ( 9.63 ms per token, 103.88 tokens per second) 1.21.763.021 I slot print_timing: id 1 | task 1 | eval time = 43.72 ms / 2 tokens ( 43.72 ms per token, 22.87 tokens per second) 1.21.763.022 I slot print_timing: id 1 | task 1 | total time = 1275.93 ms / 130 tokens 1.21.763.022 I slot print_timing: id 1 | task 1 | graphs reused = 1 1.21.763.022 I slot print_timing: id 1 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.763.036 I slot release: id 1 | task 1 | stop processing: n_tokens = 129, truncated = 0 1.21.764.841 I slot print_timing: id 2 | task 2 | prompt eval time = 1234.63 ms / 130 tokens ( 9.50 ms per token, 105.29 tokens per second) 1.21.764.843 I slot print_timing: id 2 | task 2 | eval time = 43.12 ms / 2 tokens ( 43.12 ms per token, 23.19 tokens per second) 1.21.764.844 I slot print_timing: id 2 | task 2 | total time = 1277.75 ms / 132 tokens 1.21.764.844 I slot print_timing: id 2 | task 2 | graphs reused = 1 1.21.764.845 I slot print_timing: id 2 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.764.864 I slot release: id 2 | task 2 | stop processing: n_tokens = 131, truncated = 0 1.21.766.662 I slot print_timing: id 3 | task 3 | prompt eval time = 1237.00 ms / 142 tokens ( 8.71 ms per token, 114.79 tokens per second) 1.21.766.664 I slot print_timing: id 3 | task 3 | eval time = 42.56 ms / 2 tokens ( 42.56 ms per token, 23.50 tokens per second) 1.21.766.666 I slot print_timing: id 3 | task 3 | total time = 1279.56 ms / 144 tokens 1.21.766.667 I slot print_timing: id 3 | task 3 | graphs reused = 1 1.21.766.667 I slot print_timing: id 3 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.766.678 I slot release: id 3 | task 3 | stop processing: n_tokens = 143, truncated = 0 1.21.772.477 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.319 (> 0.100 thold), f_keep = 0.281 1.21.775.965 I slot launch_slot_: id 0 | task 8 | processing task, is_child = 0 1.21.785.428 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.287 1.21.785.507 I slot launch_slot_: id 1 | task 9 | processing task, is_child = 0 1.21.785.567 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.266 1.21.785.635 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 1.21.785.667 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.282 1.21.785.731 I slot launch_slot_: id 2 | task 11 | processing task, is_child = 0 1.23.244.921 I slot print_timing: id 0 | task 8 | prompt eval time = 1414.33 ms / 110 tokens ( 12.86 ms per token, 77.78 tokens per second) 1.23.244.926 I slot print_timing: id 0 | task 8 | eval time = 44.85 ms / 2 tokens ( 44.85 ms per token, 22.30 tokens per second) 1.23.244.927 I slot print_timing: id 0 | task 8 | total time = 1459.18 ms / 112 tokens 1.23.244.927 I slot print_timing: id 0 | task 8 | graphs reused = 1 1.23.244.928 I slot print_timing: id 0 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.244.951 I slot release: id 0 | task 8 | stop processing: n_tokens = 120, truncated = 0 1.23.246.953 I slot print_timing: id 1 | task 9 | prompt eval time = 1416.70 ms / 164 tokens ( 8.64 ms per token, 115.76 tokens per second) 1.23.246.955 I slot print_timing: id 1 | task 9 | eval time = 44.32 ms / 2 tokens ( 44.32 ms per token, 22.56 tokens per second) 1.23.246.956 I slot print_timing: id 1 | task 9 | total time = 1461.02 ms / 166 tokens 1.23.246.956 I slot print_timing: id 1 | task 9 | graphs reused = 1 1.23.246.957 I slot print_timing: id 1 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.246.975 I slot release: id 1 | task 9 | stop processing: n_tokens = 174, truncated = 0 1.23.248.803 I slot print_timing: id 2 | task 11 | prompt eval time = 1418.99 ms / 204 tokens ( 6.96 ms per token, 143.76 tokens per second) 1.23.248.807 I slot print_timing: id 2 | task 11 | eval time = 43.70 ms / 2 tokens ( 43.70 ms per token, 22.89 tokens per second) 1.23.248.807 I slot print_timing: id 2 | task 11 | total time = 1462.69 ms / 206 tokens 1.23.248.808 I slot print_timing: id 2 | task 11 | graphs reused = 1 1.23.248.808 I slot print_timing: id 2 | task 11 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.248.827 I slot release: id 2 | task 11 | stop processing: n_tokens = 214, truncated = 0 1.23.250.582 I slot print_timing: id 3 | task 10 | prompt eval time = 1421.16 ms / 159 tokens ( 8.94 ms per token, 111.88 tokens per second) 1.23.250.586 I slot print_timing: id 3 | task 10 | eval time = 43.13 ms / 2 tokens ( 43.13 ms per token, 23.19 tokens per second) 1.23.250.586 I slot print_timing: id 3 | task 10 | total time = 1464.29 ms / 161 tokens 1.23.250.586 I slot print_timing: id 3 | task 10 | graphs reused = 1 1.23.250.587 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.250.603 I slot release: id 3 | task 10 | stop processing: n_tokens = 169, truncated = 0 1.23.251.209 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.297 (> 0.100 thold), f_keep = 0.317 1.23.253.978 I slot launch_slot_: id 0 | task 16 | processing task, is_child = 0 1.23.268.290 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.213 1.23.268.384 I slot launch_slot_: id 1 | task 17 | processing task, is_child = 0 1.23.268.468 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.173 1.23.268.548 I slot launch_slot_: id 2 | task 18 | processing task, is_child = 0 1.23.268.586 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.287 (> 0.100 thold), f_keep = 0.219 1.23.268.663 I slot launch_slot_: id 3 | task 19 | processing task, is_child = 0 1.24.457.165 I slot print_timing: id 0 | task 16 | prompt eval time = 1141.98 ms / 119 tokens ( 9.60 ms per token, 104.21 tokens per second) 1.24.457.170 I slot print_timing: id 0 | task 16 | eval time = 46.51 ms / 2 tokens ( 46.51 ms per token, 21.50 tokens per second) 1.24.457.171 I slot print_timing: id 0 | task 16 | total time = 1188.49 ms / 121 tokens 1.24.457.172 I slot print_timing: id 0 | task 16 | graphs reused = 1 1.24.457.172 I slot print_timing: id 0 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.457.211 I slot release: id 0 | task 16 | stop processing: n_tokens = 129, truncated = 0 1.24.459.342 I slot print_timing: id 1 | task 17 | prompt eval time = 1144.88 ms / 151 tokens ( 7.58 ms per token, 131.89 tokens per second) 1.24.459.348 I slot print_timing: id 1 | task 17 | eval time = 45.61 ms / 2 tokens ( 45.61 ms per token, 21.93 tokens per second) 1.24.459.349 I slot print_timing: id 1 | task 17 | total time = 1190.49 ms / 153 tokens 1.24.459.349 I slot print_timing: id 1 | task 17 | graphs reused = 1 1.24.459.350 I slot print_timing: id 1 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.459.384 I slot release: id 1 | task 17 | stop processing: n_tokens = 161, truncated = 0 1.24.461.315 I slot print_timing: id 2 | task 18 | prompt eval time = 1147.59 ms / 127 tokens ( 9.04 ms per token, 110.67 tokens per second) 1.24.461.318 I slot print_timing: id 2 | task 18 | eval time = 44.65 ms / 2 tokens ( 44.65 ms per token, 22.40 tokens per second) 1.24.461.319 I slot print_timing: id 2 | task 18 | total time = 1192.24 ms / 129 tokens 1.24.461.319 I slot print_timing: id 2 | task 18 | graphs reused = 1 1.24.461.320 I slot print_timing: id 2 | task 18 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.461.332 I slot release: id 2 | task 18 | stop processing: n_tokens = 137, truncated = 0 1.24.463.168 I slot print_timing: id 3 | task 19 | prompt eval time = 1150.17 ms / 120 tokens ( 9.58 ms per token, 104.33 tokens per second) 1.24.463.175 I slot print_timing: id 3 | task 19 | eval time = 43.68 ms / 2 tokens ( 43.68 ms per token, 22.89 tokens per second) 1.24.463.176 I slot print_timing: id 3 | task 19 | total time = 1193.85 ms / 122 tokens 1.24.463.176 I slot print_timing: id 3 | task 19 | graphs reused = 1 1.24.463.177 I slot print_timing: id 3 | task 19 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.463.195 I slot release: id 3 | task 19 | stop processing: n_tokens = 130, truncated = 0 1.24.464.001 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.287 1.24.465.372 I slot launch_slot_: id 0 | task 24 | processing task, is_child = 0 1.24.476.440 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.230 1.24.476.537 I slot launch_slot_: id 1 | task 25 | processing task, is_child = 0 1.24.476.610 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.270 1.24.476.688 I slot launch_slot_: id 2 | task 26 | processing task, is_child = 0 1.24.476.726 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.285 1.24.476.812 I slot launch_slot_: id 3 | task 27 | processing task, is_child = 0 1.25.834.006 I slot print_timing: id 0 | task 24 | prompt eval time = 1312.32 ms / 145 tokens ( 9.05 ms per token, 110.49 tokens per second) 1.25.834.011 I slot print_timing: id 0 | task 24 | eval time = 44.86 ms / 2 tokens ( 44.86 ms per token, 22.29 tokens per second) 1.25.834.012 I slot print_timing: id 0 | task 24 | total time = 1357.18 ms / 147 tokens 1.25.834.012 I slot print_timing: id 0 | task 24 | graphs reused = 1 1.25.834.013 I slot print_timing: id 0 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.834.038 I slot release: id 0 | task 24 | stop processing: n_tokens = 155, truncated = 0 1.25.836.140 I slot print_timing: id 1 | task 25 | prompt eval time = 1314.63 ms / 184 tokens ( 7.14 ms per token, 139.96 tokens per second) 1.25.836.144 I slot print_timing: id 1 | task 25 | eval time = 44.52 ms / 2 tokens ( 44.52 ms per token, 22.46 tokens per second) 1.25.836.146 I slot print_timing: id 1 | task 25 | total time = 1359.15 ms / 186 tokens 1.25.836.147 I slot print_timing: id 1 | task 25 | graphs reused = 1 1.25.836.147 I slot print_timing: id 1 | task 25 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.836.181 I slot release: id 1 | task 25 | stop processing: n_tokens = 194, truncated = 0 1.25.838.038 I slot print_timing: id 2 | task 26 | prompt eval time = 1316.98 ms / 138 tokens ( 9.54 ms per token, 104.78 tokens per second) 1.25.838.041 I slot print_timing: id 2 | task 26 | eval time = 43.91 ms / 2 tokens ( 43.91 ms per token, 22.77 tokens per second) 1.25.838.042 I slot print_timing: id 2 | task 26 | total time = 1360.89 ms / 140 tokens 1.25.838.042 I slot print_timing: id 2 | task 26 | graphs reused = 1 1.25.838.043 I slot print_timing: id 2 | task 26 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.838.057 I slot release: id 2 | task 26 | stop processing: n_tokens = 148, truncated = 0 1.25.839.820 I slot print_timing: id 3 | task 27 | prompt eval time = 1319.47 ms / 122 tokens ( 10.82 ms per token, 92.46 tokens per second) 1.25.839.822 I slot print_timing: id 3 | task 27 | eval time = 43.05 ms / 2 tokens ( 43.05 ms per token, 23.23 tokens per second) 1.25.839.823 I slot print_timing: id 3 | task 27 | total time = 1362.52 ms / 124 tokens 1.25.839.823 I slot print_timing: id 3 | task 27 | graphs reused = 1 1.25.839.824 I slot print_timing: id 3 | task 27 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.839.834 I slot release: id 3 | task 27 | stop processing: n_tokens = 132, truncated = 0 1.25.839.840 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.239 1.25.844.821 I slot launch_slot_: id 0 | task 32 | processing task, is_child = 0 1.25.853.411 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.191 1.25.853.503 I slot launch_slot_: id 1 | task 33 | processing task, is_child = 0 1.25.853.577 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.250 1.25.853.653 I slot launch_slot_: id 2 | task 34 | processing task, is_child = 0 1.25.853.686 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.280 1.25.854.272 I slot launch_slot_: id 3 | task 35 | processing task, is_child = 0 1.27.165.759 I slot print_timing: id 0 | task 32 | prompt eval time = 1272.26 ms / 133 tokens ( 9.57 ms per token, 104.54 tokens per second) 1.27.165.762 I slot print_timing: id 0 | task 32 | eval time = 39.21 ms / 2 tokens ( 39.21 ms per token, 25.50 tokens per second) 1.27.165.763 I slot print_timing: id 0 | task 32 | total time = 1311.47 ms / 135 tokens 1.27.165.763 I slot print_timing: id 0 | task 32 | graphs reused = 1 1.27.165.764 I slot print_timing: id 0 | task 32 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.165.789 I slot release: id 0 | task 32 | stop processing: n_tokens = 143, truncated = 0 1.27.167.084 I slot print_timing: id 1 | task 33 | prompt eval time = 1273.23 ms / 181 tokens ( 7.03 ms per token, 142.16 tokens per second) 1.27.167.087 I slot print_timing: id 1 | task 33 | eval time = 39.44 ms / 2 tokens ( 39.44 ms per token, 25.36 tokens per second) 1.27.167.088 I slot print_timing: id 1 | task 33 | total time = 1312.66 ms / 183 tokens 1.27.167.088 I slot print_timing: id 1 | task 33 | graphs reused = 1 1.27.167.089 I slot print_timing: id 1 | task 33 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.167.104 I slot release: id 1 | task 33 | stop processing: n_tokens = 191, truncated = 0 1.27.168.422 I slot print_timing: id 2 | task 34 | prompt eval time = 1274.26 ms / 149 tokens ( 8.55 ms per token, 116.93 tokens per second) 1.27.168.424 I slot print_timing: id 2 | task 34 | eval time = 39.60 ms / 2 tokens ( 39.60 ms per token, 25.25 tokens per second) 1.27.168.425 I slot print_timing: id 2 | task 34 | total time = 1313.86 ms / 151 tokens 1.27.168.425 I slot print_timing: id 2 | task 34 | graphs reused = 1 1.27.168.425 I slot print_timing: id 2 | task 34 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.168.440 I slot release: id 2 | task 34 | stop processing: n_tokens = 159, truncated = 0 1.27.169.736 I slot print_timing: id 3 | task 35 | prompt eval time = 1275.35 ms / 127 tokens ( 10.04 ms per token, 99.58 tokens per second) 1.27.169.737 I slot print_timing: id 3 | task 35 | eval time = 39.69 ms / 2 tokens ( 39.69 ms per token, 25.19 tokens per second) 1.27.169.738 I slot print_timing: id 3 | task 35 | total time = 1315.04 ms / 129 tokens 1.27.169.738 I slot print_timing: id 3 | task 35 | graphs reused = 1 1.27.169.738 I slot print_timing: id 3 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.169.753 I slot release: id 3 | task 35 | stop processing: n_tokens = 137, truncated = 0 1.27.171.432 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.298 (> 0.100 thold), f_keep = 0.259 1.27.174.925 I slot launch_slot_: id 0 | task 40 | processing task, is_child = 0 1.27.184.942 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.194 1.27.185.020 I slot launch_slot_: id 1 | task 41 | processing task, is_child = 0 1.27.185.076 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.277 1.27.185.135 I slot launch_slot_: id 3 | task 42 | processing task, is_child = 0 1.27.185.167 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.233 1.27.185.227 I slot launch_slot_: id 2 | task 43 | processing task, is_child = 0 1.28.399.347 I slot print_timing: id 0 | task 40 | prompt eval time = 1168.41 ms / 115 tokens ( 10.16 ms per token, 98.42 tokens per second) 1.28.399.352 I slot print_timing: id 0 | task 40 | eval time = 45.69 ms / 2 tokens ( 45.69 ms per token, 21.89 tokens per second) 1.28.399.353 I slot print_timing: id 0 | task 40 | total time = 1214.11 ms / 117 tokens 1.28.399.353 I slot print_timing: id 0 | task 40 | graphs reused = 1 1.28.399.354 I slot print_timing: id 0 | task 40 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.399.380 I slot release: id 0 | task 40 | stop processing: n_tokens = 125, truncated = 0 1.28.401.474 I slot print_timing: id 1 | task 41 | prompt eval time = 1171.15 ms / 144 tokens ( 8.13 ms per token, 122.96 tokens per second) 1.28.401.479 I slot print_timing: id 1 | task 41 | eval time = 44.94 ms / 2 tokens ( 44.94 ms per token, 22.25 tokens per second) 1.28.401.480 I slot print_timing: id 1 | task 41 | total time = 1216.09 ms / 146 tokens 1.28.401.480 I slot print_timing: id 1 | task 41 | graphs reused = 1 1.28.401.481 I slot print_timing: id 1 | task 41 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.401.499 I slot release: id 1 | task 41 | stop processing: n_tokens = 154, truncated = 0 1.28.403.467 I slot print_timing: id 2 | task 43 | prompt eval time = 1173.58 ms / 148 tokens ( 7.93 ms per token, 126.11 tokens per second) 1.28.403.471 I slot print_timing: id 2 | task 43 | eval time = 44.38 ms / 2 tokens ( 44.38 ms per token, 22.53 tokens per second) 1.28.403.472 I slot print_timing: id 2 | task 43 | total time = 1217.96 ms / 150 tokens 1.28.403.472 I slot print_timing: id 2 | task 43 | graphs reused = 1 1.28.403.473 I slot print_timing: id 2 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.403.528 I slot release: id 2 | task 43 | stop processing: n_tokens = 158, truncated = 0 1.28.405.307 I slot print_timing: id 3 | task 42 | prompt eval time = 1176.17 ms / 122 tokens ( 9.64 ms per token, 103.73 tokens per second) 1.28.405.312 I slot print_timing: id 3 | task 42 | eval time = 43.51 ms / 2 tokens ( 43.51 ms per token, 22.99 tokens per second) 1.28.405.313 I slot print_timing: id 3 | task 42 | total time = 1219.68 ms / 124 tokens 1.28.405.313 I slot print_timing: id 3 | task 42 | graphs reused = 1 1.28.405.314 I slot print_timing: id 3 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.405.329 I slot release: id 3 | task 42 | stop processing: n_tokens = 132, truncated = 0 1.28.405.577 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.296 1.28.408.454 I slot launch_slot_: id 0 | task 48 | processing task, is_child = 0 1.28.418.951 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.288 1.28.419.578 I slot launch_slot_: id 3 | task 49 | processing task, is_child = 0 1.28.419.655 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.240 1.28.419.734 I slot launch_slot_: id 1 | task 50 | processing task, is_child = 0 1.28.419.773 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.308 (> 0.100 thold), f_keep = 0.234 1.28.419.850 I slot launch_slot_: id 2 | task 51 | processing task, is_child = 0 1.29.581.779 I slot print_timing: id 0 | task 48 | prompt eval time = 1116.80 ms / 124 tokens ( 9.01 ms per token, 111.03 tokens per second) 1.29.581.783 I slot print_timing: id 0 | task 48 | eval time = 45.11 ms / 2 tokens ( 45.11 ms per token, 22.17 tokens per second) 1.29.581.784 I slot print_timing: id 0 | task 48 | total time = 1161.91 ms / 126 tokens 1.29.581.785 I slot print_timing: id 0 | task 48 | graphs reused = 1 1.29.581.786 I slot print_timing: id 0 | task 48 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.581.813 I slot release: id 0 | task 48 | stop processing: n_tokens = 134, truncated = 0 1.29.583.891 I slot print_timing: id 1 | task 50 | prompt eval time = 1119.23 ms / 148 tokens ( 7.56 ms per token, 132.23 tokens per second) 1.29.583.894 I slot print_timing: id 1 | task 50 | eval time = 44.65 ms / 2 tokens ( 44.65 ms per token, 22.40 tokens per second) 1.29.583.895 I slot print_timing: id 1 | task 50 | total time = 1163.88 ms / 150 tokens 1.29.583.895 I slot print_timing: id 1 | task 50 | graphs reused = 1 1.29.583.896 I slot print_timing: id 1 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.583.916 I slot release: id 1 | task 50 | stop processing: n_tokens = 158, truncated = 0 1.29.585.881 I slot print_timing: id 2 | task 51 | prompt eval time = 1121.63 ms / 111 tokens ( 10.10 ms per token, 98.96 tokens per second) 1.29.585.886 I slot print_timing: id 2 | task 51 | eval time = 44.09 ms / 2 tokens ( 44.09 ms per token, 22.68 tokens per second) 1.29.585.887 I slot print_timing: id 2 | task 51 | total time = 1165.72 ms / 113 tokens 1.29.585.887 I slot print_timing: id 2 | task 51 | graphs reused = 1 1.29.585.888 I slot print_timing: id 2 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.585.901 I slot release: id 2 | task 51 | stop processing: n_tokens = 121, truncated = 0 1.29.587.694 I slot print_timing: id 3 | task 49 | prompt eval time = 1123.95 ms / 114 tokens ( 9.86 ms per token, 101.43 tokens per second) 1.29.587.697 I slot print_timing: id 3 | task 49 | eval time = 43.44 ms / 2 tokens ( 43.44 ms per token, 23.02 tokens per second) 1.29.587.699 I slot print_timing: id 3 | task 49 | total time = 1167.39 ms / 116 tokens 1.29.587.699 I slot print_timing: id 3 | task 49 | graphs reused = 1 1.29.587.700 I slot print_timing: id 3 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.587.712 I slot release: id 3 | task 49 | stop processing: n_tokens = 124, truncated = 0 1.29.588.022 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.293 (> 0.100 thold), f_keep = 0.331 1.29.589.540 I slot launch_slot_: id 3 | task 56 | processing task, is_child = 0 1.29.598.180 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.322 (> 0.100 thold), f_keep = 0.276 1.29.598.284 I slot launch_slot_: id 0 | task 57 | processing task, is_child = 0 1.29.598.355 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.234 1.29.598.436 I slot launch_slot_: id 1 | task 58 | processing task, is_child = 0 1.29.598.471 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.306 1.29.599.101 I slot launch_slot_: id 2 | task 59 | processing task, is_child = 0 1.30.737.015 I slot print_timing: id 0 | task 57 | prompt eval time = 1099.11 ms / 106 tokens ( 10.37 ms per token, 96.44 tokens per second) 1.30.737.017 I slot print_timing: id 0 | task 57 | eval time = 38.79 ms / 2 tokens ( 38.79 ms per token, 25.78 tokens per second) 1.30.737.018 I slot print_timing: id 0 | task 57 | total time = 1137.90 ms / 108 tokens 1.30.737.019 I slot print_timing: id 0 | task 57 | graphs reused = 1 1.30.737.019 I slot print_timing: id 0 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.737.037 I slot release: id 0 | task 57 | stop processing: n_tokens = 116, truncated = 0 1.30.738.185 I slot print_timing: id 1 | task 58 | prompt eval time = 1100.24 ms / 138 tokens ( 7.97 ms per token, 125.43 tokens per second) 1.30.738.187 I slot print_timing: id 1 | task 58 | eval time = 38.68 ms / 2 tokens ( 38.68 ms per token, 25.85 tokens per second) 1.30.738.187 I slot print_timing: id 1 | task 58 | total time = 1138.92 ms / 140 tokens 1.30.738.188 I slot print_timing: id 1 | task 58 | graphs reused = 1 1.30.738.188 I slot print_timing: id 1 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.738.199 I slot release: id 1 | task 58 | stop processing: n_tokens = 148, truncated = 0 1.30.739.476 I slot print_timing: id 2 | task 59 | prompt eval time = 1101.13 ms / 113 tokens ( 9.74 ms per token, 102.62 tokens per second) 1.30.739.479 I slot print_timing: id 2 | task 59 | eval time = 38.92 ms / 2 tokens ( 38.92 ms per token, 25.69 tokens per second) 1.30.739.479 I slot print_timing: id 2 | task 59 | total time = 1140.05 ms / 115 tokens 1.30.739.479 I slot print_timing: id 2 | task 59 | graphs reused = 1 1.30.739.480 I slot print_timing: id 2 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.739.495 I slot release: id 2 | task 59 | stop processing: n_tokens = 123, truncated = 0 1.30.740.803 I slot print_timing: id 3 | task 56 | prompt eval time = 1102.13 ms / 131 tokens ( 8.41 ms per token, 118.86 tokens per second) 1.30.740.805 I slot print_timing: id 3 | task 56 | eval time = 39.12 ms / 2 tokens ( 39.12 ms per token, 25.56 tokens per second) 1.30.740.805 I slot print_timing: id 3 | task 56 | total time = 1141.25 ms / 133 tokens 1.30.740.805 I slot print_timing: id 3 | task 56 | graphs reused = 1 1.30.740.805 I slot print_timing: id 3 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.740.814 I slot release: id 3 | task 56 | stop processing: n_tokens = 141, truncated = 0 1.30.741.454 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.319 1.30.743.538 I slot launch_slot_: id 0 | task 64 | processing task, is_child = 0 1.30.751.892 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.250 1.30.751.962 I slot launch_slot_: id 1 | task 65 | processing task, is_child = 0 1.30.752.013 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.301 1.30.752.068 I slot launch_slot_: id 2 | task 66 | processing task, is_child = 0 1.30.752.095 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.262 1.30.752.152 I slot launch_slot_: id 3 | task 67 | processing task, is_child = 0 1.32.219.093 I slot print_timing: id 0 | task 64 | prompt eval time = 1427.57 ms / 194 tokens ( 7.36 ms per token, 135.90 tokens per second) 1.32.219.095 I slot print_timing: id 0 | task 64 | eval time = 39.36 ms / 2 tokens ( 39.36 ms per token, 25.41 tokens per second) 1.32.219.096 I slot print_timing: id 0 | task 64 | total time = 1466.93 ms / 196 tokens 1.32.219.096 I slot print_timing: id 0 | task 64 | graphs reused = 1 1.32.219.097 I slot print_timing: id 0 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.219.123 I slot release: id 0 | task 64 | stop processing: n_tokens = 204, truncated = 0 1.32.220.238 I slot print_timing: id 1 | task 65 | prompt eval time = 1428.65 ms / 134 tokens ( 10.66 ms per token, 93.79 tokens per second) 1.32.220.241 I slot print_timing: id 1 | task 65 | eval time = 39.30 ms / 2 tokens ( 39.30 ms per token, 25.45 tokens per second) 1.32.220.242 I slot print_timing: id 1 | task 65 | total time = 1467.95 ms / 136 tokens 1.32.220.242 I slot print_timing: id 1 | task 65 | graphs reused = 1 1.32.220.242 I slot print_timing: id 1 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.220.266 I slot release: id 1 | task 65 | stop processing: n_tokens = 144, truncated = 0 1.32.221.373 I slot print_timing: id 2 | task 66 | prompt eval time = 1429.70 ms / 181 tokens ( 7.90 ms per token, 126.60 tokens per second) 1.32.221.375 I slot print_timing: id 2 | task 66 | eval time = 39.21 ms / 2 tokens ( 39.21 ms per token, 25.50 tokens per second) 1.32.221.375 I slot print_timing: id 2 | task 66 | total time = 1468.91 ms / 183 tokens 1.32.221.375 I slot print_timing: id 2 | task 66 | graphs reused = 1 1.32.221.376 I slot print_timing: id 2 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.221.392 I slot release: id 2 | task 66 | stop processing: n_tokens = 191, truncated = 0 1.32.222.505 I slot print_timing: id 3 | task 67 | prompt eval time = 1430.80 ms / 168 tokens ( 8.52 ms per token, 117.42 tokens per second) 1.32.222.508 I slot print_timing: id 3 | task 67 | eval time = 39.12 ms / 2 tokens ( 39.12 ms per token, 25.56 tokens per second) 1.32.222.509 I slot print_timing: id 3 | task 67 | total time = 1469.92 ms / 170 tokens 1.32.222.509 I slot print_timing: id 3 | task 67 | graphs reused = 1 1.32.222.509 I slot print_timing: id 3 | task 67 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.222.518 I slot release: id 3 | task 67 | stop processing: n_tokens = 178, truncated = 0 1.32.224.444 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.181 1.32.228.459 I slot launch_slot_: id 0 | task 72 | processing task, is_child = 0 1.32.237.419 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.257 1.32.238.030 I slot launch_slot_: id 1 | task 74 | processing task, is_child = 0 1.32.238.086 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.194 1.32.238.144 I slot launch_slot_: id 2 | task 73 | processing task, is_child = 0 1.32.238.176 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.208 1.32.238.766 I slot launch_slot_: id 3 | task 75 | processing task, is_child = 0 1.33.516.500 I slot print_timing: id 0 | task 72 | prompt eval time = 1238.66 ms / 152 tokens ( 8.15 ms per token, 122.71 tokens per second) 1.33.516.503 I slot print_timing: id 0 | task 72 | eval time = 39.06 ms / 2 tokens ( 39.06 ms per token, 25.60 tokens per second) 1.33.516.503 I slot print_timing: id 0 | task 72 | total time = 1277.72 ms / 154 tokens 1.33.516.504 I slot print_timing: id 0 | task 72 | graphs reused = 1 1.33.516.504 I slot print_timing: id 0 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.516.524 I slot release: id 0 | task 72 | stop processing: n_tokens = 162, truncated = 0 1.33.517.646 I slot print_timing: id 1 | task 74 | prompt eval time = 1239.86 ms / 143 tokens ( 8.67 ms per token, 115.34 tokens per second) 1.33.517.647 I slot print_timing: id 1 | task 74 | eval time = 38.88 ms / 2 tokens ( 38.88 ms per token, 25.72 tokens per second) 1.33.517.648 I slot print_timing: id 1 | task 74 | total time = 1278.74 ms / 145 tokens 1.33.517.648 I slot print_timing: id 1 | task 74 | graphs reused = 1 1.33.517.648 I slot print_timing: id 1 | task 74 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.517.658 I slot release: id 1 | task 74 | stop processing: n_tokens = 153, truncated = 0 1.33.518.763 I slot print_timing: id 2 | task 73 | prompt eval time = 1240.98 ms / 171 tokens ( 7.26 ms per token, 137.79 tokens per second) 1.33.518.765 I slot print_timing: id 2 | task 73 | eval time = 38.77 ms / 2 tokens ( 38.77 ms per token, 25.80 tokens per second) 1.33.518.765 I slot print_timing: id 2 | task 73 | total time = 1279.75 ms / 173 tokens 1.33.518.765 I slot print_timing: id 2 | task 73 | graphs reused = 1 1.33.518.766 I slot print_timing: id 2 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.518.778 I slot release: id 2 | task 73 | stop processing: n_tokens = 181, truncated = 0 1.33.519.853 I slot print_timing: id 3 | task 75 | prompt eval time = 1242.13 ms / 125 tokens ( 9.94 ms per token, 100.63 tokens per second) 1.33.519.855 I slot print_timing: id 3 | task 75 | eval time = 38.60 ms / 2 tokens ( 38.60 ms per token, 25.91 tokens per second) 1.33.519.856 I slot print_timing: id 3 | task 75 | total time = 1280.72 ms / 127 tokens 1.33.519.856 I slot print_timing: id 3 | task 75 | graphs reused = 1 1.33.519.856 I slot print_timing: id 3 | task 75 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.519.865 I slot release: id 3 | task 75 | stop processing: n_tokens = 135, truncated = 0 1.33.520.504 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.281 1.33.521.724 I slot launch_slot_: id 3 | task 80 | processing task, is_child = 0 1.33.529.822 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.228 1.33.529.895 I slot launch_slot_: id 0 | task 81 | processing task, is_child = 0 1.33.529.956 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.322 (> 0.100 thold), f_keep = 0.248 1.33.530.019 I slot launch_slot_: id 1 | task 82 | processing task, is_child = 0 1.33.530.051 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.204 1.33.530.606 I slot launch_slot_: id 2 | task 83 | processing task, is_child = 0 1.34.767.599 I slot print_timing: id 0 | task 81 | prompt eval time = 1198.29 ms / 130 tokens ( 9.22 ms per token, 108.49 tokens per second) 1.34.767.602 I slot print_timing: id 0 | task 81 | eval time = 38.69 ms / 2 tokens ( 38.69 ms per token, 25.84 tokens per second) 1.34.767.603 I slot print_timing: id 0 | task 81 | total time = 1236.98 ms / 132 tokens 1.34.767.603 I slot print_timing: id 0 | task 81 | graphs reused = 1 1.34.767.604 I slot print_timing: id 0 | task 81 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.767.623 I slot release: id 0 | task 81 | stop processing: n_tokens = 140, truncated = 0 1.34.768.724 I slot print_timing: id 1 | task 82 | prompt eval time = 1199.28 ms / 109 tokens ( 11.00 ms per token, 90.89 tokens per second) 1.34.768.726 I slot print_timing: id 1 | task 82 | eval time = 38.71 ms / 2 tokens ( 38.71 ms per token, 25.83 tokens per second) 1.34.768.727 I slot print_timing: id 1 | task 82 | total time = 1237.99 ms / 111 tokens 1.34.768.727 I slot print_timing: id 1 | task 82 | graphs reused = 1 1.34.768.728 I slot print_timing: id 1 | task 82 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.768.742 I slot release: id 1 | task 82 | stop processing: n_tokens = 119, truncated = 0 1.34.769.836 I slot print_timing: id 2 | task 83 | prompt eval time = 1200.24 ms / 160 tokens ( 7.50 ms per token, 133.31 tokens per second) 1.34.769.838 I slot print_timing: id 2 | task 83 | eval time = 38.75 ms / 2 tokens ( 38.75 ms per token, 25.81 tokens per second) 1.34.769.838 I slot print_timing: id 2 | task 83 | total time = 1238.99 ms / 162 tokens 1.34.769.838 I slot print_timing: id 2 | task 83 | graphs reused = 1 1.34.769.838 I slot print_timing: id 2 | task 83 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.769.850 I slot release: id 2 | task 83 | stop processing: n_tokens = 170, truncated = 0 1.34.770.973 I slot print_timing: id 3 | task 80 | prompt eval time = 1201.45 ms / 166 tokens ( 7.24 ms per token, 138.17 tokens per second) 1.34.770.975 I slot print_timing: id 3 | task 80 | eval time = 38.57 ms / 2 tokens ( 38.57 ms per token, 25.93 tokens per second) 1.34.770.975 I slot print_timing: id 3 | task 80 | total time = 1240.02 ms / 168 tokens 1.34.770.975 I slot print_timing: id 3 | task 80 | graphs reused = 1 1.34.770.976 I slot print_timing: id 3 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.770.983 I slot release: id 3 | task 80 | stop processing: n_tokens = 176, truncated = 0 1.34.772.314 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.264 1.34.773.424 I slot launch_slot_: id 0 | task 88 | processing task, is_child = 0 1.34.781.010 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.311 1.34.781.070 I slot launch_slot_: id 1 | task 89 | processing task, is_child = 0 1.34.781.120 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.224 1.34.781.187 I slot launch_slot_: id 2 | task 90 | processing task, is_child = 0 1.34.781.217 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.317 (> 0.100 thold), f_keep = 0.216 1.34.781.283 I slot launch_slot_: id 3 | task 91 | processing task, is_child = 0 1.36.029.182 I slot print_timing: id 0 | task 88 | prompt eval time = 1206.46 ms / 170 tokens ( 7.10 ms per token, 140.91 tokens per second) 1.36.029.186 I slot print_timing: id 0 | task 88 | eval time = 41.42 ms / 2 tokens ( 41.42 ms per token, 24.14 tokens per second) 1.36.029.188 I slot print_timing: id 0 | task 88 | total time = 1247.88 ms / 172 tokens 1.36.029.189 I slot print_timing: id 0 | task 88 | graphs reused = 1 1.36.029.189 I slot print_timing: id 0 | task 88 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.029.221 I slot release: id 0 | task 88 | stop processing: n_tokens = 180, truncated = 0 1.36.031.383 I slot print_timing: id 1 | task 89 | prompt eval time = 1208.10 ms / 113 tokens ( 10.69 ms per token, 93.54 tokens per second) 1.36.031.386 I slot print_timing: id 1 | task 89 | eval time = 41.87 ms / 2 tokens ( 41.87 ms per token, 23.88 tokens per second) 1.36.031.387 I slot print_timing: id 1 | task 89 | total time = 1249.97 ms / 115 tokens 1.36.031.388 I slot print_timing: id 1 | task 89 | graphs reused = 1 1.36.031.388 I slot print_timing: id 1 | task 89 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.031.409 I slot release: id 1 | task 89 | stop processing: n_tokens = 123, truncated = 0 1.36.033.511 I slot print_timing: id 2 | task 90 | prompt eval time = 1209.45 ms / 167 tokens ( 7.24 ms per token, 138.08 tokens per second) 1.36.033.514 I slot print_timing: id 2 | task 90 | eval time = 42.55 ms / 2 tokens ( 42.55 ms per token, 23.50 tokens per second) 1.36.033.515 I slot print_timing: id 2 | task 90 | total time = 1252.00 ms / 169 tokens 1.36.033.515 I slot print_timing: id 2 | task 90 | graphs reused = 1 1.36.033.516 I slot print_timing: id 2 | task 90 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.033.531 I slot release: id 2 | task 90 | stop processing: n_tokens = 177, truncated = 0 1.36.035.548 I slot print_timing: id 3 | task 91 | prompt eval time = 1210.80 ms / 111 tokens ( 10.91 ms per token, 91.67 tokens per second) 1.36.035.550 I slot print_timing: id 3 | task 91 | eval time = 43.11 ms / 2 tokens ( 43.11 ms per token, 23.19 tokens per second) 1.36.035.551 I slot print_timing: id 3 | task 91 | total time = 1253.92 ms / 113 tokens 1.36.035.551 I slot print_timing: id 3 | task 91 | graphs reused = 1 1.36.035.552 I slot print_timing: id 3 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.035.566 I slot release: id 3 | task 91 | stop processing: n_tokens = 121, truncated = 0 1.36.035.574 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.206 1.36.041.250 I slot launch_slot_: id 0 | task 96 | processing task, is_child = 0 1.36.051.743 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.301 1.36.052.448 I slot launch_slot_: id 1 | task 97 | processing task, is_child = 0 1.36.052.523 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.209 1.36.052.608 I slot launch_slot_: id 2 | task 98 | processing task, is_child = 0 1.36.052.643 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.306 1.36.052.731 I slot launch_slot_: id 3 | task 99 | processing task, is_child = 0 1.37.218.622 I slot print_timing: id 0 | task 96 | prompt eval time = 1127.14 ms / 136 tokens ( 8.29 ms per token, 120.66 tokens per second) 1.37.218.625 I slot print_timing: id 0 | task 96 | eval time = 38.75 ms / 2 tokens ( 38.75 ms per token, 25.81 tokens per second) 1.37.218.626 I slot print_timing: id 0 | task 96 | total time = 1165.88 ms / 138 tokens 1.37.218.626 I slot print_timing: id 0 | task 96 | graphs reused = 1 1.37.218.627 I slot print_timing: id 0 | task 96 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.218.646 I slot release: id 0 | task 96 | stop processing: n_tokens = 146, truncated = 0 1.37.219.755 I slot print_timing: id 1 | task 97 | prompt eval time = 1128.10 ms / 126 tokens ( 8.95 ms per token, 111.69 tokens per second) 1.37.219.757 I slot print_timing: id 1 | task 97 | eval time = 38.76 ms / 2 tokens ( 38.76 ms per token, 25.80 tokens per second) 1.37.219.757 I slot print_timing: id 1 | task 97 | total time = 1166.85 ms / 128 tokens 1.37.219.757 I slot print_timing: id 1 | task 97 | graphs reused = 1 1.37.219.758 I slot print_timing: id 1 | task 97 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.219.775 I slot release: id 1 | task 97 | stop processing: n_tokens = 136, truncated = 0 1.37.220.899 I slot print_timing: id 2 | task 98 | prompt eval time = 1129.24 ms / 149 tokens ( 7.58 ms per token, 131.95 tokens per second) 1.37.220.902 I slot print_timing: id 2 | task 98 | eval time = 38.62 ms / 2 tokens ( 38.62 ms per token, 25.90 tokens per second) 1.37.220.902 I slot print_timing: id 2 | task 98 | total time = 1167.86 ms / 151 tokens 1.37.220.902 I slot print_timing: id 2 | task 98 | graphs reused = 1 1.37.220.903 I slot print_timing: id 2 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.220.912 I slot release: id 2 | task 98 | stop processing: n_tokens = 159, truncated = 0 1.37.221.989 I slot print_timing: id 3 | task 99 | prompt eval time = 1130.29 ms / 124 tokens ( 9.12 ms per token, 109.71 tokens per second) 1.37.221.991 I slot print_timing: id 3 | task 99 | eval time = 38.48 ms / 2 tokens ( 38.48 ms per token, 25.99 tokens per second) 1.37.221.991 I slot print_timing: id 3 | task 99 | total time = 1168.78 ms / 126 tokens 1.37.221.992 I slot print_timing: id 3 | task 99 | graphs reused = 1 1.37.221.992 I slot print_timing: id 3 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.222.000 I slot release: id 3 | task 99 | stop processing: n_tokens = 134, truncated = 0 1.37.222.378 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.279 1.37.224.246 I slot launch_slot_: id 1 | task 104 | processing task, is_child = 0 1.37.232.783 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.253 1.37.233.372 I slot launch_slot_: id 0 | task 105 | processing task, is_child = 0 1.37.233.428 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.233 1.37.233.911 I slot launch_slot_: id 2 | task 106 | processing task, is_child = 0 1.37.233.936 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.276 1.37.234.434 I slot launch_slot_: id 3 | task 107 | processing task, is_child = 0 1.38.483.668 I slot print_timing: id 0 | task 105 | prompt eval time = 1204.09 ms / 126 tokens ( 9.56 ms per token, 104.64 tokens per second) 1.38.483.673 I slot print_timing: id 0 | task 105 | eval time = 45.13 ms / 2 tokens ( 45.13 ms per token, 22.16 tokens per second) 1.38.483.674 I slot print_timing: id 0 | task 105 | total time = 1249.22 ms / 128 tokens 1.38.483.675 I slot print_timing: id 0 | task 105 | graphs reused = 1 1.38.483.676 I slot print_timing: id 0 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.483.708 I slot release: id 0 | task 105 | stop processing: n_tokens = 136, truncated = 0 1.38.485.797 I slot print_timing: id 1 | task 104 | prompt eval time = 1206.45 ms / 148 tokens ( 8.15 ms per token, 122.67 tokens per second) 1.38.485.801 I slot print_timing: id 1 | task 104 | eval time = 44.78 ms / 2 tokens ( 44.78 ms per token, 22.33 tokens per second) 1.38.485.801 I slot print_timing: id 1 | task 104 | total time = 1251.23 ms / 150 tokens 1.38.485.802 I slot print_timing: id 1 | task 104 | graphs reused = 1 1.38.485.803 I slot print_timing: id 1 | task 104 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.485.821 I slot release: id 1 | task 104 | stop processing: n_tokens = 158, truncated = 0 1.38.487.654 I slot print_timing: id 2 | task 106 | prompt eval time = 1208.89 ms / 143 tokens ( 8.45 ms per token, 118.29 tokens per second) 1.38.487.656 I slot print_timing: id 2 | task 106 | eval time = 44.08 ms / 2 tokens ( 44.08 ms per token, 22.68 tokens per second) 1.38.487.657 I slot print_timing: id 2 | task 106 | total time = 1252.97 ms / 145 tokens 1.38.487.657 I slot print_timing: id 2 | task 106 | graphs reused = 1 1.38.487.658 I slot print_timing: id 2 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.487.677 I slot release: id 2 | task 106 | stop processing: n_tokens = 153, truncated = 0 1.38.489.459 I slot print_timing: id 3 | task 107 | prompt eval time = 1211.34 ms / 136 tokens ( 8.91 ms per token, 112.27 tokens per second) 1.38.489.464 I slot print_timing: id 3 | task 107 | eval time = 43.34 ms / 2 tokens ( 43.34 ms per token, 23.07 tokens per second) 1.38.489.465 I slot print_timing: id 3 | task 107 | total time = 1254.67 ms / 138 tokens 1.38.489.465 I slot print_timing: id 3 | task 107 | graphs reused = 1 1.38.489.466 I slot print_timing: id 3 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.489.477 I slot release: id 3 | task 107 | stop processing: n_tokens = 146, truncated = 0 1.38.489.820 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.295 (> 0.100 thold), f_keep = 0.241 1.38.493.153 I slot launch_slot_: id 1 | task 112 | processing task, is_child = 0 1.38.499.236 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.319 (> 0.100 thold), f_keep = 0.260 1.38.499.340 I slot launch_slot_: id 3 | task 113 | processing task, is_child = 0 1.38.499.415 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.280 (> 0.100 thold), f_keep = 0.272 1.38.499.497 I slot launch_slot_: id 0 | task 114 | processing task, is_child = 0 1.38.499.535 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.248 1.38.499.617 I slot launch_slot_: id 2 | task 115 | processing task, is_child = 0 1.39.718.744 I slot print_timing: id 0 | task 114 | prompt eval time = 1173.91 ms / 123 tokens ( 9.54 ms per token, 104.78 tokens per second) 1.39.718.748 I slot print_timing: id 0 | task 114 | eval time = 45.21 ms / 2 tokens ( 45.21 ms per token, 22.12 tokens per second) 1.39.718.749 I slot print_timing: id 0 | task 114 | total time = 1219.12 ms / 125 tokens 1.39.718.750 I slot print_timing: id 0 | task 114 | graphs reused = 1 1.39.718.750 I slot print_timing: id 0 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.718.783 I slot release: id 0 | task 114 | stop processing: n_tokens = 133, truncated = 0 1.39.720.837 I slot print_timing: id 1 | task 112 | prompt eval time = 1176.17 ms / 120 tokens ( 9.80 ms per token, 102.03 tokens per second) 1.39.720.840 I slot print_timing: id 1 | task 112 | eval time = 44.87 ms / 2 tokens ( 44.87 ms per token, 22.29 tokens per second) 1.39.720.842 I slot print_timing: id 1 | task 112 | total time = 1221.05 ms / 122 tokens 1.39.720.843 I slot print_timing: id 1 | task 112 | graphs reused = 1 1.39.720.843 I slot print_timing: id 1 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.720.861 I slot release: id 1 | task 112 | stop processing: n_tokens = 130, truncated = 0 1.39.722.666 I slot print_timing: id 2 | task 115 | prompt eval time = 1178.60 ms / 175 tokens ( 6.73 ms per token, 148.48 tokens per second) 1.39.722.669 I slot print_timing: id 2 | task 115 | eval time = 44.11 ms / 2 tokens ( 44.11 ms per token, 22.67 tokens per second) 1.39.722.669 I slot print_timing: id 2 | task 115 | total time = 1222.71 ms / 177 tokens 1.39.722.670 I slot print_timing: id 2 | task 115 | graphs reused = 1 1.39.722.670 I slot print_timing: id 2 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.722.685 I slot release: id 2 | task 115 | stop processing: n_tokens = 185, truncated = 0 1.39.724.445 I slot print_timing: id 3 | task 113 | prompt eval time = 1181.25 ms / 110 tokens ( 10.74 ms per token, 93.12 tokens per second) 1.39.724.448 I slot print_timing: id 3 | task 113 | eval time = 43.09 ms / 2 tokens ( 43.09 ms per token, 23.21 tokens per second) 1.39.724.449 I slot print_timing: id 3 | task 113 | total time = 1224.34 ms / 112 tokens 1.39.724.449 I slot print_timing: id 3 | task 113 | graphs reused = 1 1.39.724.449 I slot print_timing: id 3 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.724.461 I slot release: id 3 | task 113 | stop processing: n_tokens = 120, truncated = 0 1.39.724.749 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.299 (> 0.100 thold), f_keep = 0.292 1.39.727.461 I slot launch_slot_: id 1 | task 120 | processing task, is_child = 0 1.39.736.774 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.145 (> 0.100 thold), f_keep = 0.278 1.39.736.867 I slot launch_slot_: id 0 | task 121 | processing task, is_child = 0 1.39.736.951 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.317 1.39.737.043 I slot launch_slot_: id 3 | task 122 | processing task, is_child = 0 1.39.737.087 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.200 1.39.737.783 I slot launch_slot_: id 2 | task 123 | processing task, is_child = 0 1.41.296.007 I slot print_timing: id 0 | task 121 | prompt eval time = 1519.26 ms / 247 tokens ( 6.15 ms per token, 162.58 tokens per second) 1.41.296.010 I slot print_timing: id 0 | task 121 | eval time = 38.95 ms / 2 tokens ( 38.95 ms per token, 25.67 tokens per second) 1.41.296.011 I slot print_timing: id 0 | task 121 | total time = 1558.21 ms / 249 tokens 1.41.296.011 I slot print_timing: id 0 | task 121 | graphs reused = 1 1.41.296.011 I slot print_timing: id 0 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.296.040 I slot release: id 0 | task 121 | stop processing: n_tokens = 257, truncated = 0 1.41.297.340 I slot print_timing: id 1 | task 120 | prompt eval time = 1520.22 ms / 118 tokens ( 12.88 ms per token, 77.62 tokens per second) 1.41.297.343 I slot print_timing: id 1 | task 120 | eval time = 39.17 ms / 2 tokens ( 39.17 ms per token, 25.53 tokens per second) 1.41.297.344 I slot print_timing: id 1 | task 120 | total time = 1559.39 ms / 120 tokens 1.41.297.345 I slot print_timing: id 1 | task 120 | graphs reused = 1 1.41.297.345 I slot print_timing: id 1 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.297.366 I slot release: id 1 | task 120 | stop processing: n_tokens = 128, truncated = 0 1.41.298.692 I slot print_timing: id 2 | task 123 | prompt eval time = 1521.06 ms / 182 tokens ( 8.36 ms per token, 119.65 tokens per second) 1.41.298.694 I slot print_timing: id 2 | task 123 | eval time = 39.46 ms / 2 tokens ( 39.46 ms per token, 25.34 tokens per second) 1.41.298.694 I slot print_timing: id 2 | task 123 | total time = 1560.51 ms / 184 tokens 1.41.298.695 I slot print_timing: id 2 | task 123 | graphs reused = 1 1.41.298.695 I slot print_timing: id 2 | task 123 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.298.708 I slot release: id 2 | task 123 | stop processing: n_tokens = 192, truncated = 0 1.41.299.961 I slot print_timing: id 3 | task 122 | prompt eval time = 1521.92 ms / 138 tokens ( 11.03 ms per token, 90.68 tokens per second) 1.41.299.964 I slot print_timing: id 3 | task 122 | eval time = 39.66 ms / 2 tokens ( 39.66 ms per token, 25.21 tokens per second) 1.41.299.964 I slot print_timing: id 3 | task 122 | total time = 1561.58 ms / 140 tokens 1.41.299.964 I slot print_timing: id 3 | task 122 | graphs reused = 1 1.41.299.964 I slot print_timing: id 3 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.299.973 I slot release: id 3 | task 122 | stop processing: n_tokens = 148, truncated = 0 1.41.300.298 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.305 1.41.301.327 I slot launch_slot_: id 1 | task 128 | processing task, is_child = 0 1.41.313.328 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.247 (> 0.100 thold), f_keep = 0.257 1.41.313.882 I slot launch_slot_: id 3 | task 129 | processing task, is_child = 0 1.41.313.952 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.144 1.41.314.023 I slot launch_slot_: id 0 | task 130 | processing task, is_child = 0 1.41.314.054 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.193 1.41.314.115 I slot launch_slot_: id 2 | task 131 | processing task, is_child = 0 1.42.873.504 I slot print_timing: id 0 | task 130 | prompt eval time = 1517.61 ms / 162 tokens ( 9.37 ms per token, 106.75 tokens per second) 1.42.873.509 I slot print_timing: id 0 | task 130 | eval time = 41.76 ms / 2 tokens ( 41.76 ms per token, 23.95 tokens per second) 1.42.873.510 I slot print_timing: id 0 | task 130 | total time = 1559.38 ms / 164 tokens 1.42.873.511 I slot print_timing: id 0 | task 130 | graphs reused = 1 1.42.873.511 I slot print_timing: id 0 | task 130 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.873.540 I slot release: id 0 | task 130 | stop processing: n_tokens = 172, truncated = 0 1.42.875.643 I slot print_timing: id 1 | task 128 | prompt eval time = 1519.26 ms / 158 tokens ( 9.62 ms per token, 104.00 tokens per second) 1.42.875.646 I slot print_timing: id 1 | task 128 | eval time = 42.11 ms / 2 tokens ( 42.11 ms per token, 23.75 tokens per second) 1.42.875.647 I slot print_timing: id 1 | task 128 | total time = 1561.37 ms / 160 tokens 1.42.875.648 I slot print_timing: id 1 | task 128 | graphs reused = 1 1.42.875.648 I slot print_timing: id 1 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.875.672 I slot release: id 1 | task 128 | stop processing: n_tokens = 168, truncated = 0 1.42.877.724 I slot print_timing: id 2 | task 131 | prompt eval time = 1520.80 ms / 229 tokens ( 6.64 ms per token, 150.58 tokens per second) 1.42.877.727 I slot print_timing: id 2 | task 131 | eval time = 42.54 ms / 2 tokens ( 42.54 ms per token, 23.51 tokens per second) 1.42.877.728 I slot print_timing: id 2 | task 131 | total time = 1563.33 ms / 231 tokens 1.42.877.728 I slot print_timing: id 2 | task 131 | graphs reused = 1 1.42.877.728 I slot print_timing: id 2 | task 131 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.877.747 I slot release: id 2 | task 131 | stop processing: n_tokens = 239, truncated = 0 1.42.879.769 I slot print_timing: id 3 | task 129 | prompt eval time = 1522.36 ms / 145 tokens ( 10.50 ms per token, 95.25 tokens per second) 1.42.879.772 I slot print_timing: id 3 | task 129 | eval time = 42.89 ms / 2 tokens ( 42.89 ms per token, 23.32 tokens per second) 1.42.879.773 I slot print_timing: id 3 | task 129 | total time = 1565.25 ms / 147 tokens 1.42.879.773 I slot print_timing: id 3 | task 129 | graphs reused = 1 1.42.879.774 I slot print_timing: id 3 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.879.787 I slot release: id 3 | task 129 | stop processing: n_tokens = 155, truncated = 0 1.42.879.795 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.345 (> 0.100 thold), f_keep = 0.258 1.42.884.916 I slot launch_slot_: id 3 | task 136 | processing task, is_child = 0 1.42.901.341 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.185 (> 0.100 thold), f_keep = 0.215 1.42.902.143 I slot launch_slot_: id 0 | task 137 | processing task, is_child = 0 1.42.902.233 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.302 (> 0.100 thold), f_keep = 0.226 1.42.902.320 I slot launch_slot_: id 1 | task 138 | processing task, is_child = 0 1.42.902.366 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.155 1.42.902.453 I slot launch_slot_: id 2 | task 139 | processing task, is_child = 0 1.44.170.127 I slot print_timing: id 0 | task 137 | prompt eval time = 1221.78 ms / 191 tokens ( 6.40 ms per token, 156.33 tokens per second) 1.44.170.135 I slot print_timing: id 0 | task 137 | eval time = 45.88 ms / 2 tokens ( 45.88 ms per token, 21.80 tokens per second) 1.44.170.136 I slot print_timing: id 0 | task 137 | total time = 1267.66 ms / 193 tokens 1.44.170.136 I slot print_timing: id 0 | task 137 | graphs reused = 1 1.44.170.137 I slot print_timing: id 0 | task 137 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.170.181 I slot release: id 0 | task 137 | stop processing: n_tokens = 201, truncated = 0 1.44.172.247 I slot print_timing: id 1 | task 138 | prompt eval time = 1224.60 ms / 117 tokens ( 10.47 ms per token, 95.54 tokens per second) 1.44.172.254 I slot print_timing: id 1 | task 138 | eval time = 45.03 ms / 2 tokens ( 45.03 ms per token, 22.21 tokens per second) 1.44.172.255 I slot print_timing: id 1 | task 138 | total time = 1269.63 ms / 119 tokens 1.44.172.255 I slot print_timing: id 1 | task 138 | graphs reused = 1 1.44.172.256 I slot print_timing: id 1 | task 138 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.172.272 I slot release: id 1 | task 138 | stop processing: n_tokens = 127, truncated = 0 1.44.174.087 I slot print_timing: id 2 | task 139 | prompt eval time = 1227.00 ms / 143 tokens ( 8.58 ms per token, 116.54 tokens per second) 1.44.174.090 I slot print_timing: id 2 | task 139 | eval time = 44.32 ms / 2 tokens ( 44.32 ms per token, 22.56 tokens per second) 1.44.174.090 I slot print_timing: id 2 | task 139 | total time = 1271.32 ms / 145 tokens 1.44.174.091 I slot print_timing: id 2 | task 139 | graphs reused = 1 1.44.174.091 I slot print_timing: id 2 | task 139 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.174.105 I slot release: id 2 | task 139 | stop processing: n_tokens = 153, truncated = 0 1.44.175.878 I slot print_timing: id 3 | task 136 | prompt eval time = 1229.37 ms / 107 tokens ( 11.49 ms per token, 87.04 tokens per second) 1.44.175.883 I slot print_timing: id 3 | task 136 | eval time = 43.58 ms / 2 tokens ( 43.58 ms per token, 22.95 tokens per second) 1.44.175.884 I slot print_timing: id 3 | task 136 | total time = 1272.94 ms / 109 tokens 1.44.175.884 I slot print_timing: id 3 | task 136 | graphs reused = 1 1.44.175.885 I slot print_timing: id 3 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.175.896 I slot release: id 3 | task 136 | stop processing: n_tokens = 117, truncated = 0 1.44.175.902 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.184 1.44.180.158 I slot launch_slot_: id 0 | task 144 | processing task, is_child = 0 1.44.184.810 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.291 1.44.184.913 I slot launch_slot_: id 1 | task 145 | processing task, is_child = 0 1.44.184.985 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.325 1.44.185.067 I slot launch_slot_: id 3 | task 146 | processing task, is_child = 0 1.44.185.109 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.306 (> 0.100 thold), f_keep = 0.242 1.44.185.826 I slot launch_slot_: id 2 | task 147 | processing task, is_child = 0 1.45.476.545 I slot print_timing: id 0 | task 144 | prompt eval time = 1245.01 ms / 175 tokens ( 7.11 ms per token, 140.56 tokens per second) 1.45.476.551 I slot print_timing: id 0 | task 144 | eval time = 45.69 ms / 2 tokens ( 45.69 ms per token, 21.89 tokens per second) 1.45.476.551 I slot print_timing: id 0 | task 144 | total time = 1290.70 ms / 177 tokens 1.45.476.552 I slot print_timing: id 0 | task 144 | graphs reused = 1 1.45.476.553 I slot print_timing: id 0 | task 144 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.476.589 I slot release: id 0 | task 144 | stop processing: n_tokens = 185, truncated = 0 1.45.478.725 I slot print_timing: id 1 | task 145 | prompt eval time = 1247.49 ms / 140 tokens ( 8.91 ms per token, 112.22 tokens per second) 1.45.478.729 I slot print_timing: id 1 | task 145 | eval time = 45.22 ms / 2 tokens ( 45.22 ms per token, 22.11 tokens per second) 1.45.478.729 I slot print_timing: id 1 | task 145 | total time = 1292.72 ms / 142 tokens 1.45.478.730 I slot print_timing: id 1 | task 145 | graphs reused = 1 1.45.478.730 I slot print_timing: id 1 | task 145 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.478.761 I slot release: id 1 | task 145 | stop processing: n_tokens = 150, truncated = 0 1.45.480.655 I slot print_timing: id 2 | task 147 | prompt eval time = 1250.12 ms / 112 tokens ( 11.16 ms per token, 89.59 tokens per second) 1.45.480.659 I slot print_timing: id 2 | task 147 | eval time = 44.38 ms / 2 tokens ( 44.38 ms per token, 22.53 tokens per second) 1.45.480.660 I slot print_timing: id 2 | task 147 | total time = 1294.50 ms / 114 tokens 1.45.480.660 I slot print_timing: id 2 | task 147 | graphs reused = 1 1.45.480.661 I slot print_timing: id 2 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.480.680 I slot release: id 2 | task 147 | stop processing: n_tokens = 122, truncated = 0 1.45.482.519 I slot print_timing: id 3 | task 146 | prompt eval time = 1252.42 ms / 122 tokens ( 10.27 ms per token, 97.41 tokens per second) 1.45.482.526 I slot print_timing: id 3 | task 146 | eval time = 43.80 ms / 2 tokens ( 43.80 ms per token, 22.83 tokens per second) 1.45.482.526 I slot print_timing: id 3 | task 146 | total time = 1296.23 ms / 124 tokens 1.45.482.527 I slot print_timing: id 3 | task 146 | graphs reused = 1 1.45.482.527 I slot print_timing: id 3 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.482.539 I slot release: id 3 | task 146 | stop processing: n_tokens = 132, truncated = 0 1.45.483.169 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.253 (> 0.100 thold), f_keep = 0.200 1.45.487.029 I slot launch_slot_: id 0 | task 152 | processing task, is_child = 0 1.45.497.425 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.247 1.45.498.252 I slot launch_slot_: id 1 | task 153 | processing task, is_child = 0 1.45.498.321 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.303 1.45.498.401 I slot launch_slot_: id 2 | task 154 | processing task, is_child = 0 1.45.498.440 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.288 1.45.499.163 I slot launch_slot_: id 3 | task 155 | processing task, is_child = 0 1.46.758.732 I slot print_timing: id 0 | task 152 | prompt eval time = 1213.11 ms / 137 tokens ( 8.85 ms per token, 112.93 tokens per second) 1.46.758.737 I slot print_timing: id 0 | task 152 | eval time = 46.45 ms / 2 tokens ( 46.45 ms per token, 21.53 tokens per second) 1.46.758.738 I slot print_timing: id 0 | task 152 | total time = 1259.56 ms / 139 tokens 1.46.758.739 I slot print_timing: id 0 | task 152 | graphs reused = 1 1.46.758.739 I slot print_timing: id 0 | task 152 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.758.776 I slot release: id 0 | task 152 | stop processing: n_tokens = 147, truncated = 0 1.46.760.861 I slot print_timing: id 1 | task 153 | prompt eval time = 1215.85 ms / 162 tokens ( 7.51 ms per token, 133.24 tokens per second) 1.46.760.863 I slot print_timing: id 1 | task 153 | eval time = 45.68 ms / 2 tokens ( 45.68 ms per token, 21.89 tokens per second) 1.46.760.864 I slot print_timing: id 1 | task 153 | total time = 1261.53 ms / 164 tokens 1.46.760.865 I slot print_timing: id 1 | task 153 | graphs reused = 1 1.46.760.865 I slot print_timing: id 1 | task 153 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.760.885 I slot release: id 1 | task 153 | stop processing: n_tokens = 172, truncated = 0 1.46.762.984 I slot print_timing: id 2 | task 154 | prompt eval time = 1218.20 ms / 138 tokens ( 8.83 ms per token, 113.28 tokens per second) 1.46.762.991 I slot print_timing: id 2 | task 154 | eval time = 45.32 ms / 2 tokens ( 45.32 ms per token, 22.07 tokens per second) 1.46.762.993 I slot print_timing: id 2 | task 154 | total time = 1263.51 ms / 140 tokens 1.46.762.993 I slot print_timing: id 2 | task 154 | graphs reused = 1 1.46.762.994 I slot print_timing: id 2 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.763.007 I slot release: id 2 | task 154 | stop processing: n_tokens = 148, truncated = 0 1.46.765.048 I slot print_timing: id 3 | task 155 | prompt eval time = 1220.78 ms / 122 tokens ( 10.01 ms per token, 99.94 tokens per second) 1.46.765.057 I slot print_timing: id 3 | task 155 | eval time = 44.66 ms / 2 tokens ( 44.66 ms per token, 22.39 tokens per second) 1.46.765.057 I slot print_timing: id 3 | task 155 | total time = 1265.44 ms / 124 tokens 1.46.765.058 I slot print_timing: id 3 | task 155 | graphs reused = 1 1.46.765.058 I slot print_timing: id 3 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.765.078 I slot release: id 3 | task 155 | stop processing: n_tokens = 132, truncated = 0 1.46.765.305 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.252 1.46.768.464 I slot launch_slot_: id 0 | task 160 | processing task, is_child = 0 1.46.779.226 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.215 1.46.779.338 I slot launch_slot_: id 1 | task 161 | processing task, is_child = 0 1.46.779.411 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.250 1.46.779.494 I slot launch_slot_: id 2 | task 162 | processing task, is_child = 0 1.46.779.531 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.198 (> 0.100 thold), f_keep = 0.280 1.46.779.611 I slot launch_slot_: id 3 | task 163 | processing task, is_child = 0 1.48.190.988 I slot print_timing: id 0 | task 160 | prompt eval time = 1371.81 ms / 132 tokens ( 10.39 ms per token, 96.22 tokens per second) 1.48.190.991 I slot print_timing: id 0 | task 160 | eval time = 39.56 ms / 2 tokens ( 39.56 ms per token, 25.28 tokens per second) 1.48.190.992 I slot print_timing: id 0 | task 160 | total time = 1411.37 ms / 134 tokens 1.48.190.993 I slot print_timing: id 0 | task 160 | graphs reused = 1 1.48.190.993 I slot print_timing: id 0 | task 160 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.191.017 I slot release: id 0 | task 160 | stop processing: n_tokens = 142, truncated = 0 1.48.192.332 I slot print_timing: id 1 | task 161 | prompt eval time = 1372.82 ms / 183 tokens ( 7.50 ms per token, 133.30 tokens per second) 1.48.192.337 I slot print_timing: id 1 | task 161 | eval time = 39.73 ms / 2 tokens ( 39.73 ms per token, 25.17 tokens per second) 1.48.192.338 I slot print_timing: id 1 | task 161 | total time = 1412.54 ms / 185 tokens 1.48.192.338 I slot print_timing: id 1 | task 161 | graphs reused = 1 1.48.192.338 I slot print_timing: id 1 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.192.353 I slot release: id 1 | task 161 | stop processing: n_tokens = 193, truncated = 0 1.48.193.654 I slot print_timing: id 2 | task 162 | prompt eval time = 1373.96 ms / 183 tokens ( 7.51 ms per token, 133.19 tokens per second) 1.48.193.657 I slot print_timing: id 2 | task 162 | eval time = 39.75 ms / 2 tokens ( 39.75 ms per token, 25.16 tokens per second) 1.48.193.657 I slot print_timing: id 2 | task 162 | total time = 1413.71 ms / 185 tokens 1.48.193.657 I slot print_timing: id 2 | task 162 | graphs reused = 1 1.48.193.658 I slot print_timing: id 2 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.193.673 I slot release: id 2 | task 162 | stop processing: n_tokens = 193, truncated = 0 1.48.194.948 I slot print_timing: id 3 | task 163 | prompt eval time = 1375.03 ms / 178 tokens ( 7.72 ms per token, 129.45 tokens per second) 1.48.194.951 I slot print_timing: id 3 | task 163 | eval time = 39.84 ms / 2 tokens ( 39.84 ms per token, 25.10 tokens per second) 1.48.194.952 I slot print_timing: id 3 | task 163 | total time = 1414.87 ms / 180 tokens 1.48.194.952 I slot print_timing: id 3 | task 163 | graphs reused = 1 1.48.194.952 I slot print_timing: id 3 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.194.963 I slot release: id 3 | task 163 | stop processing: n_tokens = 188, truncated = 0 1.48.195.661 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.261 1.48.198.028 I slot launch_slot_: id 0 | task 168 | processing task, is_child = 0 1.48.210.199 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.192 1.48.210.798 I slot launch_slot_: id 1 | task 169 | processing task, is_child = 0 1.48.210.865 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.192 1.48.210.930 I slot launch_slot_: id 2 | task 170 | processing task, is_child = 0 1.48.210.962 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.197 1.48.211.452 I slot launch_slot_: id 3 | task 171 | processing task, is_child = 0 1.49.221.170 I slot print_timing: id 0 | task 168 | prompt eval time = 970.74 ms / 117 tokens ( 8.30 ms per token, 120.53 tokens per second) 1.49.221.173 I slot print_timing: id 0 | task 168 | eval time = 38.97 ms / 2 tokens ( 38.97 ms per token, 25.66 tokens per second) 1.49.221.174 I slot print_timing: id 0 | task 168 | total time = 1009.70 ms / 119 tokens 1.49.221.175 I slot print_timing: id 0 | task 168 | graphs reused = 1 1.49.221.175 I slot print_timing: id 0 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.221.198 I slot release: id 0 | task 168 | stop processing: n_tokens = 127, truncated = 0 1.49.222.522 I slot print_timing: id 1 | task 169 | prompt eval time = 971.64 ms / 125 tokens ( 7.77 ms per token, 128.65 tokens per second) 1.49.222.525 I slot print_timing: id 1 | task 169 | eval time = 39.22 ms / 2 tokens ( 39.22 ms per token, 25.50 tokens per second) 1.49.222.526 I slot print_timing: id 1 | task 169 | total time = 1010.86 ms / 127 tokens 1.49.222.526 I slot print_timing: id 1 | task 169 | graphs reused = 1 1.49.222.526 I slot print_timing: id 1 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.222.542 I slot release: id 1 | task 169 | stop processing: n_tokens = 135, truncated = 0 1.49.223.874 I slot print_timing: id 2 | task 170 | prompt eval time = 972.58 ms / 125 tokens ( 7.78 ms per token, 128.52 tokens per second) 1.49.223.879 I slot print_timing: id 2 | task 170 | eval time = 39.47 ms / 2 tokens ( 39.47 ms per token, 25.34 tokens per second) 1.49.223.881 I slot print_timing: id 2 | task 170 | total time = 1012.05 ms / 127 tokens 1.49.223.881 I slot print_timing: id 2 | task 170 | graphs reused = 1 1.49.223.881 I slot print_timing: id 2 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.223.892 I slot release: id 2 | task 170 | stop processing: n_tokens = 135, truncated = 0 1.49.225.194 I slot print_timing: id 3 | task 171 | prompt eval time = 973.60 ms / 117 tokens ( 8.32 ms per token, 120.17 tokens per second) 1.49.225.196 I slot print_timing: id 3 | task 171 | eval time = 39.58 ms / 2 tokens ( 39.58 ms per token, 25.27 tokens per second) 1.49.225.197 I slot print_timing: id 3 | task 171 | total time = 1013.18 ms / 119 tokens 1.49.225.197 I slot print_timing: id 3 | task 171 | graphs reused = 1 1.49.225.197 I slot print_timing: id 3 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.225.207 I slot release: id 3 | task 171 | stop processing: n_tokens = 127, truncated = 0 1.49.225.816 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.293 (> 0.100 thold), f_keep = 0.323 1.49.226.948 I slot launch_slot_: id 3 | task 176 | processing task, is_child = 0 1.49.232.049 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.291 1.49.232.132 I slot launch_slot_: id 0 | task 177 | processing task, is_child = 0 1.49.232.190 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.274 1.49.232.738 I slot launch_slot_: id 1 | task 178 | processing task, is_child = 0 1.49.232.775 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.274 1.49.233.334 I slot launch_slot_: id 2 | task 179 | processing task, is_child = 0 1.50.402.061 I slot print_timing: id 0 | task 177 | prompt eval time = 1124.38 ms / 143 tokens ( 7.86 ms per token, 127.18 tokens per second) 1.50.402.065 I slot print_timing: id 0 | task 177 | eval time = 44.33 ms / 2 tokens ( 44.33 ms per token, 22.56 tokens per second) 1.50.402.066 I slot print_timing: id 0 | task 177 | total time = 1168.71 ms / 145 tokens 1.50.402.067 I slot print_timing: id 0 | task 177 | graphs reused = 1 1.50.402.068 I slot print_timing: id 0 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.402.100 I slot release: id 0 | task 177 | stop processing: n_tokens = 153, truncated = 0 1.50.404.152 I slot print_timing: id 1 | task 178 | prompt eval time = 1126.73 ms / 130 tokens ( 8.67 ms per token, 115.38 tokens per second) 1.50.404.156 I slot print_timing: id 1 | task 178 | eval time = 43.94 ms / 2 tokens ( 43.94 ms per token, 22.76 tokens per second) 1.50.404.156 I slot print_timing: id 1 | task 178 | total time = 1170.68 ms / 132 tokens 1.50.404.157 I slot print_timing: id 1 | task 178 | graphs reused = 1 1.50.404.158 I slot print_timing: id 1 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.404.177 I slot release: id 1 | task 178 | stop processing: n_tokens = 140, truncated = 0 1.50.405.989 I slot print_timing: id 2 | task 179 | prompt eval time = 1129.07 ms / 132 tokens ( 8.55 ms per token, 116.91 tokens per second) 1.50.405.992 I slot print_timing: id 2 | task 179 | eval time = 43.33 ms / 2 tokens ( 43.33 ms per token, 23.08 tokens per second) 1.50.405.997 I slot print_timing: id 2 | task 179 | total time = 1172.39 ms / 134 tokens 1.50.405.998 I slot print_timing: id 2 | task 179 | graphs reused = 1 1.50.405.998 I slot print_timing: id 2 | task 179 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.406.014 I slot release: id 2 | task 179 | stop processing: n_tokens = 142, truncated = 0 1.50.407.780 I slot print_timing: id 3 | task 176 | prompt eval time = 1131.05 ms / 131 tokens ( 8.63 ms per token, 115.82 tokens per second) 1.50.407.783 I slot print_timing: id 3 | task 176 | eval time = 43.02 ms / 2 tokens ( 43.02 ms per token, 23.24 tokens per second) 1.50.407.783 I slot print_timing: id 3 | task 176 | total time = 1174.07 ms / 133 tokens 1.50.407.784 I slot print_timing: id 3 | task 176 | graphs reused = 1 1.50.407.784 I slot print_timing: id 3 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.407.796 I slot release: id 3 | task 176 | stop processing: n_tokens = 141, truncated = 0 1.50.408.078 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.242 1.50.412.336 I slot launch_slot_: id 0 | task 184 | processing task, is_child = 0 1.50.422.942 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.264 1.50.423.031 I slot launch_slot_: id 1 | task 185 | processing task, is_child = 0 1.50.423.104 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.333 (> 0.100 thold), f_keep = 0.270 1.50.423.186 I slot launch_slot_: id 3 | task 186 | processing task, is_child = 0 1.50.423.225 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.261 1.50.423.304 I slot launch_slot_: id 2 | task 187 | processing task, is_child = 0 1.51.622.427 I slot print_timing: id 0 | task 184 | prompt eval time = 1153.42 ms / 124 tokens ( 9.30 ms per token, 107.51 tokens per second) 1.51.622.431 I slot print_timing: id 0 | task 184 | eval time = 45.69 ms / 2 tokens ( 45.69 ms per token, 21.88 tokens per second) 1.51.622.432 I slot print_timing: id 0 | task 184 | total time = 1199.11 ms / 126 tokens 1.51.622.433 I slot print_timing: id 0 | task 184 | graphs reused = 1 1.51.622.433 I slot print_timing: id 0 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.622.463 I slot release: id 0 | task 184 | stop processing: n_tokens = 134, truncated = 0 1.51.624.530 I slot print_timing: id 1 | task 185 | prompt eval time = 1156.22 ms / 131 tokens ( 8.83 ms per token, 113.30 tokens per second) 1.51.624.536 I slot print_timing: id 1 | task 185 | eval time = 44.83 ms / 2 tokens ( 44.83 ms per token, 22.31 tokens per second) 1.51.624.536 I slot print_timing: id 1 | task 185 | total time = 1201.05 ms / 133 tokens 1.51.624.537 I slot print_timing: id 1 | task 185 | graphs reused = 1 1.51.624.538 I slot print_timing: id 1 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.624.556 I slot release: id 1 | task 185 | stop processing: n_tokens = 141, truncated = 0 1.51.626.454 I slot print_timing: id 2 | task 187 | prompt eval time = 1158.55 ms / 160 tokens ( 7.24 ms per token, 138.10 tokens per second) 1.51.626.457 I slot print_timing: id 2 | task 187 | eval time = 44.29 ms / 2 tokens ( 44.29 ms per token, 22.58 tokens per second) 1.51.626.457 I slot print_timing: id 2 | task 187 | total time = 1202.83 ms / 162 tokens 1.51.626.458 I slot print_timing: id 2 | task 187 | graphs reused = 1 1.51.626.458 I slot print_timing: id 2 | task 187 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.626.481 I slot release: id 2 | task 187 | stop processing: n_tokens = 170, truncated = 0 1.51.628.244 I slot print_timing: id 3 | task 186 | prompt eval time = 1161.14 ms / 105 tokens ( 11.06 ms per token, 90.43 tokens per second) 1.51.628.247 I slot print_timing: id 3 | task 186 | eval time = 43.34 ms / 2 tokens ( 43.34 ms per token, 23.07 tokens per second) 1.51.628.248 I slot print_timing: id 3 | task 186 | total time = 1204.48 ms / 107 tokens 1.51.628.248 I slot print_timing: id 3 | task 186 | graphs reused = 1 1.51.628.249 I slot print_timing: id 3 | task 186 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.628.260 I slot release: id 3 | task 186 | stop processing: n_tokens = 115, truncated = 0 1.51.628.555 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.276 1.51.632.172 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 1.51.639.208 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.262 1.51.639.306 I slot launch_slot_: id 1 | task 193 | processing task, is_child = 0 1.51.639.381 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.218 1.51.639.468 I slot launch_slot_: id 2 | task 194 | processing task, is_child = 0 1.51.639.505 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.311 (> 0.100 thold), f_keep = 0.330 1.51.639.583 I slot launch_slot_: id 3 | task 195 | processing task, is_child = 0 1.52.999.653 I slot print_timing: id 0 | task 192 | prompt eval time = 1314.63 ms / 143 tokens ( 9.19 ms per token, 108.78 tokens per second) 1.52.999.660 I slot print_timing: id 0 | task 192 | eval time = 45.43 ms / 2 tokens ( 45.43 ms per token, 22.01 tokens per second) 1.52.999.661 I slot print_timing: id 0 | task 192 | total time = 1360.06 ms / 145 tokens 1.52.999.662 I slot print_timing: id 0 | task 192 | graphs reused = 1 1.52.999.663 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.999.690 I slot release: id 0 | task 192 | stop processing: n_tokens = 153, truncated = 0 1.53.001.744 I slot print_timing: id 1 | task 193 | prompt eval time = 1316.96 ms / 173 tokens ( 7.61 ms per token, 131.36 tokens per second) 1.53.001.747 I slot print_timing: id 1 | task 193 | eval time = 45.04 ms / 2 tokens ( 45.04 ms per token, 22.20 tokens per second) 1.53.001.749 I slot print_timing: id 1 | task 193 | total time = 1362.00 ms / 175 tokens 1.53.001.750 I slot print_timing: id 1 | task 193 | graphs reused = 1 1.53.001.750 I slot print_timing: id 1 | task 193 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.001.770 I slot release: id 1 | task 193 | stop processing: n_tokens = 183, truncated = 0 1.53.003.598 I slot print_timing: id 2 | task 194 | prompt eval time = 1319.47 ms / 161 tokens ( 8.20 ms per token, 122.02 tokens per second) 1.53.003.604 I slot print_timing: id 2 | task 194 | eval time = 44.24 ms / 2 tokens ( 44.24 ms per token, 22.60 tokens per second) 1.53.003.604 I slot print_timing: id 2 | task 194 | total time = 1363.71 ms / 163 tokens 1.53.003.604 I slot print_timing: id 2 | task 194 | graphs reused = 1 1.53.003.605 I slot print_timing: id 2 | task 194 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.003.633 I slot release: id 2 | task 194 | stop processing: n_tokens = 171, truncated = 0 1.53.005.409 I slot print_timing: id 3 | task 195 | prompt eval time = 1322.02 ms / 113 tokens ( 11.70 ms per token, 85.48 tokens per second) 1.53.005.413 I slot print_timing: id 3 | task 195 | eval time = 43.36 ms / 2 tokens ( 43.36 ms per token, 23.06 tokens per second) 1.53.005.413 I slot print_timing: id 3 | task 195 | total time = 1365.38 ms / 115 tokens 1.53.005.414 I slot print_timing: id 3 | task 195 | graphs reused = 1 1.53.005.414 I slot print_timing: id 3 | task 195 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.005.425 I slot release: id 3 | task 195 | stop processing: n_tokens = 123, truncated = 0 1.53.005.770 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.306 (> 0.100 thold), f_keep = 0.242 1.53.009.096 I slot launch_slot_: id 0 | task 200 | processing task, is_child = 0 1.53.020.448 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.202 1.53.021.207 I slot launch_slot_: id 1 | task 201 | processing task, is_child = 0 1.53.021.279 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.216 1.53.021.974 I slot launch_slot_: id 2 | task 202 | processing task, is_child = 0 1.53.022.015 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.314 (> 0.100 thold), f_keep = 0.309 1.53.022.092 I slot launch_slot_: id 3 | task 203 | processing task, is_child = 0 1.54.161.567 I slot print_timing: id 0 | task 200 | prompt eval time = 1100.70 ms / 112 tokens ( 9.83 ms per token, 101.75 tokens per second) 1.54.161.570 I slot print_timing: id 0 | task 200 | eval time = 38.76 ms / 2 tokens ( 38.76 ms per token, 25.80 tokens per second) 1.54.161.571 I slot print_timing: id 0 | task 200 | total time = 1139.46 ms / 114 tokens 1.54.161.571 I slot print_timing: id 0 | task 200 | graphs reused = 1 1.54.161.572 I slot print_timing: id 0 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.161.592 I slot release: id 0 | task 200 | stop processing: n_tokens = 122, truncated = 0 1.54.162.698 I slot print_timing: id 1 | task 201 | prompt eval time = 1101.77 ms / 152 tokens ( 7.25 ms per token, 137.96 tokens per second) 1.54.162.700 I slot print_timing: id 1 | task 201 | eval time = 38.68 ms / 2 tokens ( 38.68 ms per token, 25.85 tokens per second) 1.54.162.700 I slot print_timing: id 1 | task 201 | total time = 1140.45 ms / 154 tokens 1.54.162.701 I slot print_timing: id 1 | task 201 | graphs reused = 1 1.54.162.701 I slot print_timing: id 1 | task 201 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.162.713 I slot release: id 1 | task 201 | stop processing: n_tokens = 162, truncated = 0 1.54.163.828 I slot print_timing: id 2 | task 202 | prompt eval time = 1102.72 ms / 140 tokens ( 7.88 ms per token, 126.96 tokens per second) 1.54.163.830 I slot print_timing: id 2 | task 202 | eval time = 38.72 ms / 2 tokens ( 38.72 ms per token, 25.83 tokens per second) 1.54.163.830 I slot print_timing: id 2 | task 202 | total time = 1141.44 ms / 142 tokens 1.54.163.830 I slot print_timing: id 2 | task 202 | graphs reused = 1 1.54.163.830 I slot print_timing: id 2 | task 202 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.163.839 I slot release: id 2 | task 202 | stop processing: n_tokens = 150, truncated = 0 1.54.164.946 I slot print_timing: id 3 | task 203 | prompt eval time = 1103.70 ms / 112 tokens ( 9.85 ms per token, 101.48 tokens per second) 1.54.164.947 I slot print_timing: id 3 | task 203 | eval time = 38.72 ms / 2 tokens ( 38.72 ms per token, 25.82 tokens per second) 1.54.164.948 I slot print_timing: id 3 | task 203 | total time = 1142.42 ms / 114 tokens 1.54.164.948 I slot print_timing: id 3 | task 203 | graphs reused = 1 1.54.164.948 I slot print_timing: id 3 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.164.955 I slot release: id 3 | task 203 | stop processing: n_tokens = 122, truncated = 0 1.54.166.017 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.311 1.54.166.986 I slot launch_slot_: id 3 | task 208 | processing task, is_child = 0 1.54.173.268 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.303 1.54.173.334 I slot launch_slot_: id 0 | task 209 | processing task, is_child = 0 1.54.173.387 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.228 1.54.173.923 I slot launch_slot_: id 1 | task 210 | processing task, is_child = 0 1.54.173.954 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.247 1.54.174.009 I slot launch_slot_: id 2 | task 211 | processing task, is_child = 0 1.55.426.807 I slot print_timing: id 0 | task 209 | prompt eval time = 1214.24 ms / 155 tokens ( 7.83 ms per token, 127.65 tokens per second) 1.55.426.813 I slot print_timing: id 0 | task 209 | eval time = 38.55 ms / 2 tokens ( 38.55 ms per token, 25.94 tokens per second) 1.55.426.813 I slot print_timing: id 0 | task 209 | total time = 1252.79 ms / 157 tokens 1.55.426.814 I slot print_timing: id 0 | task 209 | graphs reused = 1 1.55.426.814 I slot print_timing: id 0 | task 209 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.426.837 I slot release: id 0 | task 209 | stop processing: n_tokens = 165, truncated = 0 1.55.427.947 I slot print_timing: id 1 | task 210 | prompt eval time = 1215.17 ms / 134 tokens ( 9.07 ms per token, 110.27 tokens per second) 1.55.427.952 I slot print_timing: id 1 | task 210 | eval time = 38.59 ms / 2 tokens ( 38.59 ms per token, 25.91 tokens per second) 1.55.427.953 I slot print_timing: id 1 | task 210 | total time = 1253.76 ms / 136 tokens 1.55.427.953 I slot print_timing: id 1 | task 210 | graphs reused = 1 1.55.427.953 I slot print_timing: id 1 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.427.967 I slot release: id 1 | task 210 | stop processing: n_tokens = 144, truncated = 0 1.55.429.105 I slot print_timing: id 2 | task 211 | prompt eval time = 1216.10 ms / 125 tokens ( 9.73 ms per token, 102.79 tokens per second) 1.55.429.107 I slot print_timing: id 2 | task 211 | eval time = 38.66 ms / 2 tokens ( 38.66 ms per token, 25.87 tokens per second) 1.55.429.108 I slot print_timing: id 2 | task 211 | total time = 1254.76 ms / 127 tokens 1.55.429.108 I slot print_timing: id 2 | task 211 | graphs reused = 1 1.55.429.108 I slot print_timing: id 2 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.429.120 I slot release: id 2 | task 211 | stop processing: n_tokens = 135, truncated = 0 1.55.430.204 I slot print_timing: id 3 | task 208 | prompt eval time = 1217.03 ms / 114 tokens ( 10.68 ms per token, 93.67 tokens per second) 1.55.430.206 I slot print_timing: id 3 | task 208 | eval time = 38.67 ms / 2 tokens ( 38.67 ms per token, 25.86 tokens per second) 1.55.430.206 I slot print_timing: id 3 | task 208 | total time = 1255.70 ms / 116 tokens 1.55.430.207 I slot print_timing: id 3 | task 208 | graphs reused = 1 1.55.430.207 I slot print_timing: id 3 | task 208 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.430.215 I slot release: id 3 | task 208 | stop processing: n_tokens = 124, truncated = 0 1.55.430.671 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.292 (> 0.100 thold), f_keep = 0.306 1.55.431.774 I slot launch_slot_: id 3 | task 216 | processing task, is_child = 0 1.55.440.466 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.224 1.55.440.541 I slot launch_slot_: id 0 | task 217 | processing task, is_child = 0 1.55.440.594 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.257 1.55.440.651 I slot launch_slot_: id 1 | task 218 | processing task, is_child = 0 1.55.440.680 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.274 1.55.440.744 I slot launch_slot_: id 2 | task 219 | processing task, is_child = 0 1.56.716.780 I slot print_timing: id 0 | task 217 | prompt eval time = 1237.02 ms / 170 tokens ( 7.28 ms per token, 137.43 tokens per second) 1.56.716.786 I slot print_timing: id 0 | task 217 | eval time = 39.00 ms / 2 tokens ( 39.00 ms per token, 25.64 tokens per second) 1.56.716.787 I slot print_timing: id 0 | task 217 | total time = 1276.02 ms / 172 tokens 1.56.716.787 I slot print_timing: id 0 | task 217 | graphs reused = 1 1.56.716.788 I slot print_timing: id 0 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.716.812 I slot release: id 0 | task 217 | stop processing: n_tokens = 180, truncated = 0 1.56.718.118 I slot print_timing: id 1 | task 218 | prompt eval time = 1237.94 ms / 159 tokens ( 7.79 ms per token, 128.44 tokens per second) 1.56.718.122 I slot print_timing: id 1 | task 218 | eval time = 39.30 ms / 2 tokens ( 39.30 ms per token, 25.44 tokens per second) 1.56.718.123 I slot print_timing: id 1 | task 218 | total time = 1277.25 ms / 161 tokens 1.56.718.123 I slot print_timing: id 1 | task 218 | graphs reused = 1 1.56.718.123 I slot print_timing: id 1 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.718.139 I slot release: id 1 | task 218 | stop processing: n_tokens = 169, truncated = 0 1.56.719.433 I slot print_timing: id 2 | task 219 | prompt eval time = 1238.90 ms / 131 tokens ( 9.46 ms per token, 105.74 tokens per second) 1.56.719.437 I slot print_timing: id 2 | task 219 | eval time = 39.55 ms / 2 tokens ( 39.55 ms per token, 25.29 tokens per second) 1.56.719.437 I slot print_timing: id 2 | task 219 | total time = 1278.45 ms / 133 tokens 1.56.719.437 I slot print_timing: id 2 | task 219 | graphs reused = 1 1.56.719.438 I slot print_timing: id 2 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.719.448 I slot release: id 2 | task 219 | stop processing: n_tokens = 141, truncated = 0 1.56.720.738 I slot print_timing: id 3 | task 216 | prompt eval time = 1239.88 ms / 121 tokens ( 10.25 ms per token, 97.59 tokens per second) 1.56.720.740 I slot print_timing: id 3 | task 216 | eval time = 39.77 ms / 2 tokens ( 39.77 ms per token, 25.14 tokens per second) 1.56.720.741 I slot print_timing: id 3 | task 216 | total time = 1279.65 ms / 123 tokens 1.56.720.741 I slot print_timing: id 3 | task 216 | graphs reused = 1 1.56.720.741 I slot print_timing: id 3 | task 216 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.720.750 I slot release: id 3 | task 216 | stop processing: n_tokens = 131, truncated = 0 1.56.721.265 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.311 (> 0.100 thold), f_keep = 0.206 1.56.725.418 I slot launch_slot_: id 0 | task 224 | processing task, is_child = 0 1.56.731.600 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.219 1.56.731.668 I slot launch_slot_: id 1 | task 225 | processing task, is_child = 0 1.56.731.723 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.262 1.56.731.783 I slot launch_slot_: id 2 | task 226 | processing task, is_child = 0 1.56.731.812 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.282 1.56.732.321 I slot launch_slot_: id 3 | task 227 | processing task, is_child = 0 1.58.118.762 I slot print_timing: id 0 | task 224 | prompt eval time = 1347.69 ms / 110 tokens ( 12.25 ms per token, 81.62 tokens per second) 1.58.118.764 I slot print_timing: id 0 | task 224 | eval time = 38.74 ms / 2 tokens ( 38.74 ms per token, 25.81 tokens per second) 1.58.118.765 I slot print_timing: id 0 | task 224 | total time = 1386.43 ms / 112 tokens 1.58.118.765 I slot print_timing: id 0 | task 224 | graphs reused = 1 1.58.118.765 I slot print_timing: id 0 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.118.785 I slot release: id 0 | task 224 | stop processing: n_tokens = 120, truncated = 0 1.58.119.882 I slot print_timing: id 1 | task 225 | prompt eval time = 1348.72 ms / 188 tokens ( 7.17 ms per token, 139.39 tokens per second) 1.58.119.884 I slot print_timing: id 1 | task 225 | eval time = 38.72 ms / 2 tokens ( 38.72 ms per token, 25.83 tokens per second) 1.58.119.885 I slot print_timing: id 1 | task 225 | total time = 1387.44 ms / 190 tokens 1.58.119.885 I slot print_timing: id 1 | task 225 | graphs reused = 1 1.58.119.885 I slot print_timing: id 1 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.119.900 I slot release: id 1 | task 225 | stop processing: n_tokens = 198, truncated = 0 1.58.120.983 I slot print_timing: id 2 | task 226 | prompt eval time = 1349.72 ms / 155 tokens ( 8.71 ms per token, 114.84 tokens per second) 1.58.120.986 I slot print_timing: id 2 | task 226 | eval time = 38.70 ms / 2 tokens ( 38.70 ms per token, 25.84 tokens per second) 1.58.120.987 I slot print_timing: id 2 | task 226 | total time = 1388.42 ms / 157 tokens 1.58.120.987 I slot print_timing: id 2 | task 226 | graphs reused = 1 1.58.120.987 I slot print_timing: id 2 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.121.000 I slot release: id 2 | task 226 | stop processing: n_tokens = 165, truncated = 0 1.58.122.095 I slot print_timing: id 3 | task 227 | prompt eval time = 1350.76 ms / 148 tokens ( 9.13 ms per token, 109.57 tokens per second) 1.58.122.096 I slot print_timing: id 3 | task 227 | eval time = 38.67 ms / 2 tokens ( 38.67 ms per token, 25.86 tokens per second) 1.58.122.096 I slot print_timing: id 3 | task 227 | total time = 1389.43 ms / 150 tokens 1.58.122.097 I slot print_timing: id 3 | task 227 | graphs reused = 1 1.58.122.097 I slot print_timing: id 3 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.122.103 I slot release: id 3 | task 227 | stop processing: n_tokens = 158, truncated = 0 1.58.123.710 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.308 1.58.125.109 I slot launch_slot_: id 0 | task 232 | processing task, is_child = 0 1.58.134.394 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.253 (> 0.100 thold), f_keep = 0.187 1.58.134.471 I slot launch_slot_: id 1 | task 233 | processing task, is_child = 0 1.58.134.529 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.224 1.58.134.589 I slot launch_slot_: id 2 | task 234 | processing task, is_child = 0 1.58.134.619 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.234 1.58.135.189 I slot launch_slot_: id 3 | task 235 | processing task, is_child = 0 1.59.328.473 I slot print_timing: id 0 | task 232 | prompt eval time = 1154.20 ms / 117 tokens ( 9.86 ms per token, 101.37 tokens per second) 1.59.328.476 I slot print_timing: id 0 | task 232 | eval time = 39.07 ms / 2 tokens ( 39.07 ms per token, 25.59 tokens per second) 1.59.328.477 I slot print_timing: id 0 | task 232 | total time = 1193.28 ms / 119 tokens 1.59.328.478 I slot print_timing: id 0 | task 232 | graphs reused = 1 1.59.328.478 I slot print_timing: id 0 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.328.498 I slot release: id 0 | task 232 | stop processing: n_tokens = 127, truncated = 0 1.59.329.787 I slot print_timing: id 1 | task 233 | prompt eval time = 1155.20 ms / 137 tokens ( 8.43 ms per token, 118.59 tokens per second) 1.59.329.789 I slot print_timing: id 1 | task 233 | eval time = 39.27 ms / 2 tokens ( 39.27 ms per token, 25.46 tokens per second) 1.59.329.789 I slot print_timing: id 1 | task 233 | total time = 1194.47 ms / 139 tokens 1.59.329.790 I slot print_timing: id 1 | task 233 | graphs reused = 1 1.59.329.790 I slot print_timing: id 1 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.329.803 I slot release: id 1 | task 233 | stop processing: n_tokens = 147, truncated = 0 1.59.331.086 I slot print_timing: id 2 | task 234 | prompt eval time = 1156.15 ms / 136 tokens ( 8.50 ms per token, 117.63 tokens per second) 1.59.331.089 I slot print_timing: id 2 | task 234 | eval time = 39.50 ms / 2 tokens ( 39.50 ms per token, 25.32 tokens per second) 1.59.331.089 I slot print_timing: id 2 | task 234 | total time = 1195.64 ms / 138 tokens 1.59.331.090 I slot print_timing: id 2 | task 234 | graphs reused = 1 1.59.331.090 I slot print_timing: id 2 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.331.102 I slot release: id 2 | task 234 | stop processing: n_tokens = 146, truncated = 0 1.59.332.402 I slot print_timing: id 3 | task 235 | prompt eval time = 1157.24 ms / 159 tokens ( 7.28 ms per token, 137.40 tokens per second) 1.59.332.404 I slot print_timing: id 3 | task 235 | eval time = 39.59 ms / 2 tokens ( 39.59 ms per token, 25.26 tokens per second) 1.59.332.404 I slot print_timing: id 3 | task 235 | total time = 1196.83 ms / 161 tokens 1.59.332.405 I slot print_timing: id 3 | task 235 | graphs reused = 1 1.59.332.405 I slot print_timing: id 3 | task 235 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.332.421 I slot release: id 3 | task 235 | stop processing: n_tokens = 169, truncated = 0 1.59.332.935 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.291 1.59.334.062 I slot launch_slot_: id 0 | task 240 | processing task, is_child = 0 1.59.342.481 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.252 1.59.343.206 I slot launch_slot_: id 1 | task 241 | processing task, is_child = 0 1.59.343.261 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.291 (> 0.100 thold), f_keep = 0.253 1.59.343.821 I slot launch_slot_: id 2 | task 242 | processing task, is_child = 0 1.59.343.854 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.219 1.59.343.920 I slot launch_slot_: id 3 | task 243 | processing task, is_child = 0 2.00.613.523 I slot print_timing: id 0 | task 240 | prompt eval time = 1230.84 ms / 152 tokens ( 8.10 ms per token, 123.49 tokens per second) 2.00.613.526 I slot print_timing: id 0 | task 240 | eval time = 38.76 ms / 2 tokens ( 38.76 ms per token, 25.80 tokens per second) 2.00.613.526 I slot print_timing: id 0 | task 240 | total time = 1269.59 ms / 154 tokens 2.00.613.527 I slot print_timing: id 0 | task 240 | graphs reused = 1 2.00.613.527 I slot print_timing: id 0 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.613.551 I slot release: id 0 | task 240 | stop processing: n_tokens = 162, truncated = 0 2.00.614.682 I slot print_timing: id 1 | task 241 | prompt eval time = 1231.82 ms / 124 tokens ( 9.93 ms per token, 100.66 tokens per second) 2.00.614.684 I slot print_timing: id 1 | task 241 | eval time = 38.82 ms / 2 tokens ( 38.82 ms per token, 25.76 tokens per second) 2.00.614.685 I slot print_timing: id 1 | task 241 | total time = 1270.64 ms / 126 tokens 2.00.614.685 I slot print_timing: id 1 | task 241 | graphs reused = 1 2.00.614.685 I slot print_timing: id 1 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.614.696 I slot release: id 1 | task 241 | stop processing: n_tokens = 134, truncated = 0 2.00.615.781 I slot print_timing: id 2 | task 242 | prompt eval time = 1232.79 ms / 118 tokens ( 10.45 ms per token, 95.72 tokens per second) 2.00.615.783 I slot print_timing: id 2 | task 242 | eval time = 38.83 ms / 2 tokens ( 38.83 ms per token, 25.76 tokens per second) 2.00.615.783 I slot print_timing: id 2 | task 242 | total time = 1271.62 ms / 120 tokens 2.00.615.784 I slot print_timing: id 2 | task 242 | graphs reused = 1 2.00.615.784 I slot print_timing: id 2 | task 242 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.615.796 I slot release: id 2 | task 242 | stop processing: n_tokens = 128, truncated = 0 2.00.616.903 I slot print_timing: id 3 | task 243 | prompt eval time = 1233.77 ms / 159 tokens ( 7.76 ms per token, 128.87 tokens per second) 2.00.616.905 I slot print_timing: id 3 | task 243 | eval time = 38.86 ms / 2 tokens ( 38.86 ms per token, 25.73 tokens per second) 2.00.616.906 I slot print_timing: id 3 | task 243 | total time = 1272.63 ms / 161 tokens 2.00.616.906 I slot print_timing: id 3 | task 243 | graphs reused = 1 2.00.616.906 I slot print_timing: id 3 | task 243 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.616.916 I slot release: id 3 | task 243 | stop processing: n_tokens = 169, truncated = 0 2.00.617.437 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.228 2.00.619.180 I slot launch_slot_: id 0 | task 248 | processing task, is_child = 0 2.00.624.581 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.276 2.00.624.646 I slot launch_slot_: id 1 | task 249 | processing task, is_child = 0 2.00.624.696 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.289 2.00.624.750 I slot launch_slot_: id 2 | task 250 | processing task, is_child = 0 2.00.624.778 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.219 2.00.624.833 I slot launch_slot_: id 3 | task 251 | processing task, is_child = 0 2.02.013.022 I slot print_timing: id 0 | task 248 | prompt eval time = 1343.41 ms / 152 tokens ( 8.84 ms per token, 113.14 tokens per second) 2.02.013.026 I slot print_timing: id 0 | task 248 | eval time = 44.76 ms / 2 tokens ( 44.76 ms per token, 22.34 tokens per second) 2.02.013.028 I slot print_timing: id 0 | task 248 | total time = 1388.17 ms / 154 tokens 2.02.013.031 I slot print_timing: id 0 | task 248 | graphs reused = 1 2.02.013.032 I slot print_timing: id 0 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.013.061 I slot release: id 0 | task 248 | stop processing: n_tokens = 162, truncated = 0 2.02.015.150 I slot print_timing: id 1 | task 249 | prompt eval time = 1345.47 ms / 164 tokens ( 8.20 ms per token, 121.89 tokens per second) 2.02.015.153 I slot print_timing: id 1 | task 249 | eval time = 44.72 ms / 2 tokens ( 44.72 ms per token, 22.36 tokens per second) 2.02.015.153 I slot print_timing: id 1 | task 249 | total time = 1390.19 ms / 166 tokens 2.02.015.154 I slot print_timing: id 1 | task 249 | graphs reused = 1 2.02.015.155 I slot print_timing: id 1 | task 249 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.015.176 I slot release: id 1 | task 249 | stop processing: n_tokens = 174, truncated = 0 2.02.017.258 I slot print_timing: id 2 | task 250 | prompt eval time = 1347.23 ms / 154 tokens ( 8.75 ms per token, 114.31 tokens per second) 2.02.017.262 I slot print_timing: id 2 | task 250 | eval time = 44.96 ms / 2 tokens ( 44.96 ms per token, 22.24 tokens per second) 2.02.017.263 I slot print_timing: id 2 | task 250 | total time = 1392.19 ms / 156 tokens 2.02.017.263 I slot print_timing: id 2 | task 250 | graphs reused = 1 2.02.017.264 I slot print_timing: id 2 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.017.283 I slot release: id 2 | task 250 | stop processing: n_tokens = 164, truncated = 0 2.02.019.343 I slot print_timing: id 3 | task 251 | prompt eval time = 1349.31 ms / 158 tokens ( 8.54 ms per token, 117.10 tokens per second) 2.02.019.350 I slot print_timing: id 3 | task 251 | eval time = 44.80 ms / 2 tokens ( 44.80 ms per token, 22.32 tokens per second) 2.02.019.350 I slot print_timing: id 3 | task 251 | total time = 1394.12 ms / 160 tokens 2.02.019.351 I slot print_timing: id 3 | task 251 | graphs reused = 1 2.02.019.351 I slot print_timing: id 3 | task 251 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.019.366 I slot release: id 3 | task 251 | stop processing: n_tokens = 168, truncated = 0 2.02.019.374 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.314 (> 0.100 thold), f_keep = 0.228 2.02.024.721 I slot launch_slot_: id 0 | task 256 | processing task, is_child = 0 2.02.035.743 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.213 2.02.035.852 I slot launch_slot_: id 1 | task 257 | processing task, is_child = 0 2.02.035.932 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.226 2.02.036.024 I slot launch_slot_: id 2 | task 258 | processing task, is_child = 0 2.02.036.070 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.330 (> 0.100 thold), f_keep = 0.220 2.02.036.799 I slot launch_slot_: id 3 | task 259 | processing task, is_child = 0 2.03.260.797 I slot print_timing: id 0 | task 256 | prompt eval time = 1184.66 ms / 109 tokens ( 10.87 ms per token, 92.01 tokens per second) 2.03.260.802 I slot print_timing: id 0 | task 256 | eval time = 39.32 ms / 2 tokens ( 39.32 ms per token, 25.43 tokens per second) 2.03.260.803 I slot print_timing: id 0 | task 256 | total time = 1223.98 ms / 111 tokens 2.03.260.804 I slot print_timing: id 0 | task 256 | graphs reused = 1 2.03.260.804 I slot print_timing: id 0 | task 256 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.260.824 I slot release: id 0 | task 256 | stop processing: n_tokens = 119, truncated = 0 2.03.262.144 I slot print_timing: id 1 | task 257 | prompt eval time = 1185.61 ms / 117 tokens ( 10.13 ms per token, 98.68 tokens per second) 2.03.262.147 I slot print_timing: id 1 | task 257 | eval time = 39.56 ms / 2 tokens ( 39.56 ms per token, 25.28 tokens per second) 2.03.262.147 I slot print_timing: id 1 | task 257 | total time = 1225.17 ms / 119 tokens 2.03.262.148 I slot print_timing: id 1 | task 257 | graphs reused = 1 2.03.262.148 I slot print_timing: id 1 | task 257 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.262.165 I slot release: id 1 | task 257 | stop processing: n_tokens = 127, truncated = 0 2.03.263.459 I slot print_timing: id 2 | task 258 | prompt eval time = 1186.68 ms / 188 tokens ( 6.31 ms per token, 158.43 tokens per second) 2.03.263.461 I slot print_timing: id 2 | task 258 | eval time = 39.64 ms / 2 tokens ( 39.64 ms per token, 25.23 tokens per second) 2.03.263.461 I slot print_timing: id 2 | task 258 | total time = 1226.32 ms / 190 tokens 2.03.263.462 I slot print_timing: id 2 | task 258 | graphs reused = 1 2.03.263.462 I slot print_timing: id 2 | task 258 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.263.478 I slot release: id 2 | task 258 | stop processing: n_tokens = 198, truncated = 0 2.03.264.776 I slot print_timing: id 3 | task 259 | prompt eval time = 1187.77 ms / 103 tokens ( 11.53 ms per token, 86.72 tokens per second) 2.03.264.780 I slot print_timing: id 3 | task 259 | eval time = 39.68 ms / 2 tokens ( 39.68 ms per token, 25.20 tokens per second) 2.03.264.780 I slot print_timing: id 3 | task 259 | total time = 1227.45 ms / 105 tokens 2.03.264.780 I slot print_timing: id 3 | task 259 | graphs reused = 1 2.03.264.781 I slot print_timing: id 3 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.264.791 I slot release: id 3 | task 259 | stop processing: n_tokens = 113, truncated = 0 2.03.265.341 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.311 (> 0.100 thold), f_keep = 0.336 2.03.266.562 I slot launch_slot_: id 3 | task 264 | processing task, is_child = 0 2.03.272.946 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.311 2.03.273.025 I slot launch_slot_: id 0 | task 265 | processing task, is_child = 0 2.03.273.081 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.291 2.03.273.142 I slot launch_slot_: id 1 | task 266 | processing task, is_child = 0 2.03.273.172 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.187 2.03.273.235 I slot launch_slot_: id 2 | task 267 | processing task, is_child = 0 2.04.522.096 I slot print_timing: id 0 | task 265 | prompt eval time = 1209.84 ms / 125 tokens ( 9.68 ms per token, 103.32 tokens per second) 2.04.522.100 I slot print_timing: id 0 | task 265 | eval time = 39.02 ms / 2 tokens ( 39.02 ms per token, 25.63 tokens per second) 2.04.522.101 I slot print_timing: id 0 | task 265 | total time = 1248.85 ms / 127 tokens 2.04.522.101 I slot print_timing: id 0 | task 265 | graphs reused = 1 2.04.522.102 I slot print_timing: id 0 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.522.123 I slot release: id 0 | task 265 | stop processing: n_tokens = 135, truncated = 0 2.04.523.271 I slot print_timing: id 1 | task 266 | prompt eval time = 1210.83 ms / 128 tokens ( 9.46 ms per token, 105.71 tokens per second) 2.04.523.273 I slot print_timing: id 1 | task 266 | eval time = 39.07 ms / 2 tokens ( 39.07 ms per token, 25.60 tokens per second) 2.04.523.273 I slot print_timing: id 1 | task 266 | total time = 1249.89 ms / 130 tokens 2.04.523.274 I slot print_timing: id 1 | task 266 | graphs reused = 1 2.04.523.274 I slot print_timing: id 1 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.523.293 I slot release: id 1 | task 266 | stop processing: n_tokens = 138, truncated = 0 2.04.524.430 I slot print_timing: id 2 | task 267 | prompt eval time = 1211.78 ms / 166 tokens ( 7.30 ms per token, 136.99 tokens per second) 2.04.524.435 I slot print_timing: id 2 | task 267 | eval time = 39.15 ms / 2 tokens ( 39.15 ms per token, 25.54 tokens per second) 2.04.524.435 I slot print_timing: id 2 | task 267 | total time = 1250.93 ms / 168 tokens 2.04.524.435 I slot print_timing: id 2 | task 267 | graphs reused = 1 2.04.524.435 I slot print_timing: id 2 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.524.447 I slot release: id 2 | task 267 | stop processing: n_tokens = 176, truncated = 0 2.04.525.590 I slot print_timing: id 3 | task 264 | prompt eval time = 1212.91 ms / 113 tokens ( 10.73 ms per token, 93.16 tokens per second) 2.04.525.597 I slot print_timing: id 3 | task 264 | eval time = 39.04 ms / 2 tokens ( 39.04 ms per token, 25.61 tokens per second) 2.04.525.597 I slot print_timing: id 3 | task 264 | total time = 1251.95 ms / 115 tokens 2.04.525.598 I slot print_timing: id 3 | task 264 | graphs reused = 1 2.04.525.598 I slot print_timing: id 3 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.525.610 I slot release: id 3 | task 264 | stop processing: n_tokens = 123, truncated = 0 2.04.527.068 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.274 2.04.529.246 I slot launch_slot_: id 0 | task 272 | processing task, is_child = 0 2.04.537.908 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.247 (> 0.100 thold), f_keep = 0.309 2.04.537.975 I slot launch_slot_: id 3 | task 273 | processing task, is_child = 0 2.04.538.029 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.268 2.04.538.089 I slot launch_slot_: id 1 | task 274 | processing task, is_child = 0 2.04.538.116 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.210 2.04.538.661 I slot launch_slot_: id 2 | task 275 | processing task, is_child = 0 2.05.683.586 I slot print_timing: id 0 | task 272 | prompt eval time = 1105.80 ms / 127 tokens ( 8.71 ms per token, 114.85 tokens per second) 2.05.683.589 I slot print_timing: id 0 | task 272 | eval time = 39.11 ms / 2 tokens ( 39.11 ms per token, 25.57 tokens per second) 2.05.683.590 I slot print_timing: id 0 | task 272 | total time = 1144.91 ms / 129 tokens 2.05.683.591 I slot print_timing: id 0 | task 272 | graphs reused = 1 2.05.683.591 I slot print_timing: id 0 | task 272 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.683.619 I slot release: id 0 | task 272 | stop processing: n_tokens = 137, truncated = 0 2.05.684.938 I slot print_timing: id 1 | task 274 | prompt eval time = 1106.81 ms / 124 tokens ( 8.93 ms per token, 112.03 tokens per second) 2.05.684.940 I slot print_timing: id 1 | task 274 | eval time = 39.34 ms / 2 tokens ( 39.34 ms per token, 25.42 tokens per second) 2.05.684.940 I slot print_timing: id 1 | task 274 | total time = 1146.15 ms / 126 tokens 2.05.684.940 I slot print_timing: id 1 | task 274 | graphs reused = 1 2.05.684.941 I slot print_timing: id 1 | task 274 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.684.954 I slot release: id 1 | task 274 | stop processing: n_tokens = 134, truncated = 0 2.05.686.267 I slot print_timing: id 2 | task 275 | prompt eval time = 1107.79 ms / 139 tokens ( 7.97 ms per token, 125.47 tokens per second) 2.05.686.270 I slot print_timing: id 2 | task 275 | eval time = 39.57 ms / 2 tokens ( 39.57 ms per token, 25.27 tokens per second) 2.05.686.270 I slot print_timing: id 2 | task 275 | total time = 1147.37 ms / 141 tokens 2.05.686.271 I slot print_timing: id 2 | task 275 | graphs reused = 1 2.05.686.271 I slot print_timing: id 2 | task 275 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.686.285 I slot release: id 2 | task 275 | stop processing: n_tokens = 149, truncated = 0 2.05.687.601 I slot print_timing: id 3 | task 273 | prompt eval time = 1108.98 ms / 145 tokens ( 7.65 ms per token, 130.75 tokens per second) 2.05.687.606 I slot print_timing: id 3 | task 273 | eval time = 39.62 ms / 2 tokens ( 39.62 ms per token, 25.24 tokens per second) 2.05.687.607 I slot print_timing: id 3 | task 273 | total time = 1148.59 ms / 147 tokens 2.05.687.607 I slot print_timing: id 3 | task 273 | graphs reused = 1 2.05.687.607 I slot print_timing: id 3 | task 273 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.687.620 I slot release: id 3 | task 273 | stop processing: n_tokens = 155, truncated = 0 2.05.689.032 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.270 2.05.692.621 I slot launch_slot_: id 0 | task 280 | processing task, is_child = 0 2.05.699.969 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.276 2.05.700.513 I slot launch_slot_: id 1 | task 281 | processing task, is_child = 0 2.05.700.577 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.248 2.05.700.639 I slot launch_slot_: id 2 | task 282 | processing task, is_child = 0 2.05.700.670 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.239 2.05.701.213 I slot launch_slot_: id 3 | task 283 | processing task, is_child = 0 2.07.005.947 I slot print_timing: id 0 | task 280 | prompt eval time = 1261.90 ms / 161 tokens ( 7.84 ms per token, 127.59 tokens per second) 2.07.005.956 I slot print_timing: id 0 | task 280 | eval time = 42.82 ms / 2 tokens ( 42.82 ms per token, 23.35 tokens per second) 2.07.005.956 I slot print_timing: id 0 | task 280 | total time = 1304.72 ms / 163 tokens 2.07.005.957 I slot print_timing: id 0 | task 280 | graphs reused = 1 2.07.005.958 I slot print_timing: id 0 | task 280 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.005.989 I slot release: id 0 | task 280 | stop processing: n_tokens = 171, truncated = 0 2.07.008.405 I slot print_timing: id 1 | task 281 | prompt eval time = 1263.66 ms / 142 tokens ( 8.90 ms per token, 112.37 tokens per second) 2.07.008.409 I slot print_timing: id 1 | task 281 | eval time = 43.41 ms / 2 tokens ( 43.41 ms per token, 23.04 tokens per second) 2.07.008.410 I slot print_timing: id 1 | task 281 | total time = 1307.07 ms / 144 tokens 2.07.008.411 I slot print_timing: id 1 | task 281 | graphs reused = 1 2.07.008.412 I slot print_timing: id 1 | task 281 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.008.432 I slot release: id 1 | task 281 | stop processing: n_tokens = 152, truncated = 0 2.07.010.900 I slot print_timing: id 2 | task 282 | prompt eval time = 1265.36 ms / 173 tokens ( 7.31 ms per token, 136.72 tokens per second) 2.07.010.906 I slot print_timing: id 2 | task 282 | eval time = 44.09 ms / 2 tokens ( 44.09 ms per token, 22.68 tokens per second) 2.07.010.907 I slot print_timing: id 2 | task 282 | total time = 1309.45 ms / 175 tokens 2.07.010.908 I slot print_timing: id 2 | task 282 | graphs reused = 1 2.07.010.908 I slot print_timing: id 2 | task 282 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.010.935 I slot release: id 2 | task 282 | stop processing: n_tokens = 183, truncated = 0 2.07.013.315 I slot print_timing: id 3 | task 283 | prompt eval time = 1267.09 ms / 122 tokens ( 10.39 ms per token, 96.28 tokens per second) 2.07.013.319 I slot print_timing: id 3 | task 283 | eval time = 44.67 ms / 2 tokens ( 44.67 ms per token, 22.39 tokens per second) 2.07.013.320 I slot print_timing: id 3 | task 283 | total time = 1311.75 ms / 124 tokens 2.07.013.321 I slot print_timing: id 3 | task 283 | graphs reused = 1 2.07.013.321 I slot print_timing: id 3 | task 283 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.013.342 I slot release: id 3 | task 283 | stop processing: n_tokens = 132, truncated = 0 2.07.013.351 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.295 2.07.014.808 I slot launch_slot_: id 3 | task 288 | processing task, is_child = 0 2.07.027.941 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.216 2.07.028.056 I slot launch_slot_: id 0 | task 289 | processing task, is_child = 0 2.07.028.147 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.325 (> 0.100 thold), f_keep = 0.243 2.07.028.239 I slot launch_slot_: id 1 | task 290 | processing task, is_child = 0 2.07.028.283 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.202 2.07.028.954 I slot launch_slot_: id 2 | task 291 | processing task, is_child = 0 2.08.321.689 I slot print_timing: id 0 | task 289 | prompt eval time = 1253.33 ms / 162 tokens ( 7.74 ms per token, 129.26 tokens per second) 2.08.321.692 I slot print_timing: id 0 | task 289 | eval time = 39.40 ms / 2 tokens ( 39.40 ms per token, 25.38 tokens per second) 2.08.321.693 I slot print_timing: id 0 | task 289 | total time = 1292.72 ms / 164 tokens 2.08.321.694 I slot print_timing: id 0 | task 289 | graphs reused = 1 2.08.321.694 I slot print_timing: id 0 | task 289 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.321.718 I slot release: id 0 | task 289 | stop processing: n_tokens = 172, truncated = 0 2.08.323.071 I slot print_timing: id 1 | task 290 | prompt eval time = 1254.47 ms / 105 tokens ( 11.95 ms per token, 83.70 tokens per second) 2.08.323.072 I slot print_timing: id 1 | task 290 | eval time = 39.49 ms / 2 tokens ( 39.49 ms per token, 25.32 tokens per second) 2.08.323.073 I slot print_timing: id 1 | task 290 | total time = 1293.96 ms / 107 tokens 2.08.323.073 I slot print_timing: id 1 | task 290 | graphs reused = 1 2.08.323.074 I slot print_timing: id 1 | task 290 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.323.091 I slot release: id 1 | task 290 | stop processing: n_tokens = 115, truncated = 0 2.08.324.406 I slot print_timing: id 2 | task 291 | prompt eval time = 1255.62 ms / 136 tokens ( 9.23 ms per token, 108.31 tokens per second) 2.08.324.409 I slot print_timing: id 2 | task 291 | eval time = 39.53 ms / 2 tokens ( 39.53 ms per token, 25.30 tokens per second) 2.08.324.409 I slot print_timing: id 2 | task 291 | total time = 1295.15 ms / 138 tokens 2.08.324.409 I slot print_timing: id 2 | task 291 | graphs reused = 1 2.08.324.410 I slot print_timing: id 2 | task 291 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.324.422 I slot release: id 2 | task 291 | stop processing: n_tokens = 146, truncated = 0 2.08.325.721 I slot print_timing: id 3 | task 288 | prompt eval time = 1256.70 ms / 190 tokens ( 6.61 ms per token, 151.19 tokens per second) 2.08.325.723 I slot print_timing: id 3 | task 288 | eval time = 39.56 ms / 2 tokens ( 39.56 ms per token, 25.28 tokens per second) 2.08.325.723 I slot print_timing: id 3 | task 288 | total time = 1296.26 ms / 192 tokens 2.08.325.723 I slot print_timing: id 3 | task 288 | graphs reused = 1 2.08.325.724 I slot print_timing: id 3 | task 288 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.325.741 I slot release: id 3 | task 288 | stop processing: n_tokens = 200, truncated = 0 2.08.327.295 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.215 2.08.330.402 I slot launch_slot_: id 0 | task 296 | processing task, is_child = 0 2.08.338.915 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.322 2.08.338.994 I slot launch_slot_: id 1 | task 297 | processing task, is_child = 0 2.08.989.658 I slot print_timing: id 0 | task 296 | prompt eval time = 615.64 ms / 126 tokens ( 4.89 ms per token, 204.66 tokens per second) 2.08.989.664 I slot print_timing: id 0 | task 296 | eval time = 34.94 ms / 2 tokens ( 34.94 ms per token, 28.62 tokens per second) 2.08.989.665 I slot print_timing: id 0 | task 296 | total time = 650.59 ms / 128 tokens 2.08.989.666 I slot print_timing: id 0 | task 296 | graphs reused = 1 2.08.989.666 I slot print_timing: id 0 | task 296 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.989.698 I slot release: id 0 | task 296 | stop processing: n_tokens = 136, truncated = 0 2.08.991.054 I slot print_timing: id 1 | task 297 | prompt eval time = 616.75 ms / 146 tokens ( 4.22 ms per token, 236.72 tokens per second) 2.08.991.056 I slot print_timing: id 1 | task 297 | eval time = 35.07 ms / 2 tokens ( 35.07 ms per token, 28.51 tokens per second) 2.08.991.057 I slot print_timing: id 1 | task 297 | total time = 651.82 ms / 148 tokens 2.08.991.057 I slot print_timing: id 1 | task 297 | graphs reused = 1 2.08.991.058 I slot print_timing: id 1 | task 297 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.991.067 I slot release: id 1 | task 297 | stop processing: n_tokens = 156, truncated = 0 2.09.008.822 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 146, t_last = 326932859677 2.09.008.879 I slot launch_slot_: id 2 | task 302 | processing task, is_child = 0 2.09.014.937 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 200, t_last = 326932860996 2.09.014.983 I slot launch_slot_: id 3 | task 303 | processing task, is_child = 0 2.09.015.040 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 136, t_last = 326933524953 2.09.015.077 I slot launch_slot_: id 0 | task 305 | processing task, is_child = 0 2.09.015.107 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 156, t_last = 326933526322 2.09.015.147 I slot launch_slot_: id 1 | task 304 | processing task, is_child = 0 2.12.927.516 I slot print_timing: id 0 | task 305 | prompt processing, n_tokens = 683, progress = 0.57, t = 3.91 s / 174.58 tokens per second 2.12.989.659 I slot print_timing: id 1 | task 304 | prompt processing, n_tokens = 674, progress = 0.57, t = 3.91 s / 172.28 tokens per second 2.13.001.085 I slot print_timing: id 2 | task 302 | prompt processing, n_tokens = 655, progress = 0.56, t = 3.91 s / 167.43 tokens per second 2.13.011.591 I slot print_timing: id 3 | task 303 | prompt processing, n_tokens = 36, progress = 0.04, t = 3.91 s / 9.20 tokens per second 2.16.333.677 I slot print_timing: id 0 | task 305 | prompt processing, n_tokens = 1086, progress = 0.91, t = 7.32 s / 148.39 tokens per second 2.16.765.544 I slot print_timing: id 1 | task 304 | prompt processing, n_tokens = 1086, progress = 0.91, t = 7.32 s / 148.39 tokens per second 2.16.770.526 I slot print_timing: id 2 | task 302 | prompt processing, n_tokens = 1086, progress = 0.93, t = 7.32 s / 148.39 tokens per second 2.16.774.887 I slot print_timing: id 3 | task 303 | prompt processing, n_tokens = 670, progress = 0.57, t = 7.32 s / 91.55 tokens per second 2.17.663.470 I slot print_timing: id 0 | task 305 | prompt processing, n_tokens = 1195, progress = 1.00, t = 8.65 s / 138.18 tokens per second 2.18.330.895 I slot print_timing: id 1 | task 304 | prompt processing, n_tokens = 1186, progress = 1.00, t = 8.65 s / 137.14 tokens per second 2.18.335.952 I slot print_timing: id 2 | task 302 | prompt processing, n_tokens = 1167, progress = 1.00, t = 8.65 s / 134.94 tokens per second 2.18.340.324 I slot print_timing: id 3 | task 303 | prompt processing, n_tokens = 1086, progress = 0.92, t = 8.65 s / 125.58 tokens per second 2.18.628.325 I slot print_timing: id 3 | task 303 | prompt processing, n_tokens = 1182, progress = 1.00, t = 9.61 s / 123.00 tokens per second 2.21.228.384 I slot print_timing: id 2 | task 302 | prompt eval time = 9612.97 ms / 1171 tokens ( 8.21 ms per token, 121.81 tokens per second) 2.21.228.387 I slot print_timing: id 2 | task 302 | eval time = 2600.08 ms / 62 tokens ( 42.62 ms per token, 23.46 tokens per second) 2.21.228.388 I slot print_timing: id 2 | task 302 | total time = 12213.05 ms / 1233 tokens 2.21.228.389 I slot print_timing: id 2 | task 302 | graphs reused = 61 2.21.228.389 I slot print_timing: id 2 | task 302 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.228.450 I slot release: id 2 | task 302 | stop processing: n_tokens = 1241, truncated = 0 2.21.289.832 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.898 2.21.289.855 I slot launch_slot_: id 2 | task 372 | processing task, is_child = 0 2.22.261.344 I slot print_timing: id 3 | task 303 | prompt eval time = 9691.17 ms / 1186 tokens ( 8.17 ms per token, 122.38 tokens per second) 2.22.261.352 I slot print_timing: id 3 | task 303 | eval time = 3554.75 ms / 77 tokens ( 46.77 ms per token, 21.38 tokens per second) 2.22.261.352 I slot print_timing: id 3 | task 303 | total time = 13245.92 ms / 1263 tokens 2.22.261.353 I slot print_timing: id 3 | task 303 | graphs reused = 72 2.22.261.353 I slot print_timing: id 3 | task 303 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.261.410 I slot release: id 3 | task 303 | stop processing: n_tokens = 1271, truncated = 0 2.22.301.627 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.877 2.22.301.648 I slot launch_slot_: id 3 | task 389 | processing task, is_child = 0 2.23.478.938 I slot print_timing: id 0 | task 305 | n_gen = 100, tg = 20.40 t/s, tg_3s = 20.61 t/s 2.23.480.531 I slot print_timing: id 1 | task 304 | n_gen = 100, tg = 20.40 t/s, tg_3s = 20.60 t/s 2.26.176.351 I slot print_timing: id 2 | task 372 | n_gen = 100, tg = 22.16 t/s, tg_3s = 22.38 t/s 2.26.510.349 I slot print_timing: id 0 | task 305 | n_gen = 172, tg = 21.69 t/s, tg_3s = 23.75 t/s 2.26.511.968 I slot print_timing: id 1 | task 304 | n_gen = 172, tg = 21.69 t/s, tg_3s = 23.75 t/s 2.26.852.061 I slot print_timing: id 3 | task 389 | n_gen = 100, tg = 23.74 t/s, tg_3s = 23.98 t/s 2.27.735.148 I slot print_timing: id 2 | task 372 | prompt eval time = 418.36 ms / 107 tokens ( 3.91 ms per token, 255.76 tokens per second) 2.27.735.152 I slot print_timing: id 2 | task 372 | eval time = 6026.92 ms / 137 tokens ( 44.32 ms per token, 22.57 tokens per second) 2.27.735.152 I slot print_timing: id 2 | task 372 | total time = 6445.29 ms / 244 tokens 2.27.735.153 I slot print_timing: id 2 | task 372 | graphs reused = 191 2.27.735.154 I slot print_timing: id 2 | task 372 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.735.210 I slot release: id 2 | task 372 | stop processing: n_tokens = 1358, truncated = 0 2.27.797.615 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.821 2.27.797.638 I slot launch_slot_: id 2 | task 513 | processing task, is_child = 0 2.29.278.285 I slot print_timing: id 0 | task 305 | prompt eval time = 9610.82 ms / 1199 tokens ( 8.02 ms per token, 124.76 tokens per second) 2.29.278.289 I slot print_timing: id 0 | task 305 | eval time = 10652.31 ms / 229 tokens ( 46.72 ms per token, 21.40 tokens per second) 2.29.278.294 I slot print_timing: id 0 | task 305 | total time = 20263.13 ms / 1428 tokens 2.29.278.294 I slot print_timing: id 0 | task 305 | graphs reused = 215 2.29.278.295 I slot print_timing: id 0 | task 305 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.278.351 I slot release: id 0 | task 305 | stop processing: n_tokens = 1436, truncated = 0 2.29.323.764 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.776 2.29.323.790 I slot launch_slot_: id 0 | task 542 | processing task, is_child = 0 2.29.567.154 I slot print_timing: id 1 | task 304 | n_gen = 231, tg = 21.02 t/s, tg_3s = 19.31 t/s 2.29.860.166 I slot print_timing: id 3 | task 389 | n_gen = 157, tg = 21.73 t/s, tg_3s = 18.95 t/s 2.30.951.135 I slot print_timing: id 1 | task 304 | prompt eval time = 9611.88 ms / 1190 tokens ( 8.08 ms per token, 123.81 tokens per second) 2.30.951.139 I slot print_timing: id 1 | task 304 | eval time = 12324.01 ms / 263 tokens ( 47.04 ms per token, 21.26 tokens per second) 2.30.951.139 I slot print_timing: id 1 | task 304 | total time = 21935.89 ms / 1453 tokens 2.30.951.140 I slot print_timing: id 1 | task 304 | graphs reused = 246 2.30.951.140 I slot print_timing: id 1 | task 304 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.951.206 I slot release: id 1 | task 304 | stop processing: n_tokens = 1461, truncated = 0 2.31.015.310 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.763 2.31.015.334 I slot launch_slot_: id 1 | task 577 | processing task, is_child = 0 2.31.839.699 I slot print_timing: id 3 | task 389 | prompt eval time = 379.48 ms / 114 tokens ( 3.33 ms per token, 300.41 tokens per second) 2.31.839.705 I slot print_timing: id 3 | task 389 | eval time = 9158.56 ms / 195 tokens ( 47.21 ms per token, 21.18 tokens per second) 2.31.839.706 I slot print_timing: id 3 | task 389 | total time = 9538.04 ms / 309 tokens 2.31.839.706 I slot print_timing: id 3 | task 389 | graphs reused = 254 2.31.839.707 I slot print_timing: id 3 | task 389 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.839.760 I slot release: id 3 | task 389 | stop processing: n_tokens = 1423, truncated = 0 2.31.880.060 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.784 2.31.880.084 I slot launch_slot_: id 3 | task 590 | processing task, is_child = 0 2.33.364.673 I slot print_timing: id 2 | task 513 | n_gen = 100, tg = 19.26 t/s, tg_3s = 19.45 t/s 2.34.537.037 I slot print_timing: id 0 | task 542 | n_gen = 100, tg = 20.23 t/s, tg_3s = 20.44 t/s 2.35.294.548 I slot print_timing: id 0 | task 542 | prompt eval time = 320.66 ms / 89 tokens ( 3.60 ms per token, 277.55 tokens per second) 2.35.294.552 I slot print_timing: id 0 | task 542 | eval time = 5650.09 ms / 118 tokens ( 48.29 ms per token, 20.71 tokens per second) 2.35.294.553 I slot print_timing: id 0 | task 542 | total time = 5970.75 ms / 207 tokens 2.35.294.553 I slot print_timing: id 0 | task 542 | graphs reused = 324 2.35.294.554 I slot print_timing: id 0 | task 542 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.294.611 I slot release: id 0 | task 542 | stop processing: n_tokens = 1321, truncated = 0 2.35.340.037 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.844 2.35.340.063 I slot launch_slot_: id 0 | task 665 | processing task, is_child = 0 2.36.123.331 I slot print_timing: id 2 | task 513 | prompt eval time = 426.37 ms / 117 tokens ( 3.64 ms per token, 274.41 tokens per second) 2.36.123.337 I slot print_timing: id 2 | task 513 | eval time = 7899.31 ms / 160 tokens ( 49.68 ms per token, 20.13 tokens per second) 2.36.123.338 I slot print_timing: id 2 | task 513 | total time = 8325.69 ms / 277 tokens 2.36.123.338 I slot print_timing: id 2 | task 513 | graphs reused = 335 2.36.123.339 I slot print_timing: id 2 | task 513 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.123.398 I slot release: id 2 | task 513 | stop processing: n_tokens = 1391, truncated = 0 2.36.185.660 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.802 2.36.185.681 I slot launch_slot_: id 2 | task 680 | processing task, is_child = 0 2.36.449.257 I slot print_timing: id 1 | task 577 | n_gen = 100, tg = 19.81 t/s, tg_3s = 20.01 t/s 2.37.016.721 I slot print_timing: id 3 | task 590 | n_gen = 100, tg = 21.05 t/s, tg_3s = 21.26 t/s 2.38.065.325 I slot print_timing: id 1 | task 577 | prompt eval time = 435.74 ms / 118 tokens ( 3.69 ms per token, 270.80 tokens per second) 2.38.065.329 I slot print_timing: id 1 | task 577 | eval time = 6614.24 ms / 137 tokens ( 48.63 ms per token, 20.56 tokens per second) 2.38.065.330 I slot print_timing: id 1 | task 577 | total time = 7049.99 ms / 255 tokens 2.38.065.331 I slot print_timing: id 1 | task 577 | graphs reused = 370 2.38.065.331 I slot print_timing: id 1 | task 577 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.065.388 I slot release: id 1 | task 577 | stop processing: n_tokens = 1369, truncated = 0 2.38.129.567 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.814 2.38.129.590 I slot launch_slot_: id 1 | task 720 | processing task, is_child = 0 2.40.024.574 I slot print_timing: id 3 | task 590 | n_gen = 164, tg = 21.14 t/s, tg_3s = 21.28 t/s 2.40.440.479 I slot print_timing: id 0 | task 665 | n_gen = 100, tg = 20.70 t/s, tg_3s = 20.91 t/s 2.40.734.678 I slot print_timing: id 0 | task 665 | prompt eval time = 317.18 ms / 100 tokens ( 3.17 ms per token, 315.28 tokens per second) 2.40.734.681 I slot print_timing: id 0 | task 665 | eval time = 5077.43 ms / 107 tokens ( 47.90 ms per token, 20.88 tokens per second) 2.40.734.682 I slot print_timing: id 0 | task 665 | total time = 5394.61 ms / 207 tokens 2.40.734.683 I slot print_timing: id 0 | task 665 | graphs reused = 422 2.40.734.683 I slot print_timing: id 0 | task 665 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.734.743 I slot release: id 0 | task 665 | stop processing: n_tokens = 1321, truncated = 0 2.40.779.784 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.844 2.40.779.805 I slot launch_slot_: id 0 | task 777 | processing task, is_child = 0 2.41.020.373 I slot print_timing: id 2 | task 680 | prompt eval time = 360.31 ms / 76 tokens ( 4.74 ms per token, 210.93 tokens per second) 2.41.020.379 I slot print_timing: id 2 | task 680 | eval time = 4474.37 ms / 95 tokens ( 47.60 ms per token, 21.01 tokens per second) 2.41.020.379 I slot print_timing: id 2 | task 680 | total time = 4834.68 ms / 171 tokens 2.41.020.380 I slot print_timing: id 2 | task 680 | graphs reused = 423 2.41.020.380 I slot print_timing: id 2 | task 680 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.020.448 I slot release: id 2 | task 680 | stop processing: n_tokens = 1285, truncated = 0 2.41.105.087 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.868 2.41.105.109 I slot launch_slot_: id 2 | task 780 | processing task, is_child = 0 2.41.512.146 I slot print_timing: id 1 | task 720 | prompt eval time = 373.41 ms / 76 tokens ( 4.91 ms per token, 203.53 tokens per second) 2.41.512.152 I slot print_timing: id 1 | task 720 | eval time = 3009.13 ms / 60 tokens ( 51.00 ms per token, 19.61 tokens per second) 2.41.512.153 I slot print_timing: id 1 | task 720 | total time = 3382.55 ms / 136 tokens 2.41.512.154 I slot print_timing: id 1 | task 720 | graphs reused = 423 2.41.512.154 I slot print_timing: id 1 | task 720 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.512.213 I slot release: id 1 | task 720 | stop processing: n_tokens = 1250, truncated = 0 2.41.577.283 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.892 2.41.577.345 I slot launch_slot_: id 1 | task 785 | processing task, is_child = 0 2.43.027.368 I slot print_timing: id 3 | task 590 | n_gen = 214, tg = 19.88 t/s, tg_3s = 16.65 t/s 2.44.365.491 I slot print_timing: id 2 | task 780 | prompt eval time = 365.75 ms / 99 tokens ( 3.69 ms per token, 270.67 tokens per second) 2.44.365.498 I slot print_timing: id 2 | task 780 | eval time = 2894.62 ms / 61 tokens ( 48.24 ms per token, 20.73 tokens per second) 2.44.365.498 I slot print_timing: id 2 | task 780 | total time = 3260.37 ms / 160 tokens 2.44.365.499 I slot print_timing: id 2 | task 780 | graphs reused = 478 2.44.365.499 I slot print_timing: id 2 | task 780 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.365.554 I slot release: id 2 | task 780 | stop processing: n_tokens = 1274, truncated = 0 2.44.427.547 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.875 2.44.427.570 I slot launch_slot_: id 2 | task 845 | processing task, is_child = 0 2.46.052.130 I slot print_timing: id 3 | task 590 | n_gen = 280, tg = 20.31 t/s, tg_3s = 21.82 t/s 2.46.173.715 I slot print_timing: id 0 | task 777 | n_gen = 100, tg = 19.52 t/s, tg_3s = 19.72 t/s 2.46.426.446 I slot print_timing: id 1 | task 785 | n_gen = 100, tg = 22.42 t/s, tg_3s = 22.64 t/s 2.48.025.869 I slot print_timing: id 3 | task 590 | prompt eval time = 433.67 ms / 145 tokens ( 2.99 ms per token, 334.35 tokens per second) 2.48.025.875 I slot print_timing: id 3 | task 590 | eval time = 15712.11 ms / 327 tokens ( 48.20 ms per token, 20.75 tokens per second) 2.48.025.876 I slot print_timing: id 3 | task 590 | total time = 16145.78 ms / 472 tokens 2.48.025.876 I slot print_timing: id 3 | task 590 | graphs reused = 554 2.48.025.877 I slot print_timing: id 3 | task 590 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.025.929 I slot release: id 3 | task 590 | stop processing: n_tokens = 1586, truncated = 0 2.48.066.402 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.703 2.48.066.425 I slot launch_slot_: id 3 | task 927 | processing task, is_child = 0 2.49.198.135 I slot print_timing: id 0 | task 777 | n_gen = 165, tg = 20.26 t/s, tg_3s = 21.49 t/s 2.49.201.303 I slot print_timing: id 2 | task 845 | n_gen = 100, tg = 22.19 t/s, tg_3s = 22.41 t/s 2.49.451.689 I slot print_timing: id 1 | task 785 | n_gen = 165, tg = 22.04 t/s, tg_3s = 21.49 t/s 2.49.621.439 I slot print_timing: id 2 | task 845 | prompt eval time = 311.47 ms / 62 tokens ( 5.02 ms per token, 199.05 tokens per second) 2.49.621.446 I slot print_timing: id 2 | task 845 | eval time = 4882.39 ms / 110 tokens ( 44.79 ms per token, 22.33 tokens per second) 2.49.621.447 I slot print_timing: id 2 | task 845 | total time = 5193.86 ms / 172 tokens 2.49.621.447 I slot print_timing: id 2 | task 845 | graphs reused = 581 2.49.621.448 I slot print_timing: id 2 | task 845 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.621.503 I slot release: id 2 | task 845 | stop processing: n_tokens = 1286, truncated = 0 2.49.683.917 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.867 2.49.683.943 I slot launch_slot_: id 2 | task 959 | processing task, is_child = 0 2.50.677.862 I slot print_timing: id 0 | task 777 | prompt eval time = 323.12 ms / 72 tokens ( 4.49 ms per token, 222.82 tokens per second) 2.50.677.866 I slot print_timing: id 0 | task 777 | eval time = 9574.92 ms / 193 tokens ( 49.87 ms per token, 20.05 tokens per second) 2.50.677.867 I slot print_timing: id 0 | task 777 | total time = 9898.05 ms / 265 tokens 2.50.677.868 I slot print_timing: id 0 | task 777 | graphs reused = 595 2.50.677.868 I slot print_timing: id 0 | task 777 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.677.927 I slot release: id 0 | task 777 | stop processing: n_tokens = 1379, truncated = 0 2.50.723.162 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.809 2.50.723.185 I slot launch_slot_: id 0 | task 978 | processing task, is_child = 0 2.52.453.639 I slot print_timing: id 1 | task 785 | n_gen = 225, tg = 21.45 t/s, tg_3s = 19.99 t/s 2.53.088.304 I slot print_timing: id 3 | task 927 | n_gen = 100, tg = 21.31 t/s, tg_3s = 21.52 t/s 2.53.212.888 I slot print_timing: id 2 | task 959 | prompt eval time = 360.13 ms / 74 tokens ( 4.87 ms per token, 205.48 tokens per second) 2.53.212.892 I slot print_timing: id 2 | task 959 | eval time = 3168.81 ms / 72 tokens ( 44.63 ms per token, 22.41 tokens per second) 2.53.212.893 I slot print_timing: id 2 | task 959 | total time = 3528.94 ms / 146 tokens 2.53.212.893 I slot print_timing: id 2 | task 959 | graphs reused = 648 2.53.212.894 I slot print_timing: id 2 | task 959 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.212.949 I slot release: id 2 | task 959 | stop processing: n_tokens = 1260, truncated = 0 2.53.274.887 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.885 2.53.274.913 I slot launch_slot_: id 2 | task 1035 | processing task, is_child = 0 2.53.890.331 I slot print_timing: id 1 | task 785 | prompt eval time = 432.84 ms / 125 tokens ( 3.46 ms per token, 288.79 tokens per second) 2.53.890.334 I slot print_timing: id 1 | task 785 | eval time = 11880.13 ms / 252 tokens ( 47.33 ms per token, 21.13 tokens per second) 2.53.890.335 I slot print_timing: id 1 | task 785 | total time = 12312.97 ms / 377 tokens 2.53.890.336 I slot print_timing: id 1 | task 785 | graphs reused = 653 2.53.890.336 I slot print_timing: id 1 | task 785 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.890.404 I slot release: id 1 | task 785 | stop processing: n_tokens = 1491, truncated = 0 2.53.954.606 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.748 2.53.954.633 I slot launch_slot_: id 1 | task 1045 | processing task, is_child = 0 2.54.921.046 I slot print_timing: id 0 | task 978 | prompt eval time = 257.06 ms / 59 tokens ( 4.36 ms per token, 229.52 tokens per second) 2.54.921.051 I slot print_timing: id 0 | task 978 | eval time = 3940.80 ms / 80 tokens ( 49.88 ms per token, 20.05 tokens per second) 2.54.921.052 I slot print_timing: id 0 | task 978 | total time = 4197.86 ms / 139 tokens 2.54.921.052 I slot print_timing: id 0 | task 978 | graphs reused = 666 2.54.921.053 I slot print_timing: id 0 | task 978 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.921.111 I slot release: id 0 | task 978 | stop processing: n_tokens = 1253, truncated = 0 2.54.966.542 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.890 2.54.966.564 I slot launch_slot_: id 0 | task 1063 | processing task, is_child = 0 2.56.100.270 I slot print_timing: id 3 | task 927 | n_gen = 150, tg = 19.46 t/s, tg_3s = 16.60 t/s 2.56.604.393 I slot print_timing: id 3 | task 927 | prompt eval time = 375.88 ms / 111 tokens ( 3.39 ms per token, 295.31 tokens per second) 2.56.604.399 I slot print_timing: id 3 | task 927 | eval time = 8162.08 ms / 162 tokens ( 50.70 ms per token, 19.73 tokens per second) 2.56.604.400 I slot print_timing: id 3 | task 927 | total time = 8537.96 ms / 273 tokens 2.56.604.400 I slot print_timing: id 3 | task 927 | graphs reused = 696 2.56.604.401 I slot print_timing: id 3 | task 927 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.604.452 I slot release: id 3 | task 927 | stop processing: n_tokens = 1387, truncated = 0 2.56.644.783 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.804 2.56.644.804 I slot launch_slot_: id 3 | task 1097 | processing task, is_child = 0 2.57.584.612 I slot print_timing: id 1 | task 1045 | prompt eval time = 374.09 ms / 70 tokens ( 5.34 ms per token, 187.12 tokens per second) 2.57.584.616 I slot print_timing: id 1 | task 1045 | eval time = 3255.88 ms / 67 tokens ( 49.33 ms per token, 20.27 tokens per second) 2.57.584.616 I slot print_timing: id 1 | task 1045 | total time = 3629.97 ms / 137 tokens 2.57.584.617 I slot print_timing: id 1 | task 1045 | graphs reused = 711 2.57.584.618 I slot print_timing: id 1 | task 1045 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.584.674 I slot release: id 1 | task 1045 | stop processing: n_tokens = 1251, truncated = 0 2.57.647.986 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.891 2.57.648.015 I slot launch_slot_: id 1 | task 1117 | processing task, is_child = 0 2.58.923.385 I slot print_timing: id 2 | task 1035 | n_gen = 100, tg = 18.72 t/s, tg_3s = 18.91 t/s 3.00.011.882 I slot print_timing: id 0 | task 1063 | n_gen = 100, tg = 21.18 t/s, tg_3s = 21.39 t/s 3.00.393.229 I slot print_timing: id 2 | task 1035 | prompt eval time = 360.45 ms / 76 tokens ( 4.74 ms per token, 210.85 tokens per second) 3.00.393.233 I slot print_timing: id 2 | task 1035 | eval time = 6757.86 ms / 135 tokens ( 50.43 ms per token, 19.83 tokens per second) 3.00.393.234 I slot print_timing: id 2 | task 1035 | total time = 7118.31 ms / 211 tokens 3.00.393.234 I slot print_timing: id 2 | task 1035 | graphs reused = 765 3.00.393.235 I slot print_timing: id 2 | task 1035 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.393.288 I slot release: id 2 | task 1035 | stop processing: n_tokens = 1325, truncated = 0 3.00.455.356 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.842 3.00.455.382 I slot launch_slot_: id 2 | task 1177 | processing task, is_child = 0 3.01.654.968 I slot print_timing: id 3 | task 1097 | n_gen = 100, tg = 20.87 t/s, tg_3s = 21.08 t/s 3.01.906.873 I slot print_timing: id 3 | task 1097 | prompt eval time = 265.76 ms / 65 tokens ( 4.09 ms per token, 244.58 tokens per second) 3.01.906.880 I slot print_timing: id 3 | task 1097 | eval time = 4996.30 ms / 106 tokens ( 47.58 ms per token, 21.02 tokens per second) 3.01.906.881 I slot print_timing: id 3 | task 1097 | total time = 5262.06 ms / 171 tokens 3.01.906.882 I slot print_timing: id 3 | task 1097 | graphs reused = 791 3.01.906.882 I slot print_timing: id 3 | task 1097 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.906.937 I slot release: id 3 | task 1097 | stop processing: n_tokens = 1285, truncated = 0 3.01.947.439 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.868 3.01.947.463 I slot launch_slot_: id 3 | task 1208 | processing task, is_child = 0 3.02.745.756 I slot print_timing: id 1 | task 1117 | n_gen = 100, tg = 21.01 t/s, tg_3s = 21.22 t/s 3.02.997.904 I slot print_timing: id 1 | task 1117 | prompt eval time = 384.69 ms / 71 tokens ( 5.42 ms per token, 184.56 tokens per second) 3.02.997.907 I slot print_timing: id 1 | task 1117 | eval time = 4965.19 ms / 106 tokens ( 47.29 ms per token, 21.15 tokens per second) 3.02.997.908 I slot print_timing: id 1 | task 1117 | total time = 5349.88 ms / 177 tokens 3.02.997.909 I slot print_timing: id 1 | task 1117 | graphs reused = 806 3.02.997.909 I slot print_timing: id 1 | task 1117 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.997.965 I slot release: id 1 | task 1117 | stop processing: n_tokens = 1291, truncated = 0 3.03.058.602 I slot print_timing: id 0 | task 1063 | n_gen = 159, tg = 20.46 t/s, tg_3s = 19.37 t/s 3.03.062.169 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.864 3.03.062.193 I slot launch_slot_: id 1 | task 1228 | processing task, is_child = 0 3.05.614.209 I slot print_timing: id 2 | task 1177 | n_gen = 100, tg = 20.40 t/s, tg_3s = 20.61 t/s 3.06.074.505 I slot print_timing: id 0 | task 1063 | n_gen = 222, tg = 20.58 t/s, tg_3s = 20.89 t/s 3.06.077.653 I slot print_timing: id 2 | task 1177 | prompt eval time = 306.05 ms / 62 tokens ( 4.94 ms per token, 202.58 tokens per second) 3.06.077.656 I slot print_timing: id 2 | task 1177 | eval time = 5316.21 ms / 111 tokens ( 48.33 ms per token, 20.69 tokens per second) 3.06.077.656 I slot print_timing: id 2 | task 1177 | total time = 5622.27 ms / 173 tokens 3.06.077.657 I slot print_timing: id 2 | task 1177 | graphs reused = 866 3.06.077.657 I slot print_timing: id 2 | task 1177 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.077.712 I slot release: id 2 | task 1177 | stop processing: n_tokens = 1287, truncated = 0 3.06.140.121 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.866 3.06.140.142 I slot launch_slot_: id 2 | task 1293 | processing task, is_child = 0 3.07.253.738 I slot print_timing: id 3 | task 1208 | n_gen = 100, tg = 20.08 t/s, tg_3s = 20.28 t/s 3.08.051.996 I slot print_timing: id 1 | task 1228 | n_gen = 100, tg = 21.72 t/s, tg_3s = 21.94 t/s 3.09.104.647 I slot print_timing: id 0 | task 1063 | n_gen = 285, tg = 20.63 t/s, tg_3s = 20.79 t/s 3.10.292.582 I slot print_timing: id 3 | task 1208 | n_gen = 172, tg = 21.46 t/s, tg_3s = 23.69 t/s 3.10.757.201 I slot print_timing: id 2 | task 1293 | n_gen = 100, tg = 23.66 t/s, tg_3s = 23.90 t/s 3.11.093.959 I slot print_timing: id 1 | task 1228 | n_gen = 172, tg = 22.50 t/s, tg_3s = 23.67 t/s 3.12.106.130 I slot print_timing: id 0 | task 1063 | n_gen = 356, tg = 21.17 t/s, tg_3s = 23.65 t/s 3.13.294.555 I slot print_timing: id 3 | task 1208 | n_gen = 243, tg = 22.06 t/s, tg_3s = 23.65 t/s 3.13.758.493 I slot print_timing: id 2 | task 1293 | n_gen = 171, tg = 23.66 t/s, tg_3s = 23.66 t/s 3.14.095.469 I slot print_timing: id 1 | task 1228 | n_gen = 243, tg = 22.83 t/s, tg_3s = 23.65 t/s 3.15.109.859 I slot print_timing: id 0 | task 1063 | n_gen = 427, tg = 21.54 t/s, tg_3s = 23.64 t/s 3.16.336.807 I slot print_timing: id 3 | task 1208 | n_gen = 315, tg = 22.41 t/s, tg_3s = 23.67 t/s 3.16.800.064 I slot print_timing: id 2 | task 1293 | n_gen = 243, tg = 23.66 t/s, tg_3s = 23.67 t/s 3.17.137.805 I slot print_timing: id 1 | task 1228 | n_gen = 315, tg = 23.01 t/s, tg_3s = 23.67 t/s 3.18.111.448 I slot print_timing: id 0 | task 1063 | n_gen = 498, tg = 21.82 t/s, tg_3s = 23.65 t/s 3.19.346.090 I slot print_timing: id 3 | task 1208 | n_gen = 386, tg = 22.62 t/s, tg_3s = 23.59 t/s 3.19.810.277 I slot print_timing: id 2 | task 1293 | n_gen = 314, tg = 23.65 t/s, tg_3s = 23.59 t/s 3.20.147.073 I slot print_timing: id 1 | task 1228 | n_gen = 386, tg = 23.12 t/s, tg_3s = 23.59 t/s 3.21.123.224 I slot print_timing: id 0 | task 1063 | n_gen = 569, tg = 22.03 t/s, tg_3s = 23.57 t/s 3.22.363.577 I slot print_timing: id 3 | task 1208 | n_gen = 457, tg = 22.75 t/s, tg_3s = 23.53 t/s 3.22.827.980 I slot print_timing: id 2 | task 1293 | n_gen = 385, tg = 23.62 t/s, tg_3s = 23.53 t/s 3.23.165.963 I slot print_timing: id 1 | task 1228 | n_gen = 457, tg = 23.18 t/s, tg_3s = 23.52 t/s 3.24.142.132 I slot print_timing: id 0 | task 1063 | n_gen = 640, tg = 22.18 t/s, tg_3s = 23.52 t/s 3.24.609.998 I slot print_timing: id 0 | task 1063 | prompt eval time = 370.21 ms / 106 tokens ( 3.49 ms per token, 286.33 tokens per second) 3.24.610.002 I slot print_timing: id 0 | task 1063 | eval time = 29273.21 ms / 651 tokens ( 45.04 ms per token, 22.20 tokens per second) 3.24.610.002 I slot print_timing: id 0 | task 1063 | total time = 29643.42 ms / 757 tokens 3.24.610.003 I slot print_timing: id 0 | task 1063 | graphs reused = 1289 3.24.610.004 I slot print_timing: id 0 | task 1063 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.610.066 I slot release: id 0 | task 1063 | stop processing: n_tokens = 1871, truncated = 0 3.24.655.694 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.596 3.24.655.721 I slot launch_slot_: id 0 | task 1723 | processing task, is_child = 0 3.25.404.619 I slot print_timing: id 3 | task 1208 | n_gen = 523, tg = 22.62 t/s, tg_3s = 21.70 t/s 3.25.828.099 I slot print_timing: id 2 | task 1293 | n_gen = 450, tg = 23.32 t/s, tg_3s = 21.67 t/s 3.26.166.575 I slot print_timing: id 1 | task 1228 | n_gen = 522, tg = 22.98 t/s, tg_3s = 21.66 t/s 3.26.547.683 I slot print_timing: id 1 | task 1228 | prompt eval time = 431.22 ms / 111 tokens ( 3.88 ms per token, 257.41 tokens per second) 3.26.547.686 I slot print_timing: id 1 | task 1228 | eval time = 23054.26 ms / 531 tokens ( 43.50 ms per token, 22.99 tokens per second) 3.26.547.687 I slot print_timing: id 1 | task 1228 | total time = 23485.48 ms / 642 tokens 3.26.547.688 I slot print_timing: id 1 | task 1228 | graphs reused = 1326 3.26.547.688 I slot print_timing: id 1 | task 1228 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.547.747 I slot release: id 1 | task 1228 | stop processing: n_tokens = 1756, truncated = 0 3.26.611.989 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.635 3.26.612.012 I slot launch_slot_: id 1 | task 1764 | processing task, is_child = 0 3.28.426.567 I slot print_timing: id 3 | task 1208 | n_gen = 588, tg = 22.49 t/s, tg_3s = 21.51 t/s 3.28.847.985 I slot print_timing: id 2 | task 1293 | n_gen = 515, tg = 23.08 t/s, tg_3s = 21.52 t/s 3.28.971.843 I slot print_timing: id 0 | task 1723 | prompt eval time = 319.68 ms / 69 tokens ( 4.63 ms per token, 215.84 tokens per second) 3.28.971.849 I slot print_timing: id 0 | task 1723 | eval time = 3996.43 ms / 89 tokens ( 45.41 ms per token, 22.02 tokens per second) 3.28.971.850 I slot print_timing: id 0 | task 1723 | total time = 4316.11 ms / 158 tokens 3.28.971.850 I slot print_timing: id 0 | task 1723 | graphs reused = 1372 3.28.971.851 I slot print_timing: id 0 | task 1723 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.971.909 I slot release: id 0 | task 1723 | stop processing: n_tokens = 1271, truncated = 0 3.29.017.523 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.877 3.29.017.550 I slot launch_slot_: id 0 | task 1816 | processing task, is_child = 0 3.29.885.341 I slot print_timing: id 1 | task 1764 | prompt eval time = 322.55 ms / 63 tokens ( 5.12 ms per token, 195.32 tokens per second) 3.29.885.345 I slot print_timing: id 1 | task 1764 | eval time = 2950.77 ms / 65 tokens ( 46.11 ms per token, 21.69 tokens per second) 3.29.885.346 I slot print_timing: id 1 | task 1764 | total time = 3273.32 ms / 128 tokens 3.29.885.346 I slot print_timing: id 1 | task 1764 | graphs reused = 1385 3.29.885.347 I slot print_timing: id 1 | task 1764 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.885.402 I slot release: id 1 | task 1764 | stop processing: n_tokens = 1241, truncated = 0 3.29.949.881 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.898 3.29.949.906 I slot launch_slot_: id 1 | task 1833 | processing task, is_child = 0 3.31.441.198 I slot print_timing: id 3 | task 1208 | n_gen = 646, tg = 22.15 t/s, tg_3s = 19.24 t/s 3.31.863.210 I slot print_timing: id 2 | task 1293 | n_gen = 573, tg = 22.62 t/s, tg_3s = 19.24 t/s 3.33.090.383 I slot print_timing: id 0 | task 1816 | prompt eval time = 313.93 ms / 74 tokens ( 4.24 ms per token, 235.72 tokens per second) 3.33.090.389 I slot print_timing: id 0 | task 1816 | eval time = 3758.90 ms / 82 tokens ( 46.41 ms per token, 21.55 tokens per second) 3.33.090.390 I slot print_timing: id 0 | task 1816 | total time = 4072.83 ms / 156 tokens 3.33.090.391 I slot print_timing: id 0 | task 1816 | graphs reused = 1449 3.33.090.391 I slot print_timing: id 0 | task 1816 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.090.448 I slot release: id 0 | task 1816 | stop processing: n_tokens = 1270, truncated = 0 3.33.136.167 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.878 3.33.136.191 I slot launch_slot_: id 0 | task 1902 | processing task, is_child = 0 3.34.479.599 I slot print_timing: id 3 | task 1208 | n_gen = 712, tg = 22.11 t/s, tg_3s = 21.72 t/s 3.34.773.833 I slot print_timing: id 1 | task 1833 | n_gen = 100, tg = 22.26 t/s, tg_3s = 22.49 t/s 3.34.902.889 I slot print_timing: id 2 | task 1293 | n_gen = 639, tg = 22.52 t/s, tg_3s = 21.71 t/s 3.37.495.727 I slot print_timing: id 3 | task 1208 | n_gen = 783, tg = 22.23 t/s, tg_3s = 23.54 t/s 3.37.661.220 I slot print_timing: id 0 | task 1902 | n_gen = 100, tg = 23.53 t/s, tg_3s = 23.77 t/s 3.37.790.426 I slot print_timing: id 1 | task 1833 | n_gen = 171, tg = 22.78 t/s, tg_3s = 23.54 t/s 3.37.919.519 I slot print_timing: id 2 | task 1293 | n_gen = 710, tg = 22.62 t/s, tg_3s = 23.54 t/s 3.38.342.976 I slot print_timing: id 1 | task 1833 | prompt eval time = 376.67 ms / 80 tokens ( 4.71 ms per token, 212.39 tokens per second) 3.38.342.979 I slot print_timing: id 1 | task 1833 | eval time = 8016.39 ms / 184 tokens ( 43.81 ms per token, 22.83 tokens per second) 3.38.342.980 I slot print_timing: id 1 | task 1833 | total time = 8393.06 ms / 264 tokens 3.38.342.981 I slot print_timing: id 1 | task 1833 | graphs reused = 1564 3.38.342.981 I slot print_timing: id 1 | task 1833 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.343.039 I slot release: id 1 | task 1833 | stop processing: n_tokens = 1378, truncated = 0 3.38.407.682 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.809 3.38.407.710 I slot launch_slot_: id 1 | task 2021 | processing task, is_child = 0 3.38.683.126 I slot print_timing: id 0 | task 1902 | prompt eval time = 317.71 ms / 88 tokens ( 3.61 ms per token, 276.98 tokens per second) 3.38.683.129 I slot print_timing: id 0 | task 1902 | eval time = 5229.22 ms / 118 tokens ( 44.69 ms per token, 22.37 tokens per second) 3.38.683.131 I slot print_timing: id 0 | task 1902 | total time = 5546.93 ms / 206 tokens 3.38.683.132 I slot print_timing: id 0 | task 1902 | graphs reused = 1564 3.38.683.132 I slot print_timing: id 0 | task 1902 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.683.200 I slot release: id 0 | task 1902 | stop processing: n_tokens = 1320, truncated = 0 3.38.759.104 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.845 3.38.759.131 I slot launch_slot_: id 0 | task 2024 | processing task, is_child = 0 3.40.527.478 I slot print_timing: id 3 | task 1208 | n_gen = 842, tg = 22.01 t/s, tg_3s = 19.46 t/s 3.40.951.724 I slot print_timing: id 2 | task 1293 | n_gen = 769, tg = 22.34 t/s, tg_3s = 19.46 t/s 3.42.995.567 I slot print_timing: id 2 | task 1293 | prompt eval time = 432.91 ms / 128 tokens ( 3.38 ms per token, 295.67 tokens per second) 3.42.995.574 I slot print_timing: id 2 | task 1293 | eval time = 36422.50 ms / 817 tokens ( 44.64 ms per token, 22.40 tokens per second) 3.42.995.575 I slot print_timing: id 2 | task 1293 | total time = 36855.42 ms / 945 tokens 3.42.995.576 I slot print_timing: id 2 | task 1293 | graphs reused = 1654 3.42.995.576 I slot print_timing: id 2 | task 1293 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.995.638 I slot release: id 2 | task 1293 | stop processing: n_tokens = 2059, truncated = 0 3.43.058.023 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.542 3.43.058.049 I slot launch_slot_: id 2 | task 2120 | processing task, is_child = 0 3.43.508.520 I slot print_timing: id 1 | task 2021 | n_gen = 100, tg = 20.84 t/s, tg_3s = 21.05 t/s 3.43.557.451 I slot print_timing: id 3 | task 1208 | n_gen = 906, tg = 21.95 t/s, tg_3s = 21.12 t/s 3.43.595.622 I slot print_timing: id 0 | task 2024 | n_gen = 100, tg = 21.89 t/s, tg_3s = 22.12 t/s 3.45.930.809 I slot print_timing: id 1 | task 2021 | prompt eval time = 349.24 ms / 98 tokens ( 3.56 ms per token, 280.61 tokens per second) 3.45.930.813 I slot print_timing: id 1 | task 2021 | eval time = 7173.85 ms / 157 tokens ( 45.99 ms per token, 21.75 tokens per second) 3.45.930.814 I slot print_timing: id 1 | task 2021 | total time = 7523.09 ms / 255 tokens 3.45.930.814 I slot print_timing: id 1 | task 2021 | graphs reused = 1712 3.45.930.815 I slot print_timing: id 1 | task 2021 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.930.869 I slot release: id 1 | task 2021 | stop processing: n_tokens = 1368, truncated = 0 3.45.995.316 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.815 3.45.995.340 I slot launch_slot_: id 1 | task 2183 | processing task, is_child = 0 3.46.574.454 I slot print_timing: id 3 | task 1208 | n_gen = 968, tg = 21.85 t/s, tg_3s = 20.55 t/s 3.46.612.099 I slot print_timing: id 0 | task 2024 | n_gen = 162, tg = 21.36 t/s, tg_3s = 20.55 t/s 3.48.028.373 I slot print_timing: id 2 | task 2120 | n_gen = 100, tg = 21.50 t/s, tg_3s = 21.72 t/s 3.48.194.200 I slot print_timing: id 0 | task 2024 | prompt eval time = 314.83 ms / 71 tokens ( 4.43 ms per token, 225.52 tokens per second) 3.48.194.204 I slot print_timing: id 0 | task 2024 | eval time = 9120.23 ms / 199 tokens ( 46.06 ms per token, 21.71 tokens per second) 3.48.194.205 I slot print_timing: id 0 | task 2024 | total time = 9435.06 ms / 270 tokens 3.48.194.206 I slot print_timing: id 0 | task 2024 | graphs reused = 1752 3.48.194.206 I slot print_timing: id 0 | task 2024 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.194.259 I slot release: id 0 | task 2024 | stop processing: n_tokens = 1384, truncated = 0 3.48.239.865 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.806 3.48.239.889 I slot launch_slot_: id 0 | task 2228 | processing task, is_child = 0 3.49.258.751 I slot print_timing: id 3 | task 1208 | prompt eval time = 376.27 ms / 105 tokens ( 3.58 ms per token, 279.06 tokens per second) 3.49.258.755 I slot print_timing: id 3 | task 1208 | eval time = 46935.01 ms / 1024 tokens ( 45.88 ms per token, 21.80 tokens per second) 3.49.258.756 I slot print_timing: id 3 | task 1208 | total time = 47311.28 ms / 1129 tokens 3.49.258.757 I slot print_timing: id 3 | task 1208 | graphs reused = 1767 3.49.258.757 I slot print_timing: id 3 | task 1208 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.258.815 I slot release: id 3 | task 1208 | stop processing: n_tokens = 2244, truncated = 0 3.49.299.618 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.497 3.49.337.658 I slot launch_slot_: id 3 | task 2247 | processing task, is_child = 0 3.51.050.277 I slot print_timing: id 2 | task 2120 | n_gen = 158, tg = 20.59 t/s, tg_3s = 19.19 t/s 3.51.216.839 I slot print_timing: id 1 | task 2183 | n_gen = 100, tg = 20.72 t/s, tg_3s = 20.93 t/s 3.51.980.097 I slot print_timing: id 2 | task 2120 | prompt eval time = 366.71 ms / 91 tokens ( 4.03 ms per token, 248.15 tokens per second) 3.51.980.102 I slot print_timing: id 2 | task 2120 | eval time = 8555.33 ms / 180 tokens ( 47.80 ms per token, 20.92 tokens per second) 3.51.980.103 I slot print_timing: id 2 | task 2120 | total time = 8922.04 ms / 271 tokens 3.51.980.103 I slot print_timing: id 2 | task 2120 | graphs reused = 1820 3.51.980.104 I slot print_timing: id 2 | task 2120 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.980.157 I slot release: id 2 | task 2120 | stop processing: n_tokens = 1384, truncated = 0 3.52.042.765 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.806 3.52.042.788 I slot launch_slot_: id 2 | task 2306 | processing task, is_child = 0 3.53.429.501 I slot print_timing: id 0 | task 2228 | n_gen = 100, tg = 20.54 t/s, tg_3s = 20.75 t/s 3.54.189.437 I slot print_timing: id 3 | task 2247 | n_gen = 100, tg = 21.87 t/s, tg_3s = 22.09 t/s 3.54.228.355 I slot print_timing: id 1 | task 2183 | n_gen = 163, tg = 20.80 t/s, tg_3s = 20.92 t/s 3.54.861.768 I slot print_timing: id 3 | task 2247 | prompt eval time = 324.16 ms / 94 tokens ( 3.45 ms per token, 289.98 tokens per second) 3.54.861.771 I slot print_timing: id 3 | task 2247 | eval time = 5199.93 ms / 116 tokens ( 45.22 ms per token, 22.12 tokens per second) 3.54.861.772 I slot print_timing: id 3 | task 2247 | total time = 5524.09 ms / 210 tokens 3.54.861.772 I slot print_timing: id 3 | task 2247 | graphs reused = 1875 3.54.861.773 I slot print_timing: id 3 | task 2247 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.861.824 I slot release: id 3 | task 2247 | stop processing: n_tokens = 1324, truncated = 0 3.54.902.300 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.842 3.54.902.322 I slot launch_slot_: id 3 | task 2367 | processing task, is_child = 0 3.56.458.620 I slot print_timing: id 0 | task 2228 | n_gen = 165, tg = 20.89 t/s, tg_3s = 21.46 t/s 3.56.924.706 I slot print_timing: id 2 | task 2306 | n_gen = 100, tg = 22.16 t/s, tg_3s = 22.38 t/s 3.57.260.054 I slot print_timing: id 1 | task 2183 | n_gen = 228, tg = 20.98 t/s, tg_3s = 21.44 t/s 3.58.185.332 I slot print_timing: id 0 | task 2228 | prompt eval time = 369.90 ms / 106 tokens ( 3.49 ms per token, 286.57 tokens per second) 3.58.185.335 I slot print_timing: id 0 | task 2228 | eval time = 9575.54 ms / 206 tokens ( 46.71 ms per token, 21.41 tokens per second) 3.58.185.337 I slot print_timing: id 0 | task 2228 | total time = 9945.44 ms / 312 tokens 3.58.185.337 I slot print_timing: id 0 | task 2228 | graphs reused = 1943 3.58.185.338 I slot print_timing: id 0 | task 2228 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.185.394 I slot release: id 0 | task 2228 | stop processing: n_tokens = 1426, truncated = 0 3.58.230.991 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.782 3.58.231.016 I slot launch_slot_: id 0 | task 2440 | processing task, is_child = 0 3.59.691.791 I slot print_timing: id 3 | task 2367 | n_gen = 100, tg = 22.44 t/s, tg_3s = 22.67 t/s 3.59.943.690 I slot print_timing: id 2 | task 2306 | n_gen = 166, tg = 22.04 t/s, tg_3s = 21.86 t/s 4.00.279.842 I slot print_timing: id 1 | task 2183 | n_gen = 294, tg = 21.17 t/s, tg_3s = 21.86 t/s 4.02.722.392 I slot print_timing: id 0 | task 2440 | n_gen = 100, tg = 23.70 t/s, tg_3s = 23.94 t/s 4.02.727.103 I slot print_timing: id 3 | task 2367 | n_gen = 172, tg = 22.96 t/s, tg_3s = 23.72 t/s 4.02.977.879 I slot print_timing: id 2 | task 2306 | n_gen = 238, tg = 22.53 t/s, tg_3s = 23.73 t/s 4.03.059.114 I slot print_timing: id 0 | task 2440 | prompt eval time = 313.90 ms / 71 tokens ( 4.42 ms per token, 226.18 tokens per second) 4.03.059.122 I slot print_timing: id 0 | task 2440 | eval time = 4514.19 ms / 108 tokens ( 42.19 ms per token, 23.70 tokens per second) 4.03.059.122 I slot print_timing: id 0 | task 2440 | total time = 4828.09 ms / 179 tokens 4.03.059.123 I slot print_timing: id 0 | task 2440 | graphs reused = 2049 4.03.059.123 I slot print_timing: id 0 | task 2440 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.059.175 I slot release: id 0 | task 2440 | stop processing: n_tokens = 1293, truncated = 0 4.03.104.764 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.862 4.03.104.787 I slot launch_slot_: id 0 | task 2551 | processing task, is_child = 0 4.03.345.523 I slot print_timing: id 1 | task 2183 | n_gen = 362, tg = 21.35 t/s, tg_3s = 22.18 t/s 4.05.753.384 I slot print_timing: id 3 | task 2367 | n_gen = 238, tg = 22.63 t/s, tg_3s = 21.81 t/s 4.06.005.425 I slot print_timing: id 2 | task 2306 | n_gen = 304, tg = 22.36 t/s, tg_3s = 21.80 t/s 4.06.384.685 I slot print_timing: id 1 | task 2183 | n_gen = 433, tg = 21.66 t/s, tg_3s = 23.36 t/s 4.07.059.352 I slot print_timing: id 0 | task 2551 | prompt eval time = 316.53 ms / 81 tokens ( 3.91 ms per token, 255.90 tokens per second) 4.07.059.358 I slot print_timing: id 0 | task 2551 | eval time = 3638.02 ms / 87 tokens ( 42.30 ms per token, 23.64 tokens per second) 4.07.059.359 I slot print_timing: id 0 | task 2551 | total time = 3954.56 ms / 168 tokens 4.07.059.359 I slot print_timing: id 0 | task 2551 | graphs reused = 2135 4.07.059.360 I slot print_timing: id 0 | task 2551 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.059.415 I slot release: id 0 | task 2551 | stop processing: n_tokens = 1282, truncated = 0 4.07.104.981 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.870 4.07.105.003 I slot launch_slot_: id 0 | task 2641 | processing task, is_child = 0 4.08.229.127 I slot print_timing: id 3 | task 2367 | prompt eval time = 377.97 ms / 115 tokens ( 3.29 ms per token, 304.26 tokens per second) 4.08.229.134 I slot print_timing: id 3 | task 2367 | eval time = 12948.83 ms / 291 tokens ( 44.65 ms per token, 22.40 tokens per second) 4.08.229.134 I slot print_timing: id 3 | task 2367 | total time = 13326.80 ms / 406 tokens 4.08.229.135 I slot print_timing: id 3 | task 2367 | graphs reused = 2154 4.08.229.135 I slot print_timing: id 3 | task 2367 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.229.198 I slot release: id 3 | task 2367 | stop processing: n_tokens = 1519, truncated = 0 4.08.270.013 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.734 4.08.270.037 I slot launch_slot_: id 3 | task 2664 | processing task, is_child = 0 4.09.016.986 I slot print_timing: id 2 | task 2306 | n_gen = 364, tg = 21.92 t/s, tg_3s = 19.92 t/s 4.09.395.882 I slot print_timing: id 1 | task 2183 | n_gen = 493, tg = 21.43 t/s, tg_3s = 19.93 t/s 4.11.844.906 I slot print_timing: id 0 | task 2641 | n_gen = 100, tg = 22.37 t/s, tg_3s = 22.60 t/s 4.12.018.252 I slot print_timing: id 2 | task 2306 | n_gen = 435, tg = 22.19 t/s, tg_3s = 23.66 t/s 4.12.146.394 I slot print_timing: id 3 | task 2664 | prompt eval time = 323.24 ms / 77 tokens ( 4.20 ms per token, 238.21 tokens per second) 4.12.146.401 I slot print_timing: id 3 | task 2664 | eval time = 3553.11 ms / 85 tokens ( 42.30 ms per token, 23.64 tokens per second) 4.12.146.401 I slot print_timing: id 3 | task 2664 | total time = 3876.35 ms / 162 tokens 4.12.146.402 I slot print_timing: id 3 | task 2664 | graphs reused = 2236 4.12.146.402 I slot print_timing: id 3 | task 2664 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.146.459 I slot release: id 3 | task 2664 | stop processing: n_tokens = 1276, truncated = 0 4.12.187.089 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.874 4.12.187.112 I slot launch_slot_: id 3 | task 2752 | processing task, is_child = 0 4.12.431.645 I slot print_timing: id 1 | task 2183 | n_gen = 560, tg = 21.51 t/s, tg_3s = 22.07 t/s 4.13.310.513 I slot print_timing: id 0 | task 2641 | prompt eval time = 314.52 ms / 74 tokens ( 4.25 ms per token, 235.28 tokens per second) 4.13.310.522 I slot print_timing: id 0 | task 2641 | eval time = 5890.98 ms / 129 tokens ( 46.02 ms per token, 21.73 tokens per second) 4.13.310.523 I slot print_timing: id 0 | task 2641 | total time = 6205.50 ms / 203 tokens 4.13.310.524 I slot print_timing: id 0 | task 2641 | graphs reused = 2254 4.13.310.524 I slot print_timing: id 0 | task 2641 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.310.578 I slot release: id 0 | task 2641 | stop processing: n_tokens = 1317, truncated = 0 4.13.355.998 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.847 4.13.356.021 I slot launch_slot_: id 0 | task 2775 | processing task, is_child = 0 4.15.031.759 I slot print_timing: id 2 | task 2306 | n_gen = 495, tg = 21.88 t/s, tg_3s = 19.91 t/s 4.15.453.301 I slot print_timing: id 1 | task 2183 | n_gen = 625, tg = 21.51 t/s, tg_3s = 21.51 t/s 4.16.341.509 I slot print_timing: id 1 | task 2183 | prompt eval time = 442.90 ms / 125 tokens ( 3.54 ms per token, 282.23 tokens per second) 4.16.341.516 I slot print_timing: id 1 | task 2183 | eval time = 29903.26 ms / 646 tokens ( 46.36 ms per token, 21.57 tokens per second) 4.16.341.517 I slot print_timing: id 1 | task 2183 | total time = 30346.16 ms / 771 tokens 4.16.341.517 I slot print_timing: id 1 | task 2183 | graphs reused = 2317 4.16.341.518 I slot print_timing: id 1 | task 2183 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.341.577 I slot release: id 1 | task 2183 | stop processing: n_tokens = 1885, truncated = 0 4.16.405.594 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.592 4.16.405.616 I slot launch_slot_: id 1 | task 2842 | processing task, is_child = 0 4.17.309.543 I slot print_timing: id 3 | task 2752 | n_gen = 100, tg = 20.62 t/s, tg_3s = 20.83 t/s 4.18.067.128 I slot print_timing: id 2 | task 2306 | n_gen = 558, tg = 21.75 t/s, tg_3s = 20.76 t/s 4.18.232.435 I slot print_timing: id 0 | task 2775 | prompt eval time = 317.84 ms / 97 tokens ( 3.28 ms per token, 305.18 tokens per second) 4.18.232.439 I slot print_timing: id 0 | task 2775 | eval time = 4558.56 ms / 100 tokens ( 46.05 ms per token, 21.72 tokens per second) 4.18.232.440 I slot print_timing: id 0 | task 2775 | total time = 4876.40 ms / 197 tokens 4.18.232.440 I slot print_timing: id 0 | task 2775 | graphs reused = 2349 4.18.232.441 I slot print_timing: id 0 | task 2775 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.232.499 I slot release: id 0 | task 2775 | stop processing: n_tokens = 1311, truncated = 0 4.18.277.939 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.850 4.18.277.961 I slot launch_slot_: id 0 | task 2879 | processing task, is_child = 0 4.18.767.954 I slot print_timing: id 3 | task 2752 | prompt eval time = 321.37 ms / 86 tokens ( 3.74 ms per token, 267.60 tokens per second) 4.18.767.959 I slot print_timing: id 3 | task 2752 | eval time = 6259.46 ms / 129 tokens ( 48.90 ms per token, 20.45 tokens per second) 4.18.767.959 I slot print_timing: id 3 | task 2752 | total time = 6580.83 ms / 215 tokens 4.18.767.960 I slot print_timing: id 3 | task 2752 | graphs reused = 2353 4.18.767.961 I slot print_timing: id 3 | task 2752 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.768.028 I slot release: id 3 | task 2752 | stop processing: n_tokens = 1329, truncated = 0 4.18.809.769 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.839 4.18.809.791 I slot launch_slot_: id 3 | task 2887 | processing task, is_child = 0 4.21.068.644 I slot print_timing: id 2 | task 2306 | n_gen = 619, tg = 21.60 t/s, tg_3s = 20.32 t/s 4.21.446.758 I slot print_timing: id 1 | task 2842 | n_gen = 100, tg = 21.47 t/s, tg_3s = 21.69 t/s 4.21.577.933 I slot print_timing: id 3 | task 2887 | prompt eval time = 270.52 ms / 65 tokens ( 4.16 ms per token, 240.28 tokens per second) 4.21.577.940 I slot print_timing: id 3 | task 2887 | eval time = 2497.62 ms / 60 tokens ( 42.33 ms per token, 23.62 tokens per second) 4.21.577.940 I slot print_timing: id 3 | task 2887 | total time = 2768.13 ms / 125 tokens 4.21.577.941 I slot print_timing: id 3 | task 2887 | graphs reused = 2410 4.21.577.941 I slot print_timing: id 3 | task 2887 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.577.997 I slot release: id 3 | task 2887 | stop processing: n_tokens = 1239, truncated = 0 4.21.618.893 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.900 4.21.618.916 I slot launch_slot_: id 3 | task 2950 | processing task, is_child = 0 4.23.204.314 I slot print_timing: id 0 | task 2879 | n_gen = 100, tg = 21.47 t/s, tg_3s = 21.69 t/s 4.24.093.556 I slot print_timing: id 2 | task 2306 | n_gen = 685, tg = 21.62 t/s, tg_3s = 21.82 t/s 4.24.472.102 I slot print_timing: id 1 | task 2842 | n_gen = 166, tg = 21.61 t/s, tg_3s = 21.82 t/s 4.25.230.091 I slot print_timing: id 1 | task 2842 | prompt eval time = 430.07 ms / 102 tokens ( 4.22 ms per token, 237.17 tokens per second) 4.25.230.098 I slot print_timing: id 1 | task 2842 | eval time = 8394.40 ms / 184 tokens ( 45.87 ms per token, 21.80 tokens per second) 4.25.230.099 I slot print_timing: id 1 | task 2842 | total time = 8824.47 ms / 286 tokens 4.25.230.099 I slot print_timing: id 1 | task 2842 | graphs reused = 2487 4.25.230.100 I slot print_timing: id 1 | task 2842 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.230.157 I slot release: id 1 | task 2842 | stop processing: n_tokens = 1399, truncated = 0 4.25.294.658 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.797 4.25.294.682 I slot launch_slot_: id 1 | task 3032 | processing task, is_child = 0 4.26.231.170 I slot print_timing: id 0 | task 2879 | prompt eval time = 316.12 ms / 86 tokens ( 3.68 ms per token, 272.05 tokens per second) 4.26.231.177 I slot print_timing: id 0 | task 2879 | eval time = 7637.08 ms / 164 tokens ( 46.85 ms per token, 21.34 tokens per second) 4.26.231.177 I slot print_timing: id 0 | task 2879 | total time = 7953.20 ms / 250 tokens 4.26.231.178 I slot print_timing: id 0 | task 2879 | graphs reused = 2499 4.26.231.178 I slot print_timing: id 0 | task 2879 | graph reallocs = 0 / 0 (same size) / (changed size) 4.26.231.233 I slot release: id 0 | task 2879 | stop processing: n_tokens = 1364, truncated = 0 4.26.276.812 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.817 4.26.276.833 I slot launch_slot_: id 0 | task 3049 | processing task, is_child = 0 4.26.621.528 I slot print_timing: id 3 | task 2950 | n_gen = 100, tg = 21.14 t/s, tg_3s = 21.36 t/s 4.27.132.946 I slot print_timing: id 2 | task 2306 | n_gen = 745, tg = 21.46 t/s, tg_3s = 19.74 t/s 4.28.697.406 I slot print_timing: id 3 | task 2950 | prompt eval time = 320.03 ms / 81 tokens ( 3.95 ms per token, 253.10 tokens per second) 4.28.697.409 I slot print_timing: id 3 | task 2950 | eval time = 6758.46 ms / 149 tokens ( 45.67 ms per token, 21.90 tokens per second) 4.28.697.410 I slot print_timing: id 3 | task 2950 | total time = 7078.48 ms / 230 tokens 4.28.697.411 I slot print_timing: id 3 | task 2950 | graphs reused = 2550 4.28.697.411 I slot print_timing: id 3 | task 2950 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.697.469 I slot release: id 3 | task 2950 | stop processing: n_tokens = 1344, truncated = 0 4.28.738.185 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.830 4.28.738.207 I slot launch_slot_: id 3 | task 3104 | processing task, is_child = 0 4.30.162.671 I slot print_timing: id 2 | task 2306 | n_gen = 811, tg = 21.48 t/s, tg_3s = 21.78 t/s 4.30.287.851 I slot print_timing: id 1 | task 3032 | n_gen = 100, tg = 21.48 t/s, tg_3s = 21.70 t/s 4.30.961.922 I slot print_timing: id 0 | task 3049 | n_gen = 100, tg = 22.37 t/s, tg_3s = 22.60 t/s 4.31.597.855 I slot print_timing: id 1 | task 3032 | prompt eval time = 384.36 ms / 73 tokens ( 5.27 ms per token, 189.92 tokens per second) 4.31.597.862 I slot print_timing: id 1 | task 3032 | eval time = 5918.80 ms / 131 tokens ( 45.53 ms per token, 21.96 tokens per second) 4.31.597.862 I slot print_timing: id 1 | task 3032 | total time = 6303.17 ms / 204 tokens 4.31.597.863 I slot print_timing: id 1 | task 3032 | graphs reused = 2608 4.31.597.863 I slot print_timing: id 1 | task 3032 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.597.943 I slot release: id 1 | task 3032 | stop processing: n_tokens = 1318, truncated = 0 4.31.662.235 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.846 4.31.662.262 I slot launch_slot_: id 1 | task 3168 | processing task, is_child = 0 4.32.722.154 I slot print_timing: id 0 | task 3049 | prompt eval time = 259.65 ms / 66 tokens ( 3.93 ms per token, 254.19 tokens per second) 4.32.722.162 I slot print_timing: id 0 | task 3049 | eval time = 6185.66 ms / 134 tokens ( 46.51 ms per token, 21.50 tokens per second) 4.32.722.162 I slot print_timing: id 0 | task 3049 | total time = 6445.31 ms / 200 tokens 4.32.722.163 I slot print_timing: id 0 | task 3049 | graphs reused = 2623 4.32.722.163 I slot print_timing: id 0 | task 3049 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.722.218 I slot release: id 0 | task 3049 | stop processing: n_tokens = 1314, truncated = 0 4.32.767.952 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.849 4.32.767.978 I slot launch_slot_: id 0 | task 3188 | processing task, is_child = 0 4.33.166.117 I slot print_timing: id 2 | task 2306 | n_gen = 869, tg = 21.32 t/s, tg_3s = 19.31 t/s 4.33.641.083 I slot print_timing: id 3 | task 3104 | prompt eval time = 323.56 ms / 96 tokens ( 3.37 ms per token, 296.70 tokens per second) 4.33.641.087 I slot print_timing: id 3 | task 3104 | eval time = 4579.31 ms / 96 tokens ( 48.20 ms per token, 20.75 tokens per second) 4.33.641.088 I slot print_timing: id 3 | task 3104 | total time = 4902.87 ms / 192 tokens 4.33.641.089 I slot print_timing: id 3 | task 3104 | graphs reused = 2636 4.33.641.089 I slot print_timing: id 3 | task 3104 | graph reallocs = 0 / 0 (same size) / (changed size) 4.33.641.154 I slot release: id 3 | task 3104 | stop processing: n_tokens = 1306, truncated = 0 4.33.681.845 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.854 4.33.681.870 I slot launch_slot_: id 3 | task 3205 | processing task, is_child = 0 4.36.183.303 I slot print_timing: id 2 | task 2306 | n_gen = 933, tg = 21.31 t/s, tg_3s = 21.21 t/s 4.36.392.272 I slot print_timing: id 0 | task 3188 | prompt eval time = 314.07 ms / 70 tokens ( 4.49 ms per token, 222.88 tokens per second) 4.36.392.276 I slot print_timing: id 0 | task 3188 | eval time = 3310.22 ms / 72 tokens ( 46.62 ms per token, 21.45 tokens per second) 4.36.392.276 I slot print_timing: id 0 | task 3188 | total time = 3624.29 ms / 142 tokens 4.36.392.277 I slot print_timing: id 0 | task 3188 | graphs reused = 2690 4.36.392.278 I slot print_timing: id 0 | task 3188 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.392.338 I slot release: id 0 | task 3188 | stop processing: n_tokens = 1256, truncated = 0 4.36.437.967 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.888 4.36.437.990 I slot launch_slot_: id 0 | task 3264 | processing task, is_child = 0 4.37.013.028 I slot print_timing: id 1 | task 3168 | n_gen = 100, tg = 19.90 t/s, tg_3s = 20.10 t/s 4.37.311.116 I slot print_timing: id 1 | task 3168 | prompt eval time = 376.36 ms / 84 tokens ( 4.48 ms per token, 223.19 tokens per second) 4.37.311.123 I slot print_timing: id 1 | task 3168 | eval time = 5272.49 ms / 107 tokens ( 49.74 ms per token, 20.10 tokens per second) 4.37.311.124 I slot print_timing: id 1 | task 3168 | total time = 5648.85 ms / 191 tokens 4.37.311.124 I slot print_timing: id 1 | task 3168 | graphs reused = 2703 4.37.311.125 I slot print_timing: id 1 | task 3168 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.311.179 I slot release: id 1 | task 3168 | stop processing: n_tokens = 1305, truncated = 0 4.37.375.825 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.854 4.37.375.852 I slot launch_slot_: id 1 | task 3281 | processing task, is_child = 0 4.38.747.856 I slot print_timing: id 2 | task 2306 | prompt eval time = 414.02 ms / 103 tokens ( 4.02 ms per token, 248.78 tokens per second) 4.38.747.860 I slot print_timing: id 2 | task 2306 | eval time = 46291.04 ms / 979 tokens ( 47.33 ms per token, 21.13 tokens per second) 4.38.747.860 I slot print_timing: id 2 | task 2306 | total time = 46705.06 ms / 1082 tokens 4.38.747.861 I slot print_timing: id 2 | task 2306 | graphs reused = 2724 4.38.747.862 I slot print_timing: id 2 | task 2306 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.747.915 I slot release: id 2 | task 2306 | stop processing: n_tokens = 2196, truncated = 0 4.38.809.749 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.508 4.38.809.770 I slot launch_slot_: id 2 | task 3307 | processing task, is_child = 0 4.39.175.470 I slot print_timing: id 3 | task 3205 | n_gen = 100, tg = 19.35 t/s, tg_3s = 19.55 t/s 4.41.614.272 I slot print_timing: id 0 | task 3264 | n_gen = 100, tg = 20.37 t/s, tg_3s = 20.58 t/s 4.42.208.728 I slot print_timing: id 3 | task 3205 | n_gen = 172, tg = 20.99 t/s, tg_3s = 23.74 t/s 4.42.290.073 I slot print_timing: id 1 | task 3281 | n_gen = 100, tg = 22.10 t/s, tg_3s = 22.32 t/s 4.43.344.179 I slot print_timing: id 2 | task 3307 | n_gen = 100, tg = 23.74 t/s, tg_3s = 23.98 t/s 4.43.889.219 I slot print_timing: id 0 | task 3264 | prompt eval time = 316.80 ms / 88 tokens ( 3.60 ms per token, 277.78 tokens per second) 4.43.889.223 I slot print_timing: id 0 | task 3264 | eval time = 7134.43 ms / 154 tokens ( 46.63 ms per token, 21.45 tokens per second) 4.43.889.224 I slot print_timing: id 0 | task 3264 | total time = 7451.22 ms / 242 tokens 4.43.889.224 I slot print_timing: id 0 | task 3264 | graphs reused = 2834 4.43.889.225 I slot print_timing: id 0 | task 3264 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.889.278 I slot release: id 0 | task 3264 | stop processing: n_tokens = 1356, truncated = 0 4.43.934.442 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.822 4.43.934.465 I slot launch_slot_: id 0 | task 3423 | processing task, is_child = 0 4.45.212.301 I slot print_timing: id 3 | task 3205 | n_gen = 236, tg = 21.07 t/s, tg_3s = 21.31 t/s 4.45.293.720 I slot print_timing: id 1 | task 3281 | n_gen = 164, tg = 21.78 t/s, tg_3s = 21.31 t/s 4.45.379.620 I slot print_timing: id 2 | task 3307 | prompt eval time = 364.64 ms / 94 tokens ( 3.88 ms per token, 257.79 tokens per second) 4.45.379.628 I slot print_timing: id 2 | task 3307 | eval time = 6205.20 ms / 141 tokens ( 44.32 ms per token, 22.56 tokens per second) 4.45.379.628 I slot print_timing: id 2 | task 3307 | total time = 6569.84 ms / 235 tokens 4.45.379.629 I slot print_timing: id 2 | task 3307 | graphs reused = 2859 4.45.379.630 I slot print_timing: id 2 | task 3307 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.379.688 I slot release: id 2 | task 3307 | stop processing: n_tokens = 1348, truncated = 0 4.45.442.269 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.827 4.45.442.292 I slot launch_slot_: id 2 | task 3452 | processing task, is_child = 0 4.48.247.828 I slot print_timing: id 3 | task 3205 | n_gen = 302, tg = 21.22 t/s, tg_3s = 21.74 t/s 4.48.330.531 I slot print_timing: id 1 | task 3281 | n_gen = 230, tg = 21.77 t/s, tg_3s = 21.73 t/s 4.48.501.064 I slot print_timing: id 2 | task 3452 | prompt eval time = 312.53 ms / 57 tokens ( 5.48 ms per token, 182.38 tokens per second) 4.48.501.069 I slot print_timing: id 2 | task 3452 | eval time = 2746.24 ms / 66 tokens ( 42.25 ms per token, 23.67 tokens per second) 4.48.501.069 I slot print_timing: id 2 | task 3452 | total time = 3058.76 ms / 123 tokens 4.48.501.070 I slot print_timing: id 2 | task 3452 | graphs reused = 2922 4.48.501.070 I slot print_timing: id 2 | task 3452 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.501.125 I slot release: id 2 | task 3452 | stop processing: n_tokens = 1237, truncated = 0 4.48.563.660 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.901 4.48.563.683 I slot launch_slot_: id 2 | task 3521 | processing task, is_child = 0 4.48.968.033 I slot print_timing: id 3 | task 3205 | prompt eval time = 378.51 ms / 119 tokens ( 3.18 ms per token, 314.39 tokens per second) 4.48.968.037 I slot print_timing: id 3 | task 3205 | eval time = 14907.65 ms / 312 tokens ( 47.93 ms per token, 20.86 tokens per second) 4.48.968.038 I slot print_timing: id 3 | task 3205 | total time = 15286.16 ms / 431 tokens 4.48.968.038 I slot print_timing: id 3 | task 3205 | graphs reused = 2922 4.48.968.039 I slot print_timing: id 3 | task 3205 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.968.092 I slot release: id 3 | task 3205 | stop processing: n_tokens = 1545, truncated = 0 4.49.009.937 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.722 4.49.009.967 I slot launch_slot_: id 3 | task 3526 | processing task, is_child = 0 4.49.255.533 I slot print_timing: id 0 | task 3423 | n_gen = 100, tg = 20.03 t/s, tg_3s = 20.23 t/s 4.51.354.441 I slot print_timing: id 1 | task 3281 | n_gen = 289, tg = 21.26 t/s, tg_3s = 19.51 t/s 4.52.284.899 I slot print_timing: id 0 | task 3423 | n_gen = 171, tg = 21.32 t/s, tg_3s = 23.44 t/s 4.52.498.669 I slot print_timing: id 2 | task 3521 | prompt eval time = 360.69 ms / 79 tokens ( 4.57 ms per token, 219.02 tokens per second) 4.52.498.673 I slot print_timing: id 2 | task 3521 | eval time = 3574.29 ms / 80 tokens ( 45.24 ms per token, 22.10 tokens per second) 4.52.498.674 I slot print_timing: id 2 | task 3521 | total time = 3934.98 ms / 159 tokens 4.52.498.674 I slot print_timing: id 2 | task 3521 | graphs reused = 2995 4.52.498.675 I slot print_timing: id 2 | task 3521 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.498.729 I slot release: id 2 | task 3521 | stop processing: n_tokens = 1273, truncated = 0 4.52.561.107 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.876 4.52.561.132 I slot launch_slot_: id 2 | task 3605 | processing task, is_child = 0 4.53.812.987 I slot print_timing: id 1 | task 3281 | prompt eval time = 433.86 ms / 133 tokens ( 3.26 ms per token, 306.55 tokens per second) 4.53.812.991 I slot print_timing: id 1 | task 3281 | eval time = 16003.26 ms / 340 tokens ( 47.21 ms per token, 21.18 tokens per second) 4.53.812.992 I slot print_timing: id 1 | task 3281 | total time = 16437.12 ms / 473 tokens 4.53.812.993 I slot print_timing: id 1 | task 3281 | graphs reused = 3015 4.53.812.993 I slot print_timing: id 1 | task 3281 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.813.049 I slot release: id 1 | task 3281 | stop processing: n_tokens = 1587, truncated = 0 4.53.816.090 I slot print_timing: id 3 | task 3526 | n_gen = 100, tg = 22.09 t/s, tg_3s = 22.31 t/s 4.53.876.945 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.703 4.53.876.969 I slot launch_slot_: id 1 | task 3630 | processing task, is_child = 0 4.55.124.250 I slot print_timing: id 3 | task 3526 | prompt eval time = 324.09 ms / 101 tokens ( 3.21 ms per token, 311.64 tokens per second) 4.55.124.257 I slot print_timing: id 3 | task 3526 | eval time = 5790.18 ms / 122 tokens ( 47.85 ms per token, 20.90 tokens per second) 4.55.124.257 I slot print_timing: id 3 | task 3526 | total time = 6114.28 ms / 223 tokens 4.55.124.258 I slot print_timing: id 3 | task 3526 | graphs reused = 3033 4.55.124.258 I slot print_timing: id 3 | task 3526 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.124.311 I slot release: id 3 | task 3526 | stop processing: n_tokens = 1337, truncated = 0 4.55.164.746 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.834 4.55.164.773 I slot launch_slot_: id 3 | task 3653 | processing task, is_child = 0 4.55.413.463 I slot print_timing: id 0 | task 3423 | n_gen = 224, tg = 20.09 t/s, tg_3s = 16.94 t/s 4.57.738.108 I slot print_timing: id 2 | task 3605 | n_gen = 100, tg = 20.55 t/s, tg_3s = 20.76 t/s 4.58.452.591 I slot print_timing: id 0 | task 3423 | n_gen = 295, tg = 20.79 t/s, tg_3s = 23.36 t/s 4.58.749.302 I slot print_timing: id 1 | task 3630 | n_gen = 100, tg = 22.33 t/s, tg_3s = 22.56 t/s 4.59.680.398 I slot print_timing: id 3 | task 3653 | n_gen = 100, tg = 23.69 t/s, tg_3s = 23.93 t/s 5.00.014.430 I slot print_timing: id 1 | task 3630 | prompt eval time = 439.27 ms / 103 tokens ( 4.26 ms per token, 234.48 tokens per second) 5.00.014.433 I slot print_timing: id 1 | task 3630 | eval time = 5698.18 ms / 130 tokens ( 44.17 ms per token, 22.64 tokens per second) 5.00.014.434 I slot print_timing: id 1 | task 3630 | total time = 6137.45 ms / 233 tokens 5.00.014.435 I slot print_timing: id 1 | task 3630 | graphs reused = 3138 5.00.014.435 I slot print_timing: id 1 | task 3630 | graph reallocs = 0 / 0 (same size) / (changed size) 5.00.014.492 I slot release: id 1 | task 3630 | stop processing: n_tokens = 1347, truncated = 0 5.00.078.816 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.828 5.00.078.843 I slot launch_slot_: id 1 | task 3764 | processing task, is_child = 0 5.00.763.202 I slot print_timing: id 2 | task 3605 | n_gen = 164, tg = 20.79 t/s, tg_3s = 21.16 t/s 5.01.476.404 I slot print_timing: id 0 | task 3423 | n_gen = 359, tg = 20.86 t/s, tg_3s = 21.17 t/s 5.02.703.043 I slot print_timing: id 3 | task 3653 | n_gen = 164, tg = 22.63 t/s, tg_3s = 21.17 t/s 5.03.798.101 I slot print_timing: id 2 | task 3605 | n_gen = 236, tg = 21.61 t/s, tg_3s = 23.72 t/s 5.04.094.104 I slot print_timing: id 2 | task 3605 | prompt eval time = 360.08 ms / 78 tokens ( 4.62 ms per token, 216.62 tokens per second) 5.04.094.110 I slot print_timing: id 2 | task 3605 | eval time = 11172.89 ms / 243 tokens ( 46.17 ms per token, 21.66 tokens per second) 5.04.094.112 I slot print_timing: id 2 | task 3605 | total time = 11532.97 ms / 321 tokens 5.04.094.113 I slot print_timing: id 2 | task 3605 | graphs reused = 3223 5.04.094.114 I slot print_timing: id 2 | task 3605 | graph reallocs = 0 / 0 (same size) / (changed size) 5.04.094.164 I slot release: id 2 | task 3605 | stop processing: n_tokens = 1435, truncated = 0 5.04.156.574 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.777 5.04.156.599 I slot launch_slot_: id 2 | task 3854 | processing task, is_child = 0 5.04.512.681 I slot print_timing: id 0 | task 3423 | n_gen = 424, tg = 20.94 t/s, tg_3s = 21.41 t/s 5.04.942.438 I slot print_timing: id 1 | task 3764 | n_gen = 100, tg = 22.10 t/s, tg_3s = 22.32 t/s 5.05.704.991 I slot print_timing: id 3 | task 3653 | n_gen = 228, tg = 22.25 t/s, tg_3s = 21.32 t/s 5.06.675.580 I slot print_timing: id 3 | task 3653 | prompt eval time = 336.81 ms / 100 tokens ( 3.37 ms per token, 296.90 tokens per second) 5.06.675.584 I slot print_timing: id 3 | task 3653 | eval time = 11173.99 ms / 251 tokens ( 44.70 ms per token, 22.37 tokens per second) 5.06.675.585 I slot print_timing: id 3 | task 3653 | total time = 11510.80 ms / 351 tokens 5.06.675.585 I slot print_timing: id 3 | task 3653 | graphs reused = 3273 5.06.675.586 I slot print_timing: id 3 | task 3653 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.675.640 I slot release: id 3 | task 3653 | stop processing: n_tokens = 1465, truncated = 0 5.06.714.756 I slot print_timing: id 1 | task 3764 | prompt eval time = 384.22 ms / 83 tokens ( 4.63 ms per token, 216.02 tokens per second) 5.06.714.759 I slot print_timing: id 1 | task 3764 | eval time = 6251.69 ms / 142 tokens ( 44.34 ms per token, 22.55 tokens per second) 5.06.714.760 I slot print_timing: id 1 | task 3764 | total time = 6635.91 ms / 225 tokens 5.06.714.760 I slot print_timing: id 1 | task 3764 | graphs reused = 3273 5.06.714.761 I slot print_timing: id 1 | task 3764 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.714.813 I slot release: id 1 | task 3764 | stop processing: n_tokens = 1339, truncated = 0 5.06.716.283 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.833 5.06.716.305 I slot launch_slot_: id 1 | task 3909 | processing task, is_child = 0 5.06.748.623 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.761 5.06.748.647 I slot launch_slot_: id 3 | task 3910 | processing task, is_child = 0 5.07.546.082 I slot print_timing: id 0 | task 3423 | n_gen = 481, tg = 20.66 t/s, tg_3s = 18.79 t/s 5.08.816.164 I slot print_timing: id 2 | task 3854 | prompt eval time = 358.41 ms / 77 tokens ( 4.65 ms per token, 214.84 tokens per second) 5.08.816.169 I slot print_timing: id 2 | task 3854 | eval time = 4301.15 ms / 88 tokens ( 49.44 ms per token, 20.23 tokens per second) 5.08.816.170 I slot print_timing: id 2 | task 3854 | total time = 4659.56 ms / 165 tokens 5.08.816.170 I slot print_timing: id 2 | task 3854 | graphs reused = 3305 5.08.816.171 I slot print_timing: id 2 | task 3854 | graph reallocs = 0 / 0 (same size) / (changed size) 5.08.816.225 I slot release: id 2 | task 3854 | stop processing: n_tokens = 1279, truncated = 0 5.08.878.601 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.872 5.08.878.627 I slot launch_slot_: id 2 | task 3947 | processing task, is_child = 0 5.10.581.191 I slot print_timing: id 0 | task 3423 | n_gen = 547, tg = 20.79 t/s, tg_3s = 21.75 t/s 5.11.045.642 I slot print_timing: id 1 | task 3909 | prompt eval time = 664.09 ms / 146 tokens ( 4.55 ms per token, 219.85 tokens per second) 5.11.045.646 I slot print_timing: id 1 | task 3909 | eval time = 3632.89 ms / 81 tokens ( 45.41 ms per token, 22.02 tokens per second) 5.11.045.646 I slot print_timing: id 1 | task 3909 | total time = 4296.99 ms / 227 tokens 5.11.045.647 I slot print_timing: id 1 | task 3909 | graphs reused = 3348 5.11.045.647 I slot print_timing: id 1 | task 3909 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.045.708 I slot release: id 1 | task 3909 | stop processing: n_tokens = 1341, truncated = 0 5.11.109.744 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.831 5.11.109.770 I slot launch_slot_: id 1 | task 3995 | processing task, is_child = 0 5.11.872.554 I slot print_timing: id 3 | task 3910 | prompt eval time = 667.47 ms / 67 tokens ( 9.96 ms per token, 100.38 tokens per second) 5.11.872.559 I slot print_timing: id 3 | task 3910 | eval time = 4454.67 ms / 93 tokens ( 48.42 ms per token, 20.65 tokens per second) 5.11.872.560 I slot print_timing: id 3 | task 3910 | total time = 5122.14 ms / 160 tokens 5.11.872.560 I slot print_timing: id 3 | task 3910 | graphs reused = 3356 5.11.872.561 I slot print_timing: id 3 | task 3910 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.872.619 I slot release: id 3 | task 3910 | stop processing: n_tokens = 1274, truncated = 0 5.11.913.527 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.875 5.11.913.548 I slot launch_slot_: id 3 | task 4008 | processing task, is_child = 0 5.12.404.461 I slot print_timing: id 2 | task 3947 | prompt eval time = 308.24 ms / 57 tokens ( 5.41 ms per token, 184.92 tokens per second) 5.12.404.465 I slot print_timing: id 2 | task 3947 | eval time = 3217.58 ms / 64 tokens ( 51.07 ms per token, 19.58 tokens per second) 5.12.404.466 I slot print_timing: id 2 | task 3947 | total time = 3525.82 ms / 121 tokens 5.12.404.466 I slot print_timing: id 2 | task 3947 | graphs reused = 3358 5.12.404.467 I slot print_timing: id 2 | task 3947 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.404.532 I slot release: id 2 | task 3947 | stop processing: n_tokens = 1235, truncated = 0 5.12.468.248 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.903 5.12.468.277 I slot launch_slot_: id 2 | task 4016 | processing task, is_child = 0 5.13.593.110 I slot print_timing: id 0 | task 3423 | n_gen = 598, tg = 20.39 t/s, tg_3s = 16.93 t/s 5.15.618.049 I slot print_timing: id 1 | task 3995 | prompt eval time = 388.60 ms / 89 tokens ( 4.37 ms per token, 229.03 tokens per second) 5.15.618.053 I slot print_timing: id 1 | task 3995 | eval time = 4119.67 ms / 86 tokens ( 48.47 ms per token, 20.63 tokens per second) 5.15.618.054 I slot print_timing: id 1 | task 3995 | total time = 4508.27 ms / 175 tokens 5.15.618.055 I slot print_timing: id 1 | task 3995 | graphs reused = 3423 5.15.618.055 I slot print_timing: id 1 | task 3995 | graph reallocs = 0 / 0 (same size) / (changed size) 5.15.618.113 I slot release: id 1 | task 3995 | stop processing: n_tokens = 1289, truncated = 0 5.15.682.380 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.865 5.15.682.404 I slot launch_slot_: id 1 | task 4086 | processing task, is_child = 0 5.16.319.670 I slot print_timing: id 3 | task 4008 | prompt eval time = 317.61 ms / 71 tokens ( 4.47 ms per token, 223.54 tokens per second) 5.16.319.677 I slot print_timing: id 3 | task 4008 | eval time = 4088.50 ms / 83 tokens ( 49.86 ms per token, 20.06 tokens per second) 5.16.319.677 I slot print_timing: id 3 | task 4008 | total time = 4406.11 ms / 154 tokens 5.16.319.678 I slot print_timing: id 3 | task 4008 | graphs reused = 3428 5.16.319.679 I slot print_timing: id 3 | task 4008 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.319.739 I slot release: id 3 | task 4008 | stop processing: n_tokens = 1268, truncated = 0 5.16.360.577 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.879 5.16.360.606 I slot launch_slot_: id 3 | task 4096 | processing task, is_child = 0 5.16.604.088 I slot print_timing: id 0 | task 3423 | n_gen = 657, tg = 20.32 t/s, tg_3s = 19.59 t/s 5.17.570.964 I slot print_timing: id 2 | task 4016 | n_gen = 100, tg = 20.88 t/s, tg_3s = 21.10 t/s 5.19.636.033 I slot print_timing: id 0 | task 3423 | n_gen = 728, tg = 20.58 t/s, tg_3s = 23.42 t/s 5.20.482.476 I slot print_timing: id 1 | task 4086 | n_gen = 100, tg = 22.37 t/s, tg_3s = 22.59 t/s 5.20.610.261 I slot print_timing: id 2 | task 4016 | n_gen = 172, tg = 21.98 t/s, tg_3s = 23.69 t/s 5.20.865.333 I slot print_timing: id 3 | task 4096 | n_gen = 100, tg = 23.66 t/s, tg_3s = 23.90 t/s 5.21.370.918 I slot print_timing: id 2 | task 4016 | prompt eval time = 362.39 ms / 84 tokens ( 4.31 ms per token, 231.80 tokens per second) 5.21.370.925 I slot print_timing: id 2 | task 4016 | eval time = 8540.25 ms / 190 tokens ( 45.19 ms per token, 22.13 tokens per second) 5.21.370.925 I slot print_timing: id 2 | task 4016 | total time = 8902.63 ms / 274 tokens 5.21.370.926 I slot print_timing: id 2 | task 4016 | graphs reused = 3538 5.21.370.927 I slot print_timing: id 2 | task 4016 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.370.978 I slot release: id 2 | task 4016 | stop processing: n_tokens = 1388, truncated = 0 5.21.432.927 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.803 5.21.432.953 I slot launch_slot_: id 2 | task 4211 | processing task, is_child = 0 5.22.656.175 I slot print_timing: id 0 | task 3423 | n_gen = 792, tg = 20.63 t/s, tg_3s = 21.19 t/s 5.22.910.633 I slot print_timing: id 1 | task 4086 | prompt eval time = 374.25 ms / 72 tokens ( 5.20 ms per token, 192.39 tokens per second) 5.22.910.640 I slot print_timing: id 1 | task 4086 | eval time = 6853.98 ms / 150 tokens ( 46.00 ms per token, 21.74 tokens per second) 5.22.910.641 I slot print_timing: id 1 | task 4086 | total time = 7228.22 ms / 222 tokens 5.22.910.641 I slot print_timing: id 1 | task 4086 | graphs reused = 3563 5.22.910.642 I slot print_timing: id 1 | task 4086 | graph reallocs = 0 / 0 (same size) / (changed size) 5.22.910.691 I slot release: id 1 | task 4086 | stop processing: n_tokens = 1336, truncated = 0 5.22.974.188 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.835 5.22.974.215 I slot launch_slot_: id 1 | task 4241 | processing task, is_child = 0 5.23.880.753 I slot print_timing: id 3 | task 4096 | n_gen = 155, tg = 21.39 t/s, tg_3s = 18.24 t/s 5.24.557.657 I slot print_timing: id 3 | task 4096 | prompt eval time = 321.32 ms / 88 tokens ( 3.65 ms per token, 273.87 tokens per second) 5.24.557.662 I slot print_timing: id 3 | task 4096 | eval time = 7875.73 ms / 171 tokens ( 46.33 ms per token, 21.59 tokens per second) 5.24.557.663 I slot print_timing: id 3 | task 4096 | total time = 8197.05 ms / 259 tokens 5.24.557.663 I slot print_timing: id 3 | task 4096 | graphs reused = 3589 5.24.557.664 I slot print_timing: id 3 | task 4096 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.557.721 I slot release: id 3 | task 4096 | stop processing: n_tokens = 1373, truncated = 0 5.24.598.721 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.812 5.24.598.743 I slot launch_slot_: id 3 | task 4272 | processing task, is_child = 0 5.25.682.228 I slot print_timing: id 0 | task 3423 | n_gen = 849, tg = 20.50 t/s, tg_3s = 18.84 t/s 5.26.619.331 I slot print_timing: id 2 | task 4211 | n_gen = 100, tg = 20.58 t/s, tg_3s = 20.79 t/s 5.27.856.540 I slot print_timing: id 1 | task 4241 | n_gen = 100, tg = 22.24 t/s, tg_3s = 22.46 t/s 5.28.703.270 I slot print_timing: id 0 | task 3423 | n_gen = 920, tg = 20.70 t/s, tg_3s = 23.50 t/s 5.29.004.476 I slot print_timing: id 2 | task 4211 | prompt eval time = 376.68 ms / 94 tokens ( 4.01 ms per token, 249.55 tokens per second) 5.29.004.481 I slot print_timing: id 2 | task 4211 | eval time = 7194.84 ms / 156 tokens ( 46.42 ms per token, 21.54 tokens per second) 5.29.004.482 I slot print_timing: id 2 | task 4211 | total time = 7571.52 ms / 250 tokens 5.29.004.482 I slot print_timing: id 2 | task 4211 | graphs reused = 3684 5.29.004.483 I slot print_timing: id 2 | task 4211 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.004.541 I slot release: id 2 | task 4211 | stop processing: n_tokens = 1364, truncated = 0 5.29.067.529 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.818 5.29.067.554 I slot launch_slot_: id 2 | task 4372 | processing task, is_child = 0 5.29.433.419 I slot print_timing: id 3 | task 4272 | n_gen = 100, tg = 21.94 t/s, tg_3s = 22.16 t/s 5.30.874.523 I slot print_timing: id 1 | task 4241 | n_gen = 164, tg = 21.82 t/s, tg_3s = 21.21 t/s 5.31.724.668 I slot print_timing: id 0 | task 3423 | n_gen = 984, tg = 20.73 t/s, tg_3s = 21.18 t/s 5.32.111.687 I slot print_timing: id 3 | task 4272 | prompt eval time = 322.26 ms / 88 tokens ( 3.66 ms per token, 273.07 tokens per second) 5.32.111.693 I slot print_timing: id 3 | task 4272 | eval time = 7190.68 ms / 163 tokens ( 44.39 ms per token, 22.53 tokens per second) 5.32.111.694 I slot print_timing: id 3 | task 4272 | total time = 7512.94 ms / 251 tokens 5.32.111.695 I slot print_timing: id 3 | task 4272 | graphs reused = 3746 5.32.111.695 I slot print_timing: id 3 | task 4272 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.111.750 I slot release: id 3 | task 4272 | stop processing: n_tokens = 1365, truncated = 0 5.32.152.645 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.817 5.32.152.667 I slot launch_slot_: id 3 | task 4439 | processing task, is_child = 0 5.33.321.152 I slot print_timing: id 1 | task 4241 | prompt eval time = 430.81 ms / 111 tokens ( 3.88 ms per token, 257.66 tokens per second) 5.33.321.158 I slot print_timing: id 1 | task 4241 | eval time = 9916.12 ms / 216 tokens ( 46.12 ms per token, 21.68 tokens per second) 5.33.321.159 I slot print_timing: id 1 | task 4241 | total time = 10346.93 ms / 327 tokens 5.33.321.160 I slot print_timing: id 1 | task 4241 | graphs reused = 3765 5.33.321.160 I slot print_timing: id 1 | task 4241 | graph reallocs = 0 / 0 (same size) / (changed size) 5.33.321.223 I slot release: id 1 | task 4241 | stop processing: n_tokens = 1441, truncated = 0 5.33.385.608 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.774 5.33.385.635 I slot launch_slot_: id 1 | task 4463 | processing task, is_child = 0 5.33.961.739 I slot print_timing: id 0 | task 3423 | prompt eval time = 378.54 ms / 103 tokens ( 3.68 ms per token, 272.10 tokens per second) 5.33.961.745 I slot print_timing: id 0 | task 3423 | eval time = 49648.72 ms / 1024 tokens ( 48.53 ms per token, 20.60 tokens per second) 5.33.961.746 I slot print_timing: id 0 | task 3423 | total time = 50027.27 ms / 1127 tokens 5.33.961.747 I slot print_timing: id 0 | task 3423 | graphs reused = 3769 5.33.961.747 I slot print_timing: id 0 | task 3423 | graph reallocs = 0 / 0 (same size) / (changed size) 5.33.961.796 I slot release: id 0 | task 3423 | stop processing: n_tokens = 2241, truncated = 0 5.34.004.167 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.498 5.34.035.889 I slot launch_slot_: id 0 | task 4472 | processing task, is_child = 0 5.34.438.910 I slot print_timing: id 2 | task 4372 | n_gen = 100, tg = 19.77 t/s, tg_3s = 19.97 t/s 5.35.538.433 I slot print_timing: id 2 | task 4372 | prompt eval time = 364.82 ms / 83 tokens ( 4.40 ms per token, 227.51 tokens per second) 5.35.538.439 I slot print_timing: id 2 | task 4372 | eval time = 6106.05 ms / 126 tokens ( 48.85 ms per token, 20.47 tokens per second) 5.35.538.440 I slot print_timing: id 2 | task 4372 | total time = 6470.87 ms / 209 tokens 5.35.538.441 I slot print_timing: id 2 | task 4372 | graphs reused = 3797 5.35.538.441 I slot print_timing: id 2 | task 4372 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.538.493 I slot release: id 2 | task 4372 | stop processing: n_tokens = 1324, truncated = 0 5.35.600.718 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.842 5.35.600.743 I slot launch_slot_: id 2 | task 4504 | processing task, is_child = 0 5.37.651.819 I slot print_timing: id 3 | task 4439 | n_gen = 100, tg = 19.11 t/s, tg_3s = 19.31 t/s 5.38.620.342 I slot print_timing: id 1 | task 4463 | n_gen = 100, tg = 20.37 t/s, tg_3s = 20.58 t/s 5.38.955.473 I slot print_timing: id 0 | task 4472 | n_gen = 100, tg = 21.52 t/s, tg_3s = 21.74 t/s 5.38.957.039 I slot print_timing: id 1 | task 4463 | prompt eval time = 374.69 ms / 73 tokens ( 5.13 ms per token, 194.83 tokens per second) 5.38.957.044 I slot print_timing: id 1 | task 4463 | eval time = 5196.71 ms / 108 tokens ( 48.57 ms per token, 20.59 tokens per second) 5.38.957.045 I slot print_timing: id 1 | task 4463 | total time = 5571.40 ms / 181 tokens 5.38.957.046 I slot print_timing: id 1 | task 4463 | graphs reused = 3863 5.38.957.046 I slot print_timing: id 1 | task 4463 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.957.102 I slot release: id 1 | task 4463 | stop processing: n_tokens = 1295, truncated = 0 5.39.020.885 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.861 5.39.020.910 I slot launch_slot_: id 1 | task 4576 | processing task, is_child = 0 5.40.593.783 I slot print_timing: id 2 | task 4504 | n_gen = 100, tg = 21.96 t/s, tg_3s = 22.18 t/s 5.40.678.618 I slot print_timing: id 3 | task 4439 | n_gen = 164, tg = 19.86 t/s, tg_3s = 21.14 t/s 5.41.978.878 I slot print_timing: id 0 | task 4472 | n_gen = 164, tg = 21.38 t/s, tg_3s = 21.17 t/s 5.43.416.180 I slot print_timing: id 3 | task 4439 | prompt eval time = 319.78 ms / 74 tokens ( 4.32 ms per token, 231.41 tokens per second) 5.43.416.185 I slot print_timing: id 3 | task 4439 | eval time = 10943.72 ms / 229 tokens ( 48.00 ms per token, 20.83 tokens per second) 5.43.416.186 I slot print_timing: id 3 | task 4439 | total time = 11263.51 ms / 303 tokens 5.43.416.187 I slot print_timing: id 3 | task 4439 | graphs reused = 3956 5.43.416.187 I slot print_timing: id 3 | task 4439 | graph reallocs = 0 / 0 (same size) / (changed size) 5.43.416.241 I slot release: id 3 | task 4439 | stop processing: n_tokens = 1417, truncated = 0 5.43.456.747 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.787 5.43.456.770 I slot launch_slot_: id 3 | task 4675 | processing task, is_child = 0 5.43.700.862 I slot print_timing: id 2 | task 4504 | n_gen = 169, tg = 22.06 t/s, tg_3s = 22.21 t/s 5.43.815.979 I slot print_timing: id 1 | task 4576 | n_gen = 100, tg = 22.45 t/s, tg_3s = 22.67 t/s 5.44.365.050 I slot print_timing: id 0 | task 4472 | prompt eval time = 319.48 ms / 98 tokens ( 3.26 ms per token, 306.74 tokens per second) 5.44.365.056 I slot print_timing: id 0 | task 4472 | eval time = 10009.66 ms / 215 tokens ( 46.77 ms per token, 21.38 tokens per second) 5.44.365.057 I slot print_timing: id 0 | task 4472 | total time = 10329.15 ms / 313 tokens 5.44.365.058 I slot print_timing: id 0 | task 4472 | graphs reused = 3969 5.44.365.058 I slot print_timing: id 0 | task 4472 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.365.118 I slot release: id 0 | task 4472 | stop processing: n_tokens = 1426, truncated = 0 5.44.410.525 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.782 5.44.410.547 I slot launch_slot_: id 0 | task 4693 | processing task, is_child = 0 5.46.670.402 I slot print_timing: id 1 | task 4576 | prompt eval time = 384.34 ms / 92 tokens ( 4.18 ms per token, 239.37 tokens per second) 5.46.670.406 I slot print_timing: id 1 | task 4576 | eval time = 7265.14 ms / 162 tokens ( 45.13 ms per token, 22.16 tokens per second) 5.46.670.408 I slot print_timing: id 1 | task 4576 | total time = 7649.48 ms / 254 tokens 5.46.670.408 I slot print_timing: id 1 | task 4576 | graphs reused = 4015 5.46.670.409 I slot print_timing: id 1 | task 4576 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.670.462 I slot release: id 1 | task 4576 | stop processing: n_tokens = 1368, truncated = 0 5.46.732.952 I slot print_timing: id 2 | task 4504 | n_gen = 234, tg = 21.88 t/s, tg_3s = 21.44 t/s 5.46.734.677 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.815 5.46.734.698 I slot launch_slot_: id 1 | task 4743 | processing task, is_child = 0 5.48.566.637 I slot print_timing: id 3 | task 4675 | n_gen = 100, tg = 20.67 t/s, tg_3s = 20.88 t/s 5.48.861.489 I slot print_timing: id 3 | task 4675 | prompt eval time = 320.26 ms / 79 tokens ( 4.05 ms per token, 246.68 tokens per second) 5.48.861.492 I slot print_timing: id 3 | task 4675 | eval time = 5084.45 ms / 107 tokens ( 47.97 ms per token, 20.85 tokens per second) 5.48.861.493 I slot print_timing: id 3 | task 4675 | total time = 5404.71 ms / 186 tokens 5.48.861.494 I slot print_timing: id 3 | task 4675 | graphs reused = 4054 5.48.861.494 I slot print_timing: id 3 | task 4675 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.861.556 I slot release: id 3 | task 4675 | stop processing: n_tokens = 1300, truncated = 0 5.48.902.304 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.858 5.48.902.326 I slot launch_slot_: id 3 | task 4787 | processing task, is_child = 0 5.49.519.778 I slot print_timing: id 0 | task 4693 | n_gen = 100, tg = 20.65 t/s, tg_3s = 20.86 t/s 5.49.734.416 I slot print_timing: id 2 | task 4504 | n_gen = 291, tg = 21.25 t/s, tg_3s = 18.99 t/s 5.50.241.482 I slot print_timing: id 2 | task 4504 | prompt eval time = 484.26 ms / 142 tokens ( 3.41 ms per token, 293.23 tokens per second) 5.50.241.489 I slot print_timing: id 2 | task 4504 | eval time = 14156.47 ms / 303 tokens ( 46.88 ms per token, 21.33 tokens per second) 5.50.241.489 I slot print_timing: id 2 | task 4504 | total time = 14640.73 ms / 445 tokens 5.50.241.490 I slot print_timing: id 2 | task 4504 | graphs reused = 4076 5.50.241.490 I slot print_timing: id 2 | task 4504 | graph reallocs = 0 / 0 (same size) / (changed size) 5.50.241.551 I slot release: id 2 | task 4504 | stop processing: n_tokens = 1559, truncated = 0 5.50.304.005 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.715 5.50.304.028 I slot launch_slot_: id 2 | task 4815 | processing task, is_child = 0 5.51.896.679 I slot print_timing: id 1 | task 4743 | n_gen = 100, tg = 20.92 t/s, tg_3s = 21.13 t/s 5.52.526.344 I slot print_timing: id 0 | task 4693 | n_gen = 164, tg = 20.90 t/s, tg_3s = 21.29 t/s 5.53.709.980 I slot print_timing: id 3 | task 4787 | n_gen = 100, tg = 22.07 t/s, tg_3s = 22.29 t/s 5.53.789.409 I slot print_timing: id 0 | task 4693 | prompt eval time = 315.65 ms / 83 tokens ( 3.80 ms per token, 262.95 tokens per second) 5.53.789.413 I slot print_timing: id 0 | task 4693 | eval time = 9063.21 ms / 194 tokens ( 46.96 ms per token, 21.29 tokens per second) 5.53.789.414 I slot print_timing: id 0 | task 4693 | total time = 9378.85 ms / 277 tokens 5.53.789.414 I slot print_timing: id 0 | task 4693 | graphs reused = 4148 5.53.789.415 I slot print_timing: id 0 | task 4693 | graph reallocs = 0 / 0 (same size) / (changed size) 5.53.789.471 I slot release: id 0 | task 4693 | stop processing: n_tokens = 1391, truncated = 0 5.53.834.710 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.802 5.53.834.733 I slot launch_slot_: id 0 | task 4893 | processing task, is_child = 0 5.54.847.655 I slot print_timing: id 2 | task 4815 | prompt eval time = 362.29 ms / 91 tokens ( 3.98 ms per token, 251.18 tokens per second) 5.54.847.659 I slot print_timing: id 2 | task 4815 | eval time = 4181.33 ms / 94 tokens ( 44.96 ms per token, 22.24 tokens per second) 5.54.847.660 I slot print_timing: id 2 | task 4815 | total time = 4543.62 ms / 185 tokens 5.54.847.660 I slot print_timing: id 2 | task 4815 | graphs reused = 4163 5.54.847.661 I slot print_timing: id 2 | task 4815 | graph reallocs = 0 / 0 (same size) / (changed size) 5.54.847.717 I slot release: id 2 | task 4815 | stop processing: n_tokens = 1299, truncated = 0 5.54.908.154 I slot print_timing: id 1 | task 4743 | n_gen = 165, tg = 21.18 t/s, tg_3s = 21.58 t/s 5.54.909.740 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.858 5.54.909.761 I slot launch_slot_: id 2 | task 4913 | processing task, is_child = 0 5.55.182.460 I slot print_timing: id 3 | task 4787 | prompt eval time = 322.24 ms / 88 tokens ( 3.66 ms per token, 273.09 tokens per second) 5.55.182.481 I slot print_timing: id 3 | task 4787 | eval time = 5957.86 ms / 123 tokens ( 48.83 ms per token, 20.48 tokens per second) 5.55.182.482 I slot print_timing: id 3 | task 4787 | total time = 6280.11 ms / 211 tokens 5.55.182.483 I slot print_timing: id 3 | task 4787 | graphs reused = 4163 5.55.182.484 I slot print_timing: id 3 | task 4787 | graph reallocs = 0 / 0 (same size) / (changed size) 5.55.182.668 I slot release: id 3 | task 4787 | stop processing: n_tokens = 1325, truncated = 0 5.55.264.043 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.842 5.55.264.076 I slot launch_slot_: id 3 | task 4916 | processing task, is_child = 0 5.57.922.916 I slot print_timing: id 1 | task 4743 | n_gen = 224, tg = 20.73 t/s, tg_3s = 19.57 t/s 5.58.889.737 I slot print_timing: id 0 | task 4893 | n_gen = 100, tg = 20.94 t/s, tg_3s = 21.15 t/s 5.59.692.606 I slot print_timing: id 2 | task 4913 | n_gen = 100, tg = 22.35 t/s, tg_3s = 22.58 t/s 5.59.778.366 I slot print_timing: id 3 | task 4916 | n_gen = 100, tg = 23.71 t/s, tg_3s = 23.95 t/s 5.59.942.579 I slot print_timing: id 0 | task 4893 | prompt eval time = 327.79 ms / 95 tokens ( 3.45 ms per token, 289.82 tokens per second) 5.59.942.588 I slot print_timing: id 0 | task 4893 | eval time = 5780.05 ms / 125 tokens ( 46.61 ms per token, 21.45 tokens per second) 5.59.942.589 I slot print_timing: id 0 | task 4893 | total time = 6107.84 ms / 220 tokens 5.59.942.590 I slot print_timing: id 0 | task 4893 | graphs reused = 4265 5.59.942.590 I slot print_timing: id 0 | task 4893 | graph reallocs = 0 / 0 (same size) / (changed size) 5.59.942.643 I slot release: id 0 | task 4893 | stop processing: n_tokens = 1334, truncated = 0 5.59.988.171 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.836 5.59.988.194 I slot launch_slot_: id 0 | task 5023 | processing task, is_child = 0 6.00.351.330 I slot print_timing: id 3 | task 4916 | prompt eval time = 338.82 ms / 78 tokens ( 4.34 ms per token, 230.21 tokens per second) 6.00.351.333 I slot print_timing: id 3 | task 4916 | eval time = 4748.43 ms / 108 tokens ( 44.38 ms per token, 22.53 tokens per second) 6.00.351.334 I slot print_timing: id 3 | task 4916 | total time = 5087.24 ms / 186 tokens 6.00.351.335 I slot print_timing: id 3 | task 4916 | graphs reused = 4266 6.00.351.335 I slot print_timing: id 3 | task 4916 | graph reallocs = 0 / 0 (same size) / (changed size) 6.00.351.387 I slot release: id 3 | task 4916 | stop processing: n_tokens = 1300, truncated = 0 6.00.391.043 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.858 6.00.391.062 I slot launch_slot_: id 3 | task 5028 | processing task, is_child = 0 6.00.964.810 I slot print_timing: id 1 | task 4743 | n_gen = 285, tg = 20.58 t/s, tg_3s = 20.05 t/s 6.02.318.843 I slot print_timing: id 2 | task 4913 | prompt eval time = 354.27 ms / 97 tokens ( 3.65 ms per token, 273.80 tokens per second) 6.02.318.849 I slot print_timing: id 2 | task 4913 | eval time = 7054.81 ms / 151 tokens ( 47.03 ms per token, 21.26 tokens per second) 6.02.318.850 I slot print_timing: id 2 | task 4913 | total time = 7409.07 ms / 248 tokens 6.02.318.850 I slot print_timing: id 2 | task 4913 | graphs reused = 4302 6.02.318.851 I slot print_timing: id 2 | task 4913 | graph reallocs = 0 / 0 (same size) / (changed size) 6.02.318.904 I slot release: id 2 | task 4913 | stop processing: n_tokens = 1362, truncated = 0 6.02.380.931 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.819 6.02.380.963 I slot launch_slot_: id 2 | task 5070 | processing task, is_child = 0 6.03.965.491 I slot print_timing: id 1 | task 4743 | n_gen = 349, tg = 20.71 t/s, tg_3s = 21.33 t/s 6.05.017.805 I slot print_timing: id 0 | task 5023 | n_gen = 100, tg = 21.02 t/s, tg_3s = 21.23 t/s 6.05.191.040 I slot print_timing: id 3 | task 5028 | n_gen = 100, tg = 22.11 t/s, tg_3s = 22.33 t/s 6.05.950.695 I slot print_timing: id 3 | task 5028 | prompt eval time = 322.03 ms / 89 tokens ( 3.62 ms per token, 276.37 tokens per second) 6.05.950.702 I slot print_timing: id 3 | task 5028 | eval time = 5237.59 ms / 118 tokens ( 44.77 ms per token, 22.34 tokens per second) 6.05.950.703 I slot print_timing: id 3 | task 5028 | total time = 5559.63 ms / 207 tokens 6.05.950.703 I slot print_timing: id 3 | task 5028 | graphs reused = 4377 6.05.950.704 I slot print_timing: id 3 | task 5028 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.950.760 I slot release: id 3 | task 5028 | stop processing: n_tokens = 1321, truncated = 0 6.05.991.280 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.844 6.05.991.309 I slot launch_slot_: id 3 | task 5150 | processing task, is_child = 0 6.06.692.043 I slot print_timing: id 2 | task 5070 | prompt eval time = 358.91 ms / 74 tokens ( 4.85 ms per token, 206.18 tokens per second) 6.06.692.046 I slot print_timing: id 2 | task 5070 | eval time = 3952.16 ms / 89 tokens ( 44.91 ms per token, 22.27 tokens per second) 6.06.692.047 I slot print_timing: id 2 | task 5070 | total time = 4311.07 ms / 163 tokens 6.06.692.047 I slot print_timing: id 2 | task 5070 | graphs reused = 4385 6.06.692.048 I slot print_timing: id 2 | task 5070 | graph reallocs = 0 / 0 (same size) / (changed size) 6.06.692.101 I slot release: id 2 | task 5070 | stop processing: n_tokens = 1277, truncated = 0 6.06.754.836 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.873 6.06.754.859 I slot launch_slot_: id 2 | task 5163 | processing task, is_child = 0 6.07.134.071 I slot print_timing: id 1 | task 4743 | n_gen = 410, tg = 20.48 t/s, tg_3s = 19.25 t/s 6.08.040.779 I slot print_timing: id 0 | task 5023 | n_gen = 156, tg = 20.04 t/s, tg_3s = 18.52 t/s 6.08.925.468 I slot print_timing: id 0 | task 5023 | prompt eval time = 318.80 ms / 95 tokens ( 3.36 ms per token, 298.00 tokens per second) 6.08.925.472 I slot print_timing: id 0 | task 5023 | eval time = 8618.47 ms / 177 tokens ( 48.97 ms per token, 20.42 tokens per second) 6.08.925.473 I slot print_timing: id 0 | task 5023 | total time = 8937.27 ms / 272 tokens 6.08.925.474 I slot print_timing: id 0 | task 5023 | graphs reused = 4424 6.08.925.474 I slot print_timing: id 0 | task 5023 | graph reallocs = 0 / 0 (same size) / (changed size) 6.08.925.531 I slot release: id 0 | task 5023 | stop processing: n_tokens = 1386, truncated = 0 6.08.970.902 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.804 6.08.970.924 I slot launch_slot_: id 0 | task 5207 | processing task, is_child = 0 6.10.136.790 I slot print_timing: id 1 | task 4743 | n_gen = 474, tg = 20.59 t/s, tg_3s = 21.31 t/s 6.10.435.344 I slot print_timing: id 3 | task 5150 | prompt eval time = 319.20 ms / 75 tokens ( 4.26 ms per token, 234.96 tokens per second) 6.10.435.349 I slot print_timing: id 3 | task 5150 | eval time = 4124.83 ms / 83 tokens ( 50.30 ms per token, 19.88 tokens per second) 6.10.435.349 I slot print_timing: id 3 | task 5150 | total time = 4444.03 ms / 158 tokens 6.10.435.350 I slot print_timing: id 3 | task 5150 | graphs reused = 4451 6.10.435.350 I slot print_timing: id 3 | task 5150 | graph reallocs = 0 / 0 (same size) / (changed size) 6.10.435.404 I slot release: id 3 | task 5150 | stop processing: n_tokens = 1272, truncated = 0 6.10.476.115 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.877 6.10.476.142 I slot launch_slot_: id 3 | task 5238 | processing task, is_child = 0 6.11.897.910 I slot print_timing: id 2 | task 5163 | n_gen = 100, tg = 21.22 t/s, tg_3s = 21.44 t/s 6.13.162.070 I slot print_timing: id 1 | task 4743 | n_gen = 540, tg = 20.73 t/s, tg_3s = 21.82 t/s 6.13.710.061 I slot print_timing: id 0 | task 5207 | n_gen = 100, tg = 22.39 t/s, tg_3s = 22.62 t/s 6.14.937.474 I slot print_timing: id 2 | task 5163 | n_gen = 172, tg = 22.20 t/s, tg_3s = 23.69 t/s 6.14.981.129 I slot print_timing: id 3 | task 5238 | n_gen = 100, tg = 23.67 t/s, tg_3s = 23.91 t/s 6.16.197.269 I slot print_timing: id 1 | task 4743 | n_gen = 612, tg = 21.04 t/s, tg_3s = 23.72 t/s 6.16.744.632 I slot print_timing: id 0 | task 5207 | n_gen = 172, tg = 22.93 t/s, tg_3s = 23.73 t/s 6.17.971.873 I slot print_timing: id 2 | task 5163 | n_gen = 244, tg = 22.63 t/s, tg_3s = 23.73 t/s 6.18.015.727 I slot print_timing: id 3 | task 5238 | n_gen = 172, tg = 23.69 t/s, tg_3s = 23.73 t/s 6.19.150.884 I slot print_timing: id 0 | task 5207 | prompt eval time = 317.67 ms / 95 tokens ( 3.34 ms per token, 299.05 tokens per second) 6.19.150.893 I slot print_timing: id 0 | task 5207 | eval time = 9862.28 ms / 229 tokens ( 43.26 ms per token, 23.12 tokens per second) 6.19.150.893 I slot print_timing: id 0 | task 5207 | total time = 10179.95 ms / 324 tokens 6.19.150.894 I slot print_timing: id 0 | task 5207 | graphs reused = 4647 6.19.150.895 I slot print_timing: id 0 | task 5207 | graph reallocs = 0 / 0 (same size) / (changed size) 6.19.150.956 I slot release: id 0 | task 5207 | stop processing: n_tokens = 1438, truncated = 0 6.19.196.541 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.775 6.19.196.562 I slot launch_slot_: id 0 | task 5440 | processing task, is_child = 0 6.19.436.929 I slot print_timing: id 1 | task 4743 | n_gen = 684, tg = 21.16 t/s, tg_3s = 22.22 t/s 6.20.704.107 I slot print_timing: id 2 | task 5163 | prompt eval time = 478.21 ms / 151 tokens ( 3.17 ms per token, 315.76 tokens per second) 6.20.704.113 I slot print_timing: id 2 | task 5163 | eval time = 13471.03 ms / 303 tokens ( 44.61 ms per token, 22.42 tokens per second) 6.20.704.113 I slot print_timing: id 2 | task 5163 | total time = 13949.24 ms / 454 tokens 6.20.704.114 I slot print_timing: id 2 | task 5163 | graphs reused = 4675 6.20.704.114 I slot print_timing: id 2 | task 5163 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.704.170 I slot release: id 2 | task 5163 | stop processing: n_tokens = 1568, truncated = 0 6.20.766.850 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.711 6.20.766.874 I slot launch_slot_: id 2 | task 5472 | processing task, is_child = 0 6.21.035.382 I slot print_timing: id 3 | task 5238 | n_gen = 232, tg = 22.57 t/s, tg_3s = 19.87 t/s 6.22.447.881 I slot print_timing: id 1 | task 4743 | n_gen = 747, tg = 21.14 t/s, tg_3s = 20.92 t/s 6.24.011.268 I slot print_timing: id 0 | task 5440 | n_gen = 100, tg = 22.00 t/s, tg_3s = 22.22 t/s 6.24.058.300 I slot print_timing: id 3 | task 5238 | n_gen = 302, tg = 22.70 t/s, tg_3s = 23.16 t/s 6.24.095.870 I slot print_timing: id 0 | task 5440 | prompt eval time = 314.90 ms / 80 tokens ( 3.94 ms per token, 254.05 tokens per second) 6.24.095.876 I slot print_timing: id 0 | task 5440 | eval time = 4584.40 ms / 102 tokens ( 45.39 ms per token, 22.03 tokens per second) 6.24.095.877 I slot print_timing: id 0 | task 5440 | total time = 4899.30 ms / 182 tokens 6.24.095.877 I slot print_timing: id 0 | task 5440 | graphs reused = 4744 6.24.095.878 I slot print_timing: id 0 | task 5440 | graph reallocs = 0 / 0 (same size) / (changed size) 6.24.095.935 I slot release: id 0 | task 5440 | stop processing: n_tokens = 1296, truncated = 0 6.24.141.531 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.860 6.24.141.553 I slot launch_slot_: id 0 | task 5546 | processing task, is_child = 0 6.25.297.849 I slot print_timing: id 3 | task 5238 | prompt eval time = 322.41 ms / 92 tokens ( 3.50 ms per token, 285.35 tokens per second) 6.25.297.856 I slot print_timing: id 3 | task 5238 | eval time = 14499.29 ms / 327 tokens ( 44.48 ms per token, 22.48 tokens per second) 6.25.297.856 I slot print_timing: id 3 | task 5238 | total time = 14821.70 ms / 419 tokens 6.25.297.857 I slot print_timing: id 3 | task 5238 | graphs reused = 4765 6.25.297.858 I slot print_timing: id 3 | task 5238 | graph reallocs = 0 / 0 (same size) / (changed size) 6.25.297.912 I slot release: id 3 | task 5238 | stop processing: n_tokens = 1533, truncated = 0 6.25.338.516 I slot print_timing: id 2 | task 5472 | prompt eval time = 364.18 ms / 95 tokens ( 3.83 ms per token, 260.86 tokens per second) 6.25.338.519 I slot print_timing: id 2 | task 5472 | eval time = 4207.45 ms / 96 tokens ( 44.29 ms per token, 22.58 tokens per second) 6.25.338.521 I slot print_timing: id 2 | task 5472 | total time = 4571.64 ms / 191 tokens 6.25.338.521 I slot print_timing: id 2 | task 5472 | graphs reused = 4765 6.25.338.522 I slot print_timing: id 2 | task 5472 | graph reallocs = 0 / 0 (same size) / (changed size) 6.25.338.574 I slot release: id 2 | task 5472 | stop processing: n_tokens = 1305, truncated = 0 6.25.338.581 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.854 6.25.338.598 I slot launch_slot_: id 2 | task 5571 | processing task, is_child = 0 6.25.369.810 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.727 6.25.369.831 I slot launch_slot_: id 3 | task 5572 | processing task, is_child = 0 6.25.814.712 I slot print_timing: id 1 | task 4743 | n_gen = 812, tg = 20.98 t/s, tg_3s = 19.31 t/s 6.28.393.151 I slot print_timing: id 0 | task 5546 | prompt eval time = 259.17 ms / 63 tokens ( 4.11 ms per token, 243.08 tokens per second) 6.28.393.155 I slot print_timing: id 0 | task 5546 | eval time = 3992.42 ms / 84 tokens ( 48.10 ms per token, 20.79 tokens per second) 6.28.393.156 I slot print_timing: id 0 | task 5546 | total time = 4251.59 ms / 147 tokens 6.28.393.156 I slot print_timing: id 0 | task 5546 | graphs reused = 4822 6.28.393.157 I slot print_timing: id 0 | task 5546 | graph reallocs = 0 / 0 (same size) / (changed size) 6.28.393.211 I slot release: id 0 | task 5546 | stop processing: n_tokens = 1261, truncated = 0 6.28.438.744 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.884 6.28.438.767 I slot launch_slot_: id 0 | task 5635 | processing task, is_child = 0 6.28.865.085 I slot print_timing: id 1 | task 4743 | n_gen = 875, tg = 20.96 t/s, tg_3s = 20.65 t/s 6.29.549.359 I slot print_timing: id 3 | task 5572 | prompt eval time = 525.21 ms / 62 tokens ( 8.47 ms per token, 118.05 tokens per second) 6.29.549.363 I slot print_timing: id 3 | task 5572 | eval time = 3652.55 ms / 79 tokens ( 46.83 ms per token, 21.35 tokens per second) 6.29.549.364 I slot print_timing: id 3 | task 5572 | total time = 4177.76 ms / 141 tokens 6.29.549.364 I slot print_timing: id 3 | task 5572 | graphs reused = 4838 6.29.549.365 I slot print_timing: id 3 | task 5572 | graph reallocs = 0 / 0 (same size) / (changed size) 6.29.549.422 I slot release: id 3 | task 5572 | stop processing: n_tokens = 1255, truncated = 0 6.29.589.927 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.888 6.29.589.949 I slot launch_slot_: id 3 | task 5655 | processing task, is_child = 0 6.30.680.161 I slot print_timing: id 2 | task 5571 | n_gen = 100, tg = 20.69 t/s, tg_3s = 20.90 t/s 6.31.357.152 I slot print_timing: id 2 | task 5571 | prompt eval time = 525.90 ms / 105 tokens ( 5.01 ms per token, 199.66 tokens per second) 6.31.357.159 I slot print_timing: id 2 | task 5571 | eval time = 5461.42 ms / 116 tokens ( 47.49 ms per token, 21.06 tokens per second) 6.31.357.160 I slot print_timing: id 2 | task 5571 | total time = 5987.31 ms / 221 tokens 6.31.357.161 I slot print_timing: id 2 | task 5571 | graphs reused = 4871 6.31.357.161 I slot print_timing: id 2 | task 5571 | graph reallocs = 0 / 0 (same size) / (changed size) 6.31.357.216 I slot release: id 2 | task 5571 | stop processing: n_tokens = 1335, truncated = 0 6.31.419.176 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.835 6.31.419.202 I slot launch_slot_: id 2 | task 5693 | processing task, is_child = 0 6.31.878.141 I slot print_timing: id 1 | task 4743 | n_gen = 933, tg = 20.84 t/s, tg_3s = 19.25 t/s 6.33.610.456 I slot print_timing: id 0 | task 5635 | n_gen = 100, tg = 20.86 t/s, tg_3s = 21.07 t/s 6.34.417.604 I slot print_timing: id 3 | task 5655 | n_gen = 100, tg = 21.99 t/s, tg_3s = 22.21 t/s 6.34.878.937 I slot print_timing: id 1 | task 4743 | n_gen = 1004, tg = 21.02 t/s, tg_3s = 23.66 t/s 6.35.724.492 I slot print_timing: id 1 | task 4743 | prompt eval time = 428.73 ms / 108 tokens ( 3.97 ms per token, 251.91 tokens per second) 6.35.724.496 I slot print_timing: id 1 | task 4743 | eval time = 48561.06 ms / 1024 tokens ( 47.47 ms per token, 21.07 tokens per second) 6.35.724.496 I slot print_timing: id 1 | task 4743 | total time = 48989.79 ms / 1132 tokens 6.35.724.497 I slot print_timing: id 1 | task 4743 | graphs reused = 4963 6.35.724.498 I slot print_timing: id 1 | task 4743 | graph reallocs = 0 / 0 (same size) / (changed size) 6.35.724.552 I slot release: id 1 | task 4743 | stop processing: n_tokens = 2246, truncated = 0 6.35.788.212 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.496 6.35.825.687 I slot launch_slot_: id 1 | task 5790 | processing task, is_child = 0 6.36.339.821 I slot print_timing: id 3 | task 5655 | prompt eval time = 325.37 ms / 94 tokens ( 3.46 ms per token, 288.90 tokens per second) 6.36.339.826 I slot print_timing: id 3 | task 5655 | eval time = 6424.49 ms / 136 tokens ( 47.59 ms per token, 21.01 tokens per second) 6.36.339.826 I slot print_timing: id 3 | task 5655 | total time = 6749.87 ms / 230 tokens 6.36.339.827 I slot print_timing: id 3 | task 5655 | graphs reused = 4964 6.36.339.827 I slot print_timing: id 3 | task 5655 | graph reallocs = 0 / 0 (same size) / (changed size) 6.36.339.877 I slot release: id 3 | task 5655 | stop processing: n_tokens = 1344, truncated = 0 6.36.380.730 I slot print_timing: id 2 | task 5693 | n_gen = 100, tg = 21.57 t/s, tg_3s = 21.79 t/s 6.36.380.737 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.830 6.36.380.762 I slot launch_slot_: id 3 | task 5796 | processing task, is_child = 0 6.36.651.366 I slot print_timing: id 0 | task 5635 | n_gen = 158, tg = 20.16 t/s, tg_3s = 19.07 t/s 6.37.457.549 I slot print_timing: id 0 | task 5635 | prompt eval time = 425.21 ms / 133 tokens ( 3.20 ms per token, 312.78 tokens per second) 6.37.457.553 I slot print_timing: id 0 | task 5635 | eval time = 8593.56 ms / 177 tokens ( 48.83 ms per token, 20.48 tokens per second) 6.37.457.553 I slot print_timing: id 0 | task 5635 | total time = 9018.77 ms / 310 tokens 6.37.457.554 I slot print_timing: id 0 | task 5635 | graphs reused = 4982 6.37.457.554 I slot print_timing: id 0 | task 5635 | graph reallocs = 0 / 0 (same size) / (changed size) 6.37.457.614 I slot release: id 0 | task 5635 | stop processing: n_tokens = 1424, truncated = 0 6.37.502.739 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.783 6.37.502.762 I slot launch_slot_: id 0 | task 5819 | processing task, is_child = 0 6.39.422.461 I slot print_timing: id 2 | task 5693 | n_gen = 162, tg = 21.10 t/s, tg_3s = 20.38 t/s 6.40.180.524 I slot print_timing: id 3 | task 5796 | prompt eval time = 276.63 ms / 68 tokens ( 4.07 ms per token, 245.81 tokens per second) 6.40.180.531 I slot print_timing: id 3 | task 5796 | eval time = 3523.12 ms / 79 tokens ( 45.17 ms per token, 22.14 tokens per second) 6.40.180.533 I slot print_timing: id 3 | task 5796 | total time = 3799.75 ms / 147 tokens 6.40.180.533 I slot print_timing: id 3 | task 5796 | graphs reused = 5037 6.40.180.534 I slot print_timing: id 3 | task 5796 | graph reallocs = 0 / 0 (same size) / (changed size) 6.40.180.589 I slot release: id 3 | task 5796 | stop processing: n_tokens = 1261, truncated = 0 6.40.220.822 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.884 6.40.220.845 I slot launch_slot_: id 3 | task 5879 | processing task, is_child = 0 6.41.128.360 I slot print_timing: id 1 | task 5790 | n_gen = 100, tg = 20.32 t/s, tg_3s = 20.52 t/s 6.42.264.346 I slot print_timing: id 0 | task 5819 | n_gen = 100, tg = 22.28 t/s, tg_3s = 22.50 t/s 6.42.435.779 I slot print_timing: id 2 | task 5693 | n_gen = 227, tg = 21.23 t/s, tg_3s = 21.57 t/s 6.42.978.532 I slot print_timing: id 0 | task 5819 | prompt eval time = 317.43 ms / 100 tokens ( 3.17 ms per token, 315.03 tokens per second) 6.42.978.537 I slot print_timing: id 0 | task 5819 | eval time = 5158.33 ms / 117 tokens ( 44.47 ms per token, 22.49 tokens per second) 6.42.978.537 I slot print_timing: id 0 | task 5819 | total time = 5475.76 ms / 217 tokens 6.42.978.538 I slot print_timing: id 0 | task 5819 | graphs reused = 5093 6.42.978.539 I slot print_timing: id 0 | task 5819 | graph reallocs = 0 / 0 (same size) / (changed size) 6.42.978.602 I slot release: id 0 | task 5819 | stop processing: n_tokens = 1331, truncated = 0 6.43.023.254 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.838 6.43.023.280 I slot launch_slot_: id 0 | task 5940 | processing task, is_child = 0 6.43.971.564 I slot print_timing: id 1 | task 5790 | prompt eval time = 430.46 ms / 111 tokens ( 3.88 ms per token, 257.87 tokens per second) 6.43.971.568 I slot print_timing: id 1 | task 5790 | eval time = 7715.40 ms / 162 tokens ( 47.92 ms per token, 20.87 tokens per second) 6.43.971.569 I slot print_timing: id 1 | task 5790 | total time = 8145.86 ms / 273 tokens 6.43.971.569 I slot print_timing: id 1 | task 5790 | graphs reused = 5108 6.43.971.570 I slot print_timing: id 1 | task 5790 | graph reallocs = 0 / 0 (same size) / (changed size) 6.43.971.625 I slot release: id 1 | task 5790 | stop processing: n_tokens = 1386, truncated = 0 6.44.035.625 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.804 6.44.035.651 I slot launch_slot_: id 1 | task 5959 | processing task, is_child = 0 6.44.450.844 I slot print_timing: id 2 | task 5693 | prompt eval time = 372.08 ms / 85 tokens ( 4.38 ms per token, 228.44 tokens per second) 6.44.450.851 I slot print_timing: id 2 | task 5693 | eval time = 12659.56 ms / 262 tokens ( 48.50 ms per token, 20.62 tokens per second) 6.44.450.851 I slot print_timing: id 2 | task 5693 | total time = 13031.64 ms / 347 tokens 6.44.450.852 I slot print_timing: id 2 | task 5693 | graphs reused = 5108 6.44.450.852 I slot print_timing: id 2 | task 5693 | graph reallocs = 0 / 0 (same size) / (changed size) 6.44.450.908 I slot release: id 2 | task 5693 | stop processing: n_tokens = 1461, truncated = 0 6.44.510.429 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.763 6.44.510.449 I slot launch_slot_: id 2 | task 5964 | processing task, is_child = 0 6.45.585.773 I slot print_timing: id 3 | task 5879 | n_gen = 100, tg = 19.84 t/s, tg_3s = 20.04 t/s 6.48.099.595 I slot print_timing: id 0 | task 5940 | n_gen = 100, tg = 20.78 t/s, tg_3s = 20.99 t/s 6.48.609.069 I slot print_timing: id 3 | task 5879 | n_gen = 172, tg = 21.34 t/s, tg_3s = 23.82 t/s 6.48.858.447 I slot print_timing: id 1 | task 5959 | n_gen = 100, tg = 22.25 t/s, tg_3s = 22.47 t/s 6.49.028.034 I slot print_timing: id 2 | task 5964 | n_gen = 100, tg = 23.82 t/s, tg_3s = 24.06 t/s 6.49.739.566 I slot print_timing: id 1 | task 5959 | prompt eval time = 373.21 ms / 73 tokens ( 5.11 ms per token, 195.60 tokens per second) 6.49.739.570 I slot print_timing: id 1 | task 5959 | eval time = 5330.70 ms / 121 tokens ( 44.42 ms per token, 22.51 tokens per second) 6.49.739.570 I slot print_timing: id 1 | task 5959 | total time = 5703.90 ms / 194 tokens 6.49.739.571 I slot print_timing: id 1 | task 5959 | graphs reused = 5222 6.49.739.571 I slot print_timing: id 1 | task 5959 | graph reallocs = 0 / 0 (same size) / (changed size) 6.49.739.629 I slot release: id 1 | task 5959 | stop processing: n_tokens = 1308, truncated = 0 6.49.803.472 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.852 6.49.803.494 I slot launch_slot_: id 1 | task 6084 | processing task, is_child = 0 6.51.129.394 I slot print_timing: id 0 | task 5940 | n_gen = 163, tg = 20.78 t/s, tg_3s = 20.79 t/s 6.51.640.749 I slot print_timing: id 3 | task 5879 | n_gen = 235, tg = 21.18 t/s, tg_3s = 20.78 t/s 6.52.059.327 I slot print_timing: id 2 | task 5964 | n_gen = 163, tg = 22.54 t/s, tg_3s = 20.78 t/s 6.53.568.055 I slot print_timing: id 0 | task 5940 | prompt eval time = 311.81 ms / 70 tokens ( 4.45 ms per token, 224.50 tokens per second) 6.53.568.061 I slot print_timing: id 0 | task 5940 | eval time = 10232.96 ms / 221 tokens ( 46.51 ms per token, 21.50 tokens per second) 6.53.568.062 I slot print_timing: id 0 | task 5940 | total time = 10544.77 ms / 291 tokens 6.53.568.062 I slot print_timing: id 0 | task 5940 | graphs reused = 5300 6.53.568.063 I slot print_timing: id 0 | task 5940 | graph reallocs = 0 / 0 (same size) / (changed size) 6.53.568.117 I slot release: id 0 | task 5940 | stop processing: n_tokens = 1405, truncated = 0 6.53.613.249 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.794 6.53.613.277 I slot launch_slot_: id 0 | task 6167 | processing task, is_child = 0 6.54.646.126 I slot print_timing: id 1 | task 6084 | n_gen = 100, tg = 22.48 t/s, tg_3s = 22.71 t/s 6.54.649.208 I slot print_timing: id 3 | task 5879 | n_gen = 301, tg = 21.35 t/s, tg_3s = 21.94 t/s 6.55.067.434 I slot print_timing: id 2 | task 5964 | n_gen = 229, tg = 22.36 t/s, tg_3s = 21.94 t/s 6.56.958.339 I slot print_timing: id 1 | task 6084 | prompt eval time = 438.92 ms / 105 tokens ( 4.18 ms per token, 239.22 tokens per second) 6.56.958.344 I slot print_timing: id 1 | task 6084 | eval time = 6715.92 ms / 155 tokens ( 43.61 ms per token, 22.93 tokens per second) 6.56.958.345 I slot print_timing: id 1 | task 6084 | total time = 7154.84 ms / 260 tokens 6.56.958.345 I slot print_timing: id 1 | task 6084 | graphs reused = 5371 6.56.958.346 I slot print_timing: id 1 | task 6084 | graph reallocs = 0 / 0 (same size) / (changed size) 6.56.958.400 I slot release: id 1 | task 6084 | stop processing: n_tokens = 1374, truncated = 0 6.57.022.355 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.811 6.57.022.381 I slot launch_slot_: id 1 | task 6243 | processing task, is_child = 0 6.57.657.646 I slot print_timing: id 3 | task 5879 | n_gen = 365, tg = 21.33 t/s, tg_3s = 21.27 t/s 6.58.081.853 I slot print_timing: id 2 | task 5964 | n_gen = 293, tg = 22.11 t/s, tg_3s = 21.23 t/s 6.58.417.262 I slot print_timing: id 0 | task 6167 | n_gen = 100, tg = 22.05 t/s, tg_3s = 22.27 t/s 6.59.764.522 I slot print_timing: id 0 | task 6167 | prompt eval time = 314.53 ms / 79 tokens ( 3.98 ms per token, 251.17 tokens per second) 6.59.764.526 I slot print_timing: id 0 | task 6167 | eval time = 5836.71 ms / 132 tokens ( 44.56 ms per token, 22.44 tokens per second) 6.59.764.527 I slot print_timing: id 0 | task 6167 | total time = 6151.24 ms / 211 tokens 6.59.764.527 I slot print_timing: id 0 | task 6167 | graphs reused = 5426 6.59.764.528 I slot print_timing: id 0 | task 6167 | graph reallocs = 0 / 0 (same size) / (changed size) 6.59.764.587 I slot release: id 0 | task 6167 | stop processing: n_tokens = 1325, truncated = 0 6.59.810.003 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.842 6.59.810.027 I slot launch_slot_: id 0 | task 6303 | processing task, is_child = 0 7.00.686.189 I slot print_timing: id 3 | task 5879 | n_gen = 430, tg = 21.35 t/s, tg_3s = 21.46 t/s 7.01.106.407 I slot print_timing: id 2 | task 5964 | n_gen = 358, tg = 21.99 t/s, tg_3s = 21.49 t/s 7.01.862.673 I slot print_timing: id 1 | task 6243 | n_gen = 100, tg = 22.18 t/s, tg_3s = 22.40 t/s 7.03.721.643 I slot print_timing: id 3 | task 5879 | n_gen = 502, tg = 21.66 t/s, tg_3s = 23.72 t/s 7.04.141.498 I slot print_timing: id 2 | task 5964 | n_gen = 430, tg = 22.26 t/s, tg_3s = 23.72 t/s 7.04.349.135 I slot print_timing: id 0 | task 6303 | n_gen = 100, tg = 23.74 t/s, tg_3s = 23.98 t/s 7.04.871.771 I slot print_timing: id 1 | task 6243 | n_gen = 172, tg = 22.88 t/s, tg_3s = 23.93 t/s 7.06.742.723 I slot print_timing: id 3 | task 5879 | n_gen = 577, tg = 22.03 t/s, tg_3s = 24.83 t/s 7.07.182.142 I slot print_timing: id 2 | task 5964 | n_gen = 506, tg = 22.64 t/s, tg_3s = 24.99 t/s 7.07.389.927 I slot print_timing: id 0 | task 6303 | n_gen = 176, tg = 24.27 t/s, tg_3s = 24.99 t/s 7.07.897.595 I slot print_timing: id 1 | task 6243 | n_gen = 247, tg = 23.43 t/s, tg_3s = 24.79 t/s 7.09.205.846 I slot print_timing: id 1 | task 6243 | prompt eval time = 376.87 ms / 97 tokens ( 3.89 ms per token, 257.38 tokens per second) 7.09.205.849 I slot print_timing: id 1 | task 6243 | eval time = 11806.58 ms / 278 tokens ( 42.62 ms per token, 23.46 tokens per second) 7.09.205.850 I slot print_timing: id 1 | task 6243 | total time = 12183.46 ms / 375 tokens 7.09.205.851 I slot print_timing: id 1 | task 6243 | graphs reused = 5643 7.09.205.851 I slot print_timing: id 1 | task 6243 | graph reallocs = 0 / 0 (same size) / (changed size) 7.09.205.908 I slot release: id 1 | task 6243 | stop processing: n_tokens = 1489, truncated = 0 7.09.269.947 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.749 7.09.269.973 I slot launch_slot_: id 1 | task 6525 | processing task, is_child = 0 7.09.751.867 I slot print_timing: id 3 | task 5879 | n_gen = 641, tg = 21.95 t/s, tg_3s = 21.27 t/s 7.10.214.639 I slot print_timing: id 2 | task 5964 | n_gen = 570, tg = 22.45 t/s, tg_3s = 21.10 t/s 7.10.421.599 I slot print_timing: id 0 | task 6303 | n_gen = 240, tg = 23.33 t/s, tg_3s = 21.11 t/s 7.12.787.480 I slot print_timing: id 3 | task 5879 | n_gen = 713, tg = 22.12 t/s, tg_3s = 23.72 t/s 7.13.250.120 I slot print_timing: id 2 | task 5964 | n_gen = 642, tg = 22.59 t/s, tg_3s = 23.72 t/s 7.13.457.814 I slot print_timing: id 0 | task 6303 | n_gen = 312, tg = 23.42 t/s, tg_3s = 23.71 t/s 7.13.839.976 I slot print_timing: id 1 | task 6525 | n_gen = 100, tg = 23.68 t/s, tg_3s = 23.91 t/s 7.14.389.416 I slot print_timing: id 1 | task 6525 | prompt eval time = 388.50 ms / 98 tokens ( 3.96 ms per token, 252.25 tokens per second) 7.14.389.421 I slot print_timing: id 1 | task 6525 | eval time = 4730.93 ms / 113 tokens ( 42.24 ms per token, 23.67 tokens per second) 7.14.389.428 I slot print_timing: id 1 | task 6525 | total time = 5119.44 ms / 211 tokens 7.14.389.430 I slot print_timing: id 1 | task 6525 | graphs reused = 5754 7.14.389.431 I slot print_timing: id 1 | task 6525 | graph reallocs = 0 / 0 (same size) / (changed size) 7.14.389.487 I slot release: id 1 | task 6525 | stop processing: n_tokens = 1325, truncated = 0 7.14.453.683 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.842 7.14.453.710 I slot launch_slot_: id 1 | task 6641 | processing task, is_child = 0 7.15.812.709 I slot print_timing: id 3 | task 5879 | n_gen = 777, tg = 22.03 t/s, tg_3s = 21.16 t/s 7.16.276.175 I slot print_timing: id 2 | task 5964 | n_gen = 706, tg = 22.45 t/s, tg_3s = 21.15 t/s 7.16.484.569 I slot print_timing: id 0 | task 6303 | n_gen = 376, tg = 23.00 t/s, tg_3s = 21.14 t/s 7.18.819.205 I slot print_timing: id 3 | task 5879 | n_gen = 848, tg = 22.16 t/s, tg_3s = 23.62 t/s 7.19.027.945 I slot print_timing: id 1 | task 6641 | n_gen = 100, tg = 23.57 t/s, tg_3s = 23.81 t/s 7.19.284.284 I slot print_timing: id 2 | task 5964 | n_gen = 777, tg = 22.55 t/s, tg_3s = 23.60 t/s 7.19.493.055 I slot print_timing: id 0 | task 6303 | n_gen = 447, tg = 23.09 t/s, tg_3s = 23.60 t/s 7.21.836.217 I slot print_timing: id 3 | task 5879 | n_gen = 919, tg = 22.26 t/s, tg_3s = 23.53 t/s 7.22.045.429 I slot print_timing: id 1 | task 6641 | n_gen = 171, tg = 23.56 t/s, tg_3s = 23.53 t/s 7.22.301.816 I slot print_timing: id 2 | task 5964 | n_gen = 848, tg = 22.63 t/s, tg_3s = 23.53 t/s 7.22.511.041 I slot print_timing: id 0 | task 6303 | n_gen = 518, tg = 23.15 t/s, tg_3s = 23.53 t/s 7.24.253.866 I slot print_timing: id 1 | task 6641 | prompt eval time = 374.86 ms / 93 tokens ( 4.03 ms per token, 248.09 tokens per second) 7.24.253.870 I slot print_timing: id 1 | task 6641 | eval time = 9425.28 ms / 223 tokens ( 42.46 ms per token, 23.55 tokens per second) 7.24.253.870 I slot print_timing: id 1 | task 6641 | total time = 9800.15 ms / 316 tokens 7.24.253.871 I slot print_timing: id 1 | task 6641 | graphs reused = 5974 7.24.253.871 I slot print_timing: id 1 | task 6641 | graph reallocs = 0 / 0 (same size) / (changed size) 7.24.253.933 I slot release: id 1 | task 6641 | stop processing: n_tokens = 1430, truncated = 0 7.24.317.956 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.780 7.24.317.986 I slot launch_slot_: id 1 | task 6867 | processing task, is_child = 0 7.24.839.035 I slot print_timing: id 3 | task 5879 | n_gen = 982, tg = 22.17 t/s, tg_3s = 20.98 t/s 7.25.304.180 I slot print_timing: id 2 | task 5964 | n_gen = 911, tg = 22.51 t/s, tg_3s = 20.98 t/s 7.25.513.490 I slot print_timing: id 0 | task 6303 | n_gen = 581, tg = 22.89 t/s, tg_3s = 20.98 t/s 7.26.623.460 I slot print_timing: id 3 | task 5879 | prompt eval time = 374.25 ms / 106 tokens ( 3.53 ms per token, 283.23 tokens per second) 7.26.623.467 I slot print_timing: id 3 | task 5879 | eval time = 46028.36 ms / 1024 tokens ( 44.99 ms per token, 22.23 tokens per second) 7.26.623.468 I slot print_timing: id 3 | task 5879 | total time = 46402.61 ms / 1130 tokens 7.26.623.468 I slot print_timing: id 3 | task 5879 | graphs reused = 6018 7.26.623.469 I slot print_timing: id 3 | task 5879 | graph reallocs = 0 / 0 (same size) / (changed size) 7.26.623.523 I slot release: id 3 | task 5879 | stop processing: n_tokens = 2244, truncated = 0 7.26.664.490 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.497 7.26.711.448 I slot launch_slot_: id 3 | task 6916 | processing task, is_child = 0 7.28.342.975 I slot print_timing: id 2 | task 5964 | n_gen = 976, tg = 22.43 t/s, tg_3s = 21.39 t/s 7.28.551.560 I slot print_timing: id 0 | task 6303 | n_gen = 646, tg = 22.73 t/s, tg_3s = 21.40 t/s 7.29.187.795 I slot print_timing: id 1 | task 6867 | n_gen = 100, tg = 22.07 t/s, tg_3s = 22.30 t/s 7.30.375.437 I slot print_timing: id 2 | task 5964 | prompt eval time = 362.14 ms / 91 tokens ( 3.98 ms per token, 251.28 tokens per second) 7.30.375.441 I slot print_timing: id 2 | task 5964 | eval time = 45502.84 ms / 1024 tokens ( 44.48 ms per token, 22.48 tokens per second) 7.30.375.441 I slot print_timing: id 2 | task 5964 | total time = 45864.98 ms / 1115 tokens 7.30.375.442 I slot print_timing: id 2 | task 5964 | graphs reused = 6096 7.30.375.442 I slot print_timing: id 2 | task 5964 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.375.498 I slot release: id 2 | task 5964 | stop processing: n_tokens = 2229, truncated = 0 7.30.437.777 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.500 7.30.437.803 I slot launch_slot_: id 2 | task 6999 | processing task, is_child = 0 7.31.451.395 I slot print_timing: id 1 | task 6867 | prompt eval time = 384.99 ms / 76 tokens ( 5.07 ms per token, 197.41 tokens per second) 7.31.451.402 I slot print_timing: id 1 | task 6867 | eval time = 6748.41 ms / 145 tokens ( 46.86 ms per token, 21.34 tokens per second) 7.31.451.402 I slot print_timing: id 1 | task 6867 | total time = 7133.40 ms / 221 tokens 7.31.451.403 I slot print_timing: id 1 | task 6867 | graphs reused = 6109 7.31.451.403 I slot print_timing: id 1 | task 6867 | graph reallocs = 0 / 0 (same size) / (changed size) 7.31.451.458 I slot release: id 1 | task 6867 | stop processing: n_tokens = 1335, truncated = 0 7.31.515.427 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.835 7.31.515.454 I slot launch_slot_: id 1 | task 7017 | processing task, is_child = 0 7.31.728.722 I slot print_timing: id 0 | task 6303 | n_gen = 708, tg = 22.41 t/s, tg_3s = 19.51 t/s 7.31.847.428 I slot print_timing: id 3 | task 6916 | n_gen = 100, tg = 20.56 t/s, tg_3s = 20.77 t/s 7.32.356.143 I slot print_timing: id 3 | task 6916 | prompt eval time = 320.39 ms / 72 tokens ( 4.45 ms per token, 224.73 tokens per second) 7.32.356.147 I slot print_timing: id 3 | task 6916 | eval time = 5324.29 ms / 112 tokens ( 47.97 ms per token, 20.85 tokens per second) 7.32.356.148 I slot print_timing: id 3 | task 6916 | total time = 5644.68 ms / 184 tokens 7.32.356.149 I slot print_timing: id 3 | task 6916 | graphs reused = 6120 7.32.356.149 I slot print_timing: id 3 | task 6916 | graph reallocs = 0 / 0 (same size) / (changed size) 7.32.356.201 I slot release: id 3 | task 6916 | stop processing: n_tokens = 1297, truncated = 0 7.32.396.775 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.860 7.32.396.800 I slot launch_slot_: id 3 | task 7033 | processing task, is_child = 0 7.34.767.347 I slot print_timing: id 0 | task 6303 | n_gen = 773, tg = 22.32 t/s, tg_3s = 21.39 t/s 7.34.894.650 I slot print_timing: id 1 | task 7017 | prompt eval time = 327.37 ms / 64 tokens ( 5.12 ms per token, 195.50 tokens per second) 7.34.894.656 I slot print_timing: id 1 | task 7017 | eval time = 3051.82 ms / 68 tokens ( 45.55 ms per token, 21.95 tokens per second) 7.34.894.657 I slot print_timing: id 1 | task 7017 | total time = 3379.19 ms / 132 tokens 7.34.894.657 I slot print_timing: id 1 | task 7017 | graphs reused = 6171 7.34.894.658 I slot print_timing: id 1 | task 7017 | graph reallocs = 0 / 0 (same size) / (changed size) 7.34.894.713 I slot release: id 1 | task 7017 | stop processing: n_tokens = 1246, truncated = 0 7.34.958.693 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.895 7.34.958.719 I slot launch_slot_: id 1 | task 7089 | processing task, is_child = 0 7.35.802.331 I slot print_timing: id 2 | task 6999 | n_gen = 100, tg = 20.02 t/s, tg_3s = 20.22 t/s 7.37.150.758 I slot print_timing: id 3 | task 7033 | n_gen = 100, tg = 22.32 t/s, tg_3s = 22.54 t/s 7.37.781.140 I slot print_timing: id 0 | task 6303 | n_gen = 838, tg = 22.26 t/s, tg_3s = 21.57 t/s 7.38.417.022 I slot print_timing: id 1 | task 7089 | prompt eval time = 326.83 ms / 69 tokens ( 4.74 ms per token, 211.12 tokens per second) 7.38.417.026 I slot print_timing: id 1 | task 7089 | eval time = 3131.46 ms / 75 tokens ( 42.32 ms per token, 23.63 tokens per second) 7.38.417.027 I slot print_timing: id 1 | task 7089 | total time = 3458.30 ms / 144 tokens 7.38.417.027 I slot print_timing: id 1 | task 7089 | graphs reused = 6243 7.38.417.028 I slot print_timing: id 1 | task 7089 | graph reallocs = 0 / 0 (same size) / (changed size) 7.38.417.081 I slot release: id 1 | task 7089 | stop processing: n_tokens = 1258, truncated = 0 7.38.481.045 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.886 7.38.481.079 I slot launch_slot_: id 1 | task 7167 | processing task, is_child = 0 7.38.857.939 I slot print_timing: id 2 | task 6999 | n_gen = 165, tg = 20.50 t/s, tg_3s = 21.27 t/s 7.40.173.902 I slot print_timing: id 3 | task 7033 | n_gen = 164, tg = 21.85 t/s, tg_3s = 21.17 t/s 7.40.385.251 I slot print_timing: id 3 | task 7033 | prompt eval time = 318.27 ms / 74 tokens ( 4.30 ms per token, 232.51 tokens per second) 7.40.385.254 I slot print_timing: id 3 | task 7033 | eval time = 7670.17 ms / 169 tokens ( 45.66 ms per token, 21.90 tokens per second) 7.40.385.255 I slot print_timing: id 3 | task 7033 | total time = 7988.44 ms / 243 tokens 7.40.385.255 I slot print_timing: id 3 | task 7033 | graphs reused = 6278 7.40.385.256 I slot print_timing: id 3 | task 7033 | graph reallocs = 0 / 0 (same size) / (changed size) 7.40.385.315 I slot release: id 3 | task 7033 | stop processing: n_tokens = 1357, truncated = 0 7.40.425.898 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.822 7.40.425.920 I slot launch_slot_: id 3 | task 7207 | processing task, is_child = 0 7.40.786.265 I slot print_timing: id 0 | task 6303 | n_gen = 896, tg = 22.04 t/s, tg_3s = 19.30 t/s 7.41.890.961 I slot print_timing: id 2 | task 6999 | n_gen = 231, tg = 20.85 t/s, tg_3s = 21.76 t/s 7.43.285.439 I slot print_timing: id 1 | task 7167 | n_gen = 100, tg = 22.35 t/s, tg_3s = 22.58 t/s 7.43.788.273 I slot print_timing: id 0 | task 6303 | n_gen = 967, tg = 22.15 t/s, tg_3s = 23.65 t/s 7.44.463.593 I slot print_timing: id 1 | task 7167 | prompt eval time = 375.70 ms / 88 tokens ( 4.27 ms per token, 234.23 tokens per second) 7.44.463.597 I slot print_timing: id 1 | task 7167 | eval time = 5606.81 ms / 128 tokens ( 44.15 ms per token, 22.65 tokens per second) 7.44.463.597 I slot print_timing: id 1 | task 7167 | total time = 5982.51 ms / 216 tokens 7.44.463.598 I slot print_timing: id 1 | task 7167 | graphs reused = 6365 7.44.463.598 I slot print_timing: id 1 | task 7167 | graph reallocs = 0 / 0 (same size) / (changed size) 7.44.463.662 I slot release: id 1 | task 7167 | stop processing: n_tokens = 1330, truncated = 0 7.44.527.468 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.838 7.44.527.497 I slot launch_slot_: id 1 | task 7299 | processing task, is_child = 0 7.44.903.741 I slot print_timing: id 2 | task 6999 | n_gen = 296, tg = 21.00 t/s, tg_3s = 21.57 t/s 7.45.203.931 I slot print_timing: id 3 | task 7207 | n_gen = 100, tg = 22.22 t/s, tg_3s = 22.44 t/s 7.46.469.198 I slot print_timing: id 0 | task 6303 | prompt eval time = 368.10 ms / 108 tokens ( 3.41 ms per token, 293.40 tokens per second) 7.46.469.202 I slot print_timing: id 0 | task 6303 | eval time = 46291.06 ms / 1024 tokens ( 45.25 ms per token, 22.10 tokens per second) 7.46.469.203 I slot print_timing: id 0 | task 6303 | total time = 46659.16 ms / 1132 tokens 7.46.469.204 I slot print_timing: id 0 | task 6303 | graphs reused = 6402 7.46.469.204 I slot print_timing: id 0 | task 6303 | graph reallocs = 0 / 0 (same size) / (changed size) 7.46.469.270 I slot release: id 0 | task 6303 | stop processing: n_tokens = 2246, truncated = 0 7.46.514.713 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.496 7.46.560.294 I slot launch_slot_: id 0 | task 7341 | processing task, is_child = 0 7.47.541.757 I slot print_timing: id 2 | task 6999 | prompt eval time = 419.85 ms / 128 tokens ( 3.28 ms per token, 304.87 tokens per second) 7.47.541.763 I slot print_timing: id 2 | task 6999 | eval time = 16684.10 ms / 349 tokens ( 47.94 ms per token, 20.86 tokens per second) 7.47.541.764 I slot print_timing: id 2 | task 6999 | total time = 17103.95 ms / 477 tokens 7.47.541.765 I slot print_timing: id 2 | task 6999 | graphs reused = 6415 7.47.541.765 I slot print_timing: id 2 | task 6999 | graph reallocs = 0 / 0 (same size) / (changed size) 7.47.541.822 I slot release: id 2 | task 6999 | stop processing: n_tokens = 1590, truncated = 0 7.47.603.855 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.701 7.47.603.880 I slot launch_slot_: id 2 | task 7358 | processing task, is_child = 0 7.48.228.843 I slot print_timing: id 3 | task 7207 | n_gen = 155, tg = 20.59 t/s, tg_3s = 18.18 t/s 7.48.730.385 I slot print_timing: id 1 | task 7299 | prompt eval time = 327.68 ms / 65 tokens ( 5.04 ms per token, 198.37 tokens per second) 7.48.730.390 I slot print_timing: id 1 | task 7299 | eval time = 3875.20 ms / 76 tokens ( 51.67 ms per token, 19.35 tokens per second) 7.48.730.391 I slot print_timing: id 1 | task 7299 | total time = 4202.88 ms / 141 tokens 7.48.730.393 I slot print_timing: id 1 | task 7299 | graphs reused = 6431 7.48.730.394 I slot print_timing: id 1 | task 7299 | graph reallocs = 0 / 0 (same size) / (changed size) 7.48.730.454 I slot release: id 1 | task 7299 | stop processing: n_tokens = 1255, truncated = 0 7.48.794.428 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.888 7.48.794.452 I slot launch_slot_: id 1 | task 7380 | processing task, is_child = 0 7.51.078.675 I slot print_timing: id 3 | task 7207 | prompt eval time = 322.54 ms / 95 tokens ( 3.40 ms per token, 294.54 tokens per second) 7.51.078.679 I slot print_timing: id 3 | task 7207 | eval time = 10330.21 ms / 214 tokens ( 48.50 ms per token, 20.62 tokens per second) 7.51.078.679 I slot print_timing: id 3 | task 7207 | total time = 10652.75 ms / 309 tokens 7.51.078.680 I slot print_timing: id 3 | task 7207 | graphs reused = 6474 7.51.078.680 I slot print_timing: id 3 | task 7207 | graph reallocs = 0 / 0 (same size) / (changed size) 7.51.078.736 I slot release: id 3 | task 7207 | stop processing: n_tokens = 1423, truncated = 0 7.51.119.201 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.784 7.51.119.227 I slot launch_slot_: id 3 | task 7428 | processing task, is_child = 0 7.52.069.658 I slot print_timing: id 0 | task 7341 | n_gen = 100, tg = 19.49 t/s, tg_3s = 19.69 t/s 7.52.745.007 I slot print_timing: id 2 | task 7358 | n_gen = 100, tg = 20.72 t/s, tg_3s = 20.93 t/s 7.53.624.974 I slot print_timing: id 1 | task 7380 | n_gen = 100, tg = 22.50 t/s, tg_3s = 22.73 t/s 7.55.091.236 I slot print_timing: id 0 | task 7341 | n_gen = 172, tg = 21.11 t/s, tg_3s = 23.83 t/s 7.55.218.263 I slot print_timing: id 1 | task 7380 | prompt eval time = 431.19 ms / 123 tokens ( 3.51 ms per token, 285.26 tokens per second) 7.55.218.267 I slot print_timing: id 1 | task 7380 | eval time = 5992.61 ms / 138 tokens ( 43.74 ms per token, 22.86 tokens per second) 7.55.218.267 I slot print_timing: id 1 | task 7380 | total time = 6423.80 ms / 261 tokens 7.55.218.268 I slot print_timing: id 1 | task 7380 | graphs reused = 6562 7.55.218.268 I slot print_timing: id 1 | task 7380 | graph reallocs = 0 / 0 (same size) / (changed size) 7.55.218.324 I slot release: id 1 | task 7380 | stop processing: n_tokens = 1375, truncated = 0 7.55.281.744 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.811 7.55.281.768 I slot launch_slot_: id 1 | task 7522 | processing task, is_child = 0 7.55.757.958 I slot print_timing: id 2 | task 7358 | n_gen = 163, tg = 20.79 t/s, tg_3s = 20.91 t/s 7.55.975.058 I slot print_timing: id 3 | task 7428 | n_gen = 100, tg = 21.83 t/s, tg_3s = 22.05 t/s 7.56.059.010 I slot print_timing: id 3 | task 7428 | prompt eval time = 321.08 ms / 85 tokens ( 3.78 ms per token, 264.73 tokens per second) 7.56.059.014 I slot print_timing: id 3 | task 7428 | eval time = 4618.70 ms / 102 tokens ( 45.73 ms per token, 21.87 tokens per second) 7.56.059.015 I slot print_timing: id 3 | task 7428 | total time = 4939.77 ms / 187 tokens 7.56.059.015 I slot print_timing: id 3 | task 7428 | graphs reused = 6569 7.56.059.016 I slot print_timing: id 3 | task 7428 | graph reallocs = 0 / 0 (same size) / (changed size) 7.56.059.081 I slot release: id 3 | task 7428 | stop processing: n_tokens = 1301, truncated = 0 7.56.099.428 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.857 7.56.099.451 I slot launch_slot_: id 3 | task 7534 | processing task, is_child = 0 7.58.098.488 I slot print_timing: id 0 | task 7341 | n_gen = 229, tg = 20.53 t/s, tg_3s = 18.95 t/s 7.58.776.160 I slot print_timing: id 2 | task 7358 | n_gen = 229, tg = 21.09 t/s, tg_3s = 21.87 t/s 7.59.405.898 I slot print_timing: id 0 | task 7341 | prompt eval time = 430.01 ms / 146 tokens ( 2.95 ms per token, 339.52 tokens per second) 7.59.405.905 I slot print_timing: id 0 | task 7341 | eval time = 12415.58 ms / 260 tokens ( 47.94 ms per token, 20.86 tokens per second) 7.59.405.906 I slot print_timing: id 0 | task 7341 | total time = 12845.59 ms / 406 tokens 7.59.405.906 I slot print_timing: id 0 | task 7341 | graphs reused = 6639 7.59.405.907 I slot print_timing: id 0 | task 7341 | graph reallocs = 0 / 0 (same size) / (changed size) 7.59.405.968 I slot release: id 0 | task 7341 | stop processing: n_tokens = 1519, truncated = 0 7.59.451.283 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.734 7.59.451.315 I slot launch_slot_: id 0 | task 7609 | processing task, is_child = 0 8.00.418.142 I slot print_timing: id 1 | task 7522 | n_gen = 100, tg = 21.04 t/s, tg_3s = 21.25 t/s 8.00.884.611 I slot print_timing: id 3 | task 7534 | n_gen = 100, tg = 22.17 t/s, tg_3s = 22.39 t/s 8.01.808.943 I slot print_timing: id 2 | task 7358 | n_gen = 294, tg = 21.17 t/s, tg_3s = 21.43 t/s 8.03.449.985 I slot print_timing: id 1 | task 7522 | n_gen = 172, tg = 22.10 t/s, tg_3s = 23.75 t/s 8.03.917.409 I slot print_timing: id 3 | task 7534 | n_gen = 172, tg = 22.81 t/s, tg_3s = 23.74 t/s 8.03.997.017 I slot print_timing: id 0 | task 7609 | n_gen = 100, tg = 23.72 t/s, tg_3s = 23.96 t/s 8.04.673.692 I slot print_timing: id 1 | task 7522 | prompt eval time = 431.03 ms / 120 tokens ( 3.59 ms per token, 278.40 tokens per second) 8.04.673.696 I slot print_timing: id 1 | task 7522 | eval time = 8960.89 ms / 201 tokens ( 44.80 ms per token, 22.32 tokens per second) 8.04.673.697 I slot print_timing: id 1 | task 7522 | total time = 9391.92 ms / 321 tokens 8.04.673.697 I slot print_timing: id 1 | task 7522 | graphs reused = 6753 8.04.673.698 I slot print_timing: id 1 | task 7522 | graph reallocs = 0 / 0 (same size) / (changed size) 8.04.673.752 I slot release: id 1 | task 7522 | stop processing: n_tokens = 1435, truncated = 0 8.04.737.988 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.777 8.04.738.014 I slot launch_slot_: id 1 | task 7728 | processing task, is_child = 0 8.05.012.327 I slot print_timing: id 2 | task 7358 | n_gen = 364, tg = 21.30 t/s, tg_3s = 21.85 t/s 8.05.199.945 I slot print_timing: id 3 | task 7534 | prompt eval time = 319.83 ms / 85 tokens ( 3.76 ms per token, 265.77 tokens per second) 8.05.199.951 I slot print_timing: id 3 | task 7534 | eval time = 8780.66 ms / 195 tokens ( 45.26 ms per token, 22.09 tokens per second) 8.05.199.952 I slot print_timing: id 3 | task 7534 | total time = 9100.49 ms / 280 tokens 8.05.199.953 I slot print_timing: id 3 | task 7534 | graphs reused = 6754 8.05.199.953 I slot print_timing: id 3 | task 7534 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.200.005 I slot release: id 3 | task 7534 | stop processing: n_tokens = 1394, truncated = 0 8.05.242.054 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.800 8.05.242.078 I slot launch_slot_: id 3 | task 7734 | processing task, is_child = 0 8.07.032.003 I slot print_timing: id 0 | task 7609 | n_gen = 159, tg = 21.92 t/s, tg_3s = 19.44 t/s 8.07.748.457 I slot print_timing: id 0 | task 7609 | prompt eval time = 371.27 ms / 111 tokens ( 3.34 ms per token, 298.97 tokens per second) 8.07.748.461 I slot print_timing: id 0 | task 7609 | eval time = 7925.85 ms / 176 tokens ( 45.29 ms per token, 22.08 tokens per second) 8.07.748.461 I slot print_timing: id 0 | task 7609 | total time = 8297.13 ms / 287 tokens 8.07.748.462 I slot print_timing: id 0 | task 7609 | graphs reused = 6805 8.07.748.462 I slot print_timing: id 0 | task 7609 | graph reallocs = 0 / 0 (same size) / (changed size) 8.07.748.520 I slot release: id 0 | task 7609 | stop processing: n_tokens = 1401, truncated = 0 8.07.793.907 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.796 8.07.793.932 I slot launch_slot_: id 0 | task 7790 | processing task, is_child = 0 8.08.040.241 I slot print_timing: id 2 | task 7358 | n_gen = 424, tg = 21.07 t/s, tg_3s = 19.82 t/s 8.09.400.686 I slot print_timing: id 3 | task 7734 | prompt eval time = 320.68 ms / 71 tokens ( 4.52 ms per token, 221.41 tokens per second) 8.09.400.692 I slot print_timing: id 3 | task 7734 | eval time = 3837.92 ms / 86 tokens ( 45.15 ms per token, 22.15 tokens per second) 8.09.400.692 I slot print_timing: id 3 | task 7734 | total time = 4158.60 ms / 157 tokens 8.09.400.693 I slot print_timing: id 3 | task 7734 | graphs reused = 6835 8.09.400.694 I slot print_timing: id 3 | task 7734 | graph reallocs = 0 / 0 (same size) / (changed size) 8.09.400.743 I slot release: id 3 | task 7734 | stop processing: n_tokens = 1271, truncated = 0 8.09.441.508 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.877 8.09.441.530 I slot launch_slot_: id 3 | task 7824 | processing task, is_child = 0 8.10.016.264 I slot print_timing: id 1 | task 7728 | n_gen = 100, tg = 20.20 t/s, tg_3s = 20.40 t/s 8.11.070.322 I slot print_timing: id 2 | task 7358 | n_gen = 489, tg = 21.12 t/s, tg_3s = 21.45 t/s 8.12.337.230 I slot print_timing: id 3 | task 7824 | prompt eval time = 318.68 ms / 76 tokens ( 4.19 ms per token, 238.48 tokens per second) 8.12.337.237 I slot print_timing: id 3 | task 7824 | eval time = 2577.01 ms / 62 tokens ( 42.25 ms per token, 23.67 tokens per second) 8.12.337.238 I slot print_timing: id 3 | task 7824 | total time = 2895.69 ms / 138 tokens 8.12.337.239 I slot print_timing: id 3 | task 7824 | graphs reused = 6895 8.12.337.239 I slot print_timing: id 3 | task 7824 | graph reallocs = 0 / 0 (same size) / (changed size) 8.12.337.294 I slot release: id 3 | task 7824 | stop processing: n_tokens = 1252, truncated = 0 8.12.377.998 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.891 8.12.378.021 I slot launch_slot_: id 3 | task 7889 | processing task, is_child = 0 8.12.776.896 I slot print_timing: id 0 | task 7790 | n_gen = 100, tg = 21.26 t/s, tg_3s = 21.47 t/s 8.13.033.819 I slot print_timing: id 1 | task 7728 | n_gen = 166, tg = 20.84 t/s, tg_3s = 21.87 t/s 8.13.076.764 I slot print_timing: id 1 | task 7728 | prompt eval time = 376.49 ms / 96 tokens ( 3.92 ms per token, 254.99 tokens per second) 8.13.076.768 I slot print_timing: id 1 | task 7728 | eval time = 7962.26 ms / 167 tokens ( 47.97 ms per token, 20.85 tokens per second) 8.13.076.769 I slot print_timing: id 1 | task 7728 | total time = 8338.74 ms / 263 tokens 8.13.076.770 I slot print_timing: id 1 | task 7728 | graphs reused = 6903 8.13.076.770 I slot print_timing: id 1 | task 7728 | graph reallocs = 0 / 0 (same size) / (changed size) 8.13.076.829 I slot release: id 1 | task 7728 | stop processing: n_tokens = 1377, truncated = 0 8.13.141.347 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.810 8.13.141.377 I slot launch_slot_: id 1 | task 7902 | processing task, is_child = 0 8.14.095.501 I slot print_timing: id 2 | task 7358 | n_gen = 545, tg = 20.82 t/s, tg_3s = 18.51 t/s 8.15.780.583 I slot print_timing: id 0 | task 7790 | n_gen = 161, tg = 20.89 t/s, tg_3s = 20.31 t/s 8.17.135.025 I slot print_timing: id 2 | task 7358 | n_gen = 617, tg = 21.12 t/s, tg_3s = 23.69 t/s 8.17.305.380 I slot print_timing: id 3 | task 7889 | n_gen = 100, tg = 21.49 t/s, tg_3s = 21.71 t/s 8.17.808.662 I slot print_timing: id 1 | task 7902 | n_gen = 100, tg = 23.68 t/s, tg_3s = 23.92 t/s 8.18.819.423 I slot print_timing: id 0 | task 7790 | n_gen = 233, tg = 21.68 t/s, tg_3s = 23.69 t/s 8.20.171.436 I slot print_timing: id 2 | task 7358 | n_gen = 689, tg = 21.36 t/s, tg_3s = 23.71 t/s 8.20.340.847 I slot print_timing: id 3 | task 7889 | n_gen = 172, tg = 22.38 t/s, tg_3s = 23.72 t/s 8.20.844.379 I slot print_timing: id 1 | task 7902 | n_gen = 172, tg = 23.70 t/s, tg_3s = 23.72 t/s 8.21.855.119 I slot print_timing: id 0 | task 7790 | n_gen = 305, tg = 22.13 t/s, tg_3s = 23.72 t/s 8.22.620.935 I slot print_timing: id 3 | task 7889 | prompt eval time = 320.93 ms / 83 tokens ( 3.87 ms per token, 258.62 tokens per second) 8.22.620.944 I slot print_timing: id 3 | task 7889 | eval time = 9921.97 ms / 226 tokens ( 44.10 ms per token, 22.68 tokens per second) 8.22.620.944 I slot print_timing: id 3 | task 7889 | total time = 10242.91 ms / 309 tokens 8.22.620.945 I slot print_timing: id 3 | task 7889 | graphs reused = 7114 8.22.620.945 I slot print_timing: id 3 | task 7889 | graph reallocs = 0 / 0 (same size) / (changed size) 8.22.621.005 I slot release: id 3 | task 7889 | stop processing: n_tokens = 1423, truncated = 0 8.22.661.702 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.784 8.22.661.724 I slot launch_slot_: id 3 | task 8119 | processing task, is_child = 0 8.23.202.233 I slot print_timing: id 2 | task 7358 | n_gen = 755, tg = 21.40 t/s, tg_3s = 21.78 t/s 8.23.877.960 I slot print_timing: id 1 | task 7902 | n_gen = 238, tg = 23.12 t/s, tg_3s = 21.76 t/s 8.23.920.201 I slot print_timing: id 1 | task 7902 | prompt eval time = 486.40 ms / 142 tokens ( 3.43 ms per token, 291.94 tokens per second) 8.23.920.205 I slot print_timing: id 1 | task 7902 | eval time = 10292.42 ms / 239 tokens ( 43.25 ms per token, 23.12 tokens per second) 8.23.920.206 I slot print_timing: id 1 | task 7902 | total time = 10778.82 ms / 381 tokens 8.23.920.207 I slot print_timing: id 1 | task 7902 | graphs reused = 7135 8.23.920.207 I slot print_timing: id 1 | task 7902 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.920.270 I slot release: id 1 | task 7902 | stop processing: n_tokens = 1495, truncated = 0 8.23.984.570 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.746 8.23.984.594 I slot launch_slot_: id 1 | task 8145 | processing task, is_child = 0 8.24.879.414 I slot print_timing: id 0 | task 7790 | n_gen = 362, tg = 21.54 t/s, tg_3s = 18.85 t/s 8.26.236.081 I slot print_timing: id 2 | task 7358 | n_gen = 818, tg = 21.35 t/s, tg_3s = 20.77 t/s 8.27.549.038 I slot print_timing: id 3 | task 8119 | n_gen = 100, tg = 21.69 t/s, tg_3s = 21.90 t/s 8.27.884.569 I slot print_timing: id 0 | task 7790 | n_gen = 433, tg = 21.86 t/s, tg_3s = 23.63 t/s 8.28.143.941 I slot print_timing: id 3 | task 8119 | prompt eval time = 322.09 ms / 86 tokens ( 3.75 ms per token, 267.01 tokens per second) 8.28.143.947 I slot print_timing: id 3 | task 8119 | eval time = 5160.12 ms / 114 tokens ( 45.66 ms per token, 21.90 tokens per second) 8.28.143.948 I slot print_timing: id 3 | task 8119 | total time = 5482.21 ms / 200 tokens 8.28.143.948 I slot print_timing: id 3 | task 8119 | graphs reused = 7221 8.28.143.949 I slot print_timing: id 3 | task 8119 | graph reallocs = 0 / 0 (same size) / (changed size) 8.28.144.008 I slot release: id 3 | task 8119 | stop processing: n_tokens = 1314, truncated = 0 8.28.185.003 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.849 8.28.185.027 I slot launch_slot_: id 3 | task 8237 | processing task, is_child = 0 8.28.844.805 I slot print_timing: id 1 | task 8145 | n_gen = 100, tg = 22.34 t/s, tg_3s = 22.56 t/s 8.29.270.984 I slot print_timing: id 2 | task 7358 | n_gen = 884, tg = 21.38 t/s, tg_3s = 21.75 t/s 8.30.921.038 I slot print_timing: id 0 | task 7790 | n_gen = 499, tg = 21.84 t/s, tg_3s = 21.74 t/s 8.31.007.426 I slot print_timing: id 1 | task 8145 | prompt eval time = 427.94 ms / 103 tokens ( 4.15 ms per token, 240.69 tokens per second) 8.31.007.429 I slot print_timing: id 1 | task 8145 | eval time = 6594.89 ms / 151 tokens ( 43.97 ms per token, 22.74 tokens per second) 8.31.007.431 I slot print_timing: id 1 | task 8145 | total time = 7022.82 ms / 254 tokens 8.31.007.431 I slot print_timing: id 1 | task 8145 | graphs reused = 7279 8.31.007.432 I slot print_timing: id 1 | task 8145 | graph reallocs = 0 / 0 (same size) / (changed size) 8.31.007.487 I slot release: id 1 | task 8145 | stop processing: n_tokens = 1368, truncated = 0 8.31.071.483 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.815 8.31.071.506 I slot launch_slot_: id 1 | task 8300 | processing task, is_child = 0 8.32.273.419 I slot print_timing: id 2 | task 7358 | n_gen = 946, tg = 21.33 t/s, tg_3s = 20.65 t/s 8.33.082.641 I slot print_timing: id 3 | task 8237 | prompt eval time = 319.03 ms / 71 tokens ( 4.49 ms per token, 222.55 tokens per second) 8.33.082.644 I slot print_timing: id 3 | task 8237 | eval time = 4578.58 ms / 100 tokens ( 46.25 ms per token, 21.62 tokens per second) 8.33.082.645 I slot print_timing: id 3 | task 8237 | total time = 4897.61 ms / 171 tokens 8.33.082.645 I slot print_timing: id 3 | task 8237 | graphs reused = 7315 8.33.082.646 I slot print_timing: id 3 | task 8237 | graph reallocs = 0 / 0 (same size) / (changed size) 8.33.082.701 I slot release: id 3 | task 8237 | stop processing: n_tokens = 1285, truncated = 0 8.33.123.613 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.868 8.33.123.635 I slot launch_slot_: id 3 | task 8341 | processing task, is_child = 0 8.33.956.280 I slot print_timing: id 0 | task 7790 | n_gen = 556, tg = 21.48 t/s, tg_3s = 18.78 t/s 8.35.275.640 I slot print_timing: id 2 | task 7358 | n_gen = 1011, tg = 21.35 t/s, tg_3s = 21.65 t/s 8.35.828.721 I slot print_timing: id 2 | task 7358 | prompt eval time = 362.51 ms / 82 tokens ( 4.42 ms per token, 226.20 tokens per second) 8.35.828.728 I slot print_timing: id 2 | task 7358 | eval time = 47862.33 ms / 1024 tokens ( 46.79 ms per token, 21.37 tokens per second) 8.35.828.728 I slot print_timing: id 2 | task 7358 | total time = 48224.83 ms / 1106 tokens 8.35.828.729 I slot print_timing: id 2 | task 7358 | graphs reused = 7370 8.35.828.730 I slot print_timing: id 2 | task 7358 | graph reallocs = 0 / 0 (same size) / (changed size) 8.35.828.784 I slot release: id 2 | task 7358 | stop processing: n_tokens = 2220, truncated = 0 8.36.013.419 I slot print_timing: id 1 | task 8300 | n_gen = 100, tg = 21.95 t/s, tg_3s = 22.17 t/s 8.36.973.229 I slot print_timing: id 0 | task 7790 | n_gen = 618, tg = 21.38 t/s, tg_3s = 20.55 t/s 8.38.068.288 I slot print_timing: id 3 | task 8341 | prompt eval time = 322.57 ms / 70 tokens ( 4.61 ms per token, 217.00 tokens per second) 8.38.068.300 I slot print_timing: id 3 | task 8341 | eval time = 4622.05 ms / 92 tokens ( 50.79 ms per token, 19.69 tokens per second) 8.38.068.301 I slot print_timing: id 3 | task 8341 | total time = 4944.62 ms / 162 tokens 8.38.068.302 I slot print_timing: id 3 | task 8341 | graphs reused = 7370 8.38.068.303 I slot print_timing: id 3 | task 8341 | graph reallocs = 0 / 0 (same size) / (changed size) 8.38.068.433 I slot release: id 3 | task 8341 | stop processing: n_tokens = 1277, truncated = 0 8.39.048.155 I slot print_timing: id 1 | task 8300 | n_gen = 159, tg = 20.94 t/s, tg_3s = 19.44 t/s 8.39.984.303 I slot print_timing: id 0 | task 7790 | n_gen = 688, tg = 21.56 t/s, tg_3s = 23.25 t/s 8.41.356.697 I slot print_timing: id 1 | task 8300 | prompt eval time = 432.19 ms / 117 tokens ( 3.69 ms per token, 270.71 tokens per second) 8.41.356.701 I slot print_timing: id 1 | task 8300 | eval time = 9852.99 ms / 223 tokens ( 44.38 ms per token, 22.53 tokens per second) 8.41.356.702 I slot print_timing: id 1 | task 8300 | total time = 10285.18 ms / 340 tokens 8.41.356.702 I slot print_timing: id 1 | task 8300 | graphs reused = 7460 8.41.356.703 I slot print_timing: id 1 | task 8300 | graph reallocs = 0 / 0 (same size) / (changed size) 8.41.356.761 I slot release: id 1 | task 8300 | stop processing: n_tokens = 1454, truncated = 0 8.42.987.574 I slot print_timing: id 0 | task 7790 | n_gen = 795, tg = 22.77 t/s, tg_3s = 35.63 t/s 8.45.998.194 I slot print_timing: id 0 | task 7790 | n_gen = 922, tg = 24.31 t/s, tg_3s = 42.18 t/s 8.48.419.004 I slot print_timing: id 0 | task 7790 | prompt eval time = 325.99 ms / 86 tokens ( 3.79 ms per token, 263.81 tokens per second) 8.48.419.015 I slot print_timing: id 0 | task 7790 | eval time = 40299.07 ms / 1024 tokens ( 39.39 ms per token, 25.39 tokens per second) 8.48.419.018 I slot print_timing: id 0 | task 7790 | total time = 40625.06 ms / 1110 tokens 8.48.419.018 I slot print_timing: id 0 | task 7790 | graphs reused = 7756 8.48.419.019 I slot print_timing: id 0 | task 7790 | graph reallocs = 0 / 0 (same size) / (changed size) 8.48.419.067 I slot release: id 0 | task 7790 | stop processing: n_tokens = 2224, truncated = 0 8.48.438.175 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2220, t_last = 327320364039 8.48.482.792 I slot launch_slot_: id 2 | task 8824 | processing task, is_child = 0 8.48.505.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.306 MiB) 8.48.505.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.151 MiB) 8.48.505.140 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.106 MiB) 8.48.505.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.629 MiB) 8.48.505.144 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 49.228 MiB) 8.48.543.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.490 MiB) 8.48.543.878 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.614 MiB) 8.48.543.880 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.246 MiB) 8.48.543.882 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.383 MiB) 8.48.543.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 8.48.543.887 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.368 MiB) 8.48.543.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 30.030 MiB) 8.48.543.892 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 51.690 MiB) 8.48.543.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.922 MiB) 8.48.543.896 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.490 MiB) 8.48.588.612 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1277, t_last = 327322603688 8.48.589.409 I slot launch_slot_: id 3 | task 8825 | processing task, is_child = 0 8.48.589.616 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1454, t_last = 327325892016 8.48.590.412 I slot launch_slot_: id 1 | task 8826 | processing task, is_child = 0 8.48.590.537 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2224, t_last = 327332954322 8.48.591.372 I slot launch_slot_: id 0 | task 8827 | processing task, is_child = 0 8.54.334.720 I slot print_timing: id 0 | task 8827 | prompt processing, n_tokens = 842, progress = 0.88, t = 5.74 s / 146.61 tokens per second 8.54.372.114 I slot print_timing: id 1 | task 8826 | prompt processing, n_tokens = 865, progress = 0.89, t = 5.74 s / 150.61 tokens per second 8.54.376.415 I slot print_timing: id 2 | task 8824 | prompt processing, n_tokens = 642, progress = 0.84, t = 5.74 s / 111.78 tokens per second 8.54.380.192 I slot print_timing: id 3 | task 8825 | prompt processing, n_tokens = 616, progress = 0.79, t = 5.74 s / 107.26 tokens per second 8.55.370.949 I slot print_timing: id 0 | task 8827 | prompt processing, n_tokens = 955, progress = 1.00, t = 6.78 s / 140.87 tokens per second 8.55.515.372 I slot print_timing: id 1 | task 8826 | prompt processing, n_tokens = 972, progress = 1.00, t = 6.78 s / 143.37 tokens per second 8.55.520.188 I slot print_timing: id 2 | task 8824 | prompt processing, n_tokens = 762, progress = 0.99, t = 6.78 s / 112.40 tokens per second 8.55.524.515 I slot print_timing: id 3 | task 8825 | prompt processing, n_tokens = 774, progress = 0.99, t = 6.78 s / 114.17 tokens per second 8.55.653.503 I slot print_timing: id 0 | task 8827 | prompt eval time = 7015.32 ms / 959 tokens ( 7.32 ms per token, 136.70 tokens per second) 8.55.653.510 I slot print_timing: id 0 | task 8827 | eval time = 46.80 ms / 2 tokens ( 46.80 ms per token, 21.37 tokens per second) 8.55.653.511 I slot print_timing: id 0 | task 8827 | total time = 7062.12 ms / 961 tokens 8.55.653.512 I slot print_timing: id 0 | task 8827 | graphs reused = 7757 8.55.653.512 I slot print_timing: id 0 | task 8827 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.653.570 I slot release: id 0 | task 8827 | stop processing: n_tokens = 969, truncated = 0 8.55.655.363 I slot print_timing: id 1 | task 8826 | prompt eval time = 7017.86 ms / 976 tokens ( 7.19 ms per token, 139.07 tokens per second) 8.55.655.367 I slot print_timing: id 1 | task 8826 | eval time = 46.05 ms / 2 tokens ( 46.05 ms per token, 21.72 tokens per second) 8.55.655.368 I slot print_timing: id 1 | task 8826 | total time = 7063.91 ms / 978 tokens 8.55.655.368 I slot print_timing: id 1 | task 8826 | graphs reused = 7757 8.55.655.369 I slot print_timing: id 1 | task 8826 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.655.411 I slot release: id 1 | task 8826 | stop processing: n_tokens = 986, truncated = 0 8.55.657.215 I slot print_timing: id 2 | task 8824 | prompt eval time = 7020.21 ms / 766 tokens ( 9.16 ms per token, 109.11 tokens per second) 8.55.657.219 I slot print_timing: id 2 | task 8824 | eval time = 45.49 ms / 2 tokens ( 45.49 ms per token, 21.98 tokens per second) 8.55.657.220 I slot print_timing: id 2 | task 8824 | total time = 7065.70 ms / 768 tokens 8.55.657.220 I slot print_timing: id 2 | task 8824 | graphs reused = 7757 8.55.657.220 I slot print_timing: id 2 | task 8824 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.657.249 I slot release: id 2 | task 8824 | stop processing: n_tokens = 776, truncated = 0 8.55.659.036 I slot print_timing: id 3 | task 8825 | prompt eval time = 7022.63 ms / 778 tokens ( 9.03 ms per token, 110.78 tokens per second) 8.55.659.038 I slot print_timing: id 3 | task 8825 | eval time = 44.82 ms / 2 tokens ( 44.82 ms per token, 22.31 tokens per second) 8.55.659.039 I slot print_timing: id 3 | task 8825 | total time = 7067.45 ms / 780 tokens 8.55.659.039 I slot print_timing: id 3 | task 8825 | graphs reused = 7757 8.55.659.040 I slot print_timing: id 3 | task 8825 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.659.069 I slot release: id 3 | task 8825 | stop processing: n_tokens = 788, truncated = 0 8.55.664.628 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 969, t_last = 327340188825 8.55.664.751 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.290 MiB) 8.55.664.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 8.55.664.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 8.55.664.762 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.029 MiB) 8.55.683.248 I slot launch_slot_: id 0 | task 8833 | processing task, is_child = 0 8.55.683.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.321 MiB) 8.55.683.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.798 MiB) 8.55.683.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.783 MiB) 8.55.683.369 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.044 MiB) 8.55.683.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.953 MiB) 8.55.683.550 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.614 MiB) 8.55.699.491 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.368 MiB) 8.55.699.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 8.55.699.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.414 MiB) 8.55.699.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.215 MiB) 8.55.700.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.013 MiB) 8.55.720.815 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.735 MiB) 8.55.721.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.736 MiB) 8.55.721.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.907 MiB) 8.55.721.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.629 MiB) 8.55.722.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.814 MiB) 8.55.738.723 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 327340190666 8.55.738.917 I slot launch_slot_: id 1 | task 8834 | processing task, is_child = 0 8.55.739.039 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 776, t_last = 327340192504 8.55.739.140 I slot launch_slot_: id 2 | task 8835 | processing task, is_child = 0 8.55.739.201 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 788, t_last = 327340194324 8.55.739.292 I slot launch_slot_: id 3 | task 8836 | processing task, is_child = 0 9.01.045.291 I slot print_timing: id 0 | task 8833 | prompt processing, n_tokens = 690, progress = 0.82, t = 5.31 s / 130.04 tokens per second 9.01.078.078 I slot print_timing: id 1 | task 8834 | prompt processing, n_tokens = 690, progress = 0.87, t = 5.31 s / 130.06 tokens per second 9.01.083.558 I slot print_timing: id 2 | task 8835 | prompt processing, n_tokens = 690, progress = 0.87, t = 5.30 s / 130.08 tokens per second 9.01.087.532 I slot print_timing: id 3 | task 8836 | prompt processing, n_tokens = 690, progress = 0.81, t = 5.30 s / 130.09 tokens per second 9.02.056.212 I slot print_timing: id 0 | task 8833 | prompt processing, n_tokens = 837, progress = 1.00, t = 6.32 s / 132.50 tokens per second 9.02.199.060 I slot print_timing: id 1 | task 8834 | prompt processing, n_tokens = 792, progress = 1.00, t = 6.32 s / 125.39 tokens per second 9.02.202.259 I slot print_timing: id 2 | task 8835 | prompt processing, n_tokens = 794, progress = 1.00, t = 6.32 s / 125.72 tokens per second 9.02.207.154 I slot print_timing: id 3 | task 8836 | prompt processing, n_tokens = 845, progress = 1.00, t = 6.31 s / 133.81 tokens per second 9.02.327.478 I slot print_timing: id 0 | task 8833 | prompt eval time = 6547.51 ms / 841 tokens ( 7.79 ms per token, 128.45 tokens per second) 9.02.327.480 I slot print_timing: id 0 | task 8833 | eval time = 40.66 ms / 2 tokens ( 40.66 ms per token, 24.59 tokens per second) 9.02.327.485 I slot print_timing: id 0 | task 8833 | total time = 6588.17 ms / 843 tokens 9.02.327.485 I slot print_timing: id 0 | task 8833 | graphs reused = 7757 9.02.327.485 I slot print_timing: id 0 | task 8833 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.327.525 I slot release: id 0 | task 8833 | stop processing: n_tokens = 851, truncated = 0 9.02.328.650 I slot print_timing: id 1 | task 8834 | prompt eval time = 6548.08 ms / 796 tokens ( 8.23 ms per token, 121.56 tokens per second) 9.02.328.657 I slot print_timing: id 1 | task 8834 | eval time = 40.71 ms / 2 tokens ( 40.71 ms per token, 24.57 tokens per second) 9.02.328.657 I slot print_timing: id 1 | task 8834 | total time = 6588.79 ms / 798 tokens 9.02.328.657 I slot print_timing: id 1 | task 8834 | graphs reused = 7757 9.02.328.658 I slot print_timing: id 1 | task 8834 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.328.680 I slot release: id 1 | task 8834 | stop processing: n_tokens = 806, truncated = 0 9.02.329.775 I slot print_timing: id 2 | task 8835 | prompt eval time = 6548.40 ms / 798 tokens ( 8.21 ms per token, 121.86 tokens per second) 9.02.329.776 I slot print_timing: id 2 | task 8835 | eval time = 40.75 ms / 2 tokens ( 40.75 ms per token, 24.54 tokens per second) 9.02.329.778 I slot print_timing: id 2 | task 8835 | total time = 6589.15 ms / 800 tokens 9.02.329.778 I slot print_timing: id 2 | task 8835 | graphs reused = 7757 9.02.329.778 I slot print_timing: id 2 | task 8835 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.329.808 I slot release: id 2 | task 8835 | stop processing: n_tokens = 808, truncated = 0 9.02.330.926 I slot print_timing: id 3 | task 8836 | prompt eval time = 6548.91 ms / 849 tokens ( 7.71 ms per token, 129.64 tokens per second) 9.02.330.928 I slot print_timing: id 3 | task 8836 | eval time = 40.80 ms / 2 tokens ( 40.80 ms per token, 24.51 tokens per second) 9.02.330.928 I slot print_timing: id 3 | task 8836 | total time = 6589.71 ms / 851 tokens 9.02.330.928 I slot print_timing: id 3 | task 8836 | graphs reused = 7757 9.02.330.929 I slot print_timing: id 3 | task 8836 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.330.949 I slot release: id 3 | task 8836 | stop processing: n_tokens = 859, truncated = 0 9.02.334.383 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.874 (> 0.100 thold), f_keep = 0.853 9.02.334.424 I slot launch_slot_: id 0 | task 8842 | processing task, is_child = 0 9.02.334.516 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.829 MiB) 9.02.334.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.304 MiB) 9.02.334.522 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.951 MiB) 9.02.334.524 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 9.02.334.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.013 MiB) 9.02.351.318 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.399 MiB) 9.02.351.436 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.507 MiB) 9.02.351.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 33.969 MiB) 9.02.352.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.660 MiB) 9.02.352.335 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.814 MiB) 9.02.369.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.907 MiB) 9.02.369.531 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.430 MiB) 9.02.369.737 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.982 MiB) 9.02.370.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.982 MiB) 9.02.370.380 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.752 MiB) 9.02.370.664 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.738 MiB) 9.02.387.643 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 327346863935 9.02.387.801 I slot launch_slot_: id 1 | task 8843 | processing task, is_child = 0 9.02.387.930 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 808, t_last = 327346865063 9.02.388.024 I slot launch_slot_: id 2 | task 8844 | processing task, is_child = 0 9.02.388.089 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 859, t_last = 327346866204 9.02.388.187 I slot launch_slot_: id 3 | task 8845 | processing task, is_child = 0 9.07.168.034 I slot print_timing: id 1 | task 8843 | prompt processing, n_tokens = 739, progress = 0.85, t = 4.78 s / 154.71 tokens per second 9.07.170.869 I slot print_timing: id 2 | task 8844 | prompt processing, n_tokens = 739, progress = 0.84, t = 4.78 s / 154.72 tokens per second 9.07.172.945 I slot print_timing: id 3 | task 8845 | prompt processing, n_tokens = 817, progress = 0.86, t = 4.78 s / 171.07 tokens per second 9.08.004.610 I slot print_timing: id 0 | task 8842 | prompt eval time = 4779.82 ms / 105 tokens ( 45.52 ms per token, 21.97 tokens per second) 9.08.004.615 I slot print_timing: id 0 | task 8842 | eval time = 836.59 ms / 2 tokens ( 836.59 ms per token, 1.20 tokens per second) 9.08.004.615 I slot print_timing: id 0 | task 8842 | total time = 5616.41 ms / 107 tokens 9.08.004.616 I slot print_timing: id 0 | task 8842 | graphs reused = 7757 9.08.004.616 I slot print_timing: id 0 | task 8842 | graph reallocs = 0 / 0 (same size) / (changed size) 9.08.004.661 I slot release: id 0 | task 8842 | stop processing: n_tokens = 832, truncated = 0 9.08.004.675 I slot print_timing: id 1 | task 8843 | prompt processing, n_tokens = 864, progress = 1.00, t = 5.61 s / 153.93 tokens per second 9.08.006.833 I slot print_timing: id 2 | task 8844 | prompt processing, n_tokens = 874, progress = 1.00, t = 5.61 s / 155.72 tokens per second 9.08.008.975 I slot print_timing: id 3 | task 8845 | prompt processing, n_tokens = 945, progress = 1.00, t = 5.61 s / 168.39 tokens per second 9.08.091.287 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 327352539916 9.08.091.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 9.08.091.474 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 9.08.091.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 9.08.091.486 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 9.08.091.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 9.08.091.694 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.321 MiB) 9.08.092.224 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.784 MiB) 9.08.092.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 9.08.124.254 I slot launch_slot_: id 0 | task 8850 | processing task, is_child = 0 9.09.026.573 I slot print_timing: id 1 | task 8843 | prompt eval time = 5695.01 ms / 868 tokens ( 6.56 ms per token, 152.41 tokens per second) 9.09.026.578 I slot print_timing: id 1 | task 8843 | eval time = 941.43 ms / 2 tokens ( 941.43 ms per token, 1.06 tokens per second) 9.09.026.579 I slot print_timing: id 1 | task 8843 | total time = 6636.44 ms / 870 tokens 9.09.026.579 I slot print_timing: id 1 | task 8843 | graphs reused = 7757 9.09.026.580 I slot print_timing: id 1 | task 8843 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.026.661 I slot release: id 1 | task 8843 | stop processing: n_tokens = 878, truncated = 0 9.09.027.819 I slot print_timing: id 2 | task 8844 | prompt eval time = 5697.74 ms / 878 tokens ( 6.49 ms per token, 154.10 tokens per second) 9.09.027.821 I slot print_timing: id 2 | task 8844 | eval time = 939.50 ms / 2 tokens ( 939.50 ms per token, 1.06 tokens per second) 9.09.027.821 I slot print_timing: id 2 | task 8844 | total time = 6637.25 ms / 880 tokens 9.09.027.821 I slot print_timing: id 2 | task 8844 | graphs reused = 7757 9.09.027.822 I slot print_timing: id 2 | task 8844 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.027.859 I slot release: id 2 | task 8844 | stop processing: n_tokens = 888, truncated = 0 9.09.029.000 I slot print_timing: id 3 | task 8845 | prompt eval time = 5700.13 ms / 949 tokens ( 6.01 ms per token, 166.49 tokens per second) 9.09.029.002 I slot print_timing: id 3 | task 8845 | eval time = 937.72 ms / 2 tokens ( 937.72 ms per token, 1.07 tokens per second) 9.09.029.003 I slot print_timing: id 3 | task 8845 | total time = 6637.85 ms / 951 tokens 9.09.029.003 I slot print_timing: id 3 | task 8845 | graphs reused = 7757 9.09.029.003 I slot print_timing: id 3 | task 8845 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.029.041 I slot release: id 3 | task 8845 | stop processing: n_tokens = 959, truncated = 0 9.09.815.125 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 878, t_last = 327353561918 9.09.815.208 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.521 MiB) 9.09.815.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.568 MiB) 9.09.815.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.753 MiB) 9.09.815.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.507 MiB) 9.09.816.121 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.507 MiB) 9.09.816.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 9.10.084.655 I slot launch_slot_: id 1 | task 8854 | processing task, is_child = 0 9.10.084.866 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.999 MiB) 9.10.084.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.091 MiB) 9.10.085.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.922 MiB) 9.10.086.504 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 9.10.087.123 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.783 MiB) 9.10.087.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.075 MiB) 9.10.122.348 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 9.10.122.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.015 MiB) 9.10.123.133 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.213 MiB) 9.10.123.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.091 MiB) 9.10.123.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.368 MiB) 9.10.123.985 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.738 MiB) 9.10.147.528 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 888, t_last = 327353563114 9.10.147.689 I slot launch_slot_: id 2 | task 8855 | processing task, is_child = 0 9.10.147.765 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 959, t_last = 327353564296 9.10.147.883 I slot launch_slot_: id 3 | task 8856 | processing task, is_child = 0 9.13.359.017 I slot print_timing: id 1 | task 8854 | prompt processing, n_tokens = 507, progress = 0.50, t = 3.20 s / 158.41 tokens per second 9.13.366.006 I slot print_timing: id 2 | task 8855 | prompt processing, n_tokens = 402, progress = 0.44, t = 3.20 s / 125.63 tokens per second 9.13.369.367 I slot print_timing: id 3 | task 8856 | prompt processing, n_tokens = 747, progress = 0.42, t = 3.20 s / 233.51 tokens per second 9.15.937.294 I slot print_timing: id 0 | task 8850 | prompt eval time = 5234.64 ms / 988 tokens ( 5.30 ms per token, 188.74 tokens per second) 9.15.937.299 I slot print_timing: id 0 | task 8850 | eval time = 2578.38 ms / 2 tokens ( 2578.38 ms per token, 0.39 tokens per second) 9.15.937.299 I slot print_timing: id 0 | task 8850 | total time = 7813.02 ms / 990 tokens 9.15.937.300 I slot print_timing: id 0 | task 8850 | graphs reused = 7757 9.15.937.301 I slot print_timing: id 0 | task 8850 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.937.362 I slot release: id 0 | task 8850 | stop processing: n_tokens = 998, truncated = 0 9.15.937.379 I slot print_timing: id 1 | task 8854 | prompt processing, n_tokens = 871, progress = 0.85, t = 5.78 s / 150.64 tokens per second 9.15.939.728 I slot print_timing: id 2 | task 8855 | prompt processing, n_tokens = 747, progress = 0.82, t = 5.78 s / 129.21 tokens per second 9.15.941.901 I slot print_timing: id 3 | task 8856 | prompt processing, n_tokens = 1294, progress = 0.72, t = 5.78 s / 223.86 tokens per second 9.16.964.126 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 998, t_last = 327360472617 9.16.964.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.660 MiB) 9.16.964.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.414 MiB) 9.16.964.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.075 MiB) 9.16.964.445 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 9.16.965.507 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 9.16.966.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.075 MiB) 9.17.656.649 I slot launch_slot_: id 0 | task 8860 | processing task, is_child = 0 9.17.657.340 I slot print_timing: id 1 | task 8854 | prompt processing, n_tokens = 1019, progress = 1.00, t = 6.81 s / 149.63 tokens per second 9.17.661.884 I slot print_timing: id 2 | task 8855 | prompt processing, n_tokens = 914, progress = 1.00, t = 6.81 s / 134.22 tokens per second 9.17.666.095 I slot print_timing: id 3 | task 8856 | prompt processing, n_tokens = 1806, progress = 1.00, t = 6.81 s / 265.25 tokens per second 9.19.216.572 I slot print_timing: id 1 | task 8854 | prompt eval time = 8347.06 ms / 1023 tokens ( 8.16 ms per token, 122.56 tokens per second) 9.19.216.586 I slot print_timing: id 1 | task 8854 | eval time = 715.63 ms / 2 tokens ( 715.63 ms per token, 1.40 tokens per second) 9.19.216.588 I slot print_timing: id 1 | task 8854 | total time = 9062.69 ms / 1025 tokens 9.19.216.590 I slot print_timing: id 1 | task 8854 | graphs reused = 7757 9.19.216.591 I slot print_timing: id 1 | task 8854 | graph reallocs = 0 / 0 (same size) / (changed size) 9.19.216.752 I slot release: id 1 | task 8854 | stop processing: n_tokens = 1033, truncated = 0 9.19.219.204 I slot print_timing: id 2 | task 8855 | prompt eval time = 8348.54 ms / 918 tokens ( 9.09 ms per token, 109.96 tokens per second) 9.19.219.211 I slot print_timing: id 2 | task 8855 | eval time = 716.08 ms / 2 tokens ( 716.08 ms per token, 1.40 tokens per second) 9.19.219.213 I slot print_timing: id 2 | task 8855 | total time = 9064.62 ms / 920 tokens 9.19.219.214 I slot print_timing: id 2 | task 8855 | graphs reused = 7757 9.19.219.216 I slot print_timing: id 2 | task 8855 | graph reallocs = 0 / 0 (same size) / (changed size) 9.19.219.329 I slot release: id 2 | task 8855 | stop processing: n_tokens = 928, truncated = 0 9.19.221.361 I slot print_timing: id 3 | task 8856 | prompt eval time = 8349.80 ms / 1810 tokens ( 4.61 ms per token, 216.77 tokens per second) 9.19.221.370 I slot print_timing: id 3 | task 8856 | eval time = 716.22 ms / 2 tokens ( 716.22 ms per token, 1.40 tokens per second) 9.19.221.371 I slot print_timing: id 3 | task 8856 | total time = 9066.02 ms / 1812 tokens 9.19.221.373 I slot print_timing: id 3 | task 8856 | graphs reused = 7757 9.19.221.374 I slot print_timing: id 3 | task 8856 | graph reallocs = 0 / 0 (same size) / (changed size) 9.19.221.566 I slot release: id 3 | task 8856 | stop processing: n_tokens = 1820, truncated = 0 9.19.237.502 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1033, t_last = 327363752008 9.19.237.675 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 9.19.237.683 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.306 MiB) 9.19.237.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.845 MiB) 9.19.238.217 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.829 MiB) 9.19.238.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.292 MiB) 9.19.238.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.738 MiB) 9.19.239.344 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.213 MiB) 9.19.633.152 I slot launch_slot_: id 1 | task 8864 | processing task, is_child = 0 9.19.633.387 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 9.19.634.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.798 MiB) 9.19.635.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.753 MiB) 9.19.635.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 35.199 MiB) 9.19.636.483 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 9.19.637.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.153 MiB) 9.19.672.512 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.629 MiB) 9.19.672.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 33.969 MiB) 9.19.673.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.568 MiB) 9.19.673.725 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.891 MiB) 9.19.674.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.521 MiB) 9.19.674.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.814 MiB) 9.19.674.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.784 MiB) 9.19.700.078 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 327363754584 9.19.700.268 I slot launch_slot_: id 2 | task 8865 | processing task, is_child = 0 9.19.700.390 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1820, t_last = 327363756830 9.19.700.548 I slot launch_slot_: id 3 | task 8866 | processing task, is_child = 0 9.23.590.672 I slot print_timing: id 0 | task 8860 | prompt eval time = 3570.99 ms / 934 tokens ( 3.82 ms per token, 261.55 tokens per second) 9.23.590.676 I slot print_timing: id 0 | task 8860 | eval time = 2363.00 ms / 2 tokens ( 2363.00 ms per token, 0.42 tokens per second) 9.23.590.676 I slot print_timing: id 0 | task 8860 | total time = 5933.99 ms / 936 tokens 9.23.590.677 I slot print_timing: id 0 | task 8860 | graphs reused = 7758 9.23.590.677 I slot print_timing: id 0 | task 8860 | graph reallocs = 0 / 0 (same size) / (changed size) 9.23.590.761 I slot release: id 0 | task 8860 | stop processing: n_tokens = 944, truncated = 0 9.23.590.794 I slot print_timing: id 1 | task 8864 | prompt processing, n_tokens = 590, progress = 0.84, t = 3.88 s / 151.93 tokens per second 9.23.593.770 I slot print_timing: id 2 | task 8865 | prompt processing, n_tokens = 590, progress = 0.81, t = 3.88 s / 151.96 tokens per second 9.23.595.782 I slot print_timing: id 3 | task 8866 | prompt processing, n_tokens = 759, progress = 0.87, t = 3.88 s / 195.52 tokens per second 9.24.246.124 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 944, t_last = 327368126017 9.24.246.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.414 MiB) 9.24.246.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.705 MiB) 9.24.246.222 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.953 MiB) 9.24.246.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.876 MiB) 9.24.246.515 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.961 MiB) 9.24.335.463 I slot launch_slot_: id 0 | task 8870 | processing task, is_child = 0 9.24.335.697 I slot print_timing: id 1 | task 8864 | prompt processing, n_tokens = 696, progress = 0.99, t = 4.54 s / 153.30 tokens per second 9.24.337.703 I slot print_timing: id 2 | task 8865 | prompt processing, n_tokens = 724, progress = 0.99, t = 4.54 s / 159.50 tokens per second 9.24.339.598 I slot print_timing: id 3 | task 8866 | prompt processing, n_tokens = 868, progress = 1.00, t = 4.54 s / 191.25 tokens per second 9.25.580.336 I slot print_timing: id 1 | task 8864 | prompt eval time = 5070.06 ms / 700 tokens ( 7.24 ms per token, 138.07 tokens per second) 9.25.580.339 I slot print_timing: id 1 | task 8864 | eval time = 804.14 ms / 2 tokens ( 804.14 ms per token, 1.24 tokens per second) 9.25.580.339 I slot print_timing: id 1 | task 8864 | total time = 5874.20 ms / 702 tokens 9.25.580.340 I slot print_timing: id 1 | task 8864 | graphs reused = 7758 9.25.580.340 I slot print_timing: id 1 | task 8864 | graph reallocs = 0 / 0 (same size) / (changed size) 9.25.580.389 I slot release: id 1 | task 8864 | stop processing: n_tokens = 710, truncated = 0 9.25.581.565 I slot print_timing: id 2 | task 8865 | prompt eval time = 5070.55 ms / 728 tokens ( 6.97 ms per token, 143.57 tokens per second) 9.25.581.569 I slot print_timing: id 2 | task 8865 | eval time = 804.13 ms / 2 tokens ( 804.13 ms per token, 1.24 tokens per second) 9.25.581.570 I slot print_timing: id 2 | task 8865 | total time = 5874.68 ms / 730 tokens 9.25.581.570 I slot print_timing: id 2 | task 8865 | graphs reused = 7758 9.25.581.570 I slot print_timing: id 2 | task 8865 | graph reallocs = 0 / 0 (same size) / (changed size) 9.25.581.593 I slot release: id 2 | task 8865 | stop processing: n_tokens = 738, truncated = 0 9.25.582.675 I slot print_timing: id 3 | task 8866 | prompt eval time = 5071.04 ms / 872 tokens ( 5.82 ms per token, 171.96 tokens per second) 9.25.582.677 I slot print_timing: id 3 | task 8866 | eval time = 804.07 ms / 2 tokens ( 804.07 ms per token, 1.24 tokens per second) 9.25.582.677 I slot print_timing: id 3 | task 8866 | total time = 5875.11 ms / 874 tokens 9.25.582.678 I slot print_timing: id 3 | task 8866 | graphs reused = 7758 9.25.582.678 I slot print_timing: id 3 | task 8866 | graph reallocs = 0 / 0 (same size) / (changed size) 9.25.582.705 I slot release: id 3 | task 8866 | stop processing: n_tokens = 882, truncated = 0 9.25.878.064 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 327370115644 9.25.888.426 I slot launch_slot_: id 1 | task 8875 | processing task, is_child = 0 9.25.888.496 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.249 MiB) 9.25.904.368 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.848 9.25.904.418 I slot launch_slot_: id 2 | task 8876 | processing task, is_child = 0 9.25.904.483 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 327370117960 9.25.906.725 I slot launch_slot_: id 3 | task 8877 | processing task, is_child = 0 9.26.844.321 I slot print_timing: id 0 | task 8870 | prompt eval time = 1542.59 ms / 703 tokens ( 2.19 ms per token, 455.73 tokens per second) 9.26.844.327 I slot print_timing: id 0 | task 8870 | eval time = 966.25 ms / 2 tokens ( 966.25 ms per token, 1.03 tokens per second) 9.26.844.328 I slot print_timing: id 0 | task 8870 | total time = 2508.84 ms / 705 tokens 9.26.844.328 I slot print_timing: id 0 | task 8870 | graphs reused = 7758 9.26.844.329 I slot print_timing: id 0 | task 8870 | graph reallocs = 0 / 0 (same size) / (changed size) 9.26.844.375 I slot release: id 0 | task 8870 | stop processing: n_tokens = 713, truncated = 0 9.27.947.730 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 713, t_last = 327371379630 9.27.959.106 I slot launch_slot_: id 0 | task 8880 | processing task, is_child = 0 9.29.156.015 I slot print_timing: id 2 | task 8876 | prompt eval time = 2040.80 ms / 89 tokens ( 22.93 ms per token, 43.61 tokens per second) 9.29.156.025 I slot print_timing: id 2 | task 8876 | eval time = 1208.28 ms / 2 tokens ( 1208.28 ms per token, 0.83 tokens per second) 9.29.156.026 I slot print_timing: id 2 | task 8876 | total time = 3249.08 ms / 91 tokens 9.29.156.029 I slot print_timing: id 2 | task 8876 | graphs reused = 7758 9.29.156.030 I slot print_timing: id 2 | task 8876 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.156.167 I slot release: id 2 | task 8876 | stop processing: n_tokens = 716, truncated = 0 9.29.163.045 I slot print_timing: id 1 | task 8875 | prompt processing, n_tokens = 860, progress = 1.00, t = 3.25 s / 264.86 tokens per second 9.29.959.135 I slot print_timing: id 3 | task 8877 | prompt eval time = 3250.65 ms / 123 tokens ( 26.43 ms per token, 37.84 tokens per second) 9.29.959.146 I slot print_timing: id 3 | task 8877 | eval time = 799.81 ms / 2 tokens ( 799.81 ms per token, 1.25 tokens per second) 9.29.959.148 I slot print_timing: id 3 | task 8877 | total time = 4050.46 ms / 125 tokens 9.29.959.150 I slot print_timing: id 3 | task 8877 | graphs reused = 7758 9.29.959.151 I slot print_timing: id 3 | task 8877 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.959.298 I slot release: id 3 | task 8877 | stop processing: n_tokens = 722, truncated = 0 9.29.959.340 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 327373691422 9.29.959.576 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.750 MiB) 9.29.979.331 I slot launch_slot_: id 2 | task 8883 | processing task, is_child = 0 9.29.979.470 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.640 MiB) 9.29.996.542 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 722, t_last = 327374494553 9.29.996.704 I slot launch_slot_: id 3 | task 8884 | processing task, is_child = 0 9.32.120.076 I slot print_timing: id 1 | task 8875 | prompt eval time = 4050.09 ms / 864 tokens ( 4.69 ms per token, 213.33 tokens per second) 9.32.120.080 I slot print_timing: id 1 | task 8875 | eval time = 2163.25 ms / 2 tokens ( 2163.25 ms per token, 0.46 tokens per second) 9.32.120.081 I slot print_timing: id 1 | task 8875 | total time = 6213.33 ms / 866 tokens 9.32.120.081 I slot print_timing: id 1 | task 8875 | graphs reused = 7758 9.32.120.082 I slot print_timing: id 1 | task 8875 | graph reallocs = 0 / 0 (same size) / (changed size) 9.32.120.162 I slot release: id 1 | task 8875 | stop processing: n_tokens = 874, truncated = 0 9.32.120.194 I slot print_timing: id 0 | task 8880 | prompt processing, n_tokens = 977, progress = 1.00, t = 4.16 s / 234.86 tokens per second 9.33.585.276 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 874, t_last = 327376655418 9.33.598.227 I slot launch_slot_: id 1 | task 8887 | processing task, is_child = 0 9.33.598.443 I slot print_timing: id 2 | task 8883 | prompt processing, n_tokens = 850, progress = 0.83, t = 3.59 s / 237.07 tokens per second 9.33.600.190 I slot print_timing: id 3 | task 8884 | prompt processing, n_tokens = 850, progress = 0.86, t = 3.59 s / 237.09 tokens per second 9.35.209.081 I slot print_timing: id 0 | task 8880 | prompt eval time = 5626.14 ms / 981 tokens ( 5.74 ms per token, 174.36 tokens per second) 9.35.209.087 I slot print_timing: id 0 | task 8880 | eval time = 1623.81 ms / 2 tokens ( 1623.81 ms per token, 0.62 tokens per second) 9.35.209.087 I slot print_timing: id 0 | task 8880 | total time = 7249.95 ms / 983 tokens 9.35.209.088 I slot print_timing: id 0 | task 8880 | graphs reused = 7758 9.35.209.088 I slot print_timing: id 0 | task 8880 | graph reallocs = 0 / 0 (same size) / (changed size) 9.35.209.134 I slot release: id 0 | task 8880 | stop processing: n_tokens = 991, truncated = 0 9.35.212.989 I slot print_timing: id 2 | task 8883 | prompt processing, n_tokens = 1021, progress = 1.00, t = 5.21 s / 196.00 tokens per second 9.35.214.916 I slot print_timing: id 3 | task 8884 | prompt processing, n_tokens = 991, progress = 1.00, t = 5.21 s / 190.25 tokens per second 9.36.009.779 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.894 9.36.009.924 I slot launch_slot_: id 0 | task 8890 | processing task, is_child = 0 9.36.573.750 I slot print_timing: id 2 | task 8883 | prompt eval time = 6009.86 ms / 1025 tokens ( 5.86 ms per token, 170.55 tokens per second) 9.36.573.756 I slot print_timing: id 2 | task 8883 | eval time = 565.19 ms / 2 tokens ( 565.19 ms per token, 1.77 tokens per second) 9.36.573.758 I slot print_timing: id 2 | task 8883 | total time = 6575.05 ms / 1027 tokens 9.36.573.759 I slot print_timing: id 2 | task 8883 | graphs reused = 7758 9.36.573.759 I slot print_timing: id 2 | task 8883 | graph reallocs = 0 / 0 (same size) / (changed size) 9.36.573.830 I slot release: id 2 | task 8883 | stop processing: n_tokens = 1035, truncated = 0 9.36.574.976 I slot print_timing: id 3 | task 8884 | prompt eval time = 6010.79 ms / 995 tokens ( 6.04 ms per token, 165.54 tokens per second) 9.36.574.980 I slot print_timing: id 3 | task 8884 | eval time = 565.21 ms / 2 tokens ( 565.21 ms per token, 1.77 tokens per second) 9.36.574.980 I slot print_timing: id 3 | task 8884 | total time = 6576.00 ms / 997 tokens 9.36.574.981 I slot print_timing: id 3 | task 8884 | graphs reused = 7758 9.36.574.981 I slot print_timing: id 3 | task 8884 | graph reallocs = 0 / 0 (same size) / (changed size) 9.36.575.022 I slot release: id 3 | task 8884 | stop processing: n_tokens = 1005, truncated = 0 9.36.620.878 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 327381109085 9.36.620.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.715 MiB) 9.36.637.750 I slot launch_slot_: id 2 | task 8893 | processing task, is_child = 0 9.36.637.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.645 MiB) 9.36.651.146 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1005, t_last = 327381110277 9.36.651.273 I slot launch_slot_: id 3 | task 8894 | processing task, is_child = 0 9.38.325.590 I slot print_timing: id 0 | task 8890 | prompt eval time = 609.83 ms / 105 tokens ( 5.81 ms per token, 172.18 tokens per second) 9.38.325.593 I slot print_timing: id 0 | task 8890 | eval time = 1705.81 ms / 2 tokens ( 1705.81 ms per token, 0.59 tokens per second) 9.38.325.594 I slot print_timing: id 0 | task 8890 | total time = 2315.64 ms / 107 tokens 9.38.325.594 I slot print_timing: id 0 | task 8890 | graphs reused = 7758 9.38.325.595 I slot print_timing: id 0 | task 8890 | graph reallocs = 0 / 0 (same size) / (changed size) 9.38.325.642 I slot release: id 0 | task 8890 | stop processing: n_tokens = 992, truncated = 0 9.38.326.738 I slot print_timing: id 1 | task 8887 | prompt eval time = 3022.63 ms / 987 tokens ( 3.06 ms per token, 326.54 tokens per second) 9.38.326.744 I slot print_timing: id 1 | task 8887 | eval time = 1705.86 ms / 2 tokens ( 1705.86 ms per token, 0.59 tokens per second) 9.38.326.752 I slot print_timing: id 1 | task 8887 | total time = 4728.49 ms / 989 tokens 9.38.326.752 I slot print_timing: id 1 | task 8887 | graphs reused = 7758 9.38.326.752 I slot print_timing: id 1 | task 8887 | graph reallocs = 0 / 0 (same size) / (changed size) 9.38.326.790 I slot release: id 1 | task 8887 | stop processing: n_tokens = 997, truncated = 0 9.39.380.618 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 992, t_last = 327382860897 9.39.587.148 I slot launch_slot_: id 0 | task 8897 | processing task, is_child = 0 9.39.587.232 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.926 MiB) 9.39.599.565 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 997, t_last = 327382862045 9.39.599.689 I slot launch_slot_: id 1 | task 8898 | processing task, is_child = 0 9.42.069.581 I slot print_timing: id 2 | task 8893 | prompt processing, n_tokens = 871, progress = 1.00, t = 5.21 s / 167.31 tokens per second 9.42.071.476 I slot print_timing: id 3 | task 8894 | prompt processing, n_tokens = 1010, progress = 1.00, t = 5.21 s / 194.02 tokens per second 9.43.494.541 I slot print_timing: id 0 | task 8897 | prompt processing, n_tokens = 768, progress = 0.86, t = 3.89 s / 197.30 tokens per second 9.43.497.585 I slot print_timing: id 1 | task 8898 | prompt processing, n_tokens = 768, progress = 0.77, t = 3.89 s / 197.31 tokens per second 9.44.287.073 I slot print_timing: id 2 | task 8893 | prompt eval time = 6842.10 ms / 875 tokens ( 7.82 ms per token, 127.88 tokens per second) 9.44.287.078 I slot print_timing: id 2 | task 8893 | eval time = 793.67 ms / 2 tokens ( 793.67 ms per token, 1.26 tokens per second) 9.44.287.079 I slot print_timing: id 2 | task 8893 | total time = 7635.77 ms / 877 tokens 9.44.287.079 I slot print_timing: id 2 | task 8893 | graphs reused = 7758 9.44.287.079 I slot print_timing: id 2 | task 8893 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.287.152 I slot release: id 2 | task 8893 | stop processing: n_tokens = 885, truncated = 0 9.44.288.286 I slot print_timing: id 3 | task 8894 | prompt eval time = 6842.99 ms / 1014 tokens ( 6.75 ms per token, 148.18 tokens per second) 9.44.288.288 I slot print_timing: id 3 | task 8894 | eval time = 793.77 ms / 2 tokens ( 793.77 ms per token, 1.26 tokens per second) 9.44.288.289 I slot print_timing: id 3 | task 8894 | total time = 7636.76 ms / 1016 tokens 9.44.288.289 I slot print_timing: id 3 | task 8894 | graphs reused = 7758 9.44.288.289 I slot print_timing: id 3 | task 8894 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.288.350 I slot release: id 3 | task 8894 | stop processing: n_tokens = 1024, truncated = 0 9.44.288.368 I slot print_timing: id 0 | task 8897 | prompt processing, n_tokens = 890, progress = 1.00, t = 4.69 s / 189.92 tokens per second 9.44.293.177 I slot print_timing: id 1 | task 8898 | prompt processing, n_tokens = 998, progress = 1.00, t = 4.69 s / 212.97 tokens per second 9.44.336.019 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.785 9.44.336.120 I slot launch_slot_: id 3 | task 8903 | processing task, is_child = 0 9.44.336.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 403.801 MiB) 9.44.347.512 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 327388822407 9.44.347.648 I slot launch_slot_: id 2 | task 8904 | processing task, is_child = 0 9.45.513.113 I slot print_timing: id 0 | task 8897 | prompt eval time = 4735.16 ms / 894 tokens ( 5.30 ms per token, 188.80 tokens per second) 9.45.513.119 I slot print_timing: id 0 | task 8897 | eval time = 1178.24 ms / 2 tokens ( 1178.24 ms per token, 0.85 tokens per second) 9.45.513.120 I slot print_timing: id 0 | task 8897 | total time = 5913.40 ms / 896 tokens 9.45.513.120 I slot print_timing: id 0 | task 8897 | graphs reused = 7758 9.45.513.121 I slot print_timing: id 0 | task 8897 | graph reallocs = 0 / 0 (same size) / (changed size) 9.45.513.197 I slot release: id 0 | task 8897 | stop processing: n_tokens = 904, truncated = 0 9.45.514.359 I slot print_timing: id 1 | task 8898 | prompt eval time = 4736.10 ms / 1002 tokens ( 4.73 ms per token, 211.57 tokens per second) 9.45.514.364 I slot print_timing: id 1 | task 8898 | eval time = 1178.34 ms / 2 tokens ( 1178.34 ms per token, 0.85 tokens per second) 9.45.514.365 I slot print_timing: id 1 | task 8898 | total time = 5914.44 ms / 1004 tokens 9.45.514.365 I slot print_timing: id 1 | task 8898 | graphs reused = 7758 9.45.514.365 I slot print_timing: id 1 | task 8898 | graph reallocs = 0 / 0 (same size) / (changed size) 9.45.514.405 I slot release: id 1 | task 8898 | stop processing: n_tokens = 1012, truncated = 0 9.46.163.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 327390048452 9.46.184.285 I slot launch_slot_: id 0 | task 8907 | processing task, is_child = 0 9.46.184.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.152 MiB) 9.46.190.557 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.794 9.46.190.611 I slot launch_slot_: id 1 | task 8908 | processing task, is_child = 0 9.47.652.937 I slot print_timing: id 3 | task 8903 | prompt eval time = 1815.24 ms / 102 tokens ( 17.80 ms per token, 56.19 tokens per second) 9.47.652.941 I slot print_timing: id 3 | task 8903 | eval time = 1489.83 ms / 2 tokens ( 1489.83 ms per token, 0.67 tokens per second) 9.47.652.946 I slot print_timing: id 3 | task 8903 | total time = 3305.07 ms / 104 tokens 9.47.652.946 I slot print_timing: id 3 | task 8903 | graphs reused = 7758 9.47.652.947 I slot print_timing: id 3 | task 8903 | graph reallocs = 0 / 0 (same size) / (changed size) 9.47.653.025 I slot release: id 3 | task 8903 | stop processing: n_tokens = 907, truncated = 0 9.47.659.434 I slot print_timing: id 2 | task 8904 | prompt processing, n_tokens = 979, progress = 1.00, t = 3.30 s / 296.30 tokens per second 9.48.389.657 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 327392188280 9.48.408.162 I slot launch_slot_: id 3 | task 8911 | processing task, is_child = 0 9.49.519.036 I slot print_timing: id 1 | task 8908 | prompt eval time = 2197.73 ms / 81 tokens ( 27.13 ms per token, 36.86 tokens per second) 9.49.519.044 I slot print_timing: id 1 | task 8908 | eval time = 1130.47 ms / 2 tokens ( 1130.47 ms per token, 0.88 tokens per second) 9.49.519.047 I slot print_timing: id 1 | task 8908 | total time = 3328.20 ms / 83 tokens 9.49.519.047 I slot print_timing: id 1 | task 8908 | graphs reused = 7758 9.49.519.047 I slot print_timing: id 1 | task 8908 | graph reallocs = 0 / 0 (same size) / (changed size) 9.49.519.122 I slot release: id 1 | task 8908 | stop processing: n_tokens = 886, truncated = 0 9.49.520.383 I slot print_timing: id 2 | task 8904 | prompt eval time = 4041.99 ms / 983 tokens ( 4.11 ms per token, 243.20 tokens per second) 9.49.520.385 I slot print_timing: id 2 | task 8904 | eval time = 1130.73 ms / 2 tokens ( 1130.73 ms per token, 0.88 tokens per second) 9.49.520.386 I slot print_timing: id 2 | task 8904 | total time = 5172.72 ms / 985 tokens 9.49.520.386 I slot print_timing: id 2 | task 8904 | graphs reused = 7758 9.49.520.386 I slot print_timing: id 2 | task 8904 | graph reallocs = 0 / 0 (same size) / (changed size) 9.49.520.432 I slot release: id 2 | task 8904 | stop processing: n_tokens = 993, truncated = 0 9.49.520.449 I slot print_timing: id 0 | task 8907 | prompt processing, n_tokens = 927, progress = 1.00, t = 3.33 s / 278.61 tokens per second 9.50.330.716 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 327394054377 9.50.330.867 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.862 MiB) 9.50.348.734 I slot launch_slot_: id 1 | task 8914 | processing task, is_child = 0 9.50.348.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 424.644 MiB) 9.50.361.524 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 993, t_last = 327394055687 9.50.361.656 I slot launch_slot_: id 2 | task 8915 | processing task, is_child = 0 9.53.014.249 I slot print_timing: id 0 | task 8907 | prompt eval time = 4140.08 ms / 931 tokens ( 4.45 ms per token, 224.88 tokens per second) 9.53.014.252 I slot print_timing: id 0 | task 8907 | eval time = 2683.55 ms / 2 tokens ( 2683.55 ms per token, 0.37 tokens per second) 9.53.014.253 I slot print_timing: id 0 | task 8907 | total time = 6823.62 ms / 933 tokens 9.53.014.254 I slot print_timing: id 0 | task 8907 | graphs reused = 7758 9.53.014.254 I slot print_timing: id 0 | task 8907 | graph reallocs = 0 / 0 (same size) / (changed size) 9.53.014.305 I slot release: id 0 | task 8907 | stop processing: n_tokens = 941, truncated = 0 9.53.018.632 I slot print_timing: id 3 | task 8911 | prompt processing, n_tokens = 880, progress = 1.00, t = 4.60 s / 191.17 tokens per second 9.54.437.496 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 327397549560 9.54.451.736 I slot launch_slot_: id 0 | task 8918 | processing task, is_child = 0 9.54.451.991 I slot print_timing: id 1 | task 8914 | prompt processing, n_tokens = 753, progress = 0.82, t = 4.07 s / 184.80 tokens per second 9.54.453.852 I slot print_timing: id 2 | task 8915 | prompt processing, n_tokens = 1148, progress = 0.85, t = 4.07 s / 281.76 tokens per second 9.56.821.537 I slot print_timing: id 3 | task 8911 | prompt eval time = 6027.60 ms / 884 tokens ( 6.82 ms per token, 146.66 tokens per second) 9.56.821.540 I slot print_timing: id 3 | task 8911 | eval time = 2384.05 ms / 2 tokens ( 2384.05 ms per token, 0.42 tokens per second) 9.56.821.541 I slot print_timing: id 3 | task 8911 | total time = 8411.65 ms / 886 tokens 9.56.821.541 I slot print_timing: id 3 | task 8911 | graphs reused = 7758 9.56.821.542 I slot print_timing: id 3 | task 8911 | graph reallocs = 0 / 0 (same size) / (changed size) 9.56.821.605 I slot release: id 3 | task 8911 | stop processing: n_tokens = 894, truncated = 0 9.56.826.551 I slot print_timing: id 1 | task 8914 | prompt processing, n_tokens = 914, progress = 1.00, t = 6.46 s / 141.51 tokens per second 9.56.828.596 I slot print_timing: id 2 | task 8915 | prompt processing, n_tokens = 1349, progress = 1.00, t = 6.46 s / 208.87 tokens per second 9.57.511.666 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 327401356860 9.57.511.789 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 245.780 MiB) 9.57.519.795 I slot launch_slot_: id 3 | task 8921 | processing task, is_child = 0 9.57.519.807 I slot print_timing: id 0 | task 8918 | prompt processing, n_tokens = 1148, progress = 0.86, t = 3.06 s / 375.45 tokens per second 9.59.354.009 I slot print_timing: id 1 | task 8914 | prompt eval time = 7148.86 ms / 918 tokens ( 7.79 ms per token, 128.41 tokens per second) 9.59.354.012 I slot print_timing: id 1 | task 8914 | eval time = 1843.48 ms / 2 tokens ( 1843.48 ms per token, 0.54 tokens per second) 9.59.354.012 I slot print_timing: id 1 | task 8914 | total time = 8992.34 ms / 920 tokens 9.59.354.013 I slot print_timing: id 1 | task 8914 | graphs reused = 7758 9.59.354.013 I slot print_timing: id 1 | task 8914 | graph reallocs = 0 / 0 (same size) / (changed size) 9.59.354.074 I slot release: id 1 | task 8914 | stop processing: n_tokens = 928, truncated = 0 9.59.355.215 I slot print_timing: id 2 | task 8915 | prompt eval time = 7149.77 ms / 1353 tokens ( 5.28 ms per token, 189.24 tokens per second) 9.59.355.217 I slot print_timing: id 2 | task 8915 | eval time = 1843.56 ms / 2 tokens ( 1843.56 ms per token, 0.54 tokens per second) 9.59.355.218 I slot print_timing: id 2 | task 8915 | total time = 8993.33 ms / 1355 tokens 9.59.355.218 I slot print_timing: id 2 | task 8915 | graphs reused = 7758 9.59.355.219 I slot print_timing: id 2 | task 8915 | graph reallocs = 0 / 0 (same size) / (changed size) 9.59.355.276 I slot release: id 2 | task 8915 | stop processing: n_tokens = 1363, truncated = 0 9.59.355.294 I slot print_timing: id 0 | task 8918 | prompt processing, n_tokens = 1336, progress = 1.00, t = 4.90 s / 272.59 tokens per second 10.00.184.749 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 327403889329 10.00.184.888 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 248.171 MiB) 10.00.193.969 I slot launch_slot_: id 1 | task 8924 | processing task, is_child = 0 10.00.194.059 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.635 MiB) 10.00.194.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.323 MiB) 10.00.208.676 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.869 10.00.208.737 I slot launch_slot_: id 2 | task 8925 | processing task, is_child = 0 10.01.250.293 I slot print_timing: id 0 | task 8918 | prompt eval time = 5732.98 ms / 1340 tokens ( 4.28 ms per token, 233.74 tokens per second) 10.01.250.297 I slot print_timing: id 0 | task 8918 | eval time = 1065.55 ms / 2 tokens ( 1065.55 ms per token, 0.94 tokens per second) 10.01.250.297 I slot print_timing: id 0 | task 8918 | total time = 6798.53 ms / 1342 tokens 10.01.250.298 I slot print_timing: id 0 | task 8918 | graphs reused = 7758 10.01.250.299 I slot print_timing: id 0 | task 8918 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.250.409 I slot release: id 0 | task 8918 | stop processing: n_tokens = 1350, truncated = 0 10.01.254.990 I slot print_timing: id 3 | task 8921 | prompt processing, n_tokens = 1251, progress = 1.00, t = 3.73 s / 335.60 tokens per second 10.02.097.318 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1350, t_last = 327405785665 10.02.097.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 222.855 MiB) 10.02.115.148 I slot launch_slot_: id 0 | task 8928 | processing task, is_child = 0 10.02.945.370 I slot print_timing: id 2 | task 8925 | prompt eval time = 1887.12 ms / 121 tokens ( 15.60 ms per token, 64.12 tokens per second) 10.02.945.377 I slot print_timing: id 2 | task 8925 | eval time = 849.27 ms / 2 tokens ( 849.27 ms per token, 1.18 tokens per second) 10.02.945.378 I slot print_timing: id 2 | task 8925 | total time = 2736.40 ms / 123 tokens 10.02.945.378 I slot print_timing: id 2 | task 8925 | graphs reused = 7758 10.02.945.379 I slot print_timing: id 2 | task 8925 | graph reallocs = 0 / 0 (same size) / (changed size) 10.02.945.480 I slot release: id 2 | task 8925 | stop processing: n_tokens = 1306, truncated = 0 10.02.946.650 I slot print_timing: id 3 | task 8921 | prompt eval time = 4575.76 ms / 1255 tokens ( 3.65 ms per token, 274.27 tokens per second) 10.02.946.652 I slot print_timing: id 3 | task 8921 | eval time = 849.35 ms / 2 tokens ( 849.35 ms per token, 1.18 tokens per second) 10.02.946.653 I slot print_timing: id 3 | task 8921 | total time = 5425.11 ms / 1257 tokens 10.02.946.653 I slot print_timing: id 3 | task 8921 | graphs reused = 7758 10.02.946.653 I slot print_timing: id 3 | task 8921 | graph reallocs = 0 / 0 (same size) / (changed size) 10.02.946.699 I slot release: id 3 | task 8921 | stop processing: n_tokens = 1265, truncated = 0 10.03.705.638 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1306, t_last = 327407480737 10.03.705.816 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.136 MiB) 10.03.723.355 I slot launch_slot_: id 2 | task 8931 | processing task, is_child = 0 10.03.723.447 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 230.309 MiB) 10.03.735.666 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1265, t_last = 327407481954 10.03.735.804 I slot launch_slot_: id 3 | task 8932 | processing task, is_child = 0 10.05.394.785 I slot print_timing: id 1 | task 8924 | prompt eval time = 3496.87 ms / 782 tokens ( 4.47 ms per token, 223.63 tokens per second) 10.05.394.788 I slot print_timing: id 1 | task 8924 | eval time = 1689.16 ms / 2 tokens ( 1689.16 ms per token, 0.59 tokens per second) 10.05.394.789 I slot print_timing: id 1 | task 8924 | total time = 5186.03 ms / 784 tokens 10.05.394.789 I slot print_timing: id 1 | task 8924 | graphs reused = 7758 10.05.394.790 I slot print_timing: id 1 | task 8924 | graph reallocs = 0 / 0 (same size) / (changed size) 10.05.394.840 I slot release: id 1 | task 8924 | stop processing: n_tokens = 792, truncated = 0 10.05.394.856 I slot print_timing: id 0 | task 8928 | prompt processing, n_tokens = 797, progress = 1.00, t = 3.28 s / 243.09 tokens per second 10.06.907.669 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 792, t_last = 327409930095 10.06.907.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.522 MiB) 10.06.914.685 I slot launch_slot_: id 1 | task 8935 | processing task, is_child = 0 10.06.914.894 I slot print_timing: id 2 | task 8931 | prompt processing, n_tokens = 736, progress = 0.83, t = 3.17 s / 232.25 tokens per second 10.06.916.625 I slot print_timing: id 3 | task 8932 | prompt processing, n_tokens = 736, progress = 0.86, t = 3.17 s / 232.27 tokens per second 10.08.006.022 I slot print_timing: id 0 | task 8928 | prompt eval time = 4792.50 ms / 801 tokens ( 5.98 ms per token, 167.14 tokens per second) 10.08.006.027 I slot print_timing: id 0 | task 8928 | eval time = 1098.36 ms / 2 tokens ( 1098.36 ms per token, 0.91 tokens per second) 10.08.006.027 I slot print_timing: id 0 | task 8928 | total time = 5890.86 ms / 803 tokens 10.08.006.028 I slot print_timing: id 0 | task 8928 | graphs reused = 7758 10.08.006.028 I slot print_timing: id 0 | task 8928 | graph reallocs = 0 / 0 (same size) / (changed size) 10.08.006.079 I slot release: id 0 | task 8928 | stop processing: n_tokens = 811, truncated = 0 10.08.008.411 I slot print_timing: id 2 | task 8931 | prompt processing, n_tokens = 882, progress = 1.00, t = 4.27 s / 206.68 tokens per second 10.08.010.609 I slot print_timing: id 3 | task 8932 | prompt processing, n_tokens = 853, progress = 1.00, t = 4.27 s / 199.90 tokens per second 10.08.795.581 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 811, t_last = 327412541334 10.08.795.666 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.981 MiB) 10.08.802.130 I slot launch_slot_: id 0 | task 8938 | processing task, is_child = 0 10.09.793.227 I slot print_timing: id 2 | task 8931 | prompt eval time = 5056.96 ms / 886 tokens ( 5.71 ms per token, 175.20 tokens per second) 10.09.793.233 I slot print_timing: id 2 | task 8931 | eval time = 998.76 ms / 2 tokens ( 998.76 ms per token, 1.00 tokens per second) 10.09.793.233 I slot print_timing: id 2 | task 8931 | total time = 6055.72 ms / 888 tokens 10.09.793.234 I slot print_timing: id 2 | task 8931 | graphs reused = 7758 10.09.793.234 I slot print_timing: id 2 | task 8931 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.793.287 I slot release: id 2 | task 8931 | stop processing: n_tokens = 896, truncated = 0 10.09.794.440 I slot print_timing: id 3 | task 8932 | prompt eval time = 5057.84 ms / 857 tokens ( 5.90 ms per token, 169.44 tokens per second) 10.09.794.450 I slot print_timing: id 3 | task 8932 | eval time = 998.86 ms / 2 tokens ( 998.86 ms per token, 1.00 tokens per second) 10.09.794.451 I slot print_timing: id 3 | task 8932 | total time = 6056.70 ms / 859 tokens 10.09.794.451 I slot print_timing: id 3 | task 8932 | graphs reused = 7758 10.09.794.451 I slot print_timing: id 3 | task 8932 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.794.490 I slot release: id 3 | task 8932 | stop processing: n_tokens = 867, truncated = 0 10.10.437.564 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 896, t_last = 327414328542 10.10.437.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 234.388 MiB) 10.10.451.393 I slot launch_slot_: id 2 | task 8942 | processing task, is_child = 0 10.10.451.471 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.374 MiB) 10.10.457.322 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 867, t_last = 327414329745 10.10.457.436 I slot launch_slot_: id 3 | task 8941 | processing task, is_child = 0 10.11.866.366 I slot print_timing: id 1 | task 8935 | prompt eval time = 3522.85 ms / 778 tokens ( 4.53 ms per token, 220.84 tokens per second) 10.11.866.369 I slot print_timing: id 1 | task 8935 | eval time = 1428.81 ms / 2 tokens ( 1428.81 ms per token, 0.70 tokens per second) 10.11.866.369 I slot print_timing: id 1 | task 8935 | total time = 4951.66 ms / 780 tokens 10.11.866.369 I slot print_timing: id 1 | task 8935 | graphs reused = 7758 10.11.866.370 I slot print_timing: id 1 | task 8935 | graph reallocs = 0 / 0 (same size) / (changed size) 10.11.866.413 I slot release: id 1 | task 8935 | stop processing: n_tokens = 788, truncated = 0 10.11.866.430 I slot print_timing: id 0 | task 8938 | prompt processing, n_tokens = 839, progress = 1.00, t = 3.06 s / 273.90 tokens per second 10.13.420.009 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.849 (> 0.100 thold), f_keep = 0.862 10.13.420.164 I slot launch_slot_: id 1 | task 8945 | processing task, is_child = 0 10.14.193.701 I slot print_timing: id 0 | task 8938 | prompt eval time = 4617.85 ms / 843 tokens ( 5.48 ms per token, 182.55 tokens per second) 10.14.193.704 I slot print_timing: id 0 | task 8938 | eval time = 773.70 ms / 2 tokens ( 773.70 ms per token, 1.29 tokens per second) 10.14.193.705 I slot print_timing: id 0 | task 8938 | total time = 5391.56 ms / 845 tokens 10.14.193.705 I slot print_timing: id 0 | task 8938 | graphs reused = 7758 10.14.193.706 I slot print_timing: id 0 | task 8938 | graph reallocs = 0 / 0 (same size) / (changed size) 10.14.193.749 I slot release: id 0 | task 8938 | stop processing: n_tokens = 853, truncated = 0 10.14.195.917 I slot print_timing: id 2 | task 8942 | prompt processing, n_tokens = 764, progress = 0.99, t = 3.73 s / 204.64 tokens per second 10.14.198.028 I slot print_timing: id 3 | task 8941 | prompt processing, n_tokens = 758, progress = 0.99, t = 3.73 s / 203.04 tokens per second 10.14.270.579 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 853, t_last = 327418729004 10.14.270.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.859 MiB) 10.14.276.653 I slot launch_slot_: id 0 | task 8948 | processing task, is_child = 0 10.15.127.975 I slot print_timing: id 1 | task 8945 | prompt eval time = 848.09 ms / 121 tokens ( 7.01 ms per token, 142.67 tokens per second) 10.15.127.980 I slot print_timing: id 1 | task 8945 | eval time = 859.70 ms / 2 tokens ( 859.70 ms per token, 1.16 tokens per second) 10.15.127.981 I slot print_timing: id 1 | task 8945 | total time = 1707.78 ms / 123 tokens 10.15.127.981 I slot print_timing: id 1 | task 8945 | graphs reused = 7758 10.15.127.982 I slot print_timing: id 1 | task 8945 | graph reallocs = 0 / 0 (same size) / (changed size) 10.15.128.028 I slot release: id 1 | task 8945 | stop processing: n_tokens = 801, truncated = 0 10.15.129.142 I slot print_timing: id 2 | task 8942 | prompt eval time = 3810.29 ms / 768 tokens ( 4.96 ms per token, 201.56 tokens per second) 10.15.129.144 I slot print_timing: id 2 | task 8942 | eval time = 859.70 ms / 2 tokens ( 859.70 ms per token, 1.16 tokens per second) 10.15.129.145 I slot print_timing: id 2 | task 8942 | total time = 4670.00 ms / 770 tokens 10.15.129.145 I slot print_timing: id 2 | task 8942 | graphs reused = 7758 10.15.129.145 I slot print_timing: id 2 | task 8942 | graph reallocs = 0 / 0 (same size) / (changed size) 10.15.129.169 I slot release: id 2 | task 8942 | stop processing: n_tokens = 778, truncated = 0 10.15.130.283 I slot print_timing: id 3 | task 8941 | prompt eval time = 3811.24 ms / 762 tokens ( 5.00 ms per token, 199.93 tokens per second) 10.15.130.295 I slot print_timing: id 3 | task 8941 | eval time = 859.71 ms / 2 tokens ( 859.71 ms per token, 1.16 tokens per second) 10.15.130.295 I slot print_timing: id 3 | task 8941 | total time = 4670.95 ms / 764 tokens 10.15.130.295 I slot print_timing: id 3 | task 8941 | graphs reused = 7758 10.15.130.296 I slot print_timing: id 3 | task 8941 | graph reallocs = 0 / 0 (same size) / (changed size) 10.15.130.318 I slot release: id 3 | task 8941 | stop processing: n_tokens = 772, truncated = 0 10.15.863.594 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 801, t_last = 327419663283 10.15.863.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.360 MiB) 10.16.178.177 I slot launch_slot_: id 1 | task 8952 | processing task, is_child = 0 10.16.178.252 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.014 MiB) 10.16.183.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.037 MiB) 10.16.189.164 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 327419664424 10.16.189.284 I slot launch_slot_: id 2 | task 8953 | processing task, is_child = 0 10.16.189.346 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 327419665573 10.16.189.446 I slot launch_slot_: id 3 | task 8954 | processing task, is_child = 0 10.21.014.602 I slot print_timing: id 0 | task 8948 | prompt eval time = 4342.86 ms / 952 tokens ( 4.56 ms per token, 219.21 tokens per second) 10.21.014.605 I slot print_timing: id 0 | task 8948 | eval time = 2395.07 ms / 2 tokens ( 2395.07 ms per token, 0.42 tokens per second) 10.21.014.606 I slot print_timing: id 0 | task 8948 | total time = 6737.93 ms / 954 tokens 10.21.014.607 I slot print_timing: id 0 | task 8948 | graphs reused = 7758 10.21.014.607 I slot print_timing: id 0 | task 8948 | graph reallocs = 0 / 0 (same size) / (changed size) 10.21.014.665 I slot release: id 0 | task 8948 | stop processing: n_tokens = 962, truncated = 0 10.21.014.683 I slot print_timing: id 1 | task 8952 | prompt processing, n_tokens = 817, progress = 0.88, t = 4.82 s / 169.42 tokens per second 10.21.017.040 I slot print_timing: id 2 | task 8953 | prompt processing, n_tokens = 817, progress = 0.88, t = 4.82 s / 169.43 tokens per second 10.21.019.024 I slot print_timing: id 3 | task 8954 | prompt processing, n_tokens = 817, progress = 0.87, t = 4.82 s / 169.43 tokens per second 10.21.672.093 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.887 10.21.672.197 I slot launch_slot_: id 0 | task 8958 | processing task, is_child = 0 10.21.740.588 I slot print_timing: id 1 | task 8952 | prompt processing, n_tokens = 922, progress = 1.00, t = 5.48 s / 168.22 tokens per second 10.21.742.938 I slot print_timing: id 2 | task 8953 | prompt processing, n_tokens = 924, progress = 1.00, t = 5.48 s / 168.59 tokens per second 10.21.744.786 I slot print_timing: id 3 | task 8954 | prompt processing, n_tokens = 940, progress = 1.00, t = 5.48 s / 171.52 tokens per second 10.22.151.159 I slot print_timing: id 1 | task 8952 | prompt eval time = 5884.84 ms / 926 tokens ( 6.36 ms per token, 157.35 tokens per second) 10.22.151.162 I slot print_timing: id 1 | task 8952 | eval time = 75.08 ms / 2 tokens ( 75.08 ms per token, 13.32 tokens per second) 10.22.151.162 I slot print_timing: id 1 | task 8952 | total time = 5959.92 ms / 928 tokens 10.22.151.163 I slot print_timing: id 1 | task 8952 | graphs reused = 7758 10.22.151.163 I slot print_timing: id 1 | task 8952 | graph reallocs = 0 / 0 (same size) / (changed size) 10.22.151.208 I slot release: id 1 | task 8952 | stop processing: n_tokens = 936, truncated = 0 10.22.152.290 I slot print_timing: id 2 | task 8953 | prompt eval time = 5885.97 ms / 928 tokens ( 6.34 ms per token, 157.66 tokens per second) 10.22.152.291 I slot print_timing: id 2 | task 8953 | eval time = 74.89 ms / 2 tokens ( 74.89 ms per token, 13.35 tokens per second) 10.22.152.292 I slot print_timing: id 2 | task 8953 | total time = 5960.86 ms / 930 tokens 10.22.152.292 I slot print_timing: id 2 | task 8953 | graphs reused = 7758 10.22.152.292 I slot print_timing: id 2 | task 8953 | graph reallocs = 0 / 0 (same size) / (changed size) 10.22.152.321 I slot release: id 2 | task 8953 | stop processing: n_tokens = 938, truncated = 0 10.22.153.418 I slot print_timing: id 3 | task 8954 | prompt eval time = 5886.96 ms / 944 tokens ( 6.24 ms per token, 160.35 tokens per second) 10.22.153.425 I slot print_timing: id 3 | task 8954 | eval time = 74.88 ms / 2 tokens ( 74.88 ms per token, 13.36 tokens per second) 10.22.153.425 I slot print_timing: id 3 | task 8954 | total time = 5961.84 ms / 946 tokens 10.22.153.425 I slot print_timing: id 3 | task 8954 | graphs reused = 7758 10.22.153.426 I slot print_timing: id 3 | task 8954 | graph reallocs = 0 / 0 (same size) / (changed size) 10.22.153.455 I slot release: id 3 | task 8954 | stop processing: n_tokens = 954, truncated = 0 10.22.177.286 I slot print_timing: id 0 | task 8958 | prompt eval time = 477.88 ms / 107 tokens ( 4.47 ms per token, 223.91 tokens per second) 10.22.177.289 I slot print_timing: id 0 | task 8958 | eval time = 27.20 ms / 2 tokens ( 27.20 ms per token, 36.77 tokens per second) 10.22.177.289 I slot print_timing: id 0 | task 8958 | total time = 505.08 ms / 109 tokens 10.22.177.290 I slot print_timing: id 0 | task 8958 | graphs reused = 7758 10.22.177.290 I slot print_timing: id 0 | task 8958 | graph reallocs = 0 / 0 (same size) / (changed size) 10.22.177.323 I slot release: id 0 | task 8958 | stop processing: n_tokens = 961, truncated = 0 10.22.177.330 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 327426686463 10.22.177.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 242.264 MiB) 10.22.183.553 I slot launch_slot_: id 1 | task 8962 | processing task, is_child = 0 10.22.183.637 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.291 MiB) 10.22.191.053 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 233.544 MiB) 10.22.197.164 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 209.775 MiB) 10.22.203.245 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 327426687576 10.22.203.384 I slot launch_slot_: id 2 | task 8963 | processing task, is_child = 0 10.22.203.531 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 327426688710 10.22.203.632 I slot launch_slot_: id 3 | task 8964 | processing task, is_child = 0 10.22.203.704 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 327426712578 10.22.203.807 I slot launch_slot_: id 0 | task 8965 | processing task, is_child = 0 10.27.835.690 I slot print_timing: id 0 | task 8965 | prompt processing, n_tokens = 818, progress = 0.87, t = 5.63 s / 145.25 tokens per second 10.27.925.024 I slot print_timing: id 1 | task 8962 | prompt processing, n_tokens = 668, progress = 0.85, t = 5.63 s / 118.62 tokens per second 10.27.928.851 I slot print_timing: id 2 | task 8963 | prompt processing, n_tokens = 818, progress = 0.85, t = 5.63 s / 145.26 tokens per second 10.27.932.609 I slot print_timing: id 3 | task 8964 | prompt processing, n_tokens = 668, progress = 0.85, t = 5.63 s / 118.62 tokens per second 10.28.879.345 I slot print_timing: id 0 | task 8965 | prompt processing, n_tokens = 943, progress = 1.00, t = 6.68 s / 141.26 tokens per second 10.28.969.569 I slot print_timing: id 1 | task 8962 | prompt processing, n_tokens = 785, progress = 0.99, t = 6.68 s / 117.60 tokens per second 10.28.972.189 I slot print_timing: id 2 | task 8963 | prompt processing, n_tokens = 963, progress = 1.00, t = 6.68 s / 144.27 tokens per second 10.28.974.221 I slot print_timing: id 3 | task 8964 | prompt processing, n_tokens = 785, progress = 0.99, t = 6.67 s / 117.60 tokens per second 10.29.091.891 I slot print_timing: id 0 | task 8965 | prompt eval time = 6847.03 ms / 947 tokens ( 7.23 ms per token, 138.31 tokens per second) 10.29.091.896 I slot print_timing: id 0 | task 8965 | eval time = 41.04 ms / 2 tokens ( 41.04 ms per token, 24.36 tokens per second) 10.29.091.897 I slot print_timing: id 0 | task 8965 | total time = 6888.07 ms / 949 tokens 10.29.091.898 I slot print_timing: id 0 | task 8965 | graphs reused = 7759 10.29.091.898 I slot print_timing: id 0 | task 8965 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.091.943 I slot release: id 0 | task 8965 | stop processing: n_tokens = 957, truncated = 0 10.29.093.365 I slot print_timing: id 1 | task 8962 | prompt eval time = 6847.96 ms / 789 tokens ( 8.68 ms per token, 115.22 tokens per second) 10.29.093.368 I slot print_timing: id 1 | task 8962 | eval time = 41.37 ms / 2 tokens ( 41.37 ms per token, 24.17 tokens per second) 10.29.093.369 I slot print_timing: id 1 | task 8962 | total time = 6889.33 ms / 791 tokens 10.29.093.369 I slot print_timing: id 1 | task 8962 | graphs reused = 7759 10.29.093.370 I slot print_timing: id 1 | task 8962 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.093.409 I slot release: id 1 | task 8962 | stop processing: n_tokens = 799, truncated = 0 10.29.095.011 I slot print_timing: id 2 | task 8963 | prompt eval time = 6848.87 ms / 967 tokens ( 7.08 ms per token, 141.19 tokens per second) 10.29.095.015 I slot print_timing: id 2 | task 8963 | eval time = 41.92 ms / 2 tokens ( 41.92 ms per token, 23.85 tokens per second) 10.29.095.016 I slot print_timing: id 2 | task 8963 | total time = 6890.79 ms / 969 tokens 10.29.095.016 I slot print_timing: id 2 | task 8963 | graphs reused = 7759 10.29.095.017 I slot print_timing: id 2 | task 8963 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.095.055 I slot release: id 2 | task 8963 | stop processing: n_tokens = 977, truncated = 0 10.29.096.658 I slot print_timing: id 3 | task 8964 | prompt eval time = 6849.80 ms / 789 tokens ( 8.68 ms per token, 115.19 tokens per second) 10.29.096.664 I slot print_timing: id 3 | task 8964 | eval time = 42.47 ms / 2 tokens ( 42.47 ms per token, 23.55 tokens per second) 10.29.096.664 I slot print_timing: id 3 | task 8964 | total time = 6892.26 ms / 791 tokens 10.29.096.665 I slot print_timing: id 3 | task 8964 | graphs reused = 7759 10.29.096.665 I slot print_timing: id 3 | task 8964 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.096.696 I slot release: id 3 | task 8964 | stop processing: n_tokens = 799, truncated = 0 10.29.102.778 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.892 10.29.102.838 I slot launch_slot_: id 0 | task 8971 | processing task, is_child = 0 10.29.102.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.524 MiB) 10.29.109.059 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.676 MiB) 10.29.115.454 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.419 MiB) 10.29.121.170 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 327433628664 10.29.121.325 I slot launch_slot_: id 1 | task 8972 | processing task, is_child = 0 10.29.121.497 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 327433630310 10.29.121.699 I slot launch_slot_: id 2 | task 8973 | processing task, is_child = 0 10.29.121.804 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 327433631951 10.29.121.928 I slot launch_slot_: id 3 | task 8974 | processing task, is_child = 0 10.33.872.978 I slot print_timing: id 1 | task 8972 | prompt processing, n_tokens = 771, progress = 0.84, t = 4.75 s / 162.39 tokens per second 10.33.876.877 I slot print_timing: id 2 | task 8973 | prompt processing, n_tokens = 771, progress = 0.87, t = 4.75 s / 162.40 tokens per second 10.33.879.547 I slot print_timing: id 3 | task 8974 | prompt processing, n_tokens = 771, progress = 0.86, t = 4.75 s / 162.40 tokens per second 10.34.708.450 I slot print_timing: id 0 | task 8971 | prompt eval time = 4751.01 ms / 108 tokens ( 43.99 ms per token, 22.73 tokens per second) 10.34.708.453 I slot print_timing: id 0 | task 8971 | eval time = 835.50 ms / 2 tokens ( 835.50 ms per token, 1.20 tokens per second) 10.34.708.455 I slot print_timing: id 0 | task 8971 | total time = 5586.51 ms / 110 tokens 10.34.708.455 I slot print_timing: id 0 | task 8971 | graphs reused = 7760 10.34.708.456 I slot print_timing: id 0 | task 8971 | graph reallocs = 0 / 0 (same size) / (changed size) 10.34.708.525 I slot release: id 0 | task 8971 | stop processing: n_tokens = 963, truncated = 0 10.34.708.542 I slot print_timing: id 1 | task 8972 | prompt processing, n_tokens = 917, progress = 1.00, t = 5.58 s / 164.23 tokens per second 10.34.712.732 I slot print_timing: id 2 | task 8973 | prompt processing, n_tokens = 886, progress = 1.00, t = 5.58 s / 158.69 tokens per second 10.34.714.609 I slot print_timing: id 3 | task 8974 | prompt processing, n_tokens = 890, progress = 1.00, t = 5.58 s / 159.41 tokens per second 10.34.787.167 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 963, t_last = 327439243781 10.34.787.255 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.430 MiB) 10.34.794.709 I slot launch_slot_: id 0 | task 8979 | processing task, is_child = 0 10.35.526.210 I slot print_timing: id 1 | task 8972 | prompt eval time = 5661.06 ms / 921 tokens ( 6.15 ms per token, 162.69 tokens per second) 10.35.526.213 I slot print_timing: id 1 | task 8972 | eval time = 741.28 ms / 2 tokens ( 741.28 ms per token, 1.35 tokens per second) 10.35.526.215 I slot print_timing: id 1 | task 8972 | total time = 6402.35 ms / 923 tokens 10.35.526.219 I slot print_timing: id 1 | task 8972 | graphs reused = 7760 10.35.526.219 I slot print_timing: id 1 | task 8972 | graph reallocs = 0 / 0 (same size) / (changed size) 10.35.526.275 I slot release: id 1 | task 8972 | stop processing: n_tokens = 931, truncated = 0 10.35.527.424 I slot print_timing: id 2 | task 8973 | prompt eval time = 5661.92 ms / 890 tokens ( 6.36 ms per token, 157.19 tokens per second) 10.35.527.427 I slot print_timing: id 2 | task 8973 | eval time = 741.36 ms / 2 tokens ( 741.36 ms per token, 1.35 tokens per second) 10.35.527.428 I slot print_timing: id 2 | task 8973 | total time = 6403.27 ms / 892 tokens 10.35.527.428 I slot print_timing: id 2 | task 8973 | graphs reused = 7760 10.35.527.429 I slot print_timing: id 2 | task 8973 | graph reallocs = 0 / 0 (same size) / (changed size) 10.35.527.465 I slot release: id 2 | task 8973 | stop processing: n_tokens = 900, truncated = 0 10.35.528.598 I slot print_timing: id 3 | task 8974 | prompt eval time = 5662.76 ms / 894 tokens ( 6.33 ms per token, 157.87 tokens per second) 10.35.528.602 I slot print_timing: id 3 | task 8974 | eval time = 741.43 ms / 2 tokens ( 741.43 ms per token, 1.35 tokens per second) 10.35.528.602 I slot print_timing: id 3 | task 8974 | total time = 6404.20 ms / 896 tokens 10.35.528.603 I slot print_timing: id 3 | task 8974 | graphs reused = 7760 10.35.528.603 I slot print_timing: id 3 | task 8974 | graph reallocs = 0 / 0 (same size) / (changed size) 10.35.528.626 I slot release: id 3 | task 8974 | stop processing: n_tokens = 904, truncated = 0 10.36.311.055 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 327440061532 10.36.311.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 250.844 MiB) 10.36.572.129 I slot launch_slot_: id 1 | task 8983 | processing task, is_child = 0 10.36.572.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 302.916 MiB) 10.36.579.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.719 MiB) 10.36.585.331 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.897 10.36.585.393 I slot launch_slot_: id 2 | task 8984 | processing task, is_child = 0 10.36.585.464 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 327440063882 10.36.585.564 I slot launch_slot_: id 3 | task 8985 | processing task, is_child = 0 10.40.944.801 I slot print_timing: id 0 | task 8979 | prompt eval time = 4709.41 ms / 894 tokens ( 5.27 ms per token, 189.83 tokens per second) 10.40.944.806 I slot print_timing: id 0 | task 8979 | eval time = 1440.66 ms / 2 tokens ( 1440.66 ms per token, 0.69 tokens per second) 10.40.944.807 I slot print_timing: id 0 | task 8979 | total time = 6150.07 ms / 896 tokens 10.40.944.807 I slot print_timing: id 0 | task 8979 | graphs reused = 7760 10.40.944.808 I slot print_timing: id 0 | task 8979 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.944.890 I slot release: id 0 | task 8979 | stop processing: n_tokens = 904, truncated = 0 10.40.946.134 I slot print_timing: id 1 | task 8983 | prompt processing, n_tokens = 1051, progress = 0.86, t = 4.36 s / 241.25 tokens per second 10.40.948.269 I slot print_timing: id 3 | task 8985 | prompt processing, n_tokens = 1051, progress = 0.87, t = 4.35 s / 241.36 tokens per second 10.41.687.755 I slot print_timing: id 2 | task 8984 | prompt eval time = 4358.57 ms / 83 tokens ( 52.51 ms per token, 19.04 tokens per second) 10.41.687.759 I slot print_timing: id 2 | task 8984 | eval time = 741.62 ms / 2 tokens ( 741.62 ms per token, 1.35 tokens per second) 10.41.687.760 I slot print_timing: id 2 | task 8984 | total time = 5100.20 ms / 85 tokens 10.41.687.761 I slot print_timing: id 2 | task 8984 | graphs reused = 7760 10.41.687.761 I slot print_timing: id 2 | task 8984 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.687.852 I slot release: id 2 | task 8984 | stop processing: n_tokens = 891, truncated = 0 10.41.687.872 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 327445480154 10.41.688.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 233.966 MiB) 10.41.695.669 I slot launch_slot_: id 0 | task 8989 | processing task, is_child = 0 10.41.695.748 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 10.41.702.863 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 327446223109 10.41.702.977 I slot launch_slot_: id 2 | task 8990 | processing task, is_child = 0 10.41.703.199 I slot print_timing: id 1 | task 8983 | prompt processing, n_tokens = 1222, progress = 1.00, t = 5.10 s / 239.64 tokens per second 10.45.556.234 I slot print_timing: id 0 | task 8989 | prompt processing, n_tokens = 764, progress = 0.60, t = 3.85 s / 198.33 tokens per second 10.45.558.508 I slot print_timing: id 2 | task 8990 | prompt processing, n_tokens = 1280, progress = 0.48, t = 3.85 s / 332.47 tokens per second 10.45.558.532 I slot print_timing: id 3 | task 8985 | prompt processing, n_tokens = 1211, progress = 1.00, t = 5.10 s / 237.58 tokens per second 10.47.860.325 I slot print_timing: id 1 | task 8983 | prompt eval time = 8968.86 ms / 1226 tokens ( 7.32 ms per token, 136.70 tokens per second) 10.47.860.337 I slot print_timing: id 1 | task 8983 | eval time = 2304.08 ms / 2 tokens ( 2304.08 ms per token, 0.43 tokens per second) 10.47.860.338 I slot print_timing: id 1 | task 8983 | total time = 11272.94 ms / 1228 tokens 10.47.860.340 I slot print_timing: id 1 | task 8983 | graphs reused = 7760 10.47.860.342 I slot print_timing: id 1 | task 8983 | graph reallocs = 0 / 0 (same size) / (changed size) 10.47.860.516 I slot release: id 1 | task 8983 | stop processing: n_tokens = 1236, truncated = 0 10.47.863.038 I slot print_timing: id 0 | task 8989 | prompt processing, n_tokens = 1051, progress = 0.82, t = 6.15 s / 170.82 tokens per second 10.47.868.879 I slot print_timing: id 2 | task 8990 | prompt processing, n_tokens = 2146, progress = 0.81, t = 6.15 s / 348.90 tokens per second 10.48.846.953 I slot print_timing: id 3 | task 8985 | prompt eval time = 11273.69 ms / 1215 tokens ( 9.28 ms per token, 107.77 tokens per second) 10.48.846.964 I slot print_timing: id 3 | task 8985 | eval time = 983.93 ms / 2 tokens ( 983.93 ms per token, 1.02 tokens per second) 10.48.846.969 I slot print_timing: id 3 | task 8985 | total time = 12257.62 ms / 1217 tokens 10.48.846.971 I slot print_timing: id 3 | task 8985 | graphs reused = 7760 10.48.846.972 I slot print_timing: id 3 | task 8985 | graph reallocs = 0 / 0 (same size) / (changed size) 10.48.847.164 I slot release: id 3 | task 8985 | stop processing: n_tokens = 1225, truncated = 0 10.48.847.202 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1236, t_last = 327452395771 10.48.847.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 251.828 MiB) 10.48.868.990 I slot launch_slot_: id 1 | task 8994 | processing task, is_child = 0 10.48.869.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 303.408 MiB) 10.48.880.876 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1225, t_last = 327453382419 10.48.881.078 I slot launch_slot_: id 3 | task 8995 | processing task, is_child = 0 10.48.881.092 I slot print_timing: id 0 | task 8989 | prompt processing, n_tokens = 1276, progress = 1.00, t = 7.14 s / 178.70 tokens per second 10.52.752.718 I slot print_timing: id 1 | task 8994 | prompt processing, n_tokens = 2044, progress = 0.80, t = 3.87 s / 528.42 tokens per second 10.52.752.734 I slot print_timing: id 2 | task 8990 | prompt processing, n_tokens = 2353, progress = 0.88, t = 7.14 s / 329.63 tokens per second 10.56.766.401 I slot print_timing: id 0 | task 8989 | prompt eval time = 11049.70 ms / 1280 tokens ( 8.63 ms per token, 115.84 tokens per second) 10.56.766.420 I slot print_timing: id 0 | task 8989 | eval time = 4013.68 ms / 2 tokens ( 4013.68 ms per token, 0.25 tokens per second) 10.56.766.422 I slot print_timing: id 0 | task 8989 | total time = 15063.39 ms / 1282 tokens 10.56.766.423 I slot print_timing: id 0 | task 8989 | graphs reused = 7760 10.56.766.424 I slot print_timing: id 0 | task 8989 | graph reallocs = 0 / 0 (same size) / (changed size) 10.56.766.614 I slot release: id 0 | task 8989 | stop processing: n_tokens = 1290, truncated = 0 10.56.766.688 I slot print_timing: id 1 | task 8994 | prompt processing, n_tokens = 2052, progress = 0.80, t = 7.88 s / 260.43 tokens per second 10.56.773.174 I slot print_timing: id 2 | task 8990 | prompt processing, n_tokens = 2658, progress = 1.00, t = 15.06 s / 176.52 tokens per second 10.56.777.937 I slot print_timing: id 3 | task 8995 | prompt processing, n_tokens = 1734, progress = 0.62, t = 4.01 s / 432.79 tokens per second 10.58.620.939 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1290, t_last = 327461301870 10.58.621.342 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 301.404 MiB) 10.58.642.753 I slot launch_slot_: id 0 | task 8999 | processing task, is_child = 0 11.02.522.307 I slot print_timing: id 2 | task 8990 | prompt eval time = 16915.81 ms / 2662 tokens ( 6.35 ms per token, 157.37 tokens per second) 11.02.522.322 I slot print_timing: id 2 | task 8990 | eval time = 3901.38 ms / 2 tokens ( 3901.38 ms per token, 0.26 tokens per second) 11.02.522.324 I slot print_timing: id 2 | task 8990 | total time = 20817.19 ms / 2664 tokens 11.02.522.326 I slot print_timing: id 2 | task 8990 | graphs reused = 7760 11.02.522.328 I slot print_timing: id 2 | task 8990 | graph reallocs = 0 / 0 (same size) / (changed size) 11.02.522.809 I slot release: id 2 | task 8990 | stop processing: n_tokens = 2672, truncated = 0 11.02.522.894 I slot print_timing: id 0 | task 8999 | prompt processing, n_tokens = 2047, progress = 0.75, t = 3.88 s / 528.20 tokens per second 11.02.522.936 I slot print_timing: id 1 | task 8994 | prompt processing, n_tokens = 2353, progress = 0.92, t = 9.73 s / 241.73 tokens per second 11.02.530.031 I slot print_timing: id 3 | task 8995 | prompt processing, n_tokens = 2301, progress = 0.82, t = 5.86 s / 392.59 tokens per second 11.03.380.606 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2672, t_last = 327467058071 11.03.381.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.156 MiB) 11.03.538.680 I slot launch_slot_: id 2 | task 9002 | processing task, is_child = 0 11.03.538.707 I slot print_timing: id 0 | task 8999 | prompt processing, n_tokens = 2213, progress = 0.81, t = 4.74 s / 467.09 tokens per second 11.03.542.628 I slot print_timing: id 1 | task 8994 | prompt processing, n_tokens = 2564, progress = 1.00, t = 14.50 s / 176.86 tokens per second 11.03.547.729 I slot print_timing: id 3 | task 8995 | prompt processing, n_tokens = 2353, progress = 0.84, t = 10.62 s / 221.47 tokens per second 11.07.334.388 I slot print_timing: id 0 | task 8999 | prompt processing, n_tokens = 2353, progress = 0.86, t = 8.69 s / 270.85 tokens per second 11.07.341.712 I slot print_timing: id 2 | task 9002 | prompt processing, n_tokens = 1294, progress = 0.72, t = 3.78 s / 342.03 tokens per second 11.07.345.902 I slot print_timing: id 3 | task 8995 | prompt processing, n_tokens = 2813, progress = 1.00, t = 14.57 s / 193.01 tokens per second 11.08.573.947 I slot print_timing: id 1 | task 8994 | prompt eval time = 18450.81 ms / 2568 tokens ( 7.18 ms per token, 139.18 tokens per second) 11.08.573.959 I slot print_timing: id 1 | task 8994 | eval time = 1239.62 ms / 2 tokens ( 1239.62 ms per token, 0.81 tokens per second) 11.08.573.960 I slot print_timing: id 1 | task 8994 | total time = 19690.44 ms / 2570 tokens 11.08.573.962 I slot print_timing: id 1 | task 8994 | graphs reused = 7760 11.08.573.964 I slot print_timing: id 1 | task 8994 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.574.372 I slot release: id 1 | task 8994 | stop processing: n_tokens = 2578, truncated = 0 11.08.576.704 I slot print_timing: id 0 | task 8999 | prompt processing, n_tokens = 2725, progress = 1.00, t = 9.93 s / 274.51 tokens per second 11.08.582.559 I slot print_timing: id 2 | task 9002 | prompt processing, n_tokens = 1467, progress = 0.81, t = 5.02 s / 292.09 tokens per second 11.09.335.680 I slot print_timing: id 3 | task 8995 | prompt eval time = 15820.35 ms / 2817 tokens ( 5.62 ms per token, 178.06 tokens per second) 11.09.335.688 I slot print_timing: id 3 | task 8995 | eval time = 759.00 ms / 2 tokens ( 759.00 ms per token, 1.32 tokens per second) 11.09.335.690 I slot print_timing: id 3 | task 8995 | total time = 16579.35 ms / 2819 tokens 11.09.335.692 I slot print_timing: id 3 | task 8995 | graphs reused = 7760 11.09.335.693 I slot print_timing: id 3 | task 8995 | graph reallocs = 0 / 0 (same size) / (changed size) 11.09.336.128 I slot release: id 3 | task 8995 | stop processing: n_tokens = 2827, truncated = 0 11.09.336.171 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2578, t_last = 327473109632 11.09.336.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.842 MiB) 11.09.374.598 I slot launch_slot_: id 1 | task 9006 | processing task, is_child = 0 11.09.374.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 235.232 MiB) 11.09.406.672 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2827, t_last = 327473871385 11.09.406.959 I slot launch_slot_: id 3 | task 9007 | processing task, is_child = 0 11.09.407.414 I slot print_timing: id 2 | task 9002 | prompt processing, n_tokens = 1806, progress = 1.00, t = 5.78 s / 312.36 tokens per second 11.13.352.646 I slot print_timing: id 0 | task 8999 | prompt eval time = 10690.61 ms / 2729 tokens ( 3.92 ms per token, 255.27 tokens per second) 11.13.352.653 I slot print_timing: id 0 | task 8999 | eval time = 4019.24 ms / 2 tokens ( 4019.24 ms per token, 0.25 tokens per second) 11.13.352.653 I slot print_timing: id 0 | task 8999 | total time = 14709.85 ms / 2731 tokens 11.13.352.654 I slot print_timing: id 0 | task 8999 | graphs reused = 7760 11.13.352.654 I slot print_timing: id 0 | task 8999 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.352.836 I slot release: id 0 | task 8999 | stop processing: n_tokens = 2739, truncated = 0 11.13.354.183 I slot print_timing: id 1 | task 9006 | prompt processing, n_tokens = 1354, progress = 0.73, t = 3.94 s / 343.27 tokens per second 11.13.357.577 I slot print_timing: id 3 | task 9007 | prompt processing, n_tokens = 689, progress = 0.33, t = 3.94 s / 174.81 tokens per second 11.15.171.296 I slot print_timing: id 2 | task 9002 | prompt eval time = 9807.11 ms / 1810 tokens ( 5.42 ms per token, 184.56 tokens per second) 11.15.171.303 I slot print_timing: id 2 | task 9002 | eval time = 1817.14 ms / 2 tokens ( 1817.14 ms per token, 0.55 tokens per second) 11.15.171.304 I slot print_timing: id 2 | task 9002 | total time = 11624.26 ms / 1812 tokens 11.15.171.305 I slot print_timing: id 2 | task 9002 | graphs reused = 7760 11.15.171.305 I slot print_timing: id 2 | task 9002 | graph reallocs = 0 / 0 (same size) / (changed size) 11.15.171.465 I slot release: id 2 | task 9002 | stop processing: n_tokens = 1820, truncated = 0 11.15.171.487 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.799 (> 0.100 thold), f_keep = 0.831 11.15.171.638 I slot launch_slot_: id 2 | task 9010 | processing task, is_child = 0 11.15.171.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.014 MiB) 11.15.172.474 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.965 MiB) 11.15.197.151 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2739, t_last = 327477888092 11.15.197.360 I slot launch_slot_: id 0 | task 9011 | processing task, is_child = 0 11.15.197.739 I slot print_timing: id 1 | task 9006 | prompt processing, n_tokens = 1467, progress = 0.79, t = 5.76 s / 254.55 tokens per second 11.19.085.705 I slot print_timing: id 0 | task 9011 | prompt processing, n_tokens = 1467, progress = 0.74, t = 3.89 s / 377.28 tokens per second 11.19.229.137 I slot print_timing: id 1 | task 9006 | prompt processing, n_tokens = 1866, progress = 1.00, t = 9.68 s / 192.79 tokens per second 11.19.231.365 I slot print_timing: id 2 | task 9010 | prompt processing, n_tokens = 182, progress = 0.89, t = 3.89 s / 46.83 tokens per second 11.19.233.289 I slot print_timing: id 3 | task 9007 | prompt processing, n_tokens = 1467, progress = 0.71, t = 5.76 s / 254.68 tokens per second 11.19.997.506 I slot print_timing: id 0 | task 9011 | prompt processing, n_tokens = 1475, progress = 0.74, t = 4.80 s / 307.52 tokens per second 11.20.005.019 I slot print_timing: id 2 | task 9010 | prompt processing, n_tokens = 377, progress = 1.00, t = 4.79 s / 78.64 tokens per second 11.20.009.351 I slot print_timing: id 3 | task 9007 | prompt processing, n_tokens = 1565, progress = 0.75, t = 10.58 s / 147.87 tokens per second 11.22.065.324 I slot print_timing: id 1 | task 9006 | prompt eval time = 10590.44 ms / 1870 tokens ( 5.66 ms per token, 176.57 tokens per second) 11.22.065.337 I slot print_timing: id 1 | task 9006 | eval time = 2067.86 ms / 2 tokens ( 2067.86 ms per token, 0.48 tokens per second) 11.22.065.339 I slot print_timing: id 1 | task 9006 | total time = 12658.30 ms / 1872 tokens 11.22.065.341 I slot print_timing: id 1 | task 9006 | graphs reused = 7760 11.22.065.342 I slot print_timing: id 1 | task 9006 | graph reallocs = 0 / 0 (same size) / (changed size) 11.22.065.628 I slot release: id 1 | task 9006 | stop processing: n_tokens = 1880, truncated = 0 11.22.068.020 I slot print_timing: id 0 | task 9011 | prompt processing, n_tokens = 1987, progress = 1.00, t = 6.86 s / 289.49 tokens per second 11.22.074.139 I slot print_timing: id 3 | task 9007 | prompt processing, n_tokens = 2077, progress = 1.00, t = 12.65 s / 164.17 tokens per second 11.22.184.047 I slot print_timing: id 2 | task 9010 | prompt eval time = 6868.42 ms / 381 tokens ( 18.03 ms per token, 55.47 tokens per second) 11.22.184.058 I slot print_timing: id 2 | task 9010 | eval time = 116.08 ms / 2 tokens ( 116.08 ms per token, 8.62 tokens per second) 11.22.184.059 I slot print_timing: id 2 | task 9010 | total time = 6984.49 ms / 383 tokens 11.22.184.063 I slot print_timing: id 2 | task 9010 | graphs reused = 7760 11.22.184.065 I slot print_timing: id 2 | task 9010 | graph reallocs = 0 / 0 (same size) / (changed size) 11.22.184.202 I slot release: id 2 | task 9010 | stop processing: n_tokens = 1894, truncated = 0 11.22.186.377 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.804 11.22.186.511 I slot launch_slot_: id 1 | task 9016 | processing task, is_child = 0 11.22.186.737 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.508 MiB) 11.22.205.580 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1894, t_last = 327486719461 11.22.205.817 I slot launch_slot_: id 2 | task 9017 | processing task, is_child = 0 11.23.297.845 I slot print_timing: id 0 | task 9011 | prompt eval time = 6984.19 ms / 1991 tokens ( 3.51 ms per token, 285.07 tokens per second) 11.23.297.848 I slot print_timing: id 0 | task 9011 | eval time = 1116.28 ms / 2 tokens ( 1116.28 ms per token, 0.90 tokens per second) 11.23.297.849 I slot print_timing: id 0 | task 9011 | total time = 8100.47 ms / 1993 tokens 11.23.297.849 I slot print_timing: id 0 | task 9011 | graphs reused = 7760 11.23.297.850 I slot print_timing: id 0 | task 9011 | graph reallocs = 0 / 0 (same size) / (changed size) 11.23.297.952 I slot release: id 0 | task 9011 | stop processing: n_tokens = 2001, truncated = 0 11.23.299.227 I slot print_timing: id 3 | task 9007 | prompt eval time = 12776.50 ms / 2081 tokens ( 6.14 ms per token, 162.88 tokens per second) 11.23.299.229 I slot print_timing: id 3 | task 9007 | eval time = 1112.86 ms / 2 tokens ( 1112.86 ms per token, 0.90 tokens per second) 11.23.299.230 I slot print_timing: id 3 | task 9007 | total time = 13889.35 ms / 2083 tokens 11.23.299.230 I slot print_timing: id 3 | task 9007 | graphs reused = 7760 11.23.299.231 I slot print_timing: id 3 | task 9007 | graph reallocs = 0 / 0 (same size) / (changed size) 11.23.299.324 I slot release: id 3 | task 9007 | stop processing: n_tokens = 2091, truncated = 0 11.24.105.749 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2001, t_last = 327487833209 11.24.105.914 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.967 MiB) 11.24.116.334 I slot launch_slot_: id 0 | task 9021 | processing task, is_child = 0 11.24.116.454 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 262.519 MiB) 11.24.130.178 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2091, t_last = 327487834582 11.24.130.376 I slot launch_slot_: id 3 | task 9020 | processing task, is_child = 0 11.25.254.913 I slot print_timing: id 1 | task 9016 | prompt eval time = 1899.91 ms / 301 tokens ( 6.31 ms per token, 158.43 tokens per second) 11.25.254.919 I slot print_timing: id 1 | task 9016 | eval time = 1149.16 ms / 2 tokens ( 1149.16 ms per token, 0.87 tokens per second) 11.25.254.919 I slot print_timing: id 1 | task 9016 | total time = 3049.08 ms / 303 tokens 11.25.254.920 I slot print_timing: id 1 | task 9016 | graphs reused = 7760 11.25.254.920 I slot print_timing: id 1 | task 9016 | graph reallocs = 0 / 0 (same size) / (changed size) 11.25.255.073 I slot release: id 1 | task 9016 | stop processing: n_tokens = 1814, truncated = 0 11.25.257.072 I slot print_timing: id 2 | task 9017 | prompt processing, n_tokens = 712, progress = 0.99, t = 3.05 s / 233.77 tokens per second 11.26.721.768 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1814, t_last = 327489790328 11.26.721.926 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.886 MiB) 11.26.721.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.558 MiB) 11.26.747.169 I slot launch_slot_: id 1 | task 9024 | processing task, is_child = 0 11.27.820.068 I slot print_timing: id 2 | task 9017 | prompt eval time = 4513.64 ms / 716 tokens ( 6.30 ms per token, 158.63 tokens per second) 11.27.820.074 I slot print_timing: id 2 | task 9017 | eval time = 1098.32 ms / 2 tokens ( 1098.32 ms per token, 0.91 tokens per second) 11.27.820.078 I slot print_timing: id 2 | task 9017 | total time = 5611.96 ms / 718 tokens 11.27.820.078 I slot print_timing: id 2 | task 9017 | graphs reused = 7760 11.27.820.078 I slot print_timing: id 2 | task 9017 | graph reallocs = 0 / 0 (same size) / (changed size) 11.27.820.119 I slot release: id 2 | task 9017 | stop processing: n_tokens = 726, truncated = 0 11.27.820.138 I slot print_timing: id 0 | task 9021 | prompt processing, n_tokens = 731, progress = 0.99, t = 3.69 s / 198.18 tokens per second 11.27.823.479 I slot print_timing: id 3 | task 9020 | prompt processing, n_tokens = 744, progress = 0.99, t = 3.69 s / 201.82 tokens per second 11.28.661.143 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.879 11.28.661.289 I slot launch_slot_: id 2 | task 9027 | processing task, is_child = 0 11.29.159.264 I slot print_timing: id 0 | task 9021 | prompt eval time = 4529.57 ms / 735 tokens ( 6.16 ms per token, 162.27 tokens per second) 11.29.159.271 I slot print_timing: id 0 | task 9021 | eval time = 499.29 ms / 2 tokens ( 499.29 ms per token, 2.00 tokens per second) 11.29.159.272 I slot print_timing: id 0 | task 9021 | total time = 5028.86 ms / 737 tokens 11.29.159.272 I slot print_timing: id 0 | task 9021 | graphs reused = 7760 11.29.159.273 I slot print_timing: id 0 | task 9021 | graph reallocs = 0 / 0 (same size) / (changed size) 11.29.159.345 I slot release: id 0 | task 9021 | stop processing: n_tokens = 745, truncated = 0 11.29.160.505 I slot print_timing: id 3 | task 9020 | prompt eval time = 4528.58 ms / 748 tokens ( 6.05 ms per token, 165.17 tokens per second) 11.29.160.510 I slot print_timing: id 3 | task 9020 | eval time = 499.37 ms / 2 tokens ( 499.37 ms per token, 2.00 tokens per second) 11.29.160.511 I slot print_timing: id 3 | task 9020 | total time = 5027.95 ms / 750 tokens 11.29.160.511 I slot print_timing: id 3 | task 9020 | graphs reused = 7760 11.29.160.511 I slot print_timing: id 3 | task 9020 | graph reallocs = 0 / 0 (same size) / (changed size) 11.29.160.552 I slot release: id 3 | task 9020 | stop processing: n_tokens = 758, truncated = 0 11.29.205.651 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 327493694600 11.29.205.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 235.513 MiB) 11.29.211.059 I slot launch_slot_: id 0 | task 9030 | processing task, is_child = 0 11.29.211.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 231.434 MiB) 11.29.216.410 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 758, t_last = 327493695807 11.29.216.532 I slot launch_slot_: id 3 | task 9031 | processing task, is_child = 0 11.30.764.414 I slot print_timing: id 1 | task 9024 | prompt eval time = 2455.68 ms / 712 tokens ( 3.45 ms per token, 289.94 tokens per second) 11.30.764.418 I slot print_timing: id 1 | task 9024 | eval time = 1559.86 ms / 2 tokens ( 1559.86 ms per token, 0.64 tokens per second) 11.30.764.418 I slot print_timing: id 1 | task 9024 | total time = 4015.54 ms / 714 tokens 11.30.764.419 I slot print_timing: id 1 | task 9024 | graphs reused = 7760 11.30.764.419 I slot print_timing: id 1 | task 9024 | graph reallocs = 0 / 0 (same size) / (changed size) 11.30.764.458 I slot release: id 1 | task 9024 | stop processing: n_tokens = 722, truncated = 0 11.30.765.694 I slot print_timing: id 2 | task 9027 | prompt eval time = 542.00 ms / 101 tokens ( 5.37 ms per token, 186.35 tokens per second) 11.30.765.697 I slot print_timing: id 2 | task 9027 | eval time = 1560.04 ms / 2 tokens ( 1560.04 ms per token, 0.64 tokens per second) 11.30.765.700 I slot print_timing: id 2 | task 9027 | total time = 2102.05 ms / 103 tokens 11.30.765.700 I slot print_timing: id 2 | task 9027 | graphs reused = 7760 11.30.765.701 I slot print_timing: id 2 | task 9027 | graph reallocs = 0 / 0 (same size) / (changed size) 11.30.765.731 I slot release: id 2 | task 9027 | stop processing: n_tokens = 740, truncated = 0 11.31.430.115 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 722, t_last = 327495299713 11.32.152.901 I slot launch_slot_: id 1 | task 9034 | processing task, is_child = 0 11.32.152.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.465 MiB) 11.32.152.982 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.787 MiB) 11.32.160.074 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 327495300986 11.32.160.207 I slot launch_slot_: id 2 | task 9035 | processing task, is_child = 0 11.33.924.264 I slot print_timing: id 0 | task 9030 | prompt processing, n_tokens = 792, progress = 1.00, t = 4.71 s / 168.23 tokens per second 11.33.984.893 I slot print_timing: id 3 | task 9031 | prompt processing, n_tokens = 1039, progress = 1.00, t = 4.71 s / 220.71 tokens per second 11.35.559.351 I slot print_timing: id 1 | task 9034 | prompt processing, n_tokens = 672, progress = 0.85, t = 3.39 s / 197.94 tokens per second 11.35.561.266 I slot print_timing: id 2 | task 9035 | prompt processing, n_tokens = 672, progress = 0.84, t = 3.39 s / 197.95 tokens per second 11.36.174.792 I slot print_timing: id 0 | task 9030 | prompt eval time = 6341.60 ms / 796 tokens ( 7.97 ms per token, 125.52 tokens per second) 11.36.174.795 I slot print_timing: id 0 | task 9030 | eval time = 616.65 ms / 2 tokens ( 616.65 ms per token, 1.62 tokens per second) 11.36.174.796 I slot print_timing: id 0 | task 9030 | total time = 6958.25 ms / 798 tokens 11.36.174.796 I slot print_timing: id 0 | task 9030 | graphs reused = 7760 11.36.174.796 I slot print_timing: id 0 | task 9030 | graph reallocs = 0 / 0 (same size) / (changed size) 11.36.174.831 I slot release: id 0 | task 9030 | stop processing: n_tokens = 806, truncated = 0 11.36.175.946 I slot print_timing: id 3 | task 9031 | prompt eval time = 6342.64 ms / 1043 tokens ( 6.08 ms per token, 164.44 tokens per second) 11.36.175.949 I slot print_timing: id 3 | task 9031 | eval time = 616.61 ms / 2 tokens ( 616.61 ms per token, 1.62 tokens per second) 11.36.175.949 I slot print_timing: id 3 | task 9031 | total time = 6959.24 ms / 1045 tokens 11.36.175.949 I slot print_timing: id 3 | task 9031 | graphs reused = 7760 11.36.175.950 I slot print_timing: id 3 | task 9031 | graph reallocs = 0 / 0 (same size) / (changed size) 11.36.175.980 I slot release: id 3 | task 9031 | stop processing: n_tokens = 1053, truncated = 0 11.36.175.986 I slot print_timing: id 1 | task 9034 | prompt processing, n_tokens = 789, progress = 1.00, t = 4.01 s / 196.68 tokens per second 11.36.177.844 I slot print_timing: id 2 | task 9035 | prompt processing, n_tokens = 799, progress = 1.00, t = 4.01 s / 199.18 tokens per second 11.36.221.596 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 327500710086 11.36.230.051 I slot launch_slot_: id 0 | task 9040 | processing task, is_child = 0 11.36.230.129 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.917 MiB) 11.36.230.133 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.073 MiB) 11.36.249.718 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 327500711235 11.36.249.833 I slot launch_slot_: id 3 | task 9041 | processing task, is_child = 0 11.37.457.890 I slot print_timing: id 1 | task 9034 | prompt eval time = 4058.52 ms / 793 tokens ( 5.12 ms per token, 195.39 tokens per second) 11.37.457.893 I slot print_timing: id 1 | task 9034 | eval time = 1237.37 ms / 2 tokens ( 1237.37 ms per token, 0.81 tokens per second) 11.37.457.893 I slot print_timing: id 1 | task 9034 | total time = 5295.89 ms / 795 tokens 11.37.457.894 I slot print_timing: id 1 | task 9034 | graphs reused = 7760 11.37.457.894 I slot print_timing: id 1 | task 9034 | graph reallocs = 0 / 0 (same size) / (changed size) 11.37.457.929 I slot release: id 1 | task 9034 | stop processing: n_tokens = 803, truncated = 0 11.37.459.019 I slot print_timing: id 2 | task 9035 | prompt eval time = 4059.42 ms / 803 tokens ( 5.06 ms per token, 197.81 tokens per second) 11.37.459.022 I slot print_timing: id 2 | task 9035 | eval time = 1237.42 ms / 2 tokens ( 1237.42 ms per token, 0.81 tokens per second) 11.37.459.022 I slot print_timing: id 2 | task 9035 | total time = 5296.85 ms / 805 tokens 11.37.459.022 I slot print_timing: id 2 | task 9035 | graphs reused = 7760 11.37.459.023 I slot print_timing: id 2 | task 9035 | graph reallocs = 0 / 0 (same size) / (changed size) 11.37.459.044 I slot release: id 2 | task 9035 | stop processing: n_tokens = 813, truncated = 0 11.38.241.775 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 327501993184 11.38.241.861 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.139 MiB) 11.39.015.665 I slot launch_slot_: id 1 | task 9044 | processing task, is_child = 0 11.39.030.369 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 813, t_last = 327501994299 11.39.030.488 I slot launch_slot_: id 2 | task 9045 | processing task, is_child = 0 11.40.906.974 I slot print_timing: id 0 | task 9040 | prompt processing, n_tokens = 824, progress = 1.00, t = 4.66 s / 176.93 tokens per second 11.40.943.953 I slot print_timing: id 3 | task 9041 | prompt processing, n_tokens = 832, progress = 1.00, t = 4.66 s / 178.66 tokens per second 11.42.311.795 I slot print_timing: id 1 | task 9044 | prompt processing, n_tokens = 712, progress = 0.80, t = 3.28 s / 217.26 tokens per second 11.42.315.491 I slot print_timing: id 2 | task 9045 | prompt processing, n_tokens = 712, progress = 0.79, t = 3.28 s / 217.27 tokens per second 11.43.071.287 I slot print_timing: id 0 | task 9040 | prompt eval time = 6060.59 ms / 828 tokens ( 7.32 ms per token, 136.62 tokens per second) 11.43.071.291 I slot print_timing: id 0 | task 9040 | eval time = 760.85 ms / 2 tokens ( 760.85 ms per token, 1.31 tokens per second) 11.43.071.291 I slot print_timing: id 0 | task 9040 | total time = 6821.44 ms / 830 tokens 11.43.071.292 I slot print_timing: id 0 | task 9040 | graphs reused = 7760 11.43.071.292 I slot print_timing: id 0 | task 9040 | graph reallocs = 0 / 0 (same size) / (changed size) 11.43.071.366 I slot release: id 0 | task 9040 | stop processing: n_tokens = 838, truncated = 0 11.43.072.509 I slot print_timing: id 3 | task 9041 | prompt eval time = 6061.77 ms / 836 tokens ( 7.25 ms per token, 137.91 tokens per second) 11.43.072.512 I slot print_timing: id 3 | task 9041 | eval time = 760.73 ms / 2 tokens ( 760.73 ms per token, 1.31 tokens per second) 11.43.072.512 I slot print_timing: id 3 | task 9041 | total time = 6822.50 ms / 838 tokens 11.43.072.513 I slot print_timing: id 3 | task 9041 | graphs reused = 7760 11.43.072.513 I slot print_timing: id 3 | task 9041 | graph reallocs = 0 / 0 (same size) / (changed size) 11.43.072.550 I slot release: id 3 | task 9041 | stop processing: n_tokens = 846, truncated = 0 11.43.072.569 I slot print_timing: id 1 | task 9044 | prompt processing, n_tokens = 889, progress = 1.00, t = 4.04 s / 220.16 tokens per second 11.43.075.055 I slot print_timing: id 2 | task 9045 | prompt processing, n_tokens = 895, progress = 1.00, t = 4.04 s / 221.65 tokens per second 11.43.118.101 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 838, t_last = 327507606621 11.43.118.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 298.767 MiB) 11.43.137.974 I slot launch_slot_: id 0 | task 9050 | processing task, is_child = 0 11.43.138.053 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.420 MiB) 11.43.145.994 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.869 (> 0.100 thold), f_keep = 0.884 11.43.146.060 I slot launch_slot_: id 3 | task 9051 | processing task, is_child = 0 11.43.801.005 I slot print_timing: id 1 | task 9044 | prompt eval time = 4084.81 ms / 893 tokens ( 4.57 ms per token, 218.61 tokens per second) 11.43.801.012 I slot print_timing: id 1 | task 9044 | eval time = 684.03 ms / 2 tokens ( 684.03 ms per token, 1.46 tokens per second) 11.43.801.013 I slot print_timing: id 1 | task 9044 | total time = 4768.85 ms / 895 tokens 11.43.801.014 I slot print_timing: id 1 | task 9044 | graphs reused = 7760 11.43.801.017 I slot print_timing: id 1 | task 9044 | graph reallocs = 0 / 0 (same size) / (changed size) 11.43.801.069 I slot release: id 1 | task 9044 | stop processing: n_tokens = 903, truncated = 0 11.43.802.244 I slot print_timing: id 2 | task 9045 | prompt eval time = 4085.77 ms / 899 tokens ( 4.54 ms per token, 220.03 tokens per second) 11.43.802.251 I slot print_timing: id 2 | task 9045 | eval time = 684.14 ms / 2 tokens ( 684.14 ms per token, 1.46 tokens per second) 11.43.802.252 I slot print_timing: id 2 | task 9045 | total time = 4769.92 ms / 901 tokens 11.43.802.252 I slot print_timing: id 2 | task 9045 | graphs reused = 7760 11.43.802.253 I slot print_timing: id 2 | task 9045 | graph reallocs = 0 / 0 (same size) / (changed size) 11.43.802.290 I slot release: id 2 | task 9045 | stop processing: n_tokens = 909, truncated = 0 11.44.606.727 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 327508336324 11.44.606.850 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 243.671 MiB) 11.44.621.160 I slot launch_slot_: id 1 | task 9054 | processing task, is_child = 0 11.44.621.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.870 MiB) 11.44.627.009 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 909, t_last = 327508337545 11.44.627.125 I slot launch_slot_: id 2 | task 9055 | processing task, is_child = 0 11.46.078.579 I slot print_timing: id 3 | task 9051 | prompt eval time = 1460.45 ms / 113 tokens ( 12.92 ms per token, 77.37 tokens per second) 11.46.078.582 I slot print_timing: id 3 | task 9051 | eval time = 1471.86 ms / 2 tokens ( 1471.86 ms per token, 0.68 tokens per second) 11.46.078.583 I slot print_timing: id 3 | task 9051 | total time = 2932.30 ms / 115 tokens 11.46.078.583 I slot print_timing: id 3 | task 9051 | graphs reused = 7760 11.46.078.584 I slot print_timing: id 3 | task 9051 | graph reallocs = 0 / 0 (same size) / (changed size) 11.46.078.654 I slot release: id 3 | task 9051 | stop processing: n_tokens = 862, truncated = 0 11.47.615.144 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 327510613909 11.47.615.260 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.906 MiB) 11.47.627.395 I slot launch_slot_: id 3 | task 9058 | processing task, is_child = 0 11.48.660.775 I slot print_timing: id 0 | task 9050 | prompt eval time = 4469.06 ms / 682 tokens ( 6.55 ms per token, 152.60 tokens per second) 11.48.660.782 I slot print_timing: id 0 | task 9050 | eval time = 1045.63 ms / 2 tokens ( 1045.63 ms per token, 0.96 tokens per second) 11.48.660.783 I slot print_timing: id 0 | task 9050 | total time = 5514.70 ms / 684 tokens 11.48.660.784 I slot print_timing: id 0 | task 9050 | graphs reused = 7760 11.48.660.784 I slot print_timing: id 0 | task 9050 | graph reallocs = 0 / 0 (same size) / (changed size) 11.48.660.839 I slot release: id 0 | task 9050 | stop processing: n_tokens = 692, truncated = 0 11.48.660.861 I slot print_timing: id 1 | task 9054 | prompt processing, n_tokens = 841, progress = 1.00, t = 4.03 s / 208.64 tokens per second 11.48.664.917 I slot print_timing: id 2 | task 9055 | prompt processing, n_tokens = 818, progress = 1.00, t = 4.03 s / 202.95 tokens per second 11.49.449.495 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 327513196094 11.49.449.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.870 MiB) 11.49.464.716 I slot launch_slot_: id 0 | task 9061 | processing task, is_child = 0 11.50.228.418 I slot print_timing: id 1 | task 9054 | prompt eval time = 4819.48 ms / 845 tokens ( 5.70 ms per token, 175.33 tokens per second) 11.50.228.421 I slot print_timing: id 1 | task 9054 | eval time = 780.12 ms / 2 tokens ( 780.12 ms per token, 1.28 tokens per second) 11.50.228.421 I slot print_timing: id 1 | task 9054 | total time = 5599.60 ms / 847 tokens 11.50.228.422 I slot print_timing: id 1 | task 9054 | graphs reused = 7760 11.50.228.422 I slot print_timing: id 1 | task 9054 | graph reallocs = 0 / 0 (same size) / (changed size) 11.50.228.505 I slot release: id 1 | task 9054 | stop processing: n_tokens = 855, truncated = 0 11.50.229.631 I slot print_timing: id 2 | task 9055 | prompt eval time = 4820.46 ms / 822 tokens ( 5.86 ms per token, 170.52 tokens per second) 11.50.229.639 I slot print_timing: id 2 | task 9055 | eval time = 780.14 ms / 2 tokens ( 780.14 ms per token, 1.28 tokens per second) 11.50.229.639 I slot print_timing: id 2 | task 9055 | total time = 5600.61 ms / 824 tokens 11.50.229.640 I slot print_timing: id 2 | task 9055 | graphs reused = 7760 11.50.229.640 I slot print_timing: id 2 | task 9055 | graph reallocs = 0 / 0 (same size) / (changed size) 11.50.229.677 I slot release: id 2 | task 9055 | stop processing: n_tokens = 832, truncated = 0 11.51.036.887 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 327514763760 11.51.037.007 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 298.310 MiB) 11.51.052.154 I slot launch_slot_: id 1 | task 9064 | processing task, is_child = 0 11.51.052.230 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.436 MiB) 11.51.060.921 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 327514764932 11.51.061.035 I slot launch_slot_: id 2 | task 9065 | processing task, is_child = 0 11.52.115.140 I slot print_timing: id 3 | task 9058 | prompt eval time = 3406.16 ms / 750 tokens ( 4.54 ms per token, 220.19 tokens per second) 11.52.115.146 I slot print_timing: id 3 | task 9058 | eval time = 1078.26 ms / 2 tokens ( 1078.26 ms per token, 0.93 tokens per second) 11.52.115.146 I slot print_timing: id 3 | task 9058 | total time = 4484.41 ms / 752 tokens 11.52.115.147 I slot print_timing: id 3 | task 9058 | graphs reused = 7760 11.52.115.147 I slot print_timing: id 3 | task 9058 | graph reallocs = 0 / 0 (same size) / (changed size) 11.52.115.190 I slot release: id 3 | task 9058 | stop processing: n_tokens = 760, truncated = 0 11.53.687.278 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 327516650445 11.53.687.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.076 MiB) 11.53.696.416 I slot launch_slot_: id 3 | task 9068 | processing task, is_child = 0 11.54.613.569 I slot print_timing: id 0 | task 9061 | prompt eval time = 4222.54 ms / 736 tokens ( 5.74 ms per token, 174.30 tokens per second) 11.54.613.575 I slot print_timing: id 0 | task 9061 | eval time = 926.29 ms / 2 tokens ( 926.29 ms per token, 1.08 tokens per second) 11.54.613.576 I slot print_timing: id 0 | task 9061 | total time = 5148.83 ms / 738 tokens 11.54.613.576 I slot print_timing: id 0 | task 9061 | graphs reused = 7760 11.54.613.577 I slot print_timing: id 0 | task 9061 | graph reallocs = 0 / 0 (same size) / (changed size) 11.54.613.632 I slot release: id 0 | task 9061 | stop processing: n_tokens = 746, truncated = 0 11.54.613.656 I slot print_timing: id 1 | task 9064 | prompt processing, n_tokens = 697, progress = 0.99, t = 3.55 s / 196.35 tokens per second 11.54.617.771 I slot print_timing: id 2 | task 9065 | prompt processing, n_tokens = 719, progress = 0.99, t = 3.55 s / 202.56 tokens per second 11.55.452.461 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 327519148887 11.55.452.581 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 11.55.462.743 I slot launch_slot_: id 0 | task 9071 | processing task, is_child = 0 11.56.117.934 I slot print_timing: id 1 | task 9064 | prompt eval time = 4388.52 ms / 701 tokens ( 6.26 ms per token, 159.73 tokens per second) 11.56.117.940 I slot print_timing: id 1 | task 9064 | eval time = 666.68 ms / 2 tokens ( 666.68 ms per token, 1.50 tokens per second) 11.56.117.941 I slot print_timing: id 1 | task 9064 | total time = 5055.20 ms / 703 tokens 11.56.117.942 I slot print_timing: id 1 | task 9064 | graphs reused = 7760 11.56.117.942 I slot print_timing: id 1 | task 9064 | graph reallocs = 0 / 0 (same size) / (changed size) 11.56.118.004 I slot release: id 1 | task 9064 | stop processing: n_tokens = 711, truncated = 0 11.56.119.131 I slot print_timing: id 2 | task 9065 | prompt eval time = 4389.54 ms / 723 tokens ( 6.07 ms per token, 164.71 tokens per second) 11.56.119.137 I slot print_timing: id 2 | task 9065 | eval time = 666.68 ms / 2 tokens ( 666.68 ms per token, 1.50 tokens per second) 11.56.119.138 I slot print_timing: id 2 | task 9065 | total time = 5056.22 ms / 725 tokens 11.56.119.138 I slot print_timing: id 2 | task 9065 | graphs reused = 7760 11.56.119.138 I slot print_timing: id 2 | task 9065 | graph reallocs = 0 / 0 (same size) / (changed size) 11.56.119.180 I slot release: id 2 | task 9065 | stop processing: n_tokens = 733, truncated = 0 11.56.925.540 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.880 11.56.925.635 I slot launch_slot_: id 1 | task 9074 | processing task, is_child = 0 11.56.925.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 11.56.941.514 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.854 11.56.941.604 I slot launch_slot_: id 2 | task 9075 | processing task, is_child = 0 11.57.605.688 I slot print_timing: id 3 | task 9068 | prompt eval time = 3225.75 ms / 706 tokens ( 4.57 ms per token, 218.86 tokens per second) 11.57.605.692 I slot print_timing: id 3 | task 9068 | eval time = 680.15 ms / 2 tokens ( 680.15 ms per token, 1.47 tokens per second) 11.57.605.692 I slot print_timing: id 3 | task 9068 | total time = 3905.90 ms / 708 tokens 11.57.605.693 I slot print_timing: id 3 | task 9068 | graphs reused = 7760 11.57.605.693 I slot print_timing: id 3 | task 9068 | graph reallocs = 0 / 0 (same size) / (changed size) 11.57.605.747 I slot release: id 3 | task 9068 | stop processing: n_tokens = 716, truncated = 0 11.57.683.190 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.874 11.57.683.289 I slot launch_slot_: id 3 | task 9078 | processing task, is_child = 0 11.57.920.755 I slot print_timing: id 0 | task 9071 | prompt eval time = 2218.19 ms / 699 tokens ( 3.17 ms per token, 315.12 tokens per second) 11.57.920.759 I slot print_timing: id 0 | task 9071 | eval time = 239.81 ms / 2 tokens ( 239.81 ms per token, 4.17 tokens per second) 11.57.920.760 I slot print_timing: id 0 | task 9071 | total time = 2457.99 ms / 701 tokens 11.57.920.760 I slot print_timing: id 0 | task 9071 | graphs reused = 7760 11.57.920.760 I slot print_timing: id 0 | task 9071 | graph reallocs = 0 / 0 (same size) / (changed size) 11.57.920.825 I slot release: id 0 | task 9071 | stop processing: n_tokens = 709, truncated = 0 11.57.921.978 I slot print_timing: id 1 | task 9074 | prompt eval time = 738.74 ms / 85 tokens ( 8.69 ms per token, 115.06 tokens per second) 11.57.921.981 I slot print_timing: id 1 | task 9074 | eval time = 239.90 ms / 2 tokens ( 239.90 ms per token, 4.17 tokens per second) 11.57.921.983 I slot print_timing: id 1 | task 9074 | total time = 978.64 ms / 87 tokens 11.57.921.984 I slot print_timing: id 1 | task 9074 | graphs reused = 7760 11.57.921.984 I slot print_timing: id 1 | task 9074 | graph reallocs = 0 / 0 (same size) / (changed size) 11.57.922.021 I slot release: id 1 | task 9074 | stop processing: n_tokens = 712, truncated = 0 11.57.923.156 I slot print_timing: id 2 | task 9075 | prompt eval time = 737.97 ms / 79 tokens ( 9.34 ms per token, 107.05 tokens per second) 11.57.923.158 I slot print_timing: id 2 | task 9075 | eval time = 239.97 ms / 2 tokens ( 239.97 ms per token, 4.17 tokens per second) 11.57.923.159 I slot print_timing: id 2 | task 9075 | total time = 977.94 ms / 81 tokens 11.57.923.159 I slot print_timing: id 2 | task 9075 | graphs reused = 7760 11.57.923.159 I slot print_timing: id 2 | task 9075 | graph reallocs = 0 / 0 (same size) / (changed size) 11.57.923.185 I slot release: id 2 | task 9075 | stop processing: n_tokens = 706, truncated = 0 11.57.960.506 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.883 11.57.960.568 I slot launch_slot_: id 0 | task 9081 | processing task, is_child = 0 11.57.960.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.766 MiB) 11.57.968.799 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.499 MiB) 11.57.978.109 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.891 11.57.978.181 I slot launch_slot_: id 2 | task 9082 | processing task, is_child = 0 11.57.978.243 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.879 11.57.978.281 I slot launch_slot_: id 1 | task 9083 | processing task, is_child = 0 11.58.667.735 I slot print_timing: id 3 | task 9078 | prompt eval time = 277.20 ms / 77 tokens ( 3.60 ms per token, 277.77 tokens per second) 11.58.667.738 I slot print_timing: id 3 | task 9078 | eval time = 707.23 ms / 2 tokens ( 707.23 ms per token, 1.41 tokens per second) 11.58.667.739 I slot print_timing: id 3 | task 9078 | total time = 984.43 ms / 79 tokens 11.58.667.739 I slot print_timing: id 3 | task 9078 | graphs reused = 7760 11.58.667.740 I slot print_timing: id 3 | task 9078 | graph reallocs = 0 / 0 (same size) / (changed size) 11.58.667.804 I slot release: id 3 | task 9078 | stop processing: n_tokens = 704, truncated = 0 11.58.749.133 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.889 11.58.749.201 I slot launch_slot_: id 3 | task 9086 | processing task, is_child = 0 11.58.988.287 I slot print_timing: id 0 | task 9081 | prompt eval time = 768.47 ms / 87 tokens ( 8.83 ms per token, 113.21 tokens per second) 11.58.988.290 I slot print_timing: id 0 | task 9081 | eval time = 241.51 ms / 2 tokens ( 241.51 ms per token, 4.14 tokens per second) 11.58.988.291 I slot print_timing: id 0 | task 9081 | total time = 1009.98 ms / 89 tokens 11.58.988.291 I slot print_timing: id 0 | task 9081 | graphs reused = 7760 11.58.988.292 I slot print_timing: id 0 | task 9081 | graph reallocs = 0 / 0 (same size) / (changed size) 11.58.988.347 I slot release: id 0 | task 9081 | stop processing: n_tokens = 714, truncated = 0 11.58.989.509 I slot print_timing: id 1 | task 9083 | prompt eval time = 767.98 ms / 121 tokens ( 6.35 ms per token, 157.56 tokens per second) 11.58.989.511 I slot print_timing: id 1 | task 9083 | eval time = 241.53 ms / 2 tokens ( 241.53 ms per token, 4.14 tokens per second) 11.58.989.511 I slot print_timing: id 1 | task 9083 | total time = 1009.50 ms / 123 tokens 11.58.989.511 I slot print_timing: id 1 | task 9083 | graphs reused = 7760 11.58.989.512 I slot print_timing: id 1 | task 9083 | graph reallocs = 0 / 0 (same size) / (changed size) 11.58.989.540 I slot release: id 1 | task 9083 | stop processing: n_tokens = 748, truncated = 0 11.58.990.701 I slot print_timing: id 2 | task 9082 | prompt eval time = 767.44 ms / 86 tokens ( 8.92 ms per token, 112.06 tokens per second) 11.58.990.704 I slot print_timing: id 2 | task 9082 | eval time = 241.57 ms / 2 tokens ( 241.57 ms per token, 4.14 tokens per second) 11.58.990.704 I slot print_timing: id 2 | task 9082 | total time = 1009.01 ms / 88 tokens 11.58.990.704 I slot print_timing: id 2 | task 9082 | graphs reused = 7760 11.58.990.705 I slot print_timing: id 2 | task 9082 | graph reallocs = 0 / 0 (same size) / (changed size) 11.58.990.738 I slot release: id 2 | task 9082 | stop processing: n_tokens = 716, truncated = 0 11.59.028.582 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 327523523602 11.59.028.670 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.112 MiB) 11.59.035.084 I slot launch_slot_: id 0 | task 9089 | processing task, is_child = 0 11.59.035.155 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.398 MiB) 11.59.055.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.000 MiB) 11.59.064.791 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 327523524795 11.59.064.944 I slot launch_slot_: id 1 | task 9090 | processing task, is_child = 0 11.59.065.004 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 327523525993 11.59.065.094 I slot launch_slot_: id 2 | task 9091 | processing task, is_child = 0 12.01.694.314 I slot print_timing: id 3 | task 9086 | prompt eval time = 279.37 ms / 80 tokens ( 3.49 ms per token, 286.36 tokens per second) 12.01.694.320 I slot print_timing: id 3 | task 9086 | eval time = 2665.73 ms / 2 tokens ( 2665.73 ms per token, 0.38 tokens per second) 12.01.694.321 I slot print_timing: id 3 | task 9086 | total time = 2945.10 ms / 82 tokens 12.01.694.321 I slot print_timing: id 3 | task 9086 | graphs reused = 7760 12.01.694.322 I slot print_timing: id 3 | task 9086 | graph reallocs = 0 / 0 (same size) / (changed size) 12.01.694.384 I slot release: id 3 | task 9086 | stop processing: n_tokens = 707, truncated = 0 12.03.816.863 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 327526229639 12.03.816.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.694 MiB) 12.03.906.979 I slot launch_slot_: id 3 | task 9094 | processing task, is_child = 0 12.03.906.994 I slot print_timing: id 0 | task 9089 | prompt processing, n_tokens = 761, progress = 0.87, t = 4.75 s / 160.15 tokens per second 12.03.908.979 I slot print_timing: id 1 | task 9090 | prompt processing, n_tokens = 761, progress = 0.85, t = 4.75 s / 160.16 tokens per second 12.03.910.709 I slot print_timing: id 2 | task 9091 | prompt processing, n_tokens = 909, progress = 0.83, t = 4.75 s / 191.31 tokens per second 12.05.218.817 I slot print_timing: id 0 | task 9089 | prompt processing, n_tokens = 875, progress = 1.00, t = 6.15 s / 142.19 tokens per second 12.05.981.423 I slot print_timing: id 1 | task 9090 | prompt processing, n_tokens = 892, progress = 1.00, t = 6.15 s / 144.96 tokens per second 12.05.985.141 I slot print_timing: id 2 | task 9091 | prompt processing, n_tokens = 1095, progress = 1.00, t = 6.15 s / 177.95 tokens per second 12.07.153.771 I slot print_timing: id 0 | task 9089 | prompt eval time = 7663.73 ms / 879 tokens ( 8.72 ms per token, 114.70 tokens per second) 12.07.153.777 I slot print_timing: id 0 | task 9089 | eval time = 424.93 ms / 2 tokens ( 424.93 ms per token, 2.35 tokens per second) 12.07.153.778 I slot print_timing: id 0 | task 9089 | total time = 8088.66 ms / 881 tokens 12.07.153.779 I slot print_timing: id 0 | task 9089 | graphs reused = 7760 12.07.153.779 I slot print_timing: id 0 | task 9089 | graph reallocs = 0 / 0 (same size) / (changed size) 12.07.153.836 I slot release: id 0 | task 9089 | stop processing: n_tokens = 889, truncated = 0 12.07.154.983 I slot print_timing: id 1 | task 9090 | prompt eval time = 7664.80 ms / 896 tokens ( 8.55 ms per token, 116.90 tokens per second) 12.07.154.985 I slot print_timing: id 1 | task 9090 | eval time = 424.90 ms / 2 tokens ( 424.90 ms per token, 2.35 tokens per second) 12.07.154.985 I slot print_timing: id 1 | task 9090 | total time = 8089.70 ms / 898 tokens 12.07.154.986 I slot print_timing: id 1 | task 9090 | graphs reused = 7760 12.07.154.986 I slot print_timing: id 1 | task 9090 | graph reallocs = 0 / 0 (same size) / (changed size) 12.07.155.024 I slot release: id 1 | task 9090 | stop processing: n_tokens = 906, truncated = 0 12.07.156.237 I slot print_timing: id 2 | task 9091 | prompt eval time = 7665.85 ms / 1099 tokens ( 6.98 ms per token, 143.36 tokens per second) 12.07.156.239 I slot print_timing: id 2 | task 9091 | eval time = 424.94 ms / 2 tokens ( 424.94 ms per token, 2.35 tokens per second) 12.07.156.239 I slot print_timing: id 2 | task 9091 | total time = 8090.79 ms / 1101 tokens 12.07.156.239 I slot print_timing: id 2 | task 9091 | graphs reused = 7760 12.07.156.240 I slot print_timing: id 2 | task 9091 | graph reallocs = 0 / 0 (same size) / (changed size) 12.07.156.271 I slot release: id 2 | task 9091 | stop processing: n_tokens = 1109, truncated = 0 12.07.156.277 I slot print_timing: id 3 | task 9094 | prompt processing, n_tokens = 1085, progress = 1.00, t = 3.24 s / 334.85 tokens per second 12.07.193.888 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.894 12.07.193.947 I slot launch_slot_: id 2 | task 9099 | processing task, is_child = 0 12.07.199.837 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.451 MiB) 12.07.205.661 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 327531689091 12.07.205.790 I slot launch_slot_: id 0 | task 9100 | processing task, is_child = 0 12.07.205.857 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 906, t_last = 327531690279 12.07.205.954 I slot launch_slot_: id 1 | task 9101 | processing task, is_child = 0 12.09.559.477 I slot print_timing: id 3 | task 9094 | prompt eval time = 3281.43 ms / 1089 tokens ( 3.01 ms per token, 331.87 tokens per second) 12.09.559.481 I slot print_timing: id 3 | task 9094 | eval time = 2365.59 ms / 2 tokens ( 2365.59 ms per token, 0.42 tokens per second) 12.09.559.481 I slot print_timing: id 3 | task 9094 | total time = 5647.02 ms / 1091 tokens 12.09.559.482 I slot print_timing: id 3 | task 9094 | graphs reused = 7760 12.09.559.482 I slot print_timing: id 3 | task 9094 | graph reallocs = 0 / 0 (same size) / (changed size) 12.09.559.533 I slot release: id 3 | task 9094 | stop processing: n_tokens = 1099, truncated = 0 12.10.936.123 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.901 12.10.936.273 I slot launch_slot_: id 3 | task 9104 | processing task, is_child = 0 12.10.936.290 I slot print_timing: id 0 | task 9100 | prompt processing, n_tokens = 909, progress = 0.83, t = 3.73 s / 243.78 tokens per second 12.10.939.946 I slot print_timing: id 1 | task 9101 | prompt processing, n_tokens = 909, progress = 0.84, t = 3.73 s / 243.79 tokens per second 12.11.941.898 I slot print_timing: id 2 | task 9099 | prompt eval time = 3729.74 ms / 96 tokens ( 38.85 ms per token, 25.74 tokens per second) 12.11.941.907 I slot print_timing: id 2 | task 9099 | eval time = 1005.78 ms / 2 tokens ( 1005.78 ms per token, 0.99 tokens per second) 12.11.941.908 I slot print_timing: id 2 | task 9099 | total time = 4735.52 ms / 98 tokens 12.11.941.909 I slot print_timing: id 2 | task 9099 | graphs reused = 7760 12.11.941.909 I slot print_timing: id 2 | task 9099 | graph reallocs = 0 / 0 (same size) / (changed size) 12.11.941.984 I slot release: id 2 | task 9099 | stop processing: n_tokens = 1088, truncated = 0 12.11.942.003 I slot print_timing: id 0 | task 9100 | prompt processing, n_tokens = 1088, progress = 1.00, t = 4.73 s / 229.79 tokens per second 12.11.949.367 I slot print_timing: id 1 | task 9101 | prompt processing, n_tokens = 1083, progress = 1.00, t = 4.73 s / 228.74 tokens per second 12.12.035.585 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.911 12.12.035.678 I slot launch_slot_: id 2 | task 9107 | processing task, is_child = 0 12.12.302.360 I slot print_timing: id 0 | task 9100 | prompt eval time = 4827.32 ms / 1092 tokens ( 4.42 ms per token, 226.21 tokens per second) 12.12.302.363 I slot print_timing: id 0 | task 9100 | eval time = 269.07 ms / 2 tokens ( 269.07 ms per token, 3.72 tokens per second) 12.12.302.363 I slot print_timing: id 0 | task 9100 | total time = 5096.40 ms / 1094 tokens 12.12.302.364 I slot print_timing: id 0 | task 9100 | graphs reused = 7760 12.12.302.364 I slot print_timing: id 0 | task 9100 | graph reallocs = 0 / 0 (same size) / (changed size) 12.12.302.413 I slot release: id 0 | task 9100 | stop processing: n_tokens = 1102, truncated = 0 12.12.303.505 I slot print_timing: id 1 | task 9101 | prompt eval time = 4828.19 ms / 1087 tokens ( 4.44 ms per token, 225.14 tokens per second) 12.12.303.514 I slot print_timing: id 1 | task 9101 | eval time = 269.13 ms / 2 tokens ( 269.13 ms per token, 3.72 tokens per second) 12.12.303.515 I slot print_timing: id 1 | task 9101 | total time = 5097.32 ms / 1089 tokens 12.12.303.515 I slot print_timing: id 1 | task 9101 | graphs reused = 7760 12.12.303.516 I slot print_timing: id 1 | task 9101 | graph reallocs = 0 / 0 (same size) / (changed size) 12.12.303.568 I slot release: id 1 | task 9101 | stop processing: n_tokens = 1097, truncated = 0 12.12.304.709 I slot print_timing: id 3 | task 9104 | prompt eval time = 1091.07 ms / 106 tokens ( 10.29 ms per token, 97.15 tokens per second) 12.12.304.714 I slot print_timing: id 3 | task 9104 | eval time = 269.13 ms / 2 tokens ( 269.13 ms per token, 3.72 tokens per second) 12.12.304.714 I slot print_timing: id 3 | task 9104 | total time = 1360.19 ms / 108 tokens 12.12.304.715 I slot print_timing: id 3 | task 9104 | graphs reused = 7760 12.12.304.715 I slot print_timing: id 3 | task 9104 | graph reallocs = 0 / 0 (same size) / (changed size) 12.12.304.749 I slot release: id 3 | task 9104 | stop processing: n_tokens = 1097, truncated = 0 12.12.343.099 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.899 12.12.343.142 I slot launch_slot_: id 0 | task 9110 | processing task, is_child = 0 12.12.343.233 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.356 MiB) 12.12.353.222 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 392.652 MiB) 12.12.368.056 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.903 12.12.368.130 I slot launch_slot_: id 1 | task 9111 | processing task, is_child = 0 12.12.368.209 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.903 12.12.368.243 I slot launch_slot_: id 3 | task 9112 | processing task, is_child = 0 12.13.126.400 I slot print_timing: id 2 | task 9107 | prompt eval time = 307.41 ms / 98 tokens ( 3.14 ms per token, 318.79 tokens per second) 12.13.126.405 I slot print_timing: id 2 | task 9107 | eval time = 783.30 ms / 2 tokens ( 783.30 ms per token, 1.28 tokens per second) 12.13.126.406 I slot print_timing: id 2 | task 9107 | total time = 1090.71 ms / 100 tokens 12.13.126.406 I slot print_timing: id 2 | task 9107 | graphs reused = 7760 12.13.126.407 I slot print_timing: id 2 | task 9107 | graph reallocs = 0 / 0 (same size) / (changed size) 12.13.126.454 I slot release: id 2 | task 9107 | stop processing: n_tokens = 1090, truncated = 0 12.13.217.749 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.909 12.13.217.842 I slot launch_slot_: id 2 | task 9115 | processing task, is_child = 0 12.13.484.589 I slot print_timing: id 0 | task 9110 | prompt eval time = 847.26 ms / 107 tokens ( 7.92 ms per token, 126.29 tokens per second) 12.13.484.592 I slot print_timing: id 0 | task 9110 | eval time = 269.06 ms / 2 tokens ( 269.06 ms per token, 3.72 tokens per second) 12.13.484.592 I slot print_timing: id 0 | task 9110 | total time = 1116.33 ms / 109 tokens 12.13.484.593 I slot print_timing: id 0 | task 9110 | graphs reused = 7760 12.13.484.593 I slot print_timing: id 0 | task 9110 | graph reallocs = 0 / 0 (same size) / (changed size) 12.13.484.631 I slot release: id 0 | task 9110 | stop processing: n_tokens = 1099, truncated = 0 12.13.485.738 I slot print_timing: id 1 | task 9111 | prompt eval time = 846.70 ms / 108 tokens ( 7.84 ms per token, 127.55 tokens per second) 12.13.485.742 I slot print_timing: id 1 | task 9111 | eval time = 269.08 ms / 2 tokens ( 269.08 ms per token, 3.72 tokens per second) 12.13.485.742 I slot print_timing: id 1 | task 9111 | total time = 1115.78 ms / 110 tokens 12.13.485.742 I slot print_timing: id 1 | task 9111 | graphs reused = 7760 12.13.485.743 I slot print_timing: id 1 | task 9111 | graph reallocs = 0 / 0 (same size) / (changed size) 12.13.485.768 I slot release: id 1 | task 9111 | stop processing: n_tokens = 1100, truncated = 0 12.13.486.864 I slot print_timing: id 3 | task 9112 | prompt eval time = 846.08 ms / 114 tokens ( 7.42 ms per token, 134.74 tokens per second) 12.13.486.866 I slot print_timing: id 3 | task 9112 | eval time = 269.12 ms / 2 tokens ( 269.12 ms per token, 3.72 tokens per second) 12.13.486.867 I slot print_timing: id 3 | task 9112 | total time = 1115.20 ms / 116 tokens 12.13.486.867 I slot print_timing: id 3 | task 9112 | graphs reused = 7760 12.13.486.867 I slot print_timing: id 3 | task 9112 | graph reallocs = 0 / 0 (same size) / (changed size) 12.13.486.899 I slot release: id 3 | task 9112 | stop processing: n_tokens = 1106, truncated = 0 12.13.524.709 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.902 12.13.524.776 I slot launch_slot_: id 0 | task 9119 | processing task, is_child = 0 12.13.524.883 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 288.402 MiB) 12.13.535.750 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.567 MiB) 12.13.553.565 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.901 12.13.553.649 I slot launch_slot_: id 1 | task 9118 | processing task, is_child = 0 12.13.553.731 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.896 12.13.553.766 I slot launch_slot_: id 3 | task 9120 | processing task, is_child = 0 12.14.319.048 I slot print_timing: id 2 | task 9115 | prompt eval time = 306.86 ms / 100 tokens ( 3.07 ms per token, 325.88 tokens per second) 12.14.319.051 I slot print_timing: id 2 | task 9115 | eval time = 794.34 ms / 2 tokens ( 794.34 ms per token, 1.26 tokens per second) 12.14.319.052 I slot print_timing: id 2 | task 9115 | total time = 1101.20 ms / 102 tokens 12.14.319.052 I slot print_timing: id 2 | task 9115 | graphs reused = 7760 12.14.319.053 I slot print_timing: id 2 | task 9115 | graph reallocs = 0 / 0 (same size) / (changed size) 12.14.319.117 I slot release: id 2 | task 9115 | stop processing: n_tokens = 1092, truncated = 0 12.14.402.084 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.908 12.14.402.178 I slot launch_slot_: id 2 | task 9123 | processing task, is_child = 0 12.14.718.970 I slot print_timing: id 0 | task 9119 | prompt eval time = 846.10 ms / 105 tokens ( 8.06 ms per token, 124.10 tokens per second) 12.14.718.971 I slot print_timing: id 0 | task 9119 | eval time = 319.09 ms / 2 tokens ( 319.09 ms per token, 3.13 tokens per second) 12.14.718.972 I slot print_timing: id 0 | task 9119 | total time = 1165.19 ms / 107 tokens 12.14.718.972 I slot print_timing: id 0 | task 9119 | graphs reused = 7760 12.14.718.973 I slot print_timing: id 0 | task 9119 | graph reallocs = 0 / 0 (same size) / (changed size) 12.14.719.014 I slot release: id 0 | task 9119 | stop processing: n_tokens = 1097, truncated = 0 12.14.720.074 I slot print_timing: id 1 | task 9118 | prompt eval time = 845.54 ms / 102 tokens ( 8.29 ms per token, 120.63 tokens per second) 12.14.720.076 I slot print_timing: id 1 | task 9118 | eval time = 319.06 ms / 2 tokens ( 319.06 ms per token, 3.13 tokens per second) 12.14.720.077 I slot print_timing: id 1 | task 9118 | total time = 1164.60 ms / 104 tokens 12.14.720.077 I slot print_timing: id 1 | task 9118 | graphs reused = 7760 12.14.720.077 I slot print_timing: id 1 | task 9118 | graph reallocs = 0 / 0 (same size) / (changed size) 12.14.720.111 I slot release: id 1 | task 9118 | stop processing: n_tokens = 1094, truncated = 0 12.14.721.211 I slot print_timing: id 3 | task 9120 | prompt eval time = 844.89 ms / 104 tokens ( 8.12 ms per token, 123.09 tokens per second) 12.14.721.213 I slot print_timing: id 3 | task 9120 | eval time = 319.13 ms / 2 tokens ( 319.13 ms per token, 3.13 tokens per second) 12.14.721.213 I slot print_timing: id 3 | task 9120 | total time = 1164.03 ms / 106 tokens 12.14.721.213 I slot print_timing: id 3 | task 9120 | graphs reused = 7760 12.14.721.214 I slot print_timing: id 3 | task 9120 | graph reallocs = 0 / 0 (same size) / (changed size) 12.14.721.241 I slot release: id 3 | task 9120 | stop processing: n_tokens = 1096, truncated = 0 12.14.759.174 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1097, t_last = 327539254269 12.14.759.272 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.832 MiB) 12.14.772.393 I slot launch_slot_: id 0 | task 9126 | processing task, is_child = 0 12.14.772.480 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.275 MiB) 12.14.786.630 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.104 MiB) 12.14.786.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.040 MiB) 12.14.799.399 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1094, t_last = 327539255366 12.14.799.544 I slot launch_slot_: id 1 | task 9127 | processing task, is_child = 0 12.14.799.620 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1096, t_last = 327539256496 12.14.799.724 I slot launch_slot_: id 3 | task 9128 | processing task, is_child = 0 12.17.766.699 I slot print_timing: id 2 | task 9123 | prompt eval time = 356.99 ms / 103 tokens ( 3.47 ms per token, 288.53 tokens per second) 12.17.766.702 I slot print_timing: id 2 | task 9123 | eval time = 3007.52 ms / 2 tokens ( 3007.52 ms per token, 0.33 tokens per second) 12.17.766.703 I slot print_timing: id 2 | task 9123 | total time = 3364.51 ms / 105 tokens 12.17.766.703 I slot print_timing: id 2 | task 9123 | graphs reused = 7760 12.17.766.704 I slot print_timing: id 2 | task 9123 | graph reallocs = 0 / 0 (same size) / (changed size) 12.17.766.755 I slot release: id 2 | task 9123 | stop processing: n_tokens = 1095, truncated = 0 12.19.258.824 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1095, t_last = 327542302010 12.19.258.924 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.102 MiB) 12.19.816.032 I slot launch_slot_: id 2 | task 9131 | processing task, is_child = 0 12.19.816.058 I slot print_timing: id 0 | task 9126 | prompt processing, n_tokens = 861, progress = 0.86, t = 4.46 s / 193.09 tokens per second 12.19.817.742 I slot print_timing: id 1 | task 9127 | prompt processing, n_tokens = 861, progress = 0.84, t = 4.46 s / 193.10 tokens per second 12.19.819.643 I slot print_timing: id 3 | task 9128 | prompt processing, n_tokens = 861, progress = 0.79, t = 4.46 s / 193.11 tokens per second 12.21.326.399 I slot print_timing: id 0 | task 9126 | prompt processing, n_tokens = 996, progress = 1.00, t = 6.53 s / 152.60 tokens per second 12.21.924.707 I slot print_timing: id 1 | task 9127 | prompt processing, n_tokens = 1017, progress = 1.00, t = 6.53 s / 155.83 tokens per second 12.21.930.667 I slot print_timing: id 3 | task 9128 | prompt processing, n_tokens = 1087, progress = 1.00, t = 6.53 s / 166.56 tokens per second 12.23.069.752 I slot print_timing: id 0 | task 9126 | prompt eval time = 7818.99 ms / 1000 tokens ( 7.82 ms per token, 127.89 tokens per second) 12.23.069.756 I slot print_timing: id 0 | task 9126 | eval time = 451.03 ms / 2 tokens ( 451.03 ms per token, 2.22 tokens per second) 12.23.069.757 I slot print_timing: id 0 | task 9126 | total time = 8270.02 ms / 1002 tokens 12.23.069.757 I slot print_timing: id 0 | task 9126 | graphs reused = 7760 12.23.069.758 I slot print_timing: id 0 | task 9126 | graph reallocs = 0 / 0 (same size) / (changed size) 12.23.069.810 I slot release: id 0 | task 9126 | stop processing: n_tokens = 1010, truncated = 0 12.23.070.894 I slot print_timing: id 1 | task 9127 | prompt eval time = 7819.94 ms / 1021 tokens ( 7.66 ms per token, 130.56 tokens per second) 12.23.070.897 I slot print_timing: id 1 | task 9127 | eval time = 451.00 ms / 2 tokens ( 451.00 ms per token, 2.22 tokens per second) 12.23.070.898 I slot print_timing: id 1 | task 9127 | total time = 8270.94 ms / 1023 tokens 12.23.070.898 I slot print_timing: id 1 | task 9127 | graphs reused = 7760 12.23.070.898 I slot print_timing: id 1 | task 9127 | graph reallocs = 0 / 0 (same size) / (changed size) 12.23.070.954 I slot release: id 1 | task 9127 | stop processing: n_tokens = 1031, truncated = 0 12.23.072.085 I slot print_timing: id 3 | task 9128 | prompt eval time = 7820.97 ms / 1091 tokens ( 7.17 ms per token, 139.50 tokens per second) 12.23.072.088 I slot print_timing: id 3 | task 9128 | eval time = 450.97 ms / 2 tokens ( 450.97 ms per token, 2.22 tokens per second) 12.23.072.088 I slot print_timing: id 3 | task 9128 | total time = 8271.94 ms / 1093 tokens 12.23.072.088 I slot print_timing: id 3 | task 9128 | graphs reused = 7760 12.23.072.089 I slot print_timing: id 3 | task 9128 | graph reallocs = 0 / 0 (same size) / (changed size) 12.23.072.129 I slot release: id 3 | task 9128 | stop processing: n_tokens = 1101, truncated = 0 12.23.072.141 I slot print_timing: id 2 | task 9131 | prompt processing, n_tokens = 1051, progress = 1.00, t = 3.25 s / 323.46 tokens per second 12.23.110.157 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1010, t_last = 327547605065 12.23.110.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 222.855 MiB) 12.23.131.658 I slot launch_slot_: id 0 | task 9136 | processing task, is_child = 0 12.23.131.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.063 MiB) 12.23.138.039 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 222.433 MiB) 12.23.147.223 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.870 12.23.147.291 I slot launch_slot_: id 1 | task 9137 | processing task, is_child = 0 12.23.147.372 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.815 12.23.147.407 I slot launch_slot_: id 3 | task 9138 | processing task, is_child = 0 12.24.224.102 I slot print_timing: id 2 | task 9131 | prompt eval time = 3290.73 ms / 1055 tokens ( 3.12 ms per token, 320.60 tokens per second) 12.24.224.108 I slot print_timing: id 2 | task 9131 | eval time = 1113.94 ms / 2 tokens ( 1113.94 ms per token, 0.90 tokens per second) 12.24.224.109 I slot print_timing: id 2 | task 9131 | total time = 4404.68 ms / 1057 tokens 12.24.224.109 I slot print_timing: id 2 | task 9131 | graphs reused = 7760 12.24.224.109 I slot print_timing: id 2 | task 9131 | graph reallocs = 0 / 0 (same size) / (changed size) 12.24.224.171 I slot release: id 2 | task 9131 | stop processing: n_tokens = 1065, truncated = 0 12.25.016.645 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1065, t_last = 327548759427 12.25.016.774 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.839 MiB) 12.25.030.550 I slot launch_slot_: id 2 | task 9141 | processing task, is_child = 0 12.25.921.444 I slot print_timing: id 1 | task 9137 | prompt eval time = 1867.79 ms / 122 tokens ( 15.31 ms per token, 65.32 tokens per second) 12.25.921.450 I slot print_timing: id 1 | task 9137 | eval time = 906.02 ms / 2 tokens ( 906.02 ms per token, 1.10 tokens per second) 12.25.921.451 I slot print_timing: id 1 | task 9137 | total time = 2773.80 ms / 124 tokens 12.25.921.452 I slot print_timing: id 1 | task 9137 | graphs reused = 7760 12.25.921.452 I slot print_timing: id 1 | task 9137 | graph reallocs = 0 / 0 (same size) / (changed size) 12.25.921.531 I slot release: id 1 | task 9137 | stop processing: n_tokens = 1020, truncated = 0 12.25.922.658 I slot print_timing: id 3 | task 9138 | prompt eval time = 1867.30 ms / 143 tokens ( 13.06 ms per token, 76.58 tokens per second) 12.25.922.665 I slot print_timing: id 3 | task 9138 | eval time = 906.02 ms / 2 tokens ( 906.02 ms per token, 1.10 tokens per second) 12.25.922.665 I slot print_timing: id 3 | task 9138 | total time = 2773.32 ms / 145 tokens 12.25.922.666 I slot print_timing: id 3 | task 9138 | graphs reused = 7760 12.25.922.666 I slot print_timing: id 3 | task 9138 | graph reallocs = 0 / 0 (same size) / (changed size) 12.25.922.712 I slot release: id 3 | task 9138 | stop processing: n_tokens = 1041, truncated = 0 12.26.617.164 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1020, t_last = 327550456786 12.26.617.302 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 227.356 MiB) 12.26.617.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 228.481 MiB) 12.26.631.596 I slot launch_slot_: id 1 | task 9144 | processing task, is_child = 0 12.26.631.679 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.498 MiB) 12.26.643.344 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 327550457967 12.26.643.478 I slot launch_slot_: id 3 | task 9145 | processing task, is_child = 0 12.27.832.198 I slot print_timing: id 0 | task 9136 | prompt eval time = 3469.74 ms / 745 tokens ( 4.66 ms per token, 214.71 tokens per second) 12.27.832.204 I slot print_timing: id 0 | task 9136 | eval time = 1215.04 ms / 2 tokens ( 1215.04 ms per token, 0.82 tokens per second) 12.27.832.207 I slot print_timing: id 0 | task 9136 | total time = 4684.77 ms / 747 tokens 12.27.832.207 I slot print_timing: id 0 | task 9136 | graphs reused = 7760 12.27.832.208 I slot print_timing: id 0 | task 9136 | graph reallocs = 0 / 0 (same size) / (changed size) 12.27.832.282 I slot release: id 0 | task 9136 | stop processing: n_tokens = 755, truncated = 0 12.29.434.186 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.858 12.29.434.348 I slot launch_slot_: id 0 | task 9148 | processing task, is_child = 0 12.30.196.795 I slot print_timing: id 2 | task 9141 | prompt eval time = 4401.93 ms / 787 tokens ( 5.59 ms per token, 178.79 tokens per second) 12.30.196.798 I slot print_timing: id 2 | task 9141 | eval time = 762.62 ms / 2 tokens ( 762.62 ms per token, 1.31 tokens per second) 12.30.196.799 I slot print_timing: id 2 | task 9141 | total time = 5164.55 ms / 789 tokens 12.30.196.799 I slot print_timing: id 2 | task 9141 | graphs reused = 7760 12.30.196.800 I slot print_timing: id 2 | task 9141 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.196.843 I slot release: id 2 | task 9141 | stop processing: n_tokens = 797, truncated = 0 12.30.200.857 I slot print_timing: id 1 | task 9144 | prompt processing, n_tokens = 726, progress = 0.99, t = 3.55 s / 204.38 tokens per second 12.30.202.813 I slot print_timing: id 3 | task 9145 | prompt processing, n_tokens = 713, progress = 0.99, t = 3.55 s / 200.82 tokens per second 12.30.279.159 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.813 12.30.279.266 I slot launch_slot_: id 2 | task 9151 | processing task, is_child = 0 12.30.541.014 I slot print_timing: id 0 | task 9148 | prompt eval time = 842.57 ms / 97 tokens ( 8.69 ms per token, 115.12 tokens per second) 12.30.541.021 I slot print_timing: id 0 | task 9148 | eval time = 264.07 ms / 2 tokens ( 264.07 ms per token, 3.79 tokens per second) 12.30.541.022 I slot print_timing: id 0 | task 9148 | total time = 1106.64 ms / 99 tokens 12.30.541.023 I slot print_timing: id 0 | task 9148 | graphs reused = 7760 12.30.541.023 I slot print_timing: id 0 | task 9148 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.541.081 I slot release: id 0 | task 9148 | stop processing: n_tokens = 746, truncated = 0 12.30.542.189 I slot print_timing: id 1 | task 9144 | prompt eval time = 3634.57 ms / 730 tokens ( 4.98 ms per token, 200.85 tokens per second) 12.30.542.191 I slot print_timing: id 1 | task 9144 | eval time = 264.13 ms / 2 tokens ( 264.13 ms per token, 3.79 tokens per second) 12.30.542.192 I slot print_timing: id 1 | task 9144 | total time = 3898.70 ms / 732 tokens 12.30.542.192 I slot print_timing: id 1 | task 9144 | graphs reused = 7760 12.30.542.193 I slot print_timing: id 1 | task 9144 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.542.218 I slot release: id 1 | task 9144 | stop processing: n_tokens = 740, truncated = 0 12.30.543.309 I slot print_timing: id 3 | task 9145 | prompt eval time = 3633.81 ms / 717 tokens ( 5.07 ms per token, 197.31 tokens per second) 12.30.543.311 I slot print_timing: id 3 | task 9145 | eval time = 264.15 ms / 2 tokens ( 264.15 ms per token, 3.79 tokens per second) 12.30.543.312 I slot print_timing: id 3 | task 9145 | total time = 3897.96 ms / 719 tokens 12.30.543.312 I slot print_timing: id 3 | task 9145 | graphs reused = 7760 12.30.543.313 I slot print_timing: id 3 | task 9145 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.543.333 I slot release: id 3 | task 9145 | stop processing: n_tokens = 727, truncated = 0 12.30.580.622 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.861 (> 0.100 thold), f_keep = 0.869 12.30.580.678 I slot launch_slot_: id 0 | task 9154 | processing task, is_child = 0 12.30.580.755 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 237.342 MiB) 12.30.586.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.050 MiB) 12.30.594.204 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.876 12.30.594.263 I slot launch_slot_: id 1 | task 9155 | processing task, is_child = 0 12.30.594.324 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.891 12.30.594.357 I slot launch_slot_: id 3 | task 9156 | processing task, is_child = 0 12.31.234.901 I slot print_timing: id 2 | task 9151 | prompt eval time = 301.35 ms / 89 tokens ( 3.39 ms per token, 295.34 tokens per second) 12.31.234.904 I slot print_timing: id 2 | task 9151 | eval time = 654.28 ms / 2 tokens ( 654.28 ms per token, 1.53 tokens per second) 12.31.234.904 I slot print_timing: id 2 | task 9151 | total time = 955.63 ms / 91 tokens 12.31.234.905 I slot print_timing: id 2 | task 9151 | graphs reused = 7760 12.31.234.905 I slot print_timing: id 2 | task 9151 | graph reallocs = 0 / 0 (same size) / (changed size) 12.31.234.944 I slot release: id 2 | task 9151 | stop processing: n_tokens = 738, truncated = 0 12.31.317.353 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 327555770199 12.31.317.434 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 206.821 MiB) 12.31.326.936 I slot launch_slot_: id 2 | task 9159 | processing task, is_child = 0 12.32.249.545 I slot print_timing: id 0 | task 9154 | prompt eval time = 720.79 ms / 105 tokens ( 6.86 ms per token, 145.67 tokens per second) 12.32.249.548 I slot print_timing: id 0 | task 9154 | eval time = 934.38 ms / 2 tokens ( 934.38 ms per token, 1.07 tokens per second) 12.32.249.548 I slot print_timing: id 0 | task 9154 | total time = 1655.17 ms / 107 tokens 12.32.249.549 I slot print_timing: id 0 | task 9154 | graphs reused = 7760 12.32.249.549 I slot print_timing: id 0 | task 9154 | graph reallocs = 0 / 0 (same size) / (changed size) 12.32.249.622 I slot release: id 0 | task 9154 | stop processing: n_tokens = 754, truncated = 0 12.32.250.763 I slot print_timing: id 1 | task 9155 | prompt eval time = 720.21 ms / 84 tokens ( 8.57 ms per token, 116.63 tokens per second) 12.32.250.766 I slot print_timing: id 1 | task 9155 | eval time = 934.49 ms / 2 tokens ( 934.49 ms per token, 1.07 tokens per second) 12.32.250.766 I slot print_timing: id 1 | task 9155 | total time = 1654.69 ms / 86 tokens 12.32.250.767 I slot print_timing: id 1 | task 9155 | graphs reused = 7760 12.32.250.767 I slot print_timing: id 1 | task 9155 | graph reallocs = 0 / 0 (same size) / (changed size) 12.32.250.804 I slot release: id 1 | task 9155 | stop processing: n_tokens = 733, truncated = 0 12.32.251.902 I slot print_timing: id 3 | task 9156 | prompt eval time = 719.60 ms / 100 tokens ( 7.20 ms per token, 138.97 tokens per second) 12.32.251.911 I slot print_timing: id 3 | task 9156 | eval time = 934.55 ms / 2 tokens ( 934.55 ms per token, 1.07 tokens per second) 12.32.251.911 I slot print_timing: id 3 | task 9156 | total time = 1654.15 ms / 102 tokens 12.32.251.911 I slot print_timing: id 3 | task 9156 | graphs reused = 7760 12.32.251.912 I slot print_timing: id 3 | task 9156 | graph reallocs = 0 / 0 (same size) / (changed size) 12.32.251.940 I slot release: id 3 | task 9156 | stop processing: n_tokens = 749, truncated = 0 12.32.925.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 327556784877 12.32.926.035 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.747 MiB) 12.33.309.917 I slot launch_slot_: id 0 | task 9163 | processing task, is_child = 0 12.33.309.994 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 226.512 MiB) 12.33.317.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.385 MiB) 12.33.317.417 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.416 MiB) 12.33.323.725 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 733, t_last = 327556786059 12.33.323.849 I slot launch_slot_: id 1 | task 9164 | processing task, is_child = 0 12.33.323.910 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 749, t_last = 327556787195 12.33.324.005 I slot launch_slot_: id 3 | task 9165 | processing task, is_child = 0 12.38.094.738 I slot print_timing: id 2 | task 9159 | prompt eval time = 4695.29 ms / 985 tokens ( 4.77 ms per token, 209.78 tokens per second) 12.38.094.744 I slot print_timing: id 2 | task 9159 | eval time = 2072.49 ms / 2 tokens ( 2072.49 ms per token, 0.48 tokens per second) 12.38.094.745 I slot print_timing: id 2 | task 9159 | total time = 6767.78 ms / 987 tokens 12.38.094.745 I slot print_timing: id 2 | task 9159 | graphs reused = 7760 12.38.094.746 I slot print_timing: id 2 | task 9159 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.094.833 I slot release: id 2 | task 9159 | stop processing: n_tokens = 995, truncated = 0 12.38.094.864 I slot print_timing: id 0 | task 9163 | prompt processing, n_tokens = 812, progress = 0.86, t = 4.77 s / 170.24 tokens per second 12.38.098.862 I slot print_timing: id 1 | task 9164 | prompt processing, n_tokens = 812, progress = 0.84, t = 4.77 s / 170.25 tokens per second 12.38.101.431 I slot print_timing: id 3 | task 9165 | prompt processing, n_tokens = 812, progress = 0.78, t = 4.77 s / 170.32 tokens per second 12.38.747.591 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 327562630089 12.38.747.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 212.588 MiB) 12.39.239.969 I slot launch_slot_: id 2 | task 9169 | processing task, is_child = 0 12.39.239.978 I slot print_timing: id 0 | task 9163 | prompt processing, n_tokens = 946, progress = 1.00, t = 5.42 s / 174.42 tokens per second 12.39.241.798 I slot print_timing: id 1 | task 9164 | prompt processing, n_tokens = 963, progress = 1.00, t = 5.42 s / 177.56 tokens per second 12.39.243.791 I slot print_timing: id 3 | task 9165 | prompt processing, n_tokens = 1039, progress = 1.00, t = 5.42 s / 191.65 tokens per second 12.41.246.160 I slot print_timing: id 0 | task 9163 | prompt eval time = 7121.93 ms / 950 tokens ( 7.50 ms per token, 133.39 tokens per second) 12.41.246.164 I slot print_timing: id 0 | task 9163 | eval time = 800.21 ms / 2 tokens ( 800.21 ms per token, 1.25 tokens per second) 12.41.246.166 I slot print_timing: id 0 | task 9163 | total time = 7922.14 ms / 952 tokens 12.41.246.166 I slot print_timing: id 0 | task 9163 | graphs reused = 7760 12.41.246.167 I slot print_timing: id 0 | task 9163 | graph reallocs = 0 / 0 (same size) / (changed size) 12.41.246.213 I slot release: id 0 | task 9163 | stop processing: n_tokens = 960, truncated = 0 12.41.247.314 I slot print_timing: id 1 | task 9164 | prompt eval time = 7122.97 ms / 967 tokens ( 7.37 ms per token, 135.76 tokens per second) 12.41.247.316 I slot print_timing: id 1 | task 9164 | eval time = 800.15 ms / 2 tokens ( 800.15 ms per token, 1.25 tokens per second) 12.41.247.317 I slot print_timing: id 1 | task 9164 | total time = 7923.12 ms / 969 tokens 12.41.247.317 I slot print_timing: id 1 | task 9164 | graphs reused = 7760 12.41.247.317 I slot print_timing: id 1 | task 9164 | graph reallocs = 0 / 0 (same size) / (changed size) 12.41.247.353 I slot release: id 1 | task 9164 | stop processing: n_tokens = 977, truncated = 0 12.41.248.442 I slot print_timing: id 3 | task 9165 | prompt eval time = 7122.23 ms / 1043 tokens ( 6.83 ms per token, 146.44 tokens per second) 12.41.248.444 I slot print_timing: id 3 | task 9165 | eval time = 800.09 ms / 2 tokens ( 800.09 ms per token, 1.25 tokens per second) 12.41.248.444 I slot print_timing: id 3 | task 9165 | total time = 7922.32 ms / 1045 tokens 12.41.248.444 I slot print_timing: id 3 | task 9165 | graphs reused = 7760 12.41.248.445 I slot print_timing: id 3 | task 9165 | graph reallocs = 0 / 0 (same size) / (changed size) 12.41.248.473 I slot release: id 3 | task 9165 | stop processing: n_tokens = 1053, truncated = 0 12.41.607.838 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 960, t_last = 327565781468 12.41.607.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.535 MiB) 12.41.614.747 I slot launch_slot_: id 0 | task 9174 | processing task, is_child = 0 12.41.614.832 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.645 MiB) 12.41.621.248 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.394 MiB) 12.41.627.489 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 327565782608 12.41.627.626 I slot launch_slot_: id 1 | task 9175 | processing task, is_child = 0 12.41.627.700 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 327565783728 12.41.627.804 I slot launch_slot_: id 3 | task 9176 | processing task, is_child = 0 12.45.503.135 I slot print_timing: id 2 | task 9169 | prompt eval time = 2364.26 ms / 1127 tokens ( 2.10 ms per token, 476.68 tokens per second) 12.45.503.152 I slot print_timing: id 2 | task 9169 | eval time = 3895.29 ms / 2 tokens ( 3895.29 ms per token, 0.26 tokens per second) 12.45.503.152 I slot print_timing: id 2 | task 9169 | total time = 6259.55 ms / 1129 tokens 12.45.503.153 I slot print_timing: id 2 | task 9169 | graphs reused = 7760 12.45.503.153 I slot print_timing: id 2 | task 9169 | graph reallocs = 0 / 0 (same size) / (changed size) 12.45.503.235 I slot release: id 2 | task 9169 | stop processing: n_tokens = 1137, truncated = 0 12.45.503.271 I slot print_timing: id 0 | task 9174 | prompt processing, n_tokens = 643, progress = 0.56, t = 3.87 s / 165.97 tokens per second 12.45.507.284 I slot print_timing: id 1 | task 9175 | prompt processing, n_tokens = 1404, progress = 0.66, t = 3.87 s / 362.41 tokens per second 12.48.506.046 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1137, t_last = 327570038490 12.48.506.141 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 264.801 MiB) 12.49.415.823 I slot launch_slot_: id 2 | task 9179 | processing task, is_child = 0 12.49.415.839 I slot print_timing: id 0 | task 9174 | prompt processing, n_tokens = 975, progress = 0.84, t = 6.88 s / 141.75 tokens per second 12.49.417.769 I slot print_timing: id 1 | task 9175 | prompt processing, n_tokens = 1616, progress = 0.76, t = 6.88 s / 234.95 tokens per second 12.52.638.495 I slot print_timing: id 0 | task 9174 | prompt processing, n_tokens = 1155, progress = 1.00, t = 11.01 s / 104.90 tokens per second 12.53.378.629 I slot print_timing: id 1 | task 9175 | prompt processing, n_tokens = 1795, progress = 0.84, t = 11.01 s / 163.03 tokens per second 12.53.380.609 I slot print_timing: id 2 | task 9179 | prompt processing, n_tokens = 1580, progress = 0.75, t = 3.22 s / 490.86 tokens per second 12.53.382.290 I slot print_timing: id 3 | task 9176 | prompt processing, n_tokens = 1613, progress = 0.76, t = 7.13 s / 226.19 tokens per second 12.55.021.690 I slot print_timing: id 1 | task 9175 | prompt processing, n_tokens = 2128, progress = 1.00, t = 13.39 s / 158.90 tokens per second 12.55.025.901 I slot print_timing: id 2 | task 9179 | prompt processing, n_tokens = 1795, progress = 0.86, t = 5.60 s / 320.49 tokens per second 12.55.028.512 I slot print_timing: id 3 | task 9176 | prompt processing, n_tokens = 1795, progress = 0.84, t = 9.51 s / 188.69 tokens per second 12.56.467.980 I slot print_timing: id 0 | task 9174 | prompt eval time = 13393.85 ms / 1159 tokens ( 11.56 ms per token, 86.53 tokens per second) 12.56.467.983 I slot print_timing: id 0 | task 9174 | eval time = 1446.31 ms / 2 tokens ( 1446.31 ms per token, 0.69 tokens per second) 12.56.467.985 I slot print_timing: id 0 | task 9174 | total time = 14840.17 ms / 1161 tokens 12.56.467.985 I slot print_timing: id 0 | task 9174 | graphs reused = 7760 12.56.467.986 I slot print_timing: id 0 | task 9174 | graph reallocs = 0 / 0 (same size) / (changed size) 12.56.468.049 I slot release: id 0 | task 9174 | stop processing: n_tokens = 1169, truncated = 0 12.56.469.280 I slot print_timing: id 2 | task 9179 | prompt processing, n_tokens = 2092, progress = 1.00, t = 7.05 s / 296.85 tokens per second 12.56.473.095 I slot print_timing: id 3 | task 9176 | prompt processing, n_tokens = 2125, progress = 1.00, t = 10.96 s / 193.89 tokens per second 12.56.550.729 I slot print_timing: id 1 | task 9175 | prompt eval time = 14841.24 ms / 2132 tokens ( 6.96 ms per token, 143.65 tokens per second) 12.56.550.732 I slot print_timing: id 1 | task 9175 | eval time = 81.45 ms / 2 tokens ( 81.45 ms per token, 12.28 tokens per second) 12.56.550.732 I slot print_timing: id 1 | task 9175 | total time = 14922.69 ms / 2134 tokens 12.56.550.733 I slot print_timing: id 1 | task 9175 | graphs reused = 7760 12.56.550.733 I slot print_timing: id 1 | task 9175 | graph reallocs = 0 / 0 (same size) / (changed size) 12.56.550.831 I slot release: id 1 | task 9175 | stop processing: n_tokens = 2142, truncated = 0 12.56.553.120 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.855 12.56.553.208 I slot launch_slot_: id 1 | task 9184 | processing task, is_child = 0 12.56.553.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.003 MiB) 12.56.560.055 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1169, t_last = 327581003304 12.56.560.208 I slot launch_slot_: id 0 | task 9185 | processing task, is_child = 0 13.00.196.393 I slot print_timing: id 2 | task 9179 | prompt eval time = 7132.35 ms / 2096 tokens ( 3.40 ms per token, 293.87 tokens per second) 13.00.196.398 I slot print_timing: id 2 | task 9179 | eval time = 3644.39 ms / 2 tokens ( 3644.39 ms per token, 0.27 tokens per second) 13.00.196.398 I slot print_timing: id 2 | task 9179 | total time = 10776.74 ms / 2098 tokens 13.00.196.399 I slot print_timing: id 2 | task 9179 | graphs reused = 7760 13.00.196.399 I slot print_timing: id 2 | task 9179 | graph reallocs = 0 / 0 (same size) / (changed size) 13.00.196.552 I slot release: id 2 | task 9179 | stop processing: n_tokens = 2106, truncated = 0 13.00.197.684 I slot print_timing: id 3 | task 9176 | prompt eval time = 11045.82 ms / 2129 tokens ( 5.19 ms per token, 192.74 tokens per second) 13.00.197.688 I slot print_timing: id 3 | task 9176 | eval time = 3644.57 ms / 2 tokens ( 3644.57 ms per token, 0.27 tokens per second) 13.00.197.690 I slot print_timing: id 3 | task 9176 | total time = 14690.38 ms / 2131 tokens 13.00.197.690 I slot print_timing: id 3 | task 9176 | graphs reused = 7760 13.00.197.691 I slot print_timing: id 3 | task 9176 | graph reallocs = 0 / 0 (same size) / (changed size) 13.00.197.765 I slot release: id 3 | task 9176 | stop processing: n_tokens = 2139, truncated = 0 13.00.197.793 I slot print_timing: id 0 | task 9185 | prompt processing, n_tokens = 1627, progress = 0.76, t = 3.64 s / 447.58 tokens per second 13.00.200.053 I slot print_timing: id 1 | task 9184 | prompt processing, n_tokens = 249, progress = 1.00, t = 3.63 s / 68.50 tokens per second 13.00.629.440 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.869 (> 0.100 thold), f_keep = 0.869 13.00.629.515 I slot launch_slot_: id 2 | task 9188 | processing task, is_child = 0 13.00.629.675 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.887 MiB) 13.00.646.005 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.856 13.00.646.056 I slot launch_slot_: id 3 | task 9189 | processing task, is_child = 0 13.00.646.067 I slot print_timing: id 0 | task 9185 | prompt processing, n_tokens = 1795, progress = 0.84, t = 4.07 s / 441.25 tokens per second 13.02.671.778 I slot print_timing: id 1 | task 9184 | prompt eval time = 4068.96 ms / 253 tokens ( 16.08 ms per token, 62.18 tokens per second) 13.02.671.781 I slot print_timing: id 1 | task 9184 | eval time = 2042.35 ms / 2 tokens ( 2042.35 ms per token, 0.49 tokens per second) 13.02.671.783 I slot print_timing: id 1 | task 9184 | total time = 6111.31 ms / 255 tokens 13.02.671.783 I slot print_timing: id 1 | task 9184 | graphs reused = 7760 13.02.671.784 I slot print_timing: id 1 | task 9184 | graph reallocs = 0 / 0 (same size) / (changed size) 13.02.671.875 I slot release: id 1 | task 9184 | stop processing: n_tokens = 2086, truncated = 0 13.02.671.897 I slot print_timing: id 0 | task 9185 | prompt processing, n_tokens = 2139, progress = 1.00, t = 6.11 s / 350.05 tokens per second 13.02.760.837 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.878 13.02.760.943 I slot launch_slot_: id 1 | task 9192 | processing task, is_child = 0 13.03.521.152 I slot print_timing: id 0 | task 9185 | prompt eval time = 6198.17 ms / 2143 tokens ( 2.89 ms per token, 345.75 tokens per second) 13.03.521.155 I slot print_timing: id 0 | task 9185 | eval time = 762.76 ms / 2 tokens ( 762.76 ms per token, 1.31 tokens per second) 13.03.521.156 I slot print_timing: id 0 | task 9185 | total time = 6960.93 ms / 2145 tokens 13.03.521.156 I slot print_timing: id 0 | task 9185 | graphs reused = 7760 13.03.521.157 I slot print_timing: id 0 | task 9185 | graph reallocs = 0 / 0 (same size) / (changed size) 13.03.521.302 I slot release: id 0 | task 9185 | stop processing: n_tokens = 2153, truncated = 0 13.03.522.441 I slot print_timing: id 2 | task 9188 | prompt eval time = 2111.84 ms / 276 tokens ( 7.65 ms per token, 130.69 tokens per second) 13.03.522.444 I slot print_timing: id 2 | task 9188 | eval time = 762.81 ms / 2 tokens ( 762.81 ms per token, 1.31 tokens per second) 13.03.522.445 I slot print_timing: id 2 | task 9188 | total time = 2874.65 ms / 278 tokens 13.03.522.445 I slot print_timing: id 2 | task 9188 | graphs reused = 7760 13.03.522.446 I slot print_timing: id 2 | task 9188 | graph reallocs = 0 / 0 (same size) / (changed size) 13.03.522.519 I slot release: id 2 | task 9188 | stop processing: n_tokens = 2108, truncated = 0 13.03.523.695 I slot print_timing: id 3 | task 9189 | prompt eval time = 2111.27 ms / 344 tokens ( 6.14 ms per token, 162.93 tokens per second) 13.03.523.699 I slot print_timing: id 3 | task 9189 | eval time = 762.86 ms / 2 tokens ( 762.86 ms per token, 1.31 tokens per second) 13.03.523.699 I slot print_timing: id 3 | task 9189 | total time = 2874.14 ms / 346 tokens 13.03.523.699 I slot print_timing: id 3 | task 9189 | graphs reused = 7760 13.03.523.700 I slot print_timing: id 3 | task 9189 | graph reallocs = 0 / 0 (same size) / (changed size) 13.03.523.761 I slot release: id 3 | task 9189 | stop processing: n_tokens = 2177, truncated = 0 13.03.562.704 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.851 13.03.562.752 I slot launch_slot_: id 0 | task 9195 | processing task, is_child = 0 13.03.562.886 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 234.529 MiB) 13.03.581.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.920 MiB) 13.03.600.962 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.842 13.03.601.032 I slot launch_slot_: id 3 | task 9196 | processing task, is_child = 0 13.03.601.155 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.806 (> 0.100 thold), f_keep = 0.869 13.03.601.190 I slot launch_slot_: id 2 | task 9197 | processing task, is_child = 0 13.05.416.784 I slot print_timing: id 1 | task 9192 | prompt eval time = 801.75 ms / 353 tokens ( 2.27 ms per token, 440.29 tokens per second) 13.05.416.787 I slot print_timing: id 1 | task 9192 | eval time = 1854.08 ms / 2 tokens ( 1854.08 ms per token, 0.54 tokens per second) 13.05.416.788 I slot print_timing: id 1 | task 9192 | total time = 2655.83 ms / 355 tokens 13.05.416.788 I slot print_timing: id 1 | task 9192 | graphs reused = 7760 13.05.416.789 I slot print_timing: id 1 | task 9192 | graph reallocs = 0 / 0 (same size) / (changed size) 13.05.416.885 I slot release: id 1 | task 9192 | stop processing: n_tokens = 2186, truncated = 0 13.05.509.280 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.838 13.05.509.374 I slot launch_slot_: id 1 | task 9200 | processing task, is_child = 0 13.06.030.929 I slot print_timing: id 0 | task 9195 | prompt eval time = 1905.74 ms / 189 tokens ( 10.08 ms per token, 99.17 tokens per second) 13.06.030.932 I slot print_timing: id 0 | task 9195 | eval time = 523.99 ms / 2 tokens ( 523.99 ms per token, 1.91 tokens per second) 13.06.030.933 I slot print_timing: id 0 | task 9195 | total time = 2429.73 ms / 191 tokens 13.06.030.934 I slot print_timing: id 0 | task 9195 | graphs reused = 7760 13.06.030.934 I slot print_timing: id 0 | task 9195 | graph reallocs = 0 / 0 (same size) / (changed size) 13.06.031.028 I slot release: id 0 | task 9195 | stop processing: n_tokens = 2022, truncated = 0 13.06.032.171 I slot print_timing: id 2 | task 9197 | prompt eval time = 1905.10 ms / 441 tokens ( 4.32 ms per token, 231.48 tokens per second) 13.06.032.174 I slot print_timing: id 2 | task 9197 | eval time = 524.11 ms / 2 tokens ( 524.11 ms per token, 1.91 tokens per second) 13.06.032.174 I slot print_timing: id 2 | task 9197 | total time = 2429.21 ms / 443 tokens 13.06.032.174 I slot print_timing: id 2 | task 9197 | graphs reused = 7760 13.06.032.175 I slot print_timing: id 2 | task 9197 | graph reallocs = 0 / 0 (same size) / (changed size) 13.06.032.255 I slot release: id 2 | task 9197 | stop processing: n_tokens = 2273, truncated = 0 13.06.033.444 I slot print_timing: id 3 | task 9196 | prompt eval time = 1904.57 ms / 232 tokens ( 8.21 ms per token, 121.81 tokens per second) 13.06.033.451 I slot print_timing: id 3 | task 9196 | eval time = 524.17 ms / 2 tokens ( 524.17 ms per token, 1.91 tokens per second) 13.06.033.452 I slot print_timing: id 3 | task 9196 | total time = 2428.74 ms / 234 tokens 13.06.033.452 I slot print_timing: id 3 | task 9196 | graphs reused = 7760 13.06.033.452 I slot print_timing: id 3 | task 9196 | graph reallocs = 0 / 0 (same size) / (changed size) 13.06.033.513 I slot release: id 3 | task 9196 | stop processing: n_tokens = 2064, truncated = 0 13.06.072.225 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.906 13.06.072.287 I slot launch_slot_: id 0 | task 9203 | processing task, is_child = 0 13.06.072.424 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 256.611 MiB) 13.06.072.428 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.617 MiB) 13.06.091.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.723 MiB) 13.06.100.811 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.806 13.06.100.889 I slot launch_slot_: id 2 | task 9204 | processing task, is_child = 0 13.06.101.018 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.852 (> 0.100 thold), f_keep = 0.888 13.06.101.056 I slot launch_slot_: id 3 | task 9205 | processing task, is_child = 0 13.07.814.806 I slot print_timing: id 1 | task 9200 | prompt eval time = 562.84 ms / 226 tokens ( 2.49 ms per token, 401.54 tokens per second) 13.07.814.809 I slot print_timing: id 1 | task 9200 | eval time = 1742.58 ms / 2 tokens ( 1742.58 ms per token, 0.57 tokens per second) 13.07.814.809 I slot print_timing: id 1 | task 9200 | total time = 2305.42 ms / 228 tokens 13.07.814.810 I slot print_timing: id 1 | task 9200 | graphs reused = 7760 13.07.814.810 I slot print_timing: id 1 | task 9200 | graph reallocs = 0 / 0 (same size) / (changed size) 13.07.814.951 I slot release: id 1 | task 9200 | stop processing: n_tokens = 2058, truncated = 0 13.07.900.158 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.890 13.07.900.252 I slot launch_slot_: id 1 | task 9208 | processing task, is_child = 0 13.08.540.317 I slot print_timing: id 0 | task 9203 | prompt eval time = 1796.82 ms / 193 tokens ( 9.31 ms per token, 107.41 tokens per second) 13.08.540.321 I slot print_timing: id 0 | task 9203 | eval time = 642.42 ms / 2 tokens ( 642.42 ms per token, 1.56 tokens per second) 13.08.540.322 I slot print_timing: id 0 | task 9203 | total time = 2439.24 ms / 195 tokens 13.08.540.322 I slot print_timing: id 0 | task 9203 | graphs reused = 7760 13.08.540.323 I slot print_timing: id 0 | task 9203 | graph reallocs = 0 / 0 (same size) / (changed size) 13.08.540.465 I slot release: id 0 | task 9203 | stop processing: n_tokens = 2025, truncated = 0 13.08.541.601 I slot print_timing: id 2 | task 9204 | prompt eval time = 1796.17 ms / 282 tokens ( 6.37 ms per token, 157.00 tokens per second) 13.08.541.607 I slot print_timing: id 2 | task 9204 | eval time = 642.61 ms / 2 tokens ( 642.61 ms per token, 1.56 tokens per second) 13.08.541.608 I slot print_timing: id 2 | task 9204 | total time = 2438.78 ms / 284 tokens 13.08.541.608 I slot print_timing: id 2 | task 9204 | graphs reused = 7760 13.08.541.608 I slot print_timing: id 2 | task 9204 | graph reallocs = 0 / 0 (same size) / (changed size) 13.08.541.693 I slot release: id 2 | task 9204 | stop processing: n_tokens = 2113, truncated = 0 13.08.542.859 I slot print_timing: id 3 | task 9205 | prompt eval time = 1794.38 ms / 318 tokens ( 5.64 ms per token, 177.22 tokens per second) 13.08.542.862 I slot print_timing: id 3 | task 9205 | eval time = 642.71 ms / 2 tokens ( 642.71 ms per token, 1.56 tokens per second) 13.08.542.862 I slot print_timing: id 3 | task 9205 | total time = 2437.09 ms / 320 tokens 13.08.542.862 I slot print_timing: id 3 | task 9205 | graphs reused = 7760 13.08.542.863 I slot print_timing: id 3 | task 9205 | graph reallocs = 0 / 0 (same size) / (changed size) 13.08.542.926 I slot release: id 3 | task 9205 | stop processing: n_tokens = 2151, truncated = 0 13.08.581.804 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.867 13.08.581.864 I slot launch_slot_: id 2 | task 9211 | processing task, is_child = 0 13.08.582.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.940 MiB) 13.08.590.782 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.617 MiB) 13.08.609.121 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.845 (> 0.100 thold), f_keep = 0.852 13.08.609.196 I slot launch_slot_: id 3 | task 9212 | processing task, is_child = 0 13.08.609.307 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.904 13.08.609.344 I slot launch_slot_: id 0 | task 9213 | processing task, is_child = 0 13.10.469.820 I slot print_timing: id 1 | task 9208 | prompt eval time = 681.54 ms / 289 tokens ( 2.36 ms per token, 424.04 tokens per second) 13.10.469.824 I slot print_timing: id 1 | task 9208 | eval time = 1888.01 ms / 2 tokens ( 1888.01 ms per token, 0.53 tokens per second) 13.10.469.827 I slot print_timing: id 1 | task 9208 | total time = 2569.55 ms / 291 tokens 13.10.469.828 I slot print_timing: id 1 | task 9208 | graphs reused = 7760 13.10.469.828 I slot print_timing: id 1 | task 9208 | graph reallocs = 0 / 0 (same size) / (changed size) 13.10.469.994 I slot release: id 1 | task 9208 | stop processing: n_tokens = 2121, truncated = 0 13.10.556.064 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.821 (> 0.100 thold), f_keep = 0.863 13.10.556.171 I slot launch_slot_: id 1 | task 9216 | processing task, is_child = 0 13.11.430.232 I slot print_timing: id 0 | task 9213 | prompt eval time = 1944.36 ms / 387 tokens ( 5.02 ms per token, 199.04 tokens per second) 13.11.430.235 I slot print_timing: id 0 | task 9213 | eval time = 876.52 ms / 2 tokens ( 876.52 ms per token, 1.14 tokens per second) 13.11.430.236 I slot print_timing: id 0 | task 9213 | total time = 2820.88 ms / 389 tokens 13.11.430.236 I slot print_timing: id 0 | task 9213 | graphs reused = 7760 13.11.430.237 I slot print_timing: id 0 | task 9213 | graph reallocs = 0 / 0 (same size) / (changed size) 13.11.430.394 I slot release: id 0 | task 9213 | stop processing: n_tokens = 2219, truncated = 0 13.11.431.529 I slot print_timing: id 2 | task 9211 | prompt eval time = 1943.58 ms / 189 tokens ( 10.28 ms per token, 97.24 tokens per second) 13.11.431.531 I slot print_timing: id 2 | task 9211 | eval time = 876.69 ms / 2 tokens ( 876.69 ms per token, 1.14 tokens per second) 13.11.431.532 I slot print_timing: id 2 | task 9211 | total time = 2820.27 ms / 191 tokens 13.11.431.532 I slot print_timing: id 2 | task 9211 | graphs reused = 7760 13.11.431.533 I slot print_timing: id 2 | task 9211 | graph reallocs = 0 / 0 (same size) / (changed size) 13.11.431.593 I slot release: id 2 | task 9211 | stop processing: n_tokens = 2022, truncated = 0 13.11.432.766 I slot print_timing: id 3 | task 9212 | prompt eval time = 1942.94 ms / 336 tokens ( 5.78 ms per token, 172.93 tokens per second) 13.11.432.769 I slot print_timing: id 3 | task 9212 | eval time = 876.71 ms / 2 tokens ( 876.71 ms per token, 1.14 tokens per second) 13.11.432.769 I slot print_timing: id 3 | task 9212 | total time = 2819.65 ms / 338 tokens 13.11.432.770 I slot print_timing: id 3 | task 9212 | graphs reused = 7760 13.11.432.770 I slot print_timing: id 3 | task 9212 | graph reallocs = 0 / 0 (same size) / (changed size) 13.11.432.840 I slot release: id 3 | task 9212 | stop processing: n_tokens = 2169, truncated = 0 13.11.471.361 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.825 13.11.471.442 I slot launch_slot_: id 0 | task 9219 | processing task, is_child = 0 13.11.471.580 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.512 MiB) 13.11.471.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.589 MiB) 13.11.482.966 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.547 MiB) 13.11.492.712 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 13.11.492.790 I slot launch_slot_: id 2 | task 9220 | processing task, is_child = 0 13.11.492.906 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.844 13.11.492.946 I slot launch_slot_: id 3 | task 9221 | processing task, is_child = 0 13.12.970.004 I slot print_timing: id 1 | task 9216 | prompt eval time = 915.17 ms / 399 tokens ( 2.29 ms per token, 435.98 tokens per second) 13.12.970.012 I slot print_timing: id 1 | task 9216 | eval time = 1498.64 ms / 2 tokens ( 1498.64 ms per token, 0.67 tokens per second) 13.12.970.012 I slot print_timing: id 1 | task 9216 | total time = 2413.82 ms / 401 tokens 13.12.970.013 I slot print_timing: id 1 | task 9216 | graphs reused = 7760 13.12.970.013 I slot print_timing: id 1 | task 9216 | graph reallocs = 0 / 0 (same size) / (changed size) 13.12.970.178 I slot release: id 1 | task 9216 | stop processing: n_tokens = 2231, truncated = 0 13.13.056.233 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.821 13.13.056.296 I slot launch_slot_: id 1 | task 9224 | processing task, is_child = 0 13.13.390.080 I slot print_timing: id 0 | task 9219 | prompt eval time = 1560.72 ms / 212 tokens ( 7.36 ms per token, 135.83 tokens per second) 13.13.390.085 I slot print_timing: id 0 | task 9219 | eval time = 336.40 ms / 2 tokens ( 336.40 ms per token, 2.97 tokens per second) 13.13.390.086 I slot print_timing: id 0 | task 9219 | total time = 1897.12 ms / 214 tokens 13.13.390.086 I slot print_timing: id 0 | task 9219 | graphs reused = 7760 13.13.390.087 I slot print_timing: id 0 | task 9219 | graph reallocs = 0 / 0 (same size) / (changed size) 13.13.390.186 I slot release: id 0 | task 9219 | stop processing: n_tokens = 2044, truncated = 0 13.13.391.411 I slot print_timing: id 2 | task 9220 | prompt eval time = 1560.17 ms / 238 tokens ( 6.56 ms per token, 152.55 tokens per second) 13.13.391.413 I slot print_timing: id 2 | task 9220 | eval time = 336.52 ms / 2 tokens ( 336.52 ms per token, 2.97 tokens per second) 13.13.391.414 I slot print_timing: id 2 | task 9220 | total time = 1896.69 ms / 240 tokens 13.13.391.414 I slot print_timing: id 2 | task 9220 | graphs reused = 7760 13.13.391.415 I slot print_timing: id 2 | task 9220 | graph reallocs = 0 / 0 (same size) / (changed size) 13.13.391.493 I slot release: id 2 | task 9220 | stop processing: n_tokens = 2071, truncated = 0 13.13.392.729 I slot print_timing: id 3 | task 9221 | prompt eval time = 1559.82 ms / 249 tokens ( 6.26 ms per token, 159.63 tokens per second) 13.13.392.731 I slot print_timing: id 3 | task 9221 | eval time = 336.50 ms / 2 tokens ( 336.50 ms per token, 2.97 tokens per second) 13.13.392.733 I slot print_timing: id 3 | task 9221 | total time = 1896.33 ms / 251 tokens 13.13.392.733 I slot print_timing: id 3 | task 9221 | graphs reused = 7760 13.13.392.733 I slot print_timing: id 3 | task 9221 | graph reallocs = 0 / 0 (same size) / (changed size) 13.13.392.786 I slot release: id 3 | task 9221 | stop processing: n_tokens = 2081, truncated = 0 13.13.430.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2044, t_last = 327597925442 13.13.430.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 251.547 MiB) 13.13.443.612 I slot launch_slot_: id 0 | task 9227 | processing task, is_child = 0 13.13.443.745 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.290 MiB) 13.13.443.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 256.751 MiB) 13.13.459.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.485 MiB) 13.13.468.430 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.884 13.13.468.498 I slot launch_slot_: id 2 | task 9228 | processing task, is_child = 0 13.13.468.613 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.880 13.13.468.651 I slot launch_slot_: id 3 | task 9229 | processing task, is_child = 0 13.16.103.908 I slot print_timing: id 1 | task 9224 | prompt eval time = 374.44 ms / 123 tokens ( 3.04 ms per token, 328.49 tokens per second) 13.16.103.912 I slot print_timing: id 1 | task 9224 | eval time = 2673.16 ms / 2 tokens ( 2673.16 ms per token, 0.37 tokens per second) 13.16.103.912 I slot print_timing: id 1 | task 9224 | total time = 3047.60 ms / 125 tokens 13.16.103.913 I slot print_timing: id 1 | task 9224 | graphs reused = 7760 13.16.103.913 I slot print_timing: id 1 | task 9224 | graph reallocs = 0 / 0 (same size) / (changed size) 13.16.104.015 I slot release: id 1 | task 9224 | stop processing: n_tokens = 1955, truncated = 0 13.16.772.032 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1955, t_last = 327600639272 13.16.772.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.909 MiB) 13.16.789.562 I slot launch_slot_: id 1 | task 9232 | processing task, is_child = 0 13.16.789.574 I slot print_timing: id 0 | task 9227 | prompt processing, n_tokens = 1264, progress = 0.86, t = 3.30 s / 382.92 tokens per second 13.19.392.293 I slot print_timing: id 2 | task 9228 | prompt eval time = 3301.80 ms / 172 tokens ( 19.20 ms per token, 52.09 tokens per second) 13.19.392.295 I slot print_timing: id 2 | task 9228 | eval time = 2621.51 ms / 2 tokens ( 2621.51 ms per token, 0.38 tokens per second) 13.19.392.296 I slot print_timing: id 2 | task 9228 | total time = 5923.32 ms / 174 tokens 13.19.392.296 I slot print_timing: id 2 | task 9228 | graphs reused = 7760 13.19.392.297 I slot print_timing: id 2 | task 9228 | graph reallocs = 0 / 0 (same size) / (changed size) 13.19.392.409 I slot release: id 2 | task 9228 | stop processing: n_tokens = 2004, truncated = 0 13.19.393.617 I slot print_timing: id 3 | task 9229 | prompt eval time = 3301.33 ms / 209 tokens ( 15.80 ms per token, 63.31 tokens per second) 13.19.393.621 I slot print_timing: id 3 | task 9229 | eval time = 2621.59 ms / 2 tokens ( 2621.59 ms per token, 0.38 tokens per second) 13.19.393.621 I slot print_timing: id 3 | task 9229 | total time = 5922.93 ms / 211 tokens 13.19.393.621 I slot print_timing: id 3 | task 9229 | graphs reused = 7760 13.19.393.622 I slot print_timing: id 3 | task 9229 | graph reallocs = 0 / 0 (same size) / (changed size) 13.19.393.691 I slot release: id 3 | task 9229 | stop processing: n_tokens = 2041, truncated = 0 13.19.393.714 I slot print_timing: id 0 | task 9227 | prompt processing, n_tokens = 1462, progress = 1.00, t = 5.92 s / 246.85 tokens per second 13.19.697.454 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2004, t_last = 327603927665 13.19.697.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.648 MiB) 13.19.697.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.572 MiB) 13.19.717.699 I slot launch_slot_: id 2 | task 9235 | processing task, is_child = 0 13.19.717.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.744 MiB) 13.19.733.680 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2041, t_last = 327603928948 13.19.733.853 I slot launch_slot_: id 3 | task 9236 | processing task, is_child = 0 13.23.402.592 I slot print_timing: id 0 | task 9227 | prompt eval time = 6228.79 ms / 1466 tokens ( 4.25 ms per token, 235.36 tokens per second) 13.23.402.603 I slot print_timing: id 0 | task 9227 | eval time = 3705.14 ms / 2 tokens ( 3705.14 ms per token, 0.27 tokens per second) 13.23.402.603 I slot print_timing: id 0 | task 9227 | total time = 9933.92 ms / 1468 tokens 13.23.402.604 I slot print_timing: id 0 | task 9227 | graphs reused = 7760 13.23.402.604 I slot print_timing: id 0 | task 9227 | graph reallocs = 0 / 0 (same size) / (changed size) 13.23.402.721 I slot release: id 0 | task 9227 | stop processing: n_tokens = 1476, truncated = 0 13.23.402.758 I slot print_timing: id 1 | task 9232 | prompt processing, n_tokens = 1667, progress = 1.00, t = 6.61 s / 252.19 tokens per second 13.23.406.731 I slot print_timing: id 2 | task 9235 | prompt processing, n_tokens = 479, progress = 0.49, t = 3.67 s / 130.67 tokens per second 13.23.408.623 I slot print_timing: id 3 | task 9236 | prompt processing, n_tokens = 1021, progress = 0.67, t = 3.67 s / 278.54 tokens per second 13.24.643.274 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 327607937978 13.24.643.413 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.521 MiB) 13.24.652.579 I slot launch_slot_: id 0 | task 9239 | processing task, is_child = 0 13.24.652.827 I slot print_timing: id 2 | task 9235 | prompt processing, n_tokens = 848, progress = 0.85, t = 4.91 s / 172.83 tokens per second 13.24.654.511 I slot print_timing: id 3 | task 9236 | prompt processing, n_tokens = 1264, progress = 0.82, t = 4.91 s / 257.63 tokens per second 13.26.382.053 I slot print_timing: id 1 | task 9232 | prompt eval time = 7851.90 ms / 1671 tokens ( 4.70 ms per token, 212.81 tokens per second) 13.26.382.056 I slot print_timing: id 1 | task 9232 | eval time = 1738.79 ms / 2 tokens ( 1738.79 ms per token, 0.58 tokens per second) 13.26.382.057 I slot print_timing: id 1 | task 9232 | total time = 9590.69 ms / 1673 tokens 13.26.382.057 I slot print_timing: id 1 | task 9232 | graphs reused = 7760 13.26.382.058 I slot print_timing: id 1 | task 9232 | graph reallocs = 0 / 0 (same size) / (changed size) 13.26.382.140 I slot release: id 1 | task 9232 | stop processing: n_tokens = 1681, truncated = 0 13.26.385.979 I slot print_timing: id 2 | task 9235 | prompt processing, n_tokens = 991, progress = 1.00, t = 6.65 s / 149.13 tokens per second 13.26.388.244 I slot print_timing: id 3 | task 9236 | prompt processing, n_tokens = 1533, progress = 1.00, t = 6.65 s / 230.70 tokens per second 13.27.158.755 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1681, t_last = 327610917397 13.27.158.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.653 MiB) 13.27.171.084 I slot launch_slot_: id 1 | task 9242 | processing task, is_child = 0 13.28.390.342 I slot print_timing: id 2 | task 9235 | prompt eval time = 7421.66 ms / 995 tokens ( 7.46 ms per token, 134.07 tokens per second) 13.28.390.349 I slot print_timing: id 2 | task 9235 | eval time = 1233.08 ms / 2 tokens ( 1233.08 ms per token, 0.81 tokens per second) 13.28.390.349 I slot print_timing: id 2 | task 9235 | total time = 8654.74 ms / 997 tokens 13.28.390.350 I slot print_timing: id 2 | task 9235 | graphs reused = 7760 13.28.390.351 I slot print_timing: id 2 | task 9235 | graph reallocs = 0 / 0 (same size) / (changed size) 13.28.390.430 I slot release: id 2 | task 9235 | stop processing: n_tokens = 1005, truncated = 0 13.28.391.649 I slot print_timing: id 3 | task 9236 | prompt eval time = 7422.84 ms / 1537 tokens ( 4.83 ms per token, 207.06 tokens per second) 13.28.391.651 I slot print_timing: id 3 | task 9236 | eval time = 1232.90 ms / 2 tokens ( 1232.90 ms per token, 0.81 tokens per second) 13.28.391.653 I slot print_timing: id 3 | task 9236 | total time = 8655.75 ms / 1539 tokens 13.28.391.654 I slot print_timing: id 3 | task 9236 | graphs reused = 7760 13.28.391.655 I slot print_timing: id 3 | task 9236 | graph reallocs = 0 / 0 (same size) / (changed size) 13.28.391.751 I slot release: id 3 | task 9236 | stop processing: n_tokens = 1547, truncated = 0 13.28.391.770 I slot print_timing: id 0 | task 9239 | prompt processing, n_tokens = 981, progress = 1.00, t = 3.74 s / 262.54 tokens per second 13.29.211.455 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.880 13.29.211.573 I slot launch_slot_: id 2 | task 9245 | processing task, is_child = 0 13.29.211.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.332 MiB) 13.29.228.050 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1547, t_last = 327612927007 13.29.228.193 I slot launch_slot_: id 3 | task 9246 | processing task, is_child = 0 13.30.601.793 I slot print_timing: id 0 | task 9239 | prompt eval time = 4558.85 ms / 985 tokens ( 4.63 ms per token, 216.06 tokens per second) 13.30.601.796 I slot print_timing: id 0 | task 9239 | eval time = 1390.35 ms / 2 tokens ( 1390.35 ms per token, 0.72 tokens per second) 13.30.601.796 I slot print_timing: id 0 | task 9239 | total time = 5949.20 ms / 987 tokens 13.30.601.797 I slot print_timing: id 0 | task 9239 | graphs reused = 7760 13.30.601.798 I slot print_timing: id 0 | task 9239 | graph reallocs = 0 / 0 (same size) / (changed size) 13.30.601.854 I slot release: id 0 | task 9239 | stop processing: n_tokens = 995, truncated = 0 13.30.601.867 I slot print_timing: id 1 | task 9242 | prompt processing, n_tokens = 969, progress = 1.00, t = 3.43 s / 282.68 tokens per second 13.31.457.909 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.888 13.31.458.005 I slot launch_slot_: id 0 | task 9249 | processing task, is_child = 0 13.31.963.077 I slot print_timing: id 1 | task 9242 | prompt eval time = 4283.80 ms / 973 tokens ( 4.40 ms per token, 227.13 tokens per second) 13.31.963.082 I slot print_timing: id 1 | task 9242 | eval time = 506.53 ms / 2 tokens ( 506.53 ms per token, 1.97 tokens per second) 13.31.963.083 I slot print_timing: id 1 | task 9242 | total time = 4790.33 ms / 975 tokens 13.31.963.083 I slot print_timing: id 1 | task 9242 | graphs reused = 7760 13.31.963.084 I slot print_timing: id 1 | task 9242 | graph reallocs = 0 / 0 (same size) / (changed size) 13.31.963.134 I slot release: id 1 | task 9242 | stop processing: n_tokens = 983, truncated = 0 13.31.964.362 I slot print_timing: id 2 | task 9245 | prompt eval time = 2228.03 ms / 103 tokens ( 21.63 ms per token, 46.23 tokens per second) 13.31.964.365 I slot print_timing: id 2 | task 9245 | eval time = 506.46 ms / 2 tokens ( 506.46 ms per token, 1.97 tokens per second) 13.31.964.366 I slot print_timing: id 2 | task 9245 | total time = 2734.49 ms / 105 tokens 13.31.964.366 I slot print_timing: id 2 | task 9245 | graphs reused = 7760 13.31.964.366 I slot print_timing: id 2 | task 9245 | graph reallocs = 0 / 0 (same size) / (changed size) 13.31.964.403 I slot release: id 2 | task 9245 | stop processing: n_tokens = 988, truncated = 0 13.32.039.174 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 983, t_last = 327616498389 13.32.039.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.524 MiB) 13.32.045.854 I slot launch_slot_: id 1 | task 9252 | processing task, is_child = 0 13.32.045.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.437 MiB) 13.32.045.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.515 MiB) 13.32.053.252 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.895 13.32.053.298 I slot launch_slot_: id 2 | task 9253 | processing task, is_child = 0 13.32.905.653 I slot print_timing: id 0 | task 9249 | prompt eval time = 579.91 ms / 93 tokens ( 6.24 ms per token, 160.37 tokens per second) 13.32.905.656 I slot print_timing: id 0 | task 9249 | eval time = 867.73 ms / 2 tokens ( 867.73 ms per token, 1.15 tokens per second) 13.32.905.657 I slot print_timing: id 0 | task 9249 | total time = 1447.63 ms / 95 tokens 13.32.905.657 I slot print_timing: id 0 | task 9249 | graphs reused = 7760 13.32.905.658 I slot print_timing: id 0 | task 9249 | graph reallocs = 0 / 0 (same size) / (changed size) 13.32.905.730 I slot release: id 0 | task 9249 | stop processing: n_tokens = 978, truncated = 0 13.32.906.966 I slot print_timing: id 3 | task 9246 | prompt eval time = 2807.57 ms / 958 tokens ( 2.93 ms per token, 341.22 tokens per second) 13.32.906.972 I slot print_timing: id 3 | task 9246 | eval time = 867.79 ms / 2 tokens ( 867.79 ms per token, 1.15 tokens per second) 13.32.906.973 I slot print_timing: id 3 | task 9246 | total time = 3675.37 ms / 960 tokens 13.32.906.973 I slot print_timing: id 3 | task 9246 | graphs reused = 7760 13.32.906.974 I slot print_timing: id 3 | task 9246 | graph reallocs = 0 / 0 (same size) / (changed size) 13.32.907.016 I slot release: id 3 | task 9246 | stop processing: n_tokens = 968, truncated = 0 13.33.719.256 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 978, t_last = 327617440985 13.33.719.379 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.906 MiB) 13.33.728.957 I slot launch_slot_: id 0 | task 9256 | processing task, is_child = 0 13.33.729.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.063 MiB) 13.33.735.013 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 968, t_last = 327617442271 13.33.735.135 I slot launch_slot_: id 3 | task 9257 | processing task, is_child = 0 13.37.614.215 I slot print_timing: id 2 | task 9253 | prompt eval time = 1665.72 ms / 98 tokens ( 17.00 ms per token, 58.83 tokens per second) 13.37.614.218 I slot print_timing: id 2 | task 9253 | eval time = 3894.96 ms / 2 tokens ( 3894.96 ms per token, 0.26 tokens per second) 13.37.614.219 I slot print_timing: id 2 | task 9253 | total time = 5560.68 ms / 100 tokens 13.37.614.220 I slot print_timing: id 2 | task 9253 | graphs reused = 7760 13.37.614.220 I slot print_timing: id 2 | task 9253 | graph reallocs = 0 / 0 (same size) / (changed size) 13.37.614.302 I slot release: id 2 | task 9253 | stop processing: n_tokens = 983, truncated = 0 13.37.614.335 I slot print_timing: id 0 | task 9256 | prompt processing, n_tokens = 1131, progress = 0.69, t = 3.88 s / 291.65 tokens per second 13.37.617.323 I slot print_timing: id 1 | task 9252 | prompt processing, n_tokens = 810, progress = 1.00, t = 5.56 s / 145.69 tokens per second 13.37.619.400 I slot print_timing: id 3 | task 9257 | prompt processing, n_tokens = 801, progress = 0.50, t = 3.88 s / 206.65 tokens per second 13.38.714.364 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 983, t_last = 327622149557 13.38.714.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.017 MiB) 13.38.724.982 I slot launch_slot_: id 2 | task 9260 | processing task, is_child = 0 13.38.724.993 I slot print_timing: id 0 | task 9256 | prompt processing, n_tokens = 1388, progress = 0.84, t = 4.98 s / 278.82 tokens per second 13.38.726.964 I slot print_timing: id 3 | task 9257 | prompt processing, n_tokens = 1086, progress = 0.68, t = 4.98 s / 218.24 tokens per second 13.41.970.623 I slot print_timing: id 1 | task 9252 | prompt eval time = 6661.05 ms / 814 tokens ( 8.18 ms per token, 122.20 tokens per second) 13.41.970.630 I slot print_timing: id 1 | task 9252 | eval time = 3256.25 ms / 2 tokens ( 3256.25 ms per token, 0.31 tokens per second) 13.41.970.630 I slot print_timing: id 1 | task 9252 | total time = 9917.30 ms / 816 tokens 13.41.970.631 I slot print_timing: id 1 | task 9252 | graphs reused = 7760 13.41.970.631 I slot print_timing: id 1 | task 9252 | graph reallocs = 0 / 0 (same size) / (changed size) 13.41.970.718 I slot release: id 1 | task 9252 | stop processing: n_tokens = 824, truncated = 0 13.41.970.751 I slot print_timing: id 0 | task 9256 | prompt processing, n_tokens = 1643, progress = 1.00, t = 8.23 s / 199.53 tokens per second 13.41.974.790 I slot print_timing: id 2 | task 9260 | prompt processing, n_tokens = 1114, progress = 0.69, t = 3.24 s / 343.53 tokens per second 13.41.976.823 I slot print_timing: id 3 | task 9257 | prompt processing, n_tokens = 1388, progress = 0.87, t = 8.23 s / 168.60 tokens per second 13.43.021.151 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 327626505973 13.43.021.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.143 MiB) 13.43.029.712 I slot launch_slot_: id 1 | task 9263 | processing task, is_child = 0 13.43.029.922 I slot print_timing: id 2 | task 9260 | prompt processing, n_tokens = 1388, progress = 0.85, t = 4.29 s / 323.30 tokens per second 13.43.031.680 I slot print_timing: id 3 | task 9257 | prompt processing, n_tokens = 1598, progress = 1.00, t = 9.28 s / 172.14 tokens per second 13.45.743.123 I slot print_timing: id 0 | task 9256 | prompt eval time = 9285.99 ms / 1647 tokens ( 5.64 ms per token, 177.36 tokens per second) 13.45.743.126 I slot print_timing: id 0 | task 9256 | eval time = 2721.98 ms / 2 tokens ( 2721.98 ms per token, 0.37 tokens per second) 13.45.743.127 I slot print_timing: id 0 | task 9256 | total time = 12007.97 ms / 1649 tokens 13.45.743.128 I slot print_timing: id 0 | task 9256 | graphs reused = 7760 13.45.743.128 I slot print_timing: id 0 | task 9256 | graph reallocs = 0 / 0 (same size) / (changed size) 13.45.743.261 I slot release: id 0 | task 9256 | stop processing: n_tokens = 1657, truncated = 0 13.45.747.223 I slot print_timing: id 2 | task 9260 | prompt processing, n_tokens = 1626, progress = 1.00, t = 7.02 s / 231.78 tokens per second 13.46.310.001 I slot print_timing: id 3 | task 9257 | prompt eval time = 12007.73 ms / 1602 tokens ( 7.50 ms per token, 133.41 tokens per second) 13.46.310.008 I slot print_timing: id 3 | task 9257 | eval time = 565.24 ms / 2 tokens ( 565.24 ms per token, 1.77 tokens per second) 13.46.310.009 I slot print_timing: id 3 | task 9257 | total time = 12572.97 ms / 1604 tokens 13.46.310.009 I slot print_timing: id 3 | task 9257 | graphs reused = 7760 13.46.310.010 I slot print_timing: id 3 | task 9257 | graph reallocs = 0 / 0 (same size) / (changed size) 13.46.310.112 I slot release: id 3 | task 9257 | stop processing: n_tokens = 1612, truncated = 0 13.46.310.131 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.814 (> 0.100 thold), f_keep = 0.859 13.46.310.233 I slot launch_slot_: id 0 | task 9266 | processing task, is_child = 0 13.46.310.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.255 MiB) 13.46.320.064 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1612, t_last = 327630845368 13.46.320.215 I slot launch_slot_: id 3 | task 9267 | processing task, is_child = 0 13.46.322.022 I slot print_timing: id 1 | task 9263 | prompt processing, n_tokens = 1388, progress = 0.84, t = 3.28 s / 423.44 tokens per second 13.48.134.043 I slot print_timing: id 2 | task 9260 | prompt eval time = 7582.12 ms / 1630 tokens ( 4.65 ms per token, 214.98 tokens per second) 13.48.134.048 I slot print_timing: id 2 | task 9260 | eval time = 1825.17 ms / 2 tokens ( 1825.17 ms per token, 0.55 tokens per second) 13.48.134.049 I slot print_timing: id 2 | task 9260 | total time = 9407.30 ms / 1632 tokens 13.48.134.050 I slot print_timing: id 2 | task 9260 | graphs reused = 7760 13.48.134.050 I slot print_timing: id 2 | task 9260 | graph reallocs = 0 / 0 (same size) / (changed size) 13.48.134.165 I slot release: id 2 | task 9260 | stop processing: n_tokens = 1640, truncated = 0 13.48.138.467 I slot print_timing: id 1 | task 9263 | prompt processing, n_tokens = 1652, progress = 1.00, t = 5.10 s / 323.72 tokens per second 13.48.956.691 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1640, t_last = 327632669422 13.48.956.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 346.172 MiB) 13.48.967.410 I slot launch_slot_: id 2 | task 9270 | processing task, is_child = 0 13.49.906.566 I slot print_timing: id 0 | task 9266 | prompt eval time = 2635.16 ms / 325 tokens ( 8.11 ms per token, 123.33 tokens per second) 13.49.906.569 I slot print_timing: id 0 | task 9266 | eval time = 951.18 ms / 2 tokens ( 951.18 ms per token, 1.05 tokens per second) 13.49.906.570 I slot print_timing: id 0 | task 9266 | total time = 3586.34 ms / 327 tokens 13.49.906.571 I slot print_timing: id 0 | task 9266 | graphs reused = 7760 13.49.906.571 I slot print_timing: id 0 | task 9266 | graph reallocs = 0 / 0 (same size) / (changed size) 13.49.906.696 I slot release: id 0 | task 9266 | stop processing: n_tokens = 1750, truncated = 0 13.49.907.839 I slot print_timing: id 1 | task 9263 | prompt eval time = 5926.96 ms / 1656 tokens ( 3.58 ms per token, 279.40 tokens per second) 13.49.907.842 I slot print_timing: id 1 | task 9263 | eval time = 951.16 ms / 2 tokens ( 951.16 ms per token, 1.05 tokens per second) 13.49.907.842 I slot print_timing: id 1 | task 9263 | total time = 6878.12 ms / 1658 tokens 13.49.907.843 I slot print_timing: id 1 | task 9263 | graphs reused = 7760 13.49.907.843 I slot print_timing: id 1 | task 9263 | graph reallocs = 0 / 0 (same size) / (changed size) 13.49.907.902 I slot release: id 1 | task 9263 | stop processing: n_tokens = 1666, truncated = 0 13.49.909.409 I slot print_timing: id 3 | task 9267 | prompt processing, n_tokens = 831, progress = 1.00, t = 3.58 s / 232.01 tokens per second 13.50.667.058 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1750, t_last = 327634441953 13.50.667.218 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 348.598 MiB) 13.50.678.851 I slot launch_slot_: id 0 | task 9273 | processing task, is_child = 0 13.50.691.802 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1666, t_last = 327634443157 13.50.691.956 I slot launch_slot_: id 1 | task 9274 | processing task, is_child = 0 13.52.265.816 I slot print_timing: id 3 | task 9267 | prompt eval time = 4343.31 ms / 835 tokens ( 5.20 ms per token, 192.25 tokens per second) 13.52.265.820 I slot print_timing: id 3 | task 9267 | eval time = 1598.76 ms / 2 tokens ( 1598.76 ms per token, 0.63 tokens per second) 13.52.265.821 I slot print_timing: id 3 | task 9267 | total time = 5942.06 ms / 837 tokens 13.52.265.822 I slot print_timing: id 3 | task 9267 | graphs reused = 7760 13.52.265.822 I slot print_timing: id 3 | task 9267 | graph reallocs = 0 / 0 (same size) / (changed size) 13.52.265.904 I slot release: id 3 | task 9267 | stop processing: n_tokens = 845, truncated = 0 13.52.271.060 I slot print_timing: id 2 | task 9270 | prompt processing, n_tokens = 858, progress = 1.00, t = 3.30 s / 260.21 tokens per second 13.53.809.352 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 327636801160 13.53.809.469 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 351.974 MiB) 13.53.817.616 I slot launch_slot_: id 3 | task 9277 | processing task, is_child = 0 13.53.817.627 I slot print_timing: id 0 | task 9273 | prompt processing, n_tokens = 714, progress = 0.83, t = 3.12 s / 229.12 tokens per second 13.53.819.323 I slot print_timing: id 1 | task 9274 | prompt processing, n_tokens = 714, progress = 0.85, t = 3.12 s / 229.14 tokens per second 13.55.128.798 I slot print_timing: id 2 | task 9270 | prompt eval time = 4841.92 ms / 862 tokens ( 5.62 ms per token, 178.03 tokens per second) 13.55.128.801 I slot print_timing: id 2 | task 9270 | eval time = 1319.45 ms / 2 tokens ( 1319.45 ms per token, 0.76 tokens per second) 13.55.128.803 I slot print_timing: id 2 | task 9270 | total time = 6161.38 ms / 864 tokens 13.55.128.803 I slot print_timing: id 2 | task 9270 | graphs reused = 7760 13.55.128.804 I slot print_timing: id 2 | task 9270 | graph reallocs = 0 / 0 (same size) / (changed size) 13.55.128.864 I slot release: id 2 | task 9270 | stop processing: n_tokens = 872, truncated = 0 13.55.128.893 I slot print_timing: id 0 | task 9273 | prompt processing, n_tokens = 855, progress = 1.00, t = 4.44 s / 192.75 tokens per second 13.55.133.028 I slot print_timing: id 1 | task 9274 | prompt processing, n_tokens = 836, progress = 1.00, t = 4.44 s / 188.48 tokens per second 13.55.838.114 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 872, t_last = 327639664119 13.55.838.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 398.525 MiB) 13.55.846.514 I slot launch_slot_: id 2 | task 9280 | processing task, is_child = 0 13.56.728.903 I slot print_timing: id 0 | task 9273 | prompt eval time = 5144.89 ms / 859 tokens ( 5.99 ms per token, 166.96 tokens per second) 13.56.728.907 I slot print_timing: id 0 | task 9273 | eval time = 892.04 ms / 2 tokens ( 892.04 ms per token, 1.12 tokens per second) 13.56.728.908 I slot print_timing: id 0 | task 9273 | total time = 6036.93 ms / 861 tokens 13.56.728.908 I slot print_timing: id 0 | task 9273 | graphs reused = 7760 13.56.728.909 I slot print_timing: id 0 | task 9273 | graph reallocs = 0 / 0 (same size) / (changed size) 13.56.728.989 I slot release: id 0 | task 9273 | stop processing: n_tokens = 869, truncated = 0 13.56.730.144 I slot print_timing: id 1 | task 9274 | prompt eval time = 5145.86 ms / 840 tokens ( 6.13 ms per token, 163.24 tokens per second) 13.56.730.147 I slot print_timing: id 1 | task 9274 | eval time = 892.04 ms / 2 tokens ( 892.04 ms per token, 1.12 tokens per second) 13.56.730.147 I slot print_timing: id 1 | task 9274 | total time = 6037.90 ms / 842 tokens 13.56.730.147 I slot print_timing: id 1 | task 9274 | graphs reused = 7760 13.56.730.148 I slot print_timing: id 1 | task 9274 | graph reallocs = 0 / 0 (same size) / (changed size) 13.56.730.193 I slot release: id 1 | task 9274 | stop processing: n_tokens = 850, truncated = 0 13.57.483.308 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 327641264244 13.57.492.500 I slot launch_slot_: id 0 | task 9283 | processing task, is_child = 0 13.57.492.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 343.253 MiB) 13.57.498.164 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 327641265448 13.57.498.282 I slot launch_slot_: id 1 | task 9284 | processing task, is_child = 0 13.58.617.308 I slot print_timing: id 3 | task 9277 | prompt eval time = 3662.30 ms / 884 tokens ( 4.14 ms per token, 241.38 tokens per second) 13.58.617.311 I slot print_timing: id 3 | task 9277 | eval time = 1134.00 ms / 2 tokens ( 1134.00 ms per token, 0.88 tokens per second) 13.58.617.311 I slot print_timing: id 3 | task 9277 | total time = 4796.30 ms / 886 tokens 13.58.617.312 I slot print_timing: id 3 | task 9277 | graphs reused = 7760 13.58.617.312 I slot print_timing: id 3 | task 9277 | graph reallocs = 0 / 0 (same size) / (changed size) 13.58.617.383 I slot release: id 3 | task 9277 | stop processing: n_tokens = 894, truncated = 0 14.00.195.952 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 327643152638 14.00.196.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 401.585 MiB) 14.00.204.056 I slot launch_slot_: id 3 | task 9287 | processing task, is_child = 0 14.01.121.057 I slot print_timing: id 2 | task 9280 | prompt eval time = 4349.41 ms / 762 tokens ( 5.71 ms per token, 175.20 tokens per second) 14.01.121.063 I slot print_timing: id 2 | task 9280 | eval time = 925.12 ms / 2 tokens ( 925.12 ms per token, 1.08 tokens per second) 14.01.121.064 I slot print_timing: id 2 | task 9280 | total time = 5274.53 ms / 764 tokens 14.01.121.065 I slot print_timing: id 2 | task 9280 | graphs reused = 7760 14.01.121.065 I slot print_timing: id 2 | task 9280 | graph reallocs = 0 / 0 (same size) / (changed size) 14.01.121.137 I slot release: id 2 | task 9280 | stop processing: n_tokens = 772, truncated = 0 14.01.121.157 I slot print_timing: id 0 | task 9283 | prompt processing, n_tokens = 729, progress = 0.99, t = 3.62 s / 201.29 tokens per second 14.01.124.870 I slot print_timing: id 1 | task 9284 | prompt processing, n_tokens = 684, progress = 0.99, t = 3.62 s / 188.87 tokens per second 14.01.878.455 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 327645656392 14.01.886.495 I slot launch_slot_: id 2 | task 9290 | processing task, is_child = 0 14.02.548.994 I slot print_timing: id 0 | task 9283 | prompt eval time = 4379.05 ms / 733 tokens ( 5.97 ms per token, 167.39 tokens per second) 14.02.549.000 I slot print_timing: id 0 | task 9283 | eval time = 671.63 ms / 2 tokens ( 671.63 ms per token, 1.49 tokens per second) 14.02.549.000 I slot print_timing: id 0 | task 9283 | total time = 5050.68 ms / 735 tokens 14.02.549.001 I slot print_timing: id 0 | task 9283 | graphs reused = 7760 14.02.549.001 I slot print_timing: id 0 | task 9283 | graph reallocs = 0 / 0 (same size) / (changed size) 14.02.549.062 I slot release: id 0 | task 9283 | stop processing: n_tokens = 743, truncated = 0 14.02.550.219 I slot print_timing: id 1 | task 9284 | prompt eval time = 4379.96 ms / 688 tokens ( 6.37 ms per token, 157.08 tokens per second) 14.02.550.222 I slot print_timing: id 1 | task 9284 | eval time = 671.77 ms / 2 tokens ( 671.77 ms per token, 1.49 tokens per second) 14.02.550.222 I slot print_timing: id 1 | task 9284 | total time = 5051.73 ms / 690 tokens 14.02.550.222 I slot print_timing: id 1 | task 9284 | graphs reused = 7760 14.02.550.223 I slot print_timing: id 1 | task 9284 | graph reallocs = 0 / 0 (same size) / (changed size) 14.02.550.262 I slot release: id 1 | task 9284 | stop processing: n_tokens = 698, truncated = 0 14.03.635.613 I slot print_timing: id 3 | task 9287 | prompt eval time = 3147.89 ms / 707 tokens ( 4.45 ms per token, 224.60 tokens per second) 14.03.635.619 I slot print_timing: id 3 | task 9287 | eval time = 279.97 ms / 2 tokens ( 279.97 ms per token, 3.57 tokens per second) 14.03.635.619 I slot print_timing: id 3 | task 9287 | total time = 3427.86 ms / 709 tokens 14.03.635.620 I slot print_timing: id 3 | task 9287 | graphs reused = 7760 14.03.635.620 I slot print_timing: id 3 | task 9287 | graph reallocs = 0 / 0 (same size) / (changed size) 14.03.635.682 I slot release: id 3 | task 9287 | stop processing: n_tokens = 717, truncated = 0 14.03.698.441 I slot print_timing: id 2 | task 9290 | prompt eval time = 1788.22 ms / 673 tokens ( 2.66 ms per token, 376.35 tokens per second) 14.03.698.447 I slot print_timing: id 2 | task 9290 | eval time = 23.72 ms / 2 tokens ( 23.72 ms per token, 42.16 tokens per second) 14.03.698.447 I slot print_timing: id 2 | task 9290 | total time = 1811.94 ms / 675 tokens 14.03.698.448 I slot print_timing: id 2 | task 9290 | graphs reused = 7760 14.03.698.448 I slot print_timing: id 2 | task 9290 | graph reallocs = 0 / 0 (same size) / (changed size) 14.03.698.471 I slot release: id 2 | task 9290 | stop processing: n_tokens = 683, truncated = 0 14.06.645.638 I srv operator(): operator(): cleaning up before exit...