/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/37455964b1ab/Spark-X2.6-4B.i1-Q4_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 0.00.045.052 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.045.107 I srv llama_server: initializing ... 0.00.045.112 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.045.179 I srv init_listene: The UI is disabled 0.00.045.181 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.045.219 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) 0.00.046.871 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/37455964b1ab/Spark-X2.6-4B.i1-Q4_K_M.gguf' 0.00.474.703 I cmn init: llama threadpool init, n_threads = 8 0.00.568.933 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.00.577.430 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.577.444 I srv llama_server: model loaded 0.00.577.446 I srv llama_server: listening on http://127.0.0.1:8091 0.29.811.636 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.29.811.677 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.29.814.110 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.29.814.167 I slot launch_slot_: id 1 | task 3 | processing task, is_child = 0 0.29.814.168 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.29.814.202 I slot launch_slot_: id 2 | task 4 | processing task, is_child = 0 0.29.814.202 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.29.814.229 I slot launch_slot_: id 3 | task 2 | processing task, is_child = 0 0.31.048.938 I slot print_timing: id 0 | task 0 | prompt eval time = 1153.37 ms / 130 tokens ( 8.87 ms per token, 112.71 tokens per second) 0.31.048.940 I slot print_timing: id 0 | task 0 | eval time = 83.87 ms / 2 tokens ( 83.87 ms per token, 11.92 tokens per second) 0.31.048.941 I slot print_timing: id 0 | task 0 | total time = 1237.24 ms / 132 tokens 0.31.048.941 I slot print_timing: id 0 | task 0 | graphs reused = 1 0.31.048.941 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.048.966 I slot release: id 0 | task 0 | stop processing: n_tokens = 131, truncated = 0 0.31.086.565 I slot print_timing: id 1 | task 3 | prompt eval time = 1186.39 ms / 128 tokens ( 9.27 ms per token, 107.89 tokens per second) 0.31.086.568 I slot print_timing: id 1 | task 3 | eval time = 36.27 ms / 2 tokens ( 36.27 ms per token, 27.57 tokens per second) 0.31.086.568 I slot print_timing: id 1 | task 3 | total time = 1222.65 ms / 130 tokens 0.31.086.568 I slot print_timing: id 1 | task 3 | graphs reused = 1 0.31.086.569 I slot print_timing: id 1 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.086.583 I slot release: id 1 | task 3 | stop processing: n_tokens = 129, truncated = 0 0.31.087.756 I slot print_timing: id 2 | task 4 | prompt eval time = 1187.69 ms / 142 tokens ( 8.36 ms per token, 119.56 tokens per second) 0.31.087.758 I slot print_timing: id 2 | task 4 | eval time = 36.15 ms / 2 tokens ( 36.15 ms per token, 27.66 tokens per second) 0.31.087.758 I slot print_timing: id 2 | task 4 | total time = 1223.84 ms / 144 tokens 0.31.087.758 I slot print_timing: id 2 | task 4 | graphs reused = 1 0.31.087.759 I slot print_timing: id 2 | task 4 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.087.769 I slot release: id 2 | task 4 | stop processing: n_tokens = 143, truncated = 0 0.31.088.928 I slot print_timing: id 3 | task 2 | prompt eval time = 1188.97 ms / 134 tokens ( 8.87 ms per token, 112.70 tokens per second) 0.31.088.930 I slot print_timing: id 3 | task 2 | eval time = 36.03 ms / 2 tokens ( 36.03 ms per token, 27.75 tokens per second) 0.31.088.930 I slot print_timing: id 3 | task 2 | total time = 1225.00 ms / 136 tokens 0.31.088.930 I slot print_timing: id 3 | task 2 | graphs reused = 1 0.31.088.931 I slot print_timing: id 3 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.088.939 I slot release: id 3 | task 2 | stop processing: n_tokens = 135, truncated = 0 0.31.088.942 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.282 0.31.091.646 I slot launch_slot_: id 0 | task 9 | processing task, is_child = 0 0.31.099.360 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.295 0.31.099.436 I slot launch_slot_: id 1 | task 10 | processing task, is_child = 0 0.31.099.482 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.259 0.31.099.536 I slot launch_slot_: id 2 | task 11 | processing task, is_child = 0 0.31.099.559 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.319 (> 0.100 thold), f_keep = 0.281 0.31.099.610 I slot launch_slot_: id 3 | task 12 | processing task, is_child = 0 0.32.442.942 I slot print_timing: id 0 | task 9 | prompt eval time = 1305.66 ms / 164 tokens ( 7.96 ms per token, 125.61 tokens per second) 0.32.442.944 I slot print_timing: id 0 | task 9 | eval time = 37.66 ms / 2 tokens ( 37.66 ms per token, 26.56 tokens per second) 0.32.442.945 I slot print_timing: id 0 | task 9 | total time = 1343.32 ms / 166 tokens 0.32.442.945 I slot print_timing: id 0 | task 9 | graphs reused = 1 0.32.442.945 I slot print_timing: id 0 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.442.977 I slot release: id 0 | task 9 | stop processing: n_tokens = 174, truncated = 0 0.32.444.084 I slot print_timing: id 1 | task 10 | prompt eval time = 1306.61 ms / 159 tokens ( 8.22 ms per token, 121.69 tokens per second) 0.32.444.085 I slot print_timing: id 1 | task 10 | eval time = 37.73 ms / 2 tokens ( 37.73 ms per token, 26.51 tokens per second) 0.32.444.086 I slot print_timing: id 1 | task 10 | total time = 1344.34 ms / 161 tokens 0.32.444.086 I slot print_timing: id 1 | task 10 | graphs reused = 1 0.32.444.086 I slot print_timing: id 1 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.444.097 I slot release: id 1 | task 10 | stop processing: n_tokens = 169, truncated = 0 0.32.445.184 I slot print_timing: id 2 | task 11 | prompt eval time = 1307.65 ms / 204 tokens ( 6.41 ms per token, 156.00 tokens per second) 0.32.445.186 I slot print_timing: id 2 | task 11 | eval time = 37.62 ms / 2 tokens ( 37.62 ms per token, 26.58 tokens per second) 0.32.445.187 I slot print_timing: id 2 | task 11 | total time = 1345.28 ms / 206 tokens 0.32.445.187 I slot print_timing: id 2 | task 11 | graphs reused = 1 0.32.445.187 I slot print_timing: id 2 | task 11 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.445.202 I slot release: id 2 | task 11 | stop processing: n_tokens = 214, truncated = 0 0.32.446.297 I slot print_timing: id 3 | task 12 | prompt eval time = 1308.71 ms / 110 tokens ( 11.90 ms per token, 84.05 tokens per second) 0.32.446.299 I slot print_timing: id 3 | task 12 | eval time = 37.56 ms / 2 tokens ( 37.56 ms per token, 26.62 tokens per second) 0.32.446.299 I slot print_timing: id 3 | task 12 | total time = 1346.27 ms / 112 tokens 0.32.446.300 I slot print_timing: id 3 | task 12 | graphs reused = 1 0.32.446.300 I slot print_timing: id 3 | task 12 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.446.311 I slot release: id 3 | task 12 | stop processing: n_tokens = 120, truncated = 0 0.32.447.306 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.297 (> 0.100 thold), f_keep = 0.225 0.32.450.630 I slot launch_slot_: id 1 | task 17 | processing task, is_child = 0 0.32.459.855 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.213 0.32.459.923 I slot launch_slot_: id 0 | task 18 | processing task, is_child = 0 0.32.459.980 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.173 0.32.460.043 I slot launch_slot_: id 2 | task 19 | processing task, is_child = 0 0.32.460.067 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.287 (> 0.100 thold), f_keep = 0.308 0.32.460.126 I slot launch_slot_: id 3 | task 20 | processing task, is_child = 0 0.33.541.698 I slot print_timing: id 0 | task 18 | prompt eval time = 1044.18 ms / 127 tokens ( 8.22 ms per token, 121.63 tokens per second) 0.33.541.702 I slot print_timing: id 0 | task 18 | eval time = 37.38 ms / 2 tokens ( 37.38 ms per token, 26.75 tokens per second) 0.33.541.702 I slot print_timing: id 0 | task 18 | total time = 1081.56 ms / 129 tokens 0.33.541.703 I slot print_timing: id 0 | task 18 | graphs reused = 1 0.33.541.703 I slot print_timing: id 0 | task 18 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.541.730 I slot release: id 0 | task 18 | stop processing: n_tokens = 137, truncated = 0 0.33.542.853 I slot print_timing: id 1 | task 17 | prompt eval time = 1045.06 ms / 119 tokens ( 8.78 ms per token, 113.87 tokens per second) 0.33.542.856 I slot print_timing: id 1 | task 17 | eval time = 37.47 ms / 2 tokens ( 37.47 ms per token, 26.69 tokens per second) 0.33.542.856 I slot print_timing: id 1 | task 17 | total time = 1082.53 ms / 121 tokens 0.33.542.857 I slot print_timing: id 1 | task 17 | graphs reused = 1 0.33.542.857 I slot print_timing: id 1 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.542.868 I slot release: id 1 | task 17 | stop processing: n_tokens = 129, truncated = 0 0.33.543.947 I slot print_timing: id 2 | task 19 | prompt eval time = 1045.94 ms / 151 tokens ( 6.93 ms per token, 144.37 tokens per second) 0.33.543.949 I slot print_timing: id 2 | task 19 | eval time = 37.52 ms / 2 tokens ( 37.52 ms per token, 26.65 tokens per second) 0.33.543.950 I slot print_timing: id 2 | task 19 | total time = 1083.46 ms / 153 tokens 0.33.543.950 I slot print_timing: id 2 | task 19 | graphs reused = 1 0.33.543.950 I slot print_timing: id 2 | task 19 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.543.961 I slot release: id 2 | task 19 | stop processing: n_tokens = 161, truncated = 0 0.33.545.057 I slot print_timing: id 3 | task 20 | prompt eval time = 1046.84 ms / 120 tokens ( 8.72 ms per token, 114.63 tokens per second) 0.33.545.060 I slot print_timing: id 3 | task 20 | eval time = 37.58 ms / 2 tokens ( 37.58 ms per token, 26.61 tokens per second) 0.33.545.061 I slot print_timing: id 3 | task 20 | total time = 1084.41 ms / 122 tokens 0.33.545.061 I slot print_timing: id 3 | task 20 | graphs reused = 1 0.33.545.061 I slot print_timing: id 3 | task 20 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.545.071 I slot release: id 3 | task 20 | stop processing: n_tokens = 130, truncated = 0 0.33.546.788 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.270 0.33.547.931 I slot launch_slot_: id 0 | task 25 | processing task, is_child = 0 0.33.556.168 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.287 0.33.556.245 I slot launch_slot_: id 1 | task 26 | processing task, is_child = 0 0.33.556.292 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.230 0.33.556.348 I slot launch_slot_: id 2 | task 27 | processing task, is_child = 0 0.33.556.372 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 0.33.556.427 I slot launch_slot_: id 3 | task 28 | processing task, is_child = 0 0.34.816.678 I slot print_timing: id 0 | task 25 | prompt eval time = 1222.25 ms / 138 tokens ( 8.86 ms per token, 112.91 tokens per second) 0.34.816.680 I slot print_timing: id 0 | task 25 | eval time = 37.99 ms / 2 tokens ( 37.99 ms per token, 26.32 tokens per second) 0.34.816.681 I slot print_timing: id 0 | task 25 | total time = 1260.24 ms / 140 tokens 0.34.816.681 I slot print_timing: id 0 | task 25 | graphs reused = 1 0.34.816.682 I slot print_timing: id 0 | task 25 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.816.715 I slot release: id 0 | task 25 | stop processing: n_tokens = 148, truncated = 0 0.34.817.812 I slot print_timing: id 1 | task 26 | prompt eval time = 1223.27 ms / 145 tokens ( 8.44 ms per token, 118.53 tokens per second) 0.34.817.813 I slot print_timing: id 1 | task 26 | eval time = 37.97 ms / 2 tokens ( 37.97 ms per token, 26.34 tokens per second) 0.34.817.814 I slot print_timing: id 1 | task 26 | total time = 1261.24 ms / 147 tokens 0.34.817.814 I slot print_timing: id 1 | task 26 | graphs reused = 1 0.34.817.814 I slot print_timing: id 1 | task 26 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.817.825 I slot release: id 1 | task 26 | stop processing: n_tokens = 155, truncated = 0 0.34.818.929 I slot print_timing: id 2 | task 27 | prompt eval time = 1224.36 ms / 184 tokens ( 6.65 ms per token, 150.28 tokens per second) 0.34.818.931 I slot print_timing: id 2 | task 27 | eval time = 37.88 ms / 2 tokens ( 37.88 ms per token, 26.40 tokens per second) 0.34.818.931 I slot print_timing: id 2 | task 27 | total time = 1262.24 ms / 186 tokens 0.34.818.931 I slot print_timing: id 2 | task 27 | graphs reused = 1 0.34.818.931 I slot print_timing: id 2 | task 27 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.818.943 I slot release: id 2 | task 27 | stop processing: n_tokens = 194, truncated = 0 0.34.820.040 I slot print_timing: id 3 | task 28 | prompt eval time = 1225.44 ms / 122 tokens ( 10.04 ms per token, 99.56 tokens per second) 0.34.820.044 I slot print_timing: id 3 | task 28 | eval time = 37.78 ms / 2 tokens ( 37.78 ms per token, 26.47 tokens per second) 0.34.820.045 I slot print_timing: id 3 | task 28 | total time = 1263.22 ms / 124 tokens 0.34.820.045 I slot print_timing: id 3 | task 28 | graphs reused = 1 0.34.820.045 I slot print_timing: id 3 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.820.053 I slot release: id 3 | task 28 | stop processing: n_tokens = 132, truncated = 0 0.34.820.694 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.250 0.34.823.948 I slot launch_slot_: id 0 | task 33 | processing task, is_child = 0 0.34.831.727 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.239 0.34.831.793 I slot launch_slot_: id 1 | task 34 | processing task, is_child = 0 0.34.831.847 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.191 0.34.831.910 I slot launch_slot_: id 2 | task 35 | processing task, is_child = 0 0.34.831.935 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 0.34.832.466 I slot launch_slot_: id 3 | task 36 | processing task, is_child = 0 0.36.082.128 I slot print_timing: id 1 | task 34 | prompt eval time = 1212.06 ms / 149 tokens ( 8.13 ms per token, 122.93 tokens per second) 0.36.082.131 I slot print_timing: id 1 | task 34 | eval time = 37.42 ms / 2 tokens ( 37.42 ms per token, 26.72 tokens per second) 0.36.082.131 I slot print_timing: id 1 | task 34 | total time = 1249.48 ms / 151 tokens 0.36.082.132 I slot print_timing: id 1 | task 34 | graphs reused = 1 0.36.082.132 I slot print_timing: id 1 | task 34 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.082.161 I slot release: id 1 | task 34 | stop processing: n_tokens = 159, truncated = 0 0.36.083.303 I slot print_timing: id 2 | task 35 | prompt eval time = 1212.95 ms / 181 tokens ( 6.70 ms per token, 149.22 tokens per second) 0.36.083.305 I slot print_timing: id 2 | task 35 | eval time = 37.55 ms / 2 tokens ( 37.55 ms per token, 26.63 tokens per second) 0.36.083.305 I slot print_timing: id 2 | task 35 | total time = 1250.50 ms / 183 tokens 0.36.083.306 I slot print_timing: id 2 | task 35 | graphs reused = 1 0.36.083.306 I slot print_timing: id 2 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.083.326 I slot release: id 2 | task 35 | stop processing: n_tokens = 191, truncated = 0 0.36.084.442 I slot print_timing: id 3 | task 36 | prompt eval time = 1213.87 ms / 127 tokens ( 9.56 ms per token, 104.62 tokens per second) 0.36.084.444 I slot print_timing: id 3 | task 36 | eval time = 37.61 ms / 2 tokens ( 37.61 ms per token, 26.59 tokens per second) 0.36.084.444 I slot print_timing: id 3 | task 36 | total time = 1251.48 ms / 129 tokens 0.36.084.444 I slot print_timing: id 3 | task 36 | graphs reused = 1 0.36.084.445 I slot print_timing: id 3 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.084.458 I slot release: id 3 | task 36 | stop processing: n_tokens = 137, truncated = 0 0.36.104.966 I slot print_timing: id 0 | task 33 | prompt eval time = 1211.14 ms / 133 tokens ( 9.11 ms per token, 109.81 tokens per second) 0.36.104.969 I slot print_timing: id 0 | task 33 | eval time = 61.35 ms / 3 tokens ( 30.68 ms per token, 32.60 tokens per second) 0.36.104.969 I slot print_timing: id 0 | task 33 | total time = 1272.49 ms / 136 tokens 0.36.104.970 I slot print_timing: id 0 | task 33 | graphs reused = 1 0.36.104.970 I slot print_timing: id 0 | task 33 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.104.983 I slot release: id 0 | task 33 | stop processing: n_tokens = 144, truncated = 0 0.36.104.989 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.298 (> 0.100 thold), f_keep = 0.257 0.36.108.059 I slot launch_slot_: id 0 | task 42 | processing task, is_child = 0 0.36.117.579 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.233 0.36.117.647 I slot launch_slot_: id 1 | task 43 | processing task, is_child = 0 0.36.117.700 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.199 0.36.117.761 I slot launch_slot_: id 2 | task 44 | processing task, is_child = 0 0.36.117.789 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 0.36.117.849 I slot launch_slot_: id 3 | task 45 | processing task, is_child = 0 0.37.255.748 I slot print_timing: id 0 | task 42 | prompt eval time = 1100.07 ms / 115 tokens ( 9.57 ms per token, 104.54 tokens per second) 0.37.255.750 I slot print_timing: id 0 | task 42 | eval time = 37.82 ms / 2 tokens ( 37.82 ms per token, 26.44 tokens per second) 0.37.255.751 I slot print_timing: id 0 | task 42 | total time = 1137.89 ms / 117 tokens 0.37.255.751 I slot print_timing: id 0 | task 42 | graphs reused = 1 0.37.255.752 I slot print_timing: id 0 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.255.770 I slot release: id 0 | task 42 | stop processing: n_tokens = 125, truncated = 0 0.37.256.887 I slot print_timing: id 1 | task 43 | prompt eval time = 1101.11 ms / 144 tokens ( 7.65 ms per token, 130.78 tokens per second) 0.37.256.888 I slot print_timing: id 1 | task 43 | eval time = 37.78 ms / 2 tokens ( 37.78 ms per token, 26.47 tokens per second) 0.37.256.889 I slot print_timing: id 1 | task 43 | total time = 1138.89 ms / 146 tokens 0.37.256.889 I slot print_timing: id 1 | task 43 | graphs reused = 1 0.37.256.889 I slot print_timing: id 1 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.256.901 I slot release: id 1 | task 43 | stop processing: n_tokens = 154, truncated = 0 0.37.258.004 I slot print_timing: id 2 | task 44 | prompt eval time = 1102.10 ms / 148 tokens ( 7.45 ms per token, 134.29 tokens per second) 0.37.258.005 I slot print_timing: id 2 | task 44 | eval time = 37.80 ms / 2 tokens ( 37.80 ms per token, 26.46 tokens per second) 0.37.258.006 I slot print_timing: id 2 | task 44 | total time = 1139.89 ms / 150 tokens 0.37.258.006 I slot print_timing: id 2 | task 44 | graphs reused = 1 0.37.258.006 I slot print_timing: id 2 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.258.016 I slot release: id 2 | task 44 | stop processing: n_tokens = 158, truncated = 0 0.37.259.102 I slot print_timing: id 3 | task 45 | prompt eval time = 1103.21 ms / 122 tokens ( 9.04 ms per token, 110.59 tokens per second) 0.37.259.104 I slot print_timing: id 3 | task 45 | eval time = 37.65 ms / 2 tokens ( 37.65 ms per token, 26.56 tokens per second) 0.37.259.104 I slot print_timing: id 3 | task 45 | total time = 1140.86 ms / 124 tokens 0.37.259.104 I slot print_timing: id 3 | task 45 | graphs reused = 1 0.37.259.105 I slot print_timing: id 3 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.259.112 I slot release: id 3 | task 45 | stop processing: n_tokens = 132, truncated = 0 0.37.259.484 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 0.37.260.968 I slot launch_slot_: id 3 | task 50 | processing task, is_child = 0 0.37.267.303 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 0.37.267.369 I slot launch_slot_: id 0 | task 51 | processing task, is_child = 0 0.37.267.418 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 0.37.267.476 I slot launch_slot_: id 1 | task 52 | processing task, is_child = 0 0.37.267.502 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 0.37.267.554 I slot launch_slot_: id 2 | task 53 | processing task, is_child = 0 0.38.357.434 I slot print_timing: id 0 | task 51 | prompt eval time = 1052.70 ms / 124 tokens ( 8.49 ms per token, 117.79 tokens per second) 0.38.357.437 I slot print_timing: id 0 | task 51 | eval time = 37.17 ms / 2 tokens ( 37.17 ms per token, 26.90 tokens per second) 0.38.357.437 I slot print_timing: id 0 | task 51 | total time = 1089.87 ms / 126 tokens 0.38.357.438 I slot print_timing: id 0 | task 51 | graphs reused = 1 0.38.357.438 I slot print_timing: id 0 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.357.459 I slot release: id 0 | task 51 | stop processing: n_tokens = 134, truncated = 0 0.38.358.583 I slot print_timing: id 1 | task 52 | prompt eval time = 1053.63 ms / 148 tokens ( 7.12 ms per token, 140.47 tokens per second) 0.38.358.585 I slot print_timing: id 1 | task 52 | eval time = 37.24 ms / 2 tokens ( 37.24 ms per token, 26.86 tokens per second) 0.38.358.585 I slot print_timing: id 1 | task 52 | total time = 1090.87 ms / 150 tokens 0.38.358.586 I slot print_timing: id 1 | task 52 | graphs reused = 1 0.38.358.586 I slot print_timing: id 1 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.358.606 I slot release: id 1 | task 52 | stop processing: n_tokens = 158, truncated = 0 0.38.359.673 I slot print_timing: id 2 | task 53 | prompt eval time = 1054.51 ms / 111 tokens ( 9.50 ms per token, 105.26 tokens per second) 0.38.359.674 I slot print_timing: id 2 | task 53 | eval time = 37.29 ms / 2 tokens ( 37.29 ms per token, 26.82 tokens per second) 0.38.359.675 I slot print_timing: id 2 | task 53 | total time = 1091.79 ms / 113 tokens 0.38.359.675 I slot print_timing: id 2 | task 53 | graphs reused = 1 0.38.359.675 I slot print_timing: id 2 | task 53 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.359.683 I slot release: id 2 | task 53 | stop processing: n_tokens = 121, truncated = 0 0.38.381.428 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 0.38.383.716 I slot launch_slot_: id 0 | task 59 | processing task, is_child = 0 0.38.389.408 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.234 0.38.390.043 I slot launch_slot_: id 1 | task 60 | processing task, is_child = 0 0.38.390.074 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.306 0.38.390.140 I slot launch_slot_: id 2 | task 61 | processing task, is_child = 0 0.39.173.681 I slot print_timing: id 3 | task 50 | prompt eval time = 1055.38 ms / 114 tokens ( 9.26 ms per token, 108.02 tokens per second) 0.39.173.684 I slot print_timing: id 3 | task 50 | eval time = 850.26 ms / 5 tokens ( 212.56 ms per token, 4.70 tokens per second) 0.39.173.684 I slot print_timing: id 3 | task 50 | total time = 1905.64 ms / 119 tokens 0.39.173.684 I slot print_timing: id 3 | task 50 | graphs reused = 2 0.39.173.685 I slot print_timing: id 3 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.173.706 I slot release: id 3 | task 50 | stop processing: n_tokens = 127, truncated = 0 0.39.230.718 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.311 (> 0.100 thold), f_keep = 0.299 0.39.231.821 I slot launch_slot_: id 3 | task 65 | processing task, is_child = 0 0.39.266.164 I slot print_timing: id 0 | task 59 | prompt eval time = 838.18 ms / 106 tokens ( 7.91 ms per token, 126.46 tokens per second) 0.39.266.166 I slot print_timing: id 0 | task 59 | eval time = 37.83 ms / 2 tokens ( 37.83 ms per token, 26.43 tokens per second) 0.39.266.167 I slot print_timing: id 0 | task 59 | total time = 876.01 ms / 108 tokens 0.39.266.167 I slot print_timing: id 0 | task 59 | graphs reused = 2 0.39.266.168 I slot print_timing: id 0 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.266.184 I slot release: id 0 | task 59 | stop processing: n_tokens = 116, truncated = 0 0.39.267.272 I slot print_timing: id 1 | task 60 | prompt eval time = 839.23 ms / 131 tokens ( 6.41 ms per token, 156.10 tokens per second) 0.39.267.274 I slot print_timing: id 1 | task 60 | eval time = 37.75 ms / 2 tokens ( 37.75 ms per token, 26.49 tokens per second) 0.39.267.274 I slot print_timing: id 1 | task 60 | total time = 876.98 ms / 133 tokens 0.39.267.275 I slot print_timing: id 1 | task 60 | graphs reused = 2 0.39.267.275 I slot print_timing: id 1 | task 60 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.267.285 I slot release: id 1 | task 60 | stop processing: n_tokens = 141, truncated = 0 0.39.268.358 I slot print_timing: id 2 | task 61 | prompt eval time = 840.28 ms / 138 tokens ( 6.09 ms per token, 164.23 tokens per second) 0.39.268.360 I slot print_timing: id 2 | task 61 | eval time = 37.64 ms / 2 tokens ( 37.64 ms per token, 26.56 tokens per second) 0.39.268.360 I slot print_timing: id 2 | task 61 | total time = 877.93 ms / 140 tokens 0.39.268.360 I slot print_timing: id 2 | task 61 | graphs reused = 2 0.39.268.361 I slot print_timing: id 2 | task 61 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.268.371 I slot release: id 2 | task 61 | stop processing: n_tokens = 148, truncated = 0 0.39.536.317 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.319 0.39.540.554 I slot launch_slot_: id 0 | task 68 | processing task, is_child = 0 0.39.546.900 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.262 0.39.547.448 I slot launch_slot_: id 1 | task 70 | processing task, is_child = 0 0.39.547.479 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.250 0.39.547.543 I slot launch_slot_: id 2 | task 71 | processing task, is_child = 0 0.40.664.811 I slot print_timing: id 0 | task 68 | prompt eval time = 1079.52 ms / 181 tokens ( 5.96 ms per token, 167.67 tokens per second) 0.40.664.815 I slot print_timing: id 0 | task 68 | eval time = 37.74 ms / 2 tokens ( 37.74 ms per token, 26.49 tokens per second) 0.40.664.815 I slot print_timing: id 0 | task 68 | total time = 1117.26 ms / 183 tokens 0.40.664.816 I slot print_timing: id 0 | task 68 | graphs reused = 2 0.40.664.816 I slot print_timing: id 0 | task 68 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.664.839 I slot release: id 0 | task 68 | stop processing: n_tokens = 191, truncated = 0 0.40.665.986 I slot print_timing: id 1 | task 70 | prompt eval time = 1080.60 ms / 194 tokens ( 5.57 ms per token, 179.53 tokens per second) 0.40.665.988 I slot print_timing: id 1 | task 70 | eval time = 37.72 ms / 2 tokens ( 37.72 ms per token, 26.51 tokens per second) 0.40.665.988 I slot print_timing: id 1 | task 70 | total time = 1118.32 ms / 196 tokens 0.40.665.989 I slot print_timing: id 1 | task 70 | graphs reused = 2 0.40.665.989 I slot print_timing: id 1 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.666.002 I slot release: id 1 | task 70 | stop processing: n_tokens = 204, truncated = 0 0.40.667.079 I slot print_timing: id 2 | task 71 | prompt eval time = 1081.56 ms / 134 tokens ( 8.07 ms per token, 123.90 tokens per second) 0.40.667.081 I slot print_timing: id 2 | task 71 | eval time = 37.75 ms / 2 tokens ( 37.75 ms per token, 26.49 tokens per second) 0.40.667.081 I slot print_timing: id 2 | task 71 | total time = 1119.31 ms / 136 tokens 0.40.667.082 I slot print_timing: id 2 | task 71 | graphs reused = 2 0.40.667.082 I slot print_timing: id 2 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.667.095 I slot release: id 2 | task 71 | stop processing: n_tokens = 144, truncated = 0 0.40.668.221 I slot print_timing: id 3 | task 65 | prompt eval time = 304.49 ms / 113 tokens ( 2.69 ms per token, 371.12 tokens per second) 0.40.668.223 I slot print_timing: id 3 | task 65 | eval time = 1131.91 ms / 5 tokens ( 282.98 ms per token, 3.53 tokens per second) 0.40.668.224 I slot print_timing: id 3 | task 65 | total time = 1436.39 ms / 118 tokens 0.40.668.224 I slot print_timing: id 3 | task 65 | graphs reused = 2 0.40.668.224 I slot print_timing: id 3 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.668.235 I slot release: id 3 | task 65 | stop processing: n_tokens = 126, truncated = 0 0.40.670.173 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.194 0.40.673.888 I slot launch_slot_: id 0 | task 76 | processing task, is_child = 0 0.40.681.541 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.181 0.40.681.613 I slot launch_slot_: id 1 | task 77 | processing task, is_child = 0 0.40.681.667 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.257 0.40.681.724 I slot launch_slot_: id 2 | task 78 | processing task, is_child = 0 0.40.681.754 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.302 0.40.681.808 I slot launch_slot_: id 3 | task 79 | processing task, is_child = 0 0.42.026.209 I slot print_timing: id 0 | task 76 | prompt eval time = 1306.79 ms / 171 tokens ( 7.64 ms per token, 130.86 tokens per second) 0.42.026.211 I slot print_timing: id 0 | task 76 | eval time = 37.60 ms / 2 tokens ( 37.60 ms per token, 26.60 tokens per second) 0.42.026.212 I slot print_timing: id 0 | task 76 | total time = 1344.39 ms / 173 tokens 0.42.026.212 I slot print_timing: id 0 | task 76 | graphs reused = 2 0.42.026.213 I slot print_timing: id 0 | task 76 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.026.246 I slot release: id 0 | task 76 | stop processing: n_tokens = 181, truncated = 0 0.42.027.410 I slot print_timing: id 1 | task 77 | prompt eval time = 1307.72 ms / 152 tokens ( 8.60 ms per token, 116.23 tokens per second) 0.42.027.412 I slot print_timing: id 1 | task 77 | eval time = 37.74 ms / 2 tokens ( 37.74 ms per token, 26.50 tokens per second) 0.42.027.412 I slot print_timing: id 1 | task 77 | total time = 1345.46 ms / 154 tokens 0.42.027.412 I slot print_timing: id 1 | task 77 | graphs reused = 2 0.42.027.413 I slot print_timing: id 1 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.027.425 I slot release: id 1 | task 77 | stop processing: n_tokens = 162, truncated = 0 0.42.028.536 I slot print_timing: id 2 | task 78 | prompt eval time = 1308.66 ms / 168 tokens ( 7.79 ms per token, 128.38 tokens per second) 0.42.028.538 I slot print_timing: id 2 | task 78 | eval time = 37.78 ms / 2 tokens ( 37.78 ms per token, 26.47 tokens per second) 0.42.028.538 I slot print_timing: id 2 | task 78 | total time = 1346.44 ms / 170 tokens 0.42.028.539 I slot print_timing: id 2 | task 78 | graphs reused = 2 0.42.028.539 I slot print_timing: id 2 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.028.552 I slot release: id 2 | task 78 | stop processing: n_tokens = 178, truncated = 0 0.42.029.667 I slot print_timing: id 3 | task 79 | prompt eval time = 1309.71 ms / 143 tokens ( 9.16 ms per token, 109.18 tokens per second) 0.42.029.670 I slot print_timing: id 3 | task 79 | eval time = 37.74 ms / 2 tokens ( 37.74 ms per token, 26.50 tokens per second) 0.42.029.670 I slot print_timing: id 3 | task 79 | total time = 1347.45 ms / 145 tokens 0.42.029.671 I slot print_timing: id 3 | task 79 | graphs reused = 2 0.42.029.671 I slot print_timing: id 3 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.029.684 I slot release: id 3 | task 79 | stop processing: n_tokens = 153, truncated = 0 0.42.031.528 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.204 0.42.035.232 I slot launch_slot_: id 0 | task 84 | processing task, is_child = 0 0.42.044.943 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.228 0.42.045.555 I slot launch_slot_: id 1 | task 85 | processing task, is_child = 0 0.42.045.611 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.208 0.42.045.671 I slot launch_slot_: id 2 | task 86 | processing task, is_child = 0 0.42.045.700 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.322 (> 0.100 thold), f_keep = 0.248 0.42.045.770 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 0.43.171.536 I slot print_timing: id 0 | task 84 | prompt eval time = 1088.06 ms / 130 tokens ( 8.37 ms per token, 119.48 tokens per second) 0.43.171.538 I slot print_timing: id 0 | task 84 | eval time = 37.70 ms / 2 tokens ( 37.70 ms per token, 26.53 tokens per second) 0.43.171.539 I slot print_timing: id 0 | task 84 | total time = 1125.76 ms / 132 tokens 0.43.171.539 I slot print_timing: id 0 | task 84 | graphs reused = 2 0.43.171.540 I slot print_timing: id 0 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.171.568 I slot release: id 0 | task 84 | stop processing: n_tokens = 140, truncated = 0 0.43.172.711 I slot print_timing: id 1 | task 85 | prompt eval time = 1089.05 ms / 125 tokens ( 8.71 ms per token, 114.78 tokens per second) 0.43.172.713 I slot print_timing: id 1 | task 85 | eval time = 37.76 ms / 2 tokens ( 37.76 ms per token, 26.48 tokens per second) 0.43.172.714 I slot print_timing: id 1 | task 85 | total time = 1126.80 ms / 127 tokens 0.43.172.714 I slot print_timing: id 1 | task 85 | graphs reused = 2 0.43.172.714 I slot print_timing: id 1 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.172.732 I slot release: id 1 | task 85 | stop processing: n_tokens = 135, truncated = 0 0.43.173.855 I slot print_timing: id 2 | task 86 | prompt eval time = 1090.02 ms / 166 tokens ( 6.57 ms per token, 152.29 tokens per second) 0.43.173.859 I slot print_timing: id 2 | task 86 | eval time = 37.82 ms / 2 tokens ( 37.82 ms per token, 26.44 tokens per second) 0.43.173.859 I slot print_timing: id 2 | task 86 | total time = 1127.84 ms / 168 tokens 0.43.173.859 I slot print_timing: id 2 | task 86 | graphs reused = 2 0.43.173.860 I slot print_timing: id 2 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.173.872 I slot release: id 2 | task 86 | stop processing: n_tokens = 176, truncated = 0 0.43.174.984 I slot print_timing: id 3 | task 87 | prompt eval time = 1091.10 ms / 109 tokens ( 10.01 ms per token, 99.90 tokens per second) 0.43.174.987 I slot print_timing: id 3 | task 87 | eval time = 37.76 ms / 2 tokens ( 37.76 ms per token, 26.48 tokens per second) 0.43.174.987 I slot print_timing: id 3 | task 87 | total time = 1128.86 ms / 111 tokens 0.43.174.987 I slot print_timing: id 3 | task 87 | graphs reused = 2 0.43.174.988 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.174.996 I slot release: id 3 | task 87 | stop processing: n_tokens = 119, truncated = 0 0.43.176.188 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.222 0.43.178.927 I slot launch_slot_: id 2 | task 92 | processing task, is_child = 0 0.43.183.438 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 0.43.183.510 I slot launch_slot_: id 0 | task 93 | processing task, is_child = 0 0.43.183.560 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.281 0.43.183.621 I slot launch_slot_: id 1 | task 94 | processing task, is_child = 0 0.43.183.645 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.311 0.43.183.697 I slot launch_slot_: id 3 | task 95 | processing task, is_child = 0 0.44.445.026 I slot print_timing: id 0 | task 93 | prompt eval time = 1223.09 ms / 170 tokens ( 7.19 ms per token, 138.99 tokens per second) 0.44.445.030 I slot print_timing: id 0 | task 93 | eval time = 38.23 ms / 2 tokens ( 38.23 ms per token, 26.15 tokens per second) 0.44.445.030 I slot print_timing: id 0 | task 93 | total time = 1261.32 ms / 172 tokens 0.44.445.031 I slot print_timing: id 0 | task 93 | graphs reused = 2 0.44.445.031 I slot print_timing: id 0 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.445.052 I slot release: id 0 | task 93 | stop processing: n_tokens = 180, truncated = 0 0.44.446.156 I slot print_timing: id 1 | task 94 | prompt eval time = 1224.37 ms / 167 tokens ( 7.33 ms per token, 136.40 tokens per second) 0.44.446.158 I slot print_timing: id 1 | task 94 | eval time = 37.96 ms / 2 tokens ( 37.96 ms per token, 26.35 tokens per second) 0.44.446.158 I slot print_timing: id 1 | task 94 | total time = 1262.32 ms / 169 tokens 0.44.446.158 I slot print_timing: id 1 | task 94 | graphs reused = 2 0.44.446.159 I slot print_timing: id 1 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.446.172 I slot release: id 1 | task 94 | stop processing: n_tokens = 177, truncated = 0 0.44.447.290 I slot print_timing: id 2 | task 92 | prompt eval time = 1225.46 ms / 160 tokens ( 7.66 ms per token, 130.56 tokens per second) 0.44.447.292 I slot print_timing: id 2 | task 92 | eval time = 37.83 ms / 2 tokens ( 37.83 ms per token, 26.43 tokens per second) 0.44.447.293 I slot print_timing: id 2 | task 92 | total time = 1263.29 ms / 162 tokens 0.44.447.293 I slot print_timing: id 2 | task 92 | graphs reused = 2 0.44.447.293 I slot print_timing: id 2 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.447.308 I slot release: id 2 | task 92 | stop processing: n_tokens = 170, truncated = 0 0.44.448.412 I slot print_timing: id 3 | task 95 | prompt eval time = 1226.60 ms / 113 tokens ( 10.85 ms per token, 92.12 tokens per second) 0.44.448.414 I slot print_timing: id 3 | task 95 | eval time = 37.65 ms / 2 tokens ( 37.65 ms per token, 26.56 tokens per second) 0.44.448.415 I slot print_timing: id 3 | task 95 | total time = 1264.25 ms / 115 tokens 0.44.448.415 I slot print_timing: id 3 | task 95 | graphs reused = 2 0.44.448.415 I slot print_timing: id 3 | task 95 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.448.425 I slot release: id 3 | task 95 | stop processing: n_tokens = 123, truncated = 0 0.44.449.035 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.317 (> 0.100 thold), f_keep = 0.215 0.44.452.466 I slot launch_slot_: id 1 | task 100 | processing task, is_child = 0 0.44.460.640 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 0.44.460.716 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.44.460.769 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.218 0.44.461.305 I slot launch_slot_: id 2 | task 102 | processing task, is_child = 0 0.44.461.331 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.301 0.44.461.382 I slot launch_slot_: id 3 | task 103 | processing task, is_child = 0 0.45.606.954 I slot print_timing: id 0 | task 101 | prompt eval time = 1107.97 ms / 136 tokens ( 8.15 ms per token, 122.75 tokens per second) 0.45.606.957 I slot print_timing: id 0 | task 101 | eval time = 37.59 ms / 2 tokens ( 37.59 ms per token, 26.60 tokens per second) 0.45.606.958 I slot print_timing: id 0 | task 101 | total time = 1145.56 ms / 138 tokens 0.45.606.958 I slot print_timing: id 0 | task 101 | graphs reused = 2 0.45.606.958 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.606.976 I slot release: id 0 | task 101 | stop processing: n_tokens = 146, truncated = 0 0.45.608.075 I slot print_timing: id 1 | task 100 | prompt eval time = 1108.93 ms / 111 tokens ( 9.99 ms per token, 100.10 tokens per second) 0.45.608.077 I slot print_timing: id 1 | task 100 | eval time = 37.64 ms / 2 tokens ( 37.64 ms per token, 26.57 tokens per second) 0.45.608.077 I slot print_timing: id 1 | task 100 | total time = 1146.56 ms / 113 tokens 0.45.608.078 I slot print_timing: id 1 | task 100 | graphs reused = 2 0.45.608.078 I slot print_timing: id 1 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.608.088 I slot release: id 1 | task 100 | stop processing: n_tokens = 121, truncated = 0 0.45.610.272 I slot print_timing: id 3 | task 103 | prompt eval time = 1110.94 ms / 149 tokens ( 7.46 ms per token, 134.12 tokens per second) 0.45.610.274 I slot print_timing: id 3 | task 103 | eval time = 37.59 ms / 2 tokens ( 37.59 ms per token, 26.60 tokens per second) 0.45.610.274 I slot print_timing: id 3 | task 103 | total time = 1148.53 ms / 151 tokens 0.45.610.275 I slot print_timing: id 3 | task 103 | graphs reused = 2 0.45.610.275 I slot print_timing: id 3 | task 103 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.610.284 I slot release: id 3 | task 103 | stop processing: n_tokens = 159, truncated = 0 0.45.630.840 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.253 0.45.633.311 I slot launch_slot_: id 0 | task 110 | processing task, is_child = 0 0.45.637.546 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.306 0.45.638.067 I slot launch_slot_: id 1 | task 109 | processing task, is_child = 0 0.45.638.097 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.233 0.45.638.674 I slot launch_slot_: id 3 | task 111 | processing task, is_child = 0 0.46.489.652 I slot print_timing: id 2 | task 102 | prompt eval time = 1109.98 ms / 126 tokens ( 8.81 ms per token, 113.52 tokens per second) 0.46.489.654 I slot print_timing: id 2 | task 102 | eval time = 918.03 ms / 5 tokens ( 229.51 ms per token, 4.36 tokens per second) 0.46.489.655 I slot print_timing: id 2 | task 102 | total time = 2028.02 ms / 131 tokens 0.46.489.656 I slot print_timing: id 2 | task 102 | graphs reused = 2 0.46.489.656 I slot print_timing: id 2 | task 102 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.489.680 I slot release: id 2 | task 102 | stop processing: n_tokens = 139, truncated = 0 0.46.562.706 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.266 0.46.564.607 I slot launch_slot_: id 2 | task 115 | processing task, is_child = 0 0.46.616.925 I slot print_timing: id 0 | task 110 | prompt eval time = 921.56 ms / 124 tokens ( 7.43 ms per token, 134.55 tokens per second) 0.46.616.927 I slot print_timing: id 0 | task 110 | eval time = 56.69 ms / 2 tokens ( 56.69 ms per token, 17.64 tokens per second) 0.46.616.927 I slot print_timing: id 0 | task 110 | total time = 978.24 ms / 126 tokens 0.46.616.927 I slot print_timing: id 0 | task 110 | graphs reused = 2 0.46.616.928 I slot print_timing: id 0 | task 110 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.616.944 I slot release: id 0 | task 110 | stop processing: n_tokens = 134, truncated = 0 0.46.618.042 I slot print_timing: id 1 | task 109 | prompt eval time = 922.63 ms / 148 tokens ( 6.23 ms per token, 160.41 tokens per second) 0.46.618.046 I slot print_timing: id 1 | task 109 | eval time = 56.61 ms / 2 tokens ( 56.61 ms per token, 17.67 tokens per second) 0.46.618.047 I slot print_timing: id 1 | task 109 | total time = 979.24 ms / 150 tokens 0.46.618.047 I slot print_timing: id 1 | task 109 | graphs reused = 2 0.46.618.047 I slot print_timing: id 1 | task 109 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.618.059 I slot release: id 1 | task 109 | stop processing: n_tokens = 158, truncated = 0 0.46.619.151 I slot print_timing: id 3 | task 111 | prompt eval time = 923.78 ms / 126 tokens ( 7.33 ms per token, 136.40 tokens per second) 0.46.619.152 I slot print_timing: id 3 | task 111 | eval time = 56.45 ms / 2 tokens ( 56.45 ms per token, 17.72 tokens per second) 0.46.619.153 I slot print_timing: id 3 | task 111 | total time = 980.22 ms / 128 tokens 0.46.619.153 I slot print_timing: id 3 | task 111 | graphs reused = 2 0.46.619.153 I slot print_timing: id 3 | task 111 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.619.166 I slot release: id 3 | task 111 | stop processing: n_tokens = 136, truncated = 0 0.46.621.183 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.241 0.46.905.009 I slot launch_slot_: id 1 | task 118 | processing task, is_child = 0 0.46.909.285 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.311 (> 0.100 thold), f_keep = 0.276 0.46.909.939 I slot launch_slot_: id 0 | task 119 | processing task, is_child = 0 0.46.909.971 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.287 (> 0.100 thold), f_keep = 0.272 0.46.910.495 I slot launch_slot_: id 3 | task 120 | processing task, is_child = 0 0.47.714.634 I slot print_timing: id 2 | task 115 | prompt eval time = 408.62 ms / 143 tokens ( 2.86 ms per token, 349.96 tokens per second) 0.47.714.637 I slot print_timing: id 2 | task 115 | eval time = 741.39 ms / 2 tokens ( 741.39 ms per token, 1.35 tokens per second) 0.47.714.638 I slot print_timing: id 2 | task 115 | total time = 1150.01 ms / 145 tokens 0.47.714.638 I slot print_timing: id 2 | task 115 | graphs reused = 2 0.47.714.639 I slot print_timing: id 2 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.714.656 I slot release: id 2 | task 115 | stop processing: n_tokens = 153, truncated = 0 0.47.786.269 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.280 (> 0.100 thold), f_keep = 0.242 0.47.788.873 I slot launch_slot_: id 2 | task 124 | processing task, is_child = 0 0.47.841.118 I slot print_timing: id 0 | task 119 | prompt eval time = 873.38 ms / 110 tokens ( 7.94 ms per token, 125.95 tokens per second) 0.47.841.121 I slot print_timing: id 0 | task 119 | eval time = 57.23 ms / 2 tokens ( 57.23 ms per token, 17.47 tokens per second) 0.47.841.122 I slot print_timing: id 0 | task 119 | total time = 930.61 ms / 112 tokens 0.47.841.122 I slot print_timing: id 0 | task 119 | graphs reused = 2 0.47.841.122 I slot print_timing: id 0 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.841.139 I slot release: id 0 | task 119 | stop processing: n_tokens = 120, truncated = 0 0.47.843.324 I slot print_timing: id 3 | task 120 | prompt eval time = 875.03 ms / 120 tokens ( 7.29 ms per token, 137.14 tokens per second) 0.47.843.329 I slot print_timing: id 3 | task 120 | eval time = 57.06 ms / 2 tokens ( 57.06 ms per token, 17.53 tokens per second) 0.47.843.329 I slot print_timing: id 3 | task 120 | total time = 932.09 ms / 122 tokens 0.47.843.330 I slot print_timing: id 3 | task 120 | graphs reused = 2 0.47.843.330 I slot print_timing: id 3 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.843.345 I slot release: id 3 | task 120 | stop processing: n_tokens = 130, truncated = 0 0.48.108.658 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.308 0.48.111.370 I slot launch_slot_: id 0 | task 127 | processing task, is_child = 0 0.48.112.589 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.299 (> 0.100 thold), f_keep = 0.292 0.48.112.660 I slot launch_slot_: id 3 | task 128 | processing task, is_child = 0 0.48.804.447 I slot print_timing: id 1 | task 118 | prompt eval time = 874.37 ms / 136 tokens ( 6.43 ms per token, 155.54 tokens per second) 0.48.804.449 I slot print_timing: id 1 | task 118 | eval time = 1019.45 ms / 5 tokens ( 254.86 ms per token, 3.92 tokens per second) 0.48.804.450 I slot print_timing: id 1 | task 118 | total time = 1893.82 ms / 141 tokens 0.48.804.451 I slot print_timing: id 1 | task 118 | graphs reused = 2 0.48.804.451 I slot print_timing: id 1 | task 118 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.804.483 I slot release: id 1 | task 118 | stop processing: n_tokens = 149, truncated = 0 0.48.805.609 I slot print_timing: id 2 | task 124 | prompt eval time = 405.16 ms / 123 tokens ( 3.29 ms per token, 303.58 tokens per second) 0.48.805.612 I slot print_timing: id 2 | task 124 | eval time = 611.56 ms / 2 tokens ( 611.56 ms per token, 1.64 tokens per second) 0.48.805.612 I slot print_timing: id 2 | task 124 | total time = 1016.73 ms / 125 tokens 0.48.805.612 I slot print_timing: id 2 | task 124 | graphs reused = 2 0.48.805.613 I slot print_timing: id 2 | task 124 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.805.629 I slot release: id 2 | task 124 | stop processing: n_tokens = 133, truncated = 0 0.48.874.307 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.255 0.48.876.764 I slot launch_slot_: id 1 | task 132 | processing task, is_child = 0 0.48.879.550 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.145 (> 0.100 thold), f_keep = 0.278 0.48.879.623 I slot launch_slot_: id 2 | task 133 | processing task, is_child = 0 0.48.931.134 I slot print_timing: id 0 | task 127 | prompt eval time = 760.44 ms / 175 tokens ( 4.35 ms per token, 230.13 tokens per second) 0.48.931.139 I slot print_timing: id 0 | task 127 | eval time = 58.03 ms / 2 tokens ( 58.03 ms per token, 17.23 tokens per second) 0.48.931.140 I slot print_timing: id 0 | task 127 | total time = 818.46 ms / 177 tokens 0.48.931.140 I slot print_timing: id 0 | task 127 | graphs reused = 2 0.48.931.141 I slot print_timing: id 0 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.931.158 I slot release: id 0 | task 127 | stop processing: n_tokens = 185, truncated = 0 0.48.932.272 I slot print_timing: id 3 | task 128 | prompt eval time = 760.88 ms / 118 tokens ( 6.45 ms per token, 155.08 tokens per second) 0.48.932.274 I slot print_timing: id 3 | task 128 | eval time = 57.97 ms / 2 tokens ( 57.97 ms per token, 17.25 tokens per second) 0.48.932.274 I slot print_timing: id 3 | task 128 | total time = 818.85 ms / 120 tokens 0.48.932.274 I slot print_timing: id 3 | task 128 | graphs reused = 2 0.48.932.274 I slot print_timing: id 3 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.932.292 I slot release: id 3 | task 128 | stop processing: n_tokens = 128, truncated = 0 0.49.433.516 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.305 0.49.668.308 I slot launch_slot_: id 3 | task 136 | processing task, is_child = 0 0.49.674.256 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.200 0.49.675.147 I slot launch_slot_: id 0 | task 137 | processing task, is_child = 0 0.50.407.142 I slot print_timing: id 1 | task 132 | prompt eval time = 862.62 ms / 138 tokens ( 6.25 ms per token, 159.98 tokens per second) 0.50.407.148 I slot print_timing: id 1 | task 132 | eval time = 664.88 ms / 2 tokens ( 664.88 ms per token, 1.50 tokens per second) 0.50.407.149 I slot print_timing: id 1 | task 132 | total time = 1527.51 ms / 140 tokens 0.50.407.149 I slot print_timing: id 1 | task 132 | graphs reused = 2 0.50.407.150 I slot print_timing: id 1 | task 132 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.407.173 I slot release: id 1 | task 132 | stop processing: n_tokens = 148, truncated = 0 0.50.408.249 I slot print_timing: id 2 | task 133 | prompt eval time = 863.58 ms / 247 tokens ( 3.50 ms per token, 286.02 tokens per second) 0.50.408.255 I slot print_timing: id 2 | task 133 | eval time = 664.89 ms / 2 tokens ( 664.89 ms per token, 1.50 tokens per second) 0.50.408.256 I slot print_timing: id 2 | task 133 | total time = 1528.48 ms / 249 tokens 0.50.408.256 I slot print_timing: id 2 | task 133 | graphs reused = 2 0.50.408.256 I slot print_timing: id 2 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.408.284 I slot release: id 2 | task 133 | stop processing: n_tokens = 257, truncated = 0 0.50.476.963 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.250 0.50.479.425 I slot launch_slot_: id 1 | task 142 | processing task, is_child = 0 0.50.484.456 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.144 0.50.485.019 I slot launch_slot_: id 2 | task 141 | processing task, is_child = 0 0.50.536.374 I slot print_timing: id 0 | task 137 | prompt eval time = 800.49 ms / 182 tokens ( 4.40 ms per token, 227.36 tokens per second) 0.50.536.378 I slot print_timing: id 0 | task 137 | eval time = 60.73 ms / 2 tokens ( 60.73 ms per token, 16.47 tokens per second) 0.50.536.378 I slot print_timing: id 0 | task 137 | total time = 861.22 ms / 184 tokens 0.50.536.379 I slot print_timing: id 0 | task 137 | graphs reused = 2 0.50.536.379 I slot print_timing: id 0 | task 137 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.536.399 I slot release: id 0 | task 137 | stop processing: n_tokens = 192, truncated = 0 0.50.537.505 I slot print_timing: id 3 | task 136 | prompt eval time = 799.09 ms / 158 tokens ( 5.06 ms per token, 197.72 tokens per second) 0.50.537.509 I slot print_timing: id 3 | task 136 | eval time = 60.55 ms / 2 tokens ( 60.55 ms per token, 16.52 tokens per second) 0.50.537.510 I slot print_timing: id 3 | task 136 | total time = 859.64 ms / 160 tokens 0.50.537.510 I slot print_timing: id 3 | task 136 | graphs reused = 2 0.50.537.510 I slot print_timing: id 3 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.537.521 I slot release: id 3 | task 136 | stop processing: n_tokens = 168, truncated = 0 0.51.041.479 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.336 (> 0.100 thold), f_keep = 0.232 0.51.122.569 I slot launch_slot_: id 3 | task 145 | processing task, is_child = 0 0.51.128.532 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.193 0.51.128.607 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.51.856.452 I slot print_timing: id 1 | task 142 | prompt eval time = 710.16 ms / 162 tokens ( 4.38 ms per token, 228.12 tokens per second) 0.51.856.457 I slot print_timing: id 1 | task 142 | eval time = 661.25 ms / 2 tokens ( 661.25 ms per token, 1.51 tokens per second) 0.51.856.457 I slot print_timing: id 1 | task 142 | total time = 1371.42 ms / 164 tokens 0.51.856.458 I slot print_timing: id 1 | task 142 | graphs reused = 2 0.51.856.458 I slot print_timing: id 1 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.856.479 I slot release: id 1 | task 142 | stop processing: n_tokens = 172, truncated = 0 0.51.857.535 I slot print_timing: id 2 | task 141 | prompt eval time = 711.14 ms / 145 tokens ( 4.90 ms per token, 203.90 tokens per second) 0.51.857.538 I slot print_timing: id 2 | task 141 | eval time = 661.24 ms / 2 tokens ( 661.24 ms per token, 1.51 tokens per second) 0.51.857.538 I slot print_timing: id 2 | task 141 | total time = 1372.38 ms / 147 tokens 0.51.857.538 I slot print_timing: id 2 | task 141 | graphs reused = 2 0.51.857.539 I slot print_timing: id 2 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.857.557 I slot release: id 2 | task 141 | stop processing: n_tokens = 155, truncated = 0 0.51.926.940 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.302 (> 0.100 thold), f_keep = 0.245 0.51.929.486 I slot launch_slot_: id 2 | task 150 | processing task, is_child = 0 0.51.933.199 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.185 (> 0.100 thold), f_keep = 0.215 0.51.933.892 I slot launch_slot_: id 1 | task 151 | processing task, is_child = 0 0.51.985.448 I slot print_timing: id 0 | task 146 | prompt eval time = 797.05 ms / 229 tokens ( 3.48 ms per token, 287.31 tokens per second) 0.51.985.449 I slot print_timing: id 0 | task 146 | eval time = 59.78 ms / 2 tokens ( 59.78 ms per token, 16.73 tokens per second) 0.51.985.450 I slot print_timing: id 0 | task 146 | total time = 856.83 ms / 231 tokens 0.51.985.450 I slot print_timing: id 0 | task 146 | graphs reused = 2 0.51.985.450 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.985.471 I slot release: id 0 | task 146 | stop processing: n_tokens = 239, truncated = 0 0.51.986.588 I slot print_timing: id 3 | task 145 | prompt eval time = 795.96 ms / 107 tokens ( 7.44 ms per token, 134.43 tokens per second) 0.51.986.593 I slot print_timing: id 3 | task 145 | eval time = 59.66 ms / 2 tokens ( 59.66 ms per token, 16.76 tokens per second) 0.51.986.593 I slot print_timing: id 3 | task 145 | total time = 855.61 ms / 109 tokens 0.51.986.594 I slot print_timing: id 3 | task 145 | graphs reused = 2 0.51.986.594 I slot print_timing: id 3 | task 145 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.986.604 I slot release: id 3 | task 145 | stop processing: n_tokens = 117, truncated = 0 0.52.380.051 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.155 0.52.560.789 I slot launch_slot_: id 0 | task 155 | processing task, is_child = 0 0.52.562.591 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.316 0.52.562.664 I slot launch_slot_: id 3 | task 154 | processing task, is_child = 0 0.53.292.390 I slot print_timing: id 1 | task 151 | prompt eval time = 696.01 ms / 191 tokens ( 3.64 ms per token, 274.42 tokens per second) 0.53.292.395 I slot print_timing: id 1 | task 151 | eval time = 662.48 ms / 2 tokens ( 662.48 ms per token, 1.51 tokens per second) 0.53.292.396 I slot print_timing: id 1 | task 151 | total time = 1358.49 ms / 193 tokens 0.53.292.396 I slot print_timing: id 1 | task 151 | graphs reused = 2 0.53.292.396 I slot print_timing: id 1 | task 151 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.292.424 I slot release: id 1 | task 151 | stop processing: n_tokens = 201, truncated = 0 0.53.293.627 I slot print_timing: id 2 | task 150 | prompt eval time = 696.98 ms / 117 tokens ( 5.96 ms per token, 167.87 tokens per second) 0.53.293.630 I slot print_timing: id 2 | task 150 | eval time = 662.61 ms / 2 tokens ( 662.61 ms per token, 1.51 tokens per second) 0.53.293.631 I slot print_timing: id 2 | task 150 | total time = 1359.59 ms / 119 tokens 0.53.293.631 I slot print_timing: id 2 | task 150 | graphs reused = 2 0.53.293.631 I slot print_timing: id 2 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.293.652 I slot release: id 2 | task 150 | stop processing: n_tokens = 127, truncated = 0 0.53.362.663 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.184 0.53.367.019 I slot launch_slot_: id 1 | task 160 | processing task, is_child = 0 0.53.368.995 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.299 0.53.369.064 I slot launch_slot_: id 2 | task 159 | processing task, is_child = 0 0.53.420.518 I slot print_timing: id 0 | task 155 | prompt eval time = 798.71 ms / 175 tokens ( 4.56 ms per token, 219.10 tokens per second) 0.53.420.523 I slot print_timing: id 0 | task 155 | eval time = 59.13 ms / 2 tokens ( 59.13 ms per token, 16.91 tokens per second) 0.53.420.525 I slot print_timing: id 0 | task 155 | total time = 857.85 ms / 177 tokens 0.53.420.525 I slot print_timing: id 0 | task 155 | graphs reused = 2 0.53.420.525 I slot print_timing: id 0 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.420.547 I slot release: id 0 | task 155 | stop processing: n_tokens = 185, truncated = 0 0.53.421.714 I slot print_timing: id 3 | task 154 | prompt eval time = 797.34 ms / 143 tokens ( 5.58 ms per token, 179.35 tokens per second) 0.53.421.719 I slot print_timing: id 3 | task 154 | eval time = 59.05 ms / 2 tokens ( 59.05 ms per token, 16.93 tokens per second) 0.53.421.720 I slot print_timing: id 3 | task 154 | total time = 856.39 ms / 145 tokens 0.53.421.720 I slot print_timing: id 3 | task 154 | graphs reused = 2 0.53.421.720 I slot print_timing: id 3 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.421.735 I slot release: id 3 | task 154 | stop processing: n_tokens = 153, truncated = 0 0.53.869.090 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.306 (> 0.100 thold), f_keep = 0.200 0.53.952.140 I slot launch_slot_: id 0 | task 163 | processing task, is_child = 0 0.53.954.466 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.242 0.53.955.444 I slot launch_slot_: id 3 | task 164 | processing task, is_child = 0 0.54.572.934 I slot print_timing: id 1 | task 160 | prompt eval time = 651.62 ms / 140 tokens ( 4.65 ms per token, 214.85 tokens per second) 0.54.572.939 I slot print_timing: id 1 | task 160 | eval time = 552.23 ms / 2 tokens ( 552.23 ms per token, 1.81 tokens per second) 0.54.572.940 I slot print_timing: id 1 | task 160 | total time = 1203.86 ms / 142 tokens 0.54.572.947 I slot print_timing: id 1 | task 160 | graphs reused = 2 0.54.572.947 I slot print_timing: id 1 | task 160 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.572.980 I slot release: id 1 | task 160 | stop processing: n_tokens = 150, truncated = 0 0.54.574.117 I slot print_timing: id 2 | task 159 | prompt eval time = 652.53 ms / 122 tokens ( 5.35 ms per token, 186.96 tokens per second) 0.54.574.119 I slot print_timing: id 2 | task 159 | eval time = 552.38 ms / 2 tokens ( 552.38 ms per token, 1.81 tokens per second) 0.54.574.119 I slot print_timing: id 2 | task 159 | total time = 1204.91 ms / 124 tokens 0.54.574.119 I slot print_timing: id 2 | task 159 | graphs reused = 2 0.54.574.120 I slot print_timing: id 2 | task 159 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.574.135 I slot release: id 2 | task 159 | stop processing: n_tokens = 132, truncated = 0 0.54.642.632 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.253 (> 0.100 thold), f_keep = 0.247 0.54.645.209 I slot launch_slot_: id 1 | task 169 | processing task, is_child = 0 0.54.646.220 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.280 0.54.646.290 I slot launch_slot_: id 2 | task 168 | processing task, is_child = 0 0.54.697.716 I slot print_timing: id 0 | task 163 | prompt eval time = 685.90 ms / 112 tokens ( 6.12 ms per token, 163.29 tokens per second) 0.54.697.721 I slot print_timing: id 0 | task 163 | eval time = 56.36 ms / 2 tokens ( 56.36 ms per token, 17.74 tokens per second) 0.54.697.722 I slot print_timing: id 0 | task 163 | total time = 742.26 ms / 114 tokens 0.54.697.722 I slot print_timing: id 0 | task 163 | graphs reused = 2 0.54.697.723 I slot print_timing: id 0 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.697.739 I slot release: id 0 | task 163 | stop processing: n_tokens = 122, truncated = 0 0.55.234.747 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.311 0.55.239.535 I slot launch_slot_: id 0 | task 172 | processing task, is_child = 0 0.55.592.096 I slot print_timing: id 1 | task 169 | prompt eval time = 676.27 ms / 137 tokens ( 4.94 ms per token, 202.58 tokens per second) 0.55.592.099 I slot print_timing: id 1 | task 169 | eval time = 269.53 ms / 2 tokens ( 269.53 ms per token, 3.71 tokens per second) 0.55.592.099 I slot print_timing: id 1 | task 169 | total time = 945.80 ms / 139 tokens 0.55.592.100 I slot print_timing: id 1 | task 169 | graphs reused = 3 0.55.592.100 I slot print_timing: id 1 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.592.120 I slot release: id 1 | task 169 | stop processing: n_tokens = 147, truncated = 0 0.55.593.259 I slot print_timing: id 2 | task 168 | prompt eval time = 677.24 ms / 138 tokens ( 4.91 ms per token, 203.77 tokens per second) 0.55.593.265 I slot print_timing: id 2 | task 168 | eval time = 269.59 ms / 2 tokens ( 269.59 ms per token, 3.71 tokens per second) 0.55.593.266 I slot print_timing: id 2 | task 168 | total time = 946.83 ms / 140 tokens 0.55.593.266 I slot print_timing: id 2 | task 168 | graphs reused = 3 0.55.593.266 I slot print_timing: id 2 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.593.282 I slot release: id 2 | task 168 | stop processing: n_tokens = 148, truncated = 0 0.55.594.489 I slot print_timing: id 3 | task 164 | prompt eval time = 686.11 ms / 162 tokens ( 4.24 ms per token, 236.11 tokens per second) 0.55.594.490 I slot print_timing: id 3 | task 164 | eval time = 951.86 ms / 5 tokens ( 237.96 ms per token, 4.20 tokens per second) 0.55.594.491 I slot print_timing: id 3 | task 164 | total time = 1637.97 ms / 167 tokens 0.55.594.491 I slot print_timing: id 3 | task 164 | graphs reused = 3 0.55.594.491 I slot print_timing: id 3 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.594.516 I slot release: id 3 | task 164 | stop processing: n_tokens = 175, truncated = 0 0.55.628.620 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.252 0.55.631.806 I slot launch_slot_: id 1 | task 176 | processing task, is_child = 0 0.55.638.370 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 0.55.638.444 I slot launch_slot_: id 2 | task 177 | processing task, is_child = 0 0.55.638.478 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.211 0.55.638.544 I slot launch_slot_: id 3 | task 178 | processing task, is_child = 0 0.55.672.052 I slot print_timing: id 0 | task 172 | prompt eval time = 389.07 ms / 122 tokens ( 3.19 ms per token, 313.57 tokens per second) 0.55.672.057 I slot print_timing: id 0 | task 172 | eval time = 43.44 ms / 2 tokens ( 43.44 ms per token, 23.02 tokens per second) 0.55.672.058 I slot print_timing: id 0 | task 172 | total time = 432.50 ms / 124 tokens 0.55.672.058 I slot print_timing: id 0 | task 172 | graphs reused = 3 0.55.672.059 I slot print_timing: id 0 | task 172 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.672.073 I slot release: id 0 | task 172 | stop processing: n_tokens = 132, truncated = 0 0.56.332.724 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.198 (> 0.100 thold), f_keep = 0.280 0.56.566.693 I slot launch_slot_: id 0 | task 181 | processing task, is_child = 0 0.57.028.780 I slot print_timing: id 1 | task 176 | prompt eval time = 1009.18 ms / 132 tokens ( 7.65 ms per token, 130.80 tokens per second) 0.57.028.786 I slot print_timing: id 1 | task 176 | eval time = 381.05 ms / 2 tokens ( 381.05 ms per token, 2.62 tokens per second) 0.57.028.786 I slot print_timing: id 1 | task 176 | total time = 1390.23 ms / 134 tokens 0.57.028.786 I slot print_timing: id 1 | task 176 | graphs reused = 3 0.57.028.787 I slot print_timing: id 1 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.028.809 I slot release: id 1 | task 176 | stop processing: n_tokens = 142, truncated = 0 0.57.029.913 I slot print_timing: id 2 | task 177 | prompt eval time = 1010.18 ms / 183 tokens ( 5.52 ms per token, 181.16 tokens per second) 0.57.029.914 I slot print_timing: id 2 | task 177 | eval time = 381.04 ms / 2 tokens ( 381.04 ms per token, 2.62 tokens per second) 0.57.029.915 I slot print_timing: id 2 | task 177 | total time = 1391.22 ms / 185 tokens 0.57.029.915 I slot print_timing: id 2 | task 177 | graphs reused = 3 0.57.029.915 I slot print_timing: id 2 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.029.941 I slot release: id 2 | task 177 | stop processing: n_tokens = 193, truncated = 0 0.57.031.091 I slot print_timing: id 3 | task 178 | prompt eval time = 1011.14 ms / 183 tokens ( 5.53 ms per token, 180.98 tokens per second) 0.57.031.093 I slot print_timing: id 3 | task 178 | eval time = 381.14 ms / 2 tokens ( 381.14 ms per token, 2.62 tokens per second) 0.57.031.093 I slot print_timing: id 3 | task 178 | total time = 1392.29 ms / 185 tokens 0.57.031.094 I slot print_timing: id 3 | task 178 | graphs reused = 3 0.57.031.094 I slot print_timing: id 3 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.031.115 I slot release: id 3 | task 178 | stop processing: n_tokens = 193, truncated = 0 0.57.067.229 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.261 0.57.069.977 I slot launch_slot_: id 1 | task 185 | processing task, is_child = 0 0.57.078.650 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.192 0.57.078.726 I slot launch_slot_: id 2 | task 186 | processing task, is_child = 0 0.57.078.758 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.192 0.57.079.339 I slot launch_slot_: id 3 | task 187 | processing task, is_child = 0 0.57.112.612 I slot print_timing: id 0 | task 181 | prompt eval time = 500.52 ms / 178 tokens ( 2.81 ms per token, 355.63 tokens per second) 0.57.112.615 I slot print_timing: id 0 | task 181 | eval time = 45.38 ms / 2 tokens ( 45.38 ms per token, 22.03 tokens per second) 0.57.112.615 I slot print_timing: id 0 | task 181 | total time = 545.91 ms / 180 tokens 0.57.112.616 I slot print_timing: id 0 | task 181 | graphs reused = 3 0.57.112.616 I slot print_timing: id 0 | task 181 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.112.650 I slot release: id 0 | task 181 | stop processing: n_tokens = 188, truncated = 0 0.57.747.499 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.197 0.57.779.492 I slot launch_slot_: id 0 | task 190 | processing task, is_child = 0 0.58.126.685 I slot print_timing: id 1 | task 185 | prompt eval time = 778.81 ms / 125 tokens ( 6.23 ms per token, 160.50 tokens per second) 0.58.126.694 I slot print_timing: id 1 | task 185 | eval time = 268.52 ms / 2 tokens ( 268.52 ms per token, 3.72 tokens per second) 0.58.126.695 I slot print_timing: id 1 | task 185 | total time = 1047.34 ms / 127 tokens 0.58.126.695 I slot print_timing: id 1 | task 185 | graphs reused = 3 0.58.126.696 I slot print_timing: id 1 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.126.716 I slot release: id 1 | task 185 | stop processing: n_tokens = 135, truncated = 0 0.58.127.893 I slot print_timing: id 2 | task 186 | prompt eval time = 779.79 ms / 117 tokens ( 6.66 ms per token, 150.04 tokens per second) 0.58.127.895 I slot print_timing: id 2 | task 186 | eval time = 268.64 ms / 2 tokens ( 268.64 ms per token, 3.72 tokens per second) 0.58.127.896 I slot print_timing: id 2 | task 186 | total time = 1048.43 ms / 119 tokens 0.58.127.896 I slot print_timing: id 2 | task 186 | graphs reused = 3 0.58.127.896 I slot print_timing: id 2 | task 186 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.127.911 I slot release: id 2 | task 186 | stop processing: n_tokens = 127, truncated = 0 0.58.129.057 I slot print_timing: id 3 | task 187 | prompt eval time = 780.85 ms / 125 tokens ( 6.25 ms per token, 160.08 tokens per second) 0.58.129.062 I slot print_timing: id 3 | task 187 | eval time = 268.63 ms / 2 tokens ( 268.63 ms per token, 3.72 tokens per second) 0.58.129.062 I slot print_timing: id 3 | task 187 | total time = 1049.48 ms / 127 tokens 0.58.129.062 I slot print_timing: id 3 | task 187 | graphs reused = 3 0.58.129.063 I slot print_timing: id 3 | task 187 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.129.074 I slot release: id 3 | task 187 | stop processing: n_tokens = 135, truncated = 0 0.58.162.931 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.281 0.58.164.252 I slot launch_slot_: id 3 | task 194 | processing task, is_child = 0 0.58.167.292 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.274 0.58.167.369 I slot launch_slot_: id 1 | task 195 | processing task, is_child = 0 0.58.167.397 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.291 0.58.167.935 I slot launch_slot_: id 2 | task 196 | processing task, is_child = 0 0.58.201.486 I slot print_timing: id 0 | task 190 | prompt eval time = 383.42 ms / 117 tokens ( 3.28 ms per token, 305.15 tokens per second) 0.58.201.492 I slot print_timing: id 0 | task 190 | eval time = 38.56 ms / 2 tokens ( 38.56 ms per token, 25.93 tokens per second) 0.58.201.492 I slot print_timing: id 0 | task 190 | total time = 421.98 ms / 119 tokens 0.58.201.493 I slot print_timing: id 0 | task 190 | graphs reused = 3 0.58.201.493 I slot print_timing: id 0 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.201.512 I slot release: id 0 | task 190 | stop processing: n_tokens = 127, truncated = 0 0.58.907.072 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.291 0.58.924.369 I slot launch_slot_: id 0 | task 199 | processing task, is_child = 0 0.59.273.647 I slot print_timing: id 1 | task 195 | prompt eval time = 835.26 ms / 143 tokens ( 5.84 ms per token, 171.20 tokens per second) 0.59.273.650 I slot print_timing: id 1 | task 195 | eval time = 270.43 ms / 2 tokens ( 270.43 ms per token, 3.70 tokens per second) 0.59.273.650 I slot print_timing: id 1 | task 195 | total time = 1105.70 ms / 145 tokens 0.59.273.651 I slot print_timing: id 1 | task 195 | graphs reused = 3 0.59.273.651 I slot print_timing: id 1 | task 195 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.273.676 I slot release: id 1 | task 195 | stop processing: n_tokens = 153, truncated = 0 0.59.274.768 I slot print_timing: id 2 | task 196 | prompt eval time = 836.28 ms / 130 tokens ( 6.43 ms per token, 155.45 tokens per second) 0.59.274.771 I slot print_timing: id 2 | task 196 | eval time = 270.42 ms / 2 tokens ( 270.42 ms per token, 3.70 tokens per second) 0.59.274.771 I slot print_timing: id 2 | task 196 | total time = 1106.70 ms / 132 tokens 0.59.274.771 I slot print_timing: id 2 | task 196 | graphs reused = 3 0.59.274.772 I slot print_timing: id 2 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.274.787 I slot release: id 2 | task 196 | stop processing: n_tokens = 140, truncated = 0 0.59.275.932 I slot print_timing: id 3 | task 194 | prompt eval time = 837.28 ms / 131 tokens ( 6.39 ms per token, 156.46 tokens per second) 0.59.275.935 I slot print_timing: id 3 | task 194 | eval time = 270.48 ms / 2 tokens ( 270.48 ms per token, 3.70 tokens per second) 0.59.275.935 I slot print_timing: id 3 | task 194 | total time = 1107.76 ms / 133 tokens 0.59.275.936 I slot print_timing: id 3 | task 194 | graphs reused = 3 0.59.275.936 I slot print_timing: id 3 | task 194 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.275.951 I slot release: id 3 | task 194 | stop processing: n_tokens = 141, truncated = 0 0.59.310.988 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.242 0.59.313.729 I slot launch_slot_: id 1 | task 204 | processing task, is_child = 0 0.59.319.570 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 0.59.320.091 I slot launch_slot_: id 3 | task 203 | processing task, is_child = 0 0.59.320.121 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.264 0.59.320.180 I slot launch_slot_: id 2 | task 205 | processing task, is_child = 0 0.59.353.741 I slot print_timing: id 0 | task 199 | prompt eval time = 386.60 ms / 132 tokens ( 2.93 ms per token, 341.43 tokens per second) 0.59.353.747 I slot print_timing: id 0 | task 199 | eval time = 42.75 ms / 2 tokens ( 42.75 ms per token, 23.39 tokens per second) 0.59.353.748 I slot print_timing: id 0 | task 199 | total time = 429.36 ms / 134 tokens 0.59.353.748 I slot print_timing: id 0 | task 199 | graphs reused = 3 0.59.353.748 I slot print_timing: id 0 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.353.764 I slot release: id 0 | task 199 | stop processing: n_tokens = 142, truncated = 0 1.00.042.643 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.261 1.00.073.496 I slot launch_slot_: id 0 | task 208 | processing task, is_child = 0 1.00.475.660 I slot print_timing: id 1 | task 204 | prompt eval time = 833.52 ms / 124 tokens ( 6.72 ms per token, 148.77 tokens per second) 1.00.475.663 I slot print_timing: id 1 | task 204 | eval time = 321.95 ms / 2 tokens ( 321.95 ms per token, 3.11 tokens per second) 1.00.475.664 I slot print_timing: id 1 | task 204 | total time = 1155.47 ms / 126 tokens 1.00.475.664 I slot print_timing: id 1 | task 204 | graphs reused = 3 1.00.475.665 I slot print_timing: id 1 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.475.687 I slot release: id 1 | task 204 | stop processing: n_tokens = 134, truncated = 0 1.00.476.828 I slot print_timing: id 2 | task 205 | prompt eval time = 834.52 ms / 131 tokens ( 6.37 ms per token, 156.98 tokens per second) 1.00.476.834 I slot print_timing: id 2 | task 205 | eval time = 322.00 ms / 2 tokens ( 322.00 ms per token, 3.11 tokens per second) 1.00.476.836 I slot print_timing: id 2 | task 205 | total time = 1156.53 ms / 133 tokens 1.00.476.836 I slot print_timing: id 2 | task 205 | graphs reused = 3 1.00.476.836 I slot print_timing: id 2 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.476.854 I slot release: id 2 | task 205 | stop processing: n_tokens = 141, truncated = 0 1.00.478.008 I slot print_timing: id 3 | task 203 | prompt eval time = 835.73 ms / 105 tokens ( 7.96 ms per token, 125.64 tokens per second) 1.00.478.010 I slot print_timing: id 3 | task 203 | eval time = 321.87 ms / 2 tokens ( 321.87 ms per token, 3.11 tokens per second) 1.00.478.010 I slot print_timing: id 3 | task 203 | total time = 1157.60 ms / 107 tokens 1.00.478.010 I slot print_timing: id 3 | task 203 | graphs reused = 3 1.00.478.011 I slot print_timing: id 3 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.478.021 I slot release: id 3 | task 203 | stop processing: n_tokens = 115, truncated = 0 1.00.512.190 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.276 1.00.514.521 I slot launch_slot_: id 1 | task 212 | processing task, is_child = 0 1.00.519.310 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.262 1.00.519.381 I slot launch_slot_: id 2 | task 213 | processing task, is_child = 0 1.00.519.409 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.322 1.00.519.470 I slot launch_slot_: id 3 | task 214 | processing task, is_child = 0 1.00.553.070 I slot print_timing: id 0 | task 208 | prompt eval time = 438.68 ms / 160 tokens ( 2.74 ms per token, 364.73 tokens per second) 1.00.553.074 I slot print_timing: id 0 | task 208 | eval time = 40.88 ms / 2 tokens ( 40.88 ms per token, 24.46 tokens per second) 1.00.553.074 I slot print_timing: id 0 | task 208 | total time = 479.57 ms / 162 tokens 1.00.553.075 I slot print_timing: id 0 | task 208 | graphs reused = 3 1.00.553.075 I slot print_timing: id 0 | task 208 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.553.096 I slot release: id 0 | task 208 | stop processing: n_tokens = 170, truncated = 0 1.01.400.677 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.218 1.01.446.470 I slot launch_slot_: id 0 | task 217 | processing task, is_child = 0 1.01.794.537 I slot print_timing: id 1 | task 212 | prompt eval time = 1006.28 ms / 173 tokens ( 5.82 ms per token, 171.92 tokens per second) 1.01.794.543 I slot print_timing: id 1 | task 212 | eval time = 268.77 ms / 2 tokens ( 268.77 ms per token, 3.72 tokens per second) 1.01.794.544 I slot print_timing: id 1 | task 212 | total time = 1275.06 ms / 175 tokens 1.01.794.544 I slot print_timing: id 1 | task 212 | graphs reused = 3 1.01.794.545 I slot print_timing: id 1 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.794.568 I slot release: id 1 | task 212 | stop processing: n_tokens = 183, truncated = 0 1.01.795.674 I slot print_timing: id 2 | task 213 | prompt eval time = 1007.25 ms / 161 tokens ( 6.26 ms per token, 159.84 tokens per second) 1.01.795.677 I slot print_timing: id 2 | task 213 | eval time = 268.83 ms / 2 tokens ( 268.83 ms per token, 3.72 tokens per second) 1.01.795.678 I slot print_timing: id 2 | task 213 | total time = 1276.07 ms / 163 tokens 1.01.795.678 I slot print_timing: id 2 | task 213 | graphs reused = 3 1.01.795.678 I slot print_timing: id 2 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.795.697 I slot release: id 2 | task 213 | stop processing: n_tokens = 171, truncated = 0 1.01.796.852 I slot print_timing: id 3 | task 214 | prompt eval time = 1008.57 ms / 143 tokens ( 7.05 ms per token, 141.78 tokens per second) 1.01.796.857 I slot print_timing: id 3 | task 214 | eval time = 268.57 ms / 2 tokens ( 268.57 ms per token, 3.72 tokens per second) 1.01.796.858 I slot print_timing: id 3 | task 214 | total time = 1277.14 ms / 145 tokens 1.01.796.858 I slot print_timing: id 3 | task 214 | graphs reused = 3 1.01.796.858 I slot print_timing: id 3 | task 214 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.796.875 I slot release: id 3 | task 214 | stop processing: n_tokens = 153, truncated = 0 1.01.830.862 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 1.01.835.882 I slot launch_slot_: id 1 | task 221 | processing task, is_child = 0 1.01.840.755 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.306 (> 0.100 thold), f_keep = 0.216 1.01.840.824 I slot launch_slot_: id 2 | task 222 | processing task, is_child = 0 1.01.840.853 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.242 1.01.841.379 I slot launch_slot_: id 3 | task 223 | processing task, is_child = 0 1.01.874.803 I slot print_timing: id 0 | task 217 | prompt eval time = 384.38 ms / 113 tokens ( 3.40 ms per token, 293.98 tokens per second) 1.01.874.807 I slot print_timing: id 0 | task 217 | eval time = 43.95 ms / 2 tokens ( 43.95 ms per token, 22.76 tokens per second) 1.01.874.808 I slot print_timing: id 0 | task 217 | total time = 428.32 ms / 115 tokens 1.01.874.808 I slot print_timing: id 0 | task 217 | graphs reused = 3 1.01.874.808 I slot print_timing: id 0 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.874.822 I slot release: id 0 | task 217 | stop processing: n_tokens = 123, truncated = 0 1.02.605.624 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.314 (> 0.100 thold), f_keep = 0.309 1.02.687.039 I slot launch_slot_: id 0 | task 226 | processing task, is_child = 0 1.03.035.348 I slot print_timing: id 1 | task 221 | prompt eval time = 925.80 ms / 152 tokens ( 6.09 ms per token, 164.18 tokens per second) 1.03.035.353 I slot print_timing: id 1 | task 221 | eval time = 268.16 ms / 2 tokens ( 268.16 ms per token, 3.73 tokens per second) 1.03.035.353 I slot print_timing: id 1 | task 221 | total time = 1193.96 ms / 154 tokens 1.03.035.354 I slot print_timing: id 1 | task 221 | graphs reused = 3 1.03.035.354 I slot print_timing: id 1 | task 221 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.035.375 I slot release: id 1 | task 221 | stop processing: n_tokens = 162, truncated = 0 1.03.036.486 I slot print_timing: id 2 | task 222 | prompt eval time = 926.85 ms / 112 tokens ( 8.28 ms per token, 120.84 tokens per second) 1.03.036.489 I slot print_timing: id 2 | task 222 | eval time = 268.13 ms / 2 tokens ( 268.13 ms per token, 3.73 tokens per second) 1.03.036.489 I slot print_timing: id 2 | task 222 | total time = 1194.98 ms / 114 tokens 1.03.036.490 I slot print_timing: id 2 | task 222 | graphs reused = 3 1.03.036.490 I slot print_timing: id 2 | task 222 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.036.504 I slot release: id 2 | task 222 | stop processing: n_tokens = 122, truncated = 0 1.03.037.660 I slot print_timing: id 3 | task 223 | prompt eval time = 927.84 ms / 140 tokens ( 6.63 ms per token, 150.89 tokens per second) 1.03.037.661 I slot print_timing: id 3 | task 223 | eval time = 268.21 ms / 2 tokens ( 268.21 ms per token, 3.73 tokens per second) 1.03.037.662 I slot print_timing: id 3 | task 223 | total time = 1196.05 ms / 142 tokens 1.03.037.662 I slot print_timing: id 3 | task 223 | graphs reused = 3 1.03.037.663 I slot print_timing: id 3 | task 223 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.037.680 I slot release: id 3 | task 223 | stop processing: n_tokens = 150, truncated = 0 1.03.071.920 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.228 1.03.075.322 I slot launch_slot_: id 1 | task 230 | processing task, is_child = 0 1.03.078.124 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.303 1.03.078.194 I slot launch_slot_: id 2 | task 231 | processing task, is_child = 0 1.03.078.231 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.301 (> 0.100 thold), f_keep = 0.247 1.03.078.716 I slot launch_slot_: id 3 | task 232 | processing task, is_child = 0 1.03.112.367 I slot print_timing: id 0 | task 226 | prompt eval time = 384.87 ms / 112 tokens ( 3.44 ms per token, 291.01 tokens per second) 1.03.112.370 I slot print_timing: id 0 | task 226 | eval time = 40.45 ms / 2 tokens ( 40.45 ms per token, 24.72 tokens per second) 1.03.112.379 I slot print_timing: id 0 | task 226 | total time = 425.32 ms / 114 tokens 1.03.112.381 I slot print_timing: id 0 | task 226 | graphs reused = 3 1.03.112.382 I slot print_timing: id 0 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.112.399 I slot release: id 0 | task 226 | stop processing: n_tokens = 122, truncated = 0 1.03.845.409 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.303 1.03.925.833 I slot launch_slot_: id 0 | task 235 | processing task, is_child = 0 1.04.274.277 I slot print_timing: id 1 | task 230 | prompt eval time = 926.52 ms / 155 tokens ( 5.98 ms per token, 167.29 tokens per second) 1.04.274.281 I slot print_timing: id 1 | task 230 | eval time = 269.02 ms / 2 tokens ( 269.02 ms per token, 3.72 tokens per second) 1.04.274.282 I slot print_timing: id 1 | task 230 | total time = 1195.55 ms / 157 tokens 1.04.274.282 I slot print_timing: id 1 | task 230 | graphs reused = 3 1.04.274.282 I slot print_timing: id 1 | task 230 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.274.329 I slot release: id 1 | task 230 | stop processing: n_tokens = 165, truncated = 0 1.04.275.478 I slot print_timing: id 2 | task 231 | prompt eval time = 927.54 ms / 134 tokens ( 6.92 ms per token, 144.47 tokens per second) 1.04.275.484 I slot print_timing: id 2 | task 231 | eval time = 269.10 ms / 2 tokens ( 269.10 ms per token, 3.72 tokens per second) 1.04.275.484 I slot print_timing: id 2 | task 231 | total time = 1196.64 ms / 136 tokens 1.04.275.485 I slot print_timing: id 2 | task 231 | graphs reused = 3 1.04.275.485 I slot print_timing: id 2 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.275.503 I slot release: id 2 | task 231 | stop processing: n_tokens = 144, truncated = 0 1.04.276.630 I slot print_timing: id 3 | task 232 | prompt eval time = 928.53 ms / 114 tokens ( 8.14 ms per token, 122.77 tokens per second) 1.04.276.633 I slot print_timing: id 3 | task 232 | eval time = 269.14 ms / 2 tokens ( 269.14 ms per token, 3.72 tokens per second) 1.04.276.634 I slot print_timing: id 3 | task 232 | total time = 1197.67 ms / 116 tokens 1.04.276.634 I slot print_timing: id 3 | task 232 | graphs reused = 3 1.04.276.634 I slot print_timing: id 3 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.276.649 I slot release: id 3 | task 232 | stop processing: n_tokens = 124, truncated = 0 1.04.311.556 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.224 1.04.316.162 I slot launch_slot_: id 1 | task 239 | processing task, is_child = 0 1.04.319.891 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 1.04.319.964 I slot launch_slot_: id 3 | task 240 | processing task, is_child = 0 1.04.319.993 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.257 1.04.320.057 I slot launch_slot_: id 2 | task 241 | processing task, is_child = 0 1.04.353.685 I slot print_timing: id 0 | task 235 | prompt eval time = 385.71 ms / 125 tokens ( 3.09 ms per token, 324.08 tokens per second) 1.04.353.686 I slot print_timing: id 0 | task 235 | eval time = 42.14 ms / 2 tokens ( 42.14 ms per token, 23.73 tokens per second) 1.04.353.687 I slot print_timing: id 0 | task 235 | total time = 427.84 ms / 127 tokens 1.04.353.687 I slot print_timing: id 0 | task 235 | graphs reused = 3 1.04.353.688 I slot print_timing: id 0 | task 235 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.353.702 I slot release: id 0 | task 235 | stop processing: n_tokens = 135, truncated = 0 1.05.140.989 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.274 1.05.185.849 I slot launch_slot_: id 0 | task 244 | processing task, is_child = 0 1.05.538.121 I slot print_timing: id 2 | task 241 | prompt eval time = 947.10 ms / 170 tokens ( 5.57 ms per token, 179.50 tokens per second) 1.05.538.127 I slot print_timing: id 2 | task 241 | eval time = 270.84 ms / 2 tokens ( 270.84 ms per token, 3.69 tokens per second) 1.05.538.128 I slot print_timing: id 2 | task 241 | total time = 1217.93 ms / 172 tokens 1.05.538.128 I slot print_timing: id 2 | task 241 | graphs reused = 3 1.05.538.129 I slot print_timing: id 2 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.538.158 I slot release: id 2 | task 241 | stop processing: n_tokens = 180, truncated = 0 1.05.539.355 I slot print_timing: id 3 | task 240 | prompt eval time = 948.18 ms / 121 tokens ( 7.84 ms per token, 127.61 tokens per second) 1.05.539.357 I slot print_timing: id 3 | task 240 | eval time = 270.88 ms / 2 tokens ( 270.88 ms per token, 3.69 tokens per second) 1.05.539.358 I slot print_timing: id 3 | task 240 | total time = 1219.05 ms / 123 tokens 1.05.539.358 I slot print_timing: id 3 | task 240 | graphs reused = 3 1.05.539.358 I slot print_timing: id 3 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.539.379 I slot release: id 3 | task 240 | stop processing: n_tokens = 131, truncated = 0 1.05.593.374 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.311 (> 0.100 thold), f_keep = 0.206 1.05.598.808 I slot launch_slot_: id 2 | task 248 | processing task, is_child = 0 1.05.600.417 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.282 1.05.600.488 I slot launch_slot_: id 3 | task 249 | processing task, is_child = 0 1.05.634.992 I slot print_timing: id 0 | task 244 | prompt eval time = 406.45 ms / 131 tokens ( 3.10 ms per token, 322.30 tokens per second) 1.05.634.996 I slot print_timing: id 0 | task 244 | eval time = 42.67 ms / 2 tokens ( 42.67 ms per token, 23.43 tokens per second) 1.05.634.997 I slot print_timing: id 0 | task 244 | total time = 449.13 ms / 133 tokens 1.05.634.997 I slot print_timing: id 0 | task 244 | graphs reused = 3 1.05.634.997 I slot print_timing: id 0 | task 244 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.635.014 I slot release: id 0 | task 244 | stop processing: n_tokens = 141, truncated = 0 1.06.243.668 I slot print_timing: id 1 | task 239 | prompt eval time = 946.10 ms / 159 tokens ( 5.95 ms per token, 168.06 tokens per second) 1.06.243.673 I slot print_timing: id 1 | task 239 | eval time = 977.50 ms / 5 tokens ( 244.38 ms per token, 4.09 tokens per second) 1.06.243.674 I slot print_timing: id 1 | task 239 | total time = 1923.60 ms / 164 tokens 1.06.243.674 I slot print_timing: id 1 | task 239 | graphs reused = 3 1.06.243.675 I slot print_timing: id 1 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.243.712 I slot release: id 1 | task 239 | stop processing: n_tokens = 172, truncated = 0 1.06.243.724 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.221 1.06.247.611 I slot launch_slot_: id 1 | task 252 | processing task, is_child = 0 1.06.250.010 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.262 1.06.250.572 I slot launch_slot_: id 0 | task 253 | processing task, is_child = 0 1.06.883.265 I slot print_timing: id 2 | task 248 | prompt eval time = 715.64 ms / 110 tokens ( 6.51 ms per token, 153.71 tokens per second) 1.06.883.268 I slot print_timing: id 2 | task 248 | eval time = 567.13 ms / 2 tokens ( 567.13 ms per token, 1.76 tokens per second) 1.06.883.268 I slot print_timing: id 2 | task 248 | total time = 1282.77 ms / 112 tokens 1.06.883.269 I slot print_timing: id 2 | task 248 | graphs reused = 3 1.06.883.269 I slot print_timing: id 2 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.883.298 I slot release: id 2 | task 248 | stop processing: n_tokens = 120, truncated = 0 1.06.884.461 I slot print_timing: id 3 | task 249 | prompt eval time = 716.70 ms / 188 tokens ( 3.81 ms per token, 262.32 tokens per second) 1.06.884.462 I slot print_timing: id 3 | task 249 | eval time = 567.14 ms / 2 tokens ( 567.14 ms per token, 1.76 tokens per second) 1.06.884.463 I slot print_timing: id 3 | task 249 | total time = 1283.83 ms / 190 tokens 1.06.884.463 I slot print_timing: id 3 | task 249 | graphs reused = 3 1.06.884.463 I slot print_timing: id 3 | task 249 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.884.488 I slot release: id 3 | task 249 | stop processing: n_tokens = 198, truncated = 0 1.06.924.227 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.308 1.06.927.334 I slot launch_slot_: id 2 | task 257 | processing task, is_child = 0 1.06.931.583 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.253 (> 0.100 thold), f_keep = 0.187 1.06.931.664 I slot launch_slot_: id 3 | task 258 | processing task, is_child = 0 1.06.966.118 I slot print_timing: id 0 | task 253 | prompt eval time = 672.53 ms / 148 tokens ( 4.54 ms per token, 220.07 tokens per second) 1.06.966.119 I slot print_timing: id 0 | task 253 | eval time = 43.01 ms / 2 tokens ( 43.01 ms per token, 23.25 tokens per second) 1.06.966.120 I slot print_timing: id 0 | task 253 | total time = 715.54 ms / 150 tokens 1.06.966.120 I slot print_timing: id 0 | task 253 | graphs reused = 3 1.06.966.121 I slot print_timing: id 0 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.966.136 I slot release: id 0 | task 253 | stop processing: n_tokens = 158, truncated = 0 1.06.967.220 I slot print_timing: id 1 | task 252 | prompt eval time = 673.51 ms / 155 tokens ( 4.35 ms per token, 230.14 tokens per second) 1.06.967.224 I slot print_timing: id 1 | task 252 | eval time = 43.00 ms / 2 tokens ( 43.00 ms per token, 23.26 tokens per second) 1.06.967.224 I slot print_timing: id 1 | task 252 | total time = 716.51 ms / 157 tokens 1.06.967.225 I slot print_timing: id 1 | task 252 | graphs reused = 3 1.06.967.225 I slot print_timing: id 1 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.967.235 I slot release: id 1 | task 252 | stop processing: n_tokens = 165, truncated = 0 1.07.361.058 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.234 1.07.441.731 I slot launch_slot_: id 0 | task 261 | processing task, is_child = 0 1.07.446.351 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.224 1.07.447.285 I slot launch_slot_: id 1 | task 262 | processing task, is_child = 0 1.08.126.065 I slot print_timing: id 2 | task 257 | prompt eval time = 580.60 ms / 117 tokens ( 4.96 ms per token, 201.51 tokens per second) 1.08.126.067 I slot print_timing: id 2 | task 257 | eval time = 613.79 ms / 2 tokens ( 613.79 ms per token, 1.63 tokens per second) 1.08.126.068 I slot print_timing: id 2 | task 257 | total time = 1194.39 ms / 119 tokens 1.08.126.068 I slot print_timing: id 2 | task 257 | graphs reused = 3 1.08.126.069 I slot print_timing: id 2 | task 257 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.126.087 I slot release: id 2 | task 257 | stop processing: n_tokens = 127, truncated = 0 1.08.127.266 I slot print_timing: id 3 | task 258 | prompt eval time = 581.65 ms / 137 tokens ( 4.25 ms per token, 235.54 tokens per second) 1.08.127.271 I slot print_timing: id 3 | task 258 | eval time = 613.83 ms / 2 tokens ( 613.83 ms per token, 1.63 tokens per second) 1.08.127.271 I slot print_timing: id 3 | task 258 | total time = 1195.47 ms / 139 tokens 1.08.127.271 I slot print_timing: id 3 | task 258 | graphs reused = 3 1.08.127.272 I slot print_timing: id 3 | task 258 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.127.293 I slot release: id 3 | task 258 | stop processing: n_tokens = 147, truncated = 0 1.08.166.448 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.291 1.08.167.971 I slot launch_slot_: id 2 | task 266 | processing task, is_child = 0 1.08.170.871 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.252 1.08.171.637 I slot launch_slot_: id 3 | task 267 | processing task, is_child = 0 1.08.206.175 I slot print_timing: id 0 | task 261 | prompt eval time = 717.71 ms / 136 tokens ( 5.28 ms per token, 189.49 tokens per second) 1.08.206.177 I slot print_timing: id 0 | task 261 | eval time = 41.17 ms / 2 tokens ( 41.17 ms per token, 24.29 tokens per second) 1.08.206.178 I slot print_timing: id 0 | task 261 | total time = 758.88 ms / 138 tokens 1.08.206.178 I slot print_timing: id 0 | task 261 | graphs reused = 3 1.08.206.178 I slot print_timing: id 0 | task 261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.206.198 I slot release: id 0 | task 261 | stop processing: n_tokens = 146, truncated = 0 1.08.207.383 I slot print_timing: id 1 | task 262 | prompt eval time = 719.03 ms / 159 tokens ( 4.52 ms per token, 221.13 tokens per second) 1.08.207.385 I slot print_timing: id 1 | task 262 | eval time = 40.94 ms / 2 tokens ( 40.94 ms per token, 24.43 tokens per second) 1.08.207.386 I slot print_timing: id 1 | task 262 | total time = 759.96 ms / 161 tokens 1.08.207.386 I slot print_timing: id 1 | task 262 | graphs reused = 3 1.08.207.386 I slot print_timing: id 1 | task 262 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.207.398 I slot release: id 1 | task 262 | stop processing: n_tokens = 169, truncated = 0 1.08.655.415 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.291 (> 0.100 thold), f_keep = 0.253 1.08.738.280 I slot launch_slot_: id 0 | task 270 | processing task, is_child = 0 1.08.742.541 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.219 1.08.742.615 I slot launch_slot_: id 1 | task 271 | processing task, is_child = 0 1.09.415.492 I slot print_timing: id 2 | task 266 | prompt eval time = 636.35 ms / 152 tokens ( 4.19 ms per token, 238.86 tokens per second) 1.09.415.495 I slot print_timing: id 2 | task 266 | eval time = 607.48 ms / 2 tokens ( 607.48 ms per token, 1.65 tokens per second) 1.09.415.495 I slot print_timing: id 2 | task 266 | total time = 1243.83 ms / 154 tokens 1.09.415.496 I slot print_timing: id 2 | task 266 | graphs reused = 3 1.09.415.497 I slot print_timing: id 2 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.415.536 I slot release: id 2 | task 266 | stop processing: n_tokens = 162, truncated = 0 1.09.416.740 I slot print_timing: id 3 | task 267 | prompt eval time = 637.30 ms / 124 tokens ( 5.14 ms per token, 194.57 tokens per second) 1.09.416.743 I slot print_timing: id 3 | task 267 | eval time = 607.62 ms / 2 tokens ( 607.62 ms per token, 1.65 tokens per second) 1.09.416.743 I slot print_timing: id 3 | task 267 | total time = 1244.93 ms / 126 tokens 1.09.416.744 I slot print_timing: id 3 | task 267 | graphs reused = 3 1.09.416.744 I slot print_timing: id 3 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.416.759 I slot release: id 3 | task 267 | stop processing: n_tokens = 134, truncated = 0 1.09.457.214 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.228 1.09.460.861 I slot launch_slot_: id 2 | task 275 | processing task, is_child = 0 1.09.462.945 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.276 1.09.463.019 I slot launch_slot_: id 3 | task 276 | processing task, is_child = 0 1.09.497.321 I slot print_timing: id 0 | task 270 | prompt eval time = 713.31 ms / 118 tokens ( 6.05 ms per token, 165.43 tokens per second) 1.09.497.326 I slot print_timing: id 0 | task 270 | eval time = 41.39 ms / 2 tokens ( 41.39 ms per token, 24.16 tokens per second) 1.09.497.326 I slot print_timing: id 0 | task 270 | total time = 754.70 ms / 120 tokens 1.09.497.327 I slot print_timing: id 0 | task 270 | graphs reused = 3 1.09.497.327 I slot print_timing: id 0 | task 270 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.497.343 I slot release: id 0 | task 270 | stop processing: n_tokens = 128, truncated = 0 1.09.498.523 I slot print_timing: id 1 | task 271 | prompt eval time = 714.46 ms / 159 tokens ( 4.49 ms per token, 222.55 tokens per second) 1.09.498.524 I slot print_timing: id 1 | task 271 | eval time = 41.31 ms / 2 tokens ( 41.31 ms per token, 24.21 tokens per second) 1.09.498.525 I slot print_timing: id 1 | task 271 | total time = 755.76 ms / 161 tokens 1.09.498.525 I slot print_timing: id 1 | task 271 | graphs reused = 3 1.09.498.525 I slot print_timing: id 1 | task 271 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.498.538 I slot release: id 1 | task 271 | stop processing: n_tokens = 169, truncated = 0 1.10.053.057 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.289 1.10.098.399 I slot launch_slot_: id 0 | task 279 | processing task, is_child = 0 1.10.101.350 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.219 1.10.101.420 I slot launch_slot_: id 1 | task 280 | processing task, is_child = 0 1.10.784.012 I slot print_timing: id 2 | task 275 | prompt eval time = 704.94 ms / 152 tokens ( 4.64 ms per token, 215.62 tokens per second) 1.10.784.020 I slot print_timing: id 2 | task 275 | eval time = 616.04 ms / 2 tokens ( 616.04 ms per token, 1.62 tokens per second) 1.10.784.020 I slot print_timing: id 2 | task 275 | total time = 1320.98 ms / 154 tokens 1.10.784.021 I slot print_timing: id 2 | task 275 | graphs reused = 3 1.10.784.021 I slot print_timing: id 2 | task 275 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.784.053 I slot release: id 2 | task 275 | stop processing: n_tokens = 162, truncated = 0 1.10.785.259 I slot print_timing: id 3 | task 276 | prompt eval time = 705.96 ms / 164 tokens ( 4.30 ms per token, 232.31 tokens per second) 1.10.785.261 I slot print_timing: id 3 | task 276 | eval time = 616.14 ms / 2 tokens ( 616.14 ms per token, 1.62 tokens per second) 1.10.785.262 I slot print_timing: id 3 | task 276 | total time = 1322.11 ms / 166 tokens 1.10.785.262 I slot print_timing: id 3 | task 276 | graphs reused = 3 1.10.785.263 I slot print_timing: id 3 | task 276 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.785.285 I slot release: id 3 | task 276 | stop processing: n_tokens = 174, truncated = 0 1.10.827.739 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.228 1.10.831.663 I slot launch_slot_: id 2 | task 284 | processing task, is_child = 0 1.10.836.122 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.314 (> 0.100 thold), f_keep = 0.213 1.10.836.732 I slot launch_slot_: id 3 | task 285 | processing task, is_child = 0 1.10.871.248 I slot print_timing: id 0 | task 279 | prompt eval time = 725.02 ms / 158 tokens ( 4.59 ms per token, 217.92 tokens per second) 1.10.871.250 I slot print_timing: id 0 | task 279 | eval time = 44.80 ms / 2 tokens ( 44.80 ms per token, 22.32 tokens per second) 1.10.871.250 I slot print_timing: id 0 | task 279 | total time = 769.82 ms / 160 tokens 1.10.871.250 I slot print_timing: id 0 | task 279 | graphs reused = 3 1.10.871.251 I slot print_timing: id 0 | task 279 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.871.273 I slot release: id 0 | task 279 | stop processing: n_tokens = 168, truncated = 0 1.11.331.133 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.220 1.11.336.321 I slot launch_slot_: id 0 | task 288 | processing task, is_child = 0 1.11.801.580 I slot print_timing: id 1 | task 280 | prompt eval time = 726.17 ms / 154 tokens ( 4.72 ms per token, 212.07 tokens per second) 1.11.801.582 I slot print_timing: id 1 | task 280 | eval time = 973.84 ms / 5 tokens ( 243.46 ms per token, 4.11 tokens per second) 1.11.801.583 I slot print_timing: id 1 | task 280 | total time = 1700.01 ms / 159 tokens 1.11.801.583 I slot print_timing: id 1 | task 280 | graphs reused = 3 1.11.801.583 I slot print_timing: id 1 | task 280 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.801.608 I slot release: id 1 | task 280 | stop processing: n_tokens = 167, truncated = 0 1.11.802.756 I slot print_timing: id 2 | task 284 | prompt eval time = 583.66 ms / 117 tokens ( 4.99 ms per token, 200.46 tokens per second) 1.11.802.762 I slot print_timing: id 2 | task 284 | eval time = 382.35 ms / 2 tokens ( 382.35 ms per token, 2.62 tokens per second) 1.11.802.764 I slot print_timing: id 2 | task 284 | total time = 966.02 ms / 119 tokens 1.11.802.764 I slot print_timing: id 2 | task 284 | graphs reused = 3 1.11.802.765 I slot print_timing: id 2 | task 284 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.802.783 I slot release: id 2 | task 284 | stop processing: n_tokens = 127, truncated = 0 1.11.803.972 I slot print_timing: id 3 | task 285 | prompt eval time = 584.62 ms / 109 tokens ( 5.36 ms per token, 186.45 tokens per second) 1.11.803.974 I slot print_timing: id 3 | task 285 | eval time = 382.49 ms / 2 tokens ( 382.49 ms per token, 2.61 tokens per second) 1.11.803.974 I slot print_timing: id 3 | task 285 | total time = 967.11 ms / 111 tokens 1.11.803.975 I slot print_timing: id 3 | task 285 | graphs reused = 3 1.11.803.975 I slot print_timing: id 3 | task 285 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.803.987 I slot release: id 3 | task 285 | stop processing: n_tokens = 119, truncated = 0 1.11.839.819 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.330 (> 0.100 thold), f_keep = 0.222 1.11.843.827 I slot launch_slot_: id 1 | task 292 | processing task, is_child = 0 1.11.845.996 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.291 1.11.846.558 I slot launch_slot_: id 2 | task 293 | processing task, is_child = 0 1.11.846.586 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.311 1.11.846.648 I slot launch_slot_: id 3 | task 294 | processing task, is_child = 0 1.11.880.353 I slot print_timing: id 0 | task 288 | prompt eval time = 503.48 ms / 188 tokens ( 2.68 ms per token, 373.40 tokens per second) 1.11.880.355 I slot print_timing: id 0 | task 288 | eval time = 40.54 ms / 2 tokens ( 40.54 ms per token, 24.67 tokens per second) 1.11.880.356 I slot print_timing: id 0 | task 288 | total time = 544.02 ms / 190 tokens 1.11.880.356 I slot print_timing: id 0 | task 288 | graphs reused = 3 1.11.880.356 I slot print_timing: id 0 | task 288 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.880.374 I slot release: id 0 | task 288 | stop processing: n_tokens = 198, truncated = 0 1.12.516.118 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.187 1.12.561.228 I slot launch_slot_: id 0 | task 297 | processing task, is_child = 0 1.12.910.298 I slot print_timing: id 1 | task 292 | prompt eval time = 793.27 ms / 103 tokens ( 7.70 ms per token, 129.84 tokens per second) 1.12.910.304 I slot print_timing: id 1 | task 292 | eval time = 270.37 ms / 2 tokens ( 270.37 ms per token, 3.70 tokens per second) 1.12.910.304 I slot print_timing: id 1 | task 292 | total time = 1063.64 ms / 105 tokens 1.12.910.305 I slot print_timing: id 1 | task 292 | graphs reused = 3 1.12.910.305 I slot print_timing: id 1 | task 292 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.910.331 I slot release: id 1 | task 292 | stop processing: n_tokens = 113, truncated = 0 1.12.911.439 I slot print_timing: id 2 | task 293 | prompt eval time = 794.37 ms / 113 tokens ( 7.03 ms per token, 142.25 tokens per second) 1.12.911.442 I slot print_timing: id 2 | task 293 | eval time = 270.29 ms / 2 tokens ( 270.29 ms per token, 3.70 tokens per second) 1.12.911.443 I slot print_timing: id 2 | task 293 | total time = 1064.66 ms / 115 tokens 1.12.911.443 I slot print_timing: id 2 | task 293 | graphs reused = 3 1.12.911.443 I slot print_timing: id 2 | task 293 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.911.468 I slot release: id 2 | task 293 | stop processing: n_tokens = 123, truncated = 0 1.12.912.604 I slot print_timing: id 3 | task 294 | prompt eval time = 795.34 ms / 125 tokens ( 6.36 ms per token, 157.17 tokens per second) 1.12.912.606 I slot print_timing: id 3 | task 294 | eval time = 270.36 ms / 2 tokens ( 270.36 ms per token, 3.70 tokens per second) 1.12.912.606 I slot print_timing: id 3 | task 294 | total time = 1065.70 ms / 127 tokens 1.12.912.607 I slot print_timing: id 3 | task 294 | graphs reused = 3 1.12.912.607 I slot print_timing: id 3 | task 294 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.912.621 I slot release: id 3 | task 294 | stop processing: n_tokens = 135, truncated = 0 1.12.947.441 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.327 1.12.948.629 I slot launch_slot_: id 1 | task 301 | processing task, is_child = 0 1.12.953.232 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.301 1.12.953.303 I slot launch_slot_: id 2 | task 302 | processing task, is_child = 0 1.12.953.331 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.274 1.12.953.932 I slot launch_slot_: id 3 | task 303 | processing task, is_child = 0 1.12.987.449 I slot print_timing: id 0 | task 297 | prompt eval time = 386.20 ms / 128 tokens ( 3.02 ms per token, 331.43 tokens per second) 1.12.987.450 I slot print_timing: id 0 | task 297 | eval time = 40.01 ms / 2 tokens ( 40.01 ms per token, 24.99 tokens per second) 1.12.987.451 I slot print_timing: id 0 | task 297 | total time = 426.21 ms / 130 tokens 1.12.987.451 I slot print_timing: id 0 | task 297 | graphs reused = 3 1.12.987.452 I slot print_timing: id 0 | task 297 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.987.468 I slot release: id 0 | task 297 | stop processing: n_tokens = 138, truncated = 0 1.13.779.746 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.268 1.13.861.476 I slot launch_slot_: id 0 | task 306 | processing task, is_child = 0 1.14.263.215 I slot print_timing: id 3 | task 303 | prompt eval time = 990.20 ms / 145 tokens ( 6.83 ms per token, 146.44 tokens per second) 1.14.263.222 I slot print_timing: id 3 | task 303 | eval time = 318.85 ms / 2 tokens ( 318.85 ms per token, 3.14 tokens per second) 1.14.263.222 I slot print_timing: id 3 | task 303 | total time = 1309.05 ms / 147 tokens 1.14.263.223 I slot print_timing: id 3 | task 303 | graphs reused = 3 1.14.263.224 I slot print_timing: id 3 | task 303 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.263.261 I slot release: id 3 | task 303 | stop processing: n_tokens = 155, truncated = 0 1.14.332.887 I slot print_timing: id 2 | task 302 | prompt eval time = 989.20 ms / 166 tokens ( 5.96 ms per token, 167.81 tokens per second) 1.14.332.890 I slot print_timing: id 2 | task 302 | eval time = 389.62 ms / 3 tokens ( 194.81 ms per token, 5.13 tokens per second) 1.14.332.891 I slot print_timing: id 2 | task 302 | total time = 1378.83 ms / 169 tokens 1.14.332.891 I slot print_timing: id 2 | task 302 | graphs reused = 3 1.14.332.892 I slot print_timing: id 2 | task 302 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.332.909 I slot release: id 2 | task 302 | stop processing: n_tokens = 177, truncated = 0 1.14.332.915 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.209 1.14.337.221 I slot launch_slot_: id 2 | task 310 | processing task, is_child = 0 1.14.340.747 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.239 1.14.341.303 I slot launch_slot_: id 3 | task 311 | processing task, is_child = 0 1.14.375.721 I slot print_timing: id 0 | task 306 | prompt eval time = 469.28 ms / 139 tokens ( 3.38 ms per token, 296.20 tokens per second) 1.14.375.723 I slot print_timing: id 0 | task 306 | eval time = 44.95 ms / 2 tokens ( 44.95 ms per token, 22.25 tokens per second) 1.14.375.724 I slot print_timing: id 0 | task 306 | total time = 514.23 ms / 141 tokens 1.14.375.724 I slot print_timing: id 0 | task 306 | graphs reused = 3 1.14.375.724 I slot print_timing: id 0 | task 306 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.375.738 I slot release: id 0 | task 306 | stop processing: n_tokens = 149, truncated = 0 1.14.982.315 I slot print_timing: id 1 | task 301 | prompt eval time = 988.22 ms / 127 tokens ( 7.78 ms per token, 128.51 tokens per second) 1.14.982.318 I slot print_timing: id 1 | task 301 | eval time = 1040.15 ms / 5 tokens ( 260.04 ms per token, 3.85 tokens per second) 1.14.982.319 I slot print_timing: id 1 | task 301 | total time = 2028.37 ms / 132 tokens 1.14.982.319 I slot print_timing: id 1 | task 301 | graphs reused = 3 1.14.982.320 I slot print_timing: id 1 | task 301 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.982.343 I slot release: id 1 | task 301 | stop processing: n_tokens = 140, truncated = 0 1.14.982.351 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.248 1.14.988.445 I slot launch_slot_: id 0 | task 314 | processing task, is_child = 0 1.14.989.593 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.264 1.14.989.656 I slot launch_slot_: id 1 | task 315 | processing task, is_child = 0 1.15.672.784 I slot print_timing: id 3 | task 311 | prompt eval time = 714.91 ms / 161 tokens ( 4.44 ms per token, 225.20 tokens per second) 1.15.672.790 I slot print_timing: id 3 | task 311 | eval time = 616.43 ms / 2 tokens ( 616.43 ms per token, 1.62 tokens per second) 1.15.672.791 I slot print_timing: id 3 | task 311 | total time = 1331.34 ms / 163 tokens 1.15.672.792 I slot print_timing: id 3 | task 311 | graphs reused = 3 1.15.672.792 I slot print_timing: id 3 | task 311 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.672.824 I slot release: id 3 | task 311 | stop processing: n_tokens = 171, truncated = 0 1.15.733.611 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.216 1.15.737.486 I slot launch_slot_: id 3 | task 319 | processing task, is_child = 0 1.15.771.871 I slot print_timing: id 0 | task 314 | prompt eval time = 741.67 ms / 142 tokens ( 5.22 ms per token, 191.46 tokens per second) 1.15.771.876 I slot print_timing: id 0 | task 314 | eval time = 40.54 ms / 2 tokens ( 40.54 ms per token, 24.67 tokens per second) 1.15.771.876 I slot print_timing: id 0 | task 314 | total time = 782.21 ms / 144 tokens 1.15.771.876 I slot print_timing: id 0 | task 314 | graphs reused = 3 1.15.771.877 I slot print_timing: id 0 | task 314 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.771.895 I slot release: id 0 | task 314 | stop processing: n_tokens = 152, truncated = 0 1.15.773.024 I slot print_timing: id 1 | task 315 | prompt eval time = 742.78 ms / 173 tokens ( 4.29 ms per token, 232.91 tokens per second) 1.15.773.026 I slot print_timing: id 1 | task 315 | eval time = 40.45 ms / 2 tokens ( 40.45 ms per token, 24.72 tokens per second) 1.15.773.026 I slot print_timing: id 1 | task 315 | total time = 783.24 ms / 175 tokens 1.15.773.026 I slot print_timing: id 1 | task 315 | graphs reused = 3 1.15.773.027 I slot print_timing: id 1 | task 315 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.773.038 I slot release: id 1 | task 315 | stop processing: n_tokens = 183, truncated = 0 1.16.039.337 I slot print_timing: id 2 | task 310 | prompt eval time = 713.93 ms / 124 tokens ( 5.76 ms per token, 173.69 tokens per second) 1.16.039.339 I slot print_timing: id 2 | task 310 | eval time = 984.10 ms / 5 tokens ( 246.02 ms per token, 4.06 tokens per second) 1.16.039.340 I slot print_timing: id 2 | task 310 | total time = 1698.02 ms / 129 tokens 1.16.039.340 I slot print_timing: id 2 | task 310 | graphs reused = 3 1.16.039.340 I slot print_timing: id 2 | task 310 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.039.365 I slot release: id 2 | task 310 | stop processing: n_tokens = 137, truncated = 0 1.16.039.372 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.243 1.16.043.648 I slot launch_slot_: id 0 | task 322 | processing task, is_child = 0 1.16.049.098 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.202 1.16.049.169 I slot launch_slot_: id 1 | task 323 | processing task, is_child = 0 1.16.049.198 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.325 (> 0.100 thold), f_keep = 0.270 1.16.049.261 I slot launch_slot_: id 2 | task 324 | processing task, is_child = 0 1.17.113.578 I slot print_timing: id 0 | task 322 | prompt eval time = 1026.73 ms / 190 tokens ( 5.40 ms per token, 185.05 tokens per second) 1.17.113.583 I slot print_timing: id 0 | task 322 | eval time = 37.58 ms / 2 tokens ( 37.58 ms per token, 26.61 tokens per second) 1.17.113.584 I slot print_timing: id 0 | task 322 | total time = 1064.31 ms / 192 tokens 1.17.113.584 I slot print_timing: id 0 | task 322 | graphs reused = 3 1.17.113.584 I slot print_timing: id 0 | task 322 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.113.607 I slot release: id 0 | task 322 | stop processing: n_tokens = 200, truncated = 0 1.17.117.031 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.185 1.17.122.632 I slot launch_slot_: id 0 | task 329 | processing task, is_child = 0 1.17.172.962 I slot print_timing: id 1 | task 323 | prompt eval time = 1027.83 ms / 162 tokens ( 6.34 ms per token, 157.61 tokens per second) 1.17.172.967 I slot print_timing: id 1 | task 323 | eval time = 95.70 ms / 3 tokens ( 47.85 ms per token, 20.90 tokens per second) 1.17.172.968 I slot print_timing: id 1 | task 323 | total time = 1123.53 ms / 165 tokens 1.17.172.969 I slot print_timing: id 1 | task 323 | graphs reused = 3 1.17.172.969 I slot print_timing: id 1 | task 323 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.172.989 I slot release: id 1 | task 323 | stop processing: n_tokens = 173, truncated = 0 1.17.174.208 I slot print_timing: id 2 | task 324 | prompt eval time = 1028.95 ms / 105 tokens ( 9.80 ms per token, 102.05 tokens per second) 1.17.174.211 I slot print_timing: id 2 | task 324 | eval time = 95.68 ms / 3 tokens ( 47.84 ms per token, 20.90 tokens per second) 1.17.174.211 I slot print_timing: id 2 | task 324 | total time = 1124.63 ms / 108 tokens 1.17.174.211 I slot print_timing: id 2 | task 324 | graphs reused = 3 1.17.174.212 I slot print_timing: id 2 | task 324 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.174.224 I slot release: id 2 | task 324 | stop processing: n_tokens = 116, truncated = 0 1.17.175.303 I slot print_timing: id 3 | task 319 | prompt eval time = 374.42 ms / 122 tokens ( 3.07 ms per token, 325.83 tokens per second) 1.17.175.305 I slot print_timing: id 3 | task 319 | eval time = 1063.38 ms / 5 tokens ( 265.85 ms per token, 3.76 tokens per second) 1.17.175.305 I slot print_timing: id 3 | task 319 | total time = 1437.81 ms / 127 tokens 1.17.175.305 I slot print_timing: id 3 | task 319 | graphs reused = 3 1.17.175.305 I slot print_timing: id 3 | task 319 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.175.320 I slot release: id 3 | task 319 | stop processing: n_tokens = 135, truncated = 0 1.17.177.539 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.214 1.17.460.407 I slot launch_slot_: id 1 | task 332 | processing task, is_child = 0 1.17.463.272 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.319 1.17.463.339 I slot launch_slot_: id 2 | task 333 | processing task, is_child = 0 1.18.083.685 I slot print_timing: id 0 | task 329 | prompt eval time = 403.08 ms / 136 tokens ( 2.96 ms per token, 337.40 tokens per second) 1.18.083.688 I slot print_timing: id 0 | task 329 | eval time = 557.96 ms / 2 tokens ( 557.96 ms per token, 1.79 tokens per second) 1.18.083.688 I slot print_timing: id 0 | task 329 | total time = 961.04 ms / 138 tokens 1.18.083.689 I slot print_timing: id 0 | task 329 | graphs reused = 3 1.18.083.689 I slot print_timing: id 0 | task 329 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.083.716 I slot release: id 0 | task 329 | stop processing: n_tokens = 146, truncated = 0 1.18.156.478 I slot print_timing: id 1 | task 332 | prompt eval time = 658.51 ms / 126 tokens ( 5.23 ms per token, 191.34 tokens per second) 1.18.156.486 I slot print_timing: id 1 | task 332 | eval time = 34.11 ms / 2 tokens ( 34.11 ms per token, 29.32 tokens per second) 1.18.156.486 I slot print_timing: id 1 | task 332 | total time = 692.62 ms / 128 tokens 1.18.156.487 I slot print_timing: id 1 | task 332 | graphs reused = 3 1.18.156.487 I slot print_timing: id 1 | task 332 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.156.504 I slot release: id 1 | task 332 | stop processing: n_tokens = 136, truncated = 0 1.18.157.598 I slot print_timing: id 2 | task 333 | prompt eval time = 659.69 ms / 146 tokens ( 4.52 ms per token, 221.32 tokens per second) 1.18.157.599 I slot print_timing: id 2 | task 333 | eval time = 33.92 ms / 2 tokens ( 33.92 ms per token, 29.48 tokens per second) 1.18.157.600 I slot print_timing: id 2 | task 333 | total time = 693.61 ms / 148 tokens 1.18.157.600 I slot print_timing: id 2 | task 333 | graphs reused = 3 1.18.157.600 I slot print_timing: id 2 | task 333 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.157.609 I slot release: id 2 | task 333 | stop processing: n_tokens = 156, truncated = 0 1.18.173.321 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 135, t_last = 333846389133 1.18.173.378 I slot launch_slot_: id 3 | task 339 | processing task, is_child = 0 1.18.183.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 146, t_last = 333847297529 1.18.183.368 I slot launch_slot_: id 0 | task 338 | processing task, is_child = 0 1.18.183.425 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 136, t_last = 333847370317 1.18.183.480 I slot launch_slot_: id 1 | task 340 | processing task, is_child = 0 1.18.183.514 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 156, t_last = 333847371422 1.18.183.555 I slot launch_slot_: id 2 | task 341 | processing task, is_child = 0 1.21.877.142 I slot print_timing: id 0 | task 338 | prompt processing, n_tokens = 674, progress = 0.57, t = 3.69 s / 182.48 tokens per second 1.21.964.277 I slot print_timing: id 1 | task 340 | prompt processing, n_tokens = 655, progress = 0.56, t = 3.69 s / 177.34 tokens per second 1.21.970.653 I slot print_timing: id 2 | task 341 | prompt processing, n_tokens = 683, progress = 0.57, t = 3.69 s / 184.93 tokens per second 1.21.975.563 I slot print_timing: id 3 | task 339 | prompt processing, n_tokens = 36, progress = 0.04, t = 3.69 s / 9.75 tokens per second 1.25.090.417 I slot print_timing: id 0 | task 338 | prompt processing, n_tokens = 1086, progress = 0.91, t = 6.91 s / 157.24 tokens per second 1.25.557.730 I slot print_timing: id 1 | task 340 | prompt processing, n_tokens = 1086, progress = 0.93, t = 6.91 s / 157.24 tokens per second 1.25.563.556 I slot print_timing: id 2 | task 341 | prompt processing, n_tokens = 1086, progress = 0.91, t = 6.91 s / 157.24 tokens per second 1.25.568.482 I slot print_timing: id 3 | task 339 | prompt processing, n_tokens = 670, progress = 0.57, t = 6.91 s / 97.01 tokens per second 1.26.454.039 I slot print_timing: id 0 | task 338 | prompt processing, n_tokens = 1186, progress = 1.00, t = 8.27 s / 143.40 tokens per second 1.27.045.457 I slot print_timing: id 1 | task 340 | prompt processing, n_tokens = 1167, progress = 1.00, t = 8.27 s / 141.11 tokens per second 1.27.051.924 I slot print_timing: id 2 | task 341 | prompt processing, n_tokens = 1195, progress = 1.00, t = 8.27 s / 144.49 tokens per second 1.27.056.922 I slot print_timing: id 3 | task 339 | prompt processing, n_tokens = 1086, progress = 0.92, t = 8.27 s / 131.32 tokens per second 1.27.319.955 I slot print_timing: id 3 | task 339 | prompt processing, n_tokens = 1182, progress = 1.00, t = 9.13 s / 129.43 tokens per second 1.29.886.238 I slot print_timing: id 1 | task 340 | prompt eval time = 9135.03 ms / 1171 tokens ( 7.80 ms per token, 128.19 tokens per second) 1.29.886.245 I slot print_timing: id 1 | task 340 | eval time = 2567.53 ms / 63 tokens ( 41.41 ms per token, 24.15 tokens per second) 1.29.886.245 I slot print_timing: id 1 | task 340 | total time = 11702.55 ms / 1234 tokens 1.29.886.246 I slot print_timing: id 1 | task 340 | graphs reused = 64 1.29.886.247 I slot print_timing: id 1 | task 340 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.886.333 I slot release: id 1 | task 340 | stop processing: n_tokens = 1242, truncated = 0 1.29.947.219 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.898 1.29.947.245 I slot launch_slot_: id 1 | task 409 | processing task, is_child = 0 1.30.900.313 I slot print_timing: id 3 | task 339 | prompt eval time = 9214.47 ms / 1186 tokens ( 7.77 ms per token, 128.71 tokens per second) 1.30.900.320 I slot print_timing: id 3 | task 339 | eval time = 3501.99 ms / 78 tokens ( 45.48 ms per token, 21.99 tokens per second) 1.30.900.321 I slot print_timing: id 3 | task 339 | total time = 12716.45 ms / 1264 tokens 1.30.900.321 I slot print_timing: id 3 | task 339 | graphs reused = 75 1.30.900.322 I slot print_timing: id 3 | task 339 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.900.386 I slot release: id 3 | task 339 | stop processing: n_tokens = 1272, truncated = 0 1.30.939.864 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 1.30.939.886 I slot launch_slot_: id 3 | task 426 | processing task, is_child = 0 1.32.033.665 I slot print_timing: id 0 | task 338 | n_gen = 100, tg = 20.99 t/s, tg_3s = 21.20 t/s 1.32.037.072 I slot print_timing: id 2 | task 341 | n_gen = 100, tg = 20.99 t/s, tg_3s = 21.20 t/s 1.32.567.756 I slot print_timing: id 0 | task 338 | prompt eval time = 9133.91 ms / 1190 tokens ( 7.68 ms per token, 130.28 tokens per second) 1.32.567.763 I slot print_timing: id 0 | task 338 | eval time = 5250.28 ms / 113 tokens ( 46.88 ms per token, 21.33 tokens per second) 1.32.567.764 I slot print_timing: id 0 | task 338 | total time = 14384.19 ms / 1303 tokens 1.32.567.765 I slot print_timing: id 0 | task 338 | graphs reused = 105 1.32.567.765 I slot print_timing: id 0 | task 338 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.567.833 I slot release: id 0 | task 338 | stop processing: n_tokens = 1311, truncated = 0 1.32.612.334 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.850 1.32.612.360 I slot launch_slot_: id 0 | task 461 | processing task, is_child = 0 1.34.990.997 I slot print_timing: id 1 | task 409 | n_gen = 100, tg = 21.41 t/s, tg_3s = 21.63 t/s 1.35.075.010 I slot print_timing: id 2 | task 341 | n_gen = 167, tg = 21.41 t/s, tg_3s = 22.05 t/s 1.35.652.000 I slot print_timing: id 3 | task 426 | n_gen = 100, tg = 22.80 t/s, tg_3s = 23.03 t/s 1.36.304.923 I slot print_timing: id 1 | task 409 | prompt eval time = 420.00 ms / 107 tokens ( 3.93 ms per token, 254.76 tokens per second) 1.36.304.930 I slot print_timing: id 1 | task 409 | eval time = 5937.67 ms / 132 tokens ( 45.33 ms per token, 22.06 tokens per second) 1.36.304.930 I slot print_timing: id 1 | task 409 | total time = 6357.67 ms / 239 tokens 1.36.304.931 I slot print_timing: id 1 | task 409 | graphs reused = 186 1.36.304.932 I slot print_timing: id 1 | task 409 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.304.999 I slot release: id 1 | task 409 | stop processing: n_tokens = 1353, truncated = 0 1.36.366.061 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.824 1.36.366.090 I slot launch_slot_: id 1 | task 546 | processing task, is_child = 0 1.37.356.100 I slot print_timing: id 0 | task 461 | n_gen = 100, tg = 22.61 t/s, tg_3s = 22.84 t/s 1.38.097.423 I slot print_timing: id 2 | task 341 | n_gen = 233, tg = 21.53 t/s, tg_3s = 21.84 t/s 1.38.675.862 I slot print_timing: id 3 | task 426 | n_gen = 166, tg = 22.40 t/s, tg_3s = 21.83 t/s 1.39.991.613 I slot print_timing: id 2 | task 341 | prompt eval time = 9136.17 ms / 1199 tokens ( 7.62 ms per token, 131.24 tokens per second) 1.39.991.620 I slot print_timing: id 2 | task 341 | eval time = 12671.67 ms / 279 tokens ( 45.58 ms per token, 21.94 tokens per second) 1.39.991.621 I slot print_timing: id 2 | task 341 | total time = 21807.84 ms / 1478 tokens 1.39.991.621 I slot print_timing: id 2 | task 341 | graphs reused = 264 1.39.991.622 I slot print_timing: id 2 | task 341 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.991.678 I slot release: id 2 | task 341 | stop processing: n_tokens = 1486, truncated = 0 1.40.051.331 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.750 1.40.051.364 I slot launch_slot_: id 2 | task 629 | processing task, is_child = 0 1.40.359.671 I slot print_timing: id 0 | task 461 | n_gen = 166, tg = 22.35 t/s, tg_3s = 21.97 t/s 1.40.692.552 I slot print_timing: id 3 | task 426 | prompt eval time = 369.46 ms / 114 tokens ( 3.24 ms per token, 308.56 tokens per second) 1.40.692.556 I slot print_timing: id 3 | task 426 | eval time = 9383.19 ms / 207 tokens ( 45.55 ms per token, 21.95 tokens per second) 1.40.692.556 I slot print_timing: id 3 | task 426 | total time = 9752.66 ms / 321 tokens 1.40.692.557 I slot print_timing: id 3 | task 426 | graphs reused = 269 1.40.692.558 I slot print_timing: id 3 | task 426 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.692.611 I slot release: id 3 | task 426 | stop processing: n_tokens = 1435, truncated = 0 1.40.733.434 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.777 1.40.733.465 I slot launch_slot_: id 3 | task 639 | processing task, is_child = 0 1.41.476.374 I slot print_timing: id 1 | task 546 | n_gen = 100, tg = 20.87 t/s, tg_3s = 21.08 t/s 1.42.263.091 I slot print_timing: id 0 | task 461 | prompt eval time = 364.77 ms / 117 tokens ( 3.12 ms per token, 320.75 tokens per second) 1.42.263.099 I slot print_timing: id 0 | task 461 | eval time = 9285.94 ms / 203 tokens ( 45.97 ms per token, 21.75 tokens per second) 1.42.263.099 I slot print_timing: id 0 | task 461 | total time = 9650.71 ms / 320 tokens 1.42.263.100 I slot print_timing: id 0 | task 461 | graphs reused = 295 1.42.263.100 I slot print_timing: id 0 | task 461 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.263.172 I slot release: id 0 | task 461 | stop processing: n_tokens = 1434, truncated = 0 1.42.307.705 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.778 1.42.307.735 I slot launch_slot_: id 0 | task 670 | processing task, is_child = 0 1.42.655.268 I slot print_timing: id 1 | task 546 | prompt eval time = 366.62 ms / 89 tokens ( 4.12 ms per token, 242.76 tokens per second) 1.42.655.274 I slot print_timing: id 1 | task 546 | eval time = 5922.55 ms / 123 tokens ( 48.55 ms per token, 20.60 tokens per second) 1.42.655.274 I slot print_timing: id 1 | task 546 | total time = 6289.17 ms / 212 tokens 1.42.655.274 I slot print_timing: id 1 | task 546 | graphs reused = 296 1.42.655.275 I slot print_timing: id 1 | task 546 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.655.324 I slot release: id 1 | task 546 | stop processing: n_tokens = 1326, truncated = 0 1.42.712.438 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.841 1.42.712.460 I slot launch_slot_: id 1 | task 675 | processing task, is_child = 0 1.45.381.115 I slot print_timing: id 2 | task 629 | n_gen = 100, tg = 20.10 t/s, tg_3s = 20.30 t/s 1.45.751.040 I slot print_timing: id 3 | task 639 | n_gen = 100, tg = 21.55 t/s, tg_3s = 21.77 t/s 1.46.241.404 I slot print_timing: id 2 | task 629 | prompt eval time = 404.29 ms / 118 tokens ( 3.43 ms per token, 291.87 tokens per second) 1.46.241.409 I slot print_timing: id 2 | task 629 | eval time = 5785.74 ms / 121 tokens ( 48.21 ms per token, 20.74 tokens per second) 1.46.241.409 I slot print_timing: id 2 | task 629 | total time = 6190.02 ms / 239 tokens 1.46.241.410 I slot print_timing: id 2 | task 629 | graphs reused = 372 1.46.241.411 I slot print_timing: id 2 | task 629 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.241.481 I slot release: id 2 | task 629 | stop processing: n_tokens = 1353, truncated = 0 1.46.301.178 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.824 1.46.301.206 I slot launch_slot_: id 2 | task 756 | processing task, is_child = 0 1.47.224.484 I slot print_timing: id 1 | task 675 | prompt eval time = 360.72 ms / 76 tokens ( 4.75 ms per token, 210.69 tokens per second) 1.47.224.490 I slot print_timing: id 1 | task 675 | eval time = 4151.30 ms / 95 tokens ( 44.16 ms per token, 22.64 tokens per second) 1.47.224.491 I slot print_timing: id 1 | task 675 | total time = 4512.01 ms / 171 tokens 1.47.224.491 I slot print_timing: id 1 | task 675 | graphs reused = 385 1.47.224.492 I slot print_timing: id 1 | task 675 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.224.548 I slot release: id 1 | task 675 | stop processing: n_tokens = 1285, truncated = 0 1.47.281.973 I slot print_timing: id 0 | task 670 | n_gen = 100, tg = 21.21 t/s, tg_3s = 21.42 t/s 1.47.285.594 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.868 1.47.285.618 I slot launch_slot_: id 1 | task 774 | processing task, is_child = 0 1.47.686.651 I slot print_timing: id 0 | task 670 | prompt eval time = 306.79 ms / 100 tokens ( 3.07 ms per token, 325.96 tokens per second) 1.47.686.657 I slot print_timing: id 0 | task 670 | eval time = 5072.12 ms / 103 tokens ( 49.73 ms per token, 20.11 tokens per second) 1.47.686.657 I slot print_timing: id 0 | task 670 | total time = 5378.91 ms / 203 tokens 1.47.686.657 I slot print_timing: id 0 | task 670 | graphs reused = 385 1.47.686.658 I slot print_timing: id 0 | task 670 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.686.702 I slot release: id 0 | task 670 | stop processing: n_tokens = 1317, truncated = 0 1.47.727.264 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.847 1.47.727.282 I slot launch_slot_: id 0 | task 779 | processing task, is_child = 0 1.48.772.380 I slot print_timing: id 3 | task 639 | n_gen = 154, tg = 20.09 t/s, tg_3s = 17.87 t/s 1.50.089.701 I slot print_timing: id 2 | task 756 | prompt eval time = 343.83 ms / 76 tokens ( 4.52 ms per token, 221.04 tokens per second) 1.50.089.706 I slot print_timing: id 2 | task 756 | eval time = 3444.66 ms / 72 tokens ( 48.52 ms per token, 20.61 tokens per second) 1.50.089.715 I slot print_timing: id 2 | task 756 | total time = 3788.49 ms / 148 tokens 1.50.089.716 I slot print_timing: id 2 | task 756 | graphs reused = 435 1.50.089.716 I slot print_timing: id 2 | task 756 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.089.798 I slot release: id 2 | task 756 | stop processing: n_tokens = 1262, truncated = 0 1.50.149.561 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.884 1.50.149.589 I slot launch_slot_: id 2 | task 833 | processing task, is_child = 0 1.51.791.722 I slot print_timing: id 3 | task 639 | n_gen = 219, tg = 20.50 t/s, tg_3s = 21.53 t/s 1.51.911.528 I slot print_timing: id 0 | task 779 | prompt eval time = 307.36 ms / 99 tokens ( 3.10 ms per token, 322.10 tokens per second) 1.51.911.537 I slot print_timing: id 0 | task 779 | eval time = 3876.88 ms / 87 tokens ( 45.08 ms per token, 22.18 tokens per second) 1.51.911.537 I slot print_timing: id 0 | task 779 | total time = 4184.24 ms / 186 tokens 1.51.911.538 I slot print_timing: id 0 | task 779 | graphs reused = 467 1.51.911.539 I slot print_timing: id 0 | task 779 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.911.624 I slot release: id 0 | task 779 | stop processing: n_tokens = 1300, truncated = 0 1.51.956.436 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.858 1.51.956.459 I slot launch_slot_: id 0 | task 870 | processing task, is_child = 0 1.52.445.803 I slot print_timing: id 1 | task 774 | n_gen = 100, tg = 20.63 t/s, tg_3s = 20.84 t/s 1.54.796.732 I slot print_timing: id 2 | task 833 | n_gen = 100, tg = 23.32 t/s, tg_3s = 23.56 t/s 1.54.798.298 I slot print_timing: id 3 | task 639 | prompt eval time = 423.94 ms / 145 tokens ( 2.92 ms per token, 342.03 tokens per second) 1.54.798.303 I slot print_timing: id 3 | task 639 | eval time = 13640.89 ms / 288 tokens ( 47.53 ms per token, 21.04 tokens per second) 1.54.798.304 I slot print_timing: id 3 | task 639 | total time = 14064.83 ms / 433 tokens 1.54.798.304 I slot print_timing: id 3 | task 639 | graphs reused = 529 1.54.798.305 I slot print_timing: id 3 | task 639 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.798.364 I slot release: id 3 | task 639 | stop processing: n_tokens = 1547, truncated = 0 1.54.837.745 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.721 1.54.837.770 I slot launch_slot_: id 3 | task 937 | processing task, is_child = 0 1.55.478.756 I slot print_timing: id 1 | task 774 | n_gen = 167, tg = 21.20 t/s, tg_3s = 22.09 t/s 1.56.556.354 I slot print_timing: id 0 | task 870 | n_gen = 100, tg = 22.78 t/s, tg_3s = 23.01 t/s 1.56.598.926 I slot print_timing: id 1 | task 774 | prompt eval time = 362.43 ms / 72 tokens ( 5.03 ms per token, 198.66 tokens per second) 1.56.598.932 I slot print_timing: id 1 | task 774 | eval time = 8950.88 ms / 194 tokens ( 46.38 ms per token, 21.56 tokens per second) 1.56.598.933 I slot print_timing: id 1 | task 774 | total time = 9313.30 ms / 266 tokens 1.56.598.933 I slot print_timing: id 1 | task 774 | graphs reused = 562 1.56.598.934 I slot print_timing: id 1 | task 774 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.598.988 I slot release: id 1 | task 774 | stop processing: n_tokens = 1380, truncated = 0 1.56.659.853 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.808 1.56.659.881 I slot launch_slot_: id 1 | task 975 | processing task, is_child = 0 1.57.216.630 I slot print_timing: id 0 | task 870 | prompt eval time = 253.21 ms / 62 tokens ( 4.08 ms per token, 244.86 tokens per second) 1.57.216.637 I slot print_timing: id 0 | task 870 | eval time = 5006.95 ms / 109 tokens ( 46.36 ms per token, 21.57 tokens per second) 1.57.216.638 I slot print_timing: id 0 | task 870 | total time = 5260.16 ms / 171 tokens 1.57.216.638 I slot print_timing: id 0 | task 870 | graphs reused = 566 1.57.216.639 I slot print_timing: id 0 | task 870 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.216.695 I slot release: id 0 | task 870 | stop processing: n_tokens = 1285, truncated = 0 1.57.258.840 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.868 1.57.258.865 I slot launch_slot_: id 0 | task 984 | processing task, is_child = 0 1.57.825.067 I slot print_timing: id 2 | task 833 | n_gen = 156, tg = 21.31 t/s, tg_3s = 18.49 t/s 1.59.718.087 I slot print_timing: id 3 | task 937 | n_gen = 100, tg = 21.94 t/s, tg_3s = 22.16 t/s 2.00.327.686 I slot print_timing: id 0 | task 984 | prompt eval time = 250.35 ms / 59 tokens ( 4.24 ms per token, 235.67 tokens per second) 2.00.327.692 I slot print_timing: id 0 | task 984 | eval time = 2818.46 ms / 70 tokens ( 40.85 ms per token, 24.48 tokens per second) 2.00.327.693 I slot print_timing: id 0 | task 984 | total time = 3068.81 ms / 129 tokens 2.00.327.694 I slot print_timing: id 0 | task 984 | graphs reused = 635 2.00.327.694 I slot print_timing: id 0 | task 984 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.327.756 I slot release: id 0 | task 984 | stop processing: n_tokens = 1243, truncated = 0 2.00.372.139 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.897 2.00.372.160 I slot launch_slot_: id 0 | task 1057 | processing task, is_child = 0 2.00.834.445 I slot print_timing: id 2 | task 833 | n_gen = 224, tg = 21.69 t/s, tg_3s = 22.60 t/s 2.01.046.959 I slot print_timing: id 1 | task 975 | prompt eval time = 362.27 ms / 74 tokens ( 4.90 ms per token, 204.27 tokens per second) 2.01.046.967 I slot print_timing: id 1 | task 975 | eval time = 4024.79 ms / 90 tokens ( 45.22 ms per token, 22.11 tokens per second) 2.01.046.969 I slot print_timing: id 1 | task 975 | total time = 4387.07 ms / 164 tokens 2.01.046.970 I slot print_timing: id 1 | task 975 | graphs reused = 644 2.01.046.970 I slot print_timing: id 1 | task 975 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.047.057 I slot release: id 1 | task 975 | stop processing: n_tokens = 1278, truncated = 0 2.01.108.284 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.872 2.01.108.310 I slot launch_slot_: id 1 | task 1070 | processing task, is_child = 0 2.02.741.192 I slot print_timing: id 3 | task 937 | n_gen = 161, tg = 21.23 t/s, tg_3s = 20.18 t/s 2.03.479.377 I slot print_timing: id 3 | task 937 | prompt eval time = 367.58 ms / 111 tokens ( 3.31 ms per token, 301.97 tokens per second) 2.03.479.381 I slot print_timing: id 3 | task 937 | eval time = 8274.02 ms / 179 tokens ( 46.48 ms per token, 21.51 tokens per second) 2.03.479.382 I slot print_timing: id 3 | task 937 | total time = 8641.60 ms / 290 tokens 2.03.479.383 I slot print_timing: id 3 | task 937 | graphs reused = 692 2.03.479.383 I slot print_timing: id 3 | task 937 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.479.438 I slot release: id 3 | task 937 | stop processing: n_tokens = 1404, truncated = 0 2.03.519.146 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.794 2.03.519.173 I slot launch_slot_: id 3 | task 1123 | processing task, is_child = 0 2.03.882.164 I slot print_timing: id 2 | task 833 | n_gen = 284, tg = 21.23 t/s, tg_3s = 19.69 t/s 2.04.459.020 I slot print_timing: id 1 | task 1070 | prompt eval time = 361.46 ms / 70 tokens ( 5.16 ms per token, 193.66 tokens per second) 2.04.459.028 I slot print_timing: id 1 | task 1070 | eval time = 2989.24 ms / 67 tokens ( 45.29 ms per token, 22.08 tokens per second) 2.04.459.028 I slot print_timing: id 1 | task 1070 | total time = 3350.70 ms / 137 tokens 2.04.459.029 I slot print_timing: id 1 | task 1070 | graphs reused = 704 2.04.459.030 I slot print_timing: id 1 | task 1070 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.459.096 I slot release: id 1 | task 1070 | stop processing: n_tokens = 1251, truncated = 0 2.04.520.042 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.891 2.04.520.067 I slot launch_slot_: id 1 | task 1141 | processing task, is_child = 0 2.05.570.407 I slot print_timing: id 0 | task 1057 | n_gen = 100, tg = 20.22 t/s, tg_3s = 20.42 t/s 2.05.857.831 I slot print_timing: id 0 | task 1057 | prompt eval time = 301.61 ms / 76 tokens ( 3.97 ms per token, 251.98 tokens per second) 2.05.857.838 I slot print_timing: id 0 | task 1057 | eval time = 5184.06 ms / 107 tokens ( 48.91 ms per token, 20.45 tokens per second) 2.05.857.838 I slot print_timing: id 0 | task 1057 | total time = 5485.66 ms / 183 tokens 2.05.857.839 I slot print_timing: id 0 | task 1057 | graphs reused = 728 2.05.857.840 I slot print_timing: id 0 | task 1057 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.857.907 I slot release: id 0 | task 1057 | stop processing: n_tokens = 1297, truncated = 0 2.05.902.355 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.860 2.05.902.377 I slot launch_slot_: id 0 | task 1170 | processing task, is_child = 0 2.06.651.159 I slot print_timing: id 2 | task 833 | prompt eval time = 401.96 ms / 125 tokens ( 3.22 ms per token, 310.98 tokens per second) 2.06.651.167 I slot print_timing: id 2 | task 833 | eval time = 16099.60 ms / 340 tokens ( 47.49 ms per token, 21.06 tokens per second) 2.06.651.168 I slot print_timing: id 2 | task 833 | total time = 16501.56 ms / 465 tokens 2.06.651.169 I slot print_timing: id 2 | task 833 | graphs reused = 739 2.06.651.169 I slot print_timing: id 2 | task 833 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.651.255 I slot release: id 2 | task 833 | stop processing: n_tokens = 1579, truncated = 0 2.06.711.426 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.706 2.06.711.451 I slot launch_slot_: id 2 | task 1185 | processing task, is_child = 0 2.08.653.350 I slot print_timing: id 3 | task 1123 | n_gen = 100, tg = 20.75 t/s, tg_3s = 20.96 t/s 2.09.347.228 I slot print_timing: id 1 | task 1141 | prompt eval time = 313.12 ms / 65 tokens ( 4.82 ms per token, 207.59 tokens per second) 2.09.347.235 I slot print_timing: id 1 | task 1141 | eval time = 4514.03 ms / 100 tokens ( 45.60 ms per token, 21.93 tokens per second) 2.09.347.237 I slot print_timing: id 1 | task 1141 | total time = 4827.16 ms / 165 tokens 2.09.347.237 I slot print_timing: id 1 | task 1141 | graphs reused = 795 2.09.347.238 I slot print_timing: id 1 | task 1141 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.347.294 I slot release: id 1 | task 1141 | stop processing: n_tokens = 1279, truncated = 0 2.09.408.240 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.873 2.09.408.264 I slot launch_slot_: id 1 | task 1246 | processing task, is_child = 0 2.10.850.538 I slot print_timing: id 0 | task 1170 | n_gen = 100, tg = 21.31 t/s, tg_3s = 21.53 t/s 2.11.301.768 I slot print_timing: id 0 | task 1170 | prompt eval time = 302.60 ms / 71 tokens ( 4.26 ms per token, 234.63 tokens per second) 2.11.301.772 I slot print_timing: id 0 | task 1170 | eval time = 5096.77 ms / 111 tokens ( 46.33 ms per token, 21.58 tokens per second) 2.11.301.773 I slot print_timing: id 0 | task 1170 | total time = 5399.38 ms / 182 tokens 2.11.301.774 I slot print_timing: id 0 | task 1170 | graphs reused = 830 2.11.301.774 I slot print_timing: id 0 | task 1170 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.301.859 I slot release: id 0 | task 1170 | stop processing: n_tokens = 1296, truncated = 0 2.11.346.457 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.860 2.11.346.481 I slot launch_slot_: id 0 | task 1286 | processing task, is_child = 0 2.11.709.820 I slot print_timing: id 2 | task 1185 | n_gen = 100, tg = 21.06 t/s, tg_3s = 21.27 t/s 2.11.710.880 I slot print_timing: id 3 | task 1123 | n_gen = 159, tg = 20.18 t/s, tg_3s = 19.30 t/s 2.13.015.805 I slot print_timing: id 2 | task 1185 | prompt eval time = 297.96 ms / 62 tokens ( 4.81 ms per token, 208.08 tokens per second) 2.13.015.812 I slot print_timing: id 2 | task 1185 | eval time = 6006.39 ms / 132 tokens ( 45.85 ms per token, 21.81 tokens per second) 2.13.015.812 I slot print_timing: id 2 | task 1185 | total time = 6304.35 ms / 194 tokens 2.13.015.813 I slot print_timing: id 2 | task 1185 | graphs reused = 862 2.13.015.814 I slot print_timing: id 2 | task 1185 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.015.888 I slot release: id 2 | task 1185 | stop processing: n_tokens = 1308, truncated = 0 2.13.075.485 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.852 2.13.075.514 I slot launch_slot_: id 2 | task 1322 | processing task, is_child = 0 2.14.505.265 I slot print_timing: id 1 | task 1246 | n_gen = 100, tg = 21.17 t/s, tg_3s = 21.38 t/s 2.14.714.800 I slot print_timing: id 3 | task 1123 | n_gen = 224, tg = 20.59 t/s, tg_3s = 21.64 t/s 2.16.113.310 I slot print_timing: id 0 | task 1286 | n_gen = 100, tg = 22.47 t/s, tg_3s = 22.70 t/s 2.17.022.752 I slot print_timing: id 3 | task 1123 | prompt eval time = 364.10 ms / 106 tokens ( 3.43 ms per token, 291.13 tokens per second) 2.17.022.756 I slot print_timing: id 3 | task 1123 | eval time = 13139.46 ms / 280 tokens ( 47.09 ms per token, 21.23 tokens per second) 2.17.022.757 I slot print_timing: id 3 | task 1123 | total time = 13503.57 ms / 386 tokens 2.17.022.758 I slot print_timing: id 3 | task 1123 | graphs reused = 947 2.17.022.758 I slot print_timing: id 3 | task 1123 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.022.828 I slot release: id 3 | task 1123 | stop processing: n_tokens = 1500, truncated = 0 2.17.062.659 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.743 2.17.062.680 I slot launch_slot_: id 3 | task 1412 | processing task, is_child = 0 2.17.515.151 I slot print_timing: id 1 | task 1246 | n_gen = 169, tg = 21.85 t/s, tg_3s = 22.92 t/s 2.17.725.236 I slot print_timing: id 2 | task 1322 | n_gen = 100, tg = 23.31 t/s, tg_3s = 23.55 t/s 2.19.050.588 I slot print_timing: id 1 | task 1246 | prompt eval time = 419.74 ms / 105 tokens ( 4.00 ms per token, 250.16 tokens per second) 2.19.050.595 I slot print_timing: id 1 | task 1246 | eval time = 9222.58 ms / 206 tokens ( 44.99 ms per token, 22.23 tokens per second) 2.19.050.596 I slot print_timing: id 1 | task 1246 | total time = 9642.32 ms / 311 tokens 2.19.050.597 I slot print_timing: id 1 | task 1246 | graphs reused = 988 2.19.050.597 I slot print_timing: id 1 | task 1246 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.050.653 I slot release: id 1 | task 1246 | stop processing: n_tokens = 1426, truncated = 0 2.19.111.694 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.782 2.19.111.724 I slot launch_slot_: id 1 | task 1458 | processing task, is_child = 0 2.19.320.416 I slot print_timing: id 0 | task 1286 | n_gen = 169, tg = 22.07 t/s, tg_3s = 21.51 t/s 2.20.738.701 I slot print_timing: id 2 | task 1322 | n_gen = 167, tg = 22.86 t/s, tg_3s = 22.23 t/s 2.21.272.906 I slot print_timing: id 3 | task 1412 | prompt eval time = 258.89 ms / 68 tokens ( 3.81 ms per token, 262.66 tokens per second) 2.21.272.913 I slot print_timing: id 3 | task 1412 | eval time = 3951.33 ms / 91 tokens ( 43.90 ms per token, 22.78 tokens per second) 2.21.272.913 I slot print_timing: id 3 | task 1412 | total time = 4210.22 ms / 159 tokens 2.21.272.914 I slot print_timing: id 3 | task 1412 | graphs reused = 1032 2.21.272.914 I slot print_timing: id 3 | task 1412 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.272.974 I slot release: id 3 | task 1412 | stop processing: n_tokens = 1273, truncated = 0 2.21.312.473 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.876 2.21.312.496 I slot launch_slot_: id 3 | task 1507 | processing task, is_child = 0 2.22.060.903 I slot print_timing: id 1 | task 1458 | prompt eval time = 313.78 ms / 62 tokens ( 5.06 ms per token, 197.59 tokens per second) 2.22.060.911 I slot print_timing: id 1 | task 1458 | eval time = 2635.39 ms / 60 tokens ( 44.67 ms per token, 22.39 tokens per second) 2.22.060.912 I slot print_timing: id 1 | task 1458 | total time = 2949.17 ms / 122 tokens 2.22.060.913 I slot print_timing: id 1 | task 1458 | graphs reused = 1042 2.22.060.914 I slot print_timing: id 1 | task 1458 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.060.974 I slot release: id 1 | task 1458 | stop processing: n_tokens = 1236, truncated = 0 2.22.123.576 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.902 2.22.123.605 I slot launch_slot_: id 1 | task 1522 | processing task, is_child = 0 2.22.383.696 I slot print_timing: id 0 | task 1286 | n_gen = 231, tg = 21.54 t/s, tg_3s = 20.24 t/s 2.22.565.531 I slot print_timing: id 0 | task 1286 | prompt eval time = 361.21 ms / 111 tokens ( 3.25 ms per token, 307.30 tokens per second) 2.22.565.533 I slot print_timing: id 0 | task 1286 | eval time = 10857.83 ms / 234 tokens ( 46.60 ms per token, 21.46 tokens per second) 2.22.565.534 I slot print_timing: id 0 | task 1286 | total time = 11219.04 ms / 345 tokens 2.22.565.535 I slot print_timing: id 0 | task 1286 | graphs reused = 1043 2.22.565.535 I slot print_timing: id 0 | task 1286 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.565.600 I slot release: id 0 | task 1286 | stop processing: n_tokens = 1459, truncated = 0 2.22.606.395 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.764 2.22.606.417 I slot launch_slot_: id 0 | task 1528 | processing task, is_child = 0 2.23.769.983 I slot print_timing: id 2 | task 1322 | n_gen = 223, tg = 21.57 t/s, tg_3s = 18.47 t/s 2.25.371.905 I slot print_timing: id 3 | task 1507 | prompt eval time = 307.81 ms / 74 tokens ( 4.16 ms per token, 240.40 tokens per second) 2.25.371.909 I slot print_timing: id 3 | task 1507 | eval time = 3751.59 ms / 80 tokens ( 47.49 ms per token, 21.06 tokens per second) 2.25.371.910 I slot print_timing: id 3 | task 1507 | total time = 4059.40 ms / 154 tokens 2.25.371.910 I slot print_timing: id 3 | task 1507 | graphs reused = 1103 2.25.371.911 I slot print_timing: id 3 | task 1507 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.371.963 I slot release: id 3 | task 1507 | stop processing: n_tokens = 1268, truncated = 0 2.25.411.462 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.879 2.25.411.489 I slot launch_slot_: id 3 | task 1592 | processing task, is_child = 0 2.26.791.507 I slot print_timing: id 2 | task 1322 | n_gen = 291, tg = 21.78 t/s, tg_3s = 22.51 t/s 2.26.996.240 I slot print_timing: id 1 | task 1522 | n_gen = 100, tg = 21.96 t/s, tg_3s = 22.18 t/s 2.27.199.258 I slot print_timing: id 0 | task 1528 | n_gen = 100, tg = 23.09 t/s, tg_3s = 23.32 t/s 2.27.447.066 I slot print_timing: id 1 | task 1522 | prompt eval time = 363.98 ms / 80 tokens ( 4.55 ms per token, 219.79 tokens per second) 2.27.447.072 I slot print_timing: id 1 | task 1522 | eval time = 4959.47 ms / 111 tokens ( 45.09 ms per token, 22.18 tokens per second) 2.27.447.072 I slot print_timing: id 1 | task 1522 | total time = 5323.45 ms / 191 tokens 2.27.447.073 I slot print_timing: id 1 | task 1522 | graphs reused = 1143 2.27.447.074 I slot print_timing: id 1 | task 1522 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.447.125 I slot release: id 1 | task 1522 | stop processing: n_tokens = 1305, truncated = 0 2.27.508.227 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.854 2.27.508.252 I slot launch_slot_: id 1 | task 1638 | processing task, is_child = 0 2.28.183.958 I slot print_timing: id 2 | task 1322 | prompt eval time = 402.80 ms / 128 tokens ( 3.15 ms per token, 317.77 tokens per second) 2.28.183.963 I slot print_timing: id 2 | task 1322 | eval time = 14705.64 ms / 318 tokens ( 46.39 ms per token, 21.56 tokens per second) 2.28.183.964 I slot print_timing: id 2 | task 1322 | total time = 15108.44 ms / 446 tokens 2.28.183.964 I slot print_timing: id 2 | task 1322 | graphs reused = 1150 2.28.183.965 I slot print_timing: id 2 | task 1322 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.184.007 I slot release: id 2 | task 1322 | stop processing: n_tokens = 1560, truncated = 0 2.28.240.453 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 2.28.240.471 I slot launch_slot_: id 2 | task 1650 | processing task, is_child = 0 2.30.227.674 I slot print_timing: id 0 | task 1528 | n_gen = 160, tg = 21.73 t/s, tg_3s = 19.81 t/s 2.30.356.149 I slot print_timing: id 3 | task 1592 | n_gen = 100, tg = 21.37 t/s, tg_3s = 21.59 t/s 2.31.214.666 I slot print_timing: id 0 | task 1528 | prompt eval time = 304.97 ms / 88 tokens ( 3.47 ms per token, 288.55 tokens per second) 2.31.214.670 I slot print_timing: id 0 | task 1528 | eval time = 8303.27 ms / 184 tokens ( 45.37 ms per token, 22.04 tokens per second) 2.31.214.670 I slot print_timing: id 0 | task 1528 | total time = 8608.24 ms / 272 tokens 2.31.214.671 I slot print_timing: id 0 | task 1528 | graphs reused = 1213 2.31.214.672 I slot print_timing: id 0 | task 1528 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.214.726 I slot release: id 0 | task 1528 | stop processing: n_tokens = 1386, truncated = 0 2.31.259.342 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.804 2.31.259.368 I slot launch_slot_: id 0 | task 1718 | processing task, is_child = 0 2.32.483.965 I slot print_timing: id 1 | task 1638 | n_gen = 100, tg = 21.46 t/s, tg_3s = 21.68 t/s 2.32.935.377 I slot print_timing: id 2 | task 1650 | n_gen = 100, tg = 22.76 t/s, tg_3s = 22.99 t/s 2.32.936.949 I slot print_timing: id 3 | task 1592 | prompt eval time = 312.29 ms / 97 tokens ( 3.22 ms per token, 310.61 tokens per second) 2.32.936.951 I slot print_timing: id 3 | task 1592 | eval time = 7213.16 ms / 156 tokens ( 46.54 ms per token, 21.49 tokens per second) 2.32.936.955 I slot print_timing: id 3 | task 1592 | total time = 7525.45 ms / 253 tokens 2.32.936.956 I slot print_timing: id 3 | task 1592 | graphs reused = 1245 2.32.936.956 I slot print_timing: id 3 | task 1592 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.937.013 I slot release: id 3 | task 1592 | stop processing: n_tokens = 1367, truncated = 0 2.32.976.262 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.816 2.32.976.287 I slot launch_slot_: id 3 | task 1754 | processing task, is_child = 0 2.35.384.446 I slot print_timing: id 1 | task 1638 | prompt eval time = 362.19 ms / 71 tokens ( 5.10 ms per token, 196.03 tokens per second) 2.35.384.451 I slot print_timing: id 1 | task 1638 | eval time = 7514.00 ms / 164 tokens ( 46.10 ms per token, 21.69 tokens per second) 2.35.384.452 I slot print_timing: id 1 | task 1638 | total time = 7876.18 ms / 235 tokens 2.35.384.452 I slot print_timing: id 1 | task 1638 | graphs reused = 1294 2.35.384.453 I slot print_timing: id 1 | task 1638 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.384.519 I slot release: id 1 | task 1638 | stop processing: n_tokens = 1349, truncated = 0 2.35.445.516 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.827 2.35.445.543 I slot launch_slot_: id 1 | task 1808 | processing task, is_child = 0 2.35.967.932 I slot print_timing: id 2 | task 1650 | n_gen = 160, tg = 21.54 t/s, tg_3s = 19.79 t/s 2.36.244.754 I slot print_timing: id 0 | task 1718 | n_gen = 100, tg = 21.42 t/s, tg_3s = 21.64 t/s 2.36.835.110 I slot print_timing: id 2 | task 1650 | prompt eval time = 344.55 ms / 90 tokens ( 3.83 ms per token, 261.21 tokens per second) 2.36.835.114 I slot print_timing: id 2 | task 1650 | eval time = 8250.08 ms / 181 tokens ( 45.83 ms per token, 21.82 tokens per second) 2.36.835.115 I slot print_timing: id 2 | task 1650 | total time = 8594.63 ms / 271 tokens 2.36.835.115 I slot print_timing: id 2 | task 1650 | graphs reused = 1318 2.36.835.116 I slot print_timing: id 2 | task 1650 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.835.178 I slot release: id 2 | task 1650 | stop processing: n_tokens = 1385, truncated = 0 2.36.894.547 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.805 2.36.894.572 I slot launch_slot_: id 2 | task 1837 | processing task, is_child = 0 2.38.029.127 I slot print_timing: id 3 | task 1754 | n_gen = 100, tg = 21.11 t/s, tg_3s = 21.32 t/s 2.39.255.707 I slot print_timing: id 0 | task 1718 | n_gen = 165, tg = 21.49 t/s, tg_3s = 21.59 t/s 2.40.198.893 I slot print_timing: id 1 | task 1808 | n_gen = 100, tg = 22.56 t/s, tg_3s = 22.79 t/s 2.41.062.226 I slot print_timing: id 3 | task 1754 | n_gen = 174, tg = 22.40 t/s, tg_3s = 24.40 t/s 2.41.100.241 I slot print_timing: id 1 | task 1808 | prompt eval time = 365.83 ms / 94 tokens ( 3.89 ms per token, 256.95 tokens per second) 2.41.100.245 I slot print_timing: id 1 | task 1808 | eval time = 5288.86 ms / 122 tokens ( 43.71 ms per token, 22.88 tokens per second) 2.41.100.246 I slot print_timing: id 1 | task 1808 | total time = 5654.69 ms / 216 tokens 2.41.100.246 I slot print_timing: id 1 | task 1808 | graphs reused = 1410 2.41.100.247 I slot print_timing: id 1 | task 1808 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.100.317 I slot release: id 1 | task 1808 | stop processing: n_tokens = 1330, truncated = 0 2.41.161.211 I slot print_timing: id 3 | task 1754 | prompt eval time = 362.61 ms / 106 tokens ( 3.42 ms per token, 292.33 tokens per second) 2.41.161.218 I slot print_timing: id 3 | task 1754 | eval time = 7822.31 ms / 176 tokens ( 44.70 ms per token, 22.37 tokens per second) 2.41.161.218 I slot print_timing: id 3 | task 1754 | total time = 8184.92 ms / 282 tokens 2.41.161.219 I slot print_timing: id 3 | task 1754 | graphs reused = 1410 2.41.161.219 I slot print_timing: id 3 | task 1754 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.161.268 I slot release: id 3 | task 1754 | stop processing: n_tokens = 1396, truncated = 0 2.41.161.278 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.838 2.41.161.305 I slot launch_slot_: id 1 | task 1934 | processing task, is_child = 0 2.41.194.685 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.799 2.41.194.714 I slot launch_slot_: id 3 | task 1935 | processing task, is_child = 0 2.41.957.236 I slot print_timing: id 2 | task 1837 | n_gen = 100, tg = 21.22 t/s, tg_3s = 21.44 t/s 2.42.282.195 I slot print_timing: id 0 | task 1718 | n_gen = 224, tg = 20.92 t/s, tg_3s = 19.49 t/s 2.42.982.887 I slot print_timing: id 0 | task 1718 | prompt eval time = 364.39 ms / 125 tokens ( 2.92 ms per token, 343.04 tokens per second) 2.42.982.894 I slot print_timing: id 0 | task 1718 | eval time = 11359.12 ms / 241 tokens ( 47.33 ms per token, 21.13 tokens per second) 2.42.982.894 I slot print_timing: id 0 | task 1718 | total time = 11723.51 ms / 366 tokens 2.42.982.895 I slot print_timing: id 0 | task 1718 | graphs reused = 1437 2.42.982.895 I slot print_timing: id 0 | task 1718 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.982.964 I slot release: id 0 | task 1718 | stop processing: n_tokens = 1480, truncated = 0 2.43.027.096 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.753 2.43.027.119 I slot launch_slot_: id 0 | task 1967 | processing task, is_child = 0 2.44.963.392 I slot print_timing: id 2 | task 1837 | n_gen = 168, tg = 21.77 t/s, tg_3s = 22.62 t/s 2.46.108.692 I slot print_timing: id 1 | task 1934 | n_gen = 100, tg = 23.19 t/s, tg_3s = 23.42 t/s 2.46.112.002 I slot print_timing: id 3 | task 1935 | n_gen = 100, tg = 23.18 t/s, tg_3s = 23.42 t/s 2.46.521.431 I slot print_timing: id 3 | task 1935 | prompt eval time = 644.88 ms / 71 tokens ( 9.08 ms per token, 110.10 tokens per second) 2.46.521.437 I slot print_timing: id 3 | task 1935 | eval time = 4679.86 ms / 110 tokens ( 42.93 ms per token, 23.29 tokens per second) 2.46.521.438 I slot print_timing: id 3 | task 1935 | total time = 5324.74 ms / 181 tokens 2.46.521.439 I slot print_timing: id 3 | task 1935 | graphs reused = 1515 2.46.521.439 I slot print_timing: id 3 | task 1935 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.521.495 I slot release: id 3 | task 1935 | stop processing: n_tokens = 1295, truncated = 0 2.46.561.085 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.861 2.46.561.112 I slot launch_slot_: id 3 | task 2049 | processing task, is_child = 0 2.47.059.825 I slot print_timing: id 0 | task 1967 | prompt eval time = 303.71 ms / 81 tokens ( 3.75 ms per token, 266.71 tokens per second) 2.47.059.829 I slot print_timing: id 0 | task 1967 | eval time = 3728.99 ms / 87 tokens ( 43.36 ms per token, 23.06 tokens per second) 2.47.059.829 I slot print_timing: id 0 | task 1967 | total time = 4032.70 ms / 168 tokens 2.47.059.830 I slot print_timing: id 0 | task 1967 | graphs reused = 1519 2.47.059.830 I slot print_timing: id 0 | task 1967 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.059.877 I slot release: id 0 | task 1967 | stop processing: n_tokens = 1282, truncated = 0 2.47.101.460 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.870 2.47.101.481 I slot launch_slot_: id 0 | task 2058 | processing task, is_child = 0 2.47.976.794 I slot print_timing: id 2 | task 1837 | n_gen = 231, tg = 21.53 t/s, tg_3s = 20.91 t/s 2.48.222.583 I slot print_timing: id 2 | task 1837 | prompt eval time = 397.54 ms / 103 tokens ( 3.86 ms per token, 259.09 tokens per second) 2.48.222.589 I slot print_timing: id 2 | task 1837 | eval time = 10930.46 ms / 237 tokens ( 46.32 ms per token, 21.59 tokens per second) 2.48.222.589 I slot print_timing: id 2 | task 1837 | total time = 11328.00 ms / 340 tokens 2.48.222.590 I slot print_timing: id 2 | task 1837 | graphs reused = 1539 2.48.222.591 I slot print_timing: id 2 | task 1837 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.222.657 I slot release: id 2 | task 1837 | stop processing: n_tokens = 1454, truncated = 0 2.48.281.839 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.767 2.48.281.863 I slot launch_slot_: id 2 | task 2082 | processing task, is_child = 0 2.49.111.632 I slot print_timing: id 1 | task 1934 | n_gen = 156, tg = 21.31 t/s, tg_3s = 18.65 t/s 2.51.410.364 I slot print_timing: id 3 | task 2049 | n_gen = 100, tg = 21.80 t/s, tg_3s = 22.02 t/s 2.51.733.414 I slot print_timing: id 0 | task 2058 | n_gen = 100, tg = 22.87 t/s, tg_3s = 23.11 t/s 2.51.774.171 I slot print_timing: id 0 | task 2058 | prompt eval time = 304.03 ms / 77 tokens ( 3.95 ms per token, 253.27 tokens per second) 2.51.774.178 I slot print_timing: id 0 | task 2058 | eval time = 4368.65 ms / 101 tokens ( 43.69 ms per token, 22.89 tokens per second) 2.51.774.178 I slot print_timing: id 0 | task 2058 | total time = 4672.68 ms / 178 tokens 2.51.774.179 I slot print_timing: id 0 | task 2058 | graphs reused = 1615 2.51.774.179 I slot print_timing: id 0 | task 2058 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.774.235 I slot release: id 0 | task 2058 | stop processing: n_tokens = 1292, truncated = 0 2.51.818.545 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.863 2.51.818.567 I slot launch_slot_: id 0 | task 2163 | processing task, is_child = 0 2.52.127.112 I slot print_timing: id 1 | task 1934 | n_gen = 224, tg = 21.68 t/s, tg_3s = 22.55 t/s 2.52.530.998 I slot print_timing: id 1 | task 1934 | prompt eval time = 644.67 ms / 114 tokens ( 5.66 ms per token, 176.83 tokens per second) 2.52.531.006 I slot print_timing: id 1 | task 1934 | eval time = 10691.60 ms / 234 tokens ( 45.89 ms per token, 21.79 tokens per second) 2.52.531.006 I slot print_timing: id 1 | task 1934 | total time = 11336.27 ms / 348 tokens 2.52.531.007 I slot print_timing: id 1 | task 1934 | graphs reused = 1625 2.52.531.008 I slot print_timing: id 1 | task 1934 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.531.079 I slot release: id 1 | task 1934 | stop processing: n_tokens = 1462, truncated = 0 2.52.593.283 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.763 2.52.593.307 I slot launch_slot_: id 1 | task 2177 | processing task, is_child = 0 2.53.203.953 I slot print_timing: id 2 | task 2082 | n_gen = 100, tg = 21.63 t/s, tg_3s = 21.84 t/s 2.53.205.799 I slot print_timing: id 3 | task 2049 | prompt eval time = 307.74 ms / 74 tokens ( 4.16 ms per token, 240.46 tokens per second) 2.53.205.805 I slot print_timing: id 3 | task 2049 | eval time = 6336.94 ms / 131 tokens ( 48.75 ms per token, 20.51 tokens per second) 2.53.205.806 I slot print_timing: id 3 | task 2049 | total time = 6644.68 ms / 205 tokens 2.53.205.807 I slot print_timing: id 3 | task 2049 | graphs reused = 1630 2.53.205.807 I slot print_timing: id 3 | task 2049 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.205.879 I slot release: id 3 | task 2049 | stop processing: n_tokens = 1319, truncated = 0 2.53.246.319 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.845 2.53.246.344 I slot launch_slot_: id 3 | task 2187 | processing task, is_child = 0 2.55.020.389 I slot print_timing: id 2 | task 2082 | prompt eval time = 344.19 ms / 86 tokens ( 4.00 ms per token, 249.86 tokens per second) 2.55.020.395 I slot print_timing: id 2 | task 2082 | eval time = 6394.33 ms / 139 tokens ( 46.34 ms per token, 21.58 tokens per second) 2.55.020.396 I slot print_timing: id 2 | task 2082 | total time = 6738.52 ms / 225 tokens 2.55.020.396 I slot print_timing: id 2 | task 2082 | graphs reused = 1665 2.55.020.397 I slot print_timing: id 2 | task 2082 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.020.454 I slot release: id 2 | task 2082 | stop processing: n_tokens = 1339, truncated = 0 2.55.079.410 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.833 2.55.079.434 I slot launch_slot_: id 2 | task 2227 | processing task, is_child = 0 2.56.925.178 I slot print_timing: id 0 | task 2163 | n_gen = 100, tg = 20.63 t/s, tg_3s = 20.84 t/s 2.57.170.726 I slot print_timing: id 0 | task 2163 | prompt eval time = 307.47 ms / 97 tokens ( 3.17 ms per token, 315.47 tokens per second) 2.57.170.730 I slot print_timing: id 0 | task 2163 | eval time = 5044.68 ms / 106 tokens ( 48.04 ms per token, 20.81 tokens per second) 2.57.170.730 I slot print_timing: id 0 | task 2163 | total time = 5352.15 ms / 203 tokens 2.57.170.731 I slot print_timing: id 0 | task 2163 | graphs reused = 1707 2.57.170.732 I slot print_timing: id 0 | task 2163 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.170.788 I slot release: id 0 | task 2163 | stop processing: n_tokens = 1317, truncated = 0 2.57.214.900 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.847 2.57.214.922 I slot launch_slot_: id 0 | task 2275 | processing task, is_child = 0 2.57.676.168 I slot print_timing: id 1 | task 2177 | n_gen = 100, tg = 20.97 t/s, tg_3s = 21.18 t/s 2.58.047.679 I slot print_timing: id 3 | task 2187 | n_gen = 100, tg = 22.05 t/s, tg_3s = 22.27 t/s 2.58.498.181 I slot print_timing: id 2 | task 2227 | prompt eval time = 293.84 ms / 65 tokens ( 4.52 ms per token, 221.21 tokens per second) 2.58.498.187 I slot print_timing: id 2 | task 2227 | eval time = 3124.90 ms / 72 tokens ( 44.01 ms per token, 22.72 tokens per second) 2.58.498.188 I slot print_timing: id 2 | task 2227 | total time = 3418.74 ms / 137 tokens 2.58.498.189 I slot print_timing: id 2 | task 2227 | graphs reused = 1731 2.58.498.189 I slot print_timing: id 2 | task 2227 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.498.254 I slot release: id 2 | task 2227 | stop processing: n_tokens = 1251, truncated = 0 2.58.557.723 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.891 2.58.557.747 I slot launch_slot_: id 2 | task 2303 | processing task, is_child = 0 3.00.366.538 I slot print_timing: id 1 | task 2177 | prompt eval time = 362.49 ms / 101 tokens ( 3.59 ms per token, 278.63 tokens per second) 3.00.366.542 I slot print_timing: id 1 | task 2177 | eval time = 7410.73 ms / 159 tokens ( 46.90 ms per token, 21.32 tokens per second) 3.00.366.543 I slot print_timing: id 1 | task 2177 | total time = 7773.22 ms / 260 tokens 3.00.366.543 I slot print_timing: id 1 | task 2177 | graphs reused = 1766 3.00.366.544 I slot print_timing: id 1 | task 2177 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.366.602 I slot release: id 1 | task 2177 | stop processing: n_tokens = 1374, truncated = 0 3.00.427.556 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.811 3.00.427.583 I slot launch_slot_: id 1 | task 2343 | processing task, is_child = 0 3.01.058.665 I slot print_timing: id 3 | task 2187 | n_gen = 161, tg = 21.33 t/s, tg_3s = 20.26 t/s 3.02.084.210 I slot print_timing: id 0 | task 2275 | n_gen = 100, tg = 21.69 t/s, tg_3s = 21.91 t/s 3.03.195.659 I slot print_timing: id 2 | task 2303 | n_gen = 100, tg = 23.04 t/s, tg_3s = 23.28 t/s 3.04.097.861 I slot print_timing: id 3 | task 2187 | n_gen = 235, tg = 22.20 t/s, tg_3s = 24.35 t/s 3.04.257.898 I slot print_timing: id 0 | task 2275 | prompt eval time = 304.86 ms / 81 tokens ( 3.76 ms per token, 265.70 tokens per second) 3.04.257.902 I slot print_timing: id 0 | task 2275 | eval time = 6738.11 ms / 153 tokens ( 44.33 ms per token, 22.56 tokens per second) 3.04.257.903 I slot print_timing: id 0 | task 2275 | total time = 7042.97 ms / 234 tokens 3.04.257.903 I slot print_timing: id 0 | task 2275 | graphs reused = 1851 3.04.257.904 I slot print_timing: id 0 | task 2275 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.257.984 I slot release: id 0 | task 2275 | stop processing: n_tokens = 1348, truncated = 0 3.04.302.584 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.827 3.04.302.607 I slot launch_slot_: id 0 | task 2433 | processing task, is_child = 0 3.05.007.807 I slot print_timing: id 1 | task 2343 | n_gen = 100, tg = 23.19 t/s, tg_3s = 23.43 t/s 3.05.010.187 I slot print_timing: id 2 | task 2303 | prompt eval time = 341.69 ms / 73 tokens ( 4.68 ms per token, 213.65 tokens per second) 3.05.010.192 I slot print_timing: id 2 | task 2303 | eval time = 6110.75 ms / 139 tokens ( 44.28 ms per token, 22.58 tokens per second) 3.05.010.192 I slot print_timing: id 2 | task 2303 | total time = 6452.43 ms / 212 tokens 3.05.010.193 I slot print_timing: id 2 | task 2303 | graphs reused = 1861 3.05.010.194 I slot print_timing: id 2 | task 2303 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.010.272 I slot release: id 2 | task 2303 | stop processing: n_tokens = 1326, truncated = 0 3.05.072.727 I slot print_timing: id 3 | task 2187 | prompt eval time = 310.62 ms / 86 tokens ( 3.61 ms per token, 276.87 tokens per second) 3.05.072.732 I slot print_timing: id 3 | task 2187 | eval time = 11515.76 ms / 253 tokens ( 45.70 ms per token, 21.88 tokens per second) 3.05.072.732 I slot print_timing: id 3 | task 2187 | total time = 11826.37 ms / 339 tokens 3.05.072.733 I slot print_timing: id 3 | task 2187 | graphs reused = 1861 3.05.072.734 I slot print_timing: id 3 | task 2187 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.072.800 I slot release: id 3 | task 2187 | stop processing: n_tokens = 1453, truncated = 0 3.05.072.810 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.841 3.05.072.834 I slot launch_slot_: id 2 | task 2447 | processing task, is_child = 0 3.05.108.324 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.767 3.05.108.346 I slot launch_slot_: id 3 | task 2448 | processing task, is_child = 0 3.05.584.039 I slot print_timing: id 1 | task 2343 | prompt eval time = 311.94 ms / 66 tokens ( 4.73 ms per token, 211.58 tokens per second) 3.05.584.045 I slot print_timing: id 1 | task 2343 | eval time = 4844.51 ms / 103 tokens ( 47.50 ms per token, 21.05 tokens per second) 3.05.584.045 I slot print_timing: id 1 | task 2343 | total time = 5156.45 ms / 169 tokens 3.05.584.046 I slot print_timing: id 1 | task 2343 | graphs reused = 1861 3.05.584.046 I slot print_timing: id 1 | task 2343 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.584.098 I slot release: id 1 | task 2343 | stop processing: n_tokens = 1283, truncated = 0 3.05.641.565 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.869 3.05.641.586 I slot launch_slot_: id 1 | task 2452 | processing task, is_child = 0 3.08.755.392 I slot print_timing: id 0 | task 2433 | prompt eval time = 307.38 ms / 96 tokens ( 3.20 ms per token, 312.31 tokens per second) 3.08.755.400 I slot print_timing: id 0 | task 2433 | eval time = 4145.40 ms / 83 tokens ( 50.55 ms per token, 19.78 tokens per second) 3.08.755.401 I slot print_timing: id 0 | task 2433 | total time = 4452.78 ms / 179 tokens 3.08.755.402 I slot print_timing: id 0 | task 2433 | graphs reused = 1925 3.08.755.402 I slot print_timing: id 0 | task 2433 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.755.482 I slot release: id 0 | task 2433 | stop processing: n_tokens = 1293, truncated = 0 3.08.800.045 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.862 3.08.800.071 I slot launch_slot_: id 0 | task 2522 | processing task, is_child = 0 3.09.848.701 I slot print_timing: id 3 | task 2448 | prompt eval time = 475.78 ms / 70 tokens ( 6.80 ms per token, 147.13 tokens per second) 3.09.848.711 I slot print_timing: id 3 | task 2448 | eval time = 4262.23 ms / 91 tokens ( 47.36 ms per token, 21.12 tokens per second) 3.09.848.711 I slot print_timing: id 3 | task 2448 | total time = 4738.01 ms / 161 tokens 3.09.848.712 I slot print_timing: id 3 | task 2448 | graphs reused = 1943 3.09.848.713 I slot print_timing: id 3 | task 2448 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.848.790 I slot release: id 3 | task 2448 | stop processing: n_tokens = 1275, truncated = 0 3.09.888.842 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.875 3.09.888.864 I slot launch_slot_: id 3 | task 2544 | processing task, is_child = 0 3.10.410.900 I slot print_timing: id 2 | task 2447 | prompt eval time = 476.88 ms / 84 tokens ( 5.68 ms per token, 176.15 tokens per second) 3.10.410.906 I slot print_timing: id 2 | task 2447 | eval time = 4825.67 ms / 98 tokens ( 49.75 ms per token, 20.10 tokens per second) 3.10.410.906 I slot print_timing: id 2 | task 2447 | total time = 5302.54 ms / 182 tokens 3.10.410.907 I slot print_timing: id 2 | task 2447 | graphs reused = 1946 3.10.410.907 I slot print_timing: id 2 | task 2447 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.410.965 I slot release: id 2 | task 2447 | stop processing: n_tokens = 1296, truncated = 0 3.10.467.411 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.860 3.10.467.433 I slot launch_slot_: id 2 | task 2552 | processing task, is_child = 0 3.10.887.595 I slot print_timing: id 1 | task 2452 | n_gen = 100, tg = 20.52 t/s, tg_3s = 20.73 t/s 3.13.716.368 I slot print_timing: id 0 | task 2522 | n_gen = 100, tg = 21.47 t/s, tg_3s = 21.69 t/s 3.13.923.457 I slot print_timing: id 1 | task 2452 | n_gen = 174, tg = 22.01 t/s, tg_3s = 24.38 t/s 3.14.592.392 I slot print_timing: id 3 | task 2544 | n_gen = 100, tg = 22.83 t/s, tg_3s = 23.06 t/s 3.14.757.447 I slot print_timing: id 2 | task 2552 | prompt eval time = 342.98 ms / 93 tokens ( 3.69 ms per token, 271.16 tokens per second) 3.14.757.453 I slot print_timing: id 2 | task 2552 | eval time = 3947.03 ms / 97 tokens ( 41.11 ms per token, 24.32 tokens per second) 3.14.757.454 I slot print_timing: id 2 | task 2552 | total time = 4290.01 ms / 190 tokens 3.14.757.455 I slot print_timing: id 2 | task 2552 | graphs reused = 2041 3.14.757.455 I slot print_timing: id 2 | task 2552 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.757.528 I slot release: id 2 | task 2552 | stop processing: n_tokens = 1304, truncated = 0 3.14.816.995 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.855 3.14.817.020 I slot launch_slot_: id 2 | task 2652 | processing task, is_child = 0 3.15.407.711 I slot print_timing: id 0 | task 2522 | prompt eval time = 305.11 ms / 88 tokens ( 3.47 ms per token, 288.42 tokens per second) 3.15.407.716 I slot print_timing: id 0 | task 2522 | eval time = 6302.52 ms / 133 tokens ( 47.75 ms per token, 20.94 tokens per second) 3.15.407.717 I slot print_timing: id 0 | task 2522 | total time = 6607.63 ms / 221 tokens 3.15.407.717 I slot print_timing: id 0 | task 2522 | graphs reused = 2045 3.15.407.718 I slot print_timing: id 0 | task 2522 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.407.770 I slot release: id 0 | task 2522 | stop processing: n_tokens = 1335, truncated = 0 3.15.451.671 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.835 3.15.451.699 I slot launch_slot_: id 0 | task 2661 | processing task, is_child = 0 3.16.932.052 I slot print_timing: id 1 | task 2452 | n_gen = 235, tg = 21.53 t/s, tg_3s = 20.28 t/s 3.17.054.784 I slot print_timing: id 1 | task 2452 | prompt eval time = 422.00 ms / 119 tokens ( 3.55 ms per token, 281.99 tokens per second) 3.17.054.788 I slot print_timing: id 1 | task 2452 | eval time = 10991.18 ms / 238 tokens ( 46.38 ms per token, 21.56 tokens per second) 3.17.054.789 I slot print_timing: id 1 | task 2452 | total time = 11413.19 ms / 357 tokens 3.17.054.790 I slot print_timing: id 1 | task 2452 | graphs reused = 2078 3.17.054.790 I slot print_timing: id 1 | task 2452 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.054.858 I slot release: id 1 | task 2452 | stop processing: n_tokens = 1471, truncated = 0 3.17.115.935 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.758 3.17.115.959 I slot launch_slot_: id 1 | task 2698 | processing task, is_child = 0 3.17.598.901 I slot print_timing: id 3 | task 2544 | n_gen = 154, tg = 20.84 t/s, tg_3s = 17.96 t/s 3.18.541.144 I slot print_timing: id 0 | task 2661 | prompt eval time = 250.46 ms / 57 tokens ( 4.39 ms per token, 227.58 tokens per second) 3.18.541.148 I slot print_timing: id 0 | task 2661 | eval time = 2838.97 ms / 63 tokens ( 45.79 ms per token, 21.84 tokens per second) 3.18.541.153 I slot print_timing: id 0 | task 2661 | total time = 3089.44 ms / 120 tokens 3.18.541.154 I slot print_timing: id 0 | task 2661 | graphs reused = 2103 3.18.541.154 I slot print_timing: id 0 | task 2661 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.541.214 I slot release: id 0 | task 2661 | stop processing: n_tokens = 1234, truncated = 0 3.18.585.661 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.904 3.18.585.685 I slot launch_slot_: id 0 | task 2728 | processing task, is_child = 0 3.20.011.935 I slot print_timing: id 2 | task 2652 | n_gen = 100, tg = 20.64 t/s, tg_3s = 20.85 t/s 3.20.633.473 I slot print_timing: id 3 | task 2544 | n_gen = 221, tg = 21.20 t/s, tg_3s = 22.08 t/s 3.21.823.449 I slot print_timing: id 1 | task 2698 | n_gen = 100, tg = 22.79 t/s, tg_3s = 23.02 t/s 3.21.905.244 I slot print_timing: id 1 | task 2698 | prompt eval time = 363.57 ms / 79 tokens ( 4.60 ms per token, 217.29 tokens per second) 3.21.905.250 I slot print_timing: id 1 | task 2698 | eval time = 4425.71 ms / 102 tokens ( 43.82 ms per token, 22.82 tokens per second) 3.21.905.251 I slot print_timing: id 1 | task 2698 | total time = 4789.28 ms / 181 tokens 3.21.905.251 I slot print_timing: id 1 | task 2698 | graphs reused = 2175 3.21.905.252 I slot print_timing: id 1 | task 2698 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.905.312 I slot release: id 1 | task 2698 | stop processing: n_tokens = 1295, truncated = 0 3.21.966.329 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.861 3.21.966.359 I slot launch_slot_: id 1 | task 2804 | processing task, is_child = 0 3.23.027.597 I slot print_timing: id 2 | task 2652 | n_gen = 166, tg = 21.12 t/s, tg_3s = 21.89 t/s 3.23.312.003 I slot print_timing: id 0 | task 2728 | n_gen = 100, tg = 22.67 t/s, tg_3s = 22.89 t/s 3.23.649.511 I slot print_timing: id 3 | task 2544 | n_gen = 287, tg = 21.35 t/s, tg_3s = 21.88 t/s 3.25.262.557 I slot print_timing: id 3 | task 2544 | prompt eval time = 367.17 ms / 133 tokens ( 2.76 ms per token, 362.23 tokens per second) 3.25.262.565 I slot print_timing: id 3 | task 2544 | eval time = 15006.51 ms / 326 tokens ( 46.17 ms per token, 21.66 tokens per second) 3.25.262.565 I slot print_timing: id 3 | task 2544 | total time = 15373.69 ms / 459 tokens 3.25.262.566 I slot print_timing: id 3 | task 2544 | graphs reused = 2244 3.25.262.566 I slot print_timing: id 3 | task 2544 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.262.623 I slot release: id 3 | task 2544 | stop processing: n_tokens = 1573, truncated = 0 3.25.302.045 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.709 3.25.302.073 I slot launch_slot_: id 3 | task 2879 | processing task, is_child = 0 3.26.058.781 I slot print_timing: id 2 | task 2652 | n_gen = 233, tg = 21.40 t/s, tg_3s = 22.10 t/s 3.26.309.665 I slot print_timing: id 0 | task 2728 | prompt eval time = 358.35 ms / 101 tokens ( 3.55 ms per token, 281.85 tokens per second) 3.26.309.670 I slot print_timing: id 0 | task 2728 | eval time = 7365.62 ms / 166 tokens ( 44.64 ms per token, 22.40 tokens per second) 3.26.309.670 I slot print_timing: id 0 | task 2728 | total time = 7723.97 ms / 267 tokens 3.26.309.671 I slot print_timing: id 0 | task 2728 | graphs reused = 2259 3.26.309.672 I slot print_timing: id 0 | task 2728 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.309.741 I slot release: id 0 | task 2728 | stop processing: n_tokens = 1381, truncated = 0 3.26.354.302 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.807 3.26.354.326 I slot launch_slot_: id 0 | task 2899 | processing task, is_child = 0 3.26.900.467 I slot print_timing: id 1 | task 2804 | n_gen = 100, tg = 21.66 t/s, tg_3s = 21.88 t/s 3.29.081.540 I slot print_timing: id 2 | task 2652 | n_gen = 301, tg = 21.64 t/s, tg_3s = 22.50 t/s 3.29.904.096 I slot print_timing: id 1 | task 2804 | n_gen = 173, tg = 22.71 t/s, tg_3s = 24.30 t/s 3.29.948.497 I slot print_timing: id 3 | task 2879 | n_gen = 100, tg = 23.12 t/s, tg_3s = 23.35 t/s 3.30.602.284 I slot print_timing: id 1 | task 2804 | prompt eval time = 363.23 ms / 78 tokens ( 4.66 ms per token, 214.74 tokens per second) 3.30.602.290 I slot print_timing: id 1 | task 2804 | eval time = 8272.69 ms / 190 tokens ( 43.77 ms per token, 22.85 tokens per second) 3.30.602.290 I slot print_timing: id 1 | task 2804 | total time = 8635.92 ms / 268 tokens 3.30.602.291 I slot print_timing: id 1 | task 2804 | graphs reused = 2354 3.30.602.292 I slot print_timing: id 1 | task 2804 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.602.349 I slot release: id 1 | task 2804 | stop processing: n_tokens = 1382, truncated = 0 3.30.663.469 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.807 3.30.663.500 I slot launch_slot_: id 1 | task 2999 | processing task, is_child = 0 3.30.926.858 I slot print_timing: id 3 | task 2879 | prompt eval time = 363.52 ms / 103 tokens ( 3.53 ms per token, 283.34 tokens per second) 3.30.926.866 I slot print_timing: id 3 | task 2879 | eval time = 5261.26 ms / 118 tokens ( 44.97 ms per token, 22.24 tokens per second) 3.30.926.867 I slot print_timing: id 3 | task 2879 | total time = 5624.78 ms / 221 tokens 3.30.926.867 I slot print_timing: id 3 | task 2879 | graphs reused = 2354 3.30.926.868 I slot print_timing: id 3 | task 2879 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.926.939 I slot release: id 3 | task 2879 | stop processing: n_tokens = 1335, truncated = 0 3.31.013.064 I slot print_timing: id 0 | task 2899 | n_gen = 100, tg = 22.74 t/s, tg_3s = 22.97 t/s 3.31.015.291 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.835 3.31.015.308 I slot launch_slot_: id 3 | task 3002 | processing task, is_child = 0 3.31.592.810 I slot print_timing: id 2 | task 2652 | prompt eval time = 398.32 ms / 103 tokens ( 3.87 ms per token, 258.59 tokens per second) 3.31.592.818 I slot print_timing: id 2 | task 2652 | eval time = 16377.47 ms / 350 tokens ( 46.93 ms per token, 21.31 tokens per second) 3.31.592.818 I slot print_timing: id 2 | task 2652 | total time = 16775.78 ms / 453 tokens 3.31.592.819 I slot print_timing: id 2 | task 2652 | graphs reused = 2360 3.31.592.819 I slot print_timing: id 2 | task 2652 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.592.877 I slot release: id 2 | task 2652 | stop processing: n_tokens = 1567, truncated = 0 3.31.652.175 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.712 3.31.652.203 I slot launch_slot_: id 2 | task 3013 | processing task, is_child = 0 3.34.037.829 I slot print_timing: id 0 | task 2899 | n_gen = 159, tg = 21.41 t/s, tg_3s = 19.51 t/s 3.35.026.742 I slot print_timing: id 3 | task 3002 | prompt eval time = 304.73 ms / 77 tokens ( 3.96 ms per token, 252.68 tokens per second) 3.35.026.747 I slot print_timing: id 3 | task 3002 | eval time = 3706.69 ms / 82 tokens ( 45.76 ms per token, 21.85 tokens per second) 3.35.026.748 I slot print_timing: id 3 | task 3002 | total time = 4011.42 ms / 159 tokens 3.35.026.748 I slot print_timing: id 3 | task 3002 | graphs reused = 2430 3.35.026.749 I slot print_timing: id 3 | task 3002 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.026.820 I slot release: id 3 | task 3002 | stop processing: n_tokens = 1273, truncated = 0 3.35.066.691 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.876 3.35.066.718 I slot launch_slot_: id 3 | task 3088 | processing task, is_child = 0 3.35.853.635 I slot print_timing: id 1 | task 2999 | n_gen = 100, tg = 20.46 t/s, tg_3s = 20.66 t/s 3.36.347.924 I slot print_timing: id 2 | task 3013 | n_gen = 100, tg = 23.35 t/s, tg_3s = 23.58 t/s 3.36.715.946 I slot print_timing: id 1 | task 2999 | prompt eval time = 350.73 ms / 83 tokens ( 4.23 ms per token, 236.65 tokens per second) 3.36.715.951 I slot print_timing: id 1 | task 2999 | eval time = 5701.71 ms / 121 tokens ( 47.51 ms per token, 21.05 tokens per second) 3.36.715.952 I slot print_timing: id 1 | task 2999 | total time = 6052.44 ms / 204 tokens 3.36.715.952 I slot print_timing: id 1 | task 2999 | graphs reused = 2463 3.36.715.953 I slot print_timing: id 1 | task 2999 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.716.004 I slot release: id 1 | task 2999 | stop processing: n_tokens = 1318, truncated = 0 3.36.776.876 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.846 3.36.776.905 I slot launch_slot_: id 1 | task 3126 | processing task, is_child = 0 3.36.984.661 I slot print_timing: id 2 | task 3013 | prompt eval time = 455.30 ms / 146 tokens ( 3.12 ms per token, 320.67 tokens per second) 3.36.984.666 I slot print_timing: id 2 | task 3013 | eval time = 4877.15 ms / 111 tokens ( 44.34 ms per token, 22.55 tokens per second) 3.36.984.666 I slot print_timing: id 2 | task 3013 | total time = 5332.45 ms / 257 tokens 3.36.984.667 I slot print_timing: id 2 | task 3013 | graphs reused = 2463 3.36.984.667 I slot print_timing: id 2 | task 3013 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.984.749 I slot release: id 2 | task 3013 | stop processing: n_tokens = 1371, truncated = 0 3.37.072.423 I slot print_timing: id 0 | task 2899 | n_gen = 223, tg = 21.32 t/s, tg_3s = 21.09 t/s 3.37.074.625 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.813 3.37.074.648 I slot launch_slot_: id 2 | task 3129 | processing task, is_child = 0 3.38.439.738 I slot print_timing: id 0 | task 2899 | prompt eval time = 305.02 ms / 100 tokens ( 3.05 ms per token, 327.85 tokens per second) 3.38.439.743 I slot print_timing: id 0 | task 2899 | eval time = 11780.39 ms / 250 tokens ( 47.31 ms per token, 21.14 tokens per second) 3.38.439.745 I slot print_timing: id 0 | task 2899 | total time = 12085.41 ms / 350 tokens 3.38.439.745 I slot print_timing: id 0 | task 2899 | graphs reused = 2487 3.38.439.746 I slot print_timing: id 0 | task 2899 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.439.810 I slot release: id 0 | task 2899 | stop processing: n_tokens = 1464, truncated = 0 3.38.484.463 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.762 3.38.484.488 I slot launch_slot_: id 0 | task 3158 | processing task, is_child = 0 3.39.978.302 I slot print_timing: id 3 | task 3088 | prompt eval time = 258.12 ms / 67 tokens ( 3.85 ms per token, 259.57 tokens per second) 3.39.978.309 I slot print_timing: id 3 | task 3088 | eval time = 4653.46 ms / 97 tokens ( 48.47 ms per token, 20.63 tokens per second) 3.39.978.310 I slot print_timing: id 3 | task 3088 | total time = 4911.58 ms / 164 tokens 3.39.978.310 I slot print_timing: id 3 | task 3088 | graphs reused = 2516 3.39.978.311 I slot print_timing: id 3 | task 3088 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.978.363 I slot release: id 3 | task 3088 | stop processing: n_tokens = 1278, truncated = 0 3.40.017.747 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.872 3.40.017.769 I slot launch_slot_: id 3 | task 3191 | processing task, is_child = 0 3.41.838.089 I slot print_timing: id 1 | task 3126 | n_gen = 100, tg = 20.78 t/s, tg_3s = 20.99 t/s 3.41.921.473 I slot print_timing: id 2 | task 3129 | n_gen = 100, tg = 21.98 t/s, tg_3s = 22.21 t/s 3.42.086.334 I slot print_timing: id 2 | task 3129 | prompt eval time = 343.62 ms / 89 tokens ( 3.86 ms per token, 259.01 tokens per second) 3.42.086.340 I slot print_timing: id 2 | task 3129 | eval time = 4668.06 ms / 104 tokens ( 45.32 ms per token, 22.06 tokens per second) 3.42.086.341 I slot print_timing: id 2 | task 3129 | total time = 5011.68 ms / 193 tokens 3.42.086.342 I slot print_timing: id 2 | task 3129 | graphs reused = 2557 3.42.086.342 I slot print_timing: id 2 | task 3129 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.086.425 I slot release: id 2 | task 3129 | stop processing: n_tokens = 1307, truncated = 0 3.42.145.997 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.853 3.42.146.019 I slot launch_slot_: id 2 | task 3238 | processing task, is_child = 0 3.42.719.076 I slot print_timing: id 0 | task 3158 | prompt eval time = 301.86 ms / 71 tokens ( 4.25 ms per token, 235.21 tokens per second) 3.42.719.082 I slot print_timing: id 0 | task 3158 | eval time = 3932.73 ms / 85 tokens ( 46.82 ms per token, 21.36 tokens per second) 3.42.719.083 I slot print_timing: id 0 | task 3158 | total time = 4234.58 ms / 156 tokens 3.42.719.083 I slot print_timing: id 0 | task 3158 | graphs reused = 2562 3.42.719.084 I slot print_timing: id 0 | task 3158 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.719.130 I slot release: id 0 | task 3158 | stop processing: n_tokens = 1270, truncated = 0 3.42.762.991 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 3.42.763.015 I slot launch_slot_: id 0 | task 3248 | processing task, is_child = 0 3.43.225.927 I slot print_timing: id 1 | task 3126 | prompt eval time = 296.64 ms / 57 tokens ( 5.20 ms per token, 192.15 tokens per second) 3.43.225.933 I slot print_timing: id 1 | task 3126 | eval time = 6152.37 ms / 122 tokens ( 50.85 ms per token, 19.67 tokens per second) 3.43.225.934 I slot print_timing: id 1 | task 3126 | total time = 6449.02 ms / 179 tokens 3.43.225.934 I slot print_timing: id 1 | task 3126 | graphs reused = 2566 3.43.225.935 I slot print_timing: id 1 | task 3126 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.225.983 I slot release: id 1 | task 3126 | stop processing: n_tokens = 1293, truncated = 0 3.43.285.055 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.862 3.43.285.076 I slot launch_slot_: id 1 | task 3256 | processing task, is_child = 0 3.45.171.928 I slot print_timing: id 3 | task 3191 | n_gen = 100, tg = 20.43 t/s, tg_3s = 20.64 t/s 3.47.059.091 I slot print_timing: id 2 | task 3238 | n_gen = 100, tg = 21.65 t/s, tg_3s = 21.87 t/s 3.47.224.541 I slot print_timing: id 3 | task 3191 | prompt eval time = 309.42 ms / 84 tokens ( 3.68 ms per token, 271.47 tokens per second) 3.47.224.549 I slot print_timing: id 3 | task 3191 | eval time = 6897.34 ms / 150 tokens ( 46.29 ms per token, 21.60 tokens per second) 3.47.224.549 I slot print_timing: id 3 | task 3191 | total time = 7206.76 ms / 234 tokens 3.47.224.550 I slot print_timing: id 3 | task 3191 | graphs reused = 2651 3.47.224.551 I slot print_timing: id 3 | task 3191 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.224.617 I slot release: id 3 | task 3191 | stop processing: n_tokens = 1348, truncated = 0 3.47.264.411 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.827 3.47.264.434 I slot launch_slot_: id 3 | task 3347 | processing task, is_child = 0 3.47.706.579 I slot print_timing: id 0 | task 3248 | n_gen = 100, tg = 21.35 t/s, tg_3s = 21.56 t/s 3.47.987.705 I slot print_timing: id 1 | task 3256 | n_gen = 100, tg = 22.83 t/s, tg_3s = 23.06 t/s 3.49.017.604 I slot print_timing: id 1 | task 3256 | prompt eval time = 365.61 ms / 94 tokens ( 3.89 ms per token, 257.11 tokens per second) 3.49.017.608 I slot print_timing: id 1 | task 3256 | eval time = 5366.91 ms / 125 tokens ( 43.28 ms per token, 23.10 tokens per second) 3.49.017.609 I slot print_timing: id 1 | task 3256 | total time = 5732.52 ms / 219 tokens 3.49.017.609 I slot print_timing: id 1 | task 3256 | graphs reused = 2684 3.49.017.610 I slot print_timing: id 1 | task 3256 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.017.674 I slot release: id 1 | task 3256 | stop processing: n_tokens = 1333, truncated = 0 3.49.078.747 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.836 3.49.078.775 I slot launch_slot_: id 1 | task 3385 | processing task, is_child = 0 3.49.521.016 I slot print_timing: id 0 | task 3248 | prompt eval time = 305.86 ms / 88 tokens ( 3.48 ms per token, 287.71 tokens per second) 3.49.521.019 I slot print_timing: id 0 | task 3248 | eval time = 6452.12 ms / 137 tokens ( 47.44 ms per token, 21.08 tokens per second) 3.49.521.020 I slot print_timing: id 0 | task 3248 | total time = 6757.99 ms / 225 tokens 3.49.521.020 I slot print_timing: id 0 | task 3248 | graphs reused = 2685 3.49.521.020 I slot print_timing: id 0 | task 3248 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.521.076 I slot release: id 0 | task 3248 | stop processing: n_tokens = 1339, truncated = 0 3.49.562.043 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.833 3.49.562.061 I slot launch_slot_: id 0 | task 3391 | processing task, is_child = 0 3.49.905.762 I slot print_timing: id 2 | task 3238 | prompt eval time = 341.08 ms / 72 tokens ( 4.74 ms per token, 211.09 tokens per second) 3.49.905.765 I slot print_timing: id 2 | task 3238 | eval time = 7418.66 ms / 150 tokens ( 49.79 ms per token, 20.08 tokens per second) 3.49.905.766 I slot print_timing: id 2 | task 3238 | total time = 7759.74 ms / 222 tokens 3.49.905.766 I slot print_timing: id 2 | task 3238 | graphs reused = 2686 3.49.905.766 I slot print_timing: id 2 | task 3238 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.905.810 I slot release: id 2 | task 3238 | stop processing: n_tokens = 1336, truncated = 0 3.49.961.700 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.835 3.49.961.719 I slot launch_slot_: id 2 | task 3396 | processing task, is_child = 0 3.52.479.631 I slot print_timing: id 3 | task 3347 | n_gen = 100, tg = 20.42 t/s, tg_3s = 20.63 t/s 3.54.002.995 I slot print_timing: id 1 | task 3385 | n_gen = 100, tg = 21.71 t/s, tg_3s = 21.93 t/s 3.54.209.791 I slot print_timing: id 0 | task 3391 | n_gen = 100, tg = 22.78 t/s, tg_3s = 23.01 t/s 3.54.377.652 I slot print_timing: id 2 | task 3396 | n_gen = 100, tg = 24.30 t/s, tg_3s = 24.54 t/s 3.54.670.229 I slot print_timing: id 3 | task 3347 | prompt eval time = 366.88 ms / 111 tokens ( 3.31 ms per token, 302.55 tokens per second) 3.54.670.233 I slot print_timing: id 3 | task 3347 | eval time = 7038.90 ms / 153 tokens ( 46.31 ms per token, 21.59 tokens per second) 3.54.670.234 I slot print_timing: id 3 | task 3347 | total time = 7405.78 ms / 264 tokens 3.54.670.235 I slot print_timing: id 3 | task 3347 | graphs reused = 2790 3.54.670.235 I slot print_timing: id 3 | task 3347 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.670.325 I slot release: id 3 | task 3347 | stop processing: n_tokens = 1378, truncated = 0 3.54.710.492 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.809 3.54.710.515 I slot launch_slot_: id 3 | task 3506 | processing task, is_child = 0 3.57.030.657 I slot print_timing: id 1 | task 3385 | n_gen = 168, tg = 22.01 t/s, tg_3s = 22.46 t/s 3.57.192.993 I slot print_timing: id 0 | task 3391 | prompt eval time = 301.99 ms / 84 tokens ( 3.60 ms per token, 278.16 tokens per second) 3.57.192.997 I slot print_timing: id 0 | task 3391 | eval time = 7328.94 ms / 167 tokens ( 44.15 ms per token, 22.65 tokens per second) 3.57.192.997 I slot print_timing: id 0 | task 3391 | total time = 7630.92 ms / 251 tokens 3.57.192.998 I slot print_timing: id 0 | task 3391 | graphs reused = 2842 3.57.192.999 I slot print_timing: id 0 | task 3391 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.193.051 I slot release: id 0 | task 3391 | stop processing: n_tokens = 1365, truncated = 0 3.57.237.424 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.817 3.57.237.454 I slot launch_slot_: id 0 | task 3563 | processing task, is_child = 0 3.57.471.518 I slot print_timing: id 2 | task 3396 | n_gen = 165, tg = 22.88 t/s, tg_3s = 21.01 t/s 3.57.625.388 I slot print_timing: id 2 | task 3396 | prompt eval time = 341.10 ms / 74 tokens ( 4.61 ms per token, 216.94 tokens per second) 3.57.625.393 I slot print_timing: id 2 | task 3396 | eval time = 7322.56 ms / 168 tokens ( 43.85 ms per token, 22.81 tokens per second) 3.57.625.394 I slot print_timing: id 2 | task 3396 | total time = 7663.66 ms / 242 tokens 3.57.625.394 I slot print_timing: id 2 | task 3396 | graphs reused = 2844 3.57.625.395 I slot print_timing: id 2 | task 3396 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.625.448 I slot release: id 2 | task 3396 | stop processing: n_tokens = 1356, truncated = 0 3.57.681.475 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.822 3.57.681.497 I slot launch_slot_: id 2 | task 3569 | processing task, is_child = 0 3.58.498.692 I slot print_timing: id 1 | task 3385 | prompt eval time = 364.42 ms / 88 tokens ( 4.14 ms per token, 241.48 tokens per second) 3.58.498.703 I slot print_timing: id 1 | task 3385 | eval time = 9055.47 ms / 189 tokens ( 48.17 ms per token, 20.76 tokens per second) 3.58.498.704 I slot print_timing: id 1 | task 3385 | total time = 9419.89 ms / 277 tokens 3.58.498.705 I slot print_timing: id 1 | task 3385 | graphs reused = 2852 3.58.498.705 I slot print_timing: id 1 | task 3385 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.498.772 I slot release: id 1 | task 3385 | stop processing: n_tokens = 1391, truncated = 0 3.58.561.216 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.802 3.58.561.247 I slot launch_slot_: id 1 | task 3582 | processing task, is_child = 0 3.59.992.716 I slot print_timing: id 3 | task 3506 | n_gen = 100, tg = 19.90 t/s, tg_3s = 20.10 t/s 4.00.691.487 I slot print_timing: id 3 | task 3506 | prompt eval time = 306.93 ms / 73 tokens ( 4.20 ms per token, 237.84 tokens per second) 4.00.691.494 I slot print_timing: id 3 | task 3506 | eval time = 5674.03 ms / 117 tokens ( 48.91 ms per token, 20.44 tokens per second) 4.00.691.494 I slot print_timing: id 3 | task 3506 | total time = 5980.96 ms / 190 tokens 4.00.691.495 I slot print_timing: id 3 | task 3506 | graphs reused = 2893 4.00.691.495 I slot print_timing: id 3 | task 3506 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.691.582 I slot release: id 3 | task 3506 | stop processing: n_tokens = 1304, truncated = 0 4.00.731.611 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.855 4.00.731.636 I slot launch_slot_: id 3 | task 3629 | processing task, is_child = 0 4.02.518.008 I slot print_timing: id 0 | task 3563 | n_gen = 100, tg = 19.91 t/s, tg_3s = 20.11 t/s 4.02.727.317 I slot print_timing: id 2 | task 3569 | n_gen = 100, tg = 21.56 t/s, tg_3s = 21.78 t/s 4.03.221.862 I slot print_timing: id 1 | task 3582 | n_gen = 100, tg = 23.05 t/s, tg_3s = 23.28 t/s 4.04.954.332 I slot print_timing: id 1 | task 3582 | prompt eval time = 365.38 ms / 92 tokens ( 3.97 ms per token, 251.79 tokens per second) 4.04.954.338 I slot print_timing: id 1 | task 3582 | eval time = 6027.69 ms / 142 tokens ( 42.75 ms per token, 23.39 tokens per second) 4.04.954.339 I slot print_timing: id 1 | task 3582 | total time = 6393.07 ms / 234 tokens 4.04.954.340 I slot print_timing: id 1 | task 3582 | graphs reused = 2987 4.04.954.340 I slot print_timing: id 1 | task 3582 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.954.420 I slot release: id 1 | task 3582 | stop processing: n_tokens = 1348, truncated = 0 4.05.015.655 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.827 4.05.015.679 I slot launch_slot_: id 1 | task 3728 | processing task, is_child = 0 4.05.421.735 I slot print_timing: id 3 | task 3629 | n_gen = 100, tg = 22.60 t/s, tg_3s = 22.83 t/s 4.05.536.722 I slot print_timing: id 0 | task 3563 | n_gen = 166, tg = 20.65 t/s, tg_3s = 21.86 t/s 4.05.751.988 I slot print_timing: id 2 | task 3569 | n_gen = 166, tg = 21.66 t/s, tg_3s = 21.82 t/s 4.06.628.318 I slot print_timing: id 3 | task 3629 | prompt eval time = 309.22 ms / 79 tokens ( 3.91 ms per token, 255.48 tokens per second) 4.06.628.323 I slot print_timing: id 3 | task 3629 | eval time = 5587.45 ms / 129 tokens ( 43.65 ms per token, 22.91 tokens per second) 4.06.628.324 I slot print_timing: id 3 | task 3629 | total time = 5896.67 ms / 208 tokens 4.06.628.325 I slot print_timing: id 3 | task 3629 | graphs reused = 3016 4.06.628.325 I slot print_timing: id 3 | task 3629 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.628.416 I slot release: id 3 | task 3629 | stop processing: n_tokens = 1322, truncated = 0 4.06.668.475 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.843 4.06.668.506 I slot launch_slot_: id 3 | task 3762 | processing task, is_child = 0 4.07.511.899 I slot print_timing: id 0 | task 3563 | prompt eval time = 307.16 ms / 97 tokens ( 3.17 ms per token, 315.80 tokens per second) 4.07.511.906 I slot print_timing: id 0 | task 3563 | eval time = 9967.27 ms / 207 tokens ( 48.38 ms per token, 20.67 tokens per second) 4.07.511.908 I slot print_timing: id 0 | task 3563 | total time = 10274.43 ms / 304 tokens 4.07.511.909 I slot print_timing: id 0 | task 3563 | graphs reused = 3027 4.07.511.910 I slot print_timing: id 0 | task 3563 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.511.992 I slot release: id 0 | task 3563 | stop processing: n_tokens = 1418, truncated = 0 4.07.557.482 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.786 4.07.557.505 I slot launch_slot_: id 0 | task 3778 | processing task, is_child = 0 4.08.763.712 I slot print_timing: id 2 | task 3569 | n_gen = 227, tg = 21.26 t/s, tg_3s = 20.25 t/s 4.09.952.687 I slot print_timing: id 1 | task 3728 | n_gen = 100, tg = 21.65 t/s, tg_3s = 21.87 t/s 4.11.316.445 I slot print_timing: id 3 | task 3762 | n_gen = 100, tg = 23.11 t/s, tg_3s = 23.35 t/s 4.11.766.024 I slot print_timing: id 2 | task 3569 | n_gen = 300, tg = 21.94 t/s, tg_3s = 24.31 t/s 4.11.926.589 I slot print_timing: id 0 | task 3778 | n_gen = 100, tg = 24.37 t/s, tg_3s = 24.61 t/s 4.12.829.038 I slot print_timing: id 0 | task 3778 | prompt eval time = 305.96 ms / 88 tokens ( 3.48 ms per token, 287.62 tokens per second) 4.12.829.044 I slot print_timing: id 0 | task 3778 | eval time = 4965.56 ms / 122 tokens ( 41.04 ms per token, 24.37 tokens per second) 4.12.829.045 I slot print_timing: id 0 | task 3778 | total time = 5271.52 ms / 210 tokens 4.12.829.046 I slot print_timing: id 0 | task 3778 | graphs reused = 3147 4.12.829.046 I slot print_timing: id 0 | task 3778 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.829.101 I slot release: id 0 | task 3778 | stop processing: n_tokens = 1324, truncated = 0 4.12.873.460 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.842 4.12.873.485 I slot launch_slot_: id 0 | task 3903 | processing task, is_child = 0 4.13.105.319 I slot print_timing: id 1 | task 3728 | n_gen = 172, tg = 22.14 t/s, tg_3s = 22.84 t/s 4.14.331.110 I slot print_timing: id 3 | task 3762 | n_gen = 168, tg = 22.88 t/s, tg_3s = 22.56 t/s 4.14.786.969 I slot print_timing: id 2 | task 3569 | n_gen = 368, tg = 22.04 t/s, tg_3s = 22.51 t/s 4.14.950.169 I slot print_timing: id 1 | task 3728 | prompt eval time = 364.57 ms / 83 tokens ( 4.39 ms per token, 227.66 tokens per second) 4.14.950.175 I slot print_timing: id 1 | task 3728 | eval time = 9569.91 ms / 216 tokens ( 44.51 ms per token, 22.47 tokens per second) 4.14.950.177 I slot print_timing: id 1 | task 3728 | total time = 9934.49 ms / 299 tokens 4.14.950.177 I slot print_timing: id 1 | task 3728 | graphs reused = 3190 4.14.950.178 I slot print_timing: id 1 | task 3728 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.950.232 I slot release: id 1 | task 3728 | stop processing: n_tokens = 1413, truncated = 0 4.15.011.230 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.789 4.15.011.260 I slot launch_slot_: id 1 | task 3950 | processing task, is_child = 0 4.17.243.551 I slot print_timing: id 0 | task 3903 | prompt eval time = 306.17 ms / 91 tokens ( 3.36 ms per token, 297.22 tokens per second) 4.17.243.558 I slot print_timing: id 0 | task 3903 | eval time = 4063.89 ms / 92 tokens ( 44.66 ms per token, 22.39 tokens per second) 4.17.243.558 I slot print_timing: id 0 | task 3903 | total time = 4370.06 ms / 183 tokens 4.17.243.559 I slot print_timing: id 0 | task 3903 | graphs reused = 3234 4.17.243.559 I slot print_timing: id 0 | task 3903 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.243.612 I slot release: id 0 | task 3903 | stop processing: n_tokens = 1297, truncated = 0 4.17.288.180 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.860 4.17.288.206 I slot launch_slot_: id 0 | task 3999 | processing task, is_child = 0 4.17.523.718 I slot print_timing: id 3 | task 3762 | n_gen = 233, tg = 22.11 t/s, tg_3s = 20.36 t/s 4.17.676.082 I slot print_timing: id 2 | task 3569 | prompt eval time = 454.40 ms / 142 tokens ( 3.20 ms per token, 312.50 tokens per second) 4.17.676.086 I slot print_timing: id 2 | task 3569 | eval time = 19540.17 ms / 425 tokens ( 46.09 ms per token, 21.70 tokens per second) 4.17.676.086 I slot print_timing: id 2 | task 3569 | total time = 19994.58 ms / 567 tokens 4.17.676.087 I slot print_timing: id 2 | task 3569 | graphs reused = 3236 4.17.676.087 I slot print_timing: id 2 | task 3569 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.676.140 I slot release: id 2 | task 3569 | stop processing: n_tokens = 1681, truncated = 0 4.17.732.568 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.663 4.17.732.591 I slot launch_slot_: id 2 | task 4005 | processing task, is_child = 0 4.19.966.289 I slot print_timing: id 1 | task 3950 | n_gen = 100, tg = 21.58 t/s, tg_3s = 21.80 t/s 4.20.552.660 I slot print_timing: id 3 | task 3762 | n_gen = 299, tg = 22.04 t/s, tg_3s = 21.79 t/s 4.21.949.569 I slot print_timing: id 0 | task 3999 | n_gen = 100, tg = 22.74 t/s, tg_3s = 22.97 t/s 4.22.158.807 I slot print_timing: id 2 | task 4005 | n_gen = 100, tg = 24.27 t/s, tg_3s = 24.51 t/s 4.22.897.523 I slot print_timing: id 1 | task 3950 | prompt eval time = 366.93 ms / 95 tokens ( 3.86 ms per token, 258.90 tokens per second) 4.22.897.528 I slot print_timing: id 1 | task 3950 | eval time = 7519.32 ms / 171 tokens ( 44.23 ms per token, 22.61 tokens per second) 4.22.897.529 I slot print_timing: id 1 | task 3950 | total time = 7886.25 ms / 266 tokens 4.22.897.530 I slot print_timing: id 1 | task 3950 | graphs reused = 3351 4.22.897.530 I slot print_timing: id 1 | task 3950 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.897.610 I slot release: id 1 | task 3950 | stop processing: n_tokens = 1380, truncated = 0 4.22.959.061 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.808 4.22.959.087 I slot launch_slot_: id 1 | task 4126 | processing task, is_child = 0 4.23.569.654 I slot print_timing: id 3 | task 3762 | n_gen = 365, tg = 22.01 t/s, tg_3s = 21.88 t/s 4.24.965.628 I slot print_timing: id 0 | task 3999 | n_gen = 166, tg = 22.39 t/s, tg_3s = 21.88 t/s 4.25.171.983 I slot print_timing: id 0 | task 3999 | prompt eval time = 307.11 ms / 97 tokens ( 3.17 ms per token, 315.85 tokens per second) 4.25.171.989 I slot print_timing: id 0 | task 3999 | eval time = 7576.66 ms / 171 tokens ( 44.57 ms per token, 22.44 tokens per second) 4.25.171.990 I slot print_timing: id 0 | task 3999 | total time = 7883.77 ms / 268 tokens 4.25.171.991 I slot print_timing: id 0 | task 3999 | graphs reused = 3395 4.25.171.991 I slot print_timing: id 0 | task 3999 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.172.053 I slot release: id 0 | task 3999 | stop processing: n_tokens = 1382, truncated = 0 4.25.175.226 I slot print_timing: id 2 | task 4005 | n_gen = 166, tg = 23.25 t/s, tg_3s = 21.88 t/s 4.25.216.462 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.807 4.25.216.484 I slot launch_slot_: id 0 | task 4175 | processing task, is_child = 0 4.26.596.312 I slot print_timing: id 3 | task 3762 | n_gen = 433, tg = 22.08 t/s, tg_3s = 22.47 t/s 4.27.619.352 I slot print_timing: id 1 | task 4126 | n_gen = 100, tg = 23.05 t/s, tg_3s = 23.28 t/s 4.28.072.985 I slot print_timing: id 3 | task 3762 | prompt eval time = 364.46 ms / 108 tokens ( 3.37 ms per token, 296.33 tokens per second) 4.28.072.993 I slot print_timing: id 3 | task 3762 | eval time = 21040.01 ms / 469 tokens ( 44.96 ms per token, 22.24 tokens per second) 4.28.072.993 I slot print_timing: id 3 | task 3762 | total time = 21404.47 ms / 577 tokens 4.28.072.994 I slot print_timing: id 3 | task 3762 | graphs reused = 3457 4.28.072.995 I slot print_timing: id 3 | task 3762 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.073.067 I slot release: id 3 | task 3762 | stop processing: n_tokens = 1691, truncated = 0 4.28.113.168 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.659 4.28.113.191 I slot launch_slot_: id 3 | task 4241 | processing task, is_child = 0 4.28.346.063 I slot print_timing: id 2 | task 4005 | n_gen = 233, tg = 22.60 t/s, tg_3s = 21.13 t/s 4.29.811.217 I slot print_timing: id 0 | task 4175 | n_gen = 100, tg = 23.08 t/s, tg_3s = 23.32 t/s 4.30.018.408 I slot print_timing: id 1 | task 4126 | prompt eval time = 364.51 ms / 95 tokens ( 3.84 ms per token, 260.62 tokens per second) 4.30.018.413 I slot print_timing: id 1 | task 4126 | eval time = 6694.80 ms / 153 tokens ( 44.04 ms per token, 22.70 tokens per second) 4.30.018.414 I slot print_timing: id 1 | task 4126 | total time = 7059.31 ms / 248 tokens 4.30.018.415 I slot print_timing: id 1 | task 4126 | graphs reused = 3495 4.30.018.415 I slot print_timing: id 1 | task 4126 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.018.486 I slot release: id 1 | task 4126 | stop processing: n_tokens = 1362, truncated = 0 4.30.075.885 I slot print_timing: id 0 | task 4175 | prompt eval time = 306.04 ms / 89 tokens ( 3.44 ms per token, 290.81 tokens per second) 4.30.075.892 I slot print_timing: id 0 | task 4175 | eval time = 4553.36 ms / 106 tokens ( 43.37 ms per token, 23.06 tokens per second) 4.30.075.897 I slot print_timing: id 0 | task 4175 | total time = 4859.40 ms / 195 tokens 4.30.075.897 I slot print_timing: id 0 | task 4175 | graphs reused = 3495 4.30.075.898 I slot print_timing: id 0 | task 4175 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.075.956 I slot release: id 0 | task 4175 | stop processing: n_tokens = 1309, truncated = 0 4.30.079.497 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.852 4.30.079.522 I slot launch_slot_: id 0 | task 4284 | processing task, is_child = 0 4.30.113.731 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.819 4.30.113.756 I slot launch_slot_: id 1 | task 4285 | processing task, is_child = 0 4.31.346.498 I slot print_timing: id 2 | task 4005 | n_gen = 291, tg = 21.86 t/s, tg_3s = 19.33 t/s 4.32.414.266 I slot print_timing: id 3 | task 4241 | prompt eval time = 312.13 ms / 75 tokens ( 4.16 ms per token, 240.28 tokens per second) 4.32.414.271 I slot print_timing: id 3 | task 4241 | eval time = 3988.93 ms / 84 tokens ( 48.06 ms per token, 20.81 tokens per second) 4.32.414.272 I slot print_timing: id 3 | task 4241 | total time = 4301.06 ms / 159 tokens 4.32.414.272 I slot print_timing: id 3 | task 4241 | graphs reused = 3536 4.32.414.273 I slot print_timing: id 3 | task 4241 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.414.327 I slot release: id 3 | task 4241 | stop processing: n_tokens = 1272, truncated = 0 4.32.454.007 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.877 4.32.454.029 I slot launch_slot_: id 3 | task 4330 | processing task, is_child = 0 4.32.803.007 I slot print_timing: id 2 | task 4005 | prompt eval time = 346.96 ms / 79 tokens ( 4.39 ms per token, 227.69 tokens per second) 4.32.803.010 I slot print_timing: id 2 | task 4005 | eval time = 14723.45 ms / 321 tokens ( 46.01 ms per token, 21.73 tokens per second) 4.32.803.010 I slot print_timing: id 2 | task 4005 | total time = 15070.41 ms / 400 tokens 4.32.803.011 I slot print_timing: id 2 | task 4005 | graphs reused = 3536 4.32.803.011 I slot print_timing: id 2 | task 4005 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.803.060 I slot release: id 2 | task 4005 | stop processing: n_tokens = 1513, truncated = 0 4.32.859.084 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.737 4.32.859.102 I slot launch_slot_: id 2 | task 4335 | processing task, is_child = 0 4.34.632.450 I slot print_timing: id 0 | task 4284 | prompt eval time = 617.34 ms / 75 tokens ( 8.23 ms per token, 121.49 tokens per second) 4.34.632.456 I slot print_timing: id 0 | task 4284 | eval time = 3901.34 ms / 84 tokens ( 47.00 ms per token, 21.27 tokens per second) 4.34.632.456 I slot print_timing: id 0 | task 4284 | total time = 4518.68 ms / 159 tokens 4.34.632.457 I slot print_timing: id 0 | task 4284 | graphs reused = 3570 4.34.632.458 I slot print_timing: id 0 | task 4284 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.632.523 I slot release: id 0 | task 4284 | stop processing: n_tokens = 1273, truncated = 0 4.34.676.917 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.876 4.34.676.940 I slot launch_slot_: id 0 | task 4374 | processing task, is_child = 0 4.35.509.658 I slot print_timing: id 1 | task 4285 | n_gen = 100, tg = 20.72 t/s, tg_3s = 20.93 t/s 4.37.315.023 I slot print_timing: id 3 | task 4330 | n_gen = 100, tg = 21.76 t/s, tg_3s = 21.98 t/s 4.37.478.186 I slot print_timing: id 2 | task 4335 | n_gen = 100, tg = 23.16 t/s, tg_3s = 23.39 t/s 4.38.543.297 I slot print_timing: id 1 | task 4285 | n_gen = 174, tg = 22.15 t/s, tg_3s = 24.39 t/s 4.39.034.856 I slot print_timing: id 0 | task 4374 | n_gen = 100, tg = 24.42 t/s, tg_3s = 24.67 t/s 4.39.283.397 I slot print_timing: id 0 | task 4374 | prompt eval time = 304.61 ms / 80 tokens ( 3.81 ms per token, 262.63 tokens per second) 4.39.283.404 I slot print_timing: id 0 | task 4374 | eval time = 4301.84 ms / 106 tokens ( 40.97 ms per token, 24.41 tokens per second) 4.39.283.404 I slot print_timing: id 0 | task 4374 | total time = 4606.45 ms / 186 tokens 4.39.283.405 I slot print_timing: id 0 | task 4374 | graphs reused = 3675 4.39.283.405 I slot print_timing: id 0 | task 4374 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.283.461 I slot release: id 0 | task 4374 | stop processing: n_tokens = 1300, truncated = 0 4.39.327.902 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.858 4.39.327.924 I slot launch_slot_: id 0 | task 4483 | processing task, is_child = 0 4.39.637.248 I slot print_timing: id 2 | task 4335 | prompt eval time = 343.59 ms / 92 tokens ( 3.73 ms per token, 267.76 tokens per second) 4.39.637.250 I slot print_timing: id 2 | task 4335 | eval time = 6434.55 ms / 147 tokens ( 44.07 ms per token, 22.69 tokens per second) 4.39.637.251 I slot print_timing: id 2 | task 4335 | total time = 6778.14 ms / 239 tokens 4.39.637.251 I slot print_timing: id 2 | task 4335 | graphs reused = 3676 4.39.637.252 I slot print_timing: id 2 | task 4335 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.637.303 I slot release: id 2 | task 4335 | stop processing: n_tokens = 1353, truncated = 0 4.39.693.635 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.824 4.39.693.655 I slot launch_slot_: id 2 | task 4487 | processing task, is_child = 0 4.40.350.711 I slot print_timing: id 3 | task 4330 | n_gen = 163, tg = 21.36 t/s, tg_3s = 20.75 t/s 4.41.579.557 I slot print_timing: id 1 | task 4285 | n_gen = 237, tg = 21.76 t/s, tg_3s = 20.75 t/s 4.42.408.749 I slot print_timing: id 3 | task 4330 | prompt eval time = 310.65 ms / 95 tokens ( 3.27 ms per token, 305.81 tokens per second) 4.42.408.755 I slot print_timing: id 3 | task 4330 | eval time = 9644.07 ms / 213 tokens ( 45.49 ms per token, 21.98 tokens per second) 4.42.408.756 I slot print_timing: id 3 | task 4330 | total time = 9954.71 ms / 308 tokens 4.42.408.756 I slot print_timing: id 3 | task 4330 | graphs reused = 3734 4.42.408.757 I slot print_timing: id 3 | task 4330 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.408.827 I slot release: id 3 | task 4330 | stop processing: n_tokens = 1422, truncated = 0 4.42.448.670 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.784 4.42.448.697 I slot launch_slot_: id 3 | task 4550 | processing task, is_child = 0 4.43.332.992 I slot print_timing: id 1 | task 4285 | prompt eval time = 616.24 ms / 150 tokens ( 4.11 ms per token, 243.41 tokens per second) 4.43.332.999 I slot print_timing: id 1 | task 4285 | eval time = 12600.78 ms / 273 tokens ( 46.33 ms per token, 21.59 tokens per second) 4.43.332.999 I slot print_timing: id 1 | task 4285 | total time = 13217.02 ms / 423 tokens 4.43.333.000 I slot print_timing: id 1 | task 4285 | graphs reused = 3745 4.43.333.001 I slot print_timing: id 1 | task 4285 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.333.062 I slot release: id 1 | task 4285 | stop processing: n_tokens = 1538, truncated = 0 4.43.394.823 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.725 4.43.394.851 I slot launch_slot_: id 1 | task 4567 | processing task, is_child = 0 4.44.441.272 I slot print_timing: id 0 | task 4483 | n_gen = 100, tg = 20.60 t/s, tg_3s = 20.81 t/s 4.44.567.547 I slot print_timing: id 2 | task 4487 | n_gen = 100, tg = 21.60 t/s, tg_3s = 21.82 t/s 4.45.262.665 I slot print_timing: id 0 | task 4483 | prompt eval time = 307.19 ms / 95 tokens ( 3.23 ms per token, 309.26 tokens per second) 4.45.262.671 I slot print_timing: id 0 | task 4483 | eval time = 5627.54 ms / 120 tokens ( 47.29 ms per token, 21.15 tokens per second) 4.45.262.672 I slot print_timing: id 0 | task 4483 | total time = 5934.73 ms / 215 tokens 4.45.262.673 I slot print_timing: id 0 | task 4483 | graphs reused = 3782 4.45.262.673 I slot print_timing: id 0 | task 4483 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.262.746 I slot release: id 0 | task 4483 | stop processing: n_tokens = 1329, truncated = 0 4.45.305.507 I slot print_timing: id 2 | task 4487 | prompt eval time = 291.18 ms / 64 tokens ( 4.55 ms per token, 219.79 tokens per second) 4.45.305.512 I slot print_timing: id 2 | task 4487 | eval time = 5320.67 ms / 118 tokens ( 45.48 ms per token, 21.99 tokens per second) 4.45.305.513 I slot print_timing: id 2 | task 4487 | total time = 5611.85 ms / 182 tokens 4.45.305.513 I slot print_timing: id 2 | task 4487 | graphs reused = 3782 4.45.305.514 I slot print_timing: id 2 | task 4487 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.305.564 I slot release: id 2 | task 4487 | stop processing: n_tokens = 1295, truncated = 0 4.45.307.168 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.839 4.45.307.196 I slot launch_slot_: id 0 | task 4609 | processing task, is_child = 0 4.45.342.244 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.861 4.45.342.270 I slot launch_slot_: id 2 | task 4610 | processing task, is_child = 0 4.47.742.280 I slot print_timing: id 3 | task 4550 | n_gen = 100, tg = 20.08 t/s, tg_3s = 20.29 t/s 4.47.983.894 I slot print_timing: id 1 | task 4567 | prompt eval time = 312.55 ms / 62 tokens ( 5.04 ms per token, 198.37 tokens per second) 4.47.983.898 I slot print_timing: id 1 | task 4567 | eval time = 4276.49 ms / 90 tokens ( 48.05 ms per token, 20.81 tokens per second) 4.47.983.899 I slot print_timing: id 1 | task 4567 | total time = 4589.04 ms / 152 tokens 4.47.983.900 I slot print_timing: id 1 | task 4567 | graphs reused = 3828 4.47.983.900 I slot print_timing: id 1 | task 4567 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.983.964 I slot release: id 1 | task 4567 | stop processing: n_tokens = 1266, truncated = 0 4.48.044.846 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.881 4.48.044.871 I slot launch_slot_: id 1 | task 4662 | processing task, is_child = 0 4.49.799.574 I slot print_timing: id 3 | task 4550 | prompt eval time = 364.21 ms / 106 tokens ( 3.44 ms per token, 291.04 tokens per second) 4.49.799.579 I slot print_timing: id 3 | task 4550 | eval time = 6986.66 ms / 143 tokens ( 49.20 ms per token, 20.32 tokens per second) 4.49.799.579 I slot print_timing: id 3 | task 4550 | total time = 7350.87 ms / 249 tokens 4.49.799.580 I slot print_timing: id 3 | task 4550 | graphs reused = 3861 4.49.799.580 I slot print_timing: id 3 | task 4550 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.799.649 I slot release: id 3 | task 4550 | stop processing: n_tokens = 1362, truncated = 0 4.49.839.461 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.819 4.49.839.484 I slot launch_slot_: id 3 | task 4700 | processing task, is_child = 0 4.50.639.869 I slot print_timing: id 0 | task 4609 | n_gen = 100, tg = 21.42 t/s, tg_3s = 21.64 t/s 4.50.643.782 I slot print_timing: id 2 | task 4610 | n_gen = 100, tg = 21.41 t/s, tg_3s = 21.63 t/s 4.52.161.946 I slot print_timing: id 2 | task 4610 | prompt eval time = 675.92 ms / 94 tokens ( 7.19 ms per token, 139.07 tokens per second) 4.52.161.951 I slot print_timing: id 2 | task 4610 | eval time = 6141.79 ms / 137 tokens ( 45.16 ms per token, 22.14 tokens per second) 4.52.161.951 I slot print_timing: id 2 | task 4610 | total time = 6817.71 ms / 231 tokens 4.52.161.952 I slot print_timing: id 2 | task 4610 | graphs reused = 3908 4.52.161.953 I slot print_timing: id 2 | task 4610 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.162.009 I slot release: id 2 | task 4610 | stop processing: n_tokens = 1345, truncated = 0 4.52.221.516 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.829 4.52.221.540 I slot launch_slot_: id 2 | task 4752 | processing task, is_child = 0 4.52.960.693 I slot print_timing: id 1 | task 4662 | n_gen = 100, tg = 21.74 t/s, tg_3s = 21.96 t/s 4.53.656.049 I slot print_timing: id 0 | task 4609 | n_gen = 168, tg = 21.86 t/s, tg_3s = 22.55 t/s 4.53.860.708 I slot print_timing: id 0 | task 4609 | prompt eval time = 675.54 ms / 133 tokens ( 5.08 ms per token, 196.88 tokens per second) 4.53.860.712 I slot print_timing: id 0 | task 4609 | eval time = 7842.88 ms / 173 tokens ( 45.60 ms per token, 21.93 tokens per second) 4.53.860.713 I slot print_timing: id 0 | task 4609 | total time = 8518.42 ms / 306 tokens 4.53.860.714 I slot print_timing: id 0 | task 4609 | graphs reused = 3940 4.53.860.714 I slot print_timing: id 0 | task 4609 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.860.791 I slot release: id 0 | task 4609 | stop processing: n_tokens = 1420, truncated = 0 4.53.905.336 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.785 4.53.905.361 I slot launch_slot_: id 0 | task 4789 | processing task, is_child = 0 4.54.697.332 I slot print_timing: id 3 | task 4700 | n_gen = 100, tg = 22.03 t/s, tg_3s = 22.26 t/s 4.55.679.847 I slot print_timing: id 2 | task 4752 | prompt eval time = 291.29 ms / 68 tokens ( 4.28 ms per token, 233.45 tokens per second) 4.55.679.852 I slot print_timing: id 2 | task 4752 | eval time = 3167.01 ms / 73 tokens ( 43.99 ms per token, 22.73 tokens per second) 4.55.679.852 I slot print_timing: id 2 | task 4752 | total time = 3458.30 ms / 141 tokens 4.55.679.853 I slot print_timing: id 2 | task 4752 | graphs reused = 3976 4.55.679.853 I slot print_timing: id 2 | task 4752 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.679.914 I slot release: id 2 | task 4752 | stop processing: n_tokens = 1255, truncated = 0 4.55.738.905 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.888 4.55.738.926 I slot launch_slot_: id 2 | task 4829 | processing task, is_child = 0 4.56.042.891 I slot print_timing: id 1 | task 4662 | n_gen = 163, tg = 21.21 t/s, tg_3s = 20.44 t/s 4.57.532.254 I slot print_timing: id 3 | task 4700 | prompt eval time = 364.77 ms / 110 tokens ( 3.32 ms per token, 301.56 tokens per second) 4.57.532.259 I slot print_timing: id 3 | task 4700 | eval time = 7327.99 ms / 161 tokens ( 45.80 ms per token, 21.83 tokens per second) 4.57.532.260 I slot print_timing: id 3 | task 4700 | total time = 7692.76 ms / 271 tokens 4.57.532.260 I slot print_timing: id 3 | task 4700 | graphs reused = 4009 4.57.532.261 I slot print_timing: id 3 | task 4700 | graph reallocs = 0 / 0 (same size) / (changed size) 4.57.532.332 I slot release: id 3 | task 4700 | stop processing: n_tokens = 1385, truncated = 0 4.57.571.982 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.805 4.57.572.003 I slot launch_slot_: id 3 | task 4867 | processing task, is_child = 0 4.58.812.780 I slot print_timing: id 0 | task 4789 | n_gen = 100, tg = 21.51 t/s, tg_3s = 21.73 t/s 4.59.059.988 I slot print_timing: id 1 | task 4662 | n_gen = 230, tg = 21.50 t/s, tg_3s = 22.21 t/s 4.59.140.356 I slot print_timing: id 0 | task 4789 | prompt eval time = 304.60 ms / 100 tokens ( 3.05 ms per token, 328.30 tokens per second) 4.59.140.359 I slot print_timing: id 0 | task 4789 | eval time = 4930.39 ms / 108 tokens ( 46.08 ms per token, 21.70 tokens per second) 4.59.140.360 I slot print_timing: id 0 | task 4789 | total time = 5234.99 ms / 208 tokens 4.59.140.360 I slot print_timing: id 0 | task 4789 | graphs reused = 4039 4.59.140.361 I slot print_timing: id 0 | task 4789 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.140.416 I slot release: id 0 | task 4789 | stop processing: n_tokens = 1322, truncated = 0 4.59.184.730 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.843 4.59.184.755 I slot launch_slot_: id 0 | task 4902 | processing task, is_child = 0 4.59.566.072 I slot print_timing: id 1 | task 4662 | prompt eval time = 361.57 ms / 85 tokens ( 4.25 ms per token, 235.08 tokens per second) 4.59.566.079 I slot print_timing: id 1 | task 4662 | eval time = 11159.62 ms / 237 tokens ( 47.29 ms per token, 21.15 tokens per second) 4.59.566.079 I slot print_timing: id 1 | task 4662 | total time = 11521.19 ms / 322 tokens 4.59.566.080 I slot print_timing: id 1 | task 4662 | graphs reused = 4041 4.59.566.080 I slot print_timing: id 1 | task 4662 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.566.135 I slot release: id 1 | task 4662 | stop processing: n_tokens = 1436, truncated = 0 4.59.623.366 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.776 4.59.623.391 I slot launch_slot_: id 1 | task 4908 | processing task, is_child = 0 5.00.936.995 I slot print_timing: id 2 | task 4829 | n_gen = 100, tg = 20.62 t/s, tg_3s = 20.83 t/s 5.02.453.331 I slot print_timing: id 3 | task 4867 | n_gen = 100, tg = 21.64 t/s, tg_3s = 21.85 t/s 5.03.843.681 I slot print_timing: id 0 | task 4902 | n_gen = 100, tg = 22.72 t/s, tg_3s = 22.95 t/s 5.03.969.621 I slot print_timing: id 2 | task 4829 | n_gen = 174, tg = 22.08 t/s, tg_3s = 24.40 t/s 5.04.050.260 I slot print_timing: id 1 | task 4908 | n_gen = 100, tg = 24.37 t/s, tg_3s = 24.61 t/s 5.04.990.874 I slot print_timing: id 0 | task 4902 | prompt eval time = 301.93 ms / 73 tokens ( 4.14 ms per token, 241.78 tokens per second) 5.04.990.880 I slot print_timing: id 0 | task 4902 | eval time = 5504.18 ms / 128 tokens ( 43.34 ms per token, 23.07 tokens per second) 5.04.990.881 I slot print_timing: id 0 | task 4902 | total time = 5806.11 ms / 201 tokens 5.04.990.882 I slot print_timing: id 0 | task 4902 | graphs reused = 4162 5.04.990.887 I slot print_timing: id 0 | task 4902 | graph reallocs = 0 / 0 (same size) / (changed size) 5.04.990.943 I slot release: id 0 | task 4902 | stop processing: n_tokens = 1315, truncated = 0 5.05.035.396 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.848 5.05.035.421 I slot launch_slot_: id 0 | task 5034 | processing task, is_child = 0 5.05.476.178 I slot print_timing: id 3 | task 4867 | n_gen = 167, tg = 21.85 t/s, tg_3s = 22.16 t/s 5.06.995.268 I slot print_timing: id 2 | task 4829 | n_gen = 241, tg = 22.10 t/s, tg_3s = 22.14 t/s 5.07.076.108 I slot print_timing: id 1 | task 4908 | n_gen = 167, tg = 23.42 t/s, tg_3s = 22.14 t/s 5.08.515.362 I slot print_timing: id 3 | task 4867 | n_gen = 241, tg = 22.56 t/s, tg_3s = 24.35 t/s 5.09.209.884 I slot print_timing: id 1 | task 4908 | prompt eval time = 363.71 ms / 91 tokens ( 4.00 ms per token, 250.20 tokens per second) 5.09.209.887 I slot print_timing: id 1 | task 4908 | eval time = 9222.78 ms / 219 tokens ( 42.31 ms per token, 23.64 tokens per second) 5.09.209.888 I slot print_timing: id 1 | task 4908 | total time = 9586.48 ms / 310 tokens 5.09.209.889 I slot print_timing: id 1 | task 4908 | graphs reused = 4255 5.09.209.889 I slot print_timing: id 1 | task 4908 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.209.960 I slot release: id 1 | task 4908 | stop processing: n_tokens = 1424, truncated = 0 5.09.271.308 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.783 5.09.271.334 I slot launch_slot_: id 1 | task 5131 | processing task, is_child = 0 5.09.675.513 I slot print_timing: id 3 | task 4867 | prompt eval time = 305.50 ms / 70 tokens ( 4.36 ms per token, 229.13 tokens per second) 5.09.675.520 I slot print_timing: id 3 | task 4867 | eval time = 11798.00 ms / 262 tokens ( 45.20 ms per token, 22.12 tokens per second) 5.09.675.520 I slot print_timing: id 3 | task 4867 | total time = 12103.50 ms / 332 tokens 5.09.675.520 I slot print_timing: id 3 | task 4867 | graphs reused = 4255 5.09.675.521 I slot print_timing: id 3 | task 4867 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.675.562 I slot release: id 3 | task 4867 | stop processing: n_tokens = 1446, truncated = 0 5.09.713.183 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.771 5.09.713.200 I slot launch_slot_: id 3 | task 5136 | processing task, is_child = 0 5.09.946.391 I slot print_timing: id 0 | task 5034 | n_gen = 100, tg = 21.75 t/s, tg_3s = 21.97 t/s 5.10.021.912 I slot print_timing: id 2 | task 4829 | n_gen = 302, tg = 21.68 t/s, tg_3s = 20.15 t/s 5.11.368.163 I slot print_timing: id 0 | task 5034 | prompt eval time = 359.47 ms / 105 tokens ( 3.42 ms per token, 292.09 tokens per second) 5.11.368.169 I slot print_timing: id 0 | task 5034 | eval time = 5973.26 ms / 134 tokens ( 44.91 ms per token, 22.27 tokens per second) 5.11.368.170 I slot print_timing: id 0 | task 5034 | total time = 6332.73 ms / 239 tokens 5.11.368.170 I slot print_timing: id 0 | task 5034 | graphs reused = 4286 5.11.368.171 I slot print_timing: id 0 | task 5034 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.368.238 I slot release: id 0 | task 5034 | stop processing: n_tokens = 1353, truncated = 0 5.11.412.703 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.824 5.11.412.725 I slot launch_slot_: id 0 | task 5173 | processing task, is_child = 0 5.13.040.400 I slot print_timing: id 2 | task 4829 | n_gen = 369, tg = 21.77 t/s, tg_3s = 22.20 t/s 5.14.188.705 I slot print_timing: id 1 | task 5131 | n_gen = 100, tg = 21.73 t/s, tg_3s = 21.95 t/s 5.14.355.469 I slot print_timing: id 3 | task 5136 | n_gen = 100, tg = 22.85 t/s, tg_3s = 23.08 t/s 5.15.093.515 I slot print_timing: id 1 | task 5131 | prompt eval time = 362.26 ms / 79 tokens ( 4.59 ms per token, 218.08 tokens per second) 5.15.093.520 I slot print_timing: id 1 | task 5131 | eval time = 5459.91 ms / 122 tokens ( 45.12 ms per token, 22.16 tokens per second) 5.15.093.521 I slot print_timing: id 1 | task 5131 | total time = 5822.17 ms / 201 tokens 5.15.093.521 I slot print_timing: id 1 | task 5131 | graphs reused = 4367 5.15.093.522 I slot print_timing: id 1 | task 5131 | graph reallocs = 0 / 0 (same size) / (changed size) 5.15.093.592 I slot release: id 1 | task 5131 | stop processing: n_tokens = 1315, truncated = 0 5.15.154.783 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.848 5.15.154.807 I slot launch_slot_: id 1 | task 5258 | processing task, is_child = 0 5.16.052.682 I slot print_timing: id 2 | task 4829 | n_gen = 435, tg = 21.79 t/s, tg_3s = 21.91 t/s 5.16.132.954 I slot print_timing: id 0 | task 5173 | n_gen = 100, tg = 22.69 t/s, tg_3s = 22.92 t/s 5.17.383.018 I slot print_timing: id 3 | task 5136 | n_gen = 166, tg = 22.42 t/s, tg_3s = 21.80 t/s 5.19.084.632 I slot print_timing: id 2 | task 4829 | n_gen = 508, tg = 22.09 t/s, tg_3s = 24.08 t/s 5.19.164.533 I slot print_timing: id 0 | task 5173 | n_gen = 173, tg = 23.26 t/s, tg_3s = 24.08 t/s 5.19.618.311 I slot print_timing: id 1 | task 5258 | n_gen = 100, tg = 24.16 t/s, tg_3s = 24.41 t/s 5.20.069.792 I slot print_timing: id 1 | task 5258 | prompt eval time = 366.40 ms / 98 tokens ( 3.74 ms per token, 267.46 tokens per second) 5.20.069.795 I slot print_timing: id 1 | task 5258 | eval time = 4548.57 ms / 111 tokens ( 41.35 ms per token, 24.18 tokens per second) 5.20.069.795 I slot print_timing: id 1 | task 5258 | total time = 4914.98 ms / 209 tokens 5.20.069.796 I slot print_timing: id 1 | task 5258 | graphs reused = 4476 5.20.069.797 I slot print_timing: id 1 | task 5258 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.069.848 I slot release: id 1 | task 5258 | stop processing: n_tokens = 1323, truncated = 0 5.20.131.107 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.843 5.20.131.135 I slot launch_slot_: id 1 | task 5372 | processing task, is_child = 0 5.20.393.920 I slot print_timing: id 3 | task 5136 | n_gen = 233, tg = 22.37 t/s, tg_3s = 22.25 t/s 5.20.864.231 I slot print_timing: id 3 | task 5136 | prompt eval time = 309.80 ms / 97 tokens ( 3.19 ms per token, 313.11 tokens per second) 5.20.864.236 I slot print_timing: id 3 | task 5136 | eval time = 10841.23 ms / 243 tokens ( 44.80 ms per token, 22.32 tokens per second) 5.20.864.237 I slot print_timing: id 3 | task 5136 | total time = 11151.03 ms / 340 tokens 5.20.864.238 I slot print_timing: id 3 | task 5136 | graphs reused = 4484 5.20.864.239 I slot print_timing: id 3 | task 5136 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.864.305 I slot release: id 3 | task 5136 | stop processing: n_tokens = 1454, truncated = 0 5.20.904.762 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.767 5.20.904.786 I slot launch_slot_: id 3 | task 5385 | processing task, is_child = 0 5.22.111.825 I slot print_timing: id 2 | task 4829 | n_gen = 569, tg = 21.87 t/s, tg_3s = 20.15 t/s 5.22.190.567 I slot print_timing: id 0 | task 5173 | n_gen = 234, tg = 22.36 t/s, tg_3s = 20.16 t/s 5.24.786.805 I slot print_timing: id 1 | task 5372 | n_gen = 100, tg = 23.07 t/s, tg_3s = 23.30 t/s 5.25.122.064 I slot print_timing: id 2 | task 4829 | n_gen = 642, tg = 22.11 t/s, tg_3s = 24.25 t/s 5.25.202.081 I slot print_timing: id 0 | task 5173 | n_gen = 307, tg = 22.78 t/s, tg_3s = 24.24 t/s 5.25.290.439 I slot print_timing: id 3 | task 5385 | n_gen = 100, tg = 24.27 t/s, tg_3s = 24.52 t/s 5.26.611.371 I slot print_timing: id 3 | task 5385 | prompt eval time = 307.01 ms / 76 tokens ( 4.04 ms per token, 247.55 tokens per second) 5.26.611.379 I slot print_timing: id 3 | task 5385 | eval time = 5399.56 ms / 132 tokens ( 41.22 ms per token, 24.26 tokens per second) 5.26.611.379 I slot print_timing: id 3 | task 5385 | total time = 5706.57 ms / 208 tokens 5.26.611.380 I slot print_timing: id 3 | task 5385 | graphs reused = 4613 5.26.611.381 I slot print_timing: id 3 | task 5385 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.611.434 I slot release: id 3 | task 5385 | stop processing: n_tokens = 1322, truncated = 0 5.26.651.143 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.843 5.26.651.165 I slot launch_slot_: id 3 | task 5520 | processing task, is_child = 0 5.27.816.165 I slot print_timing: id 1 | task 5372 | n_gen = 168, tg = 22.81 t/s, tg_3s = 22.45 t/s 5.27.941.117 I slot print_timing: id 2 | task 4829 | prompt eval time = 397.06 ms / 106 tokens ( 3.75 ms per token, 266.96 tokens per second) 5.27.941.124 I slot print_timing: id 2 | task 4829 | eval time = 31805.13 ms / 705 tokens ( 45.18 ms per token, 22.13 tokens per second) 5.27.941.125 I slot print_timing: id 2 | task 4829 | total time = 32202.19 ms / 811 tokens 5.27.941.126 I slot print_timing: id 2 | task 4829 | graphs reused = 4636 5.27.941.127 I slot print_timing: id 2 | task 4829 | graph reallocs = 0 / 0 (same size) / (changed size) 5.27.941.189 I slot release: id 2 | task 4829 | stop processing: n_tokens = 1925, truncated = 0 5.28.000.691 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.579 5.28.000.720 I slot launch_slot_: id 2 | task 5548 | processing task, is_child = 0 5.28.311.737 I slot print_timing: id 0 | task 5173 | n_gen = 370, tg = 22.31 t/s, tg_3s = 20.26 t/s 5.28.686.239 I slot print_timing: id 1 | task 5372 | prompt eval time = 363.95 ms / 93 tokens ( 3.91 ms per token, 255.53 tokens per second) 5.28.686.244 I slot print_timing: id 1 | task 5372 | eval time = 8191.15 ms / 181 tokens ( 45.51 ms per token, 21.97 tokens per second) 5.28.686.246 I slot print_timing: id 1 | task 5372 | total time = 8555.09 ms / 274 tokens 5.28.686.247 I slot print_timing: id 1 | task 5372 | graphs reused = 4642 5.28.686.248 I slot print_timing: id 1 | task 5372 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.686.319 I slot release: id 1 | task 5372 | stop processing: n_tokens = 1388, truncated = 0 5.28.749.987 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.803 5.28.750.015 I slot launch_slot_: id 1 | task 5559 | processing task, is_child = 0 5.30.123.348 I slot print_timing: id 0 | task 5173 | prompt eval time = 356.42 ms / 108 tokens ( 3.30 ms per token, 303.01 tokens per second) 5.30.123.355 I slot print_timing: id 0 | task 5173 | eval time = 18354.20 ms / 407 tokens ( 45.21 ms per token, 22.12 tokens per second) 5.30.123.355 I slot print_timing: id 0 | task 5173 | total time = 18710.62 ms / 515 tokens 5.30.123.356 I slot print_timing: id 0 | task 5173 | graphs reused = 4667 5.30.123.357 I slot print_timing: id 0 | task 5173 | graph reallocs = 0 / 0 (same size) / (changed size) 5.30.123.415 I slot release: id 0 | task 5173 | stop processing: n_tokens = 1629, truncated = 0 5.30.167.614 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.684 5.30.167.639 I slot launch_slot_: id 0 | task 5589 | processing task, is_child = 0 5.31.832.551 I slot print_timing: id 3 | task 5520 | n_gen = 100, tg = 20.31 t/s, tg_3s = 20.51 t/s 5.31.952.198 I slot print_timing: id 1 | task 5559 | prompt eval time = 313.27 ms / 64 tokens ( 4.89 ms per token, 204.30 tokens per second) 5.31.952.205 I slot print_timing: id 1 | task 5559 | eval time = 2888.91 ms / 66 tokens ( 44.44 ms per token, 22.50 tokens per second) 5.31.952.206 I slot print_timing: id 1 | task 5559 | total time = 3202.18 ms / 130 tokens 5.31.952.207 I slot print_timing: id 1 | task 5559 | graphs reused = 4703 5.31.952.207 I slot print_timing: id 1 | task 5559 | graph reallocs = 0 / 0 (same size) / (changed size) 5.31.952.268 I slot release: id 1 | task 5559 | stop processing: n_tokens = 1244, truncated = 0 5.32.013.229 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.896 5.32.013.252 I slot launch_slot_: id 1 | task 5629 | processing task, is_child = 0 5.33.065.801 I slot print_timing: id 3 | task 5520 | prompt eval time = 306.67 ms / 71 tokens ( 4.32 ms per token, 231.52 tokens per second) 5.33.065.805 I slot print_timing: id 3 | task 5520 | eval time = 6107.96 ms / 124 tokens ( 49.66 ms per token, 20.14 tokens per second) 5.33.065.805 I slot print_timing: id 3 | task 5520 | total time = 6414.63 ms / 195 tokens 5.33.065.806 I slot print_timing: id 3 | task 5520 | graphs reused = 4720 5.33.065.807 I slot print_timing: id 3 | task 5520 | graph reallocs = 0 / 0 (same size) / (changed size) 5.33.065.866 I slot release: id 3 | task 5520 | stop processing: n_tokens = 1309, truncated = 0 5.33.105.571 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.852 5.33.105.594 I slot launch_slot_: id 3 | task 5651 | processing task, is_child = 0 5.33.413.861 I slot print_timing: id 2 | task 5548 | n_gen = 100, tg = 19.76 t/s, tg_3s = 19.96 t/s 5.35.010.325 I slot print_timing: id 0 | task 5589 | n_gen = 100, tg = 21.82 t/s, tg_3s = 22.04 t/s 5.36.448.046 I slot print_timing: id 1 | task 5629 | prompt eval time = 309.97 ms / 69 tokens ( 4.49 ms per token, 222.60 tokens per second) 5.36.448.052 I slot print_timing: id 1 | task 5629 | eval time = 4124.82 ms / 96 tokens ( 43.42 ms per token, 23.03 tokens per second) 5.36.448.053 I slot print_timing: id 1 | task 5629 | total time = 4434.79 ms / 165 tokens 5.36.448.054 I slot print_timing: id 1 | task 5629 | graphs reused = 4793 5.36.448.054 I slot print_timing: id 1 | task 5629 | graph reallocs = 0 / 0 (same size) / (changed size) 5.36.448.107 I slot release: id 1 | task 5629 | stop processing: n_tokens = 1279, truncated = 0 5.36.449.703 I slot print_timing: id 2 | task 5548 | n_gen = 174, tg = 21.50 t/s, tg_3s = 24.38 t/s 5.36.509.194 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.872 5.36.509.221 I slot launch_slot_: id 1 | task 5729 | processing task, is_child = 0 5.37.781.835 I slot print_timing: id 3 | task 5651 | n_gen = 100, tg = 22.67 t/s, tg_3s = 22.90 t/s 5.38.022.653 I slot print_timing: id 0 | task 5589 | n_gen = 166, tg = 21.86 t/s, tg_3s = 21.91 t/s 5.38.519.936 I slot print_timing: id 3 | task 5651 | prompt eval time = 309.36 ms / 88 tokens ( 3.52 ms per token, 284.46 tokens per second) 5.38.519.944 I slot print_timing: id 3 | task 5651 | eval time = 5104.98 ms / 118 tokens ( 43.63 ms per token, 22.92 tokens per second) 5.38.519.945 I slot print_timing: id 3 | task 5651 | total time = 5414.33 ms / 206 tokens 5.38.519.945 I slot print_timing: id 3 | task 5651 | graphs reused = 4832 5.38.519.946 I slot print_timing: id 3 | task 5651 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.520.020 I slot release: id 3 | task 5651 | stop processing: n_tokens = 1320, truncated = 0 5.38.556.619 I slot print_timing: id 0 | task 5589 | prompt eval time = 305.86 ms / 75 tokens ( 4.08 ms per token, 245.21 tokens per second) 5.38.556.623 I slot print_timing: id 0 | task 5589 | eval time = 8083.12 ms / 179 tokens ( 45.41 ms per token, 22.02 tokens per second) 5.38.556.624 I slot print_timing: id 0 | task 5589 | total time = 8388.97 ms / 254 tokens 5.38.556.624 I slot print_timing: id 0 | task 5589 | graphs reused = 4832 5.38.556.625 I slot print_timing: id 0 | task 5589 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.556.673 I slot release: id 0 | task 5589 | stop processing: n_tokens = 1367, truncated = 0 5.38.559.842 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.816 5.38.559.866 I slot launch_slot_: id 0 | task 5773 | processing task, is_child = 0 5.38.594.422 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.845 5.38.594.451 I slot launch_slot_: id 3 | task 5774 | processing task, is_child = 0 5.39.460.949 I slot print_timing: id 2 | task 5548 | n_gen = 227, tg = 20.44 t/s, tg_3s = 17.60 t/s 5.41.479.879 I slot print_timing: id 1 | task 5729 | n_gen = 100, tg = 21.49 t/s, tg_3s = 21.71 t/s 5.42.140.372 I slot print_timing: id 0 | task 5773 | prompt eval time = 589.82 ms / 65 tokens ( 9.07 ms per token, 110.20 tokens per second) 5.42.140.379 I slot print_timing: id 0 | task 5773 | eval time = 2956.09 ms / 73 tokens ( 41.06 ms per token, 24.36 tokens per second) 5.42.140.380 I slot print_timing: id 0 | task 5773 | total time = 3545.91 ms / 138 tokens 5.42.140.380 I slot print_timing: id 0 | task 5773 | graphs reused = 4903 5.42.140.381 I slot print_timing: id 0 | task 5773 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.140.434 I slot release: id 0 | task 5773 | stop processing: n_tokens = 1252, truncated = 0 5.42.184.867 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.891 5.42.184.892 I slot launch_slot_: id 0 | task 5850 | processing task, is_child = 0 5.42.491.128 I slot print_timing: id 2 | task 5548 | n_gen = 295, tg = 20.87 t/s, tg_3s = 22.44 t/s 5.42.772.126 I slot print_timing: id 2 | task 5548 | prompt eval time = 404.26 ms / 128 tokens ( 3.16 ms per token, 316.63 tokens per second) 5.42.772.133 I slot print_timing: id 2 | task 5548 | eval time = 14367.14 ms / 302 tokens ( 47.73 ms per token, 20.95 tokens per second) 5.42.772.134 I slot print_timing: id 2 | task 5548 | total time = 14771.40 ms / 430 tokens 5.42.772.135 I slot print_timing: id 2 | task 5548 | graphs reused = 4910 5.42.772.136 I slot print_timing: id 2 | task 5548 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.772.214 I slot release: id 2 | task 5548 | stop processing: n_tokens = 1543, truncated = 0 5.42.833.447 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.723 5.42.833.477 I slot launch_slot_: id 2 | task 5861 | processing task, is_child = 0 5.43.813.870 I slot print_timing: id 3 | task 5774 | n_gen = 100, tg = 21.40 t/s, tg_3s = 21.62 t/s 5.44.507.762 I slot print_timing: id 1 | task 5729 | n_gen = 160, tg = 20.83 t/s, tg_3s = 19.82 t/s 5.46.815.048 I slot print_timing: id 3 | task 5774 | n_gen = 173, tg = 22.55 t/s, tg_3s = 24.32 t/s 5.46.892.240 I slot print_timing: id 0 | task 5850 | n_gen = 100, tg = 22.48 t/s, tg_3s = 22.71 t/s 5.47.099.484 I slot print_timing: id 1 | task 5729 | prompt eval time = 364.56 ms / 95 tokens ( 3.84 ms per token, 260.59 tokens per second) 5.47.099.491 I slot print_timing: id 1 | task 5729 | eval time = 10225.69 ms / 223 tokens ( 46.06 ms per token, 21.71 tokens per second) 5.47.099.492 I slot print_timing: id 1 | task 5729 | total time = 10590.25 ms / 318 tokens 5.47.099.493 I slot print_timing: id 1 | task 5729 | graphs reused = 5003 5.47.099.493 I slot print_timing: id 1 | task 5729 | graph reallocs = 0 / 0 (same size) / (changed size) 5.47.099.562 I slot release: id 1 | task 5729 | stop processing: n_tokens = 1432, truncated = 0 5.47.160.897 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.779 5.47.160.921 I slot launch_slot_: id 1 | task 5959 | processing task, is_child = 0 5.47.603.143 I slot print_timing: id 2 | task 5861 | n_gen = 100, tg = 22.66 t/s, tg_3s = 22.89 t/s 5.49.830.906 I slot print_timing: id 3 | task 5774 | n_gen = 239, tg = 22.36 t/s, tg_3s = 21.88 t/s 5.49.908.525 I slot print_timing: id 0 | task 5850 | n_gen = 166, tg = 22.24 t/s, tg_3s = 21.88 t/s 5.50.571.162 I slot print_timing: id 3 | task 5774 | prompt eval time = 590.93 ms / 145 tokens ( 4.08 ms per token, 245.38 tokens per second) 5.50.571.165 I slot print_timing: id 3 | task 5774 | eval time = 11383.70 ms / 257 tokens ( 44.47 ms per token, 22.49 tokens per second) 5.50.571.166 I slot print_timing: id 3 | task 5774 | total time = 11974.62 ms / 402 tokens 5.50.571.167 I slot print_timing: id 3 | task 5774 | graphs reused = 5076 5.50.571.167 I slot print_timing: id 3 | task 5774 | graph reallocs = 0 / 0 (same size) / (changed size) 5.50.571.227 I slot release: id 3 | task 5774 | stop processing: n_tokens = 1516, truncated = 0 5.50.610.835 I slot print_timing: id 2 | task 5861 | n_gen = 173, tg = 23.32 t/s, tg_3s = 24.27 t/s 5.50.610.841 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.735 5.50.610.862 I slot launch_slot_: id 3 | task 6037 | processing task, is_child = 0 5.51.249.929 I slot print_timing: id 1 | task 5959 | prompt eval time = 362.69 ms / 85 tokens ( 4.27 ms per token, 234.36 tokens per second) 5.51.249.936 I slot print_timing: id 1 | task 5959 | eval time = 3726.31 ms / 85 tokens ( 44.36 ms per token, 22.54 tokens per second) 5.51.249.936 I slot print_timing: id 1 | task 5959 | total time = 4089.00 ms / 170 tokens 5.51.249.937 I slot print_timing: id 1 | task 5959 | graphs reused = 5082 5.51.249.938 I slot print_timing: id 1 | task 5959 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.249.996 I slot release: id 1 | task 5959 | stop processing: n_tokens = 1284, truncated = 0 5.51.310.705 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.868 5.51.310.729 I slot launch_slot_: id 1 | task 6048 | processing task, is_child = 0 5.52.936.509 I slot print_timing: id 0 | task 5850 | n_gen = 226, tg = 21.54 t/s, tg_3s = 19.82 t/s 5.53.635.825 I slot print_timing: id 2 | task 5861 | n_gen = 233, tg = 22.31 t/s, tg_3s = 19.83 t/s 5.53.759.886 I slot print_timing: id 2 | task 5861 | prompt eval time = 401.24 ms / 123 tokens ( 3.26 ms per token, 306.55 tokens per second) 5.53.759.890 I slot print_timing: id 2 | task 5861 | eval time = 10525.16 ms / 236 tokens ( 44.79 ms per token, 22.33 tokens per second) 5.53.759.890 I slot print_timing: id 2 | task 5861 | total time = 10926.40 ms / 359 tokens 5.53.759.891 I slot print_timing: id 2 | task 5861 | graphs reused = 5132 5.53.759.892 I slot print_timing: id 2 | task 5861 | graph reallocs = 0 / 0 (same size) / (changed size) 5.53.759.966 I slot release: id 2 | task 5861 | stop processing: n_tokens = 1473, truncated = 0 5.53.819.447 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.757 5.53.819.470 I slot launch_slot_: id 2 | task 6103 | processing task, is_child = 0 5.55.651.225 I slot print_timing: id 3 | task 6037 | n_gen = 100, tg = 21.19 t/s, tg_3s = 21.40 t/s 5.55.975.350 I slot print_timing: id 0 | task 5850 | n_gen = 292, tg = 21.58 t/s, tg_3s = 21.72 t/s 5.56.058.872 I slot print_timing: id 1 | task 6048 | n_gen = 100, tg = 22.57 t/s, tg_3s = 22.80 t/s 5.58.281.893 I slot print_timing: id 2 | task 6103 | n_gen = 100, tg = 24.36 t/s, tg_3s = 24.61 t/s 5.58.651.556 I slot print_timing: id 3 | task 6037 | n_gen = 173, tg = 22.42 t/s, tg_3s = 24.33 t/s 5.59.015.597 I slot print_timing: id 0 | task 5850 | n_gen = 366, tg = 22.09 t/s, tg_3s = 24.34 t/s 5.59.099.196 I slot print_timing: id 1 | task 6048 | n_gen = 174, tg = 23.30 t/s, tg_3s = 24.34 t/s 6.00.096.417 I slot print_timing: id 3 | task 6037 | prompt eval time = 367.61 ms / 120 tokens ( 3.06 ms per token, 326.44 tokens per second) 6.00.096.422 I slot print_timing: id 3 | task 6037 | eval time = 9117.94 ms / 208 tokens ( 44.05 ms per token, 22.70 tokens per second) 6.00.096.422 I slot print_timing: id 3 | task 6037 | total time = 9485.54 ms / 328 tokens 6.00.096.423 I slot print_timing: id 3 | task 6037 | graphs reused = 5273 6.00.096.423 I slot print_timing: id 3 | task 6037 | graph reallocs = 0 / 0 (same size) / (changed size) 6.00.096.479 I slot release: id 3 | task 6037 | stop processing: n_tokens = 1442, truncated = 0 6.00.136.172 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.773 6.00.136.195 I slot launch_slot_: id 3 | task 6250 | processing task, is_child = 0 6.01.223.122 I slot print_timing: id 2 | task 6103 | prompt eval time = 398.95 ms / 111 tokens ( 3.59 ms per token, 278.23 tokens per second) 6.01.223.129 I slot print_timing: id 2 | task 6103 | eval time = 7004.70 ms / 166 tokens ( 42.45 ms per token, 23.56 tokens per second) 6.01.223.130 I slot print_timing: id 2 | task 6103 | total time = 7403.64 ms / 277 tokens 6.01.223.130 I slot print_timing: id 2 | task 6103 | graphs reused = 5291 6.01.223.131 I slot print_timing: id 2 | task 6103 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.223.185 I slot release: id 2 | task 6103 | stop processing: n_tokens = 1391, truncated = 0 6.01.282.637 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.802 6.01.282.663 I slot launch_slot_: id 2 | task 6273 | processing task, is_child = 0 6.02.023.244 I slot print_timing: id 0 | task 5850 | n_gen = 427, tg = 21.81 t/s, tg_3s = 20.28 t/s 6.02.109.090 I slot print_timing: id 1 | task 6048 | n_gen = 235, tg = 22.42 t/s, tg_3s = 20.27 t/s 6.02.275.507 I slot print_timing: id 1 | task 6048 | prompt eval time = 362.05 ms / 85 tokens ( 4.26 ms per token, 234.77 tokens per second) 6.02.275.513 I slot print_timing: id 1 | task 6048 | eval time = 10602.72 ms / 239 tokens ( 44.55 ms per token, 22.45 tokens per second) 6.02.275.514 I slot print_timing: id 1 | task 6048 | total time = 10964.77 ms / 324 tokens 6.02.275.515 I slot print_timing: id 1 | task 6048 | graphs reused = 5306 6.02.275.515 I slot print_timing: id 1 | task 6048 | graph reallocs = 0 / 0 (same size) / (changed size) 6.02.275.571 I slot release: id 1 | task 6048 | stop processing: n_tokens = 1438, truncated = 0 6.02.336.533 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.775 6.02.336.557 I slot launch_slot_: id 1 | task 6293 | processing task, is_child = 0 6.05.040.654 I slot print_timing: id 0 | task 5850 | n_gen = 493, tg = 21.82 t/s, tg_3s = 21.87 t/s 6.05.086.470 I slot print_timing: id 3 | task 6250 | n_gen = 100, tg = 21.34 t/s, tg_3s = 21.56 t/s 6.05.618.138 I slot print_timing: id 2 | task 6273 | prompt eval time = 341.24 ms / 71 tokens ( 4.81 ms per token, 208.06 tokens per second) 6.05.618.145 I slot print_timing: id 2 | task 6273 | eval time = 3994.23 ms / 91 tokens ( 44.38 ms per token, 22.53 tokens per second) 6.05.618.145 I slot print_timing: id 2 | task 6273 | total time = 4335.47 ms / 162 tokens 6.05.618.146 I slot print_timing: id 2 | task 6273 | graphs reused = 5376 6.05.618.146 I slot print_timing: id 2 | task 6273 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.618.199 I slot release: id 2 | task 6273 | stop processing: n_tokens = 1276, truncated = 0 6.05.677.867 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.874 6.05.677.889 I slot launch_slot_: id 2 | task 6368 | processing task, is_child = 0 6.07.046.817 I slot print_timing: id 1 | task 6293 | n_gen = 100, tg = 22.78 t/s, tg_3s = 23.01 t/s 6.08.074.185 I slot print_timing: id 0 | task 5850 | n_gen = 560, tg = 21.85 t/s, tg_3s = 22.09 t/s 6.08.120.243 I slot print_timing: id 3 | task 6250 | n_gen = 167, tg = 21.63 t/s, tg_3s = 22.08 t/s 6.08.618.935 I slot print_timing: id 3 | task 6250 | prompt eval time = 311.22 ms / 96 tokens ( 3.24 ms per token, 308.47 tokens per second) 6.08.618.942 I slot print_timing: id 3 | task 6250 | eval time = 8171.52 ms / 179 tokens ( 45.91 ms per token, 21.78 tokens per second) 6.08.618.943 I slot print_timing: id 3 | task 6250 | total time = 8482.73 ms / 275 tokens 6.08.618.944 I slot print_timing: id 3 | task 6250 | graphs reused = 5438 6.08.618.944 I slot print_timing: id 3 | task 6250 | graph reallocs = 0 / 0 (same size) / (changed size) 6.08.619.003 I slot release: id 3 | task 6250 | stop processing: n_tokens = 1389, truncated = 0 6.08.658.875 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.803 6.08.658.896 I slot launch_slot_: id 3 | task 6435 | processing task, is_child = 0 6.10.072.178 I slot print_timing: id 1 | task 6293 | n_gen = 168, tg = 22.66 t/s, tg_3s = 22.48 t/s 6.10.319.985 I slot print_timing: id 2 | task 6368 | n_gen = 100, tg = 23.02 t/s, tg_3s = 23.25 t/s 6.11.098.325 I slot print_timing: id 0 | task 5850 | n_gen = 628, tg = 21.92 t/s, tg_3s = 22.49 t/s 6.11.847.792 I slot print_timing: id 2 | task 6368 | prompt eval time = 340.92 ms / 76 tokens ( 4.49 ms per token, 222.92 tokens per second) 6.11.847.796 I slot print_timing: id 2 | task 6368 | eval time = 5828.97 ms / 137 tokens ( 42.86 ms per token, 23.33 tokens per second) 6.11.847.796 I slot print_timing: id 2 | task 6368 | total time = 6169.89 ms / 213 tokens 6.11.847.797 I slot print_timing: id 2 | task 6368 | graphs reused = 5506 6.11.847.798 I slot print_timing: id 2 | task 6368 | graph reallocs = 0 / 0 (same size) / (changed size) 6.11.847.881 I slot release: id 2 | task 6368 | stop processing: n_tokens = 1327, truncated = 0 6.11.907.809 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.840 6.11.907.834 I slot launch_slot_: id 2 | task 6509 | processing task, is_child = 0 6.13.099.211 I slot print_timing: id 1 | task 6293 | n_gen = 232, tg = 22.22 t/s, tg_3s = 21.14 t/s 6.13.431.820 I slot print_timing: id 3 | task 6435 | n_gen = 100, tg = 22.17 t/s, tg_3s = 22.39 t/s 6.14.128.296 I slot print_timing: id 0 | task 5850 | n_gen = 692, tg = 21.84 t/s, tg_3s = 21.12 t/s 6.16.111.667 I slot print_timing: id 1 | task 6293 | n_gen = 305, tg = 22.67 t/s, tg_3s = 24.23 t/s 6.16.443.141 I slot print_timing: id 2 | task 6509 | n_gen = 100, tg = 24.25 t/s, tg_3s = 24.49 t/s 6.16.444.813 I slot print_timing: id 3 | task 6435 | n_gen = 173, tg = 23.00 t/s, tg_3s = 24.23 t/s 6.17.145.592 I slot print_timing: id 0 | task 5850 | n_gen = 765, tg = 22.04 t/s, tg_3s = 24.19 t/s 6.17.191.563 I slot print_timing: id 3 | task 6435 | prompt eval time = 306.68 ms / 83 tokens ( 3.69 ms per token, 270.64 tokens per second) 6.17.191.569 I slot print_timing: id 3 | task 6435 | eval time = 8225.98 ms / 191 tokens ( 43.29 ms per token, 23.10 tokens per second) 6.17.191.570 I slot print_timing: id 3 | task 6435 | total time = 8532.66 ms / 274 tokens 6.17.191.570 I slot print_timing: id 3 | task 6435 | graphs reused = 5622 6.17.191.571 I slot print_timing: id 3 | task 6435 | graph reallocs = 0 / 0 (same size) / (changed size) 6.17.191.631 I slot release: id 3 | task 6435 | stop processing: n_tokens = 1388, truncated = 0 6.17.231.327 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.803 6.17.231.348 I slot launch_slot_: id 3 | task 6630 | processing task, is_child = 0 6.19.137.646 I slot print_timing: id 1 | task 6293 | n_gen = 373, tg = 22.63 t/s, tg_3s = 22.47 t/s 6.19.471.302 I slot print_timing: id 2 | task 6509 | n_gen = 168, tg = 23.48 t/s, tg_3s = 22.46 t/s 6.20.175.284 I slot print_timing: id 0 | task 5850 | n_gen = 833, tg = 22.08 t/s, tg_3s = 22.44 t/s 6.20.837.827 I slot print_timing: id 2 | task 6509 | prompt eval time = 452.25 ms / 142 tokens ( 3.18 ms per token, 313.99 tokens per second) 6.20.837.831 I slot print_timing: id 2 | task 6509 | eval time = 8477.74 ms / 201 tokens ( 42.39 ms per token, 23.59 tokens per second) 6.20.837.832 I slot print_timing: id 2 | task 6509 | total time = 8929.99 ms / 343 tokens 6.20.837.833 I slot print_timing: id 2 | task 6509 | graphs reused = 5701 6.20.837.833 I slot print_timing: id 2 | task 6509 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.837.898 I slot release: id 2 | task 6509 | stop processing: n_tokens = 1457, truncated = 0 6.20.897.616 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.765 6.20.897.637 I slot launch_slot_: id 2 | task 6714 | processing task, is_child = 0 6.21.960.758 I slot print_timing: id 3 | task 6630 | n_gen = 100, tg = 22.39 t/s, tg_3s = 22.62 t/s 6.22.166.829 I slot print_timing: id 1 | task 6293 | n_gen = 438, tg = 22.45 t/s, tg_3s = 21.46 t/s 6.22.290.991 I slot print_timing: id 1 | task 6293 | prompt eval time = 364.46 ms / 86 tokens ( 4.24 ms per token, 235.97 tokens per second) 6.22.290.998 I slot print_timing: id 1 | task 6293 | eval time = 19589.97 ms / 441 tokens ( 44.52 ms per token, 22.46 tokens per second) 6.22.290.999 I slot print_timing: id 1 | task 6293 | total time = 19954.43 ms / 527 tokens 6.22.290.999 I slot print_timing: id 1 | task 6293 | graphs reused = 5724 6.22.291.000 I slot print_timing: id 1 | task 6293 | graph reallocs = 0 / 0 (same size) / (changed size) 6.22.291.054 I slot release: id 1 | task 6293 | stop processing: n_tokens = 1641, truncated = 0 6.22.352.288 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.679 6.22.352.314 I slot launch_slot_: id 1 | task 6742 | processing task, is_child = 0 6.23.212.493 I slot print_timing: id 0 | task 5850 | n_gen = 891, tg = 21.85 t/s, tg_3s = 19.10 t/s 6.23.424.988 I slot print_timing: id 3 | task 6630 | prompt eval time = 308.18 ms / 86 tokens ( 3.58 ms per token, 279.05 tokens per second) 6.23.424.996 I slot print_timing: id 3 | task 6630 | eval time = 5885.45 ms / 128 tokens ( 46.34 ms per token, 21.58 tokens per second) 6.23.424.996 I slot print_timing: id 3 | task 6630 | total time = 6193.63 ms / 214 tokens 6.23.424.997 I slot print_timing: id 3 | task 6630 | graphs reused = 5740 6.23.424.997 I slot print_timing: id 3 | task 6630 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.425.067 I slot release: id 3 | task 6630 | stop processing: n_tokens = 1328, truncated = 0 6.23.464.890 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.840 6.23.464.911 I slot launch_slot_: id 3 | task 6763 | processing task, is_child = 0 6.25.985.060 I slot print_timing: id 2 | task 6714 | n_gen = 100, tg = 21.11 t/s, tg_3s = 21.32 t/s 6.26.231.505 I slot print_timing: id 0 | task 5850 | n_gen = 957, tg = 21.86 t/s, tg_3s = 21.86 t/s 6.27.108.984 I slot print_timing: id 1 | task 6742 | n_gen = 100, tg = 22.55 t/s, tg_3s = 22.78 t/s 6.27.150.396 I slot print_timing: id 1 | task 6742 | prompt eval time = 366.68 ms / 72 tokens ( 5.09 ms per token, 196.36 tokens per second) 6.27.150.399 I slot print_timing: id 1 | task 6742 | eval time = 4431.39 ms / 101 tokens ( 44.31 ms per token, 22.57 tokens per second) 6.27.150.404 I slot print_timing: id 1 | task 6742 | total time = 4798.07 ms / 173 tokens 6.27.150.404 I slot print_timing: id 1 | task 6742 | graphs reused = 5819 6.27.150.405 I slot print_timing: id 1 | task 6742 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.150.462 I slot release: id 1 | task 6742 | stop processing: n_tokens = 1286, truncated = 0 6.27.211.784 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.868 6.27.211.807 I slot launch_slot_: id 1 | task 6847 | processing task, is_child = 0 6.28.233.300 I slot print_timing: id 3 | task 6763 | n_gen = 100, tg = 22.49 t/s, tg_3s = 22.72 t/s 6.28.523.684 I slot print_timing: id 2 | task 6714 | prompt eval time = 397.57 ms / 103 tokens ( 3.86 ms per token, 259.07 tokens per second) 6.28.523.690 I slot print_timing: id 2 | task 6714 | eval time = 7228.47 ms / 154 tokens ( 47.24 ms per token, 21.17 tokens per second) 6.28.523.691 I slot print_timing: id 2 | task 6714 | total time = 7626.04 ms / 257 tokens 6.28.523.691 I slot print_timing: id 2 | task 6714 | graphs reused = 5841 6.28.523.692 I slot print_timing: id 2 | task 6714 | graph reallocs = 0 / 0 (same size) / (changed size) 6.28.523.750 I slot release: id 2 | task 6714 | stop processing: n_tokens = 1371, truncated = 0 6.29.251.646 I slot print_timing: id 0 | task 5850 | n_gen = 1018, tg = 21.75 t/s, tg_3s = 20.20 t/s 6.29.586.023 I slot print_timing: id 0 | task 5850 | prompt eval time = 304.09 ms / 82 tokens ( 3.71 ms per token, 269.66 tokens per second) 6.29.586.025 I slot print_timing: id 0 | task 5850 | eval time = 47097.03 ms / 1024 tokens ( 46.04 ms per token, 21.72 tokens per second) 6.29.586.026 I slot print_timing: id 0 | task 5850 | total time = 47401.12 ms / 1106 tokens 6.29.586.026 I slot print_timing: id 0 | task 5850 | graphs reused = 5841 6.29.586.027 I slot print_timing: id 0 | task 5850 | graph reallocs = 0 / 0 (same size) / (changed size) 6.29.586.071 I slot release: id 0 | task 5850 | stop processing: n_tokens = 2220, truncated = 0 6.31.247.443 I slot print_timing: id 3 | task 6763 | n_gen = 166, tg = 22.25 t/s, tg_3s = 21.90 t/s 6.31.660.157 I slot print_timing: id 1 | task 6847 | prompt eval time = 366.82 ms / 70 tokens ( 5.24 ms per token, 190.83 tokens per second) 6.31.660.160 I slot print_timing: id 1 | task 6847 | eval time = 4081.52 ms / 93 tokens ( 44.36 ms per token, 22.54 tokens per second) 6.31.660.161 I slot print_timing: id 1 | task 6847 | total time = 4448.34 ms / 163 tokens 6.31.660.161 I slot print_timing: id 1 | task 6847 | graphs reused = 5841 6.31.660.162 I slot print_timing: id 1 | task 6847 | graph reallocs = 0 / 0 (same size) / (changed size) 6.31.660.225 I slot release: id 1 | task 6847 | stop processing: n_tokens = 1278, truncated = 0 6.32.802.040 I slot print_timing: id 3 | task 6763 | prompt eval time = 366.41 ms / 117 tokens ( 3.13 ms per token, 319.32 tokens per second) 6.32.802.045 I slot print_timing: id 3 | task 6763 | eval time = 8970.72 ms / 231 tokens ( 39.00 ms per token, 25.64 tokens per second) 6.32.802.046 I slot print_timing: id 3 | task 6763 | total time = 9337.12 ms / 348 tokens 6.32.802.047 I slot print_timing: id 3 | task 6763 | graphs reused = 5896 6.32.802.047 I slot print_timing: id 3 | task 6763 | graph reallocs = 0 / 0 (same size) / (changed size) 6.32.802.096 I slot release: id 3 | task 6763 | stop processing: n_tokens = 1462, truncated = 0 6.32.820.114 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1371, t_last = 334157737563 6.32.851.155 I slot launch_slot_: id 2 | task 6997 | processing task, is_child = 0 6.32.929.279 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2220, t_last = 334158799888 6.32.930.188 I slot launch_slot_: id 0 | task 6998 | processing task, is_child = 0 6.32.930.369 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1278, t_last = 334160874038 6.32.931.008 I slot launch_slot_: id 1 | task 6999 | processing task, is_child = 0 6.32.931.096 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1462, t_last = 334162015909 6.32.931.824 I slot launch_slot_: id 3 | task 7000 | processing task, is_child = 0 6.38.453.610 I slot print_timing: id 0 | task 6998 | prompt processing, n_tokens = 616, progress = 0.79, t = 5.52 s / 111.56 tokens per second 6.38.486.831 I slot print_timing: id 1 | task 6999 | prompt processing, n_tokens = 865, progress = 0.89, t = 5.52 s / 156.66 tokens per second 6.38.490.516 I slot print_timing: id 2 | task 6997 | prompt processing, n_tokens = 642, progress = 0.84, t = 5.52 s / 116.27 tokens per second 6.38.492.386 I slot print_timing: id 3 | task 7000 | prompt processing, n_tokens = 842, progress = 0.88, t = 5.52 s / 152.49 tokens per second 6.39.502.672 I slot print_timing: id 0 | task 6998 | prompt processing, n_tokens = 774, progress = 0.99, t = 6.57 s / 117.79 tokens per second 6.39.535.899 I slot print_timing: id 1 | task 6999 | prompt processing, n_tokens = 972, progress = 1.00, t = 6.57 s / 147.93 tokens per second 6.39.538.928 I slot print_timing: id 2 | task 6997 | prompt processing, n_tokens = 762, progress = 0.99, t = 6.57 s / 115.97 tokens per second 6.39.540.689 I slot print_timing: id 3 | task 7000 | prompt processing, n_tokens = 955, progress = 1.00, t = 6.57 s / 145.34 tokens per second 6.39.641.041 I slot print_timing: id 0 | task 6998 | prompt eval time = 6669.72 ms / 778 tokens ( 8.57 ms per token, 116.65 tokens per second) 6.39.641.043 I slot print_timing: id 0 | task 6998 | eval time = 39.48 ms / 2 tokens ( 39.48 ms per token, 25.33 tokens per second) 6.39.641.044 I slot print_timing: id 0 | task 6998 | total time = 6709.20 ms / 780 tokens 6.39.641.044 I slot print_timing: id 0 | task 6998 | graphs reused = 5897 6.39.641.045 I slot print_timing: id 0 | task 6998 | graph reallocs = 0 / 0 (same size) / (changed size) 6.39.641.091 I slot release: id 0 | task 6998 | stop processing: n_tokens = 788, truncated = 0 6.39.642.212 I slot print_timing: id 1 | task 6999 | prompt eval time = 6670.75 ms / 976 tokens ( 6.83 ms per token, 146.31 tokens per second) 6.39.642.214 I slot print_timing: id 1 | task 6999 | eval time = 39.56 ms / 2 tokens ( 39.56 ms per token, 25.28 tokens per second) 6.39.642.216 I slot print_timing: id 1 | task 6999 | total time = 6710.31 ms / 978 tokens 6.39.642.216 I slot print_timing: id 1 | task 6999 | graphs reused = 5897 6.39.642.216 I slot print_timing: id 1 | task 6999 | graph reallocs = 0 / 0 (same size) / (changed size) 6.39.642.264 I slot release: id 1 | task 6999 | stop processing: n_tokens = 986, truncated = 0 6.39.643.352 I slot print_timing: id 2 | task 6997 | prompt eval time = 6671.76 ms / 766 tokens ( 8.71 ms per token, 114.81 tokens per second) 6.39.643.355 I slot print_timing: id 2 | task 6997 | eval time = 39.63 ms / 2 tokens ( 39.63 ms per token, 25.24 tokens per second) 6.39.643.355 I slot print_timing: id 2 | task 6997 | total time = 6711.39 ms / 768 tokens 6.39.643.356 I slot print_timing: id 2 | task 6997 | graphs reused = 5897 6.39.643.356 I slot print_timing: id 2 | task 6997 | graph reallocs = 0 / 0 (same size) / (changed size) 6.39.643.379 I slot release: id 2 | task 6997 | stop processing: n_tokens = 776, truncated = 0 6.39.644.487 I slot print_timing: id 3 | task 7000 | prompt eval time = 6672.81 ms / 959 tokens ( 6.96 ms per token, 143.72 tokens per second) 6.39.644.491 I slot print_timing: id 3 | task 7000 | eval time = 39.64 ms / 2 tokens ( 39.64 ms per token, 25.23 tokens per second) 6.39.644.491 I slot print_timing: id 3 | task 7000 | total time = 6712.45 ms / 961 tokens 6.39.644.491 I slot print_timing: id 3 | task 7000 | graphs reused = 5897 6.39.644.492 I slot print_timing: id 3 | task 7000 | graph reallocs = 0 / 0 (same size) / (changed size) 6.39.644.518 I slot release: id 3 | task 7000 | stop processing: n_tokens = 969, truncated = 0 6.39.649.118 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 788, t_last = 334168854904 6.39.659.827 I slot launch_slot_: id 0 | task 7006 | processing task, is_child = 0 6.39.693.953 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.306 MiB) 6.39.693.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.151 MiB) 6.39.713.468 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 334168856077 6.39.713.652 I slot launch_slot_: id 1 | task 7007 | processing task, is_child = 0 6.39.713.785 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 776, t_last = 334168857192 6.39.713.895 I slot launch_slot_: id 2 | task 7008 | processing task, is_child = 0 6.39.713.968 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 969, t_last = 334168858331 6.39.714.068 I slot launch_slot_: id 3 | task 7009 | processing task, is_child = 0 6.44.722.136 I slot print_timing: id 0 | task 7006 | prompt processing, n_tokens = 690, progress = 0.87, t = 5.01 s / 137.78 tokens per second 6.44.751.687 I slot print_timing: id 1 | task 7007 | prompt processing, n_tokens = 690, progress = 0.87, t = 5.01 s / 137.78 tokens per second 6.44.753.774 I slot print_timing: id 2 | task 7008 | prompt processing, n_tokens = 690, progress = 0.82, t = 5.01 s / 137.79 tokens per second 6.44.755.689 I slot print_timing: id 3 | task 7009 | prompt processing, n_tokens = 690, progress = 0.81, t = 5.01 s / 137.79 tokens per second 6.45.743.680 I slot print_timing: id 0 | task 7006 | prompt processing, n_tokens = 792, progress = 1.00, t = 6.03 s / 131.35 tokens per second 6.45.777.309 I slot print_timing: id 1 | task 7007 | prompt processing, n_tokens = 794, progress = 1.00, t = 6.03 s / 131.69 tokens per second 6.45.781.039 I slot print_timing: id 2 | task 7008 | prompt processing, n_tokens = 837, progress = 1.00, t = 6.03 s / 138.82 tokens per second 6.45.783.132 I slot print_timing: id 3 | task 7009 | prompt processing, n_tokens = 845, progress = 1.00, t = 6.03 s / 140.15 tokens per second 6.45.883.496 I slot print_timing: id 0 | task 7006 | prompt eval time = 6129.75 ms / 796 tokens ( 7.70 ms per token, 129.86 tokens per second) 6.45.883.498 I slot print_timing: id 0 | task 7006 | eval time = 39.67 ms / 2 tokens ( 39.67 ms per token, 25.21 tokens per second) 6.45.883.498 I slot print_timing: id 0 | task 7006 | total time = 6169.42 ms / 798 tokens 6.45.883.499 I slot print_timing: id 0 | task 7006 | graphs reused = 5897 6.45.883.499 I slot print_timing: id 0 | task 7006 | graph reallocs = 0 / 0 (same size) / (changed size) 6.45.883.540 I slot release: id 0 | task 7006 | stop processing: n_tokens = 806, truncated = 0 6.45.884.625 I slot print_timing: id 1 | task 7007 | prompt eval time = 6130.69 ms / 798 tokens ( 7.68 ms per token, 130.16 tokens per second) 6.45.884.627 I slot print_timing: id 1 | task 7007 | eval time = 39.67 ms / 2 tokens ( 39.67 ms per token, 25.21 tokens per second) 6.45.884.628 I slot print_timing: id 1 | task 7007 | total time = 6170.35 ms / 800 tokens 6.45.884.628 I slot print_timing: id 1 | task 7007 | graphs reused = 5897 6.45.884.629 I slot print_timing: id 1 | task 7007 | graph reallocs = 0 / 0 (same size) / (changed size) 6.45.884.653 I slot release: id 1 | task 7007 | stop processing: n_tokens = 808, truncated = 0 6.45.885.756 I slot print_timing: id 2 | task 7008 | prompt eval time = 6131.56 ms / 841 tokens ( 7.29 ms per token, 137.16 tokens per second) 6.45.885.757 I slot print_timing: id 2 | task 7008 | eval time = 39.72 ms / 2 tokens ( 39.72 ms per token, 25.17 tokens per second) 6.45.885.758 I slot print_timing: id 2 | task 7008 | total time = 6171.28 ms / 843 tokens 6.45.885.758 I slot print_timing: id 2 | task 7008 | graphs reused = 5897 6.45.885.758 I slot print_timing: id 2 | task 7008 | graph reallocs = 0 / 0 (same size) / (changed size) 6.45.885.785 I slot release: id 2 | task 7008 | stop processing: n_tokens = 851, truncated = 0 6.45.886.885 I slot print_timing: id 3 | task 7009 | prompt eval time = 6132.50 ms / 849 tokens ( 7.22 ms per token, 138.44 tokens per second) 6.45.886.887 I slot print_timing: id 3 | task 7009 | eval time = 39.76 ms / 2 tokens ( 39.76 ms per token, 25.15 tokens per second) 6.45.886.888 I slot print_timing: id 3 | task 7009 | total time = 6172.26 ms / 851 tokens 6.45.886.888 I slot print_timing: id 3 | task 7009 | graphs reused = 5897 6.45.886.888 I slot print_timing: id 3 | task 7009 | graph reallocs = 0 / 0 (same size) / (changed size) 6.45.886.905 I slot release: id 3 | task 7009 | stop processing: n_tokens = 859, truncated = 0 6.45.891.487 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.874 (> 0.100 thold), f_keep = 0.901 6.45.891.532 I slot launch_slot_: id 0 | task 7015 | processing task, is_child = 0 6.45.891.627 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.106 MiB) 6.45.891.631 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.629 MiB) 6.45.891.633 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 49.228 MiB) 6.45.891.635 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.614 MiB) 6.45.891.637 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.490 MiB) 6.45.909.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.383 MiB) 6.45.909.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 6.45.909.018 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.368 MiB) 6.45.909.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.490 MiB) 6.45.909.023 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 51.690 MiB) 6.45.909.025 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.922 MiB) 6.45.926.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.029 MiB) 6.45.926.436 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 6.45.926.438 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.290 MiB) 6.45.926.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 6.45.926.443 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.798 MiB) 6.45.943.850 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 808, t_last = 334175098466 6.45.943.994 I slot launch_slot_: id 1 | task 7016 | processing task, is_child = 0 6.45.944.125 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 851, t_last = 334175099598 6.45.944.228 I slot launch_slot_: id 2 | task 7017 | processing task, is_child = 0 6.45.944.294 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 859, t_last = 334175100718 6.45.944.393 I slot launch_slot_: id 3 | task 7018 | processing task, is_child = 0 6.50.481.034 I slot print_timing: id 1 | task 7016 | prompt processing, n_tokens = 739, progress = 0.84, t = 4.53 s / 163.00 tokens per second 6.50.484.768 I slot print_timing: id 2 | task 7017 | prompt processing, n_tokens = 739, progress = 0.85, t = 4.53 s / 163.00 tokens per second 6.50.487.675 I slot print_timing: id 3 | task 7018 | prompt processing, n_tokens = 817, progress = 0.86, t = 4.53 s / 180.22 tokens per second 6.51.301.137 I slot print_timing: id 0 | task 7015 | prompt eval time = 4536.61 ms / 105 tokens ( 43.21 ms per token, 23.15 tokens per second) 6.51.301.139 I slot print_timing: id 0 | task 7015 | eval time = 820.11 ms / 2 tokens ( 820.11 ms per token, 1.22 tokens per second) 6.51.301.141 I slot print_timing: id 0 | task 7015 | total time = 5356.73 ms / 107 tokens 6.51.301.143 I slot print_timing: id 0 | task 7015 | graphs reused = 5897 6.51.301.144 I slot print_timing: id 0 | task 7015 | graph reallocs = 0 / 0 (same size) / (changed size) 6.51.301.216 I slot release: id 0 | task 7015 | stop processing: n_tokens = 832, truncated = 0 6.51.301.235 I slot print_timing: id 1 | task 7016 | prompt processing, n_tokens = 874, progress = 1.00, t = 5.35 s / 163.24 tokens per second 6.51.305.403 I slot print_timing: id 2 | task 7017 | prompt processing, n_tokens = 864, progress = 1.00, t = 5.35 s / 161.38 tokens per second 6.51.307.829 I slot print_timing: id 3 | task 7018 | prompt processing, n_tokens = 945, progress = 1.00, t = 5.35 s / 176.52 tokens per second 6.51.369.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 334180515029 6.51.369.522 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.044 MiB) 6.51.369.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.783 MiB) 6.51.369.528 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.321 MiB) 6.51.369.538 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.614 MiB) 6.51.369.540 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.368 MiB) 6.51.369.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 6.51.369.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.215 MiB) 6.51.390.556 I slot launch_slot_: id 0 | task 7023 | processing task, is_child = 0 6.52.258.207 I slot print_timing: id 1 | task 7016 | prompt eval time = 5421.13 ms / 878 tokens ( 6.17 ms per token, 161.96 tokens per second) 6.52.258.210 I slot print_timing: id 1 | task 7016 | eval time = 890.99 ms / 2 tokens ( 890.99 ms per token, 1.12 tokens per second) 6.52.258.212 I slot print_timing: id 1 | task 7016 | total time = 6312.11 ms / 880 tokens 6.52.258.212 I slot print_timing: id 1 | task 7016 | graphs reused = 5897 6.52.258.213 I slot print_timing: id 1 | task 7016 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.258.263 I slot release: id 1 | task 7016 | stop processing: n_tokens = 888, truncated = 0 6.52.259.482 I slot print_timing: id 2 | task 7017 | prompt eval time = 5422.07 ms / 868 tokens ( 6.25 ms per token, 160.09 tokens per second) 6.52.259.489 I slot print_timing: id 2 | task 7017 | eval time = 891.12 ms / 2 tokens ( 891.12 ms per token, 1.12 tokens per second) 6.52.259.490 I slot print_timing: id 2 | task 7017 | total time = 6313.20 ms / 870 tokens 6.52.259.490 I slot print_timing: id 2 | task 7017 | graphs reused = 5897 6.52.259.491 I slot print_timing: id 2 | task 7017 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.259.530 I slot release: id 2 | task 7017 | stop processing: n_tokens = 878, truncated = 0 6.52.260.757 I slot print_timing: id 3 | task 7018 | prompt eval time = 5422.99 ms / 949 tokens ( 5.71 ms per token, 175.00 tokens per second) 6.52.260.760 I slot print_timing: id 3 | task 7018 | eval time = 891.32 ms / 2 tokens ( 891.32 ms per token, 1.12 tokens per second) 6.52.260.760 I slot print_timing: id 3 | task 7018 | total time = 6314.31 ms / 951 tokens 6.52.260.760 I slot print_timing: id 3 | task 7018 | graphs reused = 5897 6.52.260.761 I slot print_timing: id 3 | task 7018 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.260.806 I slot release: id 3 | task 7018 | stop processing: n_tokens = 959, truncated = 0 6.53.018.919 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 888, t_last = 334181472076 6.53.019.031 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.013 MiB) 6.53.019.037 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.907 MiB) 6.53.019.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.735 MiB) 6.53.019.631 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.829 MiB) 6.53.019.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.736 MiB) 6.53.272.509 I slot launch_slot_: id 1 | task 7027 | processing task, is_child = 0 6.53.272.597 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.629 MiB) 6.53.272.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.814 MiB) 6.53.272.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.304 MiB) 6.53.273.309 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.951 MiB) 6.53.273.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.013 MiB) 6.53.291.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.399 MiB) 6.53.291.795 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.660 MiB) 6.53.292.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.907 MiB) 6.53.292.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.236 MiB) 6.53.292.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.430 MiB) 6.53.292.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.982 MiB) 6.53.311.728 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 878, t_last = 334181473343 6.53.311.874 I slot launch_slot_: id 2 | task 7028 | processing task, is_child = 0 6.53.311.945 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 959, t_last = 334181474619 6.53.312.047 I slot launch_slot_: id 3 | task 7029 | processing task, is_child = 0 6.56.372.772 I slot print_timing: id 1 | task 7027 | prompt processing, n_tokens = 507, progress = 0.50, t = 3.05 s / 165.97 tokens per second 6.56.376.506 I slot print_timing: id 2 | task 7028 | prompt processing, n_tokens = 402, progress = 0.44, t = 3.05 s / 131.62 tokens per second 6.56.378.230 I slot print_timing: id 3 | task 7029 | prompt processing, n_tokens = 747, progress = 0.42, t = 3.05 s / 244.63 tokens per second 6.58.828.608 I slot print_timing: id 0 | task 7023 | prompt eval time = 4982.17 ms / 988 tokens ( 5.04 ms per token, 198.31 tokens per second) 6.58.828.611 I slot print_timing: id 0 | task 7023 | eval time = 2455.87 ms / 2 tokens ( 2455.87 ms per token, 0.41 tokens per second) 6.58.828.612 I slot print_timing: id 0 | task 7023 | total time = 7438.04 ms / 990 tokens 6.58.828.612 I slot print_timing: id 0 | task 7023 | graphs reused = 5897 6.58.828.613 I slot print_timing: id 0 | task 7023 | graph reallocs = 0 / 0 (same size) / (changed size) 6.58.828.662 I slot release: id 0 | task 7023 | stop processing: n_tokens = 998, truncated = 0 6.58.828.682 I slot print_timing: id 1 | task 7027 | prompt processing, n_tokens = 871, progress = 0.85, t = 5.51 s / 158.06 tokens per second 6.58.832.713 I slot print_timing: id 2 | task 7028 | prompt processing, n_tokens = 747, progress = 0.82, t = 5.51 s / 135.57 tokens per second 6.58.835.264 I slot print_timing: id 3 | task 7029 | prompt processing, n_tokens = 1294, progress = 0.72, t = 5.51 s / 234.86 tokens per second 6.59.815.412 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 998, t_last = 334188042475 6.59.815.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.982 MiB) 6.59.815.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.752 MiB) 6.59.815.512 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 6.59.815.514 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 6.59.815.787 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 6.59.816.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 7.00.477.499 I slot launch_slot_: id 0 | task 7033 | processing task, is_child = 0 7.00.477.730 I slot print_timing: id 1 | task 7027 | prompt processing, n_tokens = 1019, progress = 1.00, t = 6.50 s / 156.80 tokens per second 7.00.479.554 I slot print_timing: id 2 | task 7028 | prompt processing, n_tokens = 914, progress = 1.00, t = 6.50 s / 140.66 tokens per second 7.00.481.335 I slot print_timing: id 3 | task 7029 | prompt processing, n_tokens = 1806, progress = 1.00, t = 6.50 s / 277.95 tokens per second 7.01.942.189 I slot print_timing: id 1 | task 7027 | prompt eval time = 7946.56 ms / 1023 tokens ( 7.77 ms per token, 128.73 tokens per second) 7.01.942.193 I slot print_timing: id 1 | task 7027 | eval time = 678.83 ms / 2 tokens ( 678.83 ms per token, 1.47 tokens per second) 7.01.942.193 I slot print_timing: id 1 | task 7027 | total time = 8625.39 ms / 1025 tokens 7.01.942.194 I slot print_timing: id 1 | task 7027 | graphs reused = 5897 7.01.942.195 I slot print_timing: id 1 | task 7027 | graph reallocs = 0 / 0 (same size) / (changed size) 7.01.942.267 I slot release: id 1 | task 7027 | stop processing: n_tokens = 1033, truncated = 0 7.01.943.493 I slot print_timing: id 2 | task 7028 | prompt eval time = 7947.23 ms / 918 tokens ( 8.66 ms per token, 115.51 tokens per second) 7.01.943.496 I slot print_timing: id 2 | task 7028 | eval time = 678.90 ms / 2 tokens ( 678.90 ms per token, 1.47 tokens per second) 7.01.943.497 I slot print_timing: id 2 | task 7028 | total time = 8626.13 ms / 920 tokens 7.01.943.497 I slot print_timing: id 2 | task 7028 | graphs reused = 5897 7.01.943.498 I slot print_timing: id 2 | task 7028 | graph reallocs = 0 / 0 (same size) / (changed size) 7.01.943.549 I slot release: id 2 | task 7028 | stop processing: n_tokens = 928, truncated = 0 7.01.944.766 I slot print_timing: id 3 | task 7029 | prompt eval time = 7947.88 ms / 1810 tokens ( 4.39 ms per token, 227.73 tokens per second) 7.01.944.772 I slot print_timing: id 3 | task 7029 | eval time = 678.97 ms / 2 tokens ( 678.97 ms per token, 1.47 tokens per second) 7.01.944.773 I slot print_timing: id 3 | task 7029 | total time = 8626.86 ms / 1812 tokens 7.01.944.773 I slot print_timing: id 3 | task 7029 | graphs reused = 5897 7.01.944.774 I slot print_timing: id 3 | task 7029 | graph reallocs = 0 / 0 (same size) / (changed size) 7.01.944.873 I slot release: id 3 | task 7029 | stop processing: n_tokens = 1820, truncated = 0 7.01.953.376 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1033, t_last = 334191156080 7.01.953.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 7.01.953.470 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.784 MiB) 7.01.953.609 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.321 MiB) 7.01.953.880 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.521 MiB) 7.01.954.135 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.568 MiB) 7.01.954.384 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 7.02.323.882 I slot launch_slot_: id 1 | task 7037 | processing task, is_child = 0 7.02.323.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.753 MiB) 7.02.324.236 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 7.02.324.483 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.507 MiB) 7.02.324.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.507 MiB) 7.02.324.933 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.091 MiB) 7.02.325.197 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.922 MiB) 7.02.325.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.999 MiB) 7.02.344.496 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 7.02.344.754 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.783 MiB) 7.02.345.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.497 MiB) 7.02.345.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 7.02.345.506 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.015 MiB) 7.02.346.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.213 MiB) 7.02.346.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.368 MiB) 7.02.367.668 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 334191157362 7.02.367.816 I slot launch_slot_: id 2 | task 7038 | processing task, is_child = 0 7.02.367.913 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1820, t_last = 334191158686 7.02.368.042 I slot launch_slot_: id 3 | task 7039 | processing task, is_child = 0 7.06.096.459 I slot print_timing: id 0 | task 7033 | prompt eval time = 3347.22 ms / 934 tokens ( 3.58 ms per token, 279.04 tokens per second) 7.06.096.465 I slot print_timing: id 0 | task 7033 | eval time = 2271.72 ms / 2 tokens ( 2271.72 ms per token, 0.44 tokens per second) 7.06.096.465 I slot print_timing: id 0 | task 7033 | total time = 5618.94 ms / 936 tokens 7.06.096.466 I slot print_timing: id 0 | task 7033 | graphs reused = 5898 7.06.096.466 I slot print_timing: id 0 | task 7033 | graph reallocs = 0 / 0 (same size) / (changed size) 7.06.096.521 I slot release: id 0 | task 7033 | stop processing: n_tokens = 944, truncated = 0 7.06.096.541 I slot print_timing: id 1 | task 7037 | prompt processing, n_tokens = 759, progress = 0.87, t = 3.72 s / 203.89 tokens per second 7.06.100.462 I slot print_timing: id 2 | task 7038 | prompt processing, n_tokens = 590, progress = 0.84, t = 3.72 s / 158.53 tokens per second 7.06.102.417 I slot print_timing: id 3 | task 7039 | prompt processing, n_tokens = 590, progress = 0.81, t = 3.72 s / 158.56 tokens per second 7.06.728.617 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 944, t_last = 334195310334 7.06.728.704 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.091 MiB) 7.06.728.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.738 MiB) 7.06.728.714 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.660 MiB) 7.06.728.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.414 MiB) 7.06.729.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.075 MiB) 7.06.729.337 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 7.06.816.425 I slot launch_slot_: id 0 | task 7043 | processing task, is_child = 0 7.06.816.790 I slot print_timing: id 1 | task 7037 | prompt processing, n_tokens = 868, progress = 1.00, t = 4.36 s / 199.28 tokens per second 7.06.819.467 I slot print_timing: id 2 | task 7038 | prompt processing, n_tokens = 696, progress = 0.99, t = 4.35 s / 159.82 tokens per second 7.06.821.942 I slot print_timing: id 3 | task 7039 | prompt processing, n_tokens = 724, progress = 0.99, t = 4.35 s / 166.28 tokens per second 7.08.004.803 I slot print_timing: id 1 | task 7037 | prompt eval time = 4856.76 ms / 872 tokens ( 5.57 ms per token, 179.54 tokens per second) 7.08.004.808 I slot print_timing: id 1 | task 7037 | eval time = 775.19 ms / 2 tokens ( 775.19 ms per token, 1.29 tokens per second) 7.08.004.808 I slot print_timing: id 1 | task 7037 | total time = 5631.95 ms / 874 tokens 7.08.004.809 I slot print_timing: id 1 | task 7037 | graphs reused = 5898 7.08.004.809 I slot print_timing: id 1 | task 7037 | graph reallocs = 0 / 0 (same size) / (changed size) 7.08.004.874 I slot release: id 1 | task 7037 | stop processing: n_tokens = 882, truncated = 0 7.08.006.026 I slot print_timing: id 2 | task 7038 | prompt eval time = 4857.02 ms / 700 tokens ( 6.94 ms per token, 144.12 tokens per second) 7.08.006.028 I slot print_timing: id 2 | task 7038 | eval time = 775.21 ms / 2 tokens ( 775.21 ms per token, 1.29 tokens per second) 7.08.006.029 I slot print_timing: id 2 | task 7038 | total time = 5632.23 ms / 702 tokens 7.08.006.029 I slot print_timing: id 2 | task 7038 | graphs reused = 5898 7.08.006.029 I slot print_timing: id 2 | task 7038 | graph reallocs = 0 / 0 (same size) / (changed size) 7.08.006.069 I slot release: id 2 | task 7038 | stop processing: n_tokens = 710, truncated = 0 7.08.007.193 I slot print_timing: id 3 | task 7039 | prompt eval time = 4857.59 ms / 728 tokens ( 6.67 ms per token, 149.87 tokens per second) 7.08.007.197 I slot print_timing: id 3 | task 7039 | eval time = 775.19 ms / 2 tokens ( 775.19 ms per token, 1.29 tokens per second) 7.08.007.198 I slot print_timing: id 3 | task 7039 | total time = 5632.78 ms / 730 tokens 7.08.007.199 I slot print_timing: id 3 | task 7039 | graphs reused = 5898 7.08.007.199 I slot print_timing: id 3 | task 7039 | graph reallocs = 0 / 0 (same size) / (changed size) 7.08.007.234 I slot release: id 3 | task 7039 | stop processing: n_tokens = 738, truncated = 0 7.08.294.963 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 334197218687 7.08.295.061 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 7.08.295.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.075 MiB) 7.08.295.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 7.08.295.232 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.306 MiB) 7.08.295.501 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.829 MiB) 7.08.295.766 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.267 MiB) 7.08.311.830 I slot launch_slot_: id 1 | task 7048 | processing task, is_child = 0 7.08.311.895 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.738 MiB) 7.08.312.208 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.213 MiB) 7.08.312.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.292 MiB) 7.08.312.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.753 MiB) 7.08.312.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 7.08.313.162 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.939 MiB) 7.08.327.906 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.629 MiB) 7.08.328.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.153 MiB) 7.08.328.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 35.621 MiB) 7.08.328.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.568 MiB) 7.08.328.975 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.891 MiB) 7.08.343.412 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.882 7.08.343.487 I slot launch_slot_: id 2 | task 7049 | processing task, is_child = 0 7.08.343.559 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.848 7.08.343.594 I slot launch_slot_: id 3 | task 7050 | processing task, is_child = 0 7.09.388.371 I slot print_timing: id 0 | task 7043 | prompt eval time = 1478.52 ms / 703 tokens ( 2.10 ms per token, 475.48 tokens per second) 7.09.388.373 I slot print_timing: id 0 | task 7043 | eval time = 1093.41 ms / 2 tokens ( 1093.41 ms per token, 0.91 tokens per second) 7.09.388.374 I slot print_timing: id 0 | task 7043 | total time = 2571.93 ms / 705 tokens 7.09.388.374 I slot print_timing: id 0 | task 7043 | graphs reused = 5898 7.09.388.375 I slot print_timing: id 0 | task 7043 | graph reallocs = 0 / 0 (same size) / (changed size) 7.09.388.431 I slot release: id 0 | task 7043 | stop processing: n_tokens = 713, truncated = 0 7.10.195.152 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 713, t_last = 334198602244 7.10.195.264 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.521 MiB) 7.10.195.269 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.883 MiB) 7.10.195.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.705 MiB) 7.10.195.819 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.954 MiB) 7.10.196.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.925 MiB) 7.10.212.852 I slot launch_slot_: id 0 | task 7053 | processing task, is_child = 0 7.11.331.493 I slot print_timing: id 2 | task 7049 | prompt eval time = 1849.75 ms / 89 tokens ( 20.78 ms per token, 48.11 tokens per second) 7.11.331.497 I slot print_timing: id 2 | task 7049 | eval time = 1137.58 ms / 2 tokens ( 1137.58 ms per token, 0.88 tokens per second) 7.11.331.497 I slot print_timing: id 2 | task 7049 | total time = 2987.32 ms / 91 tokens 7.11.331.498 I slot print_timing: id 2 | task 7049 | graphs reused = 5898 7.11.331.498 I slot print_timing: id 2 | task 7049 | graph reallocs = 0 / 0 (same size) / (changed size) 7.11.331.569 I slot release: id 2 | task 7049 | stop processing: n_tokens = 716, truncated = 0 7.11.332.705 I slot print_timing: id 3 | task 7050 | prompt eval time = 1849.21 ms / 95 tokens ( 19.47 ms per token, 51.37 tokens per second) 7.11.332.709 I slot print_timing: id 3 | task 7050 | eval time = 1137.56 ms / 2 tokens ( 1137.56 ms per token, 0.88 tokens per second) 7.11.332.709 I slot print_timing: id 3 | task 7050 | total time = 2986.77 ms / 97 tokens 7.11.332.710 I slot print_timing: id 3 | task 7050 | graphs reused = 5898 7.11.332.710 I slot print_timing: id 3 | task 7050 | graph reallocs = 0 / 0 (same size) / (changed size) 7.11.332.749 I slot release: id 3 | task 7050 | stop processing: n_tokens = 722, truncated = 0 7.12.076.008 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 334200545382 7.12.076.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.390 MiB) 7.12.076.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.414 MiB) 7.12.076.674 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.953 MiB) 7.12.077.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.876 MiB) 7.12.077.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.132 MiB) 7.12.089.883 I slot launch_slot_: id 2 | task 7056 | processing task, is_child = 0 7.12.089.956 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.137 MiB) 7.12.100.733 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 722, t_last = 334200546562 7.12.100.840 I slot launch_slot_: id 3 | task 7057 | processing task, is_child = 0 7.14.140.520 I slot print_timing: id 1 | task 7048 | prompt eval time = 3732.40 ms / 864 tokens ( 4.32 ms per token, 231.49 tokens per second) 7.14.140.524 I slot print_timing: id 1 | task 7048 | eval time = 2064.51 ms / 2 tokens ( 2064.51 ms per token, 0.48 tokens per second) 7.14.140.524 I slot print_timing: id 1 | task 7048 | total time = 5796.91 ms / 866 tokens 7.14.140.525 I slot print_timing: id 1 | task 7048 | graphs reused = 5898 7.14.140.525 I slot print_timing: id 1 | task 7048 | graph reallocs = 0 / 0 (same size) / (changed size) 7.14.140.595 I slot release: id 1 | task 7048 | stop processing: n_tokens = 874, truncated = 0 7.14.140.621 I slot print_timing: id 0 | task 7053 | prompt processing, n_tokens = 977, progress = 1.00, t = 3.93 s / 248.82 tokens per second 7.15.547.641 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 874, t_last = 334203354408 7.15.560.000 I slot launch_slot_: id 1 | task 7060 | processing task, is_child = 0 7.15.560.211 I slot print_timing: id 2 | task 7056 | prompt processing, n_tokens = 850, progress = 0.86, t = 3.44 s / 246.84 tokens per second 7.15.561.906 I slot print_timing: id 3 | task 7057 | prompt processing, n_tokens = 850, progress = 0.83, t = 3.44 s / 246.86 tokens per second 7.17.109.759 I slot print_timing: id 0 | task 7053 | prompt eval time = 5334.76 ms / 981 tokens ( 5.44 ms per token, 183.89 tokens per second) 7.17.109.762 I slot print_timing: id 0 | task 7053 | eval time = 1562.13 ms / 2 tokens ( 1562.13 ms per token, 0.64 tokens per second) 7.17.109.763 I slot print_timing: id 0 | task 7053 | total time = 6896.89 ms / 983 tokens 7.17.109.763 I slot print_timing: id 0 | task 7053 | graphs reused = 5898 7.17.109.764 I slot print_timing: id 0 | task 7053 | graph reallocs = 0 / 0 (same size) / (changed size) 7.17.109.831 I slot release: id 0 | task 7053 | stop processing: n_tokens = 991, truncated = 0 7.17.113.612 I slot print_timing: id 2 | task 7056 | prompt processing, n_tokens = 991, progress = 1.00, t = 5.01 s / 197.98 tokens per second 7.17.115.887 I slot print_timing: id 3 | task 7057 | prompt processing, n_tokens = 1021, progress = 1.00, t = 5.01 s / 203.98 tokens per second 7.17.872.371 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.894 7.17.872.490 I slot launch_slot_: id 0 | task 7063 | processing task, is_child = 0 7.18.422.272 I slot print_timing: id 2 | task 7056 | prompt eval time = 5768.15 ms / 995 tokens ( 5.80 ms per token, 172.50 tokens per second) 7.18.422.275 I slot print_timing: id 2 | task 7056 | eval time = 551.09 ms / 2 tokens ( 551.09 ms per token, 1.81 tokens per second) 7.18.422.276 I slot print_timing: id 2 | task 7056 | total time = 6319.24 ms / 997 tokens 7.18.422.276 I slot print_timing: id 2 | task 7056 | graphs reused = 5898 7.18.422.277 I slot print_timing: id 2 | task 7056 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.422.344 I slot release: id 2 | task 7056 | stop processing: n_tokens = 1005, truncated = 0 7.18.423.534 I slot print_timing: id 3 | task 7057 | prompt eval time = 5769.15 ms / 1025 tokens ( 5.63 ms per token, 177.67 tokens per second) 7.18.423.538 I slot print_timing: id 3 | task 7057 | eval time = 551.17 ms / 2 tokens ( 551.17 ms per token, 1.81 tokens per second) 7.18.423.538 I slot print_timing: id 3 | task 7057 | total time = 6320.32 ms / 1027 tokens 7.18.423.539 I slot print_timing: id 3 | task 7057 | graphs reused = 5898 7.18.423.539 I slot print_timing: id 3 | task 7057 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.423.590 I slot release: id 3 | task 7057 | stop processing: n_tokens = 1035, truncated = 0 7.18.474.574 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1005, t_last = 334207636157 7.18.474.667 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.937 MiB) 7.18.483.834 I slot launch_slot_: id 2 | task 7066 | processing task, is_child = 0 7.18.483.919 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.271 MiB) 7.18.492.598 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 334207637403 7.18.492.716 I slot launch_slot_: id 3 | task 7067 | processing task, is_child = 0 7.20.096.187 I slot print_timing: id 0 | task 7063 | prompt eval time = 600.95 ms / 105 tokens ( 5.72 ms per token, 174.72 tokens per second) 7.20.096.192 I slot print_timing: id 0 | task 7063 | eval time = 1622.73 ms / 2 tokens ( 1622.73 ms per token, 0.62 tokens per second) 7.20.096.192 I slot print_timing: id 0 | task 7063 | total time = 2223.68 ms / 107 tokens 7.20.096.193 I slot print_timing: id 0 | task 7063 | graphs reused = 5898 7.20.096.193 I slot print_timing: id 0 | task 7063 | graph reallocs = 0 / 0 (same size) / (changed size) 7.20.096.258 I slot release: id 0 | task 7063 | stop processing: n_tokens = 992, truncated = 0 7.20.097.499 I slot print_timing: id 1 | task 7060 | prompt eval time = 2914.56 ms / 987 tokens ( 2.95 ms per token, 338.64 tokens per second) 7.20.097.503 I slot print_timing: id 1 | task 7060 | eval time = 1622.93 ms / 2 tokens ( 1622.93 ms per token, 0.62 tokens per second) 7.20.097.503 I slot print_timing: id 1 | task 7060 | total time = 4537.49 ms / 989 tokens 7.20.097.504 I slot print_timing: id 1 | task 7060 | graphs reused = 5898 7.20.097.504 I slot print_timing: id 1 | task 7060 | graph reallocs = 0 / 0 (same size) / (changed size) 7.20.097.546 I slot release: id 1 | task 7060 | stop processing: n_tokens = 997, truncated = 0 7.21.108.026 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 992, t_last = 334209310071 7.21.108.125 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.150 MiB) 7.21.302.320 I slot launch_slot_: id 0 | task 7070 | processing task, is_child = 0 7.21.316.871 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 997, t_last = 334209311359 7.21.317.008 I slot launch_slot_: id 1 | task 7071 | processing task, is_child = 0 7.23.678.327 I slot print_timing: id 2 | task 7066 | prompt processing, n_tokens = 871, progress = 1.00, t = 4.99 s / 174.63 tokens per second 7.23.680.122 I slot print_timing: id 3 | task 7067 | prompt processing, n_tokens = 1010, progress = 1.00, t = 4.99 s / 202.51 tokens per second 7.25.034.392 I slot print_timing: id 0 | task 7070 | prompt processing, n_tokens = 768, progress = 0.86, t = 3.71 s / 206.73 tokens per second 7.25.036.900 I slot print_timing: id 1 | task 7071 | prompt processing, n_tokens = 768, progress = 0.77, t = 3.71 s / 206.75 tokens per second 7.25.798.882 I slot print_timing: id 2 | task 7066 | prompt eval time = 6540.35 ms / 875 tokens ( 7.47 ms per token, 133.78 tokens per second) 7.25.798.889 I slot print_timing: id 2 | task 7066 | eval time = 765.78 ms / 2 tokens ( 765.78 ms per token, 1.31 tokens per second) 7.25.798.889 I slot print_timing: id 2 | task 7066 | total time = 7306.14 ms / 877 tokens 7.25.798.890 I slot print_timing: id 2 | task 7066 | graphs reused = 5898 7.25.798.890 I slot print_timing: id 2 | task 7066 | graph reallocs = 0 / 0 (same size) / (changed size) 7.25.798.960 I slot release: id 2 | task 7066 | stop processing: n_tokens = 885, truncated = 0 7.25.800.165 I slot print_timing: id 3 | task 7067 | prompt eval time = 6541.43 ms / 1014 tokens ( 6.45 ms per token, 155.01 tokens per second) 7.25.800.171 I slot print_timing: id 3 | task 7067 | eval time = 765.79 ms / 2 tokens ( 765.79 ms per token, 1.31 tokens per second) 7.25.800.171 I slot print_timing: id 3 | task 7067 | total time = 7307.22 ms / 1016 tokens 7.25.800.171 I slot print_timing: id 3 | task 7067 | graphs reused = 5898 7.25.800.172 I slot print_timing: id 3 | task 7067 | graph reallocs = 0 / 0 (same size) / (changed size) 7.25.800.229 I slot release: id 3 | task 7067 | stop processing: n_tokens = 1024, truncated = 0 7.25.800.243 I slot print_timing: id 0 | task 7070 | prompt processing, n_tokens = 890, progress = 1.00, t = 4.48 s / 198.63 tokens per second 7.25.803.542 I slot print_timing: id 1 | task 7071 | prompt processing, n_tokens = 998, progress = 1.00, t = 4.48 s / 222.74 tokens per second 7.25.845.266 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.785 7.25.845.331 I slot launch_slot_: id 3 | task 7076 | processing task, is_child = 0 7.25.845.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.943 MiB) 7.25.852.528 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 334215012773 7.25.852.645 I slot launch_slot_: id 2 | task 7077 | processing task, is_child = 0 7.26.973.318 I slot print_timing: id 0 | task 7070 | prompt eval time = 4527.15 ms / 894 tokens ( 5.06 ms per token, 197.48 tokens per second) 7.26.973.322 I slot print_timing: id 0 | task 7070 | eval time = 1129.14 ms / 2 tokens ( 1129.14 ms per token, 0.89 tokens per second) 7.26.973.323 I slot print_timing: id 0 | task 7070 | total time = 5656.29 ms / 896 tokens 7.26.973.324 I slot print_timing: id 0 | task 7070 | graphs reused = 5898 7.26.973.324 I slot print_timing: id 0 | task 7070 | graph reallocs = 0 / 0 (same size) / (changed size) 7.26.973.390 I slot release: id 0 | task 7070 | stop processing: n_tokens = 904, truncated = 0 7.26.974.593 I slot print_timing: id 1 | task 7071 | prompt eval time = 4528.02 ms / 1002 tokens ( 4.52 ms per token, 221.29 tokens per second) 7.26.974.599 I slot print_timing: id 1 | task 7071 | eval time = 1129.33 ms / 2 tokens ( 1129.33 ms per token, 0.89 tokens per second) 7.26.974.600 I slot print_timing: id 1 | task 7071 | total time = 5657.35 ms / 1004 tokens 7.26.974.600 I slot print_timing: id 1 | task 7071 | graphs reused = 5898 7.26.974.600 I slot print_timing: id 1 | task 7071 | graph reallocs = 0 / 0 (same size) / (changed size) 7.26.974.659 I slot release: id 1 | task 7071 | stop processing: n_tokens = 1012, truncated = 0 7.27.600.046 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.889 7.27.600.153 I slot launch_slot_: id 0 | task 7080 | processing task, is_child = 0 7.27.600.271 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.012 MiB) 7.27.610.063 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1012, t_last = 334216188472 7.27.610.186 I slot launch_slot_: id 1 | task 7081 | processing task, is_child = 0 7.29.028.665 I slot print_timing: id 3 | task 7076 | prompt eval time = 1747.19 ms / 102 tokens ( 17.13 ms per token, 58.38 tokens per second) 7.29.028.672 I slot print_timing: id 3 | task 7076 | eval time = 1428.62 ms / 2 tokens ( 1428.62 ms per token, 0.70 tokens per second) 7.29.028.676 I slot print_timing: id 3 | task 7076 | total time = 3175.80 ms / 104 tokens 7.29.028.676 I slot print_timing: id 3 | task 7076 | graphs reused = 5898 7.29.028.677 I slot print_timing: id 3 | task 7076 | graph reallocs = 0 / 0 (same size) / (changed size) 7.29.028.760 I slot release: id 3 | task 7076 | stop processing: n_tokens = 907, truncated = 0 7.29.033.942 I slot print_timing: id 2 | task 7077 | prompt processing, n_tokens = 979, progress = 1.00, t = 3.17 s / 308.36 tokens per second 7.29.726.069 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 334218242573 7.29.742.147 I slot launch_slot_: id 3 | task 7084 | processing task, is_child = 0 7.30.838.116 I slot print_timing: id 0 | task 7080 | prompt eval time = 2114.67 ms / 81 tokens ( 26.11 ms per token, 38.30 tokens per second) 7.30.838.120 I slot print_timing: id 0 | task 7080 | eval time = 1113.24 ms / 2 tokens ( 1113.24 ms per token, 0.90 tokens per second) 7.30.838.121 I slot print_timing: id 0 | task 7080 | total time = 3227.91 ms / 83 tokens 7.30.838.121 I slot print_timing: id 0 | task 7080 | graphs reused = 5898 7.30.838.122 I slot print_timing: id 0 | task 7080 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.838.193 I slot release: id 0 | task 7080 | stop processing: n_tokens = 886, truncated = 0 7.30.839.447 I slot print_timing: id 2 | task 7077 | prompt eval time = 3873.41 ms / 983 tokens ( 3.94 ms per token, 253.78 tokens per second) 7.30.839.453 I slot print_timing: id 2 | task 7077 | eval time = 1113.38 ms / 2 tokens ( 1113.38 ms per token, 0.90 tokens per second) 7.30.839.454 I slot print_timing: id 2 | task 7077 | total time = 4986.80 ms / 985 tokens 7.30.839.454 I slot print_timing: id 2 | task 7077 | graphs reused = 5898 7.30.839.455 I slot print_timing: id 2 | task 7077 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.839.518 I slot release: id 2 | task 7077 | stop processing: n_tokens = 993, truncated = 0 7.30.839.535 I slot print_timing: id 1 | task 7081 | prompt processing, n_tokens = 927, progress = 1.00, t = 3.23 s / 287.44 tokens per second 7.31.620.708 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 334220052006 7.31.620.816 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 424.890 MiB) 7.31.631.870 I slot launch_slot_: id 0 | task 7087 | processing task, is_child = 0 7.31.631.948 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.144 MiB) 7.31.640.744 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 993, t_last = 334220053331 7.31.640.861 I slot launch_slot_: id 2 | task 7088 | processing task, is_child = 0 7.34.170.405 I slot print_timing: id 1 | task 7081 | prompt eval time = 4008.82 ms / 931 tokens ( 4.31 ms per token, 232.24 tokens per second) 7.34.170.416 I slot print_timing: id 1 | task 7081 | eval time = 2549.68 ms / 2 tokens ( 2549.68 ms per token, 0.39 tokens per second) 7.34.170.417 I slot print_timing: id 1 | task 7081 | total time = 6558.51 ms / 933 tokens 7.34.170.417 I slot print_timing: id 1 | task 7081 | graphs reused = 5898 7.34.170.418 I slot print_timing: id 1 | task 7081 | graph reallocs = 0 / 0 (same size) / (changed size) 7.34.170.492 I slot release: id 1 | task 7081 | stop processing: n_tokens = 941, truncated = 0 7.34.175.607 I slot print_timing: id 3 | task 7084 | prompt processing, n_tokens = 880, progress = 1.00, t = 4.43 s / 198.85 tokens per second 7.35.445.892 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 334223384305 7.35.459.317 I slot launch_slot_: id 1 | task 7091 | processing task, is_child = 0 7.35.459.330 I slot print_timing: id 0 | task 7087 | prompt processing, n_tokens = 753, progress = 0.82, t = 3.80 s / 197.95 tokens per second 7.35.461.199 I slot print_timing: id 2 | task 7088 | prompt processing, n_tokens = 1148, progress = 0.85, t = 3.80 s / 301.81 tokens per second 7.37.734.860 I slot print_timing: id 3 | task 7084 | prompt eval time = 5702.00 ms / 884 tokens ( 6.45 ms per token, 155.03 tokens per second) 7.37.734.863 I slot print_timing: id 3 | task 7084 | eval time = 2288.98 ms / 2 tokens ( 2288.98 ms per token, 0.44 tokens per second) 7.37.734.863 I slot print_timing: id 3 | task 7084 | total time = 7990.98 ms / 886 tokens 7.37.734.864 I slot print_timing: id 3 | task 7084 | graphs reused = 5898 7.37.734.864 I slot print_timing: id 3 | task 7084 | graph reallocs = 0 / 0 (same size) / (changed size) 7.37.734.906 I slot release: id 3 | task 7084 | stop processing: n_tokens = 894, truncated = 0 7.37.734.921 I slot print_timing: id 0 | task 7087 | prompt processing, n_tokens = 914, progress = 1.00, t = 6.09 s / 150.01 tokens per second 7.37.741.470 I slot print_timing: id 2 | task 7088 | prompt processing, n_tokens = 1349, progress = 1.00, t = 6.09 s / 221.41 tokens per second 7.38.384.661 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 334226948719 7.38.384.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.323 MiB) 7.38.398.197 I slot launch_slot_: id 3 | task 7094 | processing task, is_child = 0 7.40.187.031 I slot print_timing: id 0 | task 7087 | prompt eval time = 6742.57 ms / 918 tokens ( 7.34 ms per token, 136.15 tokens per second) 7.40.187.037 I slot print_timing: id 0 | task 7087 | eval time = 1803.58 ms / 2 tokens ( 1803.58 ms per token, 0.55 tokens per second) 7.40.187.037 I slot print_timing: id 0 | task 7087 | total time = 8546.15 ms / 920 tokens 7.40.187.038 I slot print_timing: id 0 | task 7087 | graphs reused = 5898 7.40.187.038 I slot print_timing: id 0 | task 7087 | graph reallocs = 0 / 0 (same size) / (changed size) 7.40.187.107 I slot release: id 0 | task 7087 | stop processing: n_tokens = 928, truncated = 0 7.40.188.311 I slot print_timing: id 2 | task 7088 | prompt eval time = 6743.58 ms / 1353 tokens ( 4.98 ms per token, 200.64 tokens per second) 7.40.188.314 I slot print_timing: id 2 | task 7088 | eval time = 1803.66 ms / 2 tokens ( 1803.66 ms per token, 0.55 tokens per second) 7.40.188.315 I slot print_timing: id 2 | task 7088 | total time = 8547.24 ms / 1355 tokens 7.40.188.315 I slot print_timing: id 2 | task 7088 | graphs reused = 5898 7.40.188.315 I slot print_timing: id 2 | task 7088 | graph reallocs = 0 / 0 (same size) / (changed size) 7.40.188.401 I slot release: id 2 | task 7088 | stop processing: n_tokens = 1363, truncated = 0 7.40.188.429 I slot print_timing: id 1 | task 7091 | prompt processing, n_tokens = 1336, progress = 1.00, t = 4.72 s / 282.76 tokens per second 7.40.986.436 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 334229400920 7.40.986.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 248.171 MiB) 7.40.996.409 I slot launch_slot_: id 0 | task 7097 | processing task, is_child = 0 7.40.996.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.685 MiB) 7.41.010.758 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 7.41.010.816 I slot launch_slot_: id 2 | task 7098 | processing task, is_child = 0 7.42.028.418 I slot print_timing: id 1 | task 7091 | prompt eval time = 5525.43 ms / 1340 tokens ( 4.12 ms per token, 242.52 tokens per second) 7.42.028.428 I slot print_timing: id 1 | task 7091 | eval time = 1041.99 ms / 2 tokens ( 1041.99 ms per token, 0.96 tokens per second) 7.42.028.428 I slot print_timing: id 1 | task 7091 | total time = 6567.42 ms / 1342 tokens 7.42.028.429 I slot print_timing: id 1 | task 7091 | graphs reused = 5898 7.42.028.429 I slot print_timing: id 1 | task 7091 | graph reallocs = 0 / 0 (same size) / (changed size) 7.42.028.509 I slot release: id 1 | task 7091 | stop processing: n_tokens = 1350, truncated = 0 7.42.032.677 I slot print_timing: id 3 | task 7094 | prompt processing, n_tokens = 1251, progress = 1.00, t = 3.63 s / 344.94 tokens per second 7.42.817.480 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1350, t_last = 334231242322 7.42.817.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 245.780 MiB) 7.42.817.618 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.136 MiB) 7.42.837.463 I slot launch_slot_: id 1 | task 7101 | processing task, is_child = 0 7.43.638.464 I slot print_timing: id 2 | task 7098 | prompt eval time = 1805.17 ms / 121 tokens ( 14.92 ms per token, 67.03 tokens per second) 7.43.638.471 I slot print_timing: id 2 | task 7098 | eval time = 822.23 ms / 2 tokens ( 822.23 ms per token, 1.22 tokens per second) 7.43.638.471 I slot print_timing: id 2 | task 7098 | total time = 2627.40 ms / 123 tokens 7.43.638.472 I slot print_timing: id 2 | task 7098 | graphs reused = 5898 7.43.638.472 I slot print_timing: id 2 | task 7098 | graph reallocs = 0 / 0 (same size) / (changed size) 7.43.638.559 I slot release: id 2 | task 7098 | stop processing: n_tokens = 1306, truncated = 0 7.43.639.806 I slot print_timing: id 3 | task 7094 | prompt eval time = 4416.91 ms / 1255 tokens ( 3.52 ms per token, 284.14 tokens per second) 7.43.639.810 I slot print_timing: id 3 | task 7094 | eval time = 822.33 ms / 2 tokens ( 822.33 ms per token, 1.22 tokens per second) 7.43.639.810 I slot print_timing: id 3 | task 7094 | total time = 5239.24 ms / 1257 tokens 7.43.639.811 I slot print_timing: id 3 | task 7094 | graphs reused = 5898 7.43.639.811 I slot print_timing: id 3 | task 7094 | graph reallocs = 0 / 0 (same size) / (changed size) 7.43.639.860 I slot release: id 3 | task 7094 | stop processing: n_tokens = 1265, truncated = 0 7.44.371.641 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1306, t_last = 334232852372 7.44.371.778 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 228.234 MiB) 7.44.388.226 I slot launch_slot_: id 2 | task 7104 | processing task, is_child = 0 7.44.388.316 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 230.309 MiB) 7.44.403.288 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1265, t_last = 334232853673 7.44.403.422 I slot launch_slot_: id 3 | task 7105 | processing task, is_child = 0 7.45.983.506 I slot print_timing: id 0 | task 7097 | prompt eval time = 3360.80 ms / 782 tokens ( 4.30 ms per token, 232.68 tokens per second) 7.45.983.511 I slot print_timing: id 0 | task 7097 | eval time = 1611.87 ms / 2 tokens ( 1611.87 ms per token, 0.62 tokens per second) 7.45.983.512 I slot print_timing: id 0 | task 7097 | total time = 4972.67 ms / 784 tokens 7.45.983.512 I slot print_timing: id 0 | task 7097 | graphs reused = 5898 7.45.983.513 I slot print_timing: id 0 | task 7097 | graph reallocs = 0 / 0 (same size) / (changed size) 7.45.983.583 I slot release: id 0 | task 7097 | stop processing: n_tokens = 792, truncated = 0 7.45.983.606 I slot print_timing: id 1 | task 7101 | prompt processing, n_tokens = 797, progress = 1.00, t = 3.14 s / 253.63 tokens per second 7.47.451.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 792, t_last = 334235197396 7.47.451.187 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.776 MiB) 7.47.462.142 I slot launch_slot_: id 0 | task 7108 | processing task, is_child = 0 7.47.462.321 I slot print_timing: id 2 | task 7104 | prompt processing, n_tokens = 736, progress = 0.86, t = 3.04 s / 241.72 tokens per second 7.47.463.993 I slot print_timing: id 3 | task 7105 | prompt processing, n_tokens = 736, progress = 0.83, t = 3.04 s / 241.74 tokens per second 7.48.564.181 I slot print_timing: id 1 | task 7101 | prompt eval time = 4611.01 ms / 801 tokens ( 5.76 ms per token, 173.71 tokens per second) 7.48.564.194 I slot print_timing: id 1 | task 7101 | eval time = 1113.14 ms / 2 tokens ( 1113.14 ms per token, 0.90 tokens per second) 7.48.564.195 I slot print_timing: id 1 | task 7101 | total time = 5724.15 ms / 803 tokens 7.48.564.195 I slot print_timing: id 1 | task 7101 | graphs reused = 5898 7.48.564.196 I slot print_timing: id 1 | task 7101 | graph reallocs = 0 / 0 (same size) / (changed size) 7.48.564.265 I slot release: id 1 | task 7101 | stop processing: n_tokens = 811, truncated = 0 7.48.566.585 I slot print_timing: id 2 | task 7104 | prompt processing, n_tokens = 853, progress = 1.00, t = 4.16 s / 205.15 tokens per second 7.48.569.302 I slot print_timing: id 3 | task 7105 | prompt processing, n_tokens = 882, progress = 1.00, t = 4.16 s / 212.14 tokens per second 7.49.299.770 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 811, t_last = 334237778078 7.49.299.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 234.388 MiB) 7.49.309.762 I slot launch_slot_: id 1 | task 7111 | processing task, is_child = 0 7.50.265.250 I slot print_timing: id 2 | task 7104 | prompt eval time = 4893.46 ms / 857 tokens ( 5.71 ms per token, 175.13 tokens per second) 7.50.265.254 I slot print_timing: id 2 | task 7104 | eval time = 966.68 ms / 2 tokens ( 966.68 ms per token, 1.03 tokens per second) 7.50.265.254 I slot print_timing: id 2 | task 7104 | total time = 5860.14 ms / 859 tokens 7.50.265.255 I slot print_timing: id 2 | task 7104 | graphs reused = 5898 7.50.265.255 I slot print_timing: id 2 | task 7104 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.265.318 I slot release: id 2 | task 7104 | stop processing: n_tokens = 867, truncated = 0 7.50.266.428 I slot print_timing: id 3 | task 7105 | prompt eval time = 4894.41 ms / 886 tokens ( 5.52 ms per token, 181.02 tokens per second) 7.50.266.432 I slot print_timing: id 3 | task 7105 | eval time = 966.67 ms / 2 tokens ( 966.67 ms per token, 1.03 tokens per second) 7.50.266.432 I slot print_timing: id 3 | task 7105 | total time = 5861.08 ms / 888 tokens 7.50.266.433 I slot print_timing: id 3 | task 7105 | graphs reused = 5898 7.50.266.433 I slot print_timing: id 3 | task 7105 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.266.468 I slot release: id 3 | task 7105 | stop processing: n_tokens = 896, truncated = 0 7.50.887.964 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 867, t_last = 334239479131 7.50.888.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.032 MiB) 7.50.897.450 I slot launch_slot_: id 2 | task 7114 | processing task, is_child = 0 7.50.897.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.374 MiB) 7.50.905.185 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 896, t_last = 334239480281 7.50.905.309 I slot launch_slot_: id 3 | task 7115 | processing task, is_child = 0 7.52.295.457 I slot print_timing: id 0 | task 7108 | prompt eval time = 3425.80 ms / 778 tokens ( 4.40 ms per token, 227.10 tokens per second) 7.52.295.460 I slot print_timing: id 0 | task 7108 | eval time = 1407.50 ms / 2 tokens ( 1407.50 ms per token, 0.71 tokens per second) 7.52.295.461 I slot print_timing: id 0 | task 7108 | total time = 4833.30 ms / 780 tokens 7.52.295.461 I slot print_timing: id 0 | task 7108 | graphs reused = 5898 7.52.295.461 I slot print_timing: id 0 | task 7108 | graph reallocs = 0 / 0 (same size) / (changed size) 7.52.295.511 I slot release: id 0 | task 7108 | stop processing: n_tokens = 788, truncated = 0 7.53.805.022 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.849 (> 0.100 thold), f_keep = 0.862 7.53.805.130 I slot launch_slot_: id 0 | task 7118 | processing task, is_child = 0 7.54.597.119 I slot print_timing: id 1 | task 7111 | prompt eval time = 4493.56 ms / 843 tokens ( 5.33 ms per token, 187.60 tokens per second) 7.54.597.123 I slot print_timing: id 1 | task 7111 | eval time = 792.10 ms / 2 tokens ( 792.10 ms per token, 1.26 tokens per second) 7.54.597.124 I slot print_timing: id 1 | task 7111 | total time = 5285.66 ms / 845 tokens 7.54.597.124 I slot print_timing: id 1 | task 7111 | graphs reused = 5898 7.54.597.125 I slot print_timing: id 1 | task 7111 | graph reallocs = 0 / 0 (same size) / (changed size) 7.54.597.193 I slot release: id 1 | task 7111 | stop processing: n_tokens = 853, truncated = 0 7.54.601.324 I slot print_timing: id 2 | task 7114 | prompt processing, n_tokens = 758, progress = 0.99, t = 3.69 s / 205.47 tokens per second 7.54.603.682 I slot print_timing: id 3 | task 7115 | prompt processing, n_tokens = 764, progress = 0.99, t = 3.69 s / 207.11 tokens per second 7.54.677.867 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 853, t_last = 334243811006 7.54.677.955 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.859 MiB) 7.54.684.440 I slot launch_slot_: id 1 | task 7121 | processing task, is_child = 0 7.55.541.202 I slot print_timing: id 0 | task 7118 | prompt eval time = 870.50 ms / 121 tokens ( 7.19 ms per token, 139.00 tokens per second) 7.55.541.205 I slot print_timing: id 0 | task 7118 | eval time = 865.55 ms / 2 tokens ( 865.55 ms per token, 1.16 tokens per second) 7.55.541.205 I slot print_timing: id 0 | task 7118 | total time = 1736.05 ms / 123 tokens 7.55.541.206 I slot print_timing: id 0 | task 7118 | graphs reused = 5898 7.55.541.206 I slot print_timing: id 0 | task 7118 | graph reallocs = 0 / 0 (same size) / (changed size) 7.55.541.250 I slot release: id 0 | task 7118 | stop processing: n_tokens = 801, truncated = 0 7.55.542.393 I slot print_timing: id 2 | task 7114 | prompt eval time = 3769.77 ms / 762 tokens ( 4.95 ms per token, 202.13 tokens per second) 7.55.542.398 I slot print_timing: id 2 | task 7114 | eval time = 865.62 ms / 2 tokens ( 865.62 ms per token, 1.16 tokens per second) 7.55.542.398 I slot print_timing: id 2 | task 7114 | total time = 4635.39 ms / 764 tokens 7.55.542.399 I slot print_timing: id 2 | task 7114 | graphs reused = 5898 7.55.542.399 I slot print_timing: id 2 | task 7114 | graph reallocs = 0 / 0 (same size) / (changed size) 7.55.542.424 I slot release: id 2 | task 7114 | stop processing: n_tokens = 772, truncated = 0 7.55.543.563 I slot print_timing: id 3 | task 7115 | prompt eval time = 3770.66 ms / 768 tokens ( 4.91 ms per token, 203.68 tokens per second) 7.55.543.567 I slot print_timing: id 3 | task 7115 | eval time = 865.71 ms / 2 tokens ( 865.71 ms per token, 1.16 tokens per second) 7.55.543.567 I slot print_timing: id 3 | task 7115 | total time = 4636.37 ms / 770 tokens 7.55.543.567 I slot print_timing: id 3 | task 7115 | graphs reused = 5898 7.55.543.568 I slot print_timing: id 3 | task 7115 | graph reallocs = 0 / 0 (same size) / (changed size) 7.55.543.591 I slot release: id 3 | task 7115 | stop processing: n_tokens = 778, truncated = 0 7.56.248.616 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 801, t_last = 334244755063 7.56.248.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.360 MiB) 7.56.551.830 I slot launch_slot_: id 0 | task 7125 | processing task, is_child = 0 7.56.551.910 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 239.064 MiB) 7.56.560.144 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.037 MiB) 7.56.566.777 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 334244756237 7.56.566.898 I slot launch_slot_: id 2 | task 7126 | processing task, is_child = 0 7.56.566.963 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 334244757404 7.56.567.058 I slot launch_slot_: id 3 | task 7127 | processing task, is_child = 0 8.01.174.845 I slot print_timing: id 1 | task 7121 | prompt eval time = 4183.60 ms / 952 tokens ( 4.39 ms per token, 227.56 tokens per second) 8.01.174.851 I slot print_timing: id 1 | task 7121 | eval time = 2306.79 ms / 2 tokens ( 2306.79 ms per token, 0.43 tokens per second) 8.01.174.851 I slot print_timing: id 1 | task 7121 | total time = 6490.39 ms / 954 tokens 8.01.174.852 I slot print_timing: id 1 | task 7121 | graphs reused = 5898 8.01.174.852 I slot print_timing: id 1 | task 7121 | graph reallocs = 0 / 0 (same size) / (changed size) 8.01.174.899 I slot release: id 1 | task 7121 | stop processing: n_tokens = 962, truncated = 0 8.01.174.916 I slot print_timing: id 0 | task 7125 | prompt processing, n_tokens = 817, progress = 0.87, t = 4.61 s / 177.35 tokens per second 8.01.179.022 I slot print_timing: id 2 | task 7126 | prompt processing, n_tokens = 817, progress = 0.88, t = 4.60 s / 177.43 tokens per second 8.01.181.226 I slot print_timing: id 3 | task 7127 | prompt processing, n_tokens = 817, progress = 0.88, t = 4.60 s / 177.43 tokens per second 8.01.861.895 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.887 8.01.861.990 I slot launch_slot_: id 1 | task 7131 | processing task, is_child = 0 8.01.862.000 I slot print_timing: id 0 | task 7125 | prompt processing, n_tokens = 940, progress = 1.00, t = 5.29 s / 177.53 tokens per second 8.01.893.454 I slot print_timing: id 2 | task 7126 | prompt processing, n_tokens = 922, progress = 1.00, t = 5.29 s / 174.20 tokens per second 8.01.898.551 I slot print_timing: id 3 | task 7127 | prompt processing, n_tokens = 924, progress = 1.00, t = 5.29 s / 174.58 tokens per second 8.02.313.936 I slot print_timing: id 0 | task 7125 | prompt eval time = 5641.10 ms / 944 tokens ( 5.98 ms per token, 167.34 tokens per second) 8.02.313.939 I slot print_timing: id 0 | task 7125 | eval time = 105.77 ms / 2 tokens ( 105.77 ms per token, 9.45 tokens per second) 8.02.313.940 I slot print_timing: id 0 | task 7125 | total time = 5746.87 ms / 946 tokens 8.02.313.940 I slot print_timing: id 0 | task 7125 | graphs reused = 5898 8.02.313.941 I slot print_timing: id 0 | task 7125 | graph reallocs = 0 / 0 (same size) / (changed size) 8.02.313.994 I slot release: id 0 | task 7125 | stop processing: n_tokens = 954, truncated = 0 8.02.316.375 I slot print_timing: id 2 | task 7126 | prompt eval time = 5640.31 ms / 926 tokens ( 6.09 ms per token, 164.18 tokens per second) 8.02.316.378 I slot print_timing: id 2 | task 7126 | eval time = 107.05 ms / 2 tokens ( 107.05 ms per token, 9.34 tokens per second) 8.02.316.378 I slot print_timing: id 2 | task 7126 | total time = 5747.36 ms / 928 tokens 8.02.316.379 I slot print_timing: id 2 | task 7126 | graphs reused = 5898 8.02.316.379 I slot print_timing: id 2 | task 7126 | graph reallocs = 0 / 0 (same size) / (changed size) 8.02.316.407 I slot release: id 2 | task 7126 | stop processing: n_tokens = 936, truncated = 0 8.02.317.507 I slot print_timing: id 3 | task 7127 | prompt eval time = 5641.30 ms / 928 tokens ( 6.08 ms per token, 164.50 tokens per second) 8.02.317.508 I slot print_timing: id 3 | task 7127 | eval time = 107.02 ms / 2 tokens ( 107.02 ms per token, 9.34 tokens per second) 8.02.317.508 I slot print_timing: id 3 | task 7127 | total time = 5748.32 ms / 930 tokens 8.02.317.509 I slot print_timing: id 3 | task 7127 | graphs reused = 5898 8.02.317.509 I slot print_timing: id 3 | task 7127 | graph reallocs = 0 / 0 (same size) / (changed size) 8.02.317.533 I slot release: id 3 | task 7127 | stop processing: n_tokens = 938, truncated = 0 8.02.338.574 I slot print_timing: id 1 | task 7131 | prompt eval time = 424.10 ms / 107 tokens ( 3.96 ms per token, 252.30 tokens per second) 8.02.338.577 I slot print_timing: id 1 | task 7131 | eval time = 23.28 ms / 2 tokens ( 23.28 ms per token, 42.96 tokens per second) 8.02.338.577 I slot print_timing: id 1 | task 7131 | total time = 447.38 ms / 109 tokens 8.02.338.577 I slot print_timing: id 1 | task 7131 | graphs reused = 5898 8.02.338.578 I slot print_timing: id 1 | task 7131 | graph reallocs = 0 / 0 (same size) / (changed size) 8.02.338.608 I slot release: id 1 | task 7131 | stop processing: n_tokens = 961, truncated = 0 8.02.338.614 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 334251527807 8.02.352.463 I slot launch_slot_: id 0 | task 7135 | processing task, is_child = 0 8.02.352.540 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 242.264 MiB) 8.02.352.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 233.544 MiB) 8.02.365.995 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 208.403 MiB) 8.02.373.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.291 MiB) 8.02.385.663 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 334251530220 8.02.385.818 I slot launch_slot_: id 2 | task 7136 | processing task, is_child = 0 8.02.385.956 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 334251531346 8.02.386.055 I slot launch_slot_: id 3 | task 7137 | processing task, is_child = 0 8.02.386.123 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 334251552421 8.02.386.222 I slot launch_slot_: id 1 | task 7138 | processing task, is_child = 0 8.07.780.294 I slot print_timing: id 0 | task 7135 | prompt processing, n_tokens = 668, progress = 0.85, t = 5.39 s / 123.84 tokens per second 8.07.813.582 I slot print_timing: id 1 | task 7138 | prompt processing, n_tokens = 818, progress = 0.87, t = 5.39 s / 151.65 tokens per second 8.07.817.313 I slot print_timing: id 2 | task 7136 | prompt processing, n_tokens = 668, progress = 0.85, t = 5.39 s / 123.85 tokens per second 8.07.818.980 I slot print_timing: id 3 | task 7137 | prompt processing, n_tokens = 818, progress = 0.85, t = 5.39 s / 151.66 tokens per second 8.08.725.386 I slot print_timing: id 0 | task 7135 | prompt processing, n_tokens = 785, progress = 0.99, t = 6.34 s / 123.83 tokens per second 8.08.813.212 I slot print_timing: id 1 | task 7138 | prompt processing, n_tokens = 943, progress = 1.00, t = 6.34 s / 148.76 tokens per second 8.08.816.975 I slot print_timing: id 2 | task 7136 | prompt processing, n_tokens = 785, progress = 0.99, t = 6.34 s / 123.84 tokens per second 8.08.818.737 I slot print_timing: id 3 | task 7137 | prompt processing, n_tokens = 963, progress = 1.00, t = 6.34 s / 151.93 tokens per second 8.08.919.470 I slot print_timing: id 0 | task 7135 | prompt eval time = 6493.53 ms / 789 tokens ( 8.23 ms per token, 121.51 tokens per second) 8.08.919.473 I slot print_timing: id 0 | task 7135 | eval time = 39.71 ms / 2 tokens ( 39.71 ms per token, 25.18 tokens per second) 8.08.919.474 I slot print_timing: id 0 | task 7135 | total time = 6533.24 ms / 791 tokens 8.08.919.474 I slot print_timing: id 0 | task 7135 | graphs reused = 5899 8.08.919.475 I slot print_timing: id 0 | task 7135 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.919.519 I slot release: id 0 | task 7135 | stop processing: n_tokens = 799, truncated = 0 8.08.920.640 I slot print_timing: id 1 | task 7138 | prompt eval time = 6494.43 ms / 947 tokens ( 6.86 ms per token, 145.82 tokens per second) 8.08.920.642 I slot print_timing: id 1 | task 7138 | eval time = 39.77 ms / 2 tokens ( 39.77 ms per token, 25.14 tokens per second) 8.08.920.643 I slot print_timing: id 1 | task 7138 | total time = 6534.20 ms / 949 tokens 8.08.920.643 I slot print_timing: id 1 | task 7138 | graphs reused = 5899 8.08.920.643 I slot print_timing: id 1 | task 7138 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.920.674 I slot release: id 1 | task 7138 | stop processing: n_tokens = 957, truncated = 0 8.08.921.765 I slot print_timing: id 2 | task 7136 | prompt eval time = 6495.36 ms / 789 tokens ( 8.23 ms per token, 121.47 tokens per second) 8.08.921.771 I slot print_timing: id 2 | task 7136 | eval time = 39.78 ms / 2 tokens ( 39.78 ms per token, 25.14 tokens per second) 8.08.921.771 I slot print_timing: id 2 | task 7136 | total time = 6535.14 ms / 791 tokens 8.08.921.771 I slot print_timing: id 2 | task 7136 | graphs reused = 5899 8.08.921.772 I slot print_timing: id 2 | task 7136 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.921.794 I slot release: id 2 | task 7136 | stop processing: n_tokens = 799, truncated = 0 8.08.922.894 I slot print_timing: id 3 | task 7137 | prompt eval time = 6496.47 ms / 967 tokens ( 6.72 ms per token, 148.85 tokens per second) 8.08.922.896 I slot print_timing: id 3 | task 7137 | eval time = 39.63 ms / 2 tokens ( 39.63 ms per token, 25.23 tokens per second) 8.08.922.896 I slot print_timing: id 3 | task 7137 | total time = 6536.11 ms / 969 tokens 8.08.922.896 I slot print_timing: id 3 | task 7137 | graphs reused = 5899 8.08.922.897 I slot print_timing: id 3 | task 7137 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.922.920 I slot release: id 3 | task 7137 | stop processing: n_tokens = 977, truncated = 0 8.08.928.317 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.892 8.08.928.361 I slot launch_slot_: id 1 | task 7144 | processing task, is_child = 0 8.08.928.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 209.775 MiB) 8.08.934.761 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 262.620 MiB) 8.08.940.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.735 MiB) 8.08.946.329 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 334258133332 8.08.946.460 I slot launch_slot_: id 0 | task 7145 | processing task, is_child = 0 8.08.946.590 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 334258135607 8.08.946.685 I slot launch_slot_: id 2 | task 7146 | processing task, is_child = 0 8.08.946.753 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 334258136733 8.08.946.849 I slot launch_slot_: id 3 | task 7147 | processing task, is_child = 0 8.13.496.347 I slot print_timing: id 0 | task 7145 | prompt processing, n_tokens = 771, progress = 0.87, t = 4.55 s / 169.51 tokens per second 8.13.500.048 I slot print_timing: id 2 | task 7146 | prompt processing, n_tokens = 771, progress = 0.84, t = 4.55 s / 169.59 tokens per second 8.13.502.211 I slot print_timing: id 3 | task 7147 | prompt processing, n_tokens = 771, progress = 0.86, t = 4.55 s / 169.59 tokens per second 8.14.349.355 I slot print_timing: id 1 | task 7144 | prompt eval time = 4549.25 ms / 108 tokens ( 42.12 ms per token, 23.74 tokens per second) 8.14.349.359 I slot print_timing: id 1 | task 7144 | eval time = 853.04 ms / 2 tokens ( 853.04 ms per token, 1.17 tokens per second) 8.14.349.359 I slot print_timing: id 1 | task 7144 | total time = 5402.29 ms / 110 tokens 8.14.349.360 I slot print_timing: id 1 | task 7144 | graphs reused = 5899 8.14.349.360 I slot print_timing: id 1 | task 7144 | graph reallocs = 0 / 0 (same size) / (changed size) 8.14.349.435 I slot release: id 1 | task 7144 | stop processing: n_tokens = 963, truncated = 0 8.14.349.454 I slot print_timing: id 0 | task 7145 | prompt processing, n_tokens = 886, progress = 1.00, t = 5.40 s / 164.03 tokens per second 8.14.352.363 I slot print_timing: id 2 | task 7146 | prompt processing, n_tokens = 917, progress = 1.00, t = 5.40 s / 169.83 tokens per second 8.14.354.408 I slot print_timing: id 3 | task 7147 | prompt processing, n_tokens = 890, progress = 1.00, t = 5.40 s / 164.84 tokens per second 8.14.429.219 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 963, t_last = 334263563248 8.14.429.309 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.419 MiB) 8.14.442.582 I slot launch_slot_: id 1 | task 7152 | processing task, is_child = 0 8.15.174.515 I slot print_timing: id 0 | task 7145 | prompt eval time = 5479.96 ms / 890 tokens ( 6.16 ms per token, 162.41 tokens per second) 8.15.174.527 I slot print_timing: id 0 | task 7145 | eval time = 747.70 ms / 2 tokens ( 747.70 ms per token, 1.34 tokens per second) 8.15.174.528 I slot print_timing: id 0 | task 7145 | total time = 6227.65 ms / 892 tokens 8.15.174.529 I slot print_timing: id 0 | task 7145 | graphs reused = 5899 8.15.174.529 I slot print_timing: id 0 | task 7145 | graph reallocs = 0 / 0 (same size) / (changed size) 8.15.174.598 I slot release: id 0 | task 7145 | stop processing: n_tokens = 900, truncated = 0 8.15.175.839 I slot print_timing: id 2 | task 7146 | prompt eval time = 5479.24 ms / 921 tokens ( 5.95 ms per token, 168.09 tokens per second) 8.15.175.841 I slot print_timing: id 2 | task 7146 | eval time = 747.84 ms / 2 tokens ( 747.84 ms per token, 1.34 tokens per second) 8.15.175.841 I slot print_timing: id 2 | task 7146 | total time = 6227.08 ms / 923 tokens 8.15.175.842 I slot print_timing: id 2 | task 7146 | graphs reused = 5899 8.15.175.842 I slot print_timing: id 2 | task 7146 | graph reallocs = 0 / 0 (same size) / (changed size) 8.15.175.880 I slot release: id 2 | task 7146 | stop processing: n_tokens = 931, truncated = 0 8.15.177.074 I slot print_timing: id 3 | task 7147 | prompt eval time = 5480.29 ms / 894 tokens ( 6.13 ms per token, 163.13 tokens per second) 8.15.177.080 I slot print_timing: id 3 | task 7147 | eval time = 747.86 ms / 2 tokens ( 747.86 ms per token, 1.34 tokens per second) 8.15.177.080 I slot print_timing: id 3 | task 7147 | total time = 6228.15 ms / 896 tokens 8.15.177.080 I slot print_timing: id 3 | task 7147 | graphs reused = 5899 8.15.177.081 I slot print_timing: id 3 | task 7147 | graph reallocs = 0 / 0 (same size) / (changed size) 8.15.177.114 I slot release: id 3 | task 7147 | stop processing: n_tokens = 904, truncated = 0 8.15.932.099 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.897 8.15.932.181 I slot launch_slot_: id 0 | task 7156 | processing task, is_child = 0 8.15.932.278 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.894 MiB) 8.16.185.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.430 MiB) 8.16.192.266 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 334264389693 8.16.192.407 I slot launch_slot_: id 2 | task 7157 | processing task, is_child = 0 8.16.192.475 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 334264390927 8.16.192.573 I slot launch_slot_: id 3 | task 7158 | processing task, is_child = 0 8.20.349.545 I slot print_timing: id 1 | task 7152 | prompt eval time = 4501.28 ms / 894 tokens ( 5.03 ms per token, 198.61 tokens per second) 8.20.349.550 I slot print_timing: id 1 | task 7152 | eval time = 1405.66 ms / 2 tokens ( 1405.66 ms per token, 0.71 tokens per second) 8.20.349.551 I slot print_timing: id 1 | task 7152 | total time = 5906.95 ms / 896 tokens 8.20.349.552 I slot print_timing: id 1 | task 7152 | graphs reused = 5899 8.20.349.552 I slot print_timing: id 1 | task 7152 | graph reallocs = 0 / 0 (same size) / (changed size) 8.20.349.625 I slot release: id 1 | task 7152 | stop processing: n_tokens = 904, truncated = 0 8.20.349.650 I slot print_timing: id 2 | task 7157 | prompt processing, n_tokens = 1051, progress = 0.86, t = 4.15 s / 253.18 tokens per second 8.20.353.285 I slot print_timing: id 3 | task 7158 | prompt processing, n_tokens = 1051, progress = 0.87, t = 4.15 s / 253.20 tokens per second 8.21.011.826 I slot print_timing: id 0 | task 7156 | prompt eval time = 4155.76 ms / 83 tokens ( 50.07 ms per token, 19.97 tokens per second) 8.21.011.832 I slot print_timing: id 0 | task 7156 | eval time = 663.47 ms / 2 tokens ( 663.47 ms per token, 1.51 tokens per second) 8.21.011.833 I slot print_timing: id 0 | task 7156 | total time = 4819.23 ms / 85 tokens 8.21.011.833 I slot print_timing: id 0 | task 7156 | graphs reused = 5899 8.21.011.834 I slot print_timing: id 0 | task 7156 | graph reallocs = 0 / 0 (same size) / (changed size) 8.21.011.902 I slot release: id 0 | task 7156 | stop processing: n_tokens = 891, truncated = 0 8.21.011.914 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 334269563438 8.21.012.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 302.916 MiB) 8.21.020.006 I slot launch_slot_: id 1 | task 7162 | processing task, is_child = 0 8.21.020.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.719 MiB) 8.21.027.694 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 334270225715 8.21.027.821 I slot launch_slot_: id 0 | task 7163 | processing task, is_child = 0 8.24.696.986 I slot print_timing: id 2 | task 7157 | prompt processing, n_tokens = 1222, progress = 1.00, t = 4.81 s / 253.81 tokens per second 8.24.699.994 I slot print_timing: id 3 | task 7158 | prompt processing, n_tokens = 1211, progress = 1.00, t = 4.81 s / 251.54 tokens per second 8.26.337.340 I slot print_timing: id 0 | task 7163 | prompt processing, n_tokens = 2146, progress = 0.81, t = 5.31 s / 404.38 tokens per second 8.27.342.137 I slot print_timing: id 2 | task 7157 | prompt eval time = 10139.83 ms / 1226 tokens ( 8.27 ms per token, 120.91 tokens per second) 8.27.342.146 I slot print_timing: id 2 | task 7157 | eval time = 1006.23 ms / 2 tokens ( 1006.23 ms per token, 0.99 tokens per second) 8.27.342.147 I slot print_timing: id 2 | task 7157 | total time = 11146.06 ms / 1228 tokens 8.27.342.148 I slot print_timing: id 2 | task 7157 | graphs reused = 5899 8.27.342.148 I slot print_timing: id 2 | task 7157 | graph reallocs = 0 / 0 (same size) / (changed size) 8.27.342.245 I slot release: id 2 | task 7157 | stop processing: n_tokens = 1236, truncated = 0 8.27.343.445 I slot print_timing: id 3 | task 7158 | prompt eval time = 10141.05 ms / 1215 tokens ( 8.35 ms per token, 119.81 tokens per second) 8.27.343.449 I slot print_timing: id 3 | task 7158 | eval time = 1006.13 ms / 2 tokens ( 1006.13 ms per token, 0.99 tokens per second) 8.27.343.449 I slot print_timing: id 3 | task 7158 | total time = 11147.17 ms / 1217 tokens 8.27.343.450 I slot print_timing: id 3 | task 7158 | graphs reused = 5899 8.27.343.450 I slot print_timing: id 3 | task 7158 | graph reallocs = 0 / 0 (same size) / (changed size) 8.27.343.503 I slot release: id 3 | task 7158 | stop processing: n_tokens = 1225, truncated = 0 8.27.343.521 I slot print_timing: id 0 | task 7163 | prompt processing, n_tokens = 2353, progress = 0.88, t = 6.31 s / 372.71 tokens per second 8.27.346.830 I slot print_timing: id 1 | task 7162 | prompt processing, n_tokens = 1051, progress = 0.82, t = 3.58 s / 293.22 tokens per second 8.28.242.733 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1236, t_last = 334276556058 8.28.242.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 233.016 MiB) 8.28.444.318 I slot launch_slot_: id 2 | task 7168 | processing task, is_child = 0 8.28.444.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 251.828 MiB) 8.28.451.286 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1225, t_last = 334276557316 8.28.451.422 I slot launch_slot_: id 3 | task 7169 | processing task, is_child = 0 8.28.451.430 I slot print_timing: id 0 | task 7163 | prompt processing, n_tokens = 2658, progress = 1.00, t = 7.21 s / 368.40 tokens per second 8.28.453.342 I slot print_timing: id 1 | task 7162 | prompt processing, n_tokens = 1276, progress = 1.00, t = 4.49 s / 284.43 tokens per second 8.32.187.966 I slot print_timing: id 2 | task 7168 | prompt processing, n_tokens = 2040, progress = 0.80, t = 3.73 s / 546.88 tokens per second 8.36.011.941 I slot print_timing: id 0 | task 7163 | prompt eval time = 11158.70 ms / 2662 tokens ( 4.19 ms per token, 238.56 tokens per second) 8.36.011.947 I slot print_timing: id 0 | task 7163 | eval time = 3825.41 ms / 2 tokens ( 3825.41 ms per token, 0.26 tokens per second) 8.36.011.947 I slot print_timing: id 0 | task 7163 | total time = 14984.10 ms / 2664 tokens 8.36.011.948 I slot print_timing: id 0 | task 7163 | graphs reused = 5899 8.36.011.948 I slot print_timing: id 0 | task 7163 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.012.125 I slot release: id 0 | task 7163 | stop processing: n_tokens = 2672, truncated = 0 8.36.013.326 I slot print_timing: id 1 | task 7162 | prompt eval time = 8431.30 ms / 1280 tokens ( 6.59 ms per token, 151.82 tokens per second) 8.36.013.329 I slot print_timing: id 1 | task 7162 | eval time = 3825.39 ms / 2 tokens ( 3825.39 ms per token, 0.26 tokens per second) 8.36.013.329 I slot print_timing: id 1 | task 7162 | total time = 12256.69 ms / 1282 tokens 8.36.013.330 I slot print_timing: id 1 | task 7162 | graphs reused = 5899 8.36.013.330 I slot print_timing: id 1 | task 7162 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.013.392 I slot release: id 1 | task 7162 | stop processing: n_tokens = 1290, truncated = 0 8.36.013.420 I slot print_timing: id 2 | task 7168 | prompt processing, n_tokens = 2052, progress = 0.80, t = 7.56 s / 271.58 tokens per second 8.36.017.045 I slot print_timing: id 3 | task 7169 | prompt processing, n_tokens = 2034, progress = 0.72, t = 3.82 s / 532.06 tokens per second 8.37.066.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2672, t_last = 334285225940 8.37.066.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 303.408 MiB) 8.37.210.827 I slot launch_slot_: id 0 | task 7173 | processing task, is_child = 0 8.37.210.919 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 290.012 MiB) 8.37.223.026 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1290, t_last = 334285227207 8.37.227.200 I slot launch_slot_: id 1 | task 7174 | processing task, is_child = 0 8.37.231.148 I slot print_timing: id 2 | task 7168 | prompt processing, n_tokens = 2353, progress = 0.92, t = 8.61 s / 273.25 tokens per second 8.37.232.862 I slot print_timing: id 3 | task 7169 | prompt processing, n_tokens = 2301, progress = 0.82, t = 4.88 s / 471.66 tokens per second 8.40.220.117 I slot print_timing: id 2 | task 7168 | prompt processing, n_tokens = 2564, progress = 1.00, t = 11.44 s / 224.16 tokens per second 8.40.222.254 I slot print_timing: id 3 | task 7169 | prompt processing, n_tokens = 2353, progress = 0.84, t = 7.71 s / 305.36 tokens per second 8.42.288.844 I slot print_timing: id 0 | task 7173 | prompt processing, n_tokens = 1467, progress = 0.81, t = 5.06 s / 289.89 tokens per second 8.42.292.686 I slot print_timing: id 1 | task 7174 | prompt processing, n_tokens = 373, progress = 1.00, t = 5.06 s / 73.72 tokens per second 8.42.295.756 I slot print_timing: id 3 | task 7169 | prompt processing, n_tokens = 2813, progress = 1.00, t = 10.10 s / 278.52 tokens per second 8.43.057.110 I slot print_timing: id 2 | task 7168 | prompt eval time = 13833.63 ms / 2568 tokens ( 5.39 ms per token, 185.63 tokens per second) 8.43.057.113 I slot print_timing: id 2 | task 7168 | eval time = 768.30 ms / 2 tokens ( 768.30 ms per token, 1.30 tokens per second) 8.43.057.113 I slot print_timing: id 2 | task 7168 | total time = 14601.93 ms / 2570 tokens 8.43.057.114 I slot print_timing: id 2 | task 7168 | graphs reused = 5899 8.43.057.114 I slot print_timing: id 2 | task 7168 | graph reallocs = 0 / 0 (same size) / (changed size) 8.43.057.288 I slot release: id 2 | task 7168 | stop processing: n_tokens = 2578, truncated = 0 8.43.058.799 I slot print_timing: id 0 | task 7173 | prompt processing, n_tokens = 1806, progress = 1.00, t = 5.83 s / 309.91 tokens per second 8.43.137.441 I slot print_timing: id 1 | task 7174 | prompt eval time = 5827.94 ms / 377 tokens ( 15.46 ms per token, 64.69 tokens per second) 8.43.137.443 I slot print_timing: id 1 | task 7174 | eval time = 81.50 ms / 2 tokens ( 81.50 ms per token, 12.27 tokens per second) 8.43.137.444 I slot print_timing: id 1 | task 7174 | total time = 5909.45 ms / 379 tokens 8.43.137.444 I slot print_timing: id 1 | task 7174 | graphs reused = 5899 8.43.137.444 I slot print_timing: id 1 | task 7174 | graph reallocs = 0 / 0 (same size) / (changed size) 8.43.137.548 I slot release: id 1 | task 7174 | stop processing: n_tokens = 2739, truncated = 0 8.43.138.630 I slot print_timing: id 3 | task 7169 | prompt eval time = 10870.80 ms / 2817 tokens ( 3.86 ms per token, 259.13 tokens per second) 8.43.138.633 I slot print_timing: id 3 | task 7169 | eval time = 79.84 ms / 2 tokens ( 79.84 ms per token, 12.52 tokens per second) 8.43.138.633 I slot print_timing: id 3 | task 7169 | total time = 10950.64 ms / 2819 tokens 8.43.138.633 I slot print_timing: id 3 | task 7169 | graphs reused = 5899 8.43.138.634 I slot print_timing: id 3 | task 7169 | graph reallocs = 0 / 0 (same size) / (changed size) 8.43.138.701 I slot release: id 3 | task 7169 | stop processing: n_tokens = 2827, truncated = 0 8.43.138.709 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2578, t_last = 334292271103 8.43.146.861 I slot launch_slot_: id 2 | task 7179 | processing task, is_child = 0 8.43.147.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 248.206 MiB) 8.43.165.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.842 MiB) 8.43.165.117 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 235.232 MiB) 8.43.182.254 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2739, t_last = 334292351362 8.43.182.467 I slot launch_slot_: id 1 | task 7180 | processing task, is_child = 0 8.43.182.601 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2827, t_last = 334292352517 8.43.182.767 I slot launch_slot_: id 3 | task 7181 | processing task, is_child = 0 8.46.901.639 I slot print_timing: id 0 | task 7173 | prompt eval time = 5909.16 ms / 1810 tokens ( 3.26 ms per token, 306.30 tokens per second) 8.46.901.645 I slot print_timing: id 0 | task 7173 | eval time = 3765.26 ms / 2 tokens ( 3765.26 ms per token, 0.27 tokens per second) 8.46.901.646 I slot print_timing: id 0 | task 7173 | total time = 9674.42 ms / 1812 tokens 8.46.901.647 I slot print_timing: id 0 | task 7173 | graphs reused = 5899 8.46.901.647 I slot print_timing: id 0 | task 7173 | graph reallocs = 0 / 0 (same size) / (changed size) 8.46.901.791 I slot release: id 0 | task 7173 | stop processing: n_tokens = 1820, truncated = 0 8.46.901.833 I slot print_timing: id 1 | task 7180 | prompt processing, n_tokens = 1368, progress = 0.73, t = 3.72 s / 367.97 tokens per second 8.46.904.914 I slot print_timing: id 2 | task 7179 | prompt processing, n_tokens = 679, progress = 0.37, t = 3.72 s / 182.66 tokens per second 8.50.473.315 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.756 (> 0.100 thold), f_keep = 0.831 8.50.473.417 I slot launch_slot_: id 0 | task 7184 | processing task, is_child = 0 8.50.669.427 I slot print_timing: id 1 | task 7180 | prompt processing, n_tokens = 1467, progress = 0.78, t = 7.29 s / 201.22 tokens per second 8.50.671.905 I slot print_timing: id 2 | task 7179 | prompt processing, n_tokens = 1354, progress = 0.73, t = 7.29 s / 185.73 tokens per second 8.50.673.861 I slot print_timing: id 3 | task 7181 | prompt processing, n_tokens = 1274, progress = 0.61, t = 3.57 s / 357.03 tokens per second 8.53.089.396 I slot print_timing: id 1 | task 7180 | prompt processing, n_tokens = 1880, progress = 1.00, t = 9.71 s / 193.56 tokens per second 8.53.092.522 I slot print_timing: id 2 | task 7179 | prompt processing, n_tokens = 1467, progress = 0.79, t = 9.71 s / 151.04 tokens per second 8.53.094.467 I slot print_timing: id 3 | task 7181 | prompt processing, n_tokens = 1467, progress = 0.71, t = 5.99 s / 244.88 tokens per second 8.54.136.577 I slot print_timing: id 2 | task 7179 | prompt processing, n_tokens = 1866, progress = 1.00, t = 10.95 s / 170.40 tokens per second 8.54.139.139 I slot print_timing: id 3 | task 7181 | prompt processing, n_tokens = 1565, progress = 0.75, t = 7.23 s / 216.49 tokens per second 8.55.165.059 I slot print_timing: id 0 | task 7184 | prompt eval time = 3661.84 ms / 488 tokens ( 7.50 ms per token, 133.27 tokens per second) 8.55.165.062 I slot print_timing: id 0 | task 7184 | eval time = 1029.78 ms / 2 tokens ( 1029.78 ms per token, 0.97 tokens per second) 8.55.165.062 I slot print_timing: id 0 | task 7184 | total time = 4691.62 ms / 490 tokens 8.55.165.063 I slot print_timing: id 0 | task 7184 | graphs reused = 5899 8.55.165.064 I slot print_timing: id 0 | task 7184 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.165.219 I slot release: id 0 | task 7184 | stop processing: n_tokens = 2001, truncated = 0 8.55.166.409 I slot print_timing: id 1 | task 7180 | prompt eval time = 10953.78 ms / 1884 tokens ( 5.81 ms per token, 172.00 tokens per second) 8.55.166.413 I slot print_timing: id 1 | task 7180 | eval time = 1029.85 ms / 2 tokens ( 1029.85 ms per token, 0.97 tokens per second) 8.55.166.413 I slot print_timing: id 1 | task 7180 | total time = 11983.63 ms / 1886 tokens 8.55.166.413 I slot print_timing: id 1 | task 7180 | graphs reused = 5899 8.55.166.414 I slot print_timing: id 1 | task 7180 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.166.493 I slot release: id 1 | task 7180 | stop processing: n_tokens = 1894, truncated = 0 8.55.167.775 I slot print_timing: id 3 | task 7181 | prompt processing, n_tokens = 2077, progress = 1.00, t = 8.26 s / 251.48 tokens per second 8.55.236.656 I slot print_timing: id 2 | task 7179 | prompt eval time = 11984.61 ms / 1870 tokens ( 6.41 ms per token, 156.03 tokens per second) 8.55.236.661 I slot print_timing: id 2 | task 7179 | eval time = 68.90 ms / 2 tokens ( 68.90 ms per token, 14.51 tokens per second) 8.55.236.662 I slot print_timing: id 2 | task 7179 | total time = 12053.50 ms / 1872 tokens 8.55.236.662 I slot print_timing: id 2 | task 7179 | graphs reused = 5899 8.55.236.663 I slot print_timing: id 2 | task 7179 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.236.724 I slot release: id 2 | task 7179 | stop processing: n_tokens = 1880, truncated = 0 8.55.237.885 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2001, t_last = 334304379034 8.55.238.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.014 MiB) 8.55.253.975 I slot launch_slot_: id 0 | task 7189 | processing task, is_child = 0 8.55.254.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.015 MiB) 8.55.268.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.508 MiB) 8.55.282.225 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.798 8.55.282.293 I slot launch_slot_: id 1 | task 7190 | processing task, is_child = 0 8.55.282.410 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1880, t_last = 334304450537 8.55.282.541 I slot launch_slot_: id 2 | task 7191 | processing task, is_child = 0 8.56.746.676 I slot print_timing: id 3 | task 7181 | prompt eval time = 8332.95 ms / 2081 tokens ( 4.00 ms per token, 249.73 tokens per second) 8.56.746.682 I slot print_timing: id 3 | task 7181 | eval time = 1508.79 ms / 2 tokens ( 1508.79 ms per token, 0.66 tokens per second) 8.56.746.682 I slot print_timing: id 3 | task 7181 | total time = 9841.74 ms / 2083 tokens 8.56.746.683 I slot print_timing: id 3 | task 7181 | graphs reused = 5899 8.56.746.683 I slot print_timing: id 3 | task 7181 | graph reallocs = 0 / 0 (same size) / (changed size) 8.56.746.816 I slot release: id 3 | task 7181 | stop processing: n_tokens = 2091, truncated = 0 8.58.223.014 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2091, t_last = 334305960631 8.58.223.177 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.017 MiB) 8.58.240.851 I slot launch_slot_: id 3 | task 7194 | processing task, is_child = 0 8.59.214.185 I slot print_timing: id 1 | task 7190 | prompt eval time = 2940.17 ms / 301 tokens ( 9.77 ms per token, 102.38 tokens per second) 8.59.214.191 I slot print_timing: id 1 | task 7190 | eval time = 991.18 ms / 2 tokens ( 991.18 ms per token, 1.01 tokens per second) 8.59.214.191 I slot print_timing: id 1 | task 7190 | total time = 3931.35 ms / 303 tokens 8.59.214.192 I slot print_timing: id 1 | task 7190 | graphs reused = 5899 8.59.214.192 I slot print_timing: id 1 | task 7190 | graph reallocs = 0 / 0 (same size) / (changed size) 8.59.214.332 I slot release: id 1 | task 7190 | stop processing: n_tokens = 1814, truncated = 0 8.59.214.357 I slot print_timing: id 0 | task 7189 | prompt processing, n_tokens = 712, progress = 0.99, t = 3.93 s / 181.15 tokens per second 8.59.218.018 I slot print_timing: id 2 | task 7191 | prompt processing, n_tokens = 731, progress = 0.99, t = 3.93 s / 186.08 tokens per second 8.59.973.339 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1814, t_last = 334308428147 8.59.973.493 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 262.519 MiB) 8.59.993.045 I slot launch_slot_: id 1 | task 7197 | processing task, is_child = 0 9.00.751.277 I slot print_timing: id 0 | task 7189 | prompt eval time = 4689.53 ms / 716 tokens ( 6.55 ms per token, 152.68 tokens per second) 9.00.751.281 I slot print_timing: id 0 | task 7189 | eval time = 779.19 ms / 2 tokens ( 779.19 ms per token, 1.28 tokens per second) 9.00.751.281 I slot print_timing: id 0 | task 7189 | total time = 5468.72 ms / 718 tokens 9.00.751.282 I slot print_timing: id 0 | task 7189 | graphs reused = 5899 9.00.751.282 I slot print_timing: id 0 | task 7189 | graph reallocs = 0 / 0 (same size) / (changed size) 9.00.751.345 I slot release: id 0 | task 7189 | stop processing: n_tokens = 726, truncated = 0 9.00.752.474 I slot print_timing: id 2 | task 7191 | prompt eval time = 4688.73 ms / 735 tokens ( 6.38 ms per token, 156.76 tokens per second) 9.00.752.477 I slot print_timing: id 2 | task 7191 | eval time = 779.14 ms / 2 tokens ( 779.14 ms per token, 1.28 tokens per second) 9.00.752.478 I slot print_timing: id 2 | task 7191 | total time = 5467.87 ms / 737 tokens 9.00.752.478 I slot print_timing: id 2 | task 7191 | graphs reused = 5899 9.00.752.478 I slot print_timing: id 2 | task 7191 | graph reallocs = 0 / 0 (same size) / (changed size) 9.00.752.512 I slot release: id 2 | task 7191 | stop processing: n_tokens = 745, truncated = 0 9.01.527.746 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.879 9.01.527.922 I slot launch_slot_: id 0 | task 7200 | processing task, is_child = 0 9.01.528.029 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.886 MiB) 9.01.535.272 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 334309966325 9.01.535.387 I slot launch_slot_: id 2 | task 7201 | processing task, is_child = 0 9.02.569.680 I slot print_timing: id 3 | task 7194 | prompt eval time = 3283.52 ms / 748 tokens ( 4.39 ms per token, 227.80 tokens per second) 9.02.569.691 I slot print_timing: id 3 | task 7194 | eval time = 1041.94 ms / 2 tokens ( 1041.94 ms per token, 0.96 tokens per second) 9.02.569.691 I slot print_timing: id 3 | task 7194 | total time = 4325.46 ms / 750 tokens 9.02.569.692 I slot print_timing: id 3 | task 7194 | graphs reused = 5899 9.02.569.692 I slot print_timing: id 3 | task 7194 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.569.764 I slot release: id 3 | task 7194 | stop processing: n_tokens = 758, truncated = 0 9.03.260.686 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 758, t_last = 334311783577 9.03.260.800 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.558 MiB) 9.03.269.626 I slot launch_slot_: id 3 | task 7204 | processing task, is_child = 0 9.04.607.952 I slot print_timing: id 0 | task 7200 | prompt eval time = 1724.04 ms / 101 tokens ( 17.07 ms per token, 58.58 tokens per second) 9.04.607.958 I slot print_timing: id 0 | task 7200 | eval time = 1348.51 ms / 2 tokens ( 1348.51 ms per token, 0.74 tokens per second) 9.04.607.959 I slot print_timing: id 0 | task 7200 | total time = 3072.55 ms / 103 tokens 9.04.607.959 I slot print_timing: id 0 | task 7200 | graphs reused = 5899 9.04.607.960 I slot print_timing: id 0 | task 7200 | graph reallocs = 0 / 0 (same size) / (changed size) 9.04.608.000 I slot release: id 0 | task 7200 | stop processing: n_tokens = 740, truncated = 0 9.04.609.202 I slot print_timing: id 1 | task 7197 | prompt eval time = 3267.62 ms / 712 tokens ( 4.59 ms per token, 217.90 tokens per second) 9.04.609.206 I slot print_timing: id 1 | task 7197 | eval time = 1348.52 ms / 2 tokens ( 1348.52 ms per token, 0.74 tokens per second) 9.04.609.208 I slot print_timing: id 1 | task 7197 | total time = 4616.15 ms / 714 tokens 9.04.609.208 I slot print_timing: id 1 | task 7197 | graphs reused = 5899 9.04.609.208 I slot print_timing: id 1 | task 7197 | graph reallocs = 0 / 0 (same size) / (changed size) 9.04.609.245 I slot release: id 1 | task 7197 | stop processing: n_tokens = 722, truncated = 0 9.04.609.265 I slot print_timing: id 2 | task 7201 | prompt processing, n_tokens = 792, progress = 1.00, t = 3.07 s / 258.14 tokens per second 9.05.344.180 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 334313821813 9.05.344.299 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 230.484 MiB) 9.05.344.310 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 235.513 MiB) 9.05.353.628 I slot launch_slot_: id 0 | task 7207 | processing task, is_child = 0 9.05.359.454 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 722, t_last = 334313823058 9.05.359.562 I slot launch_slot_: id 1 | task 7208 | processing task, is_child = 0 9.06.743.470 I slot print_timing: id 2 | task 7201 | prompt eval time = 3805.42 ms / 796 tokens ( 4.78 ms per token, 209.18 tokens per second) 9.06.743.474 I slot print_timing: id 2 | task 7201 | eval time = 1399.29 ms / 2 tokens ( 1399.29 ms per token, 0.71 tokens per second) 9.06.743.474 I slot print_timing: id 2 | task 7201 | total time = 5204.71 ms / 798 tokens 9.06.743.483 I slot print_timing: id 2 | task 7201 | graphs reused = 5899 9.06.743.484 I slot print_timing: id 2 | task 7201 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.743.537 I slot release: id 2 | task 7201 | stop processing: n_tokens = 806, truncated = 0 9.06.748.142 I slot print_timing: id 3 | task 7204 | prompt processing, n_tokens = 1039, progress = 1.00, t = 3.47 s / 299.34 tokens per second 9.08.260.929 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 334315957350 9.08.261.016 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.465 MiB) 9.08.267.352 I slot launch_slot_: id 2 | task 7211 | processing task, is_child = 0 9.09.414.402 I slot print_timing: id 3 | task 7204 | prompt eval time = 4989.60 ms / 1043 tokens ( 4.78 ms per token, 209.03 tokens per second) 9.09.414.405 I slot print_timing: id 3 | task 7204 | eval time = 1153.46 ms / 2 tokens ( 1153.46 ms per token, 0.87 tokens per second) 9.09.414.406 I slot print_timing: id 3 | task 7204 | total time = 6143.07 ms / 1045 tokens 9.09.414.407 I slot print_timing: id 3 | task 7204 | graphs reused = 5899 9.09.414.407 I slot print_timing: id 3 | task 7204 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.414.486 I slot release: id 3 | task 7204 | stop processing: n_tokens = 1053, truncated = 0 9.09.414.510 I slot print_timing: id 0 | task 7207 | prompt processing, n_tokens = 789, progress = 1.00, t = 4.05 s / 194.64 tokens per second 9.09.418.585 I slot print_timing: id 1 | task 7208 | prompt processing, n_tokens = 799, progress = 1.00, t = 4.05 s / 197.11 tokens per second 9.10.216.727 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 334318628299 9.10.216.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.787 MiB) 9.10.228.508 I slot launch_slot_: id 3 | task 7214 | processing task, is_child = 0 9.11.078.491 I slot print_timing: id 0 | task 7207 | prompt eval time = 4855.83 ms / 793 tokens ( 6.12 ms per token, 163.31 tokens per second) 9.11.078.494 I slot print_timing: id 0 | task 7207 | eval time = 863.09 ms / 2 tokens ( 863.09 ms per token, 1.16 tokens per second) 9.11.078.495 I slot print_timing: id 0 | task 7207 | total time = 5718.91 ms / 795 tokens 9.11.078.495 I slot print_timing: id 0 | task 7207 | graphs reused = 5899 9.11.078.496 I slot print_timing: id 0 | task 7207 | graph reallocs = 0 / 0 (same size) / (changed size) 9.11.078.557 I slot release: id 0 | task 7207 | stop processing: n_tokens = 803, truncated = 0 9.11.079.716 I slot print_timing: id 1 | task 7208 | prompt eval time = 4856.98 ms / 803 tokens ( 6.05 ms per token, 165.33 tokens per second) 9.11.079.718 I slot print_timing: id 1 | task 7208 | eval time = 863.00 ms / 2 tokens ( 863.00 ms per token, 1.16 tokens per second) 9.11.079.719 I slot print_timing: id 1 | task 7208 | total time = 5719.98 ms / 805 tokens 9.11.079.719 I slot print_timing: id 1 | task 7208 | graphs reused = 5899 9.11.079.719 I slot print_timing: id 1 | task 7208 | graph reallocs = 0 / 0 (same size) / (changed size) 9.11.079.751 I slot release: id 1 | task 7208 | stop processing: n_tokens = 813, truncated = 0 9.11.861.598 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 334320292370 9.11.861.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.123 MiB) 9.11.870.007 I slot launch_slot_: id 0 | task 7217 | processing task, is_child = 0 9.11.870.082 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.917 MiB) 9.11.875.718 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 813, t_last = 334320293564 9.11.875.830 I slot launch_slot_: id 1 | task 7218 | processing task, is_child = 0 9.13.517.012 I slot print_timing: id 2 | task 7211 | prompt eval time = 3590.38 ms / 836 tokens ( 4.29 ms per token, 232.84 tokens per second) 9.13.517.015 I slot print_timing: id 2 | task 7211 | eval time = 1655.41 ms / 2 tokens ( 1655.41 ms per token, 0.60 tokens per second) 9.13.517.015 I slot print_timing: id 2 | task 7211 | total time = 5245.79 ms / 838 tokens 9.13.517.016 I slot print_timing: id 2 | task 7211 | graphs reused = 5899 9.13.517.016 I slot print_timing: id 2 | task 7211 | graph reallocs = 0 / 0 (same size) / (changed size) 9.13.517.081 I slot release: id 2 | task 7211 | stop processing: n_tokens = 846, truncated = 0 9.13.522.676 I slot print_timing: id 3 | task 7214 | prompt processing, n_tokens = 824, progress = 1.00, t = 3.29 s / 250.78 tokens per second 9.14.798.654 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.869 (> 0.100 thold), f_keep = 0.884 9.14.798.783 I slot launch_slot_: id 2 | task 7221 | processing task, is_child = 0 9.15.801.183 I slot print_timing: id 3 | task 7214 | prompt eval time = 4568.47 ms / 828 tokens ( 5.52 ms per token, 181.24 tokens per second) 9.15.801.188 I slot print_timing: id 3 | task 7214 | eval time = 1002.53 ms / 2 tokens ( 1002.53 ms per token, 1.00 tokens per second) 9.15.801.189 I slot print_timing: id 3 | task 7214 | total time = 5571.00 ms / 830 tokens 9.15.801.189 I slot print_timing: id 3 | task 7214 | graphs reused = 5899 9.15.801.190 I slot print_timing: id 3 | task 7214 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.801.232 I slot release: id 3 | task 7214 | stop processing: n_tokens = 838, truncated = 0 9.15.801.245 I slot print_timing: id 0 | task 7217 | prompt processing, n_tokens = 889, progress = 1.00, t = 3.92 s / 226.54 tokens per second 9.15.805.351 I slot print_timing: id 1 | task 7218 | prompt processing, n_tokens = 895, progress = 1.00, t = 3.92 s / 228.08 tokens per second 9.15.865.343 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 838, t_last = 334325015045 9.15.865.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 243.671 MiB) 9.15.872.277 I slot launch_slot_: id 3 | task 7224 | processing task, is_child = 0 9.16.251.460 I slot print_timing: id 0 | task 7217 | prompt eval time = 3987.16 ms / 893 tokens ( 4.46 ms per token, 223.97 tokens per second) 9.16.251.462 I slot print_timing: id 0 | task 7217 | eval time = 388.45 ms / 2 tokens ( 388.45 ms per token, 2.57 tokens per second) 9.16.251.463 I slot print_timing: id 0 | task 7217 | total time = 4375.61 ms / 895 tokens 9.16.251.463 I slot print_timing: id 0 | task 7217 | graphs reused = 5899 9.16.251.464 I slot print_timing: id 0 | task 7217 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.251.556 I slot release: id 0 | task 7217 | stop processing: n_tokens = 903, truncated = 0 9.16.252.685 I slot print_timing: id 1 | task 7218 | prompt eval time = 3988.10 ms / 899 tokens ( 4.44 ms per token, 225.42 tokens per second) 9.16.252.691 I slot print_timing: id 1 | task 7218 | eval time = 388.55 ms / 2 tokens ( 388.55 ms per token, 2.57 tokens per second) 9.16.252.692 I slot print_timing: id 1 | task 7218 | total time = 4376.65 ms / 901 tokens 9.16.252.692 I slot print_timing: id 1 | task 7218 | graphs reused = 5899 9.16.252.692 I slot print_timing: id 1 | task 7218 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.252.728 I slot release: id 1 | task 7218 | stop processing: n_tokens = 909, truncated = 0 9.16.253.884 I slot print_timing: id 2 | task 7221 | prompt eval time = 1060.77 ms / 113 tokens ( 9.39 ms per token, 106.53 tokens per second) 9.16.253.888 I slot print_timing: id 2 | task 7221 | eval time = 388.54 ms / 2 tokens ( 388.54 ms per token, 2.57 tokens per second) 9.16.253.888 I slot print_timing: id 2 | task 7221 | total time = 1449.32 ms / 115 tokens 9.16.253.888 I slot print_timing: id 2 | task 7221 | graphs reused = 5899 9.16.253.889 I slot print_timing: id 2 | task 7221 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.253.930 I slot release: id 2 | task 7221 | stop processing: n_tokens = 862, truncated = 0 9.16.997.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 334325465369 9.16.997.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 298.767 MiB) 9.17.242.697 I slot launch_slot_: id 0 | task 7228 | processing task, is_child = 0 9.17.242.778 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.189 MiB) 9.17.248.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.420 MiB) 9.17.257.802 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 909, t_last = 334325466541 9.17.257.930 I slot launch_slot_: id 1 | task 7229 | processing task, is_child = 0 9.17.257.997 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 334325467743 9.17.258.091 I slot launch_slot_: id 2 | task 7230 | processing task, is_child = 0 9.21.083.465 I slot print_timing: id 3 | task 7224 | prompt eval time = 3037.80 ms / 682 tokens ( 4.45 ms per token, 224.50 tokens per second) 9.21.083.471 I slot print_timing: id 3 | task 7224 | eval time = 2173.37 ms / 2 tokens ( 2173.37 ms per token, 0.46 tokens per second) 9.21.083.471 I slot print_timing: id 3 | task 7224 | total time = 5211.17 ms / 684 tokens 9.21.083.472 I slot print_timing: id 3 | task 7224 | graphs reused = 5899 9.21.083.472 I slot print_timing: id 3 | task 7224 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.083.506 I slot release: id 3 | task 7224 | stop processing: n_tokens = 692, truncated = 0 9.21.083.520 I slot print_timing: id 0 | task 7228 | prompt processing, n_tokens = 615, progress = 0.82, t = 3.82 s / 160.81 tokens per second 9.21.085.589 I slot print_timing: id 1 | task 7229 | prompt processing, n_tokens = 701, progress = 0.85, t = 3.82 s / 183.31 tokens per second 9.21.087.490 I slot print_timing: id 2 | task 7230 | prompt processing, n_tokens = 701, progress = 0.83, t = 3.82 s / 183.32 tokens per second 9.21.787.302 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 334330297319 9.21.787.379 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.870 MiB) 9.21.874.755 I slot launch_slot_: id 3 | task 7234 | processing task, is_child = 0 9.21.874.764 I slot print_timing: id 0 | task 7228 | prompt processing, n_tokens = 746, progress = 0.99, t = 4.53 s / 164.71 tokens per second 9.21.877.687 I slot print_timing: id 1 | task 7229 | prompt processing, n_tokens = 818, progress = 1.00, t = 4.53 s / 180.61 tokens per second 9.21.879.439 I slot print_timing: id 2 | task 7230 | prompt processing, n_tokens = 841, progress = 1.00, t = 4.53 s / 185.70 tokens per second 9.23.113.105 I slot print_timing: id 0 | task 7228 | prompt eval time = 5078.66 ms / 750 tokens ( 6.77 ms per token, 147.68 tokens per second) 9.23.113.107 I slot print_timing: id 0 | task 7228 | eval time = 776.34 ms / 2 tokens ( 776.34 ms per token, 1.29 tokens per second) 9.23.113.108 I slot print_timing: id 0 | task 7228 | total time = 5855.00 ms / 752 tokens 9.23.113.118 I slot print_timing: id 0 | task 7228 | graphs reused = 5899 9.23.113.119 I slot print_timing: id 0 | task 7228 | graph reallocs = 0 / 0 (same size) / (changed size) 9.23.113.187 I slot release: id 0 | task 7228 | stop processing: n_tokens = 760, truncated = 0 9.23.114.321 I slot print_timing: id 1 | task 7229 | prompt eval time = 5079.75 ms / 822 tokens ( 6.18 ms per token, 161.82 tokens per second) 9.23.114.325 I slot print_timing: id 1 | task 7229 | eval time = 776.28 ms / 2 tokens ( 776.28 ms per token, 1.29 tokens per second) 9.23.114.325 I slot print_timing: id 1 | task 7229 | total time = 5856.03 ms / 824 tokens 9.23.114.325 I slot print_timing: id 1 | task 7229 | graphs reused = 5899 9.23.114.326 I slot print_timing: id 1 | task 7229 | graph reallocs = 0 / 0 (same size) / (changed size) 9.23.114.378 I slot release: id 1 | task 7229 | stop processing: n_tokens = 832, truncated = 0 9.23.115.551 I slot print_timing: id 2 | task 7230 | prompt eval time = 5080.90 ms / 845 tokens ( 6.01 ms per token, 166.31 tokens per second) 9.23.115.553 I slot print_timing: id 2 | task 7230 | eval time = 776.20 ms / 2 tokens ( 776.20 ms per token, 1.29 tokens per second) 9.23.115.554 I slot print_timing: id 2 | task 7230 | total time = 5857.10 ms / 847 tokens 9.23.115.554 I slot print_timing: id 2 | task 7230 | graphs reused = 5899 9.23.115.554 I slot print_timing: id 2 | task 7230 | graph reallocs = 0 / 0 (same size) / (changed size) 9.23.115.590 I slot release: id 2 | task 7230 | stop processing: n_tokens = 855, truncated = 0 9.23.403.489 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 334332327000 9.23.403.565 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.920 MiB) 9.23.410.303 I slot launch_slot_: id 0 | task 7239 | processing task, is_child = 0 9.23.410.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.906 MiB) 9.23.416.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 298.310 MiB) 9.23.423.199 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 334332328191 9.23.423.349 I slot launch_slot_: id 1 | task 7240 | processing task, is_child = 0 9.23.423.417 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 334332329403 9.23.423.518 I slot launch_slot_: id 2 | task 7241 | processing task, is_child = 0 9.24.583.286 I slot print_timing: id 3 | task 7234 | prompt eval time = 1522.31 ms / 736 tokens ( 2.07 ms per token, 483.48 tokens per second) 9.24.583.289 I slot print_timing: id 3 | task 7234 | eval time = 1179.80 ms / 2 tokens ( 1179.80 ms per token, 0.85 tokens per second) 9.24.583.290 I slot print_timing: id 3 | task 7234 | total time = 2702.11 ms / 738 tokens 9.24.583.291 I slot print_timing: id 3 | task 7234 | graphs reused = 5899 9.24.583.291 I slot print_timing: id 3 | task 7234 | graph reallocs = 0 / 0 (same size) / (changed size) 9.24.583.338 I slot release: id 3 | task 7234 | stop processing: n_tokens = 746, truncated = 0 9.26.836.834 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 334333797151 9.26.836.923 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 239.486 MiB) 9.26.869.533 I slot launch_slot_: id 3 | task 7244 | processing task, is_child = 0 9.26.869.544 I slot print_timing: id 0 | task 7239 | prompt processing, n_tokens = 590, progress = 0.84, t = 3.41 s / 172.85 tokens per second 9.26.871.237 I slot print_timing: id 1 | task 7240 | prompt processing, n_tokens = 590, progress = 0.84, t = 3.41 s / 172.86 tokens per second 9.26.872.901 I slot print_timing: id 2 | task 7241 | prompt processing, n_tokens = 590, progress = 0.82, t = 3.41 s / 172.87 tokens per second 9.27.869.559 I slot print_timing: id 0 | task 7239 | prompt processing, n_tokens = 697, progress = 0.99, t = 4.45 s / 156.77 tokens per second 9.28.001.194 I slot print_timing: id 1 | task 7240 | prompt processing, n_tokens = 702, progress = 0.99, t = 4.45 s / 157.90 tokens per second 9.28.003.344 I slot print_timing: id 2 | task 7241 | prompt processing, n_tokens = 719, progress = 0.99, t = 4.45 s / 161.73 tokens per second 9.29.083.767 I slot print_timing: id 0 | task 7239 | prompt eval time = 5375.82 ms / 701 tokens ( 7.67 ms per token, 130.40 tokens per second) 9.29.083.769 I slot print_timing: id 0 | task 7239 | eval time = 284.41 ms / 2 tokens ( 284.41 ms per token, 3.52 tokens per second) 9.29.083.770 I slot print_timing: id 0 | task 7239 | total time = 5660.24 ms / 703 tokens 9.29.083.771 I slot print_timing: id 0 | task 7239 | graphs reused = 5899 9.29.083.771 I slot print_timing: id 0 | task 7239 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.083.806 I slot release: id 0 | task 7239 | stop processing: n_tokens = 711, truncated = 0 9.29.084.905 I slot print_timing: id 1 | task 7240 | prompt eval time = 5376.81 ms / 706 tokens ( 7.62 ms per token, 131.30 tokens per second) 9.29.084.906 I slot print_timing: id 1 | task 7240 | eval time = 284.38 ms / 2 tokens ( 284.38 ms per token, 3.52 tokens per second) 9.29.084.907 I slot print_timing: id 1 | task 7240 | total time = 5661.19 ms / 708 tokens 9.29.084.907 I slot print_timing: id 1 | task 7240 | graphs reused = 5899 9.29.084.908 I slot print_timing: id 1 | task 7240 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.084.933 I slot release: id 1 | task 7240 | stop processing: n_tokens = 716, truncated = 0 9.29.086.026 I slot print_timing: id 2 | task 7241 | prompt eval time = 5377.82 ms / 723 tokens ( 7.44 ms per token, 134.44 tokens per second) 9.29.086.028 I slot print_timing: id 2 | task 7241 | eval time = 284.31 ms / 2 tokens ( 284.31 ms per token, 3.52 tokens per second) 9.29.086.029 I slot print_timing: id 2 | task 7241 | total time = 5662.13 ms / 725 tokens 9.29.086.029 I slot print_timing: id 2 | task 7241 | graphs reused = 5899 9.29.086.029 I slot print_timing: id 2 | task 7241 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.086.055 I slot release: id 2 | task 7241 | stop processing: n_tokens = 733, truncated = 0 9.29.122.753 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.880 9.29.122.815 I slot launch_slot_: id 0 | task 7249 | processing task, is_child = 0 9.29.122.891 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 9.29.134.399 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.874 9.29.134.462 I slot launch_slot_: id 1 | task 7250 | processing task, is_child = 0 9.29.134.524 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.854 9.29.134.558 I slot launch_slot_: id 2 | task 7251 | processing task, is_child = 0 9.29.645.627 I slot print_timing: id 3 | task 7244 | prompt eval time = 2248.18 ms / 699 tokens ( 3.22 ms per token, 310.92 tokens per second) 9.29.645.629 I slot print_timing: id 3 | task 7244 | eval time = 522.87 ms / 2 tokens ( 522.87 ms per token, 1.91 tokens per second) 9.29.645.630 I slot print_timing: id 3 | task 7244 | total time = 2771.05 ms / 701 tokens 9.29.645.630 I slot print_timing: id 3 | task 7244 | graphs reused = 5899 9.29.645.631 I slot print_timing: id 3 | task 7244 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.645.670 I slot release: id 3 | task 7244 | stop processing: n_tokens = 709, truncated = 0 9.29.709.535 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.886 9.29.709.627 I slot launch_slot_: id 3 | task 7254 | processing task, is_child = 0 9.29.938.246 I slot print_timing: id 0 | task 7249 | prompt eval time = 572.70 ms / 85 tokens ( 6.74 ms per token, 148.42 tokens per second) 9.29.938.248 I slot print_timing: id 0 | task 7249 | eval time = 230.98 ms / 2 tokens ( 230.98 ms per token, 4.33 tokens per second) 9.29.938.248 I slot print_timing: id 0 | task 7249 | total time = 803.68 ms / 87 tokens 9.29.938.248 I slot print_timing: id 0 | task 7249 | graphs reused = 5899 9.29.938.249 I slot print_timing: id 0 | task 7249 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.938.285 I slot release: id 0 | task 7249 | stop processing: n_tokens = 712, truncated = 0 9.29.939.380 I slot print_timing: id 1 | task 7250 | prompt eval time = 572.10 ms / 79 tokens ( 7.24 ms per token, 138.09 tokens per second) 9.29.939.382 I slot print_timing: id 1 | task 7250 | eval time = 231.02 ms / 2 tokens ( 231.02 ms per token, 4.33 tokens per second) 9.29.939.382 I slot print_timing: id 1 | task 7250 | total time = 803.12 ms / 81 tokens 9.29.939.383 I slot print_timing: id 1 | task 7250 | graphs reused = 5899 9.29.939.383 I slot print_timing: id 1 | task 7250 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.939.410 I slot release: id 1 | task 7250 | stop processing: n_tokens = 706, truncated = 0 9.29.940.530 I slot print_timing: id 2 | task 7251 | prompt eval time = 571.59 ms / 77 tokens ( 7.42 ms per token, 134.71 tokens per second) 9.29.940.532 I slot print_timing: id 2 | task 7251 | eval time = 231.00 ms / 2 tokens ( 231.00 ms per token, 4.33 tokens per second) 9.29.940.532 I slot print_timing: id 2 | task 7251 | total time = 802.59 ms / 79 tokens 9.29.940.532 I slot print_timing: id 2 | task 7251 | graphs reused = 5899 9.29.940.533 I slot print_timing: id 2 | task 7251 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.940.555 I slot release: id 2 | task 7251 | stop processing: n_tokens = 704, truncated = 0 9.29.978.757 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.891 9.29.978.834 I slot launch_slot_: id 2 | task 7257 | processing task, is_child = 0 9.29.978.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 9.29.978.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.766 MiB) 9.29.994.225 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.879 9.29.994.293 I slot launch_slot_: id 0 | task 7258 | processing task, is_child = 0 9.29.994.356 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.887 9.29.994.391 I slot launch_slot_: id 1 | task 7259 | processing task, is_child = 0 9.30.671.406 I slot print_timing: id 3 | task 7254 | prompt eval time = 269.12 ms / 87 tokens ( 3.09 ms per token, 323.28 tokens per second) 9.30.671.411 I slot print_timing: id 3 | task 7254 | eval time = 692.64 ms / 2 tokens ( 692.64 ms per token, 1.44 tokens per second) 9.30.671.412 I slot print_timing: id 3 | task 7254 | total time = 961.75 ms / 89 tokens 9.30.671.413 I slot print_timing: id 3 | task 7254 | graphs reused = 5899 9.30.671.414 I slot print_timing: id 3 | task 7254 | graph reallocs = 0 / 0 (same size) / (changed size) 9.30.671.483 I slot release: id 3 | task 7254 | stop processing: n_tokens = 716, truncated = 0 9.30.734.899 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 334339885296 9.30.734.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.549 MiB) 9.30.743.056 I slot launch_slot_: id 3 | task 7262 | processing task, is_child = 0 9.31.446.354 I slot print_timing: id 0 | task 7258 | prompt eval time = 738.23 ms / 80 tokens ( 9.23 ms per token, 108.37 tokens per second) 9.31.446.360 I slot print_timing: id 0 | task 7258 | eval time = 713.72 ms / 2 tokens ( 713.72 ms per token, 1.40 tokens per second) 9.31.446.361 I slot print_timing: id 0 | task 7258 | total time = 1451.95 ms / 82 tokens 9.31.446.361 I slot print_timing: id 0 | task 7258 | graphs reused = 5899 9.31.446.362 I slot print_timing: id 0 | task 7258 | graph reallocs = 0 / 0 (same size) / (changed size) 9.31.446.406 I slot release: id 0 | task 7258 | stop processing: n_tokens = 707, truncated = 0 9.31.447.549 I slot print_timing: id 1 | task 7259 | prompt eval time = 737.60 ms / 121 tokens ( 6.10 ms per token, 164.05 tokens per second) 9.31.447.552 I slot print_timing: id 1 | task 7259 | eval time = 713.84 ms / 2 tokens ( 713.84 ms per token, 1.40 tokens per second) 9.31.447.552 I slot print_timing: id 1 | task 7259 | total time = 1451.44 ms / 123 tokens 9.31.447.553 I slot print_timing: id 1 | task 7259 | graphs reused = 5899 9.31.447.553 I slot print_timing: id 1 | task 7259 | graph reallocs = 0 / 0 (same size) / (changed size) 9.31.447.587 I slot release: id 1 | task 7259 | stop processing: n_tokens = 748, truncated = 0 9.31.448.740 I slot print_timing: id 2 | task 7257 | prompt eval time = 737.10 ms / 86 tokens ( 8.57 ms per token, 116.67 tokens per second) 9.31.448.742 I slot print_timing: id 2 | task 7257 | eval time = 713.85 ms / 2 tokens ( 713.85 ms per token, 1.40 tokens per second) 9.31.448.742 I slot print_timing: id 2 | task 7257 | total time = 1450.94 ms / 88 tokens 9.31.448.742 I slot print_timing: id 2 | task 7257 | graphs reused = 5899 9.31.448.743 I slot print_timing: id 2 | task 7257 | graph reallocs = 0 / 0 (same size) / (changed size) 9.31.448.769 I slot release: id 2 | task 7257 | stop processing: n_tokens = 714, truncated = 0 9.32.152.364 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 334340660219 9.32.152.469 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.112 MiB) 9.32.455.072 I slot launch_slot_: id 0 | task 7266 | processing task, is_child = 0 9.32.455.153 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.398 MiB) 9.32.464.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.744 MiB) 9.32.472.626 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 334340661400 9.32.472.759 I slot launch_slot_: id 1 | task 7267 | processing task, is_child = 0 9.32.472.820 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 334340662582 9.32.472.921 I slot launch_slot_: id 2 | task 7268 | processing task, is_child = 0 9.37.337.112 I slot print_timing: id 3 | task 7262 | prompt eval time = 4548.65 ms / 896 tokens ( 5.08 ms per token, 196.98 tokens per second) 9.37.337.116 I slot print_timing: id 3 | task 7262 | eval time = 2045.39 ms / 2 tokens ( 2045.39 ms per token, 0.49 tokens per second) 9.37.337.116 I slot print_timing: id 3 | task 7262 | total time = 6594.04 ms / 898 tokens 9.37.337.117 I slot print_timing: id 3 | task 7262 | graphs reused = 5899 9.37.337.118 I slot print_timing: id 3 | task 7262 | graph reallocs = 0 / 0 (same size) / (changed size) 9.37.337.208 I slot release: id 3 | task 7262 | stop processing: n_tokens = 906, truncated = 0 9.37.337.241 I slot print_timing: id 0 | task 7266 | prompt processing, n_tokens = 761, progress = 0.87, t = 4.86 s / 156.48 tokens per second 9.37.340.063 I slot print_timing: id 1 | task 7267 | prompt processing, n_tokens = 909, progress = 0.84, t = 4.86 s / 186.92 tokens per second 9.37.342.011 I slot print_timing: id 2 | task 7268 | prompt processing, n_tokens = 909, progress = 0.83, t = 4.86 s / 186.93 tokens per second 9.38.249.183 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 906, t_last = 334346551021 9.38.249.276 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 368.257 MiB) 9.38.297.462 I slot launch_slot_: id 3 | task 7272 | processing task, is_child = 0 9.38.297.472 I slot print_timing: id 0 | task 7266 | prompt processing, n_tokens = 875, progress = 1.00, t = 5.78 s / 151.48 tokens per second 9.38.299.319 I slot print_timing: id 1 | task 7267 | prompt processing, n_tokens = 1085, progress = 1.00, t = 5.78 s / 187.84 tokens per second 9.38.301.129 I slot print_timing: id 2 | task 7268 | prompt processing, n_tokens = 1095, progress = 1.00, t = 5.78 s / 189.58 tokens per second 9.40.064.341 I slot print_timing: id 0 | task 7266 | prompt eval time = 6909.08 ms / 879 tokens ( 7.86 ms per token, 127.22 tokens per second) 9.40.064.344 I slot print_timing: id 0 | task 7266 | eval time = 682.33 ms / 2 tokens ( 682.33 ms per token, 1.47 tokens per second) 9.40.064.344 I slot print_timing: id 0 | task 7266 | total time = 7591.41 ms / 881 tokens 9.40.064.345 I slot print_timing: id 0 | task 7266 | graphs reused = 5899 9.40.064.346 I slot print_timing: id 0 | task 7266 | graph reallocs = 0 / 0 (same size) / (changed size) 9.40.064.389 I slot release: id 0 | task 7266 | stop processing: n_tokens = 889, truncated = 0 9.40.065.483 I slot print_timing: id 1 | task 7267 | prompt eval time = 6910.05 ms / 1089 tokens ( 6.35 ms per token, 157.60 tokens per second) 9.40.065.487 I slot print_timing: id 1 | task 7267 | eval time = 682.32 ms / 2 tokens ( 682.32 ms per token, 1.47 tokens per second) 9.40.065.487 I slot print_timing: id 1 | task 7267 | total time = 7592.37 ms / 1091 tokens 9.40.065.488 I slot print_timing: id 1 | task 7267 | graphs reused = 5899 9.40.065.488 I slot print_timing: id 1 | task 7267 | graph reallocs = 0 / 0 (same size) / (changed size) 9.40.065.528 I slot release: id 1 | task 7267 | stop processing: n_tokens = 1099, truncated = 0 9.40.066.643 I slot print_timing: id 2 | task 7268 | prompt eval time = 6911.07 ms / 1099 tokens ( 6.29 ms per token, 159.02 tokens per second) 9.40.066.648 I slot print_timing: id 2 | task 7268 | eval time = 682.30 ms / 2 tokens ( 682.30 ms per token, 1.47 tokens per second) 9.40.066.649 I slot print_timing: id 2 | task 7268 | total time = 7593.37 ms / 1101 tokens 9.40.066.649 I slot print_timing: id 2 | task 7268 | graphs reused = 5899 9.40.066.649 I slot print_timing: id 2 | task 7268 | graph reallocs = 0 / 0 (same size) / (changed size) 9.40.066.678 I slot release: id 2 | task 7268 | stop processing: n_tokens = 1109, truncated = 0 9.40.477.634 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.894 9.40.477.696 I slot launch_slot_: id 2 | task 7277 | processing task, is_child = 0 9.40.477.787 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.451 MiB) 9.40.484.083 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 342.409 MiB) 9.40.490.382 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.901 9.40.490.438 I slot launch_slot_: id 1 | task 7278 | processing task, is_child = 0 9.40.490.510 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 334349278203 9.40.492.876 I slot launch_slot_: id 0 | task 7279 | processing task, is_child = 0 9.40.991.307 I slot print_timing: id 3 | task 7272 | prompt eval time = 2174.69 ms / 1092 tokens ( 1.99 ms per token, 502.14 tokens per second) 9.40.991.310 I slot print_timing: id 3 | task 7272 | eval time = 513.68 ms / 2 tokens ( 513.68 ms per token, 1.95 tokens per second) 9.40.991.311 I slot print_timing: id 3 | task 7272 | total time = 2688.36 ms / 1094 tokens 9.40.991.312 I slot print_timing: id 3 | task 7272 | graphs reused = 5899 9.40.991.312 I slot print_timing: id 3 | task 7272 | graph reallocs = 0 / 0 (same size) / (changed size) 9.40.991.361 I slot release: id 3 | task 7272 | stop processing: n_tokens = 1102, truncated = 0 9.41.417.447 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.899 9.41.417.587 I slot launch_slot_: id 3 | task 7282 | processing task, is_child = 0 9.41.688.325 I slot print_timing: id 1 | task 7278 | prompt eval time = 920.37 ms / 106 tokens ( 8.68 ms per token, 115.17 tokens per second) 9.41.688.329 I slot print_timing: id 1 | task 7278 | eval time = 272.06 ms / 2 tokens ( 272.06 ms per token, 3.68 tokens per second) 9.41.688.330 I slot print_timing: id 1 | task 7278 | total time = 1192.43 ms / 108 tokens 9.41.688.330 I slot print_timing: id 1 | task 7278 | graphs reused = 5899 9.41.688.331 I slot print_timing: id 1 | task 7278 | graph reallocs = 0 / 0 (same size) / (changed size) 9.41.688.390 I slot release: id 1 | task 7278 | stop processing: n_tokens = 1097, truncated = 0 9.41.689.524 I slot print_timing: id 2 | task 7277 | prompt eval time = 919.86 ms / 105 tokens ( 8.76 ms per token, 114.15 tokens per second) 9.41.689.527 I slot print_timing: id 2 | task 7277 | eval time = 272.09 ms / 2 tokens ( 272.09 ms per token, 3.68 tokens per second) 9.41.689.528 I slot print_timing: id 2 | task 7277 | total time = 1191.95 ms / 107 tokens 9.41.689.528 I slot print_timing: id 2 | task 7277 | graphs reused = 5899 9.41.689.528 I slot print_timing: id 2 | task 7277 | graph reallocs = 0 / 0 (same size) / (changed size) 9.41.689.566 I slot release: id 2 | task 7277 | stop processing: n_tokens = 1097, truncated = 0 9.41.745.992 I slot print_timing: id 0 | task 7279 | prompt eval time = 1194.35 ms / 170 tokens ( 7.03 ms per token, 142.34 tokens per second) 9.41.745.997 I slot print_timing: id 0 | task 7279 | eval time = 58.75 ms / 2 tokens ( 58.75 ms per token, 17.02 tokens per second) 9.41.745.998 I slot print_timing: id 0 | task 7279 | total time = 1253.10 ms / 172 tokens 9.41.745.998 I slot print_timing: id 0 | task 7279 | graphs reused = 5899 9.41.745.998 I slot print_timing: id 0 | task 7279 | graph reallocs = 0 / 0 (same size) / (changed size) 9.41.746.031 I slot release: id 0 | task 7279 | stop processing: n_tokens = 1088, truncated = 0 9.41.747.200 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.911 9.41.747.272 I slot launch_slot_: id 0 | task 7285 | processing task, is_child = 0 9.41.760.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.639 MiB) 9.41.769.854 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.903 9.41.769.919 I slot launch_slot_: id 1 | task 7286 | processing task, is_child = 0 9.41.770.009 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.903 9.41.770.045 I slot launch_slot_: id 2 | task 7287 | processing task, is_child = 0 9.42.451.306 I slot print_timing: id 3 | task 7282 | prompt eval time = 325.74 ms / 98 tokens ( 3.32 ms per token, 300.86 tokens per second) 9.42.451.314 I slot print_timing: id 3 | task 7282 | eval time = 704.10 ms / 2 tokens ( 704.10 ms per token, 1.42 tokens per second) 9.42.451.314 I slot print_timing: id 3 | task 7282 | total time = 1029.84 ms / 100 tokens 9.42.451.315 I slot print_timing: id 3 | task 7282 | graphs reused = 5899 9.42.451.315 I slot print_timing: id 3 | task 7282 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.451.373 I slot release: id 3 | task 7282 | stop processing: n_tokens = 1090, truncated = 0 9.42.521.412 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.909 9.42.521.503 I slot launch_slot_: id 3 | task 7290 | processing task, is_child = 0 9.42.755.570 I slot print_timing: id 0 | task 7285 | prompt eval time = 749.09 ms / 107 tokens ( 7.00 ms per token, 142.84 tokens per second) 9.42.755.573 I slot print_timing: id 0 | task 7285 | eval time = 236.43 ms / 2 tokens ( 236.43 ms per token, 4.23 tokens per second) 9.42.755.573 I slot print_timing: id 0 | task 7285 | total time = 985.52 ms / 109 tokens 9.42.755.574 I slot print_timing: id 0 | task 7285 | graphs reused = 5899 9.42.755.574 I slot print_timing: id 0 | task 7285 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.755.615 I slot release: id 0 | task 7285 | stop processing: n_tokens = 1099, truncated = 0 9.42.756.745 I slot print_timing: id 1 | task 7286 | prompt eval time = 748.51 ms / 114 tokens ( 6.57 ms per token, 152.30 tokens per second) 9.42.756.749 I slot print_timing: id 1 | task 7286 | eval time = 236.50 ms / 2 tokens ( 236.50 ms per token, 4.23 tokens per second) 9.42.756.750 I slot print_timing: id 1 | task 7286 | total time = 985.01 ms / 116 tokens 9.42.756.750 I slot print_timing: id 1 | task 7286 | graphs reused = 5899 9.42.756.750 I slot print_timing: id 1 | task 7286 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.756.793 I slot release: id 1 | task 7286 | stop processing: n_tokens = 1106, truncated = 0 9.42.757.905 I slot print_timing: id 2 | task 7287 | prompt eval time = 747.94 ms / 108 tokens ( 6.93 ms per token, 144.40 tokens per second) 9.42.757.908 I slot print_timing: id 2 | task 7287 | eval time = 236.50 ms / 2 tokens ( 236.50 ms per token, 4.23 tokens per second) 9.42.757.908 I slot print_timing: id 2 | task 7287 | total time = 984.43 ms / 110 tokens 9.42.757.908 I slot print_timing: id 2 | task 7287 | graphs reused = 5899 9.42.757.909 I slot print_timing: id 2 | task 7287 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.757.942 I slot release: id 2 | task 7287 | stop processing: n_tokens = 1100, truncated = 0 9.42.795.899 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 9.42.795.954 I slot launch_slot_: id 0 | task 7293 | processing task, is_child = 0 9.42.796.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.197 MiB) 9.42.810.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.567 MiB) 9.42.820.162 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.896 9.42.820.237 I slot launch_slot_: id 1 | task 7294 | processing task, is_child = 0 9.42.820.325 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.901 9.42.820.363 I slot launch_slot_: id 2 | task 7295 | processing task, is_child = 0 9.43.497.531 I slot print_timing: id 3 | task 7290 | prompt eval time = 274.38 ms / 100 tokens ( 2.74 ms per token, 364.45 tokens per second) 9.43.497.534 I slot print_timing: id 3 | task 7290 | eval time = 701.64 ms / 2 tokens ( 701.64 ms per token, 1.43 tokens per second) 9.43.497.534 I slot print_timing: id 3 | task 7290 | total time = 976.02 ms / 102 tokens 9.43.497.535 I slot print_timing: id 3 | task 7290 | graphs reused = 5899 9.43.497.535 I slot print_timing: id 3 | task 7290 | graph reallocs = 0 / 0 (same size) / (changed size) 9.43.497.584 I slot release: id 3 | task 7290 | stop processing: n_tokens = 1092, truncated = 0 9.43.560.290 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.908 9.43.560.351 I slot launch_slot_: id 3 | task 7298 | processing task, is_child = 0 9.43.845.569 I slot print_timing: id 0 | task 7293 | prompt eval time = 737.64 ms / 105 tokens ( 7.03 ms per token, 142.35 tokens per second) 9.43.845.573 I slot print_timing: id 0 | task 7293 | eval time = 287.55 ms / 2 tokens ( 287.55 ms per token, 3.48 tokens per second) 9.43.845.574 I slot print_timing: id 0 | task 7293 | total time = 1025.20 ms / 107 tokens 9.43.845.575 I slot print_timing: id 0 | task 7293 | graphs reused = 5899 9.43.845.575 I slot print_timing: id 0 | task 7293 | graph reallocs = 0 / 0 (same size) / (changed size) 9.43.845.619 I slot release: id 0 | task 7293 | stop processing: n_tokens = 1097, truncated = 0 9.43.846.731 I slot print_timing: id 1 | task 7294 | prompt eval time = 737.07 ms / 102 tokens ( 7.23 ms per token, 138.39 tokens per second) 9.43.846.735 I slot print_timing: id 1 | task 7294 | eval time = 287.61 ms / 2 tokens ( 287.61 ms per token, 3.48 tokens per second) 9.43.846.735 I slot print_timing: id 1 | task 7294 | total time = 1024.68 ms / 104 tokens 9.43.846.736 I slot print_timing: id 1 | task 7294 | graphs reused = 5899 9.43.846.736 I slot print_timing: id 1 | task 7294 | graph reallocs = 0 / 0 (same size) / (changed size) 9.43.846.774 I slot release: id 1 | task 7294 | stop processing: n_tokens = 1094, truncated = 0 9.43.847.922 I slot print_timing: id 2 | task 7295 | prompt eval time = 736.52 ms / 104 tokens ( 7.08 ms per token, 141.20 tokens per second) 9.43.847.928 I slot print_timing: id 2 | task 7295 | eval time = 287.63 ms / 2 tokens ( 287.63 ms per token, 3.48 tokens per second) 9.43.847.929 I slot print_timing: id 2 | task 7295 | total time = 1024.16 ms / 106 tokens 9.43.847.929 I slot print_timing: id 2 | task 7295 | graphs reused = 5899 9.43.847.929 I slot print_timing: id 2 | task 7295 | graph reallocs = 0 / 0 (same size) / (changed size) 9.43.847.956 I slot release: id 2 | task 7295 | stop processing: n_tokens = 1096, truncated = 0 9.43.886.670 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1097, t_last = 334353059432 9.43.886.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.832 MiB) 9.43.900.859 I slot launch_slot_: id 0 | task 7301 | processing task, is_child = 0 9.43.900.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.325 MiB) 9.43.900.954 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.104 MiB) 9.43.909.480 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.102 MiB) 9.43.917.758 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1094, t_last = 334353060587 9.43.917.902 I slot launch_slot_: id 1 | task 7302 | processing task, is_child = 0 9.43.917.980 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1096, t_last = 334353061769 9.43.918.085 I slot launch_slot_: id 2 | task 7303 | processing task, is_child = 0 9.46.775.071 I slot print_timing: id 3 | task 7298 | prompt eval time = 326.31 ms / 103 tokens ( 3.17 ms per token, 315.65 tokens per second) 9.46.775.074 I slot print_timing: id 3 | task 7298 | eval time = 2888.40 ms / 2 tokens ( 2888.40 ms per token, 0.35 tokens per second) 9.46.775.075 I slot print_timing: id 3 | task 7298 | total time = 3214.71 ms / 105 tokens 9.46.775.075 I slot print_timing: id 3 | task 7298 | graphs reused = 5899 9.46.775.076 I slot print_timing: id 3 | task 7298 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.775.128 I slot release: id 3 | task 7298 | stop processing: n_tokens = 1095, truncated = 0 9.48.656.167 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1095, t_last = 334355988941 9.48.656.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.040 MiB) 9.48.743.939 I slot launch_slot_: id 3 | task 7306 | processing task, is_child = 0 9.48.743.952 I slot print_timing: id 0 | task 7301 | prompt processing, n_tokens = 861, progress = 0.84, t = 4.74 s / 181.72 tokens per second 9.48.746.114 I slot print_timing: id 1 | task 7302 | prompt processing, n_tokens = 861, progress = 0.86, t = 4.74 s / 181.73 tokens per second 9.48.747.797 I slot print_timing: id 2 | task 7303 | prompt processing, n_tokens = 861, progress = 0.79, t = 4.74 s / 181.74 tokens per second 9.50.199.378 I slot print_timing: id 0 | task 7301 | prompt processing, n_tokens = 1017, progress = 1.00, t = 6.28 s / 161.91 tokens per second 9.50.775.102 I slot print_timing: id 1 | task 7302 | prompt processing, n_tokens = 996, progress = 1.00, t = 6.28 s / 158.57 tokens per second 9.50.778.751 I slot print_timing: id 2 | task 7303 | prompt processing, n_tokens = 1087, progress = 1.00, t = 6.28 s / 173.07 tokens per second 9.51.843.769 I slot print_timing: id 0 | task 7301 | prompt eval time = 7511.33 ms / 1021 tokens ( 7.36 ms per token, 135.93 tokens per second) 9.51.843.773 I slot print_timing: id 0 | task 7301 | eval time = 414.34 ms / 2 tokens ( 414.34 ms per token, 2.41 tokens per second) 9.51.843.773 I slot print_timing: id 0 | task 7301 | total time = 7925.67 ms / 1023 tokens 9.51.843.774 I slot print_timing: id 0 | task 7301 | graphs reused = 5899 9.51.843.774 I slot print_timing: id 0 | task 7301 | graph reallocs = 0 / 0 (same size) / (changed size) 9.51.843.856 I slot release: id 0 | task 7301 | stop processing: n_tokens = 1031, truncated = 0 9.51.844.993 I slot print_timing: id 1 | task 7302 | prompt eval time = 7512.31 ms / 1000 tokens ( 7.51 ms per token, 133.11 tokens per second) 9.51.844.996 I slot print_timing: id 1 | task 7302 | eval time = 414.37 ms / 2 tokens ( 414.37 ms per token, 2.41 tokens per second) 9.51.844.997 I slot print_timing: id 1 | task 7302 | total time = 7926.69 ms / 1002 tokens 9.51.844.997 I slot print_timing: id 1 | task 7302 | graphs reused = 5899 9.51.844.998 I slot print_timing: id 1 | task 7302 | graph reallocs = 0 / 0 (same size) / (changed size) 9.51.845.045 I slot release: id 1 | task 7302 | stop processing: n_tokens = 1010, truncated = 0 9.51.846.204 I slot print_timing: id 2 | task 7303 | prompt eval time = 7513.46 ms / 1091 tokens ( 6.89 ms per token, 145.21 tokens per second) 9.51.846.206 I slot print_timing: id 2 | task 7303 | eval time = 414.23 ms / 2 tokens ( 414.23 ms per token, 2.41 tokens per second) 9.51.846.207 I slot print_timing: id 2 | task 7303 | total time = 7927.69 ms / 1093 tokens 9.51.846.207 I slot print_timing: id 2 | task 7303 | graphs reused = 5899 9.51.846.208 I slot print_timing: id 2 | task 7303 | graph reallocs = 0 / 0 (same size) / (changed size) 9.51.846.253 I slot release: id 2 | task 7303 | stop processing: n_tokens = 1101, truncated = 0 9.51.846.265 I slot print_timing: id 3 | task 7306 | prompt processing, n_tokens = 1051, progress = 1.00, t = 3.09 s / 339.78 tokens per second 9.51.883.895 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 334361057669 9.51.883.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.905 MiB) 9.51.883.995 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.063 MiB) 9.51.890.341 I slot launch_slot_: id 0 | task 7311 | processing task, is_child = 0 9.51.890.419 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 222.433 MiB) 9.51.896.573 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.839 MiB) 9.51.902.814 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.888 9.51.902.868 I slot launch_slot_: id 1 | task 7312 | processing task, is_child = 0 9.51.902.950 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.815 9.51.902.985 I slot launch_slot_: id 2 | task 7313 | processing task, is_child = 0 9.52.933.343 I slot print_timing: id 3 | task 7306 | prompt eval time = 3134.44 ms / 1055 tokens ( 2.97 ms per token, 336.58 tokens per second) 9.52.933.356 I slot print_timing: id 3 | task 7306 | eval time = 1049.43 ms / 2 tokens ( 1049.43 ms per token, 0.95 tokens per second) 9.52.933.357 I slot print_timing: id 3 | task 7306 | total time = 4183.87 ms / 1057 tokens 9.52.933.359 I slot print_timing: id 3 | task 7306 | graphs reused = 5899 9.52.933.366 I slot print_timing: id 3 | task 7306 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.933.458 I slot release: id 3 | task 7306 | stop processing: n_tokens = 1065, truncated = 0 9.53.680.720 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1065, t_last = 334362147271 9.53.680.854 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 227.356 MiB) 9.53.690.852 I slot launch_slot_: id 3 | task 7316 | processing task, is_child = 0 9.54.528.208 I slot print_timing: id 1 | task 7312 | prompt eval time = 1776.24 ms / 143 tokens ( 12.42 ms per token, 80.51 tokens per second) 9.54.528.211 I slot print_timing: id 1 | task 7312 | eval time = 848.75 ms / 2 tokens ( 848.75 ms per token, 1.18 tokens per second) 9.54.528.211 I slot print_timing: id 1 | task 7312 | total time = 2624.99 ms / 145 tokens 9.54.528.212 I slot print_timing: id 1 | task 7312 | graphs reused = 5899 9.54.528.212 I slot print_timing: id 1 | task 7312 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.528.287 I slot release: id 1 | task 7312 | stop processing: n_tokens = 1041, truncated = 0 9.54.529.527 I slot print_timing: id 2 | task 7313 | prompt eval time = 1775.78 ms / 122 tokens ( 14.56 ms per token, 68.70 tokens per second) 9.54.529.531 I slot print_timing: id 2 | task 7313 | eval time = 848.82 ms / 2 tokens ( 848.82 ms per token, 1.18 tokens per second) 9.54.529.532 I slot print_timing: id 2 | task 7313 | total time = 2624.60 ms / 124 tokens 9.54.529.532 I slot print_timing: id 2 | task 7313 | graphs reused = 5899 9.54.529.532 I slot print_timing: id 2 | task 7313 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.529.580 I slot release: id 2 | task 7313 | stop processing: n_tokens = 1020, truncated = 0 9.55.198.752 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 334363742100 9.55.198.878 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.498 MiB) 9.55.213.878 I slot launch_slot_: id 1 | task 7319 | processing task, is_child = 0 9.55.213.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 237.342 MiB) 9.55.226.450 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1020, t_last = 334363743393 9.55.226.580 I slot launch_slot_: id 2 | task 7320 | processing task, is_child = 0 9.56.337.801 I slot print_timing: id 0 | task 7311 | prompt eval time = 3295.74 ms / 745 tokens ( 4.42 ms per token, 226.05 tokens per second) 9.56.337.810 I slot print_timing: id 0 | task 7311 | eval time = 1139.05 ms / 2 tokens ( 1139.05 ms per token, 0.88 tokens per second) 9.56.337.811 I slot print_timing: id 0 | task 7311 | total time = 4434.79 ms / 747 tokens 9.56.337.811 I slot print_timing: id 0 | task 7311 | graphs reused = 5899 9.56.337.812 I slot print_timing: id 0 | task 7311 | graph reallocs = 0 / 0 (same size) / (changed size) 9.56.337.886 I slot release: id 0 | task 7311 | stop processing: n_tokens = 755, truncated = 0 9.57.859.302 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 9.57.859.448 I slot launch_slot_: id 0 | task 7323 | processing task, is_child = 0 9.58.520.383 I slot print_timing: id 3 | task 7316 | prompt eval time = 4166.76 ms / 787 tokens ( 5.29 ms per token, 188.88 tokens per second) 9.58.520.389 I slot print_timing: id 3 | task 7316 | eval time = 661.09 ms / 2 tokens ( 661.09 ms per token, 1.51 tokens per second) 9.58.520.389 I slot print_timing: id 3 | task 7316 | total time = 4827.85 ms / 789 tokens 9.58.520.390 I slot print_timing: id 3 | task 7316 | graphs reused = 5899 9.58.520.390 I slot print_timing: id 3 | task 7316 | graph reallocs = 0 / 0 (same size) / (changed size) 9.58.520.462 I slot release: id 3 | task 7316 | stop processing: n_tokens = 797, truncated = 0 9.58.524.406 I slot print_timing: id 1 | task 7319 | prompt processing, n_tokens = 713, progress = 0.99, t = 3.29 s / 216.54 tokens per second 9.58.526.145 I slot print_timing: id 2 | task 7320 | prompt processing, n_tokens = 726, progress = 0.99, t = 3.29 s / 220.51 tokens per second 9.58.583.675 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.813 9.58.583.759 I slot launch_slot_: id 3 | task 7326 | processing task, is_child = 0 9.58.812.330 I slot print_timing: id 0 | task 7323 | prompt eval time = 722.01 ms / 97 tokens ( 7.44 ms per token, 134.35 tokens per second) 9.58.812.332 I slot print_timing: id 0 | task 7323 | eval time = 230.84 ms / 2 tokens ( 230.84 ms per token, 4.33 tokens per second) 9.58.812.333 I slot print_timing: id 0 | task 7323 | total time = 952.85 ms / 99 tokens 9.58.812.333 I slot print_timing: id 0 | task 7323 | graphs reused = 5899 9.58.812.334 I slot print_timing: id 0 | task 7323 | graph reallocs = 0 / 0 (same size) / (changed size) 9.58.812.378 I slot release: id 0 | task 7323 | stop processing: n_tokens = 746, truncated = 0 9.58.813.492 I slot print_timing: id 1 | task 7319 | prompt eval time = 3356.01 ms / 717 tokens ( 4.68 ms per token, 213.65 tokens per second) 9.58.813.499 I slot print_timing: id 1 | task 7319 | eval time = 230.90 ms / 2 tokens ( 230.90 ms per token, 4.33 tokens per second) 9.58.813.500 I slot print_timing: id 1 | task 7319 | total time = 3586.90 ms / 719 tokens 9.58.813.500 I slot print_timing: id 1 | task 7319 | graphs reused = 5899 9.58.813.501 I slot print_timing: id 1 | task 7319 | graph reallocs = 0 / 0 (same size) / (changed size) 9.58.813.541 I slot release: id 1 | task 7319 | stop processing: n_tokens = 727, truncated = 0 9.58.814.681 I slot print_timing: id 2 | task 7320 | prompt eval time = 3356.87 ms / 730 tokens ( 4.60 ms per token, 217.46 tokens per second) 9.58.814.683 I slot print_timing: id 2 | task 7320 | eval time = 231.00 ms / 2 tokens ( 231.00 ms per token, 4.33 tokens per second) 9.58.814.684 I slot print_timing: id 2 | task 7320 | total time = 3587.87 ms / 732 tokens 9.58.814.684 I slot print_timing: id 2 | task 7320 | graphs reused = 5899 9.58.814.684 I slot print_timing: id 2 | task 7320 | graph reallocs = 0 / 0 (same size) / (changed size) 9.58.814.712 I slot release: id 2 | task 7320 | stop processing: n_tokens = 740, truncated = 0 9.58.852.839 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.869 9.58.852.886 I slot launch_slot_: id 0 | task 7329 | processing task, is_child = 0 9.58.852.968 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.100 MiB) 9.58.858.258 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 206.821 MiB) 9.58.863.536 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.861 (> 0.100 thold), f_keep = 0.891 9.58.863.584 I slot launch_slot_: id 1 | task 7330 | processing task, is_child = 0 9.58.863.650 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.876 9.58.863.686 I slot launch_slot_: id 2 | task 7331 | processing task, is_child = 0 9.59.484.825 I slot print_timing: id 3 | task 7326 | prompt eval time = 269.07 ms / 89 tokens ( 3.02 ms per token, 330.77 tokens per second) 9.59.484.830 I slot print_timing: id 3 | task 7326 | eval time = 631.99 ms / 2 tokens ( 631.99 ms per token, 1.58 tokens per second) 9.59.484.830 I slot print_timing: id 3 | task 7326 | total time = 901.06 ms / 91 tokens 9.59.484.831 I slot print_timing: id 3 | task 7326 | graphs reused = 5899 9.59.484.831 I slot print_timing: id 3 | task 7326 | graph reallocs = 0 / 0 (same size) / (changed size) 9.59.484.893 I slot release: id 3 | task 7326 | stop processing: n_tokens = 738, truncated = 0 9.59.548.539 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 334368698706 9.59.548.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.385 MiB) 9.59.555.151 I slot launch_slot_: id 3 | task 7334 | processing task, is_child = 0 10.00.421.450 I slot print_timing: id 0 | task 7329 | prompt eval time = 682.61 ms / 100 tokens ( 6.83 ms per token, 146.50 tokens per second) 10.00.421.453 I slot print_timing: id 0 | task 7329 | eval time = 875.14 ms / 2 tokens ( 875.14 ms per token, 1.14 tokens per second) 10.00.421.453 I slot print_timing: id 0 | task 7329 | total time = 1557.75 ms / 102 tokens 10.00.421.454 I slot print_timing: id 0 | task 7329 | graphs reused = 5899 10.00.421.454 I slot print_timing: id 0 | task 7329 | graph reallocs = 0 / 0 (same size) / (changed size) 10.00.421.525 I slot release: id 0 | task 7329 | stop processing: n_tokens = 749, truncated = 0 10.00.422.744 I slot print_timing: id 1 | task 7330 | prompt eval time = 682.02 ms / 105 tokens ( 6.50 ms per token, 153.95 tokens per second) 10.00.422.747 I slot print_timing: id 1 | task 7330 | eval time = 875.32 ms / 2 tokens ( 875.32 ms per token, 1.14 tokens per second) 10.00.422.747 I slot print_timing: id 1 | task 7330 | total time = 1557.34 ms / 107 tokens 10.00.422.748 I slot print_timing: id 1 | task 7330 | graphs reused = 5899 10.00.422.748 I slot print_timing: id 1 | task 7330 | graph reallocs = 0 / 0 (same size) / (changed size) 10.00.422.804 I slot release: id 1 | task 7330 | stop processing: n_tokens = 754, truncated = 0 10.00.424.063 I slot print_timing: id 2 | task 7331 | prompt eval time = 681.48 ms / 84 tokens ( 8.11 ms per token, 123.26 tokens per second) 10.00.424.068 I slot print_timing: id 2 | task 7331 | eval time = 875.53 ms / 2 tokens ( 875.53 ms per token, 1.14 tokens per second) 10.00.424.068 I slot print_timing: id 2 | task 7331 | total time = 1557.01 ms / 86 tokens 10.00.424.069 I slot print_timing: id 2 | task 7331 | graphs reused = 5899 10.00.424.069 I slot print_timing: id 2 | task 7331 | graph reallocs = 0 / 0 (same size) / (changed size) 10.00.424.106 I slot release: id 2 | task 7331 | stop processing: n_tokens = 733, truncated = 0 10.01.073.360 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 749, t_last = 334369635338 10.01.073.438 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 226.512 MiB) 10.01.073.444 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 228.797 MiB) 10.01.440.801 I slot launch_slot_: id 0 | task 7338 | processing task, is_child = 0 10.01.440.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.416 MiB) 10.01.448.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 210.197 MiB) 10.01.454.806 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 334369636617 10.01.454.939 I slot launch_slot_: id 1 | task 7339 | processing task, is_child = 0 10.01.455.002 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 733, t_last = 334369637919 10.01.455.091 I slot launch_slot_: id 2 | task 7340 | processing task, is_child = 0 10.06.099.992 I slot print_timing: id 3 | task 7334 | prompt eval time = 4567.00 ms / 985 tokens ( 4.64 ms per token, 215.68 tokens per second) 10.06.099.998 I slot print_timing: id 3 | task 7334 | eval time = 1977.82 ms / 2 tokens ( 1977.82 ms per token, 0.51 tokens per second) 10.06.099.999 I slot print_timing: id 3 | task 7334 | total time = 6544.82 ms / 987 tokens 10.06.099.999 I slot print_timing: id 3 | task 7334 | graphs reused = 5899 10.06.100.000 I slot print_timing: id 3 | task 7334 | graph reallocs = 0 / 0 (same size) / (changed size) 10.06.100.096 I slot release: id 3 | task 7334 | stop processing: n_tokens = 995, truncated = 0 10.06.100.125 I slot print_timing: id 0 | task 7338 | prompt processing, n_tokens = 812, progress = 0.86, t = 4.64 s / 174.86 tokens per second 10.06.104.160 I slot print_timing: id 1 | task 7339 | prompt processing, n_tokens = 812, progress = 0.78, t = 4.64 s / 174.87 tokens per second 10.06.105.932 I slot print_timing: id 2 | task 7340 | prompt processing, n_tokens = 812, progress = 0.84, t = 4.64 s / 174.87 tokens per second 10.07.008.726 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 334375313909 10.07.008.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.638 MiB) 10.07.203.155 I slot launch_slot_: id 3 | task 7344 | processing task, is_child = 0 10.07.203.165 I slot print_timing: id 0 | task 7338 | prompt processing, n_tokens = 946, progress = 1.00, t = 5.55 s / 170.34 tokens per second 10.07.204.961 I slot print_timing: id 1 | task 7339 | prompt processing, n_tokens = 1039, progress = 1.00, t = 5.55 s / 187.09 tokens per second 10.07.206.768 I slot print_timing: id 2 | task 7340 | prompt processing, n_tokens = 963, progress = 1.00, t = 5.55 s / 173.41 tokens per second 10.09.080.422 I slot print_timing: id 0 | task 7338 | prompt eval time = 6885.58 ms / 950 tokens ( 7.25 ms per token, 137.97 tokens per second) 10.09.080.425 I slot print_timing: id 0 | task 7338 | eval time = 739.74 ms / 2 tokens ( 739.74 ms per token, 1.35 tokens per second) 10.09.080.436 I slot print_timing: id 0 | task 7338 | total time = 7625.32 ms / 952 tokens 10.09.080.437 I slot print_timing: id 0 | task 7338 | graphs reused = 5899 10.09.080.438 I slot print_timing: id 0 | task 7338 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.080.516 I slot release: id 0 | task 7338 | stop processing: n_tokens = 960, truncated = 0 10.09.081.728 I slot print_timing: id 1 | task 7339 | prompt eval time = 6886.59 ms / 1043 tokens ( 6.60 ms per token, 151.45 tokens per second) 10.09.081.731 I slot print_timing: id 1 | task 7339 | eval time = 739.86 ms / 2 tokens ( 739.86 ms per token, 1.35 tokens per second) 10.09.081.732 I slot print_timing: id 1 | task 7339 | total time = 7626.45 ms / 1045 tokens 10.09.081.732 I slot print_timing: id 1 | task 7339 | graphs reused = 5899 10.09.081.732 I slot print_timing: id 1 | task 7339 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.081.777 I slot release: id 1 | task 7339 | stop processing: n_tokens = 1053, truncated = 0 10.09.083.073 I slot print_timing: id 2 | task 7340 | prompt eval time = 6887.66 ms / 967 tokens ( 7.12 ms per token, 140.40 tokens per second) 10.09.083.076 I slot print_timing: id 2 | task 7340 | eval time = 739.98 ms / 2 tokens ( 739.98 ms per token, 1.35 tokens per second) 10.09.083.077 I slot print_timing: id 2 | task 7340 | total time = 7627.64 ms / 969 tokens 10.09.083.077 I slot print_timing: id 2 | task 7340 | graphs reused = 5899 10.09.083.077 I slot print_timing: id 2 | task 7340 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.083.111 I slot release: id 2 | task 7340 | stop processing: n_tokens = 977, truncated = 0 10.09.427.737 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 960, t_last = 334378294329 10.09.427.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.535 MiB) 10.09.433.951 I slot launch_slot_: id 0 | task 7349 | processing task, is_child = 0 10.09.434.041 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.851 MiB) 10.09.440.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.465 MiB) 10.09.446.286 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 334378295590 10.09.446.426 I slot launch_slot_: id 1 | task 7350 | processing task, is_child = 0 10.09.446.496 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 334378296924 10.09.446.606 I slot launch_slot_: id 2 | task 7351 | processing task, is_child = 0 10.13.160.778 I slot print_timing: id 3 | task 7344 | prompt eval time = 2219.20 ms / 1127 tokens ( 1.97 ms per token, 507.84 tokens per second) 10.13.160.781 I slot print_timing: id 3 | task 7344 | eval time = 3733.04 ms / 2 tokens ( 3733.04 ms per token, 0.27 tokens per second) 10.13.160.782 I slot print_timing: id 3 | task 7344 | total time = 5952.24 ms / 1129 tokens 10.13.160.782 I slot print_timing: id 3 | task 7344 | graphs reused = 5899 10.13.160.782 I slot print_timing: id 3 | task 7344 | graph reallocs = 0 / 0 (same size) / (changed size) 10.13.160.843 I slot release: id 3 | task 7344 | stop processing: n_tokens = 1137, truncated = 0 10.13.160.859 I slot print_timing: id 0 | task 7349 | prompt processing, n_tokens = 643, progress = 0.56, t = 3.71 s / 173.18 tokens per second 10.13.162.992 I slot print_timing: id 1 | task 7350 | prompt processing, n_tokens = 1404, progress = 0.66, t = 3.71 s / 378.16 tokens per second 10.16.413.633 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1137, t_last = 334382374656 10.16.413.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.359 MiB) 10.16.954.181 I slot launch_slot_: id 3 | task 7354 | processing task, is_child = 0 10.16.954.197 I slot print_timing: id 0 | task 7349 | prompt processing, n_tokens = 975, progress = 0.84, t = 6.97 s / 139.95 tokens per second 10.16.956.261 I slot print_timing: id 1 | task 7350 | prompt processing, n_tokens = 1616, progress = 0.76, t = 6.97 s / 231.96 tokens per second 10.16.958.121 I slot print_timing: id 2 | task 7351 | prompt processing, n_tokens = 1504, progress = 0.71, t = 3.25 s / 462.68 tokens per second 10.19.918.660 I slot print_timing: id 0 | task 7349 | prompt processing, n_tokens = 1155, progress = 1.00, t = 10.47 s / 110.29 tokens per second 10.20.751.926 I slot print_timing: id 1 | task 7350 | prompt processing, n_tokens = 1795, progress = 0.84, t = 10.47 s / 171.41 tokens per second 10.20.755.349 I slot print_timing: id 2 | task 7351 | prompt processing, n_tokens = 1613, progress = 0.76, t = 6.76 s / 238.76 tokens per second 10.22.316.030 I slot print_timing: id 1 | task 7350 | prompt processing, n_tokens = 2128, progress = 1.00, t = 12.87 s / 165.37 tokens per second 10.22.319.781 I slot print_timing: id 2 | task 7351 | prompt processing, n_tokens = 1795, progress = 0.84, t = 9.15 s / 196.13 tokens per second 10.22.321.439 I slot print_timing: id 3 | task 7354 | prompt processing, n_tokens = 1795, progress = 0.86, t = 5.36 s / 335.09 tokens per second 10.23.695.028 I slot print_timing: id 0 | task 7349 | prompt eval time = 12869.39 ms / 1159 tokens ( 11.10 ms per token, 90.06 tokens per second) 10.23.695.031 I slot print_timing: id 0 | task 7349 | eval time = 1379.02 ms / 2 tokens ( 1379.02 ms per token, 0.73 tokens per second) 10.23.695.031 I slot print_timing: id 0 | task 7349 | total time = 14248.41 ms / 1161 tokens 10.23.695.032 I slot print_timing: id 0 | task 7349 | graphs reused = 5899 10.23.695.032 I slot print_timing: id 0 | task 7349 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.695.089 I slot release: id 0 | task 7349 | stop processing: n_tokens = 1169, truncated = 0 10.23.696.345 I slot print_timing: id 2 | task 7351 | prompt processing, n_tokens = 2125, progress = 1.00, t = 10.53 s / 201.79 tokens per second 10.23.700.325 I slot print_timing: id 3 | task 7354 | prompt processing, n_tokens = 2092, progress = 1.00, t = 6.74 s / 310.58 tokens per second 10.23.773.137 I slot print_timing: id 1 | task 7350 | prompt eval time = 14249.49 ms / 2132 tokens ( 6.68 ms per token, 149.62 tokens per second) 10.23.773.139 I slot print_timing: id 1 | task 7350 | eval time = 76.80 ms / 2 tokens ( 76.80 ms per token, 13.02 tokens per second) 10.23.773.140 I slot print_timing: id 1 | task 7350 | total time = 14326.30 ms / 2134 tokens 10.23.773.140 I slot print_timing: id 1 | task 7350 | graphs reused = 5899 10.23.773.141 I slot print_timing: id 1 | task 7350 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.773.216 I slot release: id 1 | task 7350 | stop processing: n_tokens = 2142, truncated = 0 10.23.775.466 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 10.23.775.541 I slot launch_slot_: id 1 | task 7359 | processing task, is_child = 0 10.23.775.630 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.328 MiB) 10.23.782.330 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1169, t_last = 334392908902 10.23.782.489 I slot launch_slot_: id 0 | task 7360 | processing task, is_child = 0 10.27.272.692 I slot print_timing: id 2 | task 7351 | prompt eval time = 10611.34 ms / 2129 tokens ( 4.98 ms per token, 200.63 tokens per second) 10.27.272.695 I slot print_timing: id 2 | task 7351 | eval time = 3498.33 ms / 2 tokens ( 3498.33 ms per token, 0.29 tokens per second) 10.27.272.697 I slot print_timing: id 2 | task 7351 | total time = 14109.68 ms / 2131 tokens 10.27.272.697 I slot print_timing: id 2 | task 7351 | graphs reused = 5899 10.27.272.698 I slot print_timing: id 2 | task 7351 | graph reallocs = 0 / 0 (same size) / (changed size) 10.27.272.805 I slot release: id 2 | task 7351 | stop processing: n_tokens = 2139, truncated = 0 10.27.274.013 I slot print_timing: id 3 | task 7354 | prompt eval time = 6817.33 ms / 2096 tokens ( 3.25 ms per token, 307.45 tokens per second) 10.27.274.017 I slot print_timing: id 3 | task 7354 | eval time = 3498.55 ms / 2 tokens ( 3498.55 ms per token, 0.29 tokens per second) 10.27.274.017 I slot print_timing: id 3 | task 7354 | total time = 10315.88 ms / 2098 tokens 10.27.274.017 I slot print_timing: id 3 | task 7354 | graphs reused = 5899 10.27.274.018 I slot print_timing: id 3 | task 7354 | graph reallocs = 0 / 0 (same size) / (changed size) 10.27.274.095 I slot release: id 3 | task 7354 | stop processing: n_tokens = 2106, truncated = 0 10.27.274.125 I slot print_timing: id 0 | task 7360 | prompt processing, n_tokens = 1627, progress = 0.76, t = 3.49 s / 466.31 tokens per second 10.27.276.799 I slot print_timing: id 1 | task 7359 | prompt processing, n_tokens = 249, progress = 1.00, t = 3.49 s / 71.37 tokens per second 10.27.689.356 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.869 (> 0.100 thold), f_keep = 0.856 10.27.689.411 I slot launch_slot_: id 2 | task 7363 | processing task, is_child = 0 10.27.689.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.982 MiB) 10.27.707.238 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.870 10.27.707.288 I slot launch_slot_: id 3 | task 7364 | processing task, is_child = 0 10.27.707.295 I slot print_timing: id 0 | task 7360 | prompt processing, n_tokens = 1795, progress = 0.84, t = 3.91 s / 459.58 tokens per second 10.29.652.512 I slot print_timing: id 1 | task 7359 | prompt eval time = 3906.58 ms / 253 tokens ( 15.44 ms per token, 64.76 tokens per second) 10.29.652.516 I slot print_timing: id 1 | task 7359 | eval time = 1963.16 ms / 2 tokens ( 1963.16 ms per token, 0.51 tokens per second) 10.29.652.521 I slot print_timing: id 1 | task 7359 | total time = 5869.74 ms / 255 tokens 10.29.652.521 I slot print_timing: id 1 | task 7359 | graphs reused = 5899 10.29.652.522 I slot print_timing: id 1 | task 7359 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.652.651 I slot release: id 1 | task 7359 | stop processing: n_tokens = 2086, truncated = 0 10.29.652.684 I slot print_timing: id 0 | task 7360 | prompt processing, n_tokens = 2139, progress = 1.00, t = 5.87 s / 364.46 tokens per second 10.29.734.618 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 10.29.734.717 I slot launch_slot_: id 1 | task 7367 | processing task, is_child = 0 10.30.469.076 I slot print_timing: id 0 | task 7360 | prompt eval time = 5949.97 ms / 2143 tokens ( 2.78 ms per token, 360.17 tokens per second) 10.30.469.080 I slot print_timing: id 0 | task 7360 | eval time = 736.60 ms / 2 tokens ( 736.60 ms per token, 1.36 tokens per second) 10.30.469.081 I slot print_timing: id 0 | task 7360 | total time = 6686.57 ms / 2145 tokens 10.30.469.082 I slot print_timing: id 0 | task 7360 | graphs reused = 5899 10.30.469.082 I slot print_timing: id 0 | task 7360 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.469.235 I slot release: id 0 | task 7360 | stop processing: n_tokens = 2153, truncated = 0 10.30.470.443 I slot print_timing: id 2 | task 7363 | prompt eval time = 2024.59 ms / 276 tokens ( 7.34 ms per token, 136.32 tokens per second) 10.30.470.444 I slot print_timing: id 2 | task 7363 | eval time = 736.90 ms / 2 tokens ( 736.90 ms per token, 1.36 tokens per second) 10.30.470.445 I slot print_timing: id 2 | task 7363 | total time = 2761.49 ms / 278 tokens 10.30.470.445 I slot print_timing: id 2 | task 7363 | graphs reused = 5899 10.30.470.445 I slot print_timing: id 2 | task 7363 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.470.520 I slot release: id 2 | task 7363 | stop processing: n_tokens = 2108, truncated = 0 10.30.471.719 I slot print_timing: id 3 | task 7364 | prompt eval time = 2023.93 ms / 344 tokens ( 5.88 ms per token, 169.97 tokens per second) 10.30.471.722 I slot print_timing: id 3 | task 7364 | eval time = 737.11 ms / 2 tokens ( 737.11 ms per token, 1.36 tokens per second) 10.30.471.722 I slot print_timing: id 3 | task 7364 | total time = 2761.03 ms / 346 tokens 10.30.471.723 I slot print_timing: id 3 | task 7364 | graphs reused = 5899 10.30.471.723 I slot print_timing: id 3 | task 7364 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.471.795 I slot release: id 3 | task 7364 | stop processing: n_tokens = 2177, truncated = 0 10.30.509.767 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 10.30.509.822 I slot launch_slot_: id 0 | task 7370 | processing task, is_child = 0 10.30.509.946 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.920 MiB) 10.30.525.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 234.529 MiB) 10.30.525.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.617 MiB) 10.30.541.803 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 10.30.541.878 I slot launch_slot_: id 3 | task 7371 | processing task, is_child = 0 10.30.541.991 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 10.30.542.029 I slot launch_slot_: id 2 | task 7372 | processing task, is_child = 0 10.32.292.379 I slot print_timing: id 1 | task 7367 | prompt eval time = 775.04 ms / 353 tokens ( 2.20 ms per token, 455.46 tokens per second) 10.32.292.384 I slot print_timing: id 1 | task 7367 | eval time = 1782.61 ms / 2 tokens ( 1782.61 ms per token, 0.56 tokens per second) 10.32.292.384 I slot print_timing: id 1 | task 7367 | total time = 2557.65 ms / 355 tokens 10.32.292.385 I slot print_timing: id 1 | task 7367 | graphs reused = 5899 10.32.292.393 I slot print_timing: id 1 | task 7367 | graph reallocs = 0 / 0 (same size) / (changed size) 10.32.292.538 I slot release: id 1 | task 7367 | stop processing: n_tokens = 2186, truncated = 0 10.32.375.266 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 10.32.375.358 I slot launch_slot_: id 1 | task 7375 | processing task, is_child = 0 10.32.880.499 I slot print_timing: id 0 | task 7370 | prompt eval time = 1831.02 ms / 189 tokens ( 9.69 ms per token, 103.22 tokens per second) 10.32.880.502 I slot print_timing: id 0 | task 7370 | eval time = 507.43 ms / 2 tokens ( 507.43 ms per token, 1.97 tokens per second) 10.32.880.504 I slot print_timing: id 0 | task 7370 | total time = 2338.45 ms / 191 tokens 10.32.880.504 I slot print_timing: id 0 | task 7370 | graphs reused = 5899 10.32.880.505 I slot print_timing: id 0 | task 7370 | graph reallocs = 0 / 0 (same size) / (changed size) 10.32.880.637 I slot release: id 0 | task 7370 | stop processing: n_tokens = 2022, truncated = 0 10.32.881.810 I slot print_timing: id 2 | task 7372 | prompt eval time = 1830.43 ms / 441 tokens ( 4.15 ms per token, 240.93 tokens per second) 10.32.881.815 I slot print_timing: id 2 | task 7372 | eval time = 507.62 ms / 2 tokens ( 507.62 ms per token, 1.97 tokens per second) 10.32.881.815 I slot print_timing: id 2 | task 7372 | total time = 2338.05 ms / 443 tokens 10.32.881.816 I slot print_timing: id 2 | task 7372 | graphs reused = 5899 10.32.881.816 I slot print_timing: id 2 | task 7372 | graph reallocs = 0 / 0 (same size) / (changed size) 10.32.881.894 I slot release: id 2 | task 7372 | stop processing: n_tokens = 2273, truncated = 0 10.32.883.121 I slot print_timing: id 3 | task 7371 | prompt eval time = 1829.79 ms / 232 tokens ( 7.89 ms per token, 126.79 tokens per second) 10.32.883.123 I slot print_timing: id 3 | task 7371 | eval time = 507.86 ms / 2 tokens ( 507.86 ms per token, 1.97 tokens per second) 10.32.883.123 I slot print_timing: id 3 | task 7371 | total time = 2337.65 ms / 234 tokens 10.32.883.124 I slot print_timing: id 3 | task 7371 | graphs reused = 5899 10.32.883.124 I slot print_timing: id 3 | task 7371 | graph reallocs = 0 / 0 (same size) / (changed size) 10.32.883.175 I slot release: id 3 | task 7371 | stop processing: n_tokens = 2064, truncated = 0 10.32.920.716 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.906 10.32.920.777 I slot launch_slot_: id 0 | task 7378 | processing task, is_child = 0 10.32.920.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.667 MiB) 10.32.937.907 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.940 MiB) 10.32.955.745 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.806 10.32.955.821 I slot launch_slot_: id 2 | task 7379 | processing task, is_child = 0 10.32.955.935 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 10.32.955.970 I slot launch_slot_: id 3 | task 7380 | processing task, is_child = 0 10.34.526.394 I slot print_timing: id 1 | task 7375 | prompt eval time = 545.34 ms / 226 tokens ( 2.41 ms per token, 414.42 tokens per second) 10.34.526.399 I slot print_timing: id 1 | task 7375 | eval time = 1605.68 ms / 2 tokens ( 1605.68 ms per token, 0.62 tokens per second) 10.34.526.399 I slot print_timing: id 1 | task 7375 | total time = 2151.02 ms / 228 tokens 10.34.526.400 I slot print_timing: id 1 | task 7375 | graphs reused = 5899 10.34.526.400 I slot print_timing: id 1 | task 7375 | graph reallocs = 0 / 0 (same size) / (changed size) 10.34.526.557 I slot release: id 1 | task 7375 | stop processing: n_tokens = 2058, truncated = 0 10.34.609.344 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 10.34.609.405 I slot launch_slot_: id 1 | task 7383 | processing task, is_child = 0 10.35.227.853 I slot print_timing: id 0 | task 7378 | prompt eval time = 1651.16 ms / 280 tokens ( 5.90 ms per token, 169.58 tokens per second) 10.35.227.856 I slot print_timing: id 0 | task 7378 | eval time = 620.71 ms / 2 tokens ( 620.71 ms per token, 1.61 tokens per second) 10.35.227.857 I slot print_timing: id 0 | task 7378 | total time = 2271.87 ms / 282 tokens 10.35.227.857 I slot print_timing: id 0 | task 7378 | graphs reused = 5899 10.35.227.858 I slot print_timing: id 0 | task 7378 | graph reallocs = 0 / 0 (same size) / (changed size) 10.35.227.988 I slot release: id 0 | task 7378 | stop processing: n_tokens = 2113, truncated = 0 10.35.229.221 I slot print_timing: id 2 | task 7379 | prompt eval time = 1650.57 ms / 194 tokens ( 8.51 ms per token, 117.54 tokens per second) 10.35.229.227 I slot print_timing: id 2 | task 7379 | eval time = 620.94 ms / 2 tokens ( 620.94 ms per token, 1.61 tokens per second) 10.35.229.228 I slot print_timing: id 2 | task 7379 | total time = 2271.51 ms / 196 tokens 10.35.229.229 I slot print_timing: id 2 | task 7379 | graphs reused = 5899 10.35.229.229 I slot print_timing: id 2 | task 7379 | graph reallocs = 0 / 0 (same size) / (changed size) 10.35.229.297 I slot release: id 2 | task 7379 | stop processing: n_tokens = 2025, truncated = 0 10.35.230.544 I slot print_timing: id 3 | task 7380 | prompt eval time = 1648.69 ms / 318 tokens ( 5.18 ms per token, 192.88 tokens per second) 10.35.230.546 I slot print_timing: id 3 | task 7380 | eval time = 621.20 ms / 2 tokens ( 621.20 ms per token, 1.61 tokens per second) 10.35.230.547 I slot print_timing: id 3 | task 7380 | total time = 2269.90 ms / 320 tokens 10.35.230.547 I slot print_timing: id 3 | task 7380 | graphs reused = 5899 10.35.230.547 I slot print_timing: id 3 | task 7380 | graph reallocs = 0 / 0 (same size) / (changed size) 10.35.230.620 I slot release: id 3 | task 7380 | stop processing: n_tokens = 2151, truncated = 0 10.35.268.072 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.867 10.35.268.141 I slot launch_slot_: id 0 | task 7386 | processing task, is_child = 0 10.35.268.257 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.773 MiB) 10.35.286.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.518 MiB) 10.35.305.622 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.904 10.35.305.699 I slot launch_slot_: id 2 | task 7387 | processing task, is_child = 0 10.35.305.813 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 10.35.305.852 I slot launch_slot_: id 3 | task 7388 | processing task, is_child = 0 10.37.129.067 I slot print_timing: id 1 | task 7383 | prompt eval time = 658.66 ms / 289 tokens ( 2.28 ms per token, 438.77 tokens per second) 10.37.129.072 I slot print_timing: id 1 | task 7383 | eval time = 1860.99 ms / 2 tokens ( 1860.99 ms per token, 0.54 tokens per second) 10.37.129.072 I slot print_timing: id 1 | task 7383 | total time = 2519.65 ms / 291 tokens 10.37.129.073 I slot print_timing: id 1 | task 7383 | graphs reused = 5899 10.37.129.074 I slot print_timing: id 1 | task 7383 | graph reallocs = 0 / 0 (same size) / (changed size) 10.37.129.230 I slot release: id 1 | task 7383 | stop processing: n_tokens = 2121, truncated = 0 10.37.211.961 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 10.37.212.050 I slot launch_slot_: id 1 | task 7391 | processing task, is_child = 0 10.38.054.653 I slot print_timing: id 0 | task 7386 | prompt eval time = 1903.89 ms / 189 tokens ( 10.07 ms per token, 99.27 tokens per second) 10.38.054.659 I slot print_timing: id 0 | task 7386 | eval time = 844.90 ms / 2 tokens ( 844.90 ms per token, 1.18 tokens per second) 10.38.054.660 I slot print_timing: id 0 | task 7386 | total time = 2748.79 ms / 191 tokens 10.38.054.660 I slot print_timing: id 0 | task 7386 | graphs reused = 5899 10.38.054.661 I slot print_timing: id 0 | task 7386 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.054.791 I slot release: id 0 | task 7386 | stop processing: n_tokens = 2022, truncated = 0 10.38.055.995 I slot print_timing: id 2 | task 7387 | prompt eval time = 1903.24 ms / 387 tokens ( 4.92 ms per token, 203.34 tokens per second) 10.38.055.998 I slot print_timing: id 2 | task 7387 | eval time = 845.14 ms / 2 tokens ( 845.14 ms per token, 1.18 tokens per second) 10.38.055.999 I slot print_timing: id 2 | task 7387 | total time = 2748.38 ms / 389 tokens 10.38.055.999 I slot print_timing: id 2 | task 7387 | graphs reused = 5899 10.38.055.999 I slot print_timing: id 2 | task 7387 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.056.077 I slot release: id 2 | task 7387 | stop processing: n_tokens = 2219, truncated = 0 10.38.057.321 I slot print_timing: id 3 | task 7388 | prompt eval time = 1902.64 ms / 336 tokens ( 5.66 ms per token, 176.60 tokens per second) 10.38.057.324 I slot print_timing: id 3 | task 7388 | eval time = 845.37 ms / 2 tokens ( 845.37 ms per token, 1.18 tokens per second) 10.38.057.325 I slot print_timing: id 3 | task 7388 | total time = 2748.00 ms / 338 tokens 10.38.057.327 I slot print_timing: id 3 | task 7388 | graphs reused = 5899 10.38.057.327 I slot print_timing: id 3 | task 7388 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.057.378 I slot release: id 3 | task 7388 | stop processing: n_tokens = 2169, truncated = 0 10.38.098.395 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.906 10.38.098.456 I slot launch_slot_: id 0 | task 7394 | processing task, is_child = 0 10.38.098.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.518 MiB) 10.38.098.605 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.632 MiB) 10.38.117.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.547 MiB) 10.38.127.368 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.825 10.38.127.438 I slot launch_slot_: id 2 | task 7395 | processing task, is_child = 0 10.38.127.565 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.845 10.38.127.610 I slot launch_slot_: id 3 | task 7396 | processing task, is_child = 0 10.39.524.921 I slot print_timing: id 1 | task 7391 | prompt eval time = 886.33 ms / 399 tokens ( 2.22 ms per token, 450.17 tokens per second) 10.39.524.924 I slot print_timing: id 1 | task 7391 | eval time = 1426.53 ms / 2 tokens ( 1426.53 ms per token, 0.70 tokens per second) 10.39.524.924 I slot print_timing: id 1 | task 7391 | total time = 2312.86 ms / 401 tokens 10.39.524.925 I slot print_timing: id 1 | task 7391 | graphs reused = 5899 10.39.524.925 I slot print_timing: id 1 | task 7391 | graph reallocs = 0 / 0 (same size) / (changed size) 10.39.525.031 I slot release: id 1 | task 7391 | stop processing: n_tokens = 2231, truncated = 0 10.39.608.280 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 10.39.608.349 I slot launch_slot_: id 1 | task 7399 | processing task, is_child = 0 10.39.931.787 I slot print_timing: id 0 | task 7394 | prompt eval time = 1478.46 ms / 249 tokens ( 5.94 ms per token, 168.42 tokens per second) 10.39.931.790 I slot print_timing: id 0 | task 7394 | eval time = 325.71 ms / 2 tokens ( 325.71 ms per token, 3.07 tokens per second) 10.39.931.790 I slot print_timing: id 0 | task 7394 | total time = 1804.17 ms / 251 tokens 10.39.931.791 I slot print_timing: id 0 | task 7394 | graphs reused = 5899 10.39.931.791 I slot print_timing: id 0 | task 7394 | graph reallocs = 0 / 0 (same size) / (changed size) 10.39.931.932 I slot release: id 0 | task 7394 | stop processing: n_tokens = 2081, truncated = 0 10.39.933.035 I slot print_timing: id 2 | task 7395 | prompt eval time = 1477.80 ms / 212 tokens ( 6.97 ms per token, 143.46 tokens per second) 10.39.933.038 I slot print_timing: id 2 | task 7395 | eval time = 325.82 ms / 2 tokens ( 325.82 ms per token, 3.07 tokens per second) 10.39.933.039 I slot print_timing: id 2 | task 7395 | total time = 1803.63 ms / 214 tokens 10.39.933.039 I slot print_timing: id 2 | task 7395 | graphs reused = 5899 10.39.933.039 I slot print_timing: id 2 | task 7395 | graph reallocs = 0 / 0 (same size) / (changed size) 10.39.933.106 I slot release: id 2 | task 7395 | stop processing: n_tokens = 2044, truncated = 0 10.39.934.275 I slot print_timing: id 3 | task 7396 | prompt eval time = 1477.11 ms / 238 tokens ( 6.21 ms per token, 161.13 tokens per second) 10.39.934.277 I slot print_timing: id 3 | task 7396 | eval time = 326.00 ms / 2 tokens ( 326.00 ms per token, 3.07 tokens per second) 10.39.934.277 I slot print_timing: id 3 | task 7396 | total time = 1803.11 ms / 240 tokens 10.39.934.277 I slot print_timing: id 3 | task 7396 | graphs reused = 5899 10.39.934.278 I slot print_timing: id 3 | task 7396 | graph reallocs = 0 / 0 (same size) / (changed size) 10.39.934.336 I slot release: id 3 | task 7396 | stop processing: n_tokens = 2071, truncated = 0 10.39.972.576 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2081, t_last = 334409145747 10.39.972.709 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.290 MiB) 10.39.982.222 I slot launch_slot_: id 0 | task 7402 | processing task, is_child = 0 10.39.982.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 251.547 MiB) 10.39.982.348 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.801 MiB) 10.39.991.903 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.485 MiB) 10.40.001.432 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.885 10.40.001.508 I slot launch_slot_: id 3 | task 7403 | processing task, is_child = 0 10.40.001.628 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.896 10.40.001.662 I slot launch_slot_: id 2 | task 7404 | processing task, is_child = 0 10.42.541.331 I slot print_timing: id 1 | task 7399 | prompt eval time = 364.22 ms / 123 tokens ( 2.96 ms per token, 337.71 tokens per second) 10.42.541.334 I slot print_timing: id 1 | task 7399 | eval time = 2568.75 ms / 2 tokens ( 2568.75 ms per token, 0.39 tokens per second) 10.42.541.335 I slot print_timing: id 1 | task 7399 | total time = 2932.97 ms / 125 tokens 10.42.541.335 I slot print_timing: id 1 | task 7399 | graphs reused = 5899 10.42.541.336 I slot print_timing: id 1 | task 7399 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.541.411 I slot release: id 1 | task 7399 | stop processing: n_tokens = 1955, truncated = 0 10.43.184.641 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1955, t_last = 334411755224 10.43.184.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.644 MiB) 10.43.196.293 I slot launch_slot_: id 1 | task 7407 | processing task, is_child = 0 10.43.196.319 I slot print_timing: id 0 | task 7402 | prompt processing, n_tokens = 1264, progress = 0.86, t = 3.18 s / 397.45 tokens per second 10.45.692.309 I slot print_timing: id 2 | task 7404 | prompt eval time = 3181.29 ms / 172 tokens ( 18.50 ms per token, 54.07 tokens per second) 10.45.692.316 I slot print_timing: id 2 | task 7404 | eval time = 2509.03 ms / 2 tokens ( 2509.03 ms per token, 0.40 tokens per second) 10.45.692.317 I slot print_timing: id 2 | task 7404 | total time = 5690.32 ms / 174 tokens 10.45.692.317 I slot print_timing: id 2 | task 7404 | graphs reused = 5899 10.45.692.318 I slot print_timing: id 2 | task 7404 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.692.465 I slot release: id 2 | task 7404 | stop processing: n_tokens = 2004, truncated = 0 10.45.693.629 I slot print_timing: id 3 | task 7403 | prompt eval time = 3180.97 ms / 208 tokens ( 15.29 ms per token, 65.39 tokens per second) 10.45.693.633 I slot print_timing: id 3 | task 7403 | eval time = 2508.99 ms / 2 tokens ( 2508.99 ms per token, 0.40 tokens per second) 10.45.693.633 I slot print_timing: id 3 | task 7403 | total time = 5689.96 ms / 210 tokens 10.45.693.633 I slot print_timing: id 3 | task 7403 | graphs reused = 5899 10.45.693.634 I slot print_timing: id 3 | task 7403 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.693.699 I slot release: id 3 | task 7403 | stop processing: n_tokens = 2041, truncated = 0 10.45.693.723 I slot print_timing: id 0 | task 7402 | prompt processing, n_tokens = 1462, progress = 1.00, t = 5.69 s / 256.96 tokens per second 10.45.987.130 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2004, t_last = 334414906280 10.45.987.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.959 MiB) 10.45.987.331 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.744 MiB) 10.46.006.702 I slot launch_slot_: id 2 | task 7410 | processing task, is_child = 0 10.46.006.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 212.622 MiB) 10.46.006.830 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.521 MiB) 10.46.022.532 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2041, t_last = 334414907512 10.46.022.702 I slot launch_slot_: id 3 | task 7411 | processing task, is_child = 0 10.49.544.385 I slot print_timing: id 0 | task 7402 | prompt eval time = 5985.45 ms / 1466 tokens ( 4.08 ms per token, 244.93 tokens per second) 10.49.544.389 I slot print_timing: id 0 | task 7402 | eval time = 3557.25 ms / 2 tokens ( 3557.25 ms per token, 0.28 tokens per second) 10.49.544.390 I slot print_timing: id 0 | task 7402 | total time = 9542.70 ms / 1468 tokens 10.49.544.390 I slot print_timing: id 0 | task 7402 | graphs reused = 5899 10.49.544.391 I slot print_timing: id 0 | task 7402 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.544.523 I slot release: id 0 | task 7402 | stop processing: n_tokens = 1476, truncated = 0 10.49.544.558 I slot print_timing: id 1 | task 7407 | prompt processing, n_tokens = 1667, progress = 1.00, t = 6.35 s / 262.72 tokens per second 10.49.548.696 I slot print_timing: id 2 | task 7410 | prompt processing, n_tokens = 479, progress = 0.49, t = 3.52 s / 136.13 tokens per second 10.49.550.347 I slot print_timing: id 3 | task 7411 | prompt processing, n_tokens = 1021, progress = 0.67, t = 3.52 s / 290.17 tokens per second 10.50.727.863 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 334418758338 10.50.728.007 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.477 MiB) 10.50.736.984 I slot launch_slot_: id 0 | task 7414 | processing task, is_child = 0 10.50.737.231 I slot print_timing: id 2 | task 7410 | prompt processing, n_tokens = 848, progress = 0.85, t = 4.70 s / 180.34 tokens per second 10.50.738.911 I slot print_timing: id 3 | task 7411 | prompt processing, n_tokens = 1264, progress = 0.82, t = 4.70 s / 268.82 tokens per second 10.52.401.716 I slot print_timing: id 1 | task 7407 | prompt eval time = 7529.76 ms / 1671 tokens ( 4.51 ms per token, 221.92 tokens per second) 10.52.401.720 I slot print_timing: id 1 | task 7407 | eval time = 1673.86 ms / 2 tokens ( 1673.86 ms per token, 0.60 tokens per second) 10.52.401.720 I slot print_timing: id 1 | task 7407 | total time = 9203.62 ms / 1673 tokens 10.52.401.721 I slot print_timing: id 1 | task 7407 | graphs reused = 5899 10.52.401.721 I slot print_timing: id 1 | task 7407 | graph reallocs = 0 / 0 (same size) / (changed size) 10.52.401.866 I slot release: id 1 | task 7407 | stop processing: n_tokens = 1681, truncated = 0 10.52.405.573 I slot print_timing: id 2 | task 7410 | prompt processing, n_tokens = 991, progress = 1.00, t = 6.38 s / 155.42 tokens per second 10.52.407.586 I slot print_timing: id 3 | task 7411 | prompt processing, n_tokens = 1533, progress = 1.00, t = 6.38 s / 240.43 tokens per second 10.53.149.179 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1681, t_last = 334421615681 10.53.149.326 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.700 MiB) 10.53.159.784 I slot launch_slot_: id 1 | task 7417 | processing task, is_child = 0 10.54.330.794 I slot print_timing: id 2 | task 7410 | prompt eval time = 7123.32 ms / 995 tokens ( 7.16 ms per token, 139.68 tokens per second) 10.54.330.799 I slot print_timing: id 2 | task 7410 | eval time = 1183.04 ms / 2 tokens ( 1183.04 ms per token, 0.85 tokens per second) 10.54.330.799 I slot print_timing: id 2 | task 7410 | total time = 8306.35 ms / 997 tokens 10.54.330.800 I slot print_timing: id 2 | task 7410 | graphs reused = 5899 10.54.330.801 I slot print_timing: id 2 | task 7410 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.330.889 I slot release: id 2 | task 7410 | stop processing: n_tokens = 1005, truncated = 0 10.54.332.125 I slot print_timing: id 3 | task 7411 | prompt eval time = 7124.50 ms / 1537 tokens ( 4.64 ms per token, 215.73 tokens per second) 10.54.332.128 I slot print_timing: id 3 | task 7411 | eval time = 1182.95 ms / 2 tokens ( 1182.95 ms per token, 0.85 tokens per second) 10.54.332.129 I slot print_timing: id 3 | task 7411 | total time = 8307.45 ms / 1539 tokens 10.54.332.129 I slot print_timing: id 3 | task 7411 | graphs reused = 5899 10.54.332.129 I slot print_timing: id 3 | task 7411 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.332.230 I slot release: id 3 | task 7411 | stop processing: n_tokens = 1547, truncated = 0 10.54.332.248 I slot print_timing: id 0 | task 7414 | prompt processing, n_tokens = 981, progress = 1.00, t = 3.59 s / 273.05 tokens per second 10.55.120.607 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 10.55.120.721 I slot launch_slot_: id 2 | task 7420 | processing task, is_child = 0 10.55.120.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.382 MiB) 10.55.131.138 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1547, t_last = 334423546044 10.55.131.277 I slot launch_slot_: id 3 | task 7421 | processing task, is_child = 0 10.56.452.927 I slot print_timing: id 0 | task 7414 | prompt eval time = 4383.60 ms / 985 tokens ( 4.45 ms per token, 224.70 tokens per second) 10.56.452.933 I slot print_timing: id 0 | task 7414 | eval time = 1332.33 ms / 2 tokens ( 1332.33 ms per token, 0.75 tokens per second) 10.56.452.935 I slot print_timing: id 0 | task 7414 | total time = 5715.93 ms / 987 tokens 10.56.452.936 I slot print_timing: id 0 | task 7414 | graphs reused = 5899 10.56.452.937 I slot print_timing: id 0 | task 7414 | graph reallocs = 0 / 0 (same size) / (changed size) 10.56.453.022 I slot release: id 0 | task 7414 | stop processing: n_tokens = 995, truncated = 0 10.56.453.049 I slot print_timing: id 1 | task 7417 | prompt processing, n_tokens = 969, progress = 1.00, t = 3.29 s / 294.50 tokens per second 10.57.264.297 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 10.57.264.406 I slot launch_slot_: id 0 | task 7424 | processing task, is_child = 0 10.57.748.199 I slot print_timing: id 1 | task 7417 | prompt eval time = 4101.43 ms / 973 tokens ( 4.22 ms per token, 237.23 tokens per second) 10.57.748.203 I slot print_timing: id 1 | task 7417 | eval time = 485.25 ms / 2 tokens ( 485.25 ms per token, 2.06 tokens per second) 10.57.748.204 I slot print_timing: id 1 | task 7417 | total time = 4586.68 ms / 975 tokens 10.57.748.204 I slot print_timing: id 1 | task 7417 | graphs reused = 5899 10.57.748.205 I slot print_timing: id 1 | task 7417 | graph reallocs = 0 / 0 (same size) / (changed size) 10.57.748.279 I slot release: id 1 | task 7417 | stop processing: n_tokens = 983, truncated = 0 10.57.749.515 I slot print_timing: id 2 | task 7420 | prompt eval time = 2131.28 ms / 103 tokens ( 20.69 ms per token, 48.33 tokens per second) 10.57.749.517 I slot print_timing: id 2 | task 7420 | eval time = 485.23 ms / 2 tokens ( 485.23 ms per token, 2.06 tokens per second) 10.57.749.518 I slot print_timing: id 2 | task 7420 | total time = 2616.50 ms / 105 tokens 10.57.749.518 I slot print_timing: id 2 | task 7420 | graphs reused = 5899 10.57.749.518 I slot print_timing: id 2 | task 7420 | graph reallocs = 0 / 0 (same size) / (changed size) 10.57.749.557 I slot release: id 2 | task 7420 | stop processing: n_tokens = 988, truncated = 0 10.57.822.571 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 983, t_last = 334426962093 10.57.822.655 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.437 MiB) 10.57.829.362 I slot launch_slot_: id 1 | task 7427 | processing task, is_child = 0 10.57.829.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.515 MiB) 10.57.838.333 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 10.57.838.383 I slot launch_slot_: id 2 | task 7428 | processing task, is_child = 0 10.58.655.193 I slot print_timing: id 0 | task 7424 | prompt eval time = 556.90 ms / 93 tokens ( 5.99 ms per token, 167.00 tokens per second) 10.58.655.200 I slot print_timing: id 0 | task 7424 | eval time = 833.86 ms / 2 tokens ( 833.86 ms per token, 1.20 tokens per second) 10.58.655.202 I slot print_timing: id 0 | task 7424 | total time = 1390.76 ms / 95 tokens 10.58.655.203 I slot print_timing: id 0 | task 7424 | graphs reused = 5899 10.58.655.203 I slot print_timing: id 0 | task 7424 | graph reallocs = 0 / 0 (same size) / (changed size) 10.58.655.275 I slot release: id 0 | task 7424 | stop processing: n_tokens = 978, truncated = 0 10.58.656.450 I slot print_timing: id 3 | task 7421 | prompt eval time = 2687.83 ms / 958 tokens ( 2.81 ms per token, 356.42 tokens per second) 10.58.656.452 I slot print_timing: id 3 | task 7421 | eval time = 833.88 ms / 2 tokens ( 833.88 ms per token, 1.20 tokens per second) 10.58.656.452 I slot print_timing: id 3 | task 7421 | total time = 3521.71 ms / 960 tokens 10.58.656.452 I slot print_timing: id 3 | task 7421 | graphs reused = 5899 10.58.656.453 I slot print_timing: id 3 | task 7421 | graph reallocs = 0 / 0 (same size) / (changed size) 10.58.656.497 I slot release: id 3 | task 7421 | stop processing: n_tokens = 968, truncated = 0 10.59.438.009 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 978, t_last = 334427869088 10.59.438.140 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.063 MiB) 10.59.448.120 I slot launch_slot_: id 0 | task 7431 | processing task, is_child = 0 10.59.448.199 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 245.956 MiB) 10.59.454.149 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 968, t_last = 334427870311 10.59.454.266 I slot launch_slot_: id 3 | task 7432 | processing task, is_child = 0 11.03.235.167 I slot print_timing: id 2 | task 7428 | prompt eval time = 1599.38 ms / 98 tokens ( 16.32 ms per token, 61.27 tokens per second) 11.03.235.171 I slot print_timing: id 2 | task 7428 | eval time = 3797.17 ms / 2 tokens ( 3797.17 ms per token, 0.26 tokens per second) 11.03.235.172 I slot print_timing: id 2 | task 7428 | total time = 5396.55 ms / 100 tokens 11.03.235.172 I slot print_timing: id 2 | task 7428 | graphs reused = 5899 11.03.235.173 I slot print_timing: id 2 | task 7428 | graph reallocs = 0 / 0 (same size) / (changed size) 11.03.235.222 I slot release: id 2 | task 7428 | stop processing: n_tokens = 983, truncated = 0 11.03.235.251 I slot print_timing: id 0 | task 7431 | prompt processing, n_tokens = 1086, progress = 0.68, t = 3.77 s / 287.99 tokens per second 11.03.237.411 I slot print_timing: id 1 | task 7427 | prompt processing, n_tokens = 810, progress = 1.00, t = 5.39 s / 150.37 tokens per second 11.03.239.464 I slot print_timing: id 3 | task 7432 | prompt processing, n_tokens = 846, progress = 0.52, t = 3.77 s / 224.46 tokens per second 11.04.406.710 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 983, t_last = 334432449035 11.04.406.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.017 MiB) 11.04.415.996 I slot launch_slot_: id 2 | task 7435 | processing task, is_child = 0 11.04.416.006 I slot print_timing: id 0 | task 7431 | prompt processing, n_tokens = 1388, progress = 0.87, t = 4.95 s / 280.33 tokens per second 11.04.417.947 I slot print_timing: id 3 | task 7432 | prompt processing, n_tokens = 1131, progress = 0.69, t = 4.95 s / 228.51 tokens per second 11.07.331.892 I slot print_timing: id 1 | task 7427 | prompt eval time = 6568.30 ms / 814 tokens ( 8.07 ms per token, 123.93 tokens per second) 11.07.331.900 I slot print_timing: id 1 | task 7427 | eval time = 2925.18 ms / 2 tokens ( 2925.18 ms per token, 0.34 tokens per second) 11.07.331.901 I slot print_timing: id 1 | task 7427 | total time = 9493.49 ms / 816 tokens 11.07.331.901 I slot print_timing: id 1 | task 7427 | graphs reused = 5899 11.07.331.902 I slot print_timing: id 1 | task 7427 | graph reallocs = 0 / 0 (same size) / (changed size) 11.07.331.976 I slot release: id 1 | task 7427 | stop processing: n_tokens = 824, truncated = 0 11.07.332.008 I slot print_timing: id 0 | task 7431 | prompt processing, n_tokens = 1598, progress = 1.00, t = 7.88 s / 202.88 tokens per second 11.07.338.142 I slot print_timing: id 3 | task 7432 | prompt processing, n_tokens = 1388, progress = 0.84, t = 7.87 s / 176.26 tokens per second 11.08.406.074 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 334436545789 11.08.406.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.143 MiB) 11.08.413.851 I slot launch_slot_: id 1 | task 7438 | processing task, is_child = 0 11.08.414.049 I slot print_timing: id 2 | task 7435 | prompt processing, n_tokens = 1388, progress = 0.85, t = 3.99 s / 348.11 tokens per second 11.08.415.770 I slot print_timing: id 3 | task 7432 | prompt processing, n_tokens = 1643, progress = 1.00, t = 8.95 s / 183.60 tokens per second 11.11.009.215 I slot print_timing: id 0 | task 7431 | prompt eval time = 8951.79 ms / 1602 tokens ( 5.59 ms per token, 178.96 tokens per second) 11.11.009.219 I slot print_timing: id 0 | task 7431 | eval time = 2603.14 ms / 2 tokens ( 2603.14 ms per token, 0.38 tokens per second) 11.11.009.219 I slot print_timing: id 0 | task 7431 | total time = 11554.94 ms / 1604 tokens 11.11.009.220 I slot print_timing: id 0 | task 7431 | graphs reused = 5899 11.11.009.220 I slot print_timing: id 0 | task 7431 | graph reallocs = 0 / 0 (same size) / (changed size) 11.11.009.295 I slot release: id 0 | task 7431 | stop processing: n_tokens = 1612, truncated = 0 11.11.014.057 I slot print_timing: id 2 | task 7435 | prompt processing, n_tokens = 1626, progress = 1.00, t = 6.59 s / 246.72 tokens per second 11.11.556.331 I slot print_timing: id 3 | task 7432 | prompt eval time = 11554.34 ms / 1647 tokens ( 7.02 ms per token, 142.54 tokens per second) 11.11.556.338 I slot print_timing: id 3 | task 7432 | eval time = 545.82 ms / 2 tokens ( 545.82 ms per token, 1.83 tokens per second) 11.11.556.339 I slot print_timing: id 3 | task 7432 | total time = 12100.16 ms / 1649 tokens 11.11.556.339 I slot print_timing: id 3 | task 7432 | graphs reused = 5899 11.11.556.340 I slot print_timing: id 3 | task 7432 | graph reallocs = 0 / 0 (same size) / (changed size) 11.11.556.446 I slot release: id 3 | task 7432 | stop processing: n_tokens = 1657, truncated = 0 11.11.556.464 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.814 (> 0.100 thold), f_keep = 0.883 11.11.556.583 I slot launch_slot_: id 0 | task 7441 | processing task, is_child = 0 11.11.556.729 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.095 MiB) 11.11.566.845 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1657, t_last = 334440770261 11.11.566.983 I slot launch_slot_: id 3 | task 7442 | processing task, is_child = 0 11.11.568.763 I slot print_timing: id 1 | task 7438 | prompt processing, n_tokens = 1388, progress = 0.84, t = 3.14 s / 442.01 tokens per second 11.13.297.477 I slot print_timing: id 2 | task 7435 | prompt eval time = 7137.51 ms / 1630 tokens ( 4.38 ms per token, 228.37 tokens per second) 11.13.297.483 I slot print_timing: id 2 | task 7435 | eval time = 1742.24 ms / 2 tokens ( 1742.24 ms per token, 0.57 tokens per second) 11.13.297.483 I slot print_timing: id 2 | task 7435 | total time = 8879.76 ms / 1632 tokens 11.13.297.484 I slot print_timing: id 2 | task 7435 | graphs reused = 5899 11.13.297.484 I slot print_timing: id 2 | task 7435 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.297.605 I slot release: id 2 | task 7435 | stop processing: n_tokens = 1640, truncated = 0 11.13.301.848 I slot print_timing: id 1 | task 7438 | prompt processing, n_tokens = 1652, progress = 1.00, t = 4.88 s / 338.35 tokens per second 11.14.088.820 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1640, t_last = 334442511420 11.14.088.956 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 345.222 MiB) 11.14.099.686 I slot launch_slot_: id 2 | task 7445 | processing task, is_child = 0 11.15.005.383 I slot print_timing: id 0 | task 7441 | prompt eval time = 2520.63 ms / 325 tokens ( 7.76 ms per token, 128.94 tokens per second) 11.15.005.386 I slot print_timing: id 0 | task 7441 | eval time = 917.76 ms / 2 tokens ( 917.76 ms per token, 1.09 tokens per second) 11.15.005.386 I slot print_timing: id 0 | task 7441 | total time = 3438.39 ms / 327 tokens 11.15.005.387 I slot print_timing: id 0 | task 7441 | graphs reused = 5899 11.15.005.387 I slot print_timing: id 0 | task 7441 | graph reallocs = 0 / 0 (same size) / (changed size) 11.15.005.489 I slot release: id 0 | task 7441 | stop processing: n_tokens = 1750, truncated = 0 11.15.006.604 I slot print_timing: id 1 | task 7438 | prompt eval time = 5674.95 ms / 1656 tokens ( 3.43 ms per token, 291.81 tokens per second) 11.15.006.608 I slot print_timing: id 1 | task 7438 | eval time = 917.79 ms / 2 tokens ( 917.79 ms per token, 1.09 tokens per second) 11.15.006.609 I slot print_timing: id 1 | task 7438 | total time = 6592.74 ms / 1658 tokens 11.15.006.609 I slot print_timing: id 1 | task 7438 | graphs reused = 5899 11.15.006.610 I slot print_timing: id 1 | task 7438 | graph reallocs = 0 / 0 (same size) / (changed size) 11.15.006.670 I slot release: id 1 | task 7438 | stop processing: n_tokens = 1666, truncated = 0 11.15.008.378 I slot print_timing: id 3 | task 7442 | prompt processing, n_tokens = 831, progress = 1.00, t = 3.43 s / 242.01 tokens per second 11.15.737.396 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1750, t_last = 334444219304 11.15.737.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 348.598 MiB) 11.15.750.508 I slot launch_slot_: id 0 | task 7448 | processing task, is_child = 0 11.15.750.612 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 351.024 MiB) 11.15.757.441 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1666, t_last = 334444220484 11.15.757.587 I slot launch_slot_: id 1 | task 7449 | processing task, is_child = 0 11.17.268.348 I slot print_timing: id 3 | task 7442 | prompt eval time = 4166.91 ms / 835 tokens ( 4.99 ms per token, 200.39 tokens per second) 11.17.268.354 I slot print_timing: id 3 | task 7442 | eval time = 1530.94 ms / 2 tokens ( 1530.94 ms per token, 0.65 tokens per second) 11.17.268.355 I slot print_timing: id 3 | task 7442 | total time = 5697.86 ms / 837 tokens 11.17.268.355 I slot print_timing: id 3 | task 7442 | graphs reused = 5899 11.17.268.356 I slot print_timing: id 3 | task 7442 | graph reallocs = 0 / 0 (same size) / (changed size) 11.17.268.437 I slot release: id 3 | task 7442 | stop processing: n_tokens = 845, truncated = 0 11.17.272.358 I slot print_timing: id 2 | task 7445 | prompt processing, n_tokens = 858, progress = 1.00, t = 3.17 s / 270.87 tokens per second 11.18.735.190 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 334446482251 11.18.743.434 I slot launch_slot_: id 3 | task 7452 | processing task, is_child = 0 11.20.008.340 I slot print_timing: id 2 | task 7445 | prompt eval time = 4635.48 ms / 862 tokens ( 5.38 ms per token, 185.96 tokens per second) 11.20.008.343 I slot print_timing: id 2 | task 7445 | eval time = 1273.15 ms / 2 tokens ( 1273.15 ms per token, 0.79 tokens per second) 11.20.008.344 I slot print_timing: id 2 | task 7445 | total time = 5908.63 ms / 864 tokens 11.20.008.344 I slot print_timing: id 2 | task 7445 | graphs reused = 5899 11.20.008.345 I slot print_timing: id 2 | task 7445 | graph reallocs = 0 / 0 (same size) / (changed size) 11.20.008.390 I slot release: id 2 | task 7445 | stop processing: n_tokens = 872, truncated = 0 11.20.008.405 I slot print_timing: id 0 | task 7448 | prompt processing, n_tokens = 836, progress = 1.00, t = 4.25 s / 196.72 tokens per second 11.20.011.342 I slot print_timing: id 1 | task 7449 | prompt processing, n_tokens = 855, progress = 1.00, t = 4.25 s / 201.20 tokens per second 11.20.690.587 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 872, t_last = 334449222203 11.20.690.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 398.525 MiB) 11.20.698.218 I slot launch_slot_: id 2 | task 7455 | processing task, is_child = 0 11.21.543.266 I slot print_timing: id 0 | task 7448 | prompt eval time = 4931.62 ms / 840 tokens ( 5.87 ms per token, 170.33 tokens per second) 11.21.543.272 I slot print_timing: id 0 | task 7448 | eval time = 854.05 ms / 2 tokens ( 854.05 ms per token, 1.17 tokens per second) 11.21.543.273 I slot print_timing: id 0 | task 7448 | total time = 5785.67 ms / 842 tokens 11.21.543.273 I slot print_timing: id 0 | task 7448 | graphs reused = 5899 11.21.543.273 I slot print_timing: id 0 | task 7448 | graph reallocs = 0 / 0 (same size) / (changed size) 11.21.543.319 I slot release: id 0 | task 7448 | stop processing: n_tokens = 850, truncated = 0 11.21.544.454 I slot print_timing: id 1 | task 7449 | prompt eval time = 4932.73 ms / 859 tokens ( 5.74 ms per token, 174.14 tokens per second) 11.21.544.457 I slot print_timing: id 1 | task 7449 | eval time = 853.87 ms / 2 tokens ( 853.87 ms per token, 1.17 tokens per second) 11.21.544.457 I slot print_timing: id 1 | task 7449 | total time = 5786.60 ms / 861 tokens 11.21.544.457 I slot print_timing: id 1 | task 7449 | graphs reused = 5899 11.21.544.458 I slot print_timing: id 1 | task 7449 | graph reallocs = 0 / 0 (same size) / (changed size) 11.21.544.495 I slot release: id 1 | task 7449 | stop processing: n_tokens = 869, truncated = 0 11.22.269.526 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 334450757132 11.22.277.738 I slot launch_slot_: id 0 | task 7458 | processing task, is_child = 0 11.22.277.814 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 396.204 MiB) 11.22.283.476 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 334450758308 11.22.283.589 I slot launch_slot_: id 1 | task 7459 | processing task, is_child = 0 11.23.358.535 I slot print_timing: id 3 | task 7452 | prompt eval time = 3522.74 ms / 884 tokens ( 3.98 ms per token, 250.94 tokens per second) 11.23.358.539 I slot print_timing: id 3 | task 7452 | eval time = 1089.02 ms / 2 tokens ( 1089.02 ms per token, 0.92 tokens per second) 11.23.358.540 I slot print_timing: id 3 | task 7452 | total time = 4611.75 ms / 886 tokens 11.23.358.540 I slot print_timing: id 3 | task 7452 | graphs reused = 5899 11.23.358.541 I slot print_timing: id 3 | task 7452 | graph reallocs = 0 / 0 (same size) / (changed size) 11.23.358.606 I slot release: id 3 | task 7452 | stop processing: n_tokens = 894, truncated = 0 11.24.856.913 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 334452572419 11.24.857.037 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 401.585 MiB) 11.24.866.645 I slot launch_slot_: id 3 | task 7462 | processing task, is_child = 0 11.25.749.928 I slot print_timing: id 2 | task 7455 | prompt eval time = 4158.68 ms / 762 tokens ( 5.46 ms per token, 183.23 tokens per second) 11.25.749.931 I slot print_timing: id 2 | task 7455 | eval time = 893.02 ms / 2 tokens ( 893.02 ms per token, 1.12 tokens per second) 11.25.749.931 I slot print_timing: id 2 | task 7455 | total time = 5051.70 ms / 764 tokens 11.25.749.932 I slot print_timing: id 2 | task 7455 | graphs reused = 5899 11.25.749.932 I slot print_timing: id 2 | task 7455 | graph reallocs = 0 / 0 (same size) / (changed size) 11.25.750.001 I slot release: id 2 | task 7455 | stop processing: n_tokens = 772, truncated = 0 11.25.750.022 I slot print_timing: id 0 | task 7458 | prompt processing, n_tokens = 684, progress = 0.99, t = 3.47 s / 197.39 tokens per second 11.25.753.284 I slot print_timing: id 1 | task 7459 | prompt processing, n_tokens = 729, progress = 0.99, t = 3.47 s / 210.39 tokens per second 11.26.477.694 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 334454963815 11.26.486.654 I slot launch_slot_: id 2 | task 7465 | processing task, is_child = 0 11.27.124.094 I slot print_timing: id 0 | task 7458 | prompt eval time = 4192.80 ms / 688 tokens ( 6.09 ms per token, 164.09 tokens per second) 11.27.124.097 I slot print_timing: id 0 | task 7458 | eval time = 647.68 ms / 2 tokens ( 647.68 ms per token, 1.54 tokens per second) 11.27.124.097 I slot print_timing: id 0 | task 7458 | total time = 4840.49 ms / 690 tokens 11.27.124.098 I slot print_timing: id 0 | task 7458 | graphs reused = 5899 11.27.124.098 I slot print_timing: id 0 | task 7458 | graph reallocs = 0 / 0 (same size) / (changed size) 11.27.124.144 I slot release: id 0 | task 7458 | stop processing: n_tokens = 698, truncated = 0 11.27.125.301 I slot print_timing: id 1 | task 7459 | prompt eval time = 4193.90 ms / 733 tokens ( 5.72 ms per token, 174.78 tokens per second) 11.27.125.304 I slot print_timing: id 1 | task 7459 | eval time = 647.61 ms / 2 tokens ( 647.61 ms per token, 1.54 tokens per second) 11.27.125.304 I slot print_timing: id 1 | task 7459 | total time = 4841.51 ms / 735 tokens 11.27.125.305 I slot print_timing: id 1 | task 7459 | graphs reused = 5899 11.27.125.305 I slot print_timing: id 1 | task 7459 | graph reallocs = 0 / 0 (same size) / (changed size) 11.27.125.345 I slot release: id 1 | task 7459 | stop processing: n_tokens = 743, truncated = 0 11.28.167.930 I slot print_timing: id 3 | task 7462 | prompt eval time = 3029.78 ms / 707 tokens ( 4.29 ms per token, 233.35 tokens per second) 11.28.167.933 I slot print_timing: id 3 | task 7462 | eval time = 268.18 ms / 2 tokens ( 268.18 ms per token, 3.73 tokens per second) 11.28.167.933 I slot print_timing: id 3 | task 7462 | total time = 3297.95 ms / 709 tokens 11.28.167.934 I slot print_timing: id 3 | task 7462 | graphs reused = 5899 11.28.167.934 I slot print_timing: id 3 | task 7462 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.167.995 I slot release: id 3 | task 7462 | stop processing: n_tokens = 717, truncated = 0 11.28.229.618 I slot print_timing: id 2 | task 7465 | prompt eval time = 1721.92 ms / 673 tokens ( 2.56 ms per token, 390.84 tokens per second) 11.28.229.623 I slot print_timing: id 2 | task 7465 | eval time = 21.04 ms / 2 tokens ( 21.04 ms per token, 47.54 tokens per second) 11.28.229.624 I slot print_timing: id 2 | task 7465 | total time = 1742.95 ms / 675 tokens 11.28.229.624 I slot print_timing: id 2 | task 7465 | graphs reused = 5899 11.28.229.625 I slot print_timing: id 2 | task 7465 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.229.648 I slot release: id 2 | task 7465 | stop processing: n_tokens = 683, truncated = 0 11.30.774.327 I srv operator(): operator(): cleaning up before exit...