/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/cc1b0bde185f/Spark-X2.6-4B-IQ3_XXS.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.043.280 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.043.336 I srv llama_server: initializing ... 0.00.043.341 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.043.426 I srv init_listene: The UI is disabled 0.00.043.427 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.043.461 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) 0.00.045.133 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/cc1b0bde185f/Spark-X2.6-4B-IQ3_XXS.gguf' 0.00.444.205 I cmn init: llama threadpool init, n_threads = 8 0.00.538.339 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.00.546.545 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.546.556 I srv llama_server: model loaded 0.00.546.558 I srv llama_server: listening on http://127.0.0.1:8091 0.31.081.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.081.361 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.31.081.362 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.081.394 I slot launch_slot_: id 1 | task 1 | processing task, is_child = 0 0.31.081.395 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.081.420 I slot launch_slot_: id 2 | task 3 | processing task, is_child = 0 0.31.081.421 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.31.081.451 I slot launch_slot_: id 3 | task 2 | processing task, is_child = 0 0.32.270.716 I slot print_timing: id 0 | task 0 | prompt eval time = 1151.42 ms / 134 tokens ( 8.59 ms per token, 116.38 tokens per second) 0.32.270.721 I slot print_timing: id 0 | task 0 | eval time = 37.84 ms / 2 tokens ( 37.84 ms per token, 26.43 tokens per second) 0.32.270.721 I slot print_timing: id 0 | task 0 | total time = 1189.26 ms / 136 tokens 0.32.270.722 I slot print_timing: id 0 | task 0 | graphs reused = 1 0.32.270.722 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.270.743 I slot release: id 0 | task 0 | stop processing: n_tokens = 135, truncated = 0 0.32.271.840 I slot print_timing: id 1 | task 1 | prompt eval time = 1152.67 ms / 128 tokens ( 9.01 ms per token, 111.05 tokens per second) 0.32.271.844 I slot print_timing: id 1 | task 1 | eval time = 37.70 ms / 2 tokens ( 37.70 ms per token, 26.52 tokens per second) 0.32.271.845 I slot print_timing: id 1 | task 1 | total time = 1190.38 ms / 130 tokens 0.32.271.846 I slot print_timing: id 1 | task 1 | graphs reused = 1 0.32.271.846 I slot print_timing: id 1 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.271.856 I slot release: id 1 | task 1 | stop processing: n_tokens = 129, truncated = 0 0.32.272.932 I slot print_timing: id 2 | task 3 | prompt eval time = 1153.86 ms / 142 tokens ( 8.13 ms per token, 123.07 tokens per second) 0.32.272.934 I slot print_timing: id 2 | task 3 | eval time = 37.61 ms / 2 tokens ( 37.61 ms per token, 26.59 tokens per second) 0.32.272.934 I slot print_timing: id 2 | task 3 | total time = 1191.46 ms / 144 tokens 0.32.272.934 I slot print_timing: id 2 | task 3 | graphs reused = 1 0.32.272.935 I slot print_timing: id 2 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.272.945 I slot release: id 2 | task 3 | stop processing: n_tokens = 143, truncated = 0 0.32.274.020 I slot print_timing: id 3 | task 2 | prompt eval time = 1155.05 ms / 130 tokens ( 8.88 ms per token, 112.55 tokens per second) 0.32.274.024 I slot print_timing: id 3 | task 2 | eval time = 37.50 ms / 2 tokens ( 37.50 ms per token, 26.67 tokens per second) 0.32.274.025 I slot print_timing: id 3 | task 2 | total time = 1192.55 ms / 132 tokens 0.32.274.025 I slot print_timing: id 3 | task 2 | graphs reused = 1 0.32.274.025 I slot print_timing: id 3 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.274.031 I slot release: id 3 | task 2 | stop processing: n_tokens = 131, truncated = 0 0.32.278.964 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.319 (> 0.100 thold), f_keep = 0.281 0.32.281.630 I slot launch_slot_: id 0 | task 8 | processing task, is_child = 0 0.32.289.179 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 0.32.289.250 I slot launch_slot_: id 1 | task 9 | processing task, is_child = 0 0.32.289.302 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.259 0.32.289.356 I slot launch_slot_: id 2 | task 10 | processing task, is_child = 0 0.32.289.381 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.282 0.32.289.435 I slot launch_slot_: id 3 | task 11 | processing task, is_child = 0 0.33.679.847 I slot print_timing: id 0 | task 8 | prompt eval time = 1352.86 ms / 110 tokens ( 12.30 ms per token, 81.31 tokens per second) 0.33.679.849 I slot print_timing: id 0 | task 8 | eval time = 37.53 ms / 2 tokens ( 37.53 ms per token, 26.64 tokens per second) 0.33.679.850 I slot print_timing: id 0 | task 8 | total time = 1390.40 ms / 112 tokens 0.33.679.851 I slot print_timing: id 0 | task 8 | graphs reused = 1 0.33.679.851 I slot print_timing: id 0 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.679.869 I slot release: id 0 | task 8 | stop processing: n_tokens = 120, truncated = 0 0.33.680.986 I slot print_timing: id 1 | task 9 | prompt eval time = 1353.79 ms / 159 tokens ( 8.51 ms per token, 117.45 tokens per second) 0.33.680.987 I slot print_timing: id 1 | task 9 | eval time = 37.57 ms / 2 tokens ( 37.57 ms per token, 26.62 tokens per second) 0.33.680.987 I slot print_timing: id 1 | task 9 | total time = 1391.35 ms / 161 tokens 0.33.680.988 I slot print_timing: id 1 | task 9 | graphs reused = 1 0.33.680.988 I slot print_timing: id 1 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.681.000 I slot release: id 1 | task 9 | stop processing: n_tokens = 169, truncated = 0 0.33.682.089 I slot print_timing: id 2 | task 10 | prompt eval time = 1354.76 ms / 164 tokens ( 8.26 ms per token, 121.05 tokens per second) 0.33.682.093 I slot print_timing: id 2 | task 10 | eval time = 37.53 ms / 2 tokens ( 37.53 ms per token, 26.65 tokens per second) 0.33.682.093 I slot print_timing: id 2 | task 10 | total time = 1392.29 ms / 166 tokens 0.33.682.094 I slot print_timing: id 2 | task 10 | graphs reused = 1 0.33.682.094 I slot print_timing: id 2 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.682.105 I slot release: id 2 | task 10 | stop processing: n_tokens = 174, truncated = 0 0.33.683.203 I slot print_timing: id 3 | task 11 | prompt eval time = 1355.67 ms / 204 tokens ( 6.65 ms per token, 150.48 tokens per second) 0.33.683.205 I slot print_timing: id 3 | task 11 | eval time = 37.56 ms / 2 tokens ( 37.56 ms per token, 26.62 tokens per second) 0.33.683.205 I slot print_timing: id 3 | task 11 | total time = 1393.23 ms / 206 tokens 0.33.683.205 I slot print_timing: id 3 | task 11 | graphs reused = 1 0.33.683.205 I slot print_timing: id 3 | task 11 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.683.217 I slot release: id 3 | task 11 | stop processing: n_tokens = 214, truncated = 0 0.33.684.258 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.297 (> 0.100 thold), f_keep = 0.317 0.33.686.082 I slot launch_slot_: id 0 | task 16 | processing task, is_child = 0 0.33.696.559 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.219 0.33.696.638 I slot launch_slot_: id 1 | task 17 | processing task, is_child = 0 0.33.696.695 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.213 0.33.696.754 I slot launch_slot_: id 2 | task 18 | processing task, is_child = 0 0.33.696.783 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.287 (> 0.100 thold), f_keep = 0.173 0.33.696.855 I slot launch_slot_: id 3 | task 19 | processing task, is_child = 0 0.34.815.965 I slot print_timing: id 0 | task 16 | prompt eval time = 1081.54 ms / 119 tokens ( 9.09 ms per token, 110.03 tokens per second) 0.34.815.966 I slot print_timing: id 0 | task 16 | eval time = 37.56 ms / 2 tokens ( 37.56 ms per token, 26.62 tokens per second) 0.34.815.967 I slot print_timing: id 0 | task 16 | total time = 1119.10 ms / 121 tokens 0.34.815.967 I slot print_timing: id 0 | task 16 | graphs reused = 1 0.34.815.968 I slot print_timing: id 0 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.815.985 I slot release: id 0 | task 16 | stop processing: n_tokens = 129, truncated = 0 0.34.817.117 I slot print_timing: id 1 | task 17 | prompt eval time = 1082.49 ms / 127 tokens ( 8.52 ms per token, 117.32 tokens per second) 0.34.817.118 I slot print_timing: id 1 | task 17 | eval time = 37.64 ms / 2 tokens ( 37.64 ms per token, 26.56 tokens per second) 0.34.817.119 I slot print_timing: id 1 | task 17 | total time = 1120.13 ms / 129 tokens 0.34.817.119 I slot print_timing: id 1 | task 17 | graphs reused = 1 0.34.817.119 I slot print_timing: id 1 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.817.134 I slot release: id 1 | task 17 | stop processing: n_tokens = 137, truncated = 0 0.34.818.232 I slot print_timing: id 2 | task 18 | prompt eval time = 1083.41 ms / 151 tokens ( 7.17 ms per token, 139.38 tokens per second) 0.34.818.234 I slot print_timing: id 2 | task 18 | eval time = 37.73 ms / 2 tokens ( 37.73 ms per token, 26.50 tokens per second) 0.34.818.235 I slot print_timing: id 2 | task 18 | total time = 1121.14 ms / 153 tokens 0.34.818.235 I slot print_timing: id 2 | task 18 | graphs reused = 1 0.34.818.235 I slot print_timing: id 2 | task 18 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.818.247 I slot release: id 2 | task 18 | stop processing: n_tokens = 161, truncated = 0 0.34.819.351 I slot print_timing: id 3 | task 19 | prompt eval time = 1084.36 ms / 120 tokens ( 9.04 ms per token, 110.66 tokens per second) 0.34.819.352 I slot print_timing: id 3 | task 19 | eval time = 37.78 ms / 2 tokens ( 37.78 ms per token, 26.47 tokens per second) 0.34.819.353 I slot print_timing: id 3 | task 19 | total time = 1122.13 ms / 122 tokens 0.34.819.354 I slot print_timing: id 3 | task 19 | graphs reused = 1 0.34.819.354 I slot print_timing: id 3 | task 19 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.819.364 I slot release: id 3 | task 19 | stop processing: n_tokens = 130, truncated = 0 0.34.820.103 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.287 0.34.821.172 I slot launch_slot_: id 0 | task 24 | processing task, is_child = 0 0.34.829.335 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.270 0.34.829.411 I slot launch_slot_: id 1 | task 25 | processing task, is_child = 0 0.34.829.461 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.230 0.34.829.517 I slot launch_slot_: id 2 | task 26 | processing task, is_child = 0 0.34.829.542 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 0.34.829.596 I slot launch_slot_: id 3 | task 27 | processing task, is_child = 0 0.36.118.158 I slot print_timing: id 0 | task 24 | prompt eval time = 1250.40 ms / 184 tokens ( 6.80 ms per token, 147.15 tokens per second) 0.36.118.160 I slot print_timing: id 0 | task 24 | eval time = 38.16 ms / 2 tokens ( 38.16 ms per token, 26.21 tokens per second) 0.36.118.160 I slot print_timing: id 0 | task 24 | total time = 1288.55 ms / 186 tokens 0.36.118.161 I slot print_timing: id 0 | task 24 | graphs reused = 1 0.36.118.161 I slot print_timing: id 0 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.118.182 I slot release: id 0 | task 24 | stop processing: n_tokens = 194, truncated = 0 0.36.119.295 I slot print_timing: id 1 | task 25 | prompt eval time = 1251.51 ms / 145 tokens ( 8.63 ms per token, 115.86 tokens per second) 0.36.119.296 I slot print_timing: id 1 | task 25 | eval time = 38.06 ms / 2 tokens ( 38.06 ms per token, 26.27 tokens per second) 0.36.119.297 I slot print_timing: id 1 | task 25 | total time = 1289.57 ms / 147 tokens 0.36.119.297 I slot print_timing: id 1 | task 25 | graphs reused = 1 0.36.119.297 I slot print_timing: id 1 | task 25 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.119.314 I slot release: id 1 | task 25 | stop processing: n_tokens = 155, truncated = 0 0.36.120.405 I slot print_timing: id 2 | task 26 | prompt eval time = 1252.60 ms / 138 tokens ( 9.08 ms per token, 110.17 tokens per second) 0.36.120.406 I slot print_timing: id 2 | task 26 | eval time = 37.97 ms / 2 tokens ( 37.97 ms per token, 26.34 tokens per second) 0.36.120.407 I slot print_timing: id 2 | task 26 | total time = 1290.57 ms / 140 tokens 0.36.120.407 I slot print_timing: id 2 | task 26 | graphs reused = 1 0.36.120.407 I slot print_timing: id 2 | task 26 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.120.416 I slot release: id 2 | task 26 | stop processing: n_tokens = 148, truncated = 0 0.36.121.521 I slot print_timing: id 3 | task 27 | prompt eval time = 1253.75 ms / 122 tokens ( 10.28 ms per token, 97.31 tokens per second) 0.36.121.523 I slot print_timing: id 3 | task 27 | eval time = 37.82 ms / 2 tokens ( 37.82 ms per token, 26.44 tokens per second) 0.36.121.523 I slot print_timing: id 3 | task 27 | total time = 1291.58 ms / 124 tokens 0.36.121.523 I slot print_timing: id 3 | task 27 | graphs reused = 1 0.36.121.523 I slot print_timing: id 3 | task 27 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.121.531 I slot release: id 3 | task 27 | stop processing: n_tokens = 132, truncated = 0 0.36.123.246 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.191 0.36.127.634 I slot launch_slot_: id 0 | task 32 | processing task, is_child = 0 0.36.134.385 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 0.36.134.449 I slot launch_slot_: id 1 | task 33 | processing task, is_child = 0 0.36.134.499 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.250 0.36.134.556 I slot launch_slot_: id 2 | task 34 | processing task, is_child = 0 0.36.134.583 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 0.36.135.112 I slot launch_slot_: id 3 | task 35 | processing task, is_child = 0 0.37.408.123 I slot print_timing: id 0 | task 32 | prompt eval time = 1235.31 ms / 133 tokens ( 9.29 ms per token, 107.66 tokens per second) 0.37.408.126 I slot print_timing: id 0 | task 32 | eval time = 37.68 ms / 2 tokens ( 37.68 ms per token, 26.54 tokens per second) 0.37.408.126 I slot print_timing: id 0 | task 32 | total time = 1272.99 ms / 135 tokens 0.37.408.126 I slot print_timing: id 0 | task 32 | graphs reused = 1 0.37.408.127 I slot print_timing: id 0 | task 32 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.408.146 I slot release: id 0 | task 32 | stop processing: n_tokens = 143, truncated = 0 0.37.409.275 I slot print_timing: id 1 | task 33 | prompt eval time = 1236.29 ms / 149 tokens ( 8.30 ms per token, 120.52 tokens per second) 0.37.409.276 I slot print_timing: id 1 | task 33 | eval time = 37.74 ms / 2 tokens ( 37.74 ms per token, 26.50 tokens per second) 0.37.409.277 I slot print_timing: id 1 | task 33 | total time = 1274.03 ms / 151 tokens 0.37.409.277 I slot print_timing: id 1 | task 33 | graphs reused = 1 0.37.409.277 I slot print_timing: id 1 | task 33 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.409.289 I slot release: id 1 | task 33 | stop processing: n_tokens = 159, truncated = 0 0.37.410.389 I slot print_timing: id 2 | task 34 | prompt eval time = 1237.39 ms / 181 tokens ( 6.84 ms per token, 146.28 tokens per second) 0.37.410.391 I slot print_timing: id 2 | task 34 | eval time = 37.64 ms / 2 tokens ( 37.64 ms per token, 26.57 tokens per second) 0.37.410.391 I slot print_timing: id 2 | task 34 | total time = 1275.03 ms / 183 tokens 0.37.410.391 I slot print_timing: id 2 | task 34 | graphs reused = 1 0.37.410.392 I slot print_timing: id 2 | task 34 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.410.407 I slot release: id 2 | task 34 | stop processing: n_tokens = 191, truncated = 0 0.37.411.519 I slot print_timing: id 3 | task 35 | prompt eval time = 1238.52 ms / 127 tokens ( 9.75 ms per token, 102.54 tokens per second) 0.37.411.521 I slot print_timing: id 3 | task 35 | eval time = 37.53 ms / 2 tokens ( 37.53 ms per token, 26.65 tokens per second) 0.37.411.521 I slot print_timing: id 3 | task 35 | total time = 1276.05 ms / 129 tokens 0.37.411.521 I slot print_timing: id 3 | task 35 | graphs reused = 1 0.37.411.521 I slot print_timing: id 3 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.411.538 I slot release: id 3 | task 35 | stop processing: n_tokens = 137, truncated = 0 0.37.412.634 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.298 (> 0.100 thold), f_keep = 0.259 0.37.415.676 I slot launch_slot_: id 0 | task 40 | processing task, is_child = 0 0.37.424.971 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 0.37.425.044 I slot launch_slot_: id 2 | task 41 | processing task, is_child = 0 0.37.425.093 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 0.37.425.152 I slot launch_slot_: id 1 | task 42 | processing task, is_child = 0 0.37.425.177 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 0.37.425.228 I slot launch_slot_: id 3 | task 43 | processing task, is_child = 0 0.38.586.559 I slot print_timing: id 0 | task 40 | prompt eval time = 1123.86 ms / 115 tokens ( 9.77 ms per token, 102.33 tokens per second) 0.38.586.561 I slot print_timing: id 0 | task 40 | eval time = 37.46 ms / 2 tokens ( 37.46 ms per token, 26.69 tokens per second) 0.38.586.562 I slot print_timing: id 0 | task 40 | total time = 1161.32 ms / 117 tokens 0.38.586.562 I slot print_timing: id 0 | task 40 | graphs reused = 1 0.38.586.563 I slot print_timing: id 0 | task 40 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.586.588 I slot release: id 0 | task 40 | stop processing: n_tokens = 125, truncated = 0 0.38.588.780 I slot print_timing: id 2 | task 41 | prompt eval time = 1125.77 ms / 148 tokens ( 7.61 ms per token, 131.47 tokens per second) 0.38.588.782 I slot print_timing: id 2 | task 41 | eval time = 37.54 ms / 2 tokens ( 37.54 ms per token, 26.64 tokens per second) 0.38.588.782 I slot print_timing: id 2 | task 41 | total time = 1163.31 ms / 150 tokens 0.38.588.782 I slot print_timing: id 2 | task 41 | graphs reused = 1 0.38.588.783 I slot print_timing: id 2 | task 41 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.588.804 I slot release: id 2 | task 41 | stop processing: n_tokens = 158, truncated = 0 0.38.589.949 I slot print_timing: id 3 | task 43 | prompt eval time = 1126.72 ms / 122 tokens ( 9.24 ms per token, 108.28 tokens per second) 0.38.589.951 I slot print_timing: id 3 | task 43 | eval time = 37.65 ms / 2 tokens ( 37.65 ms per token, 26.56 tokens per second) 0.38.589.951 I slot print_timing: id 3 | task 43 | total time = 1164.36 ms / 124 tokens 0.38.589.952 I slot print_timing: id 3 | task 43 | graphs reused = 1 0.38.589.952 I slot print_timing: id 3 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.589.960 I slot release: id 3 | task 43 | stop processing: n_tokens = 132, truncated = 0 0.38.611.109 I slot print_timing: id 1 | task 42 | prompt eval time = 1124.82 ms / 144 tokens ( 7.81 ms per token, 128.02 tokens per second) 0.38.611.111 I slot print_timing: id 1 | task 42 | eval time = 60.93 ms / 3 tokens ( 30.46 ms per token, 32.83 tokens per second) 0.38.611.111 I slot print_timing: id 1 | task 42 | total time = 1185.75 ms / 147 tokens 0.38.611.112 I slot print_timing: id 1 | task 42 | graphs reused = 1 0.38.611.112 I slot print_timing: id 1 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.611.126 I slot release: id 1 | task 42 | stop processing: n_tokens = 155, truncated = 0 0.38.611.131 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 0.38.612.941 I slot launch_slot_: id 3 | task 49 | processing task, is_child = 0 0.38.620.622 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 0.38.620.693 I slot launch_slot_: id 0 | task 50 | processing task, is_child = 0 0.38.620.741 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.239 0.38.620.796 I slot launch_slot_: id 1 | task 51 | processing task, is_child = 0 0.38.620.821 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 0.38.620.879 I slot launch_slot_: id 2 | task 52 | processing task, is_child = 0 0.39.730.553 I slot print_timing: id 0 | task 50 | prompt eval time = 1071.85 ms / 124 tokens ( 8.64 ms per token, 115.69 tokens per second) 0.39.730.556 I slot print_timing: id 0 | task 50 | eval time = 37.81 ms / 2 tokens ( 37.81 ms per token, 26.45 tokens per second) 0.39.730.556 I slot print_timing: id 0 | task 50 | total time = 1109.67 ms / 126 tokens 0.39.730.556 I slot print_timing: id 0 | task 50 | graphs reused = 1 0.39.730.557 I slot print_timing: id 0 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.730.575 I slot release: id 0 | task 50 | stop processing: n_tokens = 134, truncated = 0 0.39.731.684 I slot print_timing: id 1 | task 51 | prompt eval time = 1072.90 ms / 148 tokens ( 7.25 ms per token, 137.94 tokens per second) 0.39.731.685 I slot print_timing: id 1 | task 51 | eval time = 37.76 ms / 2 tokens ( 37.76 ms per token, 26.48 tokens per second) 0.39.731.686 I slot print_timing: id 1 | task 51 | total time = 1110.67 ms / 150 tokens 0.39.731.686 I slot print_timing: id 1 | task 51 | graphs reused = 1 0.39.731.686 I slot print_timing: id 1 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.731.694 I slot release: id 1 | task 51 | stop processing: n_tokens = 158, truncated = 0 0.39.732.785 I slot print_timing: id 2 | task 52 | prompt eval time = 1074.03 ms / 111 tokens ( 9.68 ms per token, 103.35 tokens per second) 0.39.732.786 I slot print_timing: id 2 | task 52 | eval time = 37.62 ms / 2 tokens ( 37.62 ms per token, 26.58 tokens per second) 0.39.732.787 I slot print_timing: id 2 | task 52 | total time = 1111.65 ms / 113 tokens 0.39.732.787 I slot print_timing: id 2 | task 52 | graphs reused = 1 0.39.732.787 I slot print_timing: id 2 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.732.799 I slot release: id 2 | task 52 | stop processing: n_tokens = 121, truncated = 0 0.39.733.909 I slot print_timing: id 3 | task 49 | prompt eval time = 1075.16 ms / 114 tokens ( 9.43 ms per token, 106.03 tokens per second) 0.39.733.911 I slot print_timing: id 3 | task 49 | eval time = 37.50 ms / 2 tokens ( 37.50 ms per token, 26.66 tokens per second) 0.39.733.912 I slot print_timing: id 3 | task 49 | total time = 1112.66 ms / 116 tokens 0.39.733.912 I slot print_timing: id 3 | task 49 | graphs reused = 1 0.39.733.912 I slot print_timing: id 3 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.733.919 I slot release: id 3 | task 49 | stop processing: n_tokens = 124, truncated = 0 0.39.734.401 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.293 (> 0.100 thold), f_keep = 0.331 0.39.735.546 I slot launch_slot_: id 3 | task 57 | processing task, is_child = 0 0.39.743.661 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 0.39.743.725 I slot launch_slot_: id 0 | task 58 | processing task, is_child = 0 0.39.743.775 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.234 0.39.743.830 I slot launch_slot_: id 1 | task 59 | processing task, is_child = 0 0.39.743.857 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.306 0.39.744.364 I slot launch_slot_: id 2 | task 60 | processing task, is_child = 0 0.40.846.805 I slot print_timing: id 0 | task 58 | prompt eval time = 1065.10 ms / 106 tokens ( 10.05 ms per token, 99.52 tokens per second) 0.40.846.811 I slot print_timing: id 0 | task 58 | eval time = 37.33 ms / 2 tokens ( 37.33 ms per token, 26.79 tokens per second) 0.40.846.811 I slot print_timing: id 0 | task 58 | total time = 1102.43 ms / 108 tokens 0.40.846.811 I slot print_timing: id 0 | task 58 | graphs reused = 1 0.40.846.812 I slot print_timing: id 0 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.846.834 I slot release: id 0 | task 58 | stop processing: n_tokens = 116, truncated = 0 0.40.847.951 I slot print_timing: id 1 | task 59 | prompt eval time = 1066.04 ms / 138 tokens ( 7.72 ms per token, 129.45 tokens per second) 0.40.847.953 I slot print_timing: id 1 | task 59 | eval time = 37.41 ms / 2 tokens ( 37.41 ms per token, 26.73 tokens per second) 0.40.847.953 I slot print_timing: id 1 | task 59 | total time = 1103.45 ms / 140 tokens 0.40.847.953 I slot print_timing: id 1 | task 59 | graphs reused = 1 0.40.847.954 I slot print_timing: id 1 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.847.965 I slot release: id 1 | task 59 | stop processing: n_tokens = 148, truncated = 0 0.40.849.065 I slot print_timing: id 2 | task 60 | prompt eval time = 1066.98 ms / 113 tokens ( 9.44 ms per token, 105.91 tokens per second) 0.40.849.067 I slot print_timing: id 2 | task 60 | eval time = 37.47 ms / 2 tokens ( 37.47 ms per token, 26.69 tokens per second) 0.40.849.067 I slot print_timing: id 2 | task 60 | total time = 1104.45 ms / 115 tokens 0.40.849.068 I slot print_timing: id 2 | task 60 | graphs reused = 1 0.40.849.068 I slot print_timing: id 2 | task 60 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.849.079 I slot release: id 2 | task 60 | stop processing: n_tokens = 123, truncated = 0 0.40.870.964 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.319 0.40.872.047 I slot launch_slot_: id 0 | task 66 | processing task, is_child = 0 0.40.877.568 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.250 0.40.877.630 I slot launch_slot_: id 1 | task 67 | processing task, is_child = 0 0.40.877.656 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.301 0.40.877.714 I slot launch_slot_: id 2 | task 68 | processing task, is_child = 0 0.42.052.353 I slot print_timing: id 0 | task 66 | prompt eval time = 1136.99 ms / 194 tokens ( 5.86 ms per token, 170.63 tokens per second) 0.42.052.355 I slot print_timing: id 0 | task 66 | eval time = 37.64 ms / 2 tokens ( 37.64 ms per token, 26.57 tokens per second) 0.42.052.356 I slot print_timing: id 0 | task 66 | total time = 1174.62 ms / 196 tokens 0.42.052.356 I slot print_timing: id 0 | task 66 | graphs reused = 2 0.42.052.356 I slot print_timing: id 0 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.052.376 I slot release: id 0 | task 66 | stop processing: n_tokens = 204, truncated = 0 0.42.053.481 I slot print_timing: id 1 | task 67 | prompt eval time = 1138.04 ms / 134 tokens ( 8.49 ms per token, 117.75 tokens per second) 0.42.053.483 I slot print_timing: id 1 | task 67 | eval time = 37.60 ms / 2 tokens ( 37.60 ms per token, 26.60 tokens per second) 0.42.053.483 I slot print_timing: id 1 | task 67 | total time = 1175.64 ms / 136 tokens 0.42.053.484 I slot print_timing: id 1 | task 67 | graphs reused = 2 0.42.053.484 I slot print_timing: id 1 | task 67 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.053.496 I slot release: id 1 | task 67 | stop processing: n_tokens = 144, truncated = 0 0.42.054.594 I slot print_timing: id 2 | task 68 | prompt eval time = 1139.09 ms / 181 tokens ( 6.29 ms per token, 158.90 tokens per second) 0.42.054.595 I slot print_timing: id 2 | task 68 | eval time = 37.55 ms / 2 tokens ( 37.55 ms per token, 26.63 tokens per second) 0.42.054.596 I slot print_timing: id 2 | task 68 | total time = 1176.64 ms / 183 tokens 0.42.054.596 I slot print_timing: id 2 | task 68 | graphs reused = 2 0.42.054.596 I slot print_timing: id 2 | task 68 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.054.608 I slot release: id 2 | task 68 | stop processing: n_tokens = 191, truncated = 0 0.42.076.214 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.181 0.42.080.449 I slot launch_slot_: id 0 | task 74 | processing task, is_child = 0 0.42.086.843 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.257 0.42.086.918 I slot launch_slot_: id 1 | task 75 | processing task, is_child = 0 0.42.086.949 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.194 0.42.087.018 I slot launch_slot_: id 2 | task 76 | processing task, is_child = 0 0.43.175.011 I slot print_timing: id 0 | task 74 | prompt eval time = 1050.49 ms / 168 tokens ( 6.25 ms per token, 159.93 tokens per second) 0.43.175.013 I slot print_timing: id 0 | task 74 | eval time = 37.49 ms / 2 tokens ( 37.49 ms per token, 26.67 tokens per second) 0.43.175.014 I slot print_timing: id 0 | task 74 | total time = 1087.98 ms / 170 tokens 0.43.175.014 I slot print_timing: id 0 | task 74 | graphs reused = 3 0.43.175.014 I slot print_timing: id 0 | task 74 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.175.041 I slot release: id 0 | task 74 | stop processing: n_tokens = 178, truncated = 0 0.43.176.153 I slot print_timing: id 1 | task 75 | prompt eval time = 1051.55 ms / 171 tokens ( 6.15 ms per token, 162.62 tokens per second) 0.43.176.154 I slot print_timing: id 1 | task 75 | eval time = 37.44 ms / 2 tokens ( 37.44 ms per token, 26.71 tokens per second) 0.43.176.154 I slot print_timing: id 1 | task 75 | total time = 1088.99 ms / 173 tokens 0.43.176.155 I slot print_timing: id 1 | task 75 | graphs reused = 3 0.43.176.155 I slot print_timing: id 1 | task 75 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.176.178 I slot release: id 1 | task 75 | stop processing: n_tokens = 181, truncated = 0 0.43.177.264 I slot print_timing: id 2 | task 76 | prompt eval time = 1052.58 ms / 152 tokens ( 6.92 ms per token, 144.41 tokens per second) 0.43.177.268 I slot print_timing: id 2 | task 76 | eval time = 37.40 ms / 2 tokens ( 37.40 ms per token, 26.74 tokens per second) 0.43.177.268 I slot print_timing: id 2 | task 76 | total time = 1089.98 ms / 154 tokens 0.43.177.268 I slot print_timing: id 2 | task 76 | graphs reused = 3 0.43.177.269 I slot print_timing: id 2 | task 76 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.177.288 I slot release: id 2 | task 76 | stop processing: n_tokens = 162, truncated = 0 0.43.199.207 I slot print_timing: id 3 | task 57 | prompt eval time = 1067.94 ms / 131 tokens ( 8.15 ms per token, 122.67 tokens per second) 0.43.199.209 I slot print_timing: id 3 | task 57 | eval time = 2386.54 ms / 13 tokens ( 198.88 ms per token, 5.03 tokens per second) 0.43.199.210 I slot print_timing: id 3 | task 57 | total time = 3454.49 ms / 144 tokens 0.43.199.210 I slot print_timing: id 3 | task 57 | graphs reused = 3 0.43.199.210 I slot print_timing: id 3 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.199.224 I slot release: id 3 | task 57 | stop processing: n_tokens = 152, truncated = 0 0.43.199.229 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.250 0.43.202.368 I slot launch_slot_: id 3 | task 82 | processing task, is_child = 0 0.43.211.012 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.208 0.43.211.634 I slot launch_slot_: id 0 | task 83 | processing task, is_child = 0 0.43.211.691 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.204 0.43.211.751 I slot launch_slot_: id 1 | task 84 | processing task, is_child = 0 0.43.211.792 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.228 0.43.211.855 I slot launch_slot_: id 2 | task 85 | processing task, is_child = 0 0.44.383.921 I slot print_timing: id 0 | task 83 | prompt eval time = 1134.50 ms / 125 tokens ( 9.08 ms per token, 110.18 tokens per second) 0.44.383.927 I slot print_timing: id 0 | task 83 | eval time = 37.56 ms / 2 tokens ( 37.56 ms per token, 26.62 tokens per second) 0.44.383.927 I slot print_timing: id 0 | task 83 | total time = 1172.06 ms / 127 tokens 0.44.383.928 I slot print_timing: id 0 | task 83 | graphs reused = 3 0.44.383.928 I slot print_timing: id 0 | task 83 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.383.945 I slot release: id 0 | task 83 | stop processing: n_tokens = 135, truncated = 0 0.44.385.065 I slot print_timing: id 1 | task 84 | prompt eval time = 1135.46 ms / 130 tokens ( 8.73 ms per token, 114.49 tokens per second) 0.44.385.066 I slot print_timing: id 1 | task 84 | eval time = 37.62 ms / 2 tokens ( 37.62 ms per token, 26.58 tokens per second) 0.44.385.066 I slot print_timing: id 1 | task 84 | total time = 1173.08 ms / 132 tokens 0.44.385.067 I slot print_timing: id 1 | task 84 | graphs reused = 3 0.44.385.067 I slot print_timing: id 1 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.385.076 I slot release: id 1 | task 84 | stop processing: n_tokens = 140, truncated = 0 0.44.386.181 I slot print_timing: id 2 | task 85 | prompt eval time = 1136.41 ms / 166 tokens ( 6.85 ms per token, 146.07 tokens per second) 0.44.386.183 I slot print_timing: id 2 | task 85 | eval time = 37.67 ms / 2 tokens ( 37.67 ms per token, 26.55 tokens per second) 0.44.386.183 I slot print_timing: id 2 | task 85 | total time = 1174.08 ms / 168 tokens 0.44.386.183 I slot print_timing: id 2 | task 85 | graphs reused = 3 0.44.386.184 I slot print_timing: id 2 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.386.206 I slot release: id 2 | task 85 | stop processing: n_tokens = 176, truncated = 0 0.44.387.292 I slot print_timing: id 3 | task 82 | prompt eval time = 1137.43 ms / 143 tokens ( 7.95 ms per token, 125.72 tokens per second) 0.44.387.294 I slot print_timing: id 3 | task 82 | eval time = 37.63 ms / 2 tokens ( 37.63 ms per token, 26.58 tokens per second) 0.44.387.295 I slot print_timing: id 3 | task 82 | total time = 1175.06 ms / 145 tokens 0.44.387.295 I slot print_timing: id 3 | task 82 | graphs reused = 3 0.44.387.295 I slot print_timing: id 3 | task 82 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.387.305 I slot release: id 3 | task 82 | stop processing: n_tokens = 153, truncated = 0 0.44.387.887 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 0.44.390.628 I slot launch_slot_: id 2 | task 90 | processing task, is_child = 0 0.44.398.040 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 0.44.398.105 I slot launch_slot_: id 3 | task 91 | processing task, is_child = 0 0.44.398.155 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.274 0.44.398.207 I slot launch_slot_: id 0 | task 92 | processing task, is_child = 0 0.44.398.231 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.264 0.44.398.758 I slot launch_slot_: id 1 | task 93 | processing task, is_child = 0 0.45.619.937 I slot print_timing: id 0 | task 92 | prompt eval time = 1183.39 ms / 170 tokens ( 6.96 ms per token, 143.65 tokens per second) 0.45.619.939 I slot print_timing: id 0 | task 92 | eval time = 37.77 ms / 2 tokens ( 37.77 ms per token, 26.48 tokens per second) 0.45.619.940 I slot print_timing: id 0 | task 92 | total time = 1221.16 ms / 172 tokens 0.45.619.940 I slot print_timing: id 0 | task 92 | graphs reused = 3 0.45.619.941 I slot print_timing: id 0 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.619.959 I slot release: id 0 | task 92 | stop processing: n_tokens = 180, truncated = 0 0.45.621.060 I slot print_timing: id 1 | task 93 | prompt eval time = 1184.35 ms / 167 tokens ( 7.09 ms per token, 141.01 tokens per second) 0.45.621.064 I slot print_timing: id 1 | task 93 | eval time = 37.82 ms / 2 tokens ( 37.82 ms per token, 26.44 tokens per second) 0.45.621.066 I slot print_timing: id 1 | task 93 | total time = 1222.18 ms / 169 tokens 0.45.621.066 I slot print_timing: id 1 | task 93 | graphs reused = 3 0.45.621.066 I slot print_timing: id 1 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.621.084 I slot release: id 1 | task 93 | stop processing: n_tokens = 177, truncated = 0 0.45.622.192 I slot print_timing: id 2 | task 90 | prompt eval time = 1185.33 ms / 160 tokens ( 7.41 ms per token, 134.98 tokens per second) 0.45.622.193 I slot print_timing: id 2 | task 90 | eval time = 37.87 ms / 2 tokens ( 37.87 ms per token, 26.41 tokens per second) 0.45.622.194 I slot print_timing: id 2 | task 90 | total time = 1223.20 ms / 162 tokens 0.45.622.194 I slot print_timing: id 2 | task 90 | graphs reused = 3 0.45.622.195 I slot print_timing: id 2 | task 90 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.622.208 I slot release: id 2 | task 90 | stop processing: n_tokens = 170, truncated = 0 0.45.623.314 I slot print_timing: id 3 | task 91 | prompt eval time = 1186.38 ms / 109 tokens ( 10.88 ms per token, 91.88 tokens per second) 0.45.623.317 I slot print_timing: id 3 | task 91 | eval time = 37.83 ms / 2 tokens ( 37.83 ms per token, 26.44 tokens per second) 0.45.623.318 I slot print_timing: id 3 | task 91 | total time = 1224.20 ms / 111 tokens 0.45.623.318 I slot print_timing: id 3 | task 91 | graphs reused = 3 0.45.623.319 I slot print_timing: id 3 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.623.329 I slot release: id 3 | task 91 | stop processing: n_tokens = 119, truncated = 0 0.45.623.823 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 0.45.627.275 I slot launch_slot_: id 1 | task 98 | processing task, is_child = 0 0.45.635.754 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.311 (> 0.100 thold), f_keep = 0.211 0.45.635.823 I slot launch_slot_: id 0 | task 99 | processing task, is_child = 0 0.45.635.871 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.218 0.45.635.931 I slot launch_slot_: id 2 | task 100 | processing task, is_child = 0 0.45.635.959 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.281 (> 0.100 thold), f_keep = 0.319 0.45.636.010 I slot launch_slot_: id 3 | task 101 | processing task, is_child = 0 0.46.714.186 I slot print_timing: id 0 | task 99 | prompt eval time = 1040.75 ms / 113 tokens ( 9.21 ms per token, 108.58 tokens per second) 0.46.714.188 I slot print_timing: id 0 | task 99 | eval time = 37.42 ms / 2 tokens ( 37.42 ms per token, 26.73 tokens per second) 0.46.714.189 I slot print_timing: id 0 | task 99 | total time = 1078.17 ms / 115 tokens 0.46.714.189 I slot print_timing: id 0 | task 99 | graphs reused = 3 0.46.714.190 I slot print_timing: id 0 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.714.210 I slot release: id 0 | task 99 | stop processing: n_tokens = 123, truncated = 0 0.46.715.304 I slot print_timing: id 1 | task 98 | prompt eval time = 1041.64 ms / 111 tokens ( 9.38 ms per token, 106.56 tokens per second) 0.46.715.306 I slot print_timing: id 1 | task 98 | eval time = 37.45 ms / 2 tokens ( 37.45 ms per token, 26.70 tokens per second) 0.46.715.306 I slot print_timing: id 1 | task 98 | total time = 1079.09 ms / 113 tokens 0.46.715.307 I slot print_timing: id 1 | task 98 | graphs reused = 3 0.46.715.307 I slot print_timing: id 1 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.715.321 I slot release: id 1 | task 98 | stop processing: n_tokens = 121, truncated = 0 0.46.716.409 I slot print_timing: id 2 | task 100 | prompt eval time = 1042.54 ms / 136 tokens ( 7.67 ms per token, 130.45 tokens per second) 0.46.716.411 I slot print_timing: id 2 | task 100 | eval time = 37.49 ms / 2 tokens ( 37.49 ms per token, 26.67 tokens per second) 0.46.716.412 I slot print_timing: id 2 | task 100 | total time = 1080.03 ms / 138 tokens 0.46.716.412 I slot print_timing: id 2 | task 100 | graphs reused = 3 0.46.716.412 I slot print_timing: id 2 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.716.428 I slot release: id 2 | task 100 | stop processing: n_tokens = 146, truncated = 0 0.46.717.514 I slot print_timing: id 3 | task 101 | prompt eval time = 1043.44 ms / 126 tokens ( 8.28 ms per token, 120.75 tokens per second) 0.46.717.517 I slot print_timing: id 3 | task 101 | eval time = 37.53 ms / 2 tokens ( 37.53 ms per token, 26.65 tokens per second) 0.46.717.517 I slot print_timing: id 3 | task 101 | total time = 1080.97 ms / 128 tokens 0.46.717.517 I slot print_timing: id 3 | task 101 | graphs reused = 3 0.46.717.517 I slot print_timing: id 3 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.717.526 I slot release: id 3 | task 101 | stop processing: n_tokens = 136, truncated = 0 0.46.719.226 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.301 0.46.720.188 I slot launch_slot_: id 0 | task 106 | processing task, is_child = 0 0.46.727.252 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.306 0.46.727.330 I slot launch_slot_: id 1 | task 107 | processing task, is_child = 0 0.46.727.379 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.279 0.46.727.433 I slot launch_slot_: id 3 | task 108 | processing task, is_child = 0 0.46.727.457 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.253 0.46.728.037 I slot launch_slot_: id 2 | task 109 | processing task, is_child = 0 0.47.883.125 I slot print_timing: id 1 | task 107 | prompt eval time = 1117.26 ms / 124 tokens ( 9.01 ms per token, 110.99 tokens per second) 0.47.883.128 I slot print_timing: id 1 | task 107 | eval time = 37.70 ms / 2 tokens ( 37.70 ms per token, 26.52 tokens per second) 0.47.883.128 I slot print_timing: id 1 | task 107 | total time = 1154.96 ms / 126 tokens 0.47.883.128 I slot print_timing: id 1 | task 107 | graphs reused = 3 0.47.883.129 I slot print_timing: id 1 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.883.149 I slot release: id 1 | task 107 | stop processing: n_tokens = 134, truncated = 0 0.47.884.254 I slot print_timing: id 2 | task 109 | prompt eval time = 1118.41 ms / 126 tokens ( 8.88 ms per token, 112.66 tokens per second) 0.47.884.260 I slot print_timing: id 2 | task 109 | eval time = 37.57 ms / 2 tokens ( 37.57 ms per token, 26.62 tokens per second) 0.47.884.261 I slot print_timing: id 2 | task 109 | total time = 1155.98 ms / 128 tokens 0.47.884.261 I slot print_timing: id 2 | task 109 | graphs reused = 3 0.47.884.261 I slot print_timing: id 2 | task 109 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.884.272 I slot release: id 2 | task 109 | stop processing: n_tokens = 136, truncated = 0 0.47.885.353 I slot print_timing: id 3 | task 108 | prompt eval time = 1119.54 ms / 148 tokens ( 7.56 ms per token, 132.20 tokens per second) 0.47.885.357 I slot print_timing: id 3 | task 108 | eval time = 37.43 ms / 2 tokens ( 37.43 ms per token, 26.72 tokens per second) 0.47.885.358 I slot print_timing: id 3 | task 108 | total time = 1156.97 ms / 150 tokens 0.47.885.358 I slot print_timing: id 3 | task 108 | graphs reused = 3 0.47.885.358 I slot print_timing: id 3 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.885.369 I slot release: id 3 | task 108 | stop processing: n_tokens = 158, truncated = 0 0.47.906.150 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.276 0.47.908.798 I slot launch_slot_: id 1 | task 115 | processing task, is_child = 0 0.47.913.696 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.241 0.47.914.321 I slot launch_slot_: id 3 | task 116 | processing task, is_child = 0 0.47.914.348 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.287 (> 0.100 thold), f_keep = 0.272 0.47.914.858 I slot launch_slot_: id 2 | task 117 | processing task, is_child = 0 0.48.854.849 I slot print_timing: id 1 | task 115 | prompt eval time = 902.49 ms / 143 tokens ( 6.31 ms per token, 158.45 tokens per second) 0.48.854.854 I slot print_timing: id 1 | task 115 | eval time = 37.49 ms / 2 tokens ( 37.49 ms per token, 26.67 tokens per second) 0.48.854.855 I slot print_timing: id 1 | task 115 | total time = 939.99 ms / 145 tokens 0.48.854.855 I slot print_timing: id 1 | task 115 | graphs reused = 4 0.48.854.856 I slot print_timing: id 1 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.854.876 I slot release: id 1 | task 115 | stop processing: n_tokens = 153, truncated = 0 0.48.855.981 I slot print_timing: id 2 | task 117 | prompt eval time = 903.45 ms / 120 tokens ( 7.53 ms per token, 132.82 tokens per second) 0.48.855.983 I slot print_timing: id 2 | task 117 | eval time = 37.55 ms / 2 tokens ( 37.55 ms per token, 26.63 tokens per second) 0.48.855.984 I slot print_timing: id 2 | task 117 | total time = 941.00 ms / 122 tokens 0.48.855.984 I slot print_timing: id 2 | task 117 | graphs reused = 4 0.48.855.984 I slot print_timing: id 2 | task 117 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.855.994 I slot release: id 2 | task 117 | stop processing: n_tokens = 130, truncated = 0 0.48.857.082 I slot print_timing: id 3 | task 116 | prompt eval time = 904.43 ms / 136 tokens ( 6.65 ms per token, 150.37 tokens per second) 0.48.857.083 I slot print_timing: id 3 | task 116 | eval time = 37.56 ms / 2 tokens ( 37.56 ms per token, 26.63 tokens per second) 0.48.857.084 I slot print_timing: id 3 | task 116 | total time = 941.98 ms / 138 tokens 0.48.857.084 I slot print_timing: id 3 | task 116 | graphs reused = 4 0.48.857.084 I slot print_timing: id 3 | task 116 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.857.093 I slot release: id 3 | task 116 | stop processing: n_tokens = 146, truncated = 0 0.48.877.591 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.319 (> 0.100 thold), f_keep = 0.292 0.48.878.763 I slot launch_slot_: id 2 | task 123 | processing task, is_child = 0 0.48.882.779 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.280 (> 0.100 thold), f_keep = 0.242 0.48.882.854 I slot launch_slot_: id 1 | task 124 | processing task, is_child = 0 0.48.882.882 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.253 0.48.882.950 I slot launch_slot_: id 3 | task 125 | processing task, is_child = 0 0.49.869.725 I slot print_timing: id 1 | task 124 | prompt eval time = 948.74 ms / 123 tokens ( 7.71 ms per token, 129.65 tokens per second) 0.49.869.731 I slot print_timing: id 1 | task 124 | eval time = 38.03 ms / 2 tokens ( 38.03 ms per token, 26.30 tokens per second) 0.49.869.731 I slot print_timing: id 1 | task 124 | total time = 986.77 ms / 125 tokens 0.49.869.732 I slot print_timing: id 1 | task 124 | graphs reused = 5 0.49.869.732 I slot print_timing: id 1 | task 124 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.869.754 I slot release: id 1 | task 124 | stop processing: n_tokens = 133, truncated = 0 0.49.870.855 I slot print_timing: id 2 | task 123 | prompt eval time = 949.78 ms / 110 tokens ( 8.63 ms per token, 115.82 tokens per second) 0.49.870.861 I slot print_timing: id 2 | task 123 | eval time = 37.98 ms / 2 tokens ( 37.98 ms per token, 26.33 tokens per second) 0.49.870.862 I slot print_timing: id 2 | task 123 | total time = 987.76 ms / 112 tokens 0.49.870.862 I slot print_timing: id 2 | task 123 | graphs reused = 5 0.49.870.862 I slot print_timing: id 2 | task 123 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.870.873 I slot release: id 2 | task 123 | stop processing: n_tokens = 120, truncated = 0 0.49.871.974 I slot print_timing: id 3 | task 125 | prompt eval time = 950.99 ms / 175 tokens ( 5.43 ms per token, 184.02 tokens per second) 0.49.871.976 I slot print_timing: id 3 | task 125 | eval time = 37.78 ms / 2 tokens ( 37.78 ms per token, 26.47 tokens per second) 0.49.871.976 I slot print_timing: id 3 | task 125 | total time = 988.77 ms / 177 tokens 0.49.871.976 I slot print_timing: id 3 | task 125 | graphs reused = 5 0.49.871.977 I slot print_timing: id 3 | task 125 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.871.991 I slot release: id 3 | task 125 | stop processing: n_tokens = 185, truncated = 0 0.49.892.731 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.299 (> 0.100 thold), f_keep = 0.317 0.49.893.849 I slot launch_slot_: id 2 | task 131 | processing task, is_child = 0 0.49.899.434 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.278 0.49.900.007 I slot launch_slot_: id 1 | task 132 | processing task, is_child = 0 0.49.900.038 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.145 (> 0.100 thold), f_keep = 0.200 0.49.900.102 I slot launch_slot_: id 3 | task 133 | processing task, is_child = 0 0.51.079.546 I slot print_timing: id 1 | task 132 | prompt eval time = 1141.69 ms / 138 tokens ( 8.27 ms per token, 120.87 tokens per second) 0.51.079.551 I slot print_timing: id 1 | task 132 | eval time = 37.75 ms / 2 tokens ( 37.75 ms per token, 26.49 tokens per second) 0.51.079.552 I slot print_timing: id 1 | task 132 | total time = 1179.44 ms / 140 tokens 0.51.079.552 I slot print_timing: id 1 | task 132 | graphs reused = 6 0.51.079.552 I slot print_timing: id 1 | task 132 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.079.575 I slot release: id 1 | task 132 | stop processing: n_tokens = 148, truncated = 0 0.51.080.676 I slot print_timing: id 2 | task 131 | prompt eval time = 1142.66 ms / 118 tokens ( 9.68 ms per token, 103.27 tokens per second) 0.51.080.678 I slot print_timing: id 2 | task 131 | eval time = 37.78 ms / 2 tokens ( 37.78 ms per token, 26.47 tokens per second) 0.51.080.678 I slot print_timing: id 2 | task 131 | total time = 1180.44 ms / 120 tokens 0.51.080.679 I slot print_timing: id 2 | task 131 | graphs reused = 6 0.51.080.679 I slot print_timing: id 2 | task 131 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.080.702 I slot release: id 2 | task 131 | stop processing: n_tokens = 128, truncated = 0 0.51.081.806 I slot print_timing: id 3 | task 133 | prompt eval time = 1143.61 ms / 247 tokens ( 4.63 ms per token, 215.98 tokens per second) 0.51.081.809 I slot print_timing: id 3 | task 133 | eval time = 37.84 ms / 2 tokens ( 37.84 ms per token, 26.43 tokens per second) 0.51.081.811 I slot print_timing: id 3 | task 133 | total time = 1181.45 ms / 249 tokens 0.51.081.811 I slot print_timing: id 3 | task 133 | graphs reused = 6 0.51.081.811 I slot print_timing: id 3 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.081.828 I slot release: id 3 | task 133 | stop processing: n_tokens = 257, truncated = 0 0.51.102.387 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.250 0.51.105.209 I slot launch_slot_: id 1 | task 139 | processing task, is_child = 0 0.51.111.056 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.234 (> 0.100 thold), f_keep = 0.305 0.51.111.120 I slot launch_slot_: id 2 | task 140 | processing task, is_child = 0 0.51.111.155 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.144 0.51.111.689 I slot launch_slot_: id 3 | task 141 | processing task, is_child = 0 0.52.255.563 I slot print_timing: id 1 | task 139 | prompt eval time = 1106.12 ms / 182 tokens ( 6.08 ms per token, 164.54 tokens per second) 0.52.255.568 I slot print_timing: id 1 | task 139 | eval time = 37.74 ms / 2 tokens ( 37.74 ms per token, 26.49 tokens per second) 0.52.255.569 I slot print_timing: id 1 | task 139 | total time = 1143.87 ms / 184 tokens 0.52.255.569 I slot print_timing: id 1 | task 139 | graphs reused = 7 0.52.255.570 I slot print_timing: id 1 | task 139 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.255.590 I slot release: id 1 | task 139 | stop processing: n_tokens = 192, truncated = 0 0.52.256.686 I slot print_timing: id 2 | task 140 | prompt eval time = 1107.14 ms / 158 tokens ( 7.01 ms per token, 142.71 tokens per second) 0.52.256.687 I slot print_timing: id 2 | task 140 | eval time = 37.73 ms / 2 tokens ( 37.73 ms per token, 26.50 tokens per second) 0.52.256.687 I slot print_timing: id 2 | task 140 | total time = 1144.88 ms / 160 tokens 0.52.256.688 I slot print_timing: id 2 | task 140 | graphs reused = 7 0.52.256.688 I slot print_timing: id 2 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.256.698 I slot release: id 2 | task 140 | stop processing: n_tokens = 168, truncated = 0 0.52.257.781 I slot print_timing: id 3 | task 141 | prompt eval time = 1108.17 ms / 145 tokens ( 7.64 ms per token, 130.85 tokens per second) 0.52.257.782 I slot print_timing: id 3 | task 141 | eval time = 37.69 ms / 2 tokens ( 37.69 ms per token, 26.53 tokens per second) 0.52.257.783 I slot print_timing: id 3 | task 141 | total time = 1145.86 ms / 147 tokens 0.52.257.783 I slot print_timing: id 3 | task 141 | graphs reused = 7 0.52.257.783 I slot print_timing: id 3 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.257.796 I slot release: id 3 | task 141 | stop processing: n_tokens = 155, truncated = 0 0.52.278.529 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.193 0.52.282.446 I slot launch_slot_: id 1 | task 147 | processing task, is_child = 0 0.52.288.674 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.220 0.52.288.743 I slot launch_slot_: id 2 | task 148 | processing task, is_child = 0 0.52.288.773 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.345 (> 0.100 thold), f_keep = 0.258 0.52.288.843 I slot launch_slot_: id 3 | task 149 | processing task, is_child = 0 0.53.465.332 I slot print_timing: id 0 | task 106 | prompt eval time = 1116.31 ms / 149 tokens ( 7.49 ms per token, 133.48 tokens per second) 0.53.465.336 I slot print_timing: id 0 | task 106 | eval time = 5620.98 ms / 27 tokens ( 216.19 ms per token, 4.63 tokens per second) 0.53.465.336 I slot print_timing: id 0 | task 106 | total time = 6737.29 ms / 176 tokens 0.53.465.337 I slot print_timing: id 0 | task 106 | graphs reused = 8 0.53.465.337 I slot print_timing: id 0 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.465.374 I slot release: id 0 | task 106 | stop processing: n_tokens = 184, truncated = 0 0.53.467.622 I slot print_timing: id 2 | task 148 | prompt eval time = 1140.64 ms / 229 tokens ( 4.98 ms per token, 200.76 tokens per second) 0.53.467.623 I slot print_timing: id 2 | task 148 | eval time = 37.94 ms / 2 tokens ( 37.94 ms per token, 26.36 tokens per second) 0.53.467.624 I slot print_timing: id 2 | task 148 | total time = 1178.58 ms / 231 tokens 0.53.467.624 I slot print_timing: id 2 | task 148 | graphs reused = 8 0.53.467.625 I slot print_timing: id 2 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.467.640 I slot release: id 2 | task 148 | stop processing: n_tokens = 239, truncated = 0 0.53.468.753 I slot print_timing: id 3 | task 149 | prompt eval time = 1141.60 ms / 107 tokens ( 10.67 ms per token, 93.73 tokens per second) 0.53.468.760 I slot print_timing: id 3 | task 149 | eval time = 37.99 ms / 2 tokens ( 37.99 ms per token, 26.32 tokens per second) 0.53.468.760 I slot print_timing: id 3 | task 149 | total time = 1179.59 ms / 109 tokens 0.53.468.760 I slot print_timing: id 3 | task 149 | graphs reused = 8 0.53.468.760 I slot print_timing: id 3 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.468.767 I slot release: id 3 | task 149 | stop processing: n_tokens = 117, truncated = 0 0.53.489.496 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.185 (> 0.100 thold), f_keep = 0.201 0.53.492.829 I slot launch_slot_: id 0 | task 155 | processing task, is_child = 0 0.53.498.229 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.302 (> 0.100 thold), f_keep = 0.325 0.53.498.294 I slot launch_slot_: id 3 | task 156 | processing task, is_child = 0 0.53.498.328 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.155 0.53.498.392 I slot launch_slot_: id 2 | task 157 | processing task, is_child = 0 0.54.559.857 I slot print_timing: id 0 | task 155 | prompt eval time = 1023.67 ms / 191 tokens ( 5.36 ms per token, 186.58 tokens per second) 0.54.559.861 I slot print_timing: id 0 | task 155 | eval time = 37.78 ms / 2 tokens ( 37.78 ms per token, 26.47 tokens per second) 0.54.559.862 I slot print_timing: id 0 | task 155 | total time = 1061.45 ms / 193 tokens 0.54.559.862 I slot print_timing: id 0 | task 155 | graphs reused = 8 0.54.559.863 I slot print_timing: id 0 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.559.883 I slot release: id 0 | task 155 | stop processing: n_tokens = 201, truncated = 0 0.54.562.076 I slot print_timing: id 2 | task 157 | prompt eval time = 1025.77 ms / 143 tokens ( 7.17 ms per token, 139.41 tokens per second) 0.54.562.078 I slot print_timing: id 2 | task 157 | eval time = 37.78 ms / 2 tokens ( 37.78 ms per token, 26.47 tokens per second) 0.54.562.078 I slot print_timing: id 2 | task 157 | total time = 1063.55 ms / 145 tokens 0.54.562.078 I slot print_timing: id 2 | task 157 | graphs reused = 8 0.54.562.079 I slot print_timing: id 2 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.562.095 I slot release: id 2 | task 157 | stop processing: n_tokens = 153, truncated = 0 0.54.563.208 I slot print_timing: id 3 | task 156 | prompt eval time = 1026.71 ms / 117 tokens ( 8.78 ms per token, 113.96 tokens per second) 0.54.563.211 I slot print_timing: id 3 | task 156 | eval time = 37.84 ms / 2 tokens ( 37.84 ms per token, 26.43 tokens per second) 0.54.563.211 I slot print_timing: id 3 | task 156 | total time = 1064.54 ms / 119 tokens 0.54.563.211 I slot print_timing: id 3 | task 156 | graphs reused = 8 0.54.563.211 I slot print_timing: id 3 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.563.218 I slot release: id 3 | task 156 | stop processing: n_tokens = 127, truncated = 0 0.54.583.858 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.184 0.54.586.994 I slot launch_slot_: id 0 | task 163 | processing task, is_child = 0 0.54.591.942 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.242 0.54.592.014 I slot launch_slot_: id 2 | task 164 | processing task, is_child = 0 0.54.592.045 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.299 0.54.592.105 I slot launch_slot_: id 3 | task 165 | processing task, is_child = 0 0.55.700.293 I slot print_timing: id 0 | task 163 | prompt eval time = 1070.37 ms / 175 tokens ( 6.12 ms per token, 163.50 tokens per second) 0.55.700.298 I slot print_timing: id 0 | task 163 | eval time = 37.81 ms / 2 tokens ( 37.81 ms per token, 26.45 tokens per second) 0.55.700.299 I slot print_timing: id 0 | task 163 | total time = 1108.18 ms / 177 tokens 0.55.700.299 I slot print_timing: id 0 | task 163 | graphs reused = 8 0.55.700.299 I slot print_timing: id 0 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.700.322 I slot release: id 0 | task 163 | stop processing: n_tokens = 185, truncated = 0 0.55.702.503 I slot print_timing: id 2 | task 164 | prompt eval time = 1072.41 ms / 140 tokens ( 7.66 ms per token, 130.55 tokens per second) 0.55.702.505 I slot print_timing: id 2 | task 164 | eval time = 37.85 ms / 2 tokens ( 37.85 ms per token, 26.42 tokens per second) 0.55.702.506 I slot print_timing: id 2 | task 164 | total time = 1110.25 ms / 142 tokens 0.55.702.506 I slot print_timing: id 2 | task 164 | graphs reused = 8 0.55.702.507 I slot print_timing: id 2 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.702.518 I slot release: id 2 | task 164 | stop processing: n_tokens = 150, truncated = 0 0.55.703.646 I slot print_timing: id 3 | task 165 | prompt eval time = 1073.56 ms / 122 tokens ( 8.80 ms per token, 113.64 tokens per second) 0.55.703.648 I slot print_timing: id 3 | task 165 | eval time = 37.72 ms / 2 tokens ( 37.72 ms per token, 26.51 tokens per second) 0.55.703.648 I slot print_timing: id 3 | task 165 | total time = 1111.28 ms / 124 tokens 0.55.703.649 I slot print_timing: id 3 | task 165 | graphs reused = 8 0.55.703.649 I slot print_timing: id 3 | task 165 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.703.660 I slot release: id 3 | task 165 | stop processing: n_tokens = 132, truncated = 0 0.55.703.664 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.314 (> 0.100 thold), f_keep = 0.288 0.55.706.508 I slot launch_slot_: id 3 | task 170 | processing task, is_child = 0 0.55.712.817 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.200 0.55.713.399 I slot launch_slot_: id 0 | task 171 | processing task, is_child = 0 0.55.713.432 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.253 (> 0.100 thold), f_keep = 0.247 0.55.713.487 I slot launch_slot_: id 2 | task 172 | processing task, is_child = 0 0.55.762.731 I slot print_timing: id 1 | task 147 | prompt eval time = 1139.65 ms / 162 tokens ( 7.03 ms per token, 142.15 tokens per second) 0.55.762.733 I slot print_timing: id 1 | task 147 | eval time = 2334.23 ms / 13 tokens ( 194.52 ms per token, 5.14 tokens per second) 0.55.762.734 I slot print_timing: id 1 | task 147 | total time = 3473.88 ms / 175 tokens 0.55.762.734 I slot print_timing: id 1 | task 147 | graphs reused = 8 0.55.762.735 I slot print_timing: id 1 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.762.753 I slot release: id 1 | task 147 | stop processing: n_tokens = 183, truncated = 0 0.56.461.094 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.202 0.56.543.381 I slot launch_slot_: id 1 | task 175 | processing task, is_child = 0 0.56.992.787 I slot print_timing: id 0 | task 171 | prompt eval time = 925.61 ms / 162 tokens ( 5.71 ms per token, 175.02 tokens per second) 0.56.992.790 I slot print_timing: id 0 | task 171 | eval time = 353.68 ms / 2 tokens ( 353.68 ms per token, 2.83 tokens per second) 0.56.992.790 I slot print_timing: id 0 | task 171 | total time = 1279.29 ms / 164 tokens 0.56.992.791 I slot print_timing: id 0 | task 171 | graphs reused = 8 0.56.992.791 I slot print_timing: id 0 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.992.828 I slot release: id 0 | task 171 | stop processing: n_tokens = 172, truncated = 0 0.56.993.936 I slot print_timing: id 2 | task 172 | prompt eval time = 926.71 ms / 137 tokens ( 6.76 ms per token, 147.83 tokens per second) 0.56.993.939 I slot print_timing: id 2 | task 172 | eval time = 353.62 ms / 2 tokens ( 353.62 ms per token, 2.83 tokens per second) 0.56.993.939 I slot print_timing: id 2 | task 172 | total time = 1280.33 ms / 139 tokens 0.56.993.939 I slot print_timing: id 2 | task 172 | graphs reused = 8 0.56.993.940 I slot print_timing: id 2 | task 172 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.993.966 I slot release: id 2 | task 172 | stop processing: n_tokens = 147, truncated = 0 0.56.995.121 I slot print_timing: id 3 | task 170 | prompt eval time = 927.66 ms / 112 tokens ( 8.28 ms per token, 120.73 tokens per second) 0.56.995.124 I slot print_timing: id 3 | task 170 | eval time = 353.73 ms / 2 tokens ( 353.73 ms per token, 2.83 tokens per second) 0.56.995.124 I slot print_timing: id 3 | task 170 | total time = 1281.40 ms / 114 tokens 0.56.995.124 I slot print_timing: id 3 | task 170 | graphs reused = 8 0.56.995.125 I slot print_timing: id 3 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.995.138 I slot release: id 3 | task 170 | stop processing: n_tokens = 122, truncated = 0 0.57.029.758 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.290 (> 0.100 thold), f_keep = 0.311 0.57.032.327 I slot launch_slot_: id 3 | task 179 | processing task, is_child = 0 0.57.038.150 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.215 0.57.038.218 I slot launch_slot_: id 0 | task 180 | processing task, is_child = 0 0.57.038.247 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.252 0.57.038.310 I slot launch_slot_: id 2 | task 181 | processing task, is_child = 0 0.57.087.506 I slot print_timing: id 1 | task 175 | prompt eval time = 485.70 ms / 138 tokens ( 3.52 ms per token, 284.13 tokens per second) 0.57.087.511 I slot print_timing: id 1 | task 175 | eval time = 57.75 ms / 2 tokens ( 57.75 ms per token, 17.32 tokens per second) 0.57.087.512 I slot print_timing: id 1 | task 175 | total time = 543.45 ms / 140 tokens 0.57.087.512 I slot print_timing: id 1 | task 175 | graphs reused = 8 0.57.087.513 I slot print_timing: id 1 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.087.536 I slot release: id 1 | task 175 | stop processing: n_tokens = 148, truncated = 0 0.57.897.735 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.250 0.57.945.079 I slot launch_slot_: id 1 | task 184 | processing task, is_child = 0 0.58.461.981 I slot print_timing: id 0 | task 180 | prompt eval time = 1005.50 ms / 183 tokens ( 5.49 ms per token, 182.00 tokens per second) 0.58.461.987 I slot print_timing: id 0 | task 180 | eval time = 418.16 ms / 2 tokens ( 418.16 ms per token, 2.39 tokens per second) 0.58.461.987 I slot print_timing: id 0 | task 180 | total time = 1423.66 ms / 185 tokens 0.58.461.987 I slot print_timing: id 0 | task 180 | graphs reused = 8 0.58.461.988 I slot print_timing: id 0 | task 180 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.462.013 I slot release: id 0 | task 180 | stop processing: n_tokens = 193, truncated = 0 0.58.464.253 I slot print_timing: id 3 | task 179 | prompt eval time = 1007.42 ms / 122 tokens ( 8.26 ms per token, 121.10 tokens per second) 0.58.464.255 I slot print_timing: id 3 | task 179 | eval time = 418.24 ms / 2 tokens ( 418.24 ms per token, 2.39 tokens per second) 0.58.464.256 I slot print_timing: id 3 | task 179 | total time = 1425.67 ms / 124 tokens 0.58.464.256 I slot print_timing: id 3 | task 179 | graphs reused = 8 0.58.464.256 I slot print_timing: id 3 | task 179 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.464.268 I slot release: id 3 | task 179 | stop processing: n_tokens = 132, truncated = 0 0.58.519.152 I slot print_timing: id 2 | task 181 | prompt eval time = 1006.48 ms / 132 tokens ( 7.62 ms per token, 131.15 tokens per second) 0.58.519.154 I slot print_timing: id 2 | task 181 | eval time = 474.21 ms / 3 tokens ( 237.11 ms per token, 4.22 tokens per second) 0.58.519.155 I slot print_timing: id 2 | task 181 | total time = 1480.69 ms / 135 tokens 0.58.519.155 I slot print_timing: id 2 | task 181 | graphs reused = 8 0.58.519.156 I slot print_timing: id 2 | task 181 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.519.171 I slot release: id 2 | task 181 | stop processing: n_tokens = 143, truncated = 0 0.58.519.177 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.192 0.58.523.460 I slot launch_slot_: id 0 | task 188 | processing task, is_child = 0 0.58.528.141 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.198 (> 0.100 thold), f_keep = 0.259 0.58.528.205 I slot launch_slot_: id 2 | task 189 | processing task, is_child = 0 0.58.528.233 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.284 (> 0.100 thold), f_keep = 0.288 0.58.528.292 I slot launch_slot_: id 3 | task 190 | processing task, is_child = 0 0.58.577.618 I slot print_timing: id 1 | task 184 | prompt eval time = 570.20 ms / 183 tokens ( 3.12 ms per token, 320.94 tokens per second) 0.58.577.623 I slot print_timing: id 1 | task 184 | eval time = 59.54 ms / 2 tokens ( 59.54 ms per token, 16.80 tokens per second) 0.58.577.624 I slot print_timing: id 1 | task 184 | total time = 629.74 ms / 185 tokens 0.58.577.624 I slot print_timing: id 1 | task 184 | graphs reused = 8 0.58.577.624 I slot print_timing: id 1 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.577.644 I slot release: id 1 | task 184 | stop processing: n_tokens = 193, truncated = 0 0.59.272.230 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.192 0.59.405.359 I slot launch_slot_: id 1 | task 193 | processing task, is_child = 0 0.59.805.487 I slot print_timing: id 0 | task 188 | prompt eval time = 974.19 ms / 117 tokens ( 8.33 ms per token, 120.10 tokens per second) 0.59.805.492 I slot print_timing: id 0 | task 188 | eval time = 302.99 ms / 2 tokens ( 302.99 ms per token, 3.30 tokens per second) 0.59.805.492 I slot print_timing: id 0 | task 188 | total time = 1277.18 ms / 119 tokens 0.59.805.493 I slot print_timing: id 0 | task 188 | graphs reused = 8 0.59.805.493 I slot print_timing: id 0 | task 188 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.805.518 I slot release: id 0 | task 188 | stop processing: n_tokens = 127, truncated = 0 0.59.806.655 I slot print_timing: id 2 | task 189 | prompt eval time = 975.14 ms / 178 tokens ( 5.48 ms per token, 182.54 tokens per second) 0.59.806.661 I slot print_timing: id 2 | task 189 | eval time = 303.08 ms / 2 tokens ( 303.08 ms per token, 3.30 tokens per second) 0.59.806.662 I slot print_timing: id 2 | task 189 | total time = 1278.22 ms / 180 tokens 0.59.806.662 I slot print_timing: id 2 | task 189 | graphs reused = 8 0.59.806.662 I slot print_timing: id 2 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.806.684 I slot release: id 2 | task 189 | stop processing: n_tokens = 188, truncated = 0 0.59.807.820 I slot print_timing: id 3 | task 190 | prompt eval time = 976.20 ms / 125 tokens ( 7.81 ms per token, 128.05 tokens per second) 0.59.807.822 I slot print_timing: id 3 | task 190 | eval time = 303.08 ms / 2 tokens ( 303.08 ms per token, 3.30 tokens per second) 0.59.807.823 I slot print_timing: id 3 | task 190 | total time = 1279.27 ms / 127 tokens 0.59.807.823 I slot print_timing: id 3 | task 190 | graphs reused = 8 0.59.807.823 I slot print_timing: id 3 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.807.838 I slot release: id 3 | task 190 | stop processing: n_tokens = 135, truncated = 0 0.59.842.974 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.302 (> 0.100 thold), f_keep = 0.281 0.59.846.595 I slot launch_slot_: id 3 | task 197 | processing task, is_child = 0 0.59.851.312 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.291 0.59.851.813 I slot launch_slot_: id 0 | task 198 | processing task, is_child = 0 0.59.851.844 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.197 0.59.851.901 I slot launch_slot_: id 2 | task 199 | processing task, is_child = 0 0.59.901.164 I slot print_timing: id 1 | task 193 | prompt eval time = 436.86 ms / 125 tokens ( 3.49 ms per token, 286.13 tokens per second) 0.59.901.169 I slot print_timing: id 1 | task 193 | eval time = 58.19 ms / 2 tokens ( 58.19 ms per token, 17.18 tokens per second) 0.59.901.170 I slot print_timing: id 1 | task 193 | total time = 495.06 ms / 127 tokens 0.59.901.170 I slot print_timing: id 1 | task 193 | graphs reused = 8 0.59.901.171 I slot print_timing: id 1 | task 193 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.901.190 I slot release: id 1 | task 193 | stop processing: n_tokens = 135, truncated = 0 1.00.543.152 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.274 1.00.625.856 I slot launch_slot_: id 1 | task 202 | processing task, is_child = 0 1.01.026.311 I slot print_timing: id 0 | task 198 | prompt eval time = 870.27 ms / 131 tokens ( 6.64 ms per token, 150.53 tokens per second) 1.01.026.315 I slot print_timing: id 0 | task 198 | eval time = 304.13 ms / 2 tokens ( 304.13 ms per token, 3.29 tokens per second) 1.01.026.316 I slot print_timing: id 0 | task 198 | total time = 1174.40 ms / 133 tokens 1.01.026.316 I slot print_timing: id 0 | task 198 | graphs reused = 8 1.01.026.317 I slot print_timing: id 0 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.026.339 I slot release: id 0 | task 198 | stop processing: n_tokens = 141, truncated = 0 1.01.027.452 I slot print_timing: id 2 | task 199 | prompt eval time = 871.24 ms / 143 tokens ( 6.09 ms per token, 164.13 tokens per second) 1.01.027.453 I slot print_timing: id 2 | task 199 | eval time = 304.19 ms / 2 tokens ( 304.19 ms per token, 3.29 tokens per second) 1.01.027.454 I slot print_timing: id 2 | task 199 | total time = 1175.43 ms / 145 tokens 1.01.027.454 I slot print_timing: id 2 | task 199 | graphs reused = 8 1.01.027.454 I slot print_timing: id 2 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.027.466 I slot release: id 2 | task 199 | stop processing: n_tokens = 153, truncated = 0 1.01.028.578 I slot print_timing: id 3 | task 197 | prompt eval time = 872.21 ms / 117 tokens ( 7.45 ms per token, 134.14 tokens per second) 1.01.028.580 I slot print_timing: id 3 | task 197 | eval time = 304.24 ms / 2 tokens ( 304.24 ms per token, 3.29 tokens per second) 1.01.028.581 I slot print_timing: id 3 | task 197 | total time = 1176.44 ms / 119 tokens 1.01.028.582 I slot print_timing: id 3 | task 197 | graphs reused = 8 1.01.028.582 I slot print_timing: id 3 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.028.591 I slot release: id 3 | task 197 | stop processing: n_tokens = 127, truncated = 0 1.01.063.292 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.262 1.01.066.345 I slot launch_slot_: id 0 | task 207 | processing task, is_child = 0 1.01.071.560 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.242 1.01.072.135 I slot launch_slot_: id 2 | task 206 | processing task, is_child = 0 1.01.072.163 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.291 1.01.072.225 I slot launch_slot_: id 3 | task 208 | processing task, is_child = 0 1.01.121.312 I slot print_timing: id 1 | task 202 | prompt eval time = 436.85 ms / 130 tokens ( 3.36 ms per token, 297.58 tokens per second) 1.01.121.314 I slot print_timing: id 1 | task 202 | eval time = 58.03 ms / 2 tokens ( 58.03 ms per token, 17.23 tokens per second) 1.01.121.314 I slot print_timing: id 1 | task 202 | total time = 494.88 ms / 132 tokens 1.01.121.315 I slot print_timing: id 1 | task 202 | graphs reused = 8 1.01.121.315 I slot print_timing: id 1 | task 202 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.121.330 I slot release: id 1 | task 202 | stop processing: n_tokens = 140, truncated = 0 1.01.819.262 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.325 (> 0.100 thold), f_keep = 0.264 1.01.836.421 I slot launch_slot_: id 1 | task 211 | processing task, is_child = 0 1.02.233.625 I slot print_timing: id 0 | task 207 | prompt eval time = 860.42 ms / 124 tokens ( 6.94 ms per token, 144.12 tokens per second) 1.02.233.630 I slot print_timing: id 0 | task 207 | eval time = 300.97 ms / 2 tokens ( 300.97 ms per token, 3.32 tokens per second) 1.02.233.631 I slot print_timing: id 0 | task 207 | total time = 1161.39 ms / 126 tokens 1.02.233.631 I slot print_timing: id 0 | task 207 | graphs reused = 8 1.02.233.632 I slot print_timing: id 0 | task 207 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.233.652 I slot release: id 0 | task 207 | stop processing: n_tokens = 134, truncated = 0 1.02.234.787 I slot print_timing: id 2 | task 206 | prompt eval time = 861.38 ms / 132 tokens ( 6.53 ms per token, 153.24 tokens per second) 1.02.234.789 I slot print_timing: id 2 | task 206 | eval time = 301.05 ms / 2 tokens ( 301.05 ms per token, 3.32 tokens per second) 1.02.234.789 I slot print_timing: id 2 | task 206 | total time = 1162.43 ms / 134 tokens 1.02.234.790 I slot print_timing: id 2 | task 206 | graphs reused = 8 1.02.234.790 I slot print_timing: id 2 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.234.808 I slot release: id 2 | task 206 | stop processing: n_tokens = 142, truncated = 0 1.02.235.975 I slot print_timing: id 3 | task 208 | prompt eval time = 862.33 ms / 131 tokens ( 6.58 ms per token, 151.91 tokens per second) 1.02.235.978 I slot print_timing: id 3 | task 208 | eval time = 301.17 ms / 2 tokens ( 301.17 ms per token, 3.32 tokens per second) 1.02.235.978 I slot print_timing: id 3 | task 208 | total time = 1163.50 ms / 133 tokens 1.02.235.978 I slot print_timing: id 3 | task 208 | graphs reused = 8 1.02.235.979 I slot print_timing: id 3 | task 208 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.236.002 I slot release: id 3 | task 208 | stop processing: n_tokens = 141, truncated = 0 1.02.270.490 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.276 1.02.271.715 I slot launch_slot_: id 0 | task 215 | processing task, is_child = 0 1.02.276.216 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.261 1.02.276.283 I slot launch_slot_: id 2 | task 216 | processing task, is_child = 0 1.02.276.316 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.262 1.02.276.841 I slot launch_slot_: id 3 | task 217 | processing task, is_child = 0 1.02.326.022 I slot print_timing: id 1 | task 211 | prompt eval time = 433.00 ms / 105 tokens ( 4.12 ms per token, 242.50 tokens per second) 1.02.326.024 I slot print_timing: id 1 | task 211 | eval time = 55.53 ms / 2 tokens ( 55.53 ms per token, 18.01 tokens per second) 1.02.326.025 I slot print_timing: id 1 | task 211 | total time = 488.53 ms / 107 tokens 1.02.326.025 I slot print_timing: id 1 | task 211 | graphs reused = 8 1.02.326.025 I slot print_timing: id 1 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.326.045 I slot release: id 1 | task 211 | stop processing: n_tokens = 115, truncated = 0 1.03.131.470 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.322 1.03.214.334 I slot launch_slot_: id 1 | task 220 | processing task, is_child = 0 1.03.670.055 I slot print_timing: id 0 | task 215 | prompt eval time = 1036.78 ms / 160 tokens ( 6.48 ms per token, 154.32 tokens per second) 1.03.670.060 I slot print_timing: id 0 | task 215 | eval time = 356.42 ms / 2 tokens ( 356.42 ms per token, 2.81 tokens per second) 1.03.670.061 I slot print_timing: id 0 | task 215 | total time = 1393.20 ms / 162 tokens 1.03.670.061 I slot print_timing: id 0 | task 215 | graphs reused = 8 1.03.670.062 I slot print_timing: id 0 | task 215 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.670.087 I slot release: id 0 | task 215 | stop processing: n_tokens = 170, truncated = 0 1.03.671.225 I slot print_timing: id 2 | task 216 | prompt eval time = 1037.77 ms / 173 tokens ( 6.00 ms per token, 166.70 tokens per second) 1.03.671.228 I slot print_timing: id 2 | task 216 | eval time = 356.48 ms / 2 tokens ( 356.48 ms per token, 2.81 tokens per second) 1.03.671.228 I slot print_timing: id 2 | task 216 | total time = 1394.25 ms / 175 tokens 1.03.671.228 I slot print_timing: id 2 | task 216 | graphs reused = 8 1.03.671.229 I slot print_timing: id 2 | task 216 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.671.253 I slot release: id 2 | task 216 | stop processing: n_tokens = 183, truncated = 0 1.03.672.404 I slot print_timing: id 3 | task 217 | prompt eval time = 1038.81 ms / 143 tokens ( 7.26 ms per token, 137.66 tokens per second) 1.03.672.413 I slot print_timing: id 3 | task 217 | eval time = 356.51 ms / 2 tokens ( 356.51 ms per token, 2.80 tokens per second) 1.03.672.414 I slot print_timing: id 3 | task 217 | total time = 1395.32 ms / 145 tokens 1.03.672.414 I slot print_timing: id 3 | task 217 | graphs reused = 8 1.03.672.414 I slot print_timing: id 3 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.672.429 I slot release: id 3 | task 217 | stop processing: n_tokens = 153, truncated = 0 1.03.708.487 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 1.03.712.316 I slot launch_slot_: id 0 | task 224 | processing task, is_child = 0 1.03.716.976 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.306 (> 0.100 thold), f_keep = 0.202 1.03.717.048 I slot launch_slot_: id 2 | task 225 | processing task, is_child = 0 1.03.717.077 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.242 1.03.717.625 I slot launch_slot_: id 3 | task 226 | processing task, is_child = 0 1.03.766.889 I slot print_timing: id 1 | task 220 | prompt eval time = 493.43 ms / 161 tokens ( 3.06 ms per token, 326.29 tokens per second) 1.03.766.894 I slot print_timing: id 1 | task 220 | eval time = 58.40 ms / 2 tokens ( 58.40 ms per token, 17.12 tokens per second) 1.03.766.894 I slot print_timing: id 1 | task 220 | total time = 551.83 ms / 163 tokens 1.03.766.895 I slot print_timing: id 1 | task 220 | graphs reused = 8 1.03.766.895 I slot print_timing: id 1 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.766.919 I slot release: id 1 | task 220 | stop processing: n_tokens = 171, truncated = 0 1.04.411.086 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.216 1.04.543.039 I slot launch_slot_: id 1 | task 229 | processing task, is_child = 0 1.04.993.698 I slot print_timing: id 0 | task 224 | prompt eval time = 922.30 ms / 113 tokens ( 8.16 ms per token, 122.52 tokens per second) 1.04.993.703 I slot print_timing: id 0 | task 224 | eval time = 353.76 ms / 2 tokens ( 353.76 ms per token, 2.83 tokens per second) 1.04.993.704 I slot print_timing: id 0 | task 224 | total time = 1276.06 ms / 115 tokens 1.04.993.704 I slot print_timing: id 0 | task 224 | graphs reused = 8 1.04.993.705 I slot print_timing: id 0 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.993.726 I slot release: id 0 | task 224 | stop processing: n_tokens = 123, truncated = 0 1.04.994.826 I slot print_timing: id 2 | task 225 | prompt eval time = 923.27 ms / 112 tokens ( 8.24 ms per token, 121.31 tokens per second) 1.04.994.829 I slot print_timing: id 2 | task 225 | eval time = 353.80 ms / 2 tokens ( 353.80 ms per token, 2.83 tokens per second) 1.04.994.830 I slot print_timing: id 2 | task 225 | total time = 1277.07 ms / 114 tokens 1.04.994.830 I slot print_timing: id 2 | task 225 | graphs reused = 8 1.04.994.831 I slot print_timing: id 2 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.994.851 I slot release: id 2 | task 225 | stop processing: n_tokens = 122, truncated = 0 1.04.995.953 I slot print_timing: id 3 | task 226 | prompt eval time = 924.31 ms / 152 tokens ( 6.08 ms per token, 164.45 tokens per second) 1.04.995.957 I slot print_timing: id 3 | task 226 | eval time = 353.78 ms / 2 tokens ( 353.78 ms per token, 2.83 tokens per second) 1.04.995.957 I slot print_timing: id 3 | task 226 | total time = 1278.09 ms / 154 tokens 1.04.995.957 I slot print_timing: id 3 | task 226 | graphs reused = 8 1.04.995.958 I slot print_timing: id 3 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.995.976 I slot release: id 3 | task 226 | stop processing: n_tokens = 162, truncated = 0 1.05.030.761 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 1.05.031.972 I slot launch_slot_: id 0 | task 233 | processing task, is_child = 0 1.05.036.495 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.303 1.05.036.566 I slot launch_slot_: id 2 | task 234 | processing task, is_child = 0 1.05.036.601 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.301 (> 0.100 thold), f_keep = 0.228 1.05.037.100 I slot launch_slot_: id 3 | task 235 | processing task, is_child = 0 1.05.086.329 I slot print_timing: id 1 | task 229 | prompt eval time = 486.76 ms / 140 tokens ( 3.48 ms per token, 287.61 tokens per second) 1.05.086.334 I slot print_timing: id 1 | task 229 | eval time = 55.58 ms / 2 tokens ( 55.58 ms per token, 17.99 tokens per second) 1.05.086.334 I slot print_timing: id 1 | task 229 | total time = 542.34 ms / 142 tokens 1.05.086.335 I slot print_timing: id 1 | task 229 | graphs reused = 8 1.05.086.335 I slot print_timing: id 1 | task 229 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.086.359 I slot release: id 1 | task 229 | stop processing: n_tokens = 150, truncated = 0 1.05.730.136 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.247 1.05.862.088 I slot launch_slot_: id 1 | task 238 | processing task, is_child = 0 1.06.262.214 I slot print_timing: id 0 | task 233 | prompt eval time = 921.54 ms / 112 tokens ( 8.23 ms per token, 121.54 tokens per second) 1.06.262.220 I slot print_timing: id 0 | task 233 | eval time = 303.56 ms / 2 tokens ( 303.56 ms per token, 3.29 tokens per second) 1.06.262.221 I slot print_timing: id 0 | task 233 | total time = 1225.10 ms / 114 tokens 1.06.262.221 I slot print_timing: id 0 | task 233 | graphs reused = 8 1.06.262.222 I slot print_timing: id 0 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.262.253 I slot release: id 0 | task 233 | stop processing: n_tokens = 122, truncated = 0 1.06.263.398 I slot print_timing: id 2 | task 234 | prompt eval time = 922.59 ms / 155 tokens ( 5.95 ms per token, 168.00 tokens per second) 1.06.263.401 I slot print_timing: id 2 | task 234 | eval time = 303.57 ms / 2 tokens ( 303.57 ms per token, 3.29 tokens per second) 1.06.263.402 I slot print_timing: id 2 | task 234 | total time = 1226.16 ms / 157 tokens 1.06.263.402 I slot print_timing: id 2 | task 234 | graphs reused = 8 1.06.263.402 I slot print_timing: id 2 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.263.426 I slot release: id 2 | task 234 | stop processing: n_tokens = 165, truncated = 0 1.06.264.639 I slot print_timing: id 3 | task 235 | prompt eval time = 923.68 ms / 114 tokens ( 8.10 ms per token, 123.42 tokens per second) 1.06.264.641 I slot print_timing: id 3 | task 235 | eval time = 303.61 ms / 2 tokens ( 303.61 ms per token, 3.29 tokens per second) 1.06.264.641 I slot print_timing: id 3 | task 235 | total time = 1227.29 ms / 116 tokens 1.06.264.642 I slot print_timing: id 3 | task 235 | graphs reused = 8 1.06.264.642 I slot print_timing: id 3 | task 235 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.264.654 I slot release: id 3 | task 235 | stop processing: n_tokens = 124, truncated = 0 1.06.299.385 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.292 (> 0.100 thold), f_keep = 0.311 1.06.300.512 I slot launch_slot_: id 0 | task 242 | processing task, is_child = 0 1.06.305.543 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.224 1.06.305.619 I slot launch_slot_: id 2 | task 243 | processing task, is_child = 0 1.06.305.647 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.298 1.06.305.706 I slot launch_slot_: id 3 | task 244 | processing task, is_child = 0 1.06.354.770 I slot print_timing: id 1 | task 238 | prompt eval time = 436.36 ms / 134 tokens ( 3.26 ms per token, 307.09 tokens per second) 1.06.354.774 I slot print_timing: id 1 | task 238 | eval time = 55.39 ms / 2 tokens ( 55.39 ms per token, 18.05 tokens per second) 1.06.354.774 I slot print_timing: id 1 | task 238 | total time = 491.75 ms / 136 tokens 1.06.354.775 I slot print_timing: id 1 | task 238 | graphs reused = 8 1.06.354.775 I slot print_timing: id 1 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.354.795 I slot release: id 1 | task 238 | stop processing: n_tokens = 144, truncated = 0 1.07.049.532 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.257 1.07.181.472 I slot launch_slot_: id 1 | task 247 | processing task, is_child = 0 1.07.635.065 I slot print_timing: id 0 | task 242 | prompt eval time = 973.05 ms / 121 tokens ( 8.04 ms per token, 124.35 tokens per second) 1.07.635.070 I slot print_timing: id 0 | task 242 | eval time = 356.30 ms / 2 tokens ( 356.30 ms per token, 2.81 tokens per second) 1.07.635.071 I slot print_timing: id 0 | task 242 | total time = 1329.35 ms / 123 tokens 1.07.635.071 I slot print_timing: id 0 | task 242 | graphs reused = 8 1.07.635.072 I slot print_timing: id 0 | task 242 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.635.108 I slot release: id 0 | task 242 | stop processing: n_tokens = 131, truncated = 0 1.07.636.185 I slot print_timing: id 2 | task 243 | prompt eval time = 974.06 ms / 170 tokens ( 5.73 ms per token, 174.53 tokens per second) 1.07.636.187 I slot print_timing: id 2 | task 243 | eval time = 356.28 ms / 2 tokens ( 356.28 ms per token, 2.81 tokens per second) 1.07.636.187 I slot print_timing: id 2 | task 243 | total time = 1330.34 ms / 172 tokens 1.07.636.188 I slot print_timing: id 2 | task 243 | graphs reused = 8 1.07.636.188 I slot print_timing: id 2 | task 243 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.636.220 I slot release: id 2 | task 243 | stop processing: n_tokens = 180, truncated = 0 1.07.637.366 I slot print_timing: id 3 | task 244 | prompt eval time = 975.17 ms / 125 tokens ( 7.80 ms per token, 128.18 tokens per second) 1.07.637.367 I slot print_timing: id 3 | task 244 | eval time = 356.23 ms / 2 tokens ( 356.23 ms per token, 2.81 tokens per second) 1.07.637.368 I slot print_timing: id 3 | task 244 | total time = 1331.40 ms / 127 tokens 1.07.637.368 I slot print_timing: id 3 | task 244 | graphs reused = 8 1.07.637.368 I slot print_timing: id 3 | task 244 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.637.382 I slot release: id 3 | task 244 | stop processing: n_tokens = 135, truncated = 0 1.07.673.166 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.311 (> 0.100 thold), f_keep = 0.282 1.07.675.423 I slot launch_slot_: id 0 | task 251 | processing task, is_child = 0 1.07.681.078 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.206 1.07.681.674 I slot launch_slot_: id 2 | task 252 | processing task, is_child = 0 1.07.681.702 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.274 1.07.681.767 I slot launch_slot_: id 3 | task 253 | processing task, is_child = 0 1.07.731.018 I slot print_timing: id 1 | task 247 | prompt eval time = 491.06 ms / 159 tokens ( 3.09 ms per token, 323.79 tokens per second) 1.07.731.021 I slot print_timing: id 1 | task 247 | eval time = 57.86 ms / 2 tokens ( 57.86 ms per token, 17.28 tokens per second) 1.07.731.021 I slot print_timing: id 1 | task 247 | total time = 548.91 ms / 161 tokens 1.07.731.021 I slot print_timing: id 1 | task 247 | graphs reused = 8 1.07.731.022 I slot print_timing: id 1 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.731.037 I slot release: id 1 | task 247 | stop processing: n_tokens = 169, truncated = 0 1.08.427.120 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.225 1.08.561.025 I slot launch_slot_: id 1 | task 256 | processing task, is_child = 0 1.09.014.697 I slot print_timing: id 0 | task 251 | prompt eval time = 977.36 ms / 110 tokens ( 8.89 ms per token, 112.55 tokens per second) 1.09.014.700 I slot print_timing: id 0 | task 251 | eval time = 355.56 ms / 2 tokens ( 355.56 ms per token, 2.81 tokens per second) 1.09.014.700 I slot print_timing: id 0 | task 251 | total time = 1332.92 ms / 112 tokens 1.09.014.701 I slot print_timing: id 0 | task 251 | graphs reused = 8 1.09.014.701 I slot print_timing: id 0 | task 251 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.014.738 I slot release: id 0 | task 251 | stop processing: n_tokens = 120, truncated = 0 1.09.015.864 I slot print_timing: id 2 | task 252 | prompt eval time = 978.41 ms / 131 tokens ( 7.47 ms per token, 133.89 tokens per second) 1.09.015.871 I slot print_timing: id 2 | task 252 | eval time = 355.56 ms / 2 tokens ( 355.56 ms per token, 2.81 tokens per second) 1.09.015.872 I slot print_timing: id 2 | task 252 | total time = 1333.97 ms / 133 tokens 1.09.015.872 I slot print_timing: id 2 | task 252 | graphs reused = 8 1.09.015.872 I slot print_timing: id 2 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.015.894 I slot release: id 2 | task 252 | stop processing: n_tokens = 141, truncated = 0 1.09.017.028 I slot print_timing: id 3 | task 253 | prompt eval time = 979.37 ms / 188 tokens ( 5.21 ms per token, 191.96 tokens per second) 1.09.017.029 I slot print_timing: id 3 | task 253 | eval time = 355.65 ms / 2 tokens ( 355.65 ms per token, 2.81 tokens per second) 1.09.017.030 I slot print_timing: id 3 | task 253 | total time = 1335.02 ms / 190 tokens 1.09.017.030 I slot print_timing: id 3 | task 253 | graphs reused = 8 1.09.017.031 I slot print_timing: id 3 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.017.056 I slot release: id 3 | task 253 | stop processing: n_tokens = 198, truncated = 0 1.09.051.872 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.308 1.09.052.998 I slot launch_slot_: id 0 | task 260 | processing task, is_child = 0 1.09.058.465 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.253 (> 0.100 thold), f_keep = 0.262 1.09.058.535 I slot launch_slot_: id 2 | task 261 | processing task, is_child = 0 1.09.058.574 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.187 1.09.059.179 I slot launch_slot_: id 3 | task 262 | processing task, is_child = 0 1.09.108.472 I slot print_timing: id 1 | task 256 | prompt eval time = 490.20 ms / 155 tokens ( 3.16 ms per token, 316.20 tokens per second) 1.09.108.477 I slot print_timing: id 1 | task 256 | eval time = 56.60 ms / 2 tokens ( 56.60 ms per token, 17.67 tokens per second) 1.09.108.478 I slot print_timing: id 1 | task 256 | total time = 546.80 ms / 157 tokens 1.09.108.478 I slot print_timing: id 1 | task 256 | graphs reused = 8 1.09.108.478 I slot print_timing: id 1 | task 256 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.108.498 I slot release: id 1 | task 256 | stop processing: n_tokens = 165, truncated = 0 1.09.801.462 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 1.09.884.151 I slot launch_slot_: id 1 | task 265 | processing task, is_child = 0 1.10.337.508 I slot print_timing: id 0 | task 260 | prompt eval time = 921.99 ms / 148 tokens ( 6.23 ms per token, 160.52 tokens per second) 1.10.337.511 I slot print_timing: id 0 | task 260 | eval time = 356.33 ms / 2 tokens ( 356.33 ms per token, 2.81 tokens per second) 1.10.337.513 I slot print_timing: id 0 | task 260 | total time = 1278.32 ms / 150 tokens 1.10.337.514 I slot print_timing: id 0 | task 260 | graphs reused = 8 1.10.337.514 I slot print_timing: id 0 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.337.543 I slot release: id 0 | task 260 | stop processing: n_tokens = 158, truncated = 0 1.10.338.667 I slot print_timing: id 2 | task 261 | prompt eval time = 923.01 ms / 137 tokens ( 6.74 ms per token, 148.43 tokens per second) 1.10.338.670 I slot print_timing: id 2 | task 261 | eval time = 356.36 ms / 2 tokens ( 356.36 ms per token, 2.81 tokens per second) 1.10.338.670 I slot print_timing: id 2 | task 261 | total time = 1279.36 ms / 139 tokens 1.10.338.670 I slot print_timing: id 2 | task 261 | graphs reused = 8 1.10.338.671 I slot print_timing: id 2 | task 261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.338.689 I slot release: id 2 | task 261 | stop processing: n_tokens = 147, truncated = 0 1.10.339.871 I slot print_timing: id 3 | task 262 | prompt eval time = 923.97 ms / 117 tokens ( 7.90 ms per token, 126.63 tokens per second) 1.10.339.872 I slot print_timing: id 3 | task 262 | eval time = 356.49 ms / 2 tokens ( 356.49 ms per token, 2.81 tokens per second) 1.10.339.873 I slot print_timing: id 3 | task 262 | total time = 1280.46 ms / 119 tokens 1.10.339.873 I slot print_timing: id 3 | task 262 | graphs reused = 8 1.10.339.873 I slot print_timing: id 3 | task 262 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.339.890 I slot release: id 3 | task 262 | stop processing: n_tokens = 127, truncated = 0 1.10.374.739 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.286 (> 0.100 thold), f_keep = 0.299 1.10.376.265 I slot launch_slot_: id 3 | task 269 | processing task, is_child = 0 1.10.380.411 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.241 1.10.380.477 I slot launch_slot_: id 0 | task 270 | processing task, is_child = 0 1.10.380.505 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.252 1.10.380.569 I slot launch_slot_: id 2 | task 271 | processing task, is_child = 0 1.11.256.829 I slot print_timing: id 1 | task 265 | prompt eval time = 489.12 ms / 159 tokens ( 3.08 ms per token, 325.08 tokens per second) 1.11.256.832 I slot print_timing: id 1 | task 265 | eval time = 882.09 ms / 3 tokens ( 441.04 ms per token, 2.27 tokens per second) 1.11.256.832 I slot print_timing: id 1 | task 265 | total time = 1371.20 ms / 162 tokens 1.11.256.833 I slot print_timing: id 1 | task 265 | graphs reused = 8 1.11.256.833 I slot print_timing: id 1 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.256.867 I slot release: id 1 | task 265 | stop processing: n_tokens = 170, truncated = 0 1.11.328.344 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.291 (> 0.100 thold), f_keep = 0.218 1.11.332.605 I slot launch_slot_: id 1 | task 275 | processing task, is_child = 0 1.11.395.737 I slot print_timing: id 0 | task 270 | prompt eval time = 945.46 ms / 152 tokens ( 6.22 ms per token, 160.77 tokens per second) 1.11.395.739 I slot print_timing: id 0 | task 270 | eval time = 69.70 ms / 2 tokens ( 69.70 ms per token, 14.35 tokens per second) 1.11.395.739 I slot print_timing: id 0 | task 270 | total time = 1015.16 ms / 154 tokens 1.11.395.739 I slot print_timing: id 0 | task 270 | graphs reused = 8 1.11.395.740 I slot print_timing: id 0 | task 270 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.395.765 I slot release: id 0 | task 270 | stop processing: n_tokens = 162, truncated = 0 1.11.396.880 I slot print_timing: id 2 | task 271 | prompt eval time = 946.46 ms / 136 tokens ( 6.96 ms per token, 143.69 tokens per second) 1.11.396.882 I slot print_timing: id 2 | task 271 | eval time = 69.73 ms / 2 tokens ( 69.73 ms per token, 14.34 tokens per second) 1.11.396.882 I slot print_timing: id 2 | task 271 | total time = 1016.18 ms / 138 tokens 1.11.396.882 I slot print_timing: id 2 | task 271 | graphs reused = 8 1.11.396.883 I slot print_timing: id 2 | task 271 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.396.893 I slot release: id 2 | task 271 | stop processing: n_tokens = 146, truncated = 0 1.11.398.005 I slot print_timing: id 3 | task 269 | prompt eval time = 947.52 ms / 124 tokens ( 7.64 ms per token, 130.87 tokens per second) 1.11.398.007 I slot print_timing: id 3 | task 269 | eval time = 69.67 ms / 2 tokens ( 69.67 ms per token, 14.35 tokens per second) 1.11.398.008 I slot print_timing: id 3 | task 269 | total time = 1017.19 ms / 126 tokens 1.11.398.008 I slot print_timing: id 3 | task 269 | graphs reused = 8 1.11.398.008 I slot print_timing: id 3 | task 269 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.398.027 I slot release: id 3 | task 269 | stop processing: n_tokens = 134, truncated = 0 1.11.399.967 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.228 1.11.638.232 I slot launch_slot_: id 0 | task 278 | processing task, is_child = 0 1.11.645.043 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.253 1.11.645.115 I slot launch_slot_: id 2 | task 279 | processing task, is_child = 0 1.11.645.143 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.276 1.11.645.210 I slot launch_slot_: id 3 | task 280 | processing task, is_child = 0 1.12.642.185 I slot print_timing: id 1 | task 275 | prompt eval time = 374.62 ms / 118 tokens ( 3.17 ms per token, 314.98 tokens per second) 1.12.642.189 I slot print_timing: id 1 | task 275 | eval time = 934.94 ms / 2 tokens ( 934.94 ms per token, 1.07 tokens per second) 1.12.642.189 I slot print_timing: id 1 | task 275 | total time = 1309.56 ms / 120 tokens 1.12.642.197 I slot print_timing: id 1 | task 275 | graphs reused = 8 1.12.642.197 I slot print_timing: id 1 | task 275 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.642.231 I slot release: id 1 | task 275 | stop processing: n_tokens = 128, truncated = 0 1.12.718.585 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.289 1.12.720.571 I slot launch_slot_: id 1 | task 284 | processing task, is_child = 0 1.12.783.611 I slot print_timing: id 0 | task 278 | prompt eval time = 1070.81 ms / 159 tokens ( 6.73 ms per token, 148.49 tokens per second) 1.12.783.617 I slot print_timing: id 0 | task 278 | eval time = 67.59 ms / 2 tokens ( 67.59 ms per token, 14.80 tokens per second) 1.12.783.617 I slot print_timing: id 0 | task 278 | total time = 1138.40 ms / 161 tokens 1.12.783.618 I slot print_timing: id 0 | task 278 | graphs reused = 8 1.12.783.618 I slot print_timing: id 0 | task 278 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.783.646 I slot release: id 0 | task 278 | stop processing: n_tokens = 169, truncated = 0 1.12.784.772 I slot print_timing: id 2 | task 279 | prompt eval time = 1071.45 ms / 164 tokens ( 6.53 ms per token, 153.06 tokens per second) 1.12.784.776 I slot print_timing: id 2 | task 279 | eval time = 67.44 ms / 2 tokens ( 67.44 ms per token, 14.83 tokens per second) 1.12.784.777 I slot print_timing: id 2 | task 279 | total time = 1138.88 ms / 166 tokens 1.12.784.777 I slot print_timing: id 2 | task 279 | graphs reused = 8 1.12.784.778 I slot print_timing: id 2 | task 279 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.784.789 I slot release: id 2 | task 279 | stop processing: n_tokens = 174, truncated = 0 1.12.785.885 I slot print_timing: id 3 | task 280 | prompt eval time = 1072.56 ms / 152 tokens ( 7.06 ms per token, 141.72 tokens per second) 1.12.785.886 I slot print_timing: id 3 | task 280 | eval time = 67.30 ms / 2 tokens ( 67.30 ms per token, 14.86 tokens per second) 1.12.785.887 I slot print_timing: id 3 | task 280 | total time = 1139.86 ms / 154 tokens 1.12.785.887 I slot print_timing: id 3 | task 280 | graphs reused = 8 1.12.785.888 I slot print_timing: id 3 | task 280 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.785.902 I slot release: id 3 | task 280 | stop processing: n_tokens = 162, truncated = 0 1.12.787.884 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.219 1.13.079.318 I slot launch_slot_: id 0 | task 287 | processing task, is_child = 0 1.13.088.736 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.314 (> 0.100 thold), f_keep = 0.213 1.13.089.323 I slot launch_slot_: id 2 | task 288 | processing task, is_child = 0 1.13.089.356 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.294 (> 0.100 thold), f_keep = 0.228 1.13.089.430 I slot launch_slot_: id 3 | task 289 | processing task, is_child = 0 1.13.909.155 I slot print_timing: id 1 | task 284 | prompt eval time = 431.33 ms / 154 tokens ( 2.80 ms per token, 357.03 tokens per second) 1.13.909.158 I slot print_timing: id 1 | task 284 | eval time = 757.24 ms / 2 tokens ( 757.24 ms per token, 1.32 tokens per second) 1.13.909.158 I slot print_timing: id 1 | task 284 | total time = 1188.57 ms / 156 tokens 1.13.909.159 I slot print_timing: id 1 | task 284 | graphs reused = 8 1.13.909.159 I slot print_timing: id 1 | task 284 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.909.190 I slot release: id 1 | task 284 | stop processing: n_tokens = 164, truncated = 0 1.13.982.575 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.226 1.13.985.441 I slot launch_slot_: id 1 | task 293 | processing task, is_child = 0 1.14.048.864 I slot print_timing: id 0 | task 287 | prompt eval time = 890.56 ms / 158 tokens ( 5.64 ms per token, 177.42 tokens per second) 1.14.048.867 I slot print_timing: id 0 | task 287 | eval time = 68.87 ms / 2 tokens ( 68.87 ms per token, 14.52 tokens per second) 1.14.048.867 I slot print_timing: id 0 | task 287 | total time = 959.43 ms / 160 tokens 1.14.048.868 I slot print_timing: id 0 | task 287 | graphs reused = 8 1.14.048.868 I slot print_timing: id 0 | task 287 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.048.888 I slot release: id 0 | task 287 | stop processing: n_tokens = 168, truncated = 0 1.14.050.020 I slot print_timing: id 2 | task 288 | prompt eval time = 891.11 ms / 109 tokens ( 8.18 ms per token, 122.32 tokens per second) 1.14.050.021 I slot print_timing: id 2 | task 288 | eval time = 68.68 ms / 2 tokens ( 68.68 ms per token, 14.56 tokens per second) 1.14.050.021 I slot print_timing: id 2 | task 288 | total time = 959.79 ms / 111 tokens 1.14.050.022 I slot print_timing: id 2 | task 288 | graphs reused = 8 1.14.050.022 I slot print_timing: id 2 | task 288 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.050.032 I slot release: id 2 | task 288 | stop processing: n_tokens = 119, truncated = 0 1.14.051.142 I slot print_timing: id 3 | task 289 | prompt eval time = 892.23 ms / 117 tokens ( 7.63 ms per token, 131.13 tokens per second) 1.14.051.143 I slot print_timing: id 3 | task 289 | eval time = 68.57 ms / 2 tokens ( 68.57 ms per token, 14.58 tokens per second) 1.14.051.144 I slot print_timing: id 3 | task 289 | total time = 960.80 ms / 119 tokens 1.14.051.144 I slot print_timing: id 3 | task 289 | graphs reused = 8 1.14.051.144 I slot print_timing: id 3 | task 289 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.051.153 I slot release: id 3 | task 289 | stop processing: n_tokens = 127, truncated = 0 1.14.053.279 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.330 (> 0.100 thold), f_keep = 0.220 1.14.407.808 I slot launch_slot_: id 0 | task 296 | processing task, is_child = 0 1.14.410.130 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.311 1.14.410.200 I slot launch_slot_: id 2 | task 298 | processing task, is_child = 0 1.14.410.228 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.291 1.14.410.780 I slot launch_slot_: id 3 | task 297 | processing task, is_child = 0 1.15.194.722 I slot print_timing: id 1 | task 293 | prompt eval time = 488.02 ms / 188 tokens ( 2.60 ms per token, 385.23 tokens per second) 1.15.194.726 I slot print_timing: id 1 | task 293 | eval time = 721.25 ms / 2 tokens ( 721.25 ms per token, 1.39 tokens per second) 1.15.194.727 I slot print_timing: id 1 | task 293 | total time = 1209.27 ms / 190 tokens 1.15.194.727 I slot print_timing: id 1 | task 293 | graphs reused = 8 1.15.194.727 I slot print_timing: id 1 | task 293 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.194.747 I slot release: id 1 | task 293 | stop processing: n_tokens = 198, truncated = 0 1.15.267.994 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.187 1.15.273.185 I slot launch_slot_: id 1 | task 302 | processing task, is_child = 0 1.15.336.112 I slot print_timing: id 0 | task 296 | prompt eval time = 854.57 ms / 103 tokens ( 8.30 ms per token, 120.53 tokens per second) 1.15.336.114 I slot print_timing: id 0 | task 296 | eval time = 70.76 ms / 2 tokens ( 70.76 ms per token, 14.13 tokens per second) 1.15.336.115 I slot print_timing: id 0 | task 296 | total time = 925.33 ms / 105 tokens 1.15.336.116 I slot print_timing: id 0 | task 296 | graphs reused = 8 1.15.336.116 I slot print_timing: id 0 | task 296 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.336.132 I slot release: id 0 | task 296 | stop processing: n_tokens = 113, truncated = 0 1.15.337.263 I slot print_timing: id 2 | task 298 | prompt eval time = 855.00 ms / 125 tokens ( 6.84 ms per token, 146.20 tokens per second) 1.15.337.264 I slot print_timing: id 2 | task 298 | eval time = 70.58 ms / 2 tokens ( 70.58 ms per token, 14.17 tokens per second) 1.15.337.265 I slot print_timing: id 2 | task 298 | total time = 925.59 ms / 127 tokens 1.15.337.265 I slot print_timing: id 2 | task 298 | graphs reused = 8 1.15.337.265 I slot print_timing: id 2 | task 298 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.337.277 I slot release: id 2 | task 298 | stop processing: n_tokens = 135, truncated = 0 1.15.338.402 I slot print_timing: id 3 | task 297 | prompt eval time = 856.19 ms / 113 tokens ( 7.58 ms per token, 131.98 tokens per second) 1.15.338.403 I slot print_timing: id 3 | task 297 | eval time = 70.41 ms / 2 tokens ( 70.41 ms per token, 14.20 tokens per second) 1.15.338.404 I slot print_timing: id 3 | task 297 | total time = 926.60 ms / 115 tokens 1.15.338.404 I slot print_timing: id 3 | task 297 | graphs reused = 8 1.15.338.405 I slot print_timing: id 3 | task 297 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.338.417 I slot release: id 3 | task 297 | stop processing: n_tokens = 123, truncated = 0 1.15.340.365 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.327 1.15.579.503 I slot launch_slot_: id 0 | task 305 | processing task, is_child = 0 1.15.583.128 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.247 (> 0.100 thold), f_keep = 0.309 1.15.583.196 I slot launch_slot_: id 3 | task 306 | processing task, is_child = 0 1.15.583.225 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.274 1.15.583.296 I slot launch_slot_: id 2 | task 307 | processing task, is_child = 0 1.16.569.895 I slot print_timing: id 1 | task 302 | prompt eval time = 373.07 ms / 128 tokens ( 2.91 ms per token, 343.10 tokens per second) 1.16.569.901 I slot print_timing: id 1 | task 302 | eval time = 923.63 ms / 2 tokens ( 923.63 ms per token, 1.08 tokens per second) 1.16.569.901 I slot print_timing: id 1 | task 302 | total time = 1296.70 ms / 130 tokens 1.16.569.902 I slot print_timing: id 1 | task 302 | graphs reused = 8 1.16.569.902 I slot print_timing: id 1 | task 302 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.569.923 I slot release: id 1 | task 302 | stop processing: n_tokens = 138, truncated = 0 1.16.646.217 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.268 1.16.649.700 I slot launch_slot_: id 1 | task 311 | processing task, is_child = 0 1.16.712.810 I slot print_timing: id 0 | task 305 | prompt eval time = 1060.35 ms / 166 tokens ( 6.39 ms per token, 156.55 tokens per second) 1.16.712.815 I slot print_timing: id 0 | task 305 | eval time = 69.16 ms / 2 tokens ( 69.16 ms per token, 14.46 tokens per second) 1.16.712.816 I slot print_timing: id 0 | task 305 | total time = 1129.51 ms / 168 tokens 1.16.712.816 I slot print_timing: id 0 | task 305 | graphs reused = 8 1.16.712.817 I slot print_timing: id 0 | task 305 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.712.841 I slot release: id 0 | task 305 | stop processing: n_tokens = 176, truncated = 0 1.16.715.042 I slot print_timing: id 3 | task 306 | prompt eval time = 1061.23 ms / 145 tokens ( 7.32 ms per token, 136.63 tokens per second) 1.16.715.044 I slot print_timing: id 3 | task 306 | eval time = 68.83 ms / 2 tokens ( 68.83 ms per token, 14.53 tokens per second) 1.16.715.044 I slot print_timing: id 3 | task 306 | total time = 1130.06 ms / 147 tokens 1.16.715.044 I slot print_timing: id 3 | task 306 | graphs reused = 8 1.16.715.045 I slot print_timing: id 3 | task 306 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.715.064 I slot release: id 3 | task 306 | stop processing: n_tokens = 155, truncated = 0 1.17.024.989 I slot print_timing: id 2 | task 307 | prompt eval time = 1060.08 ms / 127 tokens ( 8.35 ms per token, 119.80 tokens per second) 1.17.024.994 I slot print_timing: id 2 | task 307 | eval time = 380.03 ms / 3 tokens ( 190.01 ms per token, 5.26 tokens per second) 1.17.024.994 I slot print_timing: id 2 | task 307 | total time = 1440.11 ms / 130 tokens 1.17.024.995 I slot print_timing: id 2 | task 307 | graphs reused = 8 1.17.024.995 I slot print_timing: id 2 | task 307 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.025.015 I slot release: id 2 | task 307 | stop processing: n_tokens = 138, truncated = 0 1.17.025.022 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.278 (> 0.100 thold), f_keep = 0.210 1.17.029.930 I slot launch_slot_: id 0 | task 314 | processing task, is_child = 0 1.17.034.062 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.268 1.17.034.549 I slot launch_slot_: id 2 | task 315 | processing task, is_child = 0 1.17.034.578 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.239 1.17.035.105 I slot launch_slot_: id 3 | task 316 | processing task, is_child = 0 1.17.962.091 I slot print_timing: id 1 | task 311 | prompt eval time = 447.38 ms / 139 tokens ( 3.22 ms per token, 310.70 tokens per second) 1.17.962.096 I slot print_timing: id 1 | task 311 | eval time = 865.00 ms / 2 tokens ( 865.00 ms per token, 1.16 tokens per second) 1.17.962.097 I slot print_timing: id 1 | task 311 | total time = 1312.38 ms / 141 tokens 1.17.962.097 I slot print_timing: id 1 | task 311 | graphs reused = 8 1.17.962.098 I slot print_timing: id 1 | task 311 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.962.123 I slot release: id 1 | task 311 | stop processing: n_tokens = 149, truncated = 0 1.18.034.905 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.248 1.18.037.441 I slot launch_slot_: id 1 | task 320 | processing task, is_child = 0 1.18.100.618 I slot print_timing: id 0 | task 314 | prompt eval time = 997.36 ms / 124 tokens ( 8.04 ms per token, 124.33 tokens per second) 1.18.100.620 I slot print_timing: id 0 | task 314 | eval time = 68.14 ms / 2 tokens ( 68.14 ms per token, 14.68 tokens per second) 1.18.100.621 I slot print_timing: id 0 | task 314 | total time = 1065.50 ms / 126 tokens 1.18.100.621 I slot print_timing: id 0 | task 314 | graphs reused = 8 1.18.100.621 I slot print_timing: id 0 | task 314 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.100.638 I slot release: id 0 | task 314 | stop processing: n_tokens = 134, truncated = 0 1.18.101.752 I slot print_timing: id 2 | task 315 | prompt eval time = 997.88 ms / 161 tokens ( 6.20 ms per token, 161.34 tokens per second) 1.18.101.760 I slot print_timing: id 2 | task 315 | eval time = 68.15 ms / 2 tokens ( 68.15 ms per token, 14.67 tokens per second) 1.18.101.760 I slot print_timing: id 2 | task 315 | total time = 1066.02 ms / 163 tokens 1.18.101.760 I slot print_timing: id 2 | task 315 | graphs reused = 8 1.18.101.761 I slot print_timing: id 2 | task 315 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.101.778 I slot release: id 2 | task 315 | stop processing: n_tokens = 171, truncated = 0 1.18.102.895 I slot print_timing: id 3 | task 316 | prompt eval time = 999.07 ms / 142 tokens ( 7.04 ms per token, 142.13 tokens per second) 1.18.102.897 I slot print_timing: id 3 | task 316 | eval time = 67.99 ms / 2 tokens ( 67.99 ms per token, 14.71 tokens per second) 1.18.102.898 I slot print_timing: id 3 | task 316 | total time = 1067.06 ms / 144 tokens 1.18.102.898 I slot print_timing: id 3 | task 316 | graphs reused = 8 1.18.102.898 I slot print_timing: id 3 | task 316 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.102.909 I slot release: id 3 | task 316 | stop processing: n_tokens = 152, truncated = 0 1.18.105.089 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.282 (> 0.100 thold), f_keep = 0.276 1.18.456.992 I slot launch_slot_: id 0 | task 323 | processing task, is_child = 0 1.18.463.412 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.216 1.18.464.074 I slot launch_slot_: id 2 | task 324 | processing task, is_child = 0 1.18.464.106 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.216 (> 0.100 thold), f_keep = 0.243 1.18.464.174 I slot launch_slot_: id 3 | task 325 | processing task, is_child = 0 1.19.446.476 I slot print_timing: id 1 | task 320 | prompt eval time = 489.48 ms / 173 tokens ( 2.83 ms per token, 353.43 tokens per second) 1.19.446.479 I slot print_timing: id 1 | task 320 | eval time = 919.54 ms / 2 tokens ( 919.54 ms per token, 1.09 tokens per second) 1.19.446.479 I slot print_timing: id 1 | task 320 | total time = 1409.02 ms / 175 tokens 1.19.446.480 I slot print_timing: id 1 | task 320 | graphs reused = 8 1.19.446.480 I slot print_timing: id 1 | task 320 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.446.502 I slot release: id 1 | task 320 | stop processing: n_tokens = 183, truncated = 0 1.19.521.385 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.325 (> 0.100 thold), f_keep = 0.202 1.19.525.667 I slot launch_slot_: id 1 | task 329 | processing task, is_child = 0 1.19.588.939 I slot print_timing: id 0 | task 323 | prompt eval time = 1054.87 ms / 122 tokens ( 8.65 ms per token, 115.65 tokens per second) 1.19.588.942 I slot print_timing: id 0 | task 323 | eval time = 69.88 ms / 2 tokens ( 69.88 ms per token, 14.31 tokens per second) 1.19.588.943 I slot print_timing: id 0 | task 323 | total time = 1124.76 ms / 124 tokens 1.19.588.943 I slot print_timing: id 0 | task 323 | graphs reused = 8 1.19.588.944 I slot print_timing: id 0 | task 323 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.588.964 I slot release: id 0 | task 323 | stop processing: n_tokens = 132, truncated = 0 1.19.590.060 I slot print_timing: id 2 | task 324 | prompt eval time = 1055.08 ms / 190 tokens ( 5.55 ms per token, 180.08 tokens per second) 1.19.590.062 I slot print_timing: id 2 | task 324 | eval time = 69.89 ms / 2 tokens ( 69.89 ms per token, 14.31 tokens per second) 1.19.590.063 I slot print_timing: id 2 | task 324 | total time = 1124.96 ms / 192 tokens 1.19.590.063 I slot print_timing: id 2 | task 324 | graphs reused = 8 1.19.590.063 I slot print_timing: id 2 | task 324 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.590.081 I slot release: id 2 | task 324 | stop processing: n_tokens = 200, truncated = 0 1.19.591.187 I slot print_timing: id 3 | task 325 | prompt eval time = 1056.15 ms / 162 tokens ( 6.52 ms per token, 153.39 tokens per second) 1.19.591.189 I slot print_timing: id 3 | task 325 | eval time = 69.81 ms / 2 tokens ( 69.81 ms per token, 14.33 tokens per second) 1.19.591.190 I slot print_timing: id 3 | task 325 | total time = 1125.96 ms / 164 tokens 1.19.591.190 I slot print_timing: id 3 | task 325 | graphs reused = 8 1.19.591.190 I slot print_timing: id 3 | task 325 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.591.201 I slot release: id 3 | task 325 | stop processing: n_tokens = 172, truncated = 0 1.19.593.036 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.280 1.19.830.245 I slot launch_slot_: id 0 | task 332 | processing task, is_child = 0 1.19.837.472 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.185 1.19.837.545 I slot launch_slot_: id 2 | task 333 | processing task, is_child = 0 1.19.837.580 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.215 1.19.837.648 I slot launch_slot_: id 3 | task 334 | processing task, is_child = 0 1.20.757.663 I slot print_timing: id 1 | task 329 | prompt eval time = 374.07 ms / 105 tokens ( 3.56 ms per token, 280.70 tokens per second) 1.20.757.666 I slot print_timing: id 1 | task 329 | eval time = 857.91 ms / 2 tokens ( 857.91 ms per token, 1.17 tokens per second) 1.20.757.667 I slot print_timing: id 1 | task 329 | total time = 1231.98 ms / 107 tokens 1.20.757.667 I slot print_timing: id 1 | task 329 | graphs reused = 8 1.20.757.668 I slot print_timing: id 1 | task 329 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.757.688 I slot release: id 1 | task 329 | stop processing: n_tokens = 115, truncated = 0 1.20.882.712 I slot print_timing: id 0 | task 332 | prompt eval time = 990.61 ms / 136 tokens ( 7.28 ms per token, 137.29 tokens per second) 1.20.882.716 I slot print_timing: id 0 | task 332 | eval time = 54.45 ms / 2 tokens ( 54.45 ms per token, 18.37 tokens per second) 1.20.882.717 I slot print_timing: id 0 | task 332 | total time = 1045.06 ms / 138 tokens 1.20.882.717 I slot print_timing: id 0 | task 332 | graphs reused = 8 1.20.882.717 I slot print_timing: id 0 | task 332 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.882.739 I slot release: id 0 | task 332 | stop processing: n_tokens = 146, truncated = 0 1.20.883.888 I slot print_timing: id 2 | task 333 | prompt eval time = 991.34 ms / 126 tokens ( 7.87 ms per token, 127.10 tokens per second) 1.20.883.890 I slot print_timing: id 2 | task 333 | eval time = 54.32 ms / 2 tokens ( 54.32 ms per token, 18.41 tokens per second) 1.20.883.890 I slot print_timing: id 2 | task 333 | total time = 1045.66 ms / 128 tokens 1.20.883.890 I slot print_timing: id 2 | task 333 | graphs reused = 8 1.20.883.891 I slot print_timing: id 2 | task 333 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.883.899 I slot release: id 2 | task 333 | stop processing: n_tokens = 136, truncated = 0 1.20.885.015 I slot print_timing: id 3 | task 334 | prompt eval time = 992.48 ms / 146 tokens ( 6.80 ms per token, 147.11 tokens per second) 1.20.885.017 I slot print_timing: id 3 | task 334 | eval time = 54.16 ms / 2 tokens ( 54.16 ms per token, 18.46 tokens per second) 1.20.885.018 I slot print_timing: id 3 | task 334 | total time = 1046.65 ms / 148 tokens 1.20.885.018 I slot print_timing: id 3 | task 334 | graphs reused = 8 1.20.885.018 I slot print_timing: id 3 | task 334 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.885.026 I slot release: id 3 | task 334 | stop processing: n_tokens = 156, truncated = 0 1.20.899.959 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 115, t_last = 328736041792 1.20.901.006 I slot launch_slot_: id 1 | task 339 | processing task, is_child = 0 1.20.907.898 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 146, t_last = 328736166843 1.20.907.940 I slot launch_slot_: id 0 | task 340 | processing task, is_child = 0 1.20.907.994 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 136, t_last = 328736168003 1.20.908.030 I slot launch_slot_: id 2 | task 341 | processing task, is_child = 0 1.20.908.063 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 156, t_last = 328736169130 1.20.908.103 I slot launch_slot_: id 3 | task 342 | processing task, is_child = 0 1.24.684.150 I slot print_timing: id 0 | task 340 | prompt processing, n_tokens = 683, progress = 0.57, t = 3.78 s / 180.88 tokens per second 1.24.733.282 I slot print_timing: id 1 | task 339 | prompt processing, n_tokens = 674, progress = 0.57, t = 3.78 s / 178.50 tokens per second 1.24.739.410 I slot print_timing: id 2 | task 341 | prompt processing, n_tokens = 670, progress = 0.57, t = 3.78 s / 177.44 tokens per second 1.24.744.084 I slot print_timing: id 3 | task 342 | prompt processing, n_tokens = 21, progress = 0.03, t = 3.78 s / 5.56 tokens per second 1.27.866.997 I slot print_timing: id 0 | task 340 | prompt processing, n_tokens = 1086, progress = 0.91, t = 6.96 s / 156.06 tokens per second 1.28.294.469 I slot print_timing: id 1 | task 339 | prompt processing, n_tokens = 1086, progress = 0.91, t = 6.96 s / 156.06 tokens per second 1.28.299.350 I slot print_timing: id 2 | task 341 | prompt processing, n_tokens = 1086, progress = 0.92, t = 6.96 s / 156.06 tokens per second 1.28.303.975 I slot print_timing: id 3 | task 342 | prompt processing, n_tokens = 655, progress = 0.56, t = 6.96 s / 94.13 tokens per second 1.29.105.171 I slot print_timing: id 0 | task 340 | prompt processing, n_tokens = 1195, progress = 1.00, t = 8.20 s / 145.78 tokens per second 1.29.760.343 I slot print_timing: id 1 | task 339 | prompt processing, n_tokens = 1186, progress = 1.00, t = 8.20 s / 144.69 tokens per second 1.29.766.140 I slot print_timing: id 2 | task 341 | prompt processing, n_tokens = 1182, progress = 1.00, t = 8.20 s / 144.20 tokens per second 1.29.770.625 I slot print_timing: id 3 | task 342 | prompt processing, n_tokens = 1086, progress = 0.93, t = 8.20 s / 132.49 tokens per second 1.30.037.350 I slot print_timing: id 3 | task 342 | prompt processing, n_tokens = 1167, progress = 1.00, t = 9.13 s / 127.88 tokens per second 1.32.531.565 I slot print_timing: id 3 | task 342 | prompt eval time = 9205.74 ms / 1171 tokens ( 7.86 ms per token, 127.20 tokens per second) 1.32.531.569 I slot print_timing: id 3 | task 342 | eval time = 2417.44 ms / 60 tokens ( 40.97 ms per token, 24.41 tokens per second) 1.32.531.571 I slot print_timing: id 3 | task 342 | total time = 11623.18 ms / 1231 tokens 1.32.531.572 I slot print_timing: id 3 | task 342 | graphs reused = 67 1.32.531.572 I slot print_timing: id 3 | task 342 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.531.640 I slot release: id 3 | task 342 | stop processing: n_tokens = 1239, truncated = 0 1.32.571.499 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.900 1.32.571.522 I slot launch_slot_: id 3 | task 408 | processing task, is_child = 0 1.33.097.817 I slot print_timing: id 2 | task 341 | prompt eval time = 9129.04 ms / 1186 tokens ( 7.70 ms per token, 129.92 tokens per second) 1.33.097.823 I slot print_timing: id 2 | task 341 | eval time = 3060.48 ms / 68 tokens ( 45.68 ms per token, 21.89 tokens per second) 1.33.097.823 I slot print_timing: id 2 | task 341 | total time = 12189.52 ms / 1254 tokens 1.33.097.824 I slot print_timing: id 2 | task 341 | graphs reused = 70 1.33.097.824 I slot print_timing: id 2 | task 341 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.097.869 I slot release: id 2 | task 341 | stop processing: n_tokens = 1262, truncated = 0 1.33.154.440 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.884 1.33.154.460 I slot launch_slot_: id 2 | task 416 | processing task, is_child = 0 1.34.748.043 I slot print_timing: id 0 | task 340 | n_gen = 100, tg = 21.01 t/s, tg_3s = 21.22 t/s 1.34.749.638 I slot print_timing: id 1 | task 339 | n_gen = 100, tg = 21.00 t/s, tg_3s = 21.22 t/s 1.35.572.336 I slot print_timing: id 0 | task 340 | prompt eval time = 9126.89 ms / 1199 tokens ( 7.61 ms per token, 131.37 tokens per second) 1.35.572.342 I slot print_timing: id 0 | task 340 | eval time = 5537.33 ms / 120 tokens ( 46.53 ms per token, 21.49 tokens per second) 1.35.572.343 I slot print_timing: id 0 | task 340 | total time = 14664.22 ms / 1319 tokens 1.35.572.343 I slot print_timing: id 0 | task 340 | graphs reused = 117 1.35.572.344 I slot print_timing: id 0 | task 340 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.572.411 I slot release: id 0 | task 340 | stop processing: n_tokens = 1327, truncated = 0 1.35.616.916 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.840 1.35.616.940 I slot launch_slot_: id 0 | task 469 | processing task, is_child = 0 1.36.027.129 I slot print_timing: id 1 | task 339 | prompt eval time = 9127.94 ms / 1190 tokens ( 7.67 ms per token, 130.37 tokens per second) 1.36.027.135 I slot print_timing: id 1 | task 339 | eval time = 5990.98 ms / 124 tokens ( 48.71 ms per token, 20.53 tokens per second) 1.36.027.136 I slot print_timing: id 1 | task 339 | total time = 15118.92 ms / 1314 tokens 1.36.027.136 I slot print_timing: id 1 | task 339 | graphs reused = 118 1.36.027.137 I slot print_timing: id 1 | task 339 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.027.184 I slot release: id 1 | task 339 | stop processing: n_tokens = 1322, truncated = 0 1.36.084.668 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.843 1.36.084.689 I slot launch_slot_: id 1 | task 474 | processing task, is_child = 0 1.37.481.592 I slot print_timing: id 3 | task 408 | prompt eval time = 371.25 ms / 107 tokens ( 3.47 ms per token, 288.21 tokens per second) 1.37.481.599 I slot print_timing: id 3 | task 408 | eval time = 4538.81 ms / 89 tokens ( 51.58 ms per token, 19.39 tokens per second) 1.37.481.600 I slot print_timing: id 3 | task 408 | total time = 4910.06 ms / 196 tokens 1.37.481.600 I slot print_timing: id 3 | task 408 | graphs reused = 142 1.37.481.601 I slot print_timing: id 3 | task 408 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.481.659 I slot release: id 3 | task 408 | stop processing: n_tokens = 1310, truncated = 0 1.37.521.144 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.851 1.37.521.166 I slot launch_slot_: id 3 | task 503 | processing task, is_child = 0 1.38.291.643 I slot print_timing: id 2 | task 416 | prompt eval time = 408.32 ms / 114 tokens ( 3.58 ms per token, 279.19 tokens per second) 1.38.291.650 I slot print_timing: id 2 | task 416 | eval time = 4728.85 ms / 95 tokens ( 50.31 ms per token, 19.88 tokens per second) 1.38.291.651 I slot print_timing: id 2 | task 416 | total time = 5137.17 ms / 209 tokens 1.38.291.651 I slot print_timing: id 2 | task 416 | graphs reused = 151 1.38.291.652 I slot print_timing: id 2 | task 416 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.291.738 I slot release: id 2 | task 416 | stop processing: n_tokens = 1323, truncated = 0 1.38.353.608 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.843 1.38.353.633 I slot launch_slot_: id 2 | task 517 | processing task, is_child = 0 1.41.025.805 I slot print_timing: id 0 | task 469 | n_gen = 100, tg = 19.65 t/s, tg_3s = 19.84 t/s 1.41.191.457 I slot print_timing: id 1 | task 474 | n_gen = 100, tg = 20.91 t/s, tg_3s = 21.12 t/s 1.41.232.292 I slot print_timing: id 1 | task 474 | prompt eval time = 372.44 ms / 89 tokens ( 4.18 ms per token, 238.96 tokens per second) 1.41.232.296 I slot print_timing: id 1 | task 474 | eval time = 4775.15 ms / 101 tokens ( 47.75 ms per token, 20.94 tokens per second) 1.41.232.296 I slot print_timing: id 1 | task 474 | total time = 5147.60 ms / 190 tokens 1.41.232.297 I slot print_timing: id 1 | task 474 | graphs reused = 208 1.41.232.298 I slot print_timing: id 1 | task 474 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.232.364 I slot release: id 1 | task 474 | stop processing: n_tokens = 1304, truncated = 0 1.41.293.665 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.855 1.41.293.691 I slot launch_slot_: id 1 | task 580 | processing task, is_child = 0 1.42.655.421 I slot print_timing: id 3 | task 503 | n_gen = 100, tg = 20.79 t/s, tg_3s = 21.00 t/s 1.43.155.068 I slot print_timing: id 3 | task 503 | prompt eval time = 371.82 ms / 118 tokens ( 3.15 ms per token, 317.36 tokens per second) 1.43.155.074 I slot print_timing: id 3 | task 503 | eval time = 5262.08 ms / 112 tokens ( 47.41 ms per token, 21.09 tokens per second) 1.43.155.075 I slot print_timing: id 3 | task 503 | total time = 5633.89 ms / 230 tokens 1.43.155.076 I slot print_timing: id 3 | task 503 | graphs reused = 243 1.43.155.076 I slot print_timing: id 3 | task 503 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.155.136 I slot release: id 3 | task 503 | stop processing: n_tokens = 1344, truncated = 0 1.43.194.695 I slot print_timing: id 2 | task 517 | n_gen = 100, tg = 22.61 t/s, tg_3s = 22.84 t/s 1.43.194.701 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.830 1.43.194.728 I slot launch_slot_: id 3 | task 620 | processing task, is_child = 0 1.43.542.626 I slot print_timing: id 0 | task 469 | prompt eval time = 369.49 ms / 117 tokens ( 3.16 ms per token, 316.65 tokens per second) 1.43.542.631 I slot print_timing: id 0 | task 469 | eval time = 7556.19 ms / 148 tokens ( 51.40 ms per token, 19.45 tokens per second) 1.43.542.631 I slot print_timing: id 0 | task 469 | total time = 7925.68 ms / 265 tokens 1.43.542.632 I slot print_timing: id 0 | task 469 | graphs reused = 243 1.43.542.632 I slot print_timing: id 0 | task 469 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.542.684 I slot release: id 0 | task 469 | stop processing: n_tokens = 1379, truncated = 0 1.43.583.320 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.809 1.43.583.337 I slot launch_slot_: id 0 | task 625 | processing task, is_child = 0 1.45.988.453 I slot print_timing: id 1 | task 580 | prompt eval time = 370.85 ms / 100 tokens ( 3.71 ms per token, 269.65 tokens per second) 1.45.988.459 I slot print_timing: id 1 | task 580 | eval time = 4323.90 ms / 95 tokens ( 46.00 ms per token, 21.74 tokens per second) 1.45.988.460 I slot print_timing: id 1 | task 580 | total time = 4694.75 ms / 195 tokens 1.45.988.461 I slot print_timing: id 1 | task 580 | graphs reused = 294 1.45.988.461 I slot print_timing: id 1 | task 580 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.988.514 I slot release: id 1 | task 580 | stop processing: n_tokens = 1309, truncated = 0 1.46.049.756 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.852 1.46.049.783 I slot launch_slot_: id 1 | task 680 | processing task, is_child = 0 1.46.313.472 I slot print_timing: id 2 | task 517 | n_gen = 159, tg = 21.07 t/s, tg_3s = 18.92 t/s 1.47.236.843 I slot print_timing: id 3 | task 620 | prompt eval time = 311.22 ms / 76 tokens ( 4.09 ms per token, 244.20 tokens per second) 1.47.236.847 I slot print_timing: id 3 | task 620 | eval time = 3730.89 ms / 79 tokens ( 47.83 ms per token, 20.91 tokens per second) 1.47.236.847 I slot print_timing: id 3 | task 620 | total time = 4042.11 ms / 155 tokens 1.47.236.848 I slot print_timing: id 3 | task 620 | graphs reused = 313 1.47.236.848 I slot print_timing: id 3 | task 620 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.236.906 I slot release: id 3 | task 620 | stop processing: n_tokens = 1269, truncated = 0 1.47.276.457 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.879 1.47.276.483 I slot launch_slot_: id 3 | task 704 | processing task, is_child = 0 1.48.116.095 I slot print_timing: id 0 | task 625 | prompt eval time = 305.40 ms / 76 tokens ( 4.02 ms per token, 248.85 tokens per second) 1.48.116.102 I slot print_timing: id 0 | task 625 | eval time = 4227.35 ms / 91 tokens ( 46.97 ms per token, 21.29 tokens per second) 1.48.116.103 I slot print_timing: id 0 | task 625 | total time = 4532.75 ms / 167 tokens 1.48.116.103 I slot print_timing: id 0 | task 625 | graphs reused = 325 1.48.116.104 I slot print_timing: id 0 | task 625 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.116.161 I slot release: id 0 | task 625 | stop processing: n_tokens = 1281, truncated = 0 1.48.160.469 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.870 1.48.160.491 I slot launch_slot_: id 0 | task 721 | processing task, is_child = 0 1.49.348.142 I slot print_timing: id 2 | task 517 | n_gen = 219, tg = 20.70 t/s, tg_3s = 19.77 t/s 1.50.257.584 I slot print_timing: id 3 | task 704 | prompt eval time = 317.02 ms / 99 tokens ( 3.20 ms per token, 312.28 tokens per second) 1.50.257.591 I slot print_timing: id 3 | task 704 | eval time = 2664.06 ms / 59 tokens ( 45.93 ms per token, 21.77 tokens per second) 1.50.257.591 I slot print_timing: id 3 | task 704 | total time = 2981.09 ms / 158 tokens 1.50.257.592 I slot print_timing: id 3 | task 704 | graphs reused = 367 1.50.257.593 I slot print_timing: id 3 | task 704 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.257.662 I slot release: id 3 | task 704 | stop processing: n_tokens = 1272, truncated = 0 1.50.297.286 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.877 1.50.297.307 I slot launch_slot_: id 3 | task 767 | processing task, is_child = 0 1.51.124.374 I slot print_timing: id 2 | task 517 | prompt eval time = 462.46 ms / 145 tokens ( 3.19 ms per token, 313.54 tokens per second) 1.51.124.382 I slot print_timing: id 2 | task 517 | eval time = 12308.27 ms / 258 tokens ( 47.89 ms per token, 20.88 tokens per second) 1.51.124.382 I slot print_timing: id 2 | task 517 | total time = 12770.73 ms / 403 tokens 1.51.124.383 I slot print_timing: id 2 | task 517 | graphs reused = 380 1.51.124.383 I slot print_timing: id 2 | task 517 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.124.456 I slot release: id 2 | task 517 | stop processing: n_tokens = 1517, truncated = 0 1.51.182.534 I slot print_timing: id 1 | task 680 | n_gen = 100, tg = 20.77 t/s, tg_3s = 20.98 t/s 1.51.184.317 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.735 1.51.184.340 I slot launch_slot_: id 2 | task 785 | processing task, is_child = 0 1.53.110.771 I slot print_timing: id 0 | task 721 | n_gen = 100, tg = 21.61 t/s, tg_3s = 21.83 t/s 1.54.222.002 I slot print_timing: id 1 | task 680 | n_gen = 166, tg = 21.14 t/s, tg_3s = 21.71 t/s 1.54.718.629 I slot print_timing: id 3 | task 767 | prompt eval time = 259.15 ms / 62 tokens ( 4.18 ms per token, 239.24 tokens per second) 1.54.718.634 I slot print_timing: id 3 | task 767 | eval time = 4162.16 ms / 94 tokens ( 44.75 ms per token, 22.34 tokens per second) 1.54.718.634 I slot print_timing: id 3 | task 767 | total time = 4421.31 ms / 156 tokens 1.54.718.635 I slot print_timing: id 3 | task 767 | graphs reused = 455 1.54.718.636 I slot print_timing: id 3 | task 767 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.718.704 I slot release: id 3 | task 767 | stop processing: n_tokens = 1270, truncated = 0 1.54.758.528 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.878 1.54.758.552 I slot launch_slot_: id 3 | task 865 | processing task, is_child = 0 1.55.889.444 I slot print_timing: id 2 | task 785 | n_gen = 100, tg = 23.01 t/s, tg_3s = 23.25 t/s 1.56.135.658 I slot print_timing: id 0 | task 721 | n_gen = 168, tg = 21.95 t/s, tg_3s = 22.48 t/s 1.56.509.915 I slot print_timing: id 1 | task 680 | prompt eval time = 365.97 ms / 72 tokens ( 5.08 ms per token, 196.74 tokens per second) 1.56.509.923 I slot print_timing: id 1 | task 680 | eval time = 10094.15 ms / 216 tokens ( 46.95 ms per token, 21.30 tokens per second) 1.56.509.923 I slot print_timing: id 1 | task 680 | total time = 10460.12 ms / 288 tokens 1.56.509.924 I slot print_timing: id 1 | task 680 | graphs reused = 489 1.56.509.925 I slot print_timing: id 1 | task 680 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.510.013 I slot release: id 1 | task 680 | stop processing: n_tokens = 1402, truncated = 0 1.56.571.796 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.795 1.56.571.825 I slot launch_slot_: id 1 | task 904 | processing task, is_child = 0 1.57.294.812 I slot print_timing: id 0 | task 721 | prompt eval time = 368.67 ms / 125 tokens ( 2.95 ms per token, 339.06 tokens per second) 1.57.294.817 I slot print_timing: id 0 | task 721 | eval time = 8765.65 ms / 190 tokens ( 46.38 ms per token, 21.56 tokens per second) 1.57.294.818 I slot print_timing: id 0 | task 721 | total time = 9134.31 ms / 315 tokens 1.57.294.818 I slot print_timing: id 0 | task 721 | graphs reused = 498 1.57.294.819 I slot print_timing: id 0 | task 721 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.294.879 I slot release: id 0 | task 721 | stop processing: n_tokens = 1429, truncated = 0 1.57.339.657 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.780 1.57.339.678 I slot launch_slot_: id 0 | task 918 | processing task, is_child = 0 1.58.129.318 I slot print_timing: id 3 | task 865 | prompt eval time = 311.21 ms / 74 tokens ( 4.21 ms per token, 237.78 tokens per second) 1.58.129.323 I slot print_timing: id 3 | task 865 | eval time = 3059.55 ms / 64 tokens ( 48.56 ms per token, 20.59 tokens per second) 1.58.129.324 I slot print_timing: id 3 | task 865 | total time = 3370.76 ms / 138 tokens 1.58.129.324 I slot print_timing: id 3 | task 865 | graphs reused = 510 1.58.129.325 I slot print_timing: id 3 | task 865 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.129.408 I slot release: id 3 | task 865 | stop processing: n_tokens = 1252, truncated = 0 1.58.169.854 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.891 1.58.169.874 I slot launch_slot_: id 3 | task 934 | processing task, is_child = 0 1.58.913.298 I slot print_timing: id 2 | task 785 | n_gen = 157, tg = 21.29 t/s, tg_3s = 18.85 t/s 1.59.865.423 I slot print_timing: id 2 | task 785 | prompt eval time = 403.11 ms / 111 tokens ( 3.63 ms per token, 275.36 tokens per second) 1.59.865.428 I slot print_timing: id 2 | task 785 | eval time = 8277.96 ms / 180 tokens ( 46.25 ms per token, 21.62 tokens per second) 1.59.865.430 I slot print_timing: id 2 | task 785 | total time = 8681.07 ms / 291 tokens 1.59.865.431 I slot print_timing: id 2 | task 785 | graphs reused = 543 1.59.865.431 I slot print_timing: id 2 | task 785 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.865.507 I slot release: id 2 | task 785 | stop processing: n_tokens = 1405, truncated = 0 1.59.925.474 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.794 1.59.925.506 I slot launch_slot_: id 2 | task 972 | processing task, is_child = 0 2.00.327.342 I slot print_timing: id 1 | task 904 | prompt eval time = 313.22 ms / 59 tokens ( 5.31 ms per token, 188.37 tokens per second) 2.00.327.344 I slot print_timing: id 1 | task 904 | eval time = 3442.29 ms / 66 tokens ( 52.96 ms per token, 18.88 tokens per second) 2.00.327.345 I slot print_timing: id 1 | task 904 | total time = 3755.51 ms / 125 tokens 2.00.327.345 I slot print_timing: id 1 | task 904 | graphs reused = 543 2.00.327.346 I slot print_timing: id 1 | task 904 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.327.393 I slot release: id 1 | task 904 | stop processing: n_tokens = 1239, truncated = 0 2.00.384.590 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.900 2.00.384.611 I slot launch_slot_: id 1 | task 976 | processing task, is_child = 0 2.01.356.860 I slot print_timing: id 3 | task 934 | prompt eval time = 311.10 ms / 70 tokens ( 4.44 ms per token, 225.01 tokens per second) 2.01.356.866 I slot print_timing: id 3 | task 934 | eval time = 2875.88 ms / 57 tokens ( 51.35 ms per token, 19.47 tokens per second) 2.01.356.867 I slot print_timing: id 3 | task 934 | total time = 3186.97 ms / 127 tokens 2.01.356.868 I slot print_timing: id 3 | task 934 | graphs reused = 558 2.01.356.868 I slot print_timing: id 3 | task 934 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.356.950 I slot release: id 3 | task 934 | stop processing: n_tokens = 1241, truncated = 0 2.01.397.023 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.898 2.01.397.049 I slot launch_slot_: id 3 | task 996 | processing task, is_child = 0 2.02.523.377 I slot print_timing: id 0 | task 918 | prompt eval time = 304.72 ms / 76 tokens ( 4.01 ms per token, 249.41 tokens per second) 2.02.523.381 I slot print_timing: id 0 | task 918 | eval time = 4878.97 ms / 95 tokens ( 51.90 ms per token, 19.27 tokens per second) 2.02.523.382 I slot print_timing: id 0 | task 918 | total time = 5183.69 ms / 171 tokens 2.02.523.383 I slot print_timing: id 0 | task 918 | graphs reused = 576 2.02.523.383 I slot print_timing: id 0 | task 918 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.523.448 I slot release: id 0 | task 918 | stop processing: n_tokens = 1285, truncated = 0 2.02.567.817 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.868 2.02.567.840 I slot launch_slot_: id 0 | task 1020 | processing task, is_child = 0 2.05.036.494 I slot print_timing: id 2 | task 972 | n_gen = 100, tg = 21.03 t/s, tg_3s = 21.24 t/s 2.05.117.615 I slot print_timing: id 1 | task 976 | prompt eval time = 314.18 ms / 65 tokens ( 4.83 ms per token, 206.89 tokens per second) 2.05.117.619 I slot print_timing: id 1 | task 976 | eval time = 4418.82 ms / 99 tokens ( 45.09 ms per token, 22.18 tokens per second) 2.05.117.620 I slot print_timing: id 1 | task 976 | total time = 4733.00 ms / 164 tokens 2.05.117.621 I slot print_timing: id 1 | task 976 | graphs reused = 631 2.05.117.621 I slot print_timing: id 1 | task 976 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.117.689 I slot release: id 1 | task 976 | stop processing: n_tokens = 1278, truncated = 0 2.05.178.936 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 2.05.178.964 I slot launch_slot_: id 1 | task 1080 | processing task, is_child = 0 2.05.931.957 I slot print_timing: id 3 | task 996 | prompt eval time = 310.81 ms / 71 tokens ( 4.38 ms per token, 228.43 tokens per second) 2.05.931.961 I slot print_timing: id 3 | task 996 | eval time = 4224.09 ms / 91 tokens ( 46.93 ms per token, 21.31 tokens per second) 2.05.931.962 I slot print_timing: id 3 | task 996 | total time = 4534.90 ms / 162 tokens 2.05.931.963 I slot print_timing: id 3 | task 996 | graphs reused = 638 2.05.931.964 I slot print_timing: id 3 | task 996 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.932.034 I slot release: id 3 | task 996 | stop processing: n_tokens = 1276, truncated = 0 2.05.972.270 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.874 2.05.972.294 I slot launch_slot_: id 3 | task 1092 | processing task, is_child = 0 2.07.539.364 I slot print_timing: id 0 | task 1020 | n_gen = 100, tg = 20.99 t/s, tg_3s = 21.20 t/s 2.07.663.589 I slot print_timing: id 0 | task 1020 | prompt eval time = 254.93 ms / 62 tokens ( 4.11 ms per token, 243.21 tokens per second) 2.07.663.596 I slot print_timing: id 0 | task 1020 | eval time = 4840.79 ms / 103 tokens ( 47.46 ms per token, 21.07 tokens per second) 2.07.663.597 I slot print_timing: id 0 | task 1020 | total time = 5095.72 ms / 165 tokens 2.07.663.597 I slot print_timing: id 0 | task 1020 | graphs reused = 669 2.07.663.598 I slot print_timing: id 0 | task 1020 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.663.674 I slot release: id 0 | task 1020 | stop processing: n_tokens = 1279, truncated = 0 2.07.708.159 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.872 2.07.708.184 I slot launch_slot_: id 0 | task 1128 | processing task, is_child = 0 2.08.078.734 I slot print_timing: id 2 | task 972 | n_gen = 151, tg = 19.35 t/s, tg_3s = 16.76 t/s 2.10.260.649 I slot print_timing: id 1 | task 1080 | n_gen = 100, tg = 21.26 t/s, tg_3s = 21.48 t/s 2.10.716.393 I slot print_timing: id 3 | task 1092 | n_gen = 100, tg = 22.63 t/s, tg_3s = 22.86 t/s 2.10.879.051 I slot print_timing: id 2 | task 972 | prompt eval time = 403.03 ms / 106 tokens ( 3.80 ms per token, 263.01 tokens per second) 2.10.879.058 I slot print_timing: id 2 | task 972 | eval time = 10550.51 ms / 219 tokens ( 48.40 ms per token, 20.66 tokens per second) 2.10.879.059 I slot print_timing: id 2 | task 972 | total time = 10953.54 ms / 325 tokens 2.10.879.059 I slot print_timing: id 2 | task 972 | graphs reused = 737 2.10.879.060 I slot print_timing: id 2 | task 972 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.879.132 I slot release: id 2 | task 972 | stop processing: n_tokens = 1439, truncated = 0 2.10.939.233 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.775 2.10.939.262 I slot launch_slot_: id 2 | task 1200 | processing task, is_child = 0 2.11.351.052 I slot print_timing: id 1 | task 1080 | prompt eval time = 425.77 ms / 105 tokens ( 4.05 ms per token, 246.61 tokens per second) 2.11.351.058 I slot print_timing: id 1 | task 1080 | eval time = 5746.31 ms / 121 tokens ( 47.89 ms per token, 20.88 tokens per second) 2.11.351.059 I slot print_timing: id 1 | task 1080 | total time = 6172.08 ms / 226 tokens 2.11.351.059 I slot print_timing: id 1 | task 1080 | graphs reused = 739 2.11.351.060 I slot print_timing: id 1 | task 1080 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.351.111 I slot release: id 1 | task 1080 | stop processing: n_tokens = 1341, truncated = 0 2.11.408.950 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.831 2.11.408.972 I slot launch_slot_: id 1 | task 1207 | processing task, is_child = 0 2.12.134.351 I slot print_timing: id 3 | task 1092 | prompt eval time = 370.11 ms / 111 tokens ( 3.33 ms per token, 299.91 tokens per second) 2.12.134.358 I slot print_timing: id 3 | task 1092 | eval time = 5791.94 ms / 123 tokens ( 47.47 ms per token, 21.06 tokens per second) 2.12.134.358 I slot print_timing: id 3 | task 1092 | total time = 6162.05 ms / 234 tokens 2.12.134.359 I slot print_timing: id 3 | task 1092 | graphs reused = 748 2.12.134.359 I slot print_timing: id 3 | task 1092 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.134.418 I slot release: id 3 | task 1092 | stop processing: n_tokens = 1348, truncated = 0 2.12.174.025 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.827 2.12.174.046 I slot launch_slot_: id 3 | task 1221 | processing task, is_child = 0 2.12.842.756 I slot print_timing: id 0 | task 1128 | n_gen = 100, tg = 20.77 t/s, tg_3s = 20.98 t/s 2.14.330.860 I slot print_timing: id 1 | task 1207 | prompt eval time = 313.86 ms / 62 tokens ( 5.06 ms per token, 197.54 tokens per second) 2.14.330.866 I slot print_timing: id 1 | task 1207 | eval time = 2608.02 ms / 59 tokens ( 44.97 ms per token, 22.24 tokens per second) 2.14.330.867 I slot print_timing: id 1 | task 1207 | total time = 2921.88 ms / 121 tokens 2.14.330.867 I slot print_timing: id 1 | task 1207 | graphs reused = 792 2.14.330.868 I slot print_timing: id 1 | task 1207 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.330.920 I slot release: id 1 | task 1207 | stop processing: n_tokens = 1235, truncated = 0 2.14.392.127 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.903 2.14.392.168 I slot launch_slot_: id 1 | task 1270 | processing task, is_child = 0 2.14.839.750 I slot print_timing: id 2 | task 1200 | prompt eval time = 295.66 ms / 68 tokens ( 4.35 ms per token, 230.00 tokens per second) 2.14.839.756 I slot print_timing: id 2 | task 1200 | eval time = 3604.82 ms / 70 tokens ( 52.24 ms per token, 19.14 tokens per second) 2.14.839.757 I slot print_timing: id 2 | task 1200 | total time = 3900.48 ms / 138 tokens 2.14.839.757 I slot print_timing: id 2 | task 1200 | graphs reused = 793 2.14.839.757 I slot print_timing: id 2 | task 1200 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.839.800 I slot release: id 2 | task 1200 | stop processing: n_tokens = 1252, truncated = 0 2.14.896.194 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.891 2.14.896.214 I slot launch_slot_: id 2 | task 1276 | processing task, is_child = 0 2.15.858.689 I slot print_timing: id 0 | task 1128 | n_gen = 159, tg = 20.30 t/s, tg_3s = 19.56 t/s 2.15.863.772 I slot print_timing: id 3 | task 1221 | prompt eval time = 311.77 ms / 74 tokens ( 4.21 ms per token, 237.36 tokens per second) 2.15.863.775 I slot print_timing: id 3 | task 1221 | eval time = 3377.95 ms / 69 tokens ( 49.68 ms per token, 20.13 tokens per second) 2.15.863.776 I slot print_timing: id 3 | task 1221 | total time = 3689.72 ms / 143 tokens 2.15.863.776 I slot print_timing: id 3 | task 1221 | graphs reused = 807 2.15.863.777 I slot print_timing: id 3 | task 1221 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.863.831 I slot release: id 3 | task 1221 | stop processing: n_tokens = 1257, truncated = 0 2.15.903.247 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.887 2.15.903.269 I slot launch_slot_: id 3 | task 1295 | processing task, is_child = 0 2.18.860.326 I slot print_timing: id 0 | task 1128 | n_gen = 226, tg = 20.86 t/s, tg_3s = 22.32 t/s 2.19.274.139 I slot print_timing: id 1 | task 1270 | prompt eval time = 368.18 ms / 80 tokens ( 4.60 ms per token, 217.28 tokens per second) 2.19.274.146 I slot print_timing: id 1 | task 1270 | eval time = 4513.78 ms / 98 tokens ( 46.53 ms per token, 21.49 tokens per second) 2.19.274.147 I slot print_timing: id 1 | task 1270 | total time = 4881.96 ms / 178 tokens 2.19.274.148 I slot print_timing: id 1 | task 1270 | graphs reused = 880 2.19.274.148 I slot print_timing: id 1 | task 1270 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.274.227 I slot release: id 1 | task 1270 | stop processing: n_tokens = 1292, truncated = 0 2.19.335.534 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.863 2.19.335.559 I slot launch_slot_: id 1 | task 1373 | processing task, is_child = 0 2.19.857.302 I slot print_timing: id 0 | task 1128 | prompt eval time = 368.42 ms / 128 tokens ( 2.88 ms per token, 347.43 tokens per second) 2.19.857.307 I slot print_timing: id 0 | task 1128 | eval time = 11780.69 ms / 243 tokens ( 48.68 ms per token, 20.54 tokens per second) 2.19.857.308 I slot print_timing: id 0 | task 1128 | total time = 12149.11 ms / 371 tokens 2.19.857.308 I slot print_timing: id 0 | task 1128 | graphs reused = 883 2.19.857.309 I slot print_timing: id 0 | task 1128 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.857.365 I slot release: id 0 | task 1128 | stop processing: n_tokens = 1485, truncated = 0 2.19.859.992 I slot print_timing: id 2 | task 1276 | n_gen = 100, tg = 21.45 t/s, tg_3s = 21.67 t/s 2.19.901.338 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.751 2.19.901.364 I slot launch_slot_: id 0 | task 1381 | processing task, is_child = 0 2.20.826.199 I slot print_timing: id 3 | task 1295 | n_gen = 100, tg = 21.49 t/s, tg_3s = 21.71 t/s 2.21.322.409 I slot print_timing: id 3 | task 1295 | prompt eval time = 315.93 ms / 97 tokens ( 3.26 ms per token, 307.03 tokens per second) 2.21.322.417 I slot print_timing: id 3 | task 1295 | eval time = 5103.20 ms / 112 tokens ( 45.97 ms per token, 21.75 tokens per second) 2.21.322.418 I slot print_timing: id 3 | task 1295 | total time = 5419.13 ms / 209 tokens 2.21.322.418 I slot print_timing: id 3 | task 1295 | graphs reused = 910 2.21.322.419 I slot print_timing: id 3 | task 1295 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.322.490 I slot release: id 3 | task 1295 | stop processing: n_tokens = 1323, truncated = 0 2.21.362.029 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.843 2.21.362.051 I slot launch_slot_: id 3 | task 1412 | processing task, is_child = 0 2.22.213.475 I slot print_timing: id 2 | task 1276 | prompt eval time = 348.53 ms / 88 tokens ( 3.96 ms per token, 252.49 tokens per second) 2.22.213.479 I slot print_timing: id 2 | task 1276 | eval time = 6968.72 ms / 145 tokens ( 48.39 ms per token, 20.66 tokens per second) 2.22.213.480 I slot print_timing: id 2 | task 1276 | total time = 7317.25 ms / 233 tokens 2.22.213.480 I slot print_timing: id 2 | task 1276 | graphs reused = 921 2.22.213.481 I slot print_timing: id 2 | task 1276 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.213.542 I slot release: id 2 | task 1276 | stop processing: n_tokens = 1347, truncated = 0 2.22.274.007 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.828 2.22.274.032 I slot launch_slot_: id 2 | task 1428 | processing task, is_child = 0 2.24.612.896 I slot print_timing: id 1 | task 1373 | n_gen = 100, tg = 20.16 t/s, tg_3s = 20.36 t/s 2.24.898.528 I slot print_timing: id 0 | task 1381 | n_gen = 100, tg = 21.12 t/s, tg_3s = 21.34 t/s 2.25.229.128 I slot print_timing: id 1 | task 1373 | prompt eval time = 366.18 ms / 71 tokens ( 5.16 ms per token, 193.89 tokens per second) 2.25.229.135 I slot print_timing: id 1 | task 1373 | eval time = 5527.38 ms / 115 tokens ( 48.49 ms per token, 20.62 tokens per second) 2.25.229.135 I slot print_timing: id 1 | task 1373 | total time = 5893.56 ms / 186 tokens 2.25.229.136 I slot print_timing: id 1 | task 1373 | graphs reused = 981 2.25.229.136 I slot print_timing: id 1 | task 1373 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.229.197 I slot release: id 1 | task 1373 | stop processing: n_tokens = 1300, truncated = 0 2.25.290.384 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.858 2.25.290.412 I slot launch_slot_: id 1 | task 1494 | processing task, is_child = 0 2.26.433.289 I slot print_timing: id 0 | task 1381 | prompt eval time = 310.13 ms / 90 tokens ( 3.45 ms per token, 290.20 tokens per second) 2.26.433.296 I slot print_timing: id 0 | task 1381 | eval time = 6221.79 ms / 130 tokens ( 48.23 ms per token, 20.73 tokens per second) 2.26.433.297 I slot print_timing: id 0 | task 1381 | total time = 6531.92 ms / 220 tokens 2.26.433.297 I slot print_timing: id 0 | task 1381 | graphs reused = 999 2.26.433.298 I slot print_timing: id 0 | task 1381 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.433.358 I slot release: id 0 | task 1381 | stop processing: n_tokens = 1334, truncated = 0 2.26.438.268 I slot print_timing: id 3 | task 1412 | n_gen = 100, tg = 21.04 t/s, tg_3s = 21.25 t/s 2.26.477.567 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.836 2.26.477.590 I slot launch_slot_: id 0 | task 1517 | processing task, is_child = 0 2.27.328.001 I slot print_timing: id 2 | task 1428 | n_gen = 100, tg = 21.28 t/s, tg_3s = 21.50 t/s 2.29.176.503 I slot print_timing: id 2 | task 1428 | prompt eval time = 402.56 ms / 106 tokens ( 3.80 ms per token, 263.31 tokens per second) 2.29.176.507 I slot print_timing: id 2 | task 1428 | eval time = 6499.90 ms / 145 tokens ( 45.14 ms per token, 22.15 tokens per second) 2.29.176.508 I slot print_timing: id 2 | task 1428 | total time = 6902.46 ms / 251 tokens 2.29.176.509 I slot print_timing: id 2 | task 1428 | graphs reused = 1056 2.29.176.509 I slot print_timing: id 2 | task 1428 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.176.581 I slot release: id 2 | task 1428 | stop processing: n_tokens = 1365, truncated = 0 2.29.178.201 I slot print_timing: id 3 | task 1412 | prompt eval time = 371.00 ms / 125 tokens ( 2.97 ms per token, 336.93 tokens per second) 2.29.178.203 I slot print_timing: id 3 | task 1412 | eval time = 7445.15 ms / 160 tokens ( 46.82 ms per token, 21.36 tokens per second) 2.29.178.204 I slot print_timing: id 3 | task 1412 | total time = 7816.15 ms / 285 tokens 2.29.178.204 I slot print_timing: id 3 | task 1412 | graphs reused = 1056 2.29.178.205 I slot print_timing: id 3 | task 1412 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.178.253 I slot release: id 3 | task 1412 | stop processing: n_tokens = 1399, truncated = 0 2.29.215.382 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.817 2.29.215.404 I slot launch_slot_: id 2 | task 1578 | processing task, is_child = 0 2.29.240.724 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.797 2.29.240.745 I slot launch_slot_: id 3 | task 1579 | processing task, is_child = 0 2.30.501.931 I slot print_timing: id 1 | task 1494 | n_gen = 100, tg = 20.45 t/s, tg_3s = 20.66 t/s 2.30.709.290 I slot print_timing: id 1 | task 1494 | prompt eval time = 370.30 ms / 94 tokens ( 3.94 ms per token, 253.85 tokens per second) 2.30.709.298 I slot print_timing: id 1 | task 1494 | eval time = 5048.57 ms / 105 tokens ( 48.54 ms per token, 20.60 tokens per second) 2.30.709.298 I slot print_timing: id 1 | task 1494 | total time = 5418.87 ms / 199 tokens 2.30.709.299 I slot print_timing: id 1 | task 1494 | graphs reused = 1077 2.30.709.299 I slot print_timing: id 1 | task 1494 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.709.357 I slot release: id 1 | task 1494 | stop processing: n_tokens = 1313, truncated = 0 2.30.770.475 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.849 2.30.770.502 I slot launch_slot_: id 1 | task 1605 | processing task, is_child = 0 2.31.707.125 I slot print_timing: id 0 | task 1517 | n_gen = 100, tg = 20.34 t/s, tg_3s = 20.54 t/s 2.32.532.519 I slot print_timing: id 3 | task 1579 | prompt eval time = 569.97 ms / 71 tokens ( 8.03 ms per token, 124.57 tokens per second) 2.32.532.526 I slot print_timing: id 3 | task 1579 | eval time = 2719.82 ms / 60 tokens ( 46.10 ms per token, 21.69 tokens per second) 2.32.532.527 I slot print_timing: id 3 | task 1579 | total time = 3289.79 ms / 131 tokens 2.32.532.527 I slot print_timing: id 3 | task 1579 | graphs reused = 1110 2.32.532.528 I slot print_timing: id 3 | task 1579 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.532.581 I slot release: id 3 | task 1579 | stop processing: n_tokens = 1245, truncated = 0 2.32.572.123 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.896 2.32.572.145 I slot launch_slot_: id 3 | task 1643 | processing task, is_child = 0 2.34.353.535 I slot print_timing: id 1 | task 1605 | prompt eval time = 367.59 ms / 81 tokens ( 4.54 ms per token, 220.35 tokens per second) 2.34.353.540 I slot print_timing: id 1 | task 1605 | eval time = 3215.43 ms / 74 tokens ( 44.05 ms per token, 22.70 tokens per second) 2.34.353.541 I slot print_timing: id 1 | task 1605 | total time = 3583.03 ms / 155 tokens 2.34.353.541 I slot print_timing: id 1 | task 1605 | graphs reused = 1145 2.34.353.542 I slot print_timing: id 1 | task 1605 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.353.599 I slot release: id 1 | task 1605 | stop processing: n_tokens = 1269, truncated = 0 2.34.413.255 I slot print_timing: id 2 | task 1578 | n_gen = 100, tg = 21.51 t/s, tg_3s = 21.73 t/s 2.34.415.069 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.879 2.34.415.103 I slot launch_slot_: id 1 | task 1683 | processing task, is_child = 0 2.34.778.954 I slot print_timing: id 0 | task 1517 | n_gen = 162, tg = 20.28 t/s, tg_3s = 20.18 t/s 2.36.793.357 I slot print_timing: id 3 | task 1643 | prompt eval time = 311.64 ms / 74 tokens ( 4.21 ms per token, 237.46 tokens per second) 2.36.793.360 I slot print_timing: id 3 | task 1643 | eval time = 3909.57 ms / 89 tokens ( 44.43 ms per token, 22.51 tokens per second) 2.36.793.361 I slot print_timing: id 3 | task 1643 | total time = 4221.20 ms / 163 tokens 2.36.793.362 I slot print_timing: id 3 | task 1643 | graphs reused = 1193 2.36.793.362 I slot print_timing: id 3 | task 1643 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.793.419 I slot release: id 3 | task 1643 | stop processing: n_tokens = 1277, truncated = 0 2.36.832.793 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.873 2.36.832.816 I slot launch_slot_: id 3 | task 1736 | processing task, is_child = 0 2.37.420.119 I slot print_timing: id 2 | task 1578 | n_gen = 161, tg = 21.03 t/s, tg_3s = 20.29 t/s 2.37.542.093 I slot print_timing: id 0 | task 1517 | prompt eval time = 362.16 ms / 103 tokens ( 3.52 ms per token, 284.41 tokens per second) 2.37.542.101 I slot print_timing: id 0 | task 1517 | eval time = 10702.34 ms / 224 tokens ( 47.99 ms per token, 20.84 tokens per second) 2.37.542.102 I slot print_timing: id 0 | task 1517 | total time = 11064.49 ms / 327 tokens 2.37.542.103 I slot print_timing: id 0 | task 1517 | graphs reused = 1202 2.37.542.104 I slot print_timing: id 0 | task 1517 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.542.178 I slot release: id 0 | task 1517 | stop processing: n_tokens = 1441, truncated = 0 2.37.589.385 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.774 2.37.589.408 I slot launch_slot_: id 0 | task 1750 | processing task, is_child = 0 2.38.018.962 I slot print_timing: id 1 | task 1683 | prompt eval time = 364.97 ms / 77 tokens ( 4.74 ms per token, 210.98 tokens per second) 2.38.018.968 I slot print_timing: id 1 | task 1683 | eval time = 3238.88 ms / 69 tokens ( 47.63 ms per token, 20.99 tokens per second) 2.38.018.969 I slot print_timing: id 1 | task 1683 | total time = 3603.85 ms / 146 tokens 2.38.018.969 I slot print_timing: id 1 | task 1683 | graphs reused = 1205 2.38.018.970 I slot print_timing: id 1 | task 1683 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.019.018 I slot release: id 1 | task 1683 | stop processing: n_tokens = 1260, truncated = 0 2.38.078.469 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.885 2.38.078.494 I slot launch_slot_: id 1 | task 1757 | processing task, is_child = 0 2.39.843.670 I slot print_timing: id 2 | task 1578 | prompt eval time = 570.86 ms / 114 tokens ( 5.01 ms per token, 199.70 tokens per second) 2.39.843.675 I slot print_timing: id 2 | task 1578 | eval time = 10032.06 ms / 207 tokens ( 48.70 ms per token, 20.53 tokens per second) 2.39.843.675 I slot print_timing: id 2 | task 1578 | total time = 10602.91 ms / 321 tokens 2.39.843.676 I slot print_timing: id 2 | task 1578 | graphs reused = 1238 2.39.843.676 I slot print_timing: id 2 | task 1578 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.843.741 I slot release: id 2 | task 1578 | stop processing: n_tokens = 1435, truncated = 0 2.39.903.295 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.777 2.39.903.317 I slot launch_slot_: id 2 | task 1795 | processing task, is_child = 0 2.42.035.701 I slot print_timing: id 3 | task 1736 | n_gen = 100, tg = 20.25 t/s, tg_3s = 20.46 t/s 2.42.565.632 I slot print_timing: id 0 | task 1750 | n_gen = 100, tg = 21.22 t/s, tg_3s = 21.44 t/s 2.42.735.257 I slot print_timing: id 3 | task 1736 | prompt eval time = 314.32 ms / 86 tokens ( 3.65 ms per token, 273.61 tokens per second) 2.42.735.261 I slot print_timing: id 3 | task 1736 | eval time = 5588.11 ms / 117 tokens ( 48.17 ms per token, 20.76 tokens per second) 2.42.735.262 I slot print_timing: id 3 | task 1736 | total time = 5902.43 ms / 203 tokens 2.42.735.262 I slot print_timing: id 3 | task 1736 | graphs reused = 1296 2.42.735.263 I slot print_timing: id 3 | task 1736 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.735.331 I slot release: id 3 | task 1736 | stop processing: n_tokens = 1317, truncated = 0 2.42.775.081 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.847 2.42.775.103 I slot launch_slot_: id 3 | task 1859 | processing task, is_child = 0 2.42.959.798 I slot print_timing: id 1 | task 1757 | n_gen = 100, tg = 21.93 t/s, tg_3s = 22.16 t/s 2.43.072.065 I slot print_timing: id 0 | task 1750 | prompt eval time = 311.13 ms / 97 tokens ( 3.21 ms per token, 311.76 tokens per second) 2.43.072.067 I slot print_timing: id 0 | task 1750 | eval time = 5171.51 ms / 108 tokens ( 48.33 ms per token, 20.69 tokens per second) 2.43.072.069 I slot print_timing: id 0 | task 1750 | total time = 5482.64 ms / 205 tokens 2.43.072.070 I slot print_timing: id 0 | task 1750 | graphs reused = 1296 2.43.072.070 I slot print_timing: id 0 | task 1750 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.072.117 I slot release: id 0 | task 1750 | stop processing: n_tokens = 1319, truncated = 0 2.43.112.756 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.845 2.43.112.773 I slot launch_slot_: id 0 | task 1864 | processing task, is_child = 0 2.44.494.211 I slot print_timing: id 1 | task 1757 | prompt eval time = 367.95 ms / 101 tokens ( 3.64 ms per token, 274.49 tokens per second) 2.44.494.216 I slot print_timing: id 1 | task 1757 | eval time = 6047.74 ms / 131 tokens ( 46.52 ms per token, 21.50 tokens per second) 2.44.494.217 I slot print_timing: id 1 | task 1757 | total time = 6415.69 ms / 232 tokens 2.44.494.217 I slot print_timing: id 1 | task 1757 | graphs reused = 1322 2.44.494.218 I slot print_timing: id 1 | task 1757 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.494.278 I slot release: id 1 | task 1757 | stop processing: n_tokens = 1346, truncated = 0 2.44.555.634 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.828 2.44.555.661 I slot launch_slot_: id 1 | task 1894 | processing task, is_child = 0 2.45.039.179 I slot print_timing: id 2 | task 1795 | n_gen = 100, tg = 20.68 t/s, tg_3s = 20.89 t/s 2.45.783.737 I slot print_timing: id 3 | task 1859 | prompt eval time = 260.31 ms / 65 tokens ( 4.00 ms per token, 249.70 tokens per second) 2.45.783.742 I slot print_timing: id 3 | task 1859 | eval time = 2748.32 ms / 55 tokens ( 50.89 ms per token, 19.65 tokens per second) 2.45.783.743 I slot print_timing: id 3 | task 1859 | total time = 3008.62 ms / 120 tokens 2.45.783.744 I slot print_timing: id 3 | task 1859 | graphs reused = 1342 2.45.783.744 I slot print_timing: id 3 | task 1859 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.783.797 I slot release: id 3 | task 1859 | stop processing: n_tokens = 1234, truncated = 0 2.45.823.366 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.904 2.45.823.391 I slot launch_slot_: id 3 | task 1919 | processing task, is_child = 0 2.46.779.772 I slot print_timing: id 2 | task 1795 | prompt eval time = 348.54 ms / 86 tokens ( 4.05 ms per token, 246.75 tokens per second) 2.46.779.779 I slot print_timing: id 2 | task 1795 | eval time = 6527.91 ms / 138 tokens ( 47.65 ms per token, 20.99 tokens per second) 2.46.779.780 I slot print_timing: id 2 | task 1795 | total time = 6876.45 ms / 224 tokens 2.46.779.781 I slot print_timing: id 2 | task 1795 | graphs reused = 1358 2.46.779.781 I slot print_timing: id 2 | task 1795 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.779.853 I slot release: id 2 | task 1795 | stop processing: n_tokens = 1338, truncated = 0 2.46.839.313 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.833 2.46.839.342 I slot launch_slot_: id 2 | task 1940 | processing task, is_child = 0 2.48.246.333 I slot print_timing: id 0 | task 1864 | n_gen = 100, tg = 20.52 t/s, tg_3s = 20.73 t/s 2.49.273.923 I slot print_timing: id 0 | task 1864 | prompt eval time = 308.70 ms / 81 tokens ( 3.81 ms per token, 262.39 tokens per second) 2.49.273.927 I slot print_timing: id 0 | task 1864 | eval time = 5852.44 ms / 125 tokens ( 47.20 ms per token, 21.19 tokens per second) 2.49.273.928 I slot print_timing: id 0 | task 1864 | total time = 6161.14 ms / 206 tokens 2.49.273.929 I slot print_timing: id 0 | task 1864 | graphs reused = 1407 2.49.273.929 I slot print_timing: id 0 | task 1864 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.273.994 I slot release: id 0 | task 1864 | stop processing: n_tokens = 1320, truncated = 0 2.49.318.446 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.845 2.49.318.470 I slot launch_slot_: id 0 | task 1995 | processing task, is_child = 0 2.49.627.360 I slot print_timing: id 2 | task 1940 | prompt eval time = 349.90 ms / 96 tokens ( 3.64 ms per token, 274.36 tokens per second) 2.49.627.364 I slot print_timing: id 2 | task 1940 | eval time = 2438.11 ms / 55 tokens ( 45.15 ms per token, 22.15 tokens per second) 2.49.627.364 I slot print_timing: id 2 | task 1940 | total time = 2788.01 ms / 151 tokens 2.49.627.365 I slot print_timing: id 2 | task 1940 | graphs reused = 1408 2.49.627.365 I slot print_timing: id 2 | task 1940 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.627.408 I slot release: id 2 | task 1940 | stop processing: n_tokens = 1265, truncated = 0 2.49.628.492 I slot print_timing: id 3 | task 1919 | prompt eval time = 259.66 ms / 66 tokens ( 3.93 ms per token, 254.18 tokens per second) 2.49.628.497 I slot print_timing: id 3 | task 1919 | eval time = 3545.44 ms / 75 tokens ( 47.91 ms per token, 20.87 tokens per second) 2.49.628.497 I slot print_timing: id 3 | task 1919 | total time = 3805.10 ms / 141 tokens 2.49.628.498 I slot print_timing: id 3 | task 1919 | graphs reused = 1408 2.49.628.498 I slot print_timing: id 3 | task 1919 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.628.526 I slot release: id 3 | task 1919 | stop processing: n_tokens = 1255, truncated = 0 2.49.663.511 I slot print_timing: id 1 | task 1894 | n_gen = 100, tg = 20.87 t/s, tg_3s = 21.09 t/s 2.49.663.516 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.881 2.49.663.531 I slot launch_slot_: id 2 | task 1999 | processing task, is_child = 0 2.49.685.893 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.888 2.49.685.912 I slot launch_slot_: id 3 | task 2000 | processing task, is_child = 0 2.51.078.136 I slot print_timing: id 1 | task 1894 | prompt eval time = 365.17 ms / 73 tokens ( 5.00 ms per token, 199.91 tokens per second) 2.51.078.143 I slot print_timing: id 1 | task 1894 | eval time = 6157.29 ms / 122 tokens ( 50.89 ms per token, 19.65 tokens per second) 2.51.078.144 I slot print_timing: id 1 | task 1894 | total time = 6522.46 ms / 195 tokens 2.51.078.145 I slot print_timing: id 1 | task 1894 | graphs reused = 1427 2.51.078.146 I slot print_timing: id 1 | task 1894 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.078.215 I slot release: id 1 | task 1894 | stop processing: n_tokens = 1309, truncated = 0 2.51.139.317 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.852 2.51.139.339 I slot launch_slot_: id 1 | task 2024 | processing task, is_child = 0 2.54.342.147 I slot print_timing: id 0 | task 1995 | prompt eval time = 306.77 ms / 84 tokens ( 3.65 ms per token, 273.82 tokens per second) 2.54.342.150 I slot print_timing: id 0 | task 1995 | eval time = 4716.89 ms / 96 tokens ( 49.65 ms per token, 20.14 tokens per second) 2.54.342.151 I slot print_timing: id 0 | task 1995 | total time = 5023.67 ms / 180 tokens 2.54.342.152 I slot print_timing: id 0 | task 1995 | graphs reused = 1494 2.54.342.152 I slot print_timing: id 0 | task 1995 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.342.208 I slot release: id 0 | task 1995 | stop processing: n_tokens = 1294, truncated = 0 2.54.386.379 I slot print_timing: id 3 | task 2000 | prompt eval time = 571.87 ms / 70 tokens ( 8.17 ms per token, 122.41 tokens per second) 2.54.386.382 I slot print_timing: id 3 | task 2000 | eval time = 4126.84 ms / 94 tokens ( 44.37 ms per token, 22.54 tokens per second) 2.54.386.383 I slot print_timing: id 3 | task 2000 | total time = 4698.70 ms / 164 tokens 2.54.386.383 I slot print_timing: id 3 | task 2000 | graphs reused = 1494 2.54.386.384 I slot print_timing: id 3 | task 2000 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.386.432 I slot release: id 3 | task 2000 | stop processing: n_tokens = 1278, truncated = 0 2.54.386.439 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.862 2.54.386.458 I slot launch_slot_: id 0 | task 2097 | processing task, is_child = 0 2.54.412.859 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.872 2.54.412.885 I slot launch_slot_: id 3 | task 2098 | processing task, is_child = 0 2.55.221.350 I slot print_timing: id 2 | task 1999 | n_gen = 100, tg = 19.95 t/s, tg_3s = 20.15 t/s 2.56.173.764 I slot print_timing: id 1 | task 2024 | n_gen = 100, tg = 21.22 t/s, tg_3s = 21.43 t/s 2.57.452.802 I slot print_timing: id 2 | task 1999 | prompt eval time = 572.45 ms / 119 tokens ( 4.81 ms per token, 207.88 tokens per second) 2.57.452.807 I slot print_timing: id 2 | task 1999 | eval time = 7194.43 ms / 154 tokens ( 47.02 ms per token, 21.27 tokens per second) 2.57.452.808 I slot print_timing: id 2 | task 1999 | total time = 7766.88 ms / 273 tokens 2.57.452.808 I slot print_timing: id 2 | task 1999 | graphs reused = 1551 2.57.452.809 I slot print_timing: id 2 | task 1999 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.452.897 I slot release: id 2 | task 1999 | stop processing: n_tokens = 1387, truncated = 0 2.57.512.391 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.804 2.57.512.414 I slot launch_slot_: id 2 | task 2160 | processing task, is_child = 0 2.58.405.969 I slot print_timing: id 3 | task 2098 | prompt eval time = 651.62 ms / 93 tokens ( 7.01 ms per token, 142.72 tokens per second) 2.58.405.975 I slot print_timing: id 3 | task 2098 | eval time = 3339.53 ms / 74 tokens ( 45.75 ms per token, 21.86 tokens per second) 2.58.405.976 I slot print_timing: id 3 | task 2098 | total time = 3991.15 ms / 167 tokens 2.58.405.976 I slot print_timing: id 3 | task 2098 | graphs reused = 1562 2.58.405.977 I slot print_timing: id 3 | task 2098 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.406.033 I slot release: id 3 | task 2098 | stop processing: n_tokens = 1281, truncated = 0 2.58.445.557 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.870 2.58.445.578 I slot launch_slot_: id 3 | task 2176 | processing task, is_child = 0 2.59.191.505 I slot print_timing: id 1 | task 2024 | n_gen = 161, tg = 20.82 t/s, tg_3s = 20.21 t/s 2.59.643.506 I slot print_timing: id 0 | task 2097 | n_gen = 100, tg = 21.61 t/s, tg_3s = 21.83 t/s 3.01.087.262 I slot print_timing: id 3 | task 2176 | prompt eval time = 258.53 ms / 57 tokens ( 4.54 ms per token, 220.47 tokens per second) 3.01.087.269 I slot print_timing: id 3 | task 2176 | eval time = 2383.14 ms / 59 tokens ( 41.09 ms per token, 24.34 tokens per second) 3.01.087.270 I slot print_timing: id 3 | task 2176 | total time = 2641.67 ms / 116 tokens 3.01.087.271 I slot print_timing: id 3 | task 2176 | graphs reused = 1619 3.01.087.271 I slot print_timing: id 3 | task 2176 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.087.344 I slot release: id 3 | task 2176 | stop processing: n_tokens = 1230, truncated = 0 3.01.127.199 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.907 3.01.127.222 I slot launch_slot_: id 3 | task 2238 | processing task, is_child = 0 3.02.215.528 I slot print_timing: id 1 | task 2024 | n_gen = 229, tg = 21.29 t/s, tg_3s = 22.49 t/s 3.02.381.189 I slot print_timing: id 2 | task 2160 | n_gen = 100, tg = 22.16 t/s, tg_3s = 22.39 t/s 3.02.665.913 I slot print_timing: id 0 | task 2097 | n_gen = 168, tg = 21.97 t/s, tg_3s = 22.50 t/s 3.03.576.270 I slot print_timing: id 3 | task 2238 | prompt eval time = 313.17 ms / 79 tokens ( 3.96 ms per token, 252.26 tokens per second) 3.03.576.274 I slot print_timing: id 3 | task 2238 | eval time = 2135.87 ms / 53 tokens ( 41.07 ms per token, 24.35 tokens per second) 3.03.576.275 I slot print_timing: id 3 | task 2238 | total time = 2449.04 ms / 132 tokens 3.03.576.276 I slot print_timing: id 3 | task 2238 | graphs reused = 1670 3.03.576.276 I slot print_timing: id 3 | task 2238 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.576.335 I slot release: id 3 | task 2238 | stop processing: n_tokens = 1246, truncated = 0 3.03.615.959 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.895 3.03.615.981 I slot launch_slot_: id 3 | task 2294 | processing task, is_child = 0 3.04.321.344 I slot print_timing: id 0 | task 2097 | prompt eval time = 650.35 ms / 133 tokens ( 4.89 ms per token, 204.51 tokens per second) 3.04.321.349 I slot print_timing: id 0 | task 2097 | eval time = 9258.10 ms / 203 tokens ( 45.83 ms per token, 21.82 tokens per second) 3.04.321.350 I slot print_timing: id 0 | task 2097 | total time = 9908.45 ms / 336 tokens 3.04.321.351 I slot print_timing: id 0 | task 2097 | graphs reused = 1679 3.04.321.351 I slot print_timing: id 0 | task 2097 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.321.418 I slot release: id 0 | task 2097 | stop processing: n_tokens = 1450, truncated = 0 3.04.370.126 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.769 3.04.370.152 I slot launch_slot_: id 0 | task 2308 | processing task, is_child = 0 3.05.246.581 I slot print_timing: id 1 | task 2024 | n_gen = 292, tg = 21.18 t/s, tg_3s = 20.78 t/s 3.05.412.133 I slot print_timing: id 2 | task 2160 | n_gen = 163, tg = 21.61 t/s, tg_3s = 20.79 t/s 3.06.726.089 I slot print_timing: id 2 | task 2160 | prompt eval time = 402.25 ms / 103 tokens ( 3.91 ms per token, 256.06 tokens per second) 3.06.726.096 I slot print_timing: id 2 | task 2160 | eval time = 8811.42 ms / 195 tokens ( 45.42 ms per token, 22.02 tokens per second) 3.06.726.097 I slot print_timing: id 2 | task 2160 | total time = 9213.67 ms / 298 tokens 3.06.726.097 I slot print_timing: id 2 | task 2160 | graphs reused = 1729 3.06.726.098 I slot print_timing: id 2 | task 2160 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.726.153 I slot release: id 2 | task 2160 | stop processing: n_tokens = 1412, truncated = 0 3.06.785.897 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.790 3.06.785.926 I slot launch_slot_: id 2 | task 2362 | processing task, is_child = 0 3.08.094.803 I slot print_timing: id 3 | task 2294 | prompt eval time = 313.65 ms / 101 tokens ( 3.11 ms per token, 322.01 tokens per second) 3.08.094.807 I slot print_timing: id 3 | task 2294 | eval time = 4165.16 ms / 89 tokens ( 47.33 ms per token, 21.13 tokens per second) 3.08.094.808 I slot print_timing: id 3 | task 2294 | total time = 4478.81 ms / 190 tokens 3.08.094.808 I slot print_timing: id 3 | task 2294 | graphs reused = 1749 3.08.094.809 I slot print_timing: id 3 | task 2294 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.094.869 I slot release: id 3 | task 2294 | stop processing: n_tokens = 1304, truncated = 0 3.08.134.488 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.855 3.08.134.510 I slot launch_slot_: id 3 | task 2388 | processing task, is_child = 0 3.08.375.236 I slot print_timing: id 1 | task 2024 | n_gen = 355, tg = 20.99 t/s, tg_3s = 20.14 t/s 3.09.306.830 I slot print_timing: id 0 | task 2308 | n_gen = 100, tg = 21.38 t/s, tg_3s = 21.60 t/s 3.11.079.041 I slot print_timing: id 2 | task 2362 | prompt eval time = 402.55 ms / 103 tokens ( 3.91 ms per token, 255.87 tokens per second) 3.11.079.046 I slot print_timing: id 2 | task 2362 | eval time = 3890.55 ms / 90 tokens ( 43.71 ms per token, 22.88 tokens per second) 3.11.079.046 I slot print_timing: id 2 | task 2362 | total time = 4293.10 ms / 193 tokens 3.11.079.047 I slot print_timing: id 2 | task 2362 | graphs reused = 1812 3.11.079.048 I slot print_timing: id 2 | task 2362 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.079.118 I slot release: id 2 | task 2362 | stop processing: n_tokens = 1307, truncated = 0 3.11.139.086 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.853 3.11.139.111 I slot launch_slot_: id 2 | task 2456 | processing task, is_child = 0 3.11.394.308 I slot print_timing: id 1 | task 2024 | n_gen = 422, tg = 21.17 t/s, tg_3s = 22.19 t/s 3.11.900.632 I slot print_timing: id 0 | task 2308 | prompt eval time = 306.99 ms / 78 tokens ( 3.94 ms per token, 254.08 tokens per second) 3.11.900.636 I slot print_timing: id 0 | task 2308 | eval time = 7223.48 ms / 156 tokens ( 46.60 ms per token, 21.46 tokens per second) 3.11.900.636 I slot print_timing: id 0 | task 2308 | total time = 7530.47 ms / 234 tokens 3.11.900.637 I slot print_timing: id 0 | task 2308 | graphs reused = 1821 3.11.900.637 I slot print_timing: id 0 | task 2308 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.900.692 I slot release: id 0 | task 2308 | stop processing: n_tokens = 1348, truncated = 0 3.11.945.234 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.827 3.11.945.256 I slot launch_slot_: id 0 | task 2470 | processing task, is_child = 0 3.13.034.358 I slot print_timing: id 3 | task 2388 | n_gen = 100, tg = 21.60 t/s, tg_3s = 21.82 t/s 3.14.431.098 I slot print_timing: id 1 | task 2024 | n_gen = 489, tg = 21.29 t/s, tg_3s = 22.06 t/s 3.14.722.565 I slot print_timing: id 3 | task 2388 | prompt eval time = 317.20 ms / 100 tokens ( 3.17 ms per token, 315.26 tokens per second) 3.14.722.569 I slot print_timing: id 3 | task 2388 | eval time = 6270.85 ms / 141 tokens ( 44.79 ms per token, 22.33 tokens per second) 3.14.722.570 I slot print_timing: id 3 | task 2388 | total time = 6588.05 ms / 241 tokens 3.14.722.570 I slot print_timing: id 3 | task 2388 | graphs reused = 1881 3.14.722.571 I slot print_timing: id 3 | task 2388 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.722.631 I slot release: id 3 | task 2388 | stop processing: n_tokens = 1355, truncated = 0 3.14.762.298 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.823 3.14.762.320 I slot launch_slot_: id 3 | task 2534 | processing task, is_child = 0 3.15.186.369 I slot print_timing: id 2 | task 2456 | prompt eval time = 347.01 ms / 83 tokens ( 4.18 ms per token, 239.18 tokens per second) 3.15.186.372 I slot print_timing: id 2 | task 2456 | eval time = 3700.24 ms / 77 tokens ( 48.69 ms per token, 20.54 tokens per second) 3.15.186.373 I slot print_timing: id 2 | task 2456 | total time = 4047.25 ms / 160 tokens 3.15.186.373 I slot print_timing: id 2 | task 2456 | graphs reused = 1881 3.15.186.374 I slot print_timing: id 2 | task 2456 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.186.425 I slot release: id 2 | task 2456 | stop processing: n_tokens = 1274, truncated = 0 3.15.243.182 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.875 3.15.243.208 I slot launch_slot_: id 2 | task 2538 | processing task, is_child = 0 3.15.861.695 I slot print_timing: id 0 | task 2470 | prompt eval time = 308.44 ms / 77 tokens ( 4.01 ms per token, 249.64 tokens per second) 3.15.861.700 I slot print_timing: id 0 | task 2470 | eval time = 3607.99 ms / 75 tokens ( 48.76 ms per token, 20.51 tokens per second) 3.15.861.700 I slot print_timing: id 0 | task 2470 | total time = 3916.43 ms / 152 tokens 3.15.861.701 I slot print_timing: id 0 | task 2470 | graphs reused = 1888 3.15.861.702 I slot print_timing: id 0 | task 2470 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.861.771 I slot release: id 0 | task 2470 | stop processing: n_tokens = 1266, truncated = 0 3.15.907.784 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.881 3.15.907.810 I slot launch_slot_: id 0 | task 2550 | processing task, is_child = 0 3.17.438.485 I slot print_timing: id 1 | task 2024 | n_gen = 544, tg = 20.94 t/s, tg_3s = 18.29 t/s 3.18.513.630 I slot print_timing: id 0 | task 2550 | prompt eval time = 253.05 ms / 57 tokens ( 4.44 ms per token, 225.25 tokens per second) 3.18.513.634 I slot print_timing: id 0 | task 2550 | eval time = 2352.76 ms / 58 tokens ( 41.28 ms per token, 24.23 tokens per second) 3.18.513.635 I slot print_timing: id 0 | task 2550 | total time = 2605.81 ms / 115 tokens 3.18.513.636 I slot print_timing: id 0 | task 2550 | graphs reused = 1945 3.18.513.636 I slot print_timing: id 0 | task 2550 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.513.724 I slot release: id 0 | task 2550 | stop processing: n_tokens = 1229, truncated = 0 3.18.558.457 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.907 3.18.558.480 I slot launch_slot_: id 0 | task 2611 | processing task, is_child = 0 3.19.202.520 I slot print_timing: id 3 | task 2534 | prompt eval time = 425.26 ms / 146 tokens ( 2.91 ms per token, 343.32 tokens per second) 3.19.202.528 I slot print_timing: id 3 | task 2534 | eval time = 4014.93 ms / 83 tokens ( 48.96 ms per token, 20.42 tokens per second) 3.19.202.529 I slot print_timing: id 3 | task 2534 | total time = 4440.19 ms / 229 tokens 3.19.202.529 I slot print_timing: id 3 | task 2534 | graphs reused = 1953 3.19.202.530 I slot print_timing: id 3 | task 2534 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.202.593 I slot release: id 3 | task 2534 | stop processing: n_tokens = 1343, truncated = 0 3.19.242.705 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.830 3.19.242.730 I slot launch_slot_: id 3 | task 2623 | processing task, is_child = 0 3.19.835.825 I slot print_timing: id 2 | task 2538 | prompt eval time = 294.33 ms / 67 tokens ( 4.39 ms per token, 227.64 tokens per second) 3.19.835.831 I slot print_timing: id 2 | task 2538 | eval time = 4298.27 ms / 90 tokens ( 48.30 ms per token, 20.71 tokens per second) 3.19.835.832 I slot print_timing: id 2 | task 2538 | total time = 4592.60 ms / 157 tokens 3.19.835.832 I slot print_timing: id 2 | task 2538 | graphs reused = 1958 3.19.835.833 I slot print_timing: id 2 | task 2538 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.835.909 I slot release: id 2 | task 2538 | stop processing: n_tokens = 1271, truncated = 0 3.19.897.272 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.877 3.19.897.302 I slot launch_slot_: id 2 | task 2634 | processing task, is_child = 0 3.20.441.258 I slot print_timing: id 1 | task 2024 | n_gen = 599, tg = 20.67 t/s, tg_3s = 18.32 t/s 3.22.547.204 I slot print_timing: id 3 | task 2623 | prompt eval time = 310.85 ms / 71 tokens ( 4.38 ms per token, 228.41 tokens per second) 3.22.547.210 I slot print_timing: id 3 | task 2623 | eval time = 2993.61 ms / 67 tokens ( 45.36 ms per token, 22.05 tokens per second) 3.22.547.211 I slot print_timing: id 3 | task 2623 | total time = 3304.46 ms / 138 tokens 3.22.547.211 I slot print_timing: id 3 | task 2623 | graphs reused = 2013 3.22.547.212 I slot print_timing: id 3 | task 2623 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.547.264 I slot release: id 3 | task 2623 | stop processing: n_tokens = 1252, truncated = 0 3.22.586.922 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.891 3.22.586.943 I slot launch_slot_: id 3 | task 2694 | processing task, is_child = 0 3.23.459.570 I slot print_timing: id 0 | task 2611 | prompt eval time = 310.13 ms / 89 tokens ( 3.48 ms per token, 286.98 tokens per second) 3.23.459.574 I slot print_timing: id 0 | task 2611 | eval time = 4590.95 ms / 95 tokens ( 48.84 ms per token, 20.48 tokens per second) 3.23.459.575 I slot print_timing: id 0 | task 2611 | total time = 4901.08 ms / 184 tokens 3.23.459.575 I slot print_timing: id 0 | task 2611 | graphs reused = 2026 3.23.459.576 I slot print_timing: id 0 | task 2611 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.459.633 I slot release: id 0 | task 2611 | stop processing: n_tokens = 1298, truncated = 0 3.23.461.453 I slot print_timing: id 1 | task 2024 | n_gen = 667, tg = 20.84 t/s, tg_3s = 22.52 t/s 3.23.504.751 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.859 3.23.504.773 I slot launch_slot_: id 0 | task 2712 | processing task, is_child = 0 3.24.768.219 I slot print_timing: id 2 | task 2634 | n_gen = 100, tg = 21.89 t/s, tg_3s = 22.11 t/s 3.26.461.596 I slot print_timing: id 1 | task 2024 | n_gen = 734, tg = 20.97 t/s, tg_3s = 22.33 t/s 3.26.792.565 I slot print_timing: id 2 | task 2634 | prompt eval time = 348.50 ms / 84 tokens ( 4.15 ms per token, 241.04 tokens per second) 3.26.792.569 I slot print_timing: id 2 | task 2634 | eval time = 6546.76 ms / 149 tokens ( 44.23 ms per token, 22.61 tokens per second) 3.26.792.570 I slot print_timing: id 2 | task 2634 | total time = 6895.25 ms / 233 tokens 3.26.792.570 I slot print_timing: id 2 | task 2634 | graphs reused = 2098 3.26.792.571 I slot print_timing: id 2 | task 2634 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.792.645 I slot release: id 2 | task 2634 | stop processing: n_tokens = 1347, truncated = 0 3.26.852.204 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.828 3.26.852.231 I slot launch_slot_: id 2 | task 2788 | processing task, is_child = 0 3.27.483.410 I slot print_timing: id 3 | task 2694 | n_gen = 100, tg = 21.59 t/s, tg_3s = 21.81 t/s 3.27.815.950 I slot print_timing: id 0 | task 2712 | prompt eval time = 310.85 ms / 88 tokens ( 3.53 ms per token, 283.09 tokens per second) 3.27.815.956 I slot print_timing: id 0 | task 2712 | eval time = 4000.32 ms / 91 tokens ( 44.45 ms per token, 22.50 tokens per second) 3.27.815.957 I slot print_timing: id 0 | task 2712 | total time = 4311.17 ms / 179 tokens 3.27.815.957 I slot print_timing: id 0 | task 2712 | graphs reused = 2112 3.27.815.958 I slot print_timing: id 0 | task 2712 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.816.010 I slot release: id 0 | task 2712 | stop processing: n_tokens = 1293, truncated = 0 3.27.860.478 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.862 3.27.860.500 I slot launch_slot_: id 0 | task 2807 | processing task, is_child = 0 3.29.179.815 I slot print_timing: id 3 | task 2694 | prompt eval time = 310.68 ms / 72 tokens ( 4.32 ms per token, 231.75 tokens per second) 3.29.179.819 I slot print_timing: id 3 | task 2694 | eval time = 6282.18 ms / 134 tokens ( 47.23 ms per token, 21.17 tokens per second) 3.29.179.820 I slot print_timing: id 3 | task 2694 | total time = 6592.86 ms / 206 tokens 3.29.179.820 I slot print_timing: id 3 | task 2694 | graphs reused = 2135 3.29.179.821 I slot print_timing: id 3 | task 2694 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.179.878 I slot release: id 3 | task 2694 | stop processing: n_tokens = 1320, truncated = 0 3.29.219.542 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.845 3.29.219.564 I slot launch_slot_: id 3 | task 2834 | processing task, is_child = 0 3.29.532.798 I slot print_timing: id 1 | task 2024 | n_gen = 789, tg = 20.72 t/s, tg_3s = 17.91 t/s 3.31.809.160 I slot print_timing: id 2 | task 2788 | n_gen = 100, tg = 21.49 t/s, tg_3s = 21.71 t/s 3.32.019.291 I slot print_timing: id 2 | task 2788 | prompt eval time = 350.36 ms / 94 tokens ( 3.73 ms per token, 268.30 tokens per second) 3.32.019.295 I slot print_timing: id 2 | task 2788 | eval time = 4816.70 ms / 105 tokens ( 46.31 ms per token, 21.59 tokens per second) 3.32.019.296 I slot print_timing: id 2 | task 2788 | total time = 5167.05 ms / 199 tokens 3.32.019.297 I slot print_timing: id 2 | task 2788 | graphs reused = 2193 3.32.019.297 I slot print_timing: id 2 | task 2788 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.019.356 I slot release: id 2 | task 2788 | stop processing: n_tokens = 1313, truncated = 0 3.32.079.264 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.850 3.32.079.290 I slot launch_slot_: id 2 | task 2898 | processing task, is_child = 0 3.32.547.641 I slot print_timing: id 1 | task 2024 | n_gen = 855, tg = 20.81 t/s, tg_3s = 21.89 t/s 3.32.841.145 I slot print_timing: id 0 | task 2807 | n_gen = 100, tg = 21.45 t/s, tg_3s = 21.67 t/s 3.33.928.513 I slot print_timing: id 3 | task 2834 | n_gen = 100, tg = 22.53 t/s, tg_3s = 22.76 t/s 3.35.549.201 I slot print_timing: id 1 | task 2024 | n_gen = 927, tg = 21.03 t/s, tg_3s = 23.99 t/s 3.35.878.861 I slot print_timing: id 0 | task 2807 | n_gen = 173, tg = 22.48 t/s, tg_3s = 24.03 t/s 3.35.883.671 I slot print_timing: id 3 | task 2834 | prompt eval time = 315.42 ms / 88 tokens ( 3.58 ms per token, 278.99 tokens per second) 3.35.883.678 I slot print_timing: id 3 | task 2834 | eval time = 6348.68 ms / 147 tokens ( 43.48 ms per token, 23.00 tokens per second) 3.35.883.679 I slot print_timing: id 3 | task 2834 | total time = 6664.10 ms / 235 tokens 3.35.883.680 I slot print_timing: id 3 | task 2834 | graphs reused = 2275 3.35.883.681 I slot print_timing: id 3 | task 2834 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.883.752 I slot release: id 3 | task 2834 | stop processing: n_tokens = 1349, truncated = 0 3.35.923.837 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.827 3.35.923.862 I slot launch_slot_: id 3 | task 2985 | processing task, is_child = 0 3.36.770.839 I slot print_timing: id 2 | task 2898 | n_gen = 100, tg = 22.81 t/s, tg_3s = 23.04 t/s 3.37.766.193 I slot print_timing: id 0 | task 2807 | prompt eval time = 365.90 ms / 111 tokens ( 3.30 ms per token, 303.36 tokens per second) 3.37.766.201 I slot print_timing: id 0 | task 2807 | eval time = 9539.79 ms / 213 tokens ( 45.00 ms per token, 22.22 tokens per second) 3.37.766.201 I slot print_timing: id 0 | task 2807 | total time = 9905.68 ms / 324 tokens 3.37.766.202 I slot print_timing: id 0 | task 2807 | graphs reused = 2311 3.37.766.203 I slot print_timing: id 0 | task 2807 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.766.290 I slot release: id 0 | task 2807 | stop processing: n_tokens = 1438, truncated = 0 3.37.811.093 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.775 3.37.811.117 I slot launch_slot_: id 0 | task 3026 | processing task, is_child = 0 3.38.440.500 I slot print_timing: id 2 | task 2898 | prompt eval time = 351.20 ms / 83 tokens ( 4.23 ms per token, 236.33 tokens per second) 3.38.440.509 I slot print_timing: id 2 | task 2898 | eval time = 6010.00 ms / 135 tokens ( 44.85 ms per token, 22.30 tokens per second) 3.38.440.510 I slot print_timing: id 2 | task 2898 | total time = 6361.20 ms / 218 tokens 3.38.440.511 I slot print_timing: id 2 | task 2898 | graphs reused = 2319 3.38.440.511 I slot print_timing: id 2 | task 2898 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.440.596 I slot release: id 2 | task 2898 | stop processing: n_tokens = 1333, truncated = 0 3.38.503.640 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.836 3.38.503.673 I slot launch_slot_: id 2 | task 3038 | processing task, is_child = 0 3.38.762.153 I slot print_timing: id 1 | task 2024 | n_gen = 988, tg = 20.89 t/s, tg_3s = 18.99 t/s 3.40.300.066 I slot print_timing: id 1 | task 2024 | prompt eval time = 368.96 ms / 88 tokens ( 4.19 ms per token, 238.51 tokens per second) 3.40.300.073 I slot print_timing: id 1 | task 2024 | eval time = 48791.76 ms / 1024 tokens ( 47.69 ms per token, 20.97 tokens per second) 3.40.300.074 I slot print_timing: id 1 | task 2024 | total time = 49160.72 ms / 1112 tokens 3.40.300.075 I slot print_timing: id 1 | task 2024 | graphs reused = 2353 3.40.300.075 I slot print_timing: id 1 | task 2024 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.300.162 I slot release: id 1 | task 2024 | stop processing: n_tokens = 2226, truncated = 0 3.40.361.294 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.501 3.40.361.322 I slot launch_slot_: id 1 | task 3077 | processing task, is_child = 0 3.41.250.303 I slot print_timing: id 3 | task 2985 | n_gen = 100, tg = 19.75 t/s, tg_3s = 19.95 t/s 3.42.890.195 I slot print_timing: id 0 | task 3026 | prompt eval time = 306.67 ms / 73 tokens ( 4.20 ms per token, 238.04 tokens per second) 3.42.890.200 I slot print_timing: id 0 | task 3026 | eval time = 4772.40 ms / 100 tokens ( 48.21 ms per token, 20.74 tokens per second) 3.42.890.201 I slot print_timing: id 0 | task 3026 | total time = 5079.07 ms / 173 tokens 3.42.890.201 I slot print_timing: id 0 | task 3026 | graphs reused = 2401 3.42.890.202 I slot print_timing: id 0 | task 3026 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.890.275 I slot release: id 0 | task 3026 | stop processing: n_tokens = 1287, truncated = 0 3.42.934.586 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.866 3.42.934.608 I slot launch_slot_: id 0 | task 3131 | processing task, is_child = 0 3.43.561.007 I slot print_timing: id 2 | task 3038 | n_gen = 100, tg = 21.04 t/s, tg_3s = 21.25 t/s 3.43.690.136 I slot print_timing: id 2 | task 3038 | prompt eval time = 350.99 ms / 97 tokens ( 3.62 ms per token, 276.36 tokens per second) 3.43.690.144 I slot print_timing: id 2 | task 3038 | eval time = 4835.46 ms / 103 tokens ( 47.41 ms per token, 21.09 tokens per second) 3.43.690.144 I slot print_timing: id 2 | task 3038 | total time = 5186.45 ms / 200 tokens 3.43.690.145 I slot print_timing: id 2 | task 3038 | graphs reused = 2412 3.43.690.154 I slot print_timing: id 2 | task 3038 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.690.234 I slot release: id 2 | task 3038 | stop processing: n_tokens = 1314, truncated = 0 3.43.750.253 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.849 3.43.750.278 I slot launch_slot_: id 2 | task 3146 | processing task, is_child = 0 3.44.257.425 I slot print_timing: id 3 | task 2985 | prompt eval time = 313.34 ms / 74 tokens ( 4.23 ms per token, 236.17 tokens per second) 3.44.257.428 I slot print_timing: id 3 | task 2985 | eval time = 8020.22 ms / 161 tokens ( 50.13 ms per token, 19.95 tokens per second) 3.44.257.429 I slot print_timing: id 3 | task 2985 | total time = 8333.55 ms / 235 tokens 3.44.257.429 I slot print_timing: id 3 | task 2985 | graphs reused = 2415 3.44.257.430 I slot print_timing: id 3 | task 2985 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.257.486 I slot release: id 3 | task 2985 | stop processing: n_tokens = 1349, truncated = 0 3.44.297.568 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.827 3.44.297.595 I slot launch_slot_: id 3 | task 3154 | processing task, is_child = 0 3.45.639.843 I slot print_timing: id 1 | task 3077 | n_gen = 100, tg = 20.64 t/s, tg_3s = 20.85 t/s 3.46.669.325 I slot print_timing: id 2 | task 3146 | prompt eval time = 348.36 ms / 79 tokens ( 4.41 ms per token, 226.77 tokens per second) 3.46.669.329 I slot print_timing: id 2 | task 3146 | eval time = 2570.67 ms / 58 tokens ( 45.10 ms per token, 22.17 tokens per second) 3.46.669.330 I slot print_timing: id 2 | task 3146 | total time = 2919.04 ms / 137 tokens 3.46.669.331 I slot print_timing: id 2 | task 3146 | graphs reused = 2464 3.46.669.331 I slot print_timing: id 2 | task 3146 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.669.391 I slot release: id 2 | task 3146 | stop processing: n_tokens = 1251, truncated = 0 3.46.729.144 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.891 3.46.729.172 I slot launch_slot_: id 2 | task 3208 | processing task, is_child = 0 3.48.162.539 I slot print_timing: id 0 | task 3131 | n_gen = 100, tg = 20.12 t/s, tg_3s = 20.33 t/s 3.48.659.515 I slot print_timing: id 1 | task 3077 | n_gen = 165, tg = 20.98 t/s, tg_3s = 21.53 t/s 3.49.033.363 I slot print_timing: id 3 | task 3154 | n_gen = 100, tg = 22.39 t/s, tg_3s = 22.62 t/s 3.50.716.551 I slot print_timing: id 0 | task 3131 | prompt eval time = 308.62 ms / 92 tokens ( 3.35 ms per token, 298.11 tokens per second) 3.50.716.557 I slot print_timing: id 0 | task 3131 | eval time = 7473.32 ms / 162 tokens ( 46.42 ms per token, 21.54 tokens per second) 3.50.716.558 I slot print_timing: id 0 | task 3131 | total time = 7781.93 ms / 254 tokens 3.50.716.559 I slot print_timing: id 0 | task 3131 | graphs reused = 2550 3.50.716.559 I slot print_timing: id 0 | task 3131 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.716.617 I slot release: id 0 | task 3131 | stop processing: n_tokens = 1368, truncated = 0 3.50.760.780 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.815 3.50.760.804 I slot launch_slot_: id 0 | task 3299 | processing task, is_child = 0 3.51.397.020 I slot print_timing: id 3 | task 3154 | prompt eval time = 314.71 ms / 83 tokens ( 3.79 ms per token, 263.73 tokens per second) 3.51.397.028 I slot print_timing: id 3 | task 3154 | eval time = 6784.70 ms / 152 tokens ( 44.93 ms per token, 22.26 tokens per second) 3.51.397.028 I slot print_timing: id 3 | task 3154 | total time = 7099.42 ms / 235 tokens 3.51.397.029 I slot print_timing: id 3 | task 3154 | graphs reused = 2558 3.51.397.030 I slot print_timing: id 3 | task 3154 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.397.097 I slot release: id 3 | task 3154 | stop processing: n_tokens = 1349, truncated = 0 3.51.437.615 I slot print_timing: id 2 | task 3208 | n_gen = 100, tg = 23.00 t/s, tg_3s = 23.23 t/s 3.51.437.622 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.827 3.51.437.652 I slot launch_slot_: id 3 | task 3311 | processing task, is_child = 0 3.51.677.113 I slot print_timing: id 1 | task 3077 | n_gen = 228, tg = 20.95 t/s, tg_3s = 20.88 t/s 3.54.096.277 I slot print_timing: id 2 | task 3208 | prompt eval time = 403.43 ms / 108 tokens ( 3.74 ms per token, 267.71 tokens per second) 3.54.096.282 I slot print_timing: id 2 | task 3208 | eval time = 6963.67 ms / 159 tokens ( 44.07 ms per token, 22.69 tokens per second) 3.54.096.284 I slot print_timing: id 2 | task 3208 | total time = 7367.09 ms / 267 tokens 3.54.096.285 I slot print_timing: id 2 | task 3208 | graphs reused = 2613 3.54.096.285 I slot print_timing: id 2 | task 3208 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.096.358 I slot release: id 2 | task 3208 | stop processing: n_tokens = 1381, truncated = 0 3.54.156.623 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.807 3.54.156.650 I slot launch_slot_: id 2 | task 3372 | processing task, is_child = 0 3.54.702.937 I slot print_timing: id 1 | task 3077 | n_gen = 294, tg = 21.14 t/s, tg_3s = 21.81 t/s 3.55.453.905 I slot print_timing: id 0 | task 3299 | prompt eval time = 309.63 ms / 88 tokens ( 3.52 ms per token, 284.21 tokens per second) 3.55.453.908 I slot print_timing: id 0 | task 3299 | eval time = 4383.46 ms / 95 tokens ( 46.63 ms per token, 21.44 tokens per second) 3.55.453.913 I slot print_timing: id 0 | task 3299 | total time = 4693.09 ms / 183 tokens 3.55.453.914 I slot print_timing: id 0 | task 3299 | graphs reused = 2635 3.55.453.916 I slot print_timing: id 0 | task 3299 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.453.997 I slot release: id 0 | task 3299 | stop processing: n_tokens = 1297, truncated = 0 3.55.498.803 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 3.55.498.826 I slot launch_slot_: id 0 | task 3399 | processing task, is_child = 0 3.56.342.949 I slot print_timing: id 3 | task 3311 | prompt eval time = 315.52 ms / 91 tokens ( 3.47 ms per token, 288.41 tokens per second) 3.56.342.957 I slot print_timing: id 3 | task 3311 | eval time = 4589.76 ms / 100 tokens ( 46.36 ms per token, 21.57 tokens per second) 3.56.342.962 I slot print_timing: id 3 | task 3311 | total time = 4905.29 ms / 191 tokens 3.56.342.963 I slot print_timing: id 3 | task 3311 | graphs reused = 2648 3.56.342.963 I slot print_timing: id 3 | task 3311 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.343.042 I slot release: id 3 | task 3311 | stop processing: n_tokens = 1305, truncated = 0 3.56.382.980 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.854 3.56.383.001 I slot launch_slot_: id 3 | task 3416 | processing task, is_child = 0 3.57.720.180 I slot print_timing: id 1 | task 3077 | n_gen = 356, tg = 21.03 t/s, tg_3s = 20.55 t/s 3.58.217.225 I slot print_timing: id 1 | task 3077 | prompt eval time = 481.33 ms / 143 tokens ( 3.37 ms per token, 297.09 tokens per second) 3.58.217.231 I slot print_timing: id 1 | task 3077 | eval time = 17374.56 ms / 368 tokens ( 47.34 ms per token, 21.12 tokens per second) 3.58.217.231 I slot print_timing: id 1 | task 3077 | total time = 17855.89 ms / 511 tokens 3.58.217.232 I slot print_timing: id 1 | task 3077 | graphs reused = 2684 3.58.217.232 I slot print_timing: id 1 | task 3077 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.217.314 I slot release: id 1 | task 3077 | stop processing: n_tokens = 1624, truncated = 0 3.58.278.565 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.687 3.58.278.589 I slot launch_slot_: id 1 | task 3457 | processing task, is_child = 0 3.59.355.104 I slot print_timing: id 2 | task 3372 | n_gen = 100, tg = 20.42 t/s, tg_3s = 20.63 t/s 3.59.807.564 I slot print_timing: id 0 | task 3399 | prompt eval time = 311.46 ms / 97 tokens ( 3.21 ms per token, 311.43 tokens per second) 3.59.807.568 I slot print_timing: id 0 | task 3399 | eval time = 3997.27 ms / 85 tokens ( 47.59 ms per token, 21.01 tokens per second) 3.59.807.569 I slot print_timing: id 0 | task 3399 | total time = 4308.73 ms / 182 tokens 3.59.807.570 I slot print_timing: id 0 | task 3399 | graphs reused = 2711 3.59.807.570 I slot print_timing: id 0 | task 3399 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.807.657 I slot release: id 0 | task 3399 | stop processing: n_tokens = 1296, truncated = 0 3.59.852.165 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.860 3.59.852.194 I slot launch_slot_: id 0 | task 3489 | processing task, is_child = 0 4.01.300.688 I slot print_timing: id 3 | task 3416 | n_gen = 100, tg = 21.50 t/s, tg_3s = 21.72 t/s 4.01.381.000 I slot print_timing: id 2 | task 3372 | prompt eval time = 350.29 ms / 95 tokens ( 3.69 ms per token, 271.21 tokens per second) 4.01.381.008 I slot print_timing: id 2 | task 3372 | eval time = 6874.06 ms / 144 tokens ( 48.07 ms per token, 20.80 tokens per second) 4.01.381.009 I slot print_timing: id 2 | task 3372 | total time = 7224.34 ms / 239 tokens 4.01.381.009 I slot print_timing: id 2 | task 3372 | graphs reused = 2741 4.01.381.010 I slot print_timing: id 2 | task 3372 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.381.064 I slot release: id 2 | task 3372 | stop processing: n_tokens = 1353, truncated = 0 4.01.440.860 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.824 4.01.440.884 I slot launch_slot_: id 2 | task 3523 | processing task, is_child = 0 4.03.218.504 I slot print_timing: id 1 | task 3457 | n_gen = 100, tg = 21.66 t/s, tg_3s = 21.88 t/s 4.04.333.316 I slot print_timing: id 3 | task 3416 | n_gen = 167, tg = 21.73 t/s, tg_3s = 22.09 t/s 4.04.492.724 I slot print_timing: id 0 | task 3489 | n_gen = 100, tg = 22.86 t/s, tg_3s = 23.09 t/s 4.04.577.338 I slot print_timing: id 1 | task 3457 | prompt eval time = 369.88 ms / 95 tokens ( 3.89 ms per token, 256.84 tokens per second) 4.04.577.341 I slot print_timing: id 1 | task 3457 | eval time = 5928.86 ms / 133 tokens ( 44.92 ms per token, 22.26 tokens per second) 4.04.577.342 I slot print_timing: id 1 | task 3457 | total time = 6298.74 ms / 228 tokens 4.04.577.342 I slot print_timing: id 1 | task 3457 | graphs reused = 2808 4.04.577.343 I slot print_timing: id 1 | task 3457 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.577.397 I slot release: id 1 | task 3457 | stop processing: n_tokens = 1342, truncated = 0 4.04.638.470 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.831 4.04.638.500 I slot launch_slot_: id 1 | task 3595 | processing task, is_child = 0 4.05.003.942 I slot print_timing: id 0 | task 3489 | prompt eval time = 309.82 ms / 89 tokens ( 3.48 ms per token, 287.26 tokens per second) 4.05.003.945 I slot print_timing: id 0 | task 3489 | eval time = 4841.92 ms / 105 tokens ( 46.56 ms per token, 21.48 tokens per second) 4.05.003.945 I slot print_timing: id 0 | task 3489 | total time = 5151.74 ms / 194 tokens 4.05.003.945 I slot print_timing: id 0 | task 3489 | graphs reused = 2808 4.05.003.946 I slot print_timing: id 0 | task 3489 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.003.989 I slot release: id 0 | task 3489 | stop processing: n_tokens = 1308, truncated = 0 4.05.044.388 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.852 4.05.044.407 I slot launch_slot_: id 0 | task 3599 | processing task, is_child = 0 4.06.329.110 I slot print_timing: id 2 | task 3523 | prompt eval time = 345.49 ms / 74 tokens ( 4.67 ms per token, 214.19 tokens per second) 4.06.329.116 I slot print_timing: id 2 | task 3523 | eval time = 4542.73 ms / 96 tokens ( 47.82 ms per token, 20.91 tokens per second) 4.06.329.117 I slot print_timing: id 2 | task 3523 | total time = 4888.22 ms / 170 tokens 4.06.329.117 I slot print_timing: id 2 | task 3523 | graphs reused = 2829 4.06.329.118 I slot print_timing: id 2 | task 3523 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.329.172 I slot release: id 2 | task 3523 | stop processing: n_tokens = 1284, truncated = 0 4.06.388.774 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.868 4.06.388.798 I slot launch_slot_: id 2 | task 3624 | processing task, is_child = 0 4.07.271.359 I slot print_timing: id 3 | task 3416 | prompt eval time = 312.79 ms / 78 tokens ( 4.01 ms per token, 249.37 tokens per second) 4.07.271.366 I slot print_timing: id 3 | task 3416 | eval time = 10575.56 ms / 216 tokens ( 49.19 ms per token, 20.33 tokens per second) 4.07.271.367 I slot print_timing: id 3 | task 3416 | total time = 10888.35 ms / 294 tokens 4.07.271.368 I slot print_timing: id 3 | task 3416 | graphs reused = 2841 4.07.271.368 I slot print_timing: id 3 | task 3416 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.271.435 I slot release: id 3 | task 3416 | stop processing: n_tokens = 1408, truncated = 0 4.07.311.130 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.792 4.07.311.154 I slot launch_slot_: id 3 | task 3641 | processing task, is_child = 0 4.08.856.713 I slot print_timing: id 1 | task 3595 | prompt eval time = 366.60 ms / 76 tokens ( 4.82 ms per token, 207.31 tokens per second) 4.08.856.718 I slot print_timing: id 1 | task 3595 | eval time = 3851.60 ms / 74 tokens ( 52.76 ms per token, 18.95 tokens per second) 4.08.856.718 I slot print_timing: id 1 | task 3595 | total time = 4218.20 ms / 150 tokens 4.08.856.719 I slot print_timing: id 1 | task 3595 | graphs reused = 2870 4.08.856.719 I slot print_timing: id 1 | task 3595 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.856.788 I slot release: id 1 | task 3595 | stop processing: n_tokens = 1263, truncated = 0 4.08.918.060 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.883 4.08.918.086 I slot launch_slot_: id 1 | task 3675 | processing task, is_child = 0 4.10.346.685 I slot print_timing: id 0 | task 3599 | n_gen = 100, tg = 20.29 t/s, tg_3s = 20.49 t/s 4.11.340.517 I slot print_timing: id 2 | task 3624 | n_gen = 100, tg = 21.51 t/s, tg_3s = 21.73 t/s 4.12.000.345 I slot print_timing: id 3 | task 3641 | n_gen = 100, tg = 22.63 t/s, tg_3s = 22.86 t/s 4.12.367.165 I slot print_timing: id 1 | task 3675 | prompt eval time = 366.99 ms / 80 tokens ( 4.59 ms per token, 217.99 tokens per second) 4.12.367.171 I slot print_timing: id 1 | task 3675 | eval time = 3082.08 ms / 76 tokens ( 41.09 ms per token, 24.33 tokens per second) 4.12.367.172 I slot print_timing: id 1 | task 3675 | total time = 3449.07 ms / 156 tokens 4.12.367.172 I slot print_timing: id 1 | task 3675 | graphs reused = 2944 4.12.367.173 I slot print_timing: id 1 | task 3675 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.367.228 I slot release: id 1 | task 3675 | stop processing: n_tokens = 1270, truncated = 0 4.12.428.551 I slot print_timing: id 3 | task 3641 | prompt eval time = 315.41 ms / 92 tokens ( 3.43 ms per token, 291.68 tokens per second) 4.12.428.556 I slot print_timing: id 3 | task 3641 | eval time = 4801.98 ms / 110 tokens ( 44.05 ms per token, 22.70 tokens per second) 4.12.428.557 I slot print_timing: id 3 | task 3641 | total time = 5117.39 ms / 202 tokens 4.12.428.557 I slot print_timing: id 3 | task 3641 | graphs reused = 2944 4.12.428.558 I slot print_timing: id 3 | task 3641 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.428.612 I slot release: id 3 | task 3641 | stop processing: n_tokens = 1316, truncated = 0 4.12.428.621 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.878 4.12.428.644 I slot launch_slot_: id 1 | task 3754 | processing task, is_child = 0 4.12.458.220 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.847 4.12.458.241 I slot launch_slot_: id 3 | task 3755 | processing task, is_child = 0 4.13.371.824 I slot print_timing: id 0 | task 3599 | n_gen = 161, tg = 20.24 t/s, tg_3s = 20.16 t/s 4.13.912.356 I slot print_timing: id 2 | task 3624 | prompt eval time = 348.87 ms / 95 tokens ( 3.67 ms per token, 272.31 tokens per second) 4.13.912.362 I slot print_timing: id 2 | task 3624 | eval time = 7174.68 ms / 150 tokens ( 48.15 ms per token, 20.77 tokens per second) 4.13.912.362 I slot print_timing: id 2 | task 3624 | total time = 7523.55 ms / 245 tokens 4.13.912.363 I slot print_timing: id 2 | task 3624 | graphs reused = 2965 4.13.912.364 I slot print_timing: id 2 | task 3624 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.912.446 I slot release: id 2 | task 3624 | stop processing: n_tokens = 1359, truncated = 0 4.13.972.543 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.820 4.13.972.574 I slot launch_slot_: id 2 | task 3781 | processing task, is_child = 0 4.14.947.952 I slot print_timing: id 0 | task 3599 | prompt eval time = 422.87 ms / 151 tokens ( 2.80 ms per token, 357.08 tokens per second) 4.14.947.957 I slot print_timing: id 0 | task 3599 | eval time = 9480.66 ms / 191 tokens ( 49.90 ms per token, 20.04 tokens per second) 4.14.947.957 I slot print_timing: id 0 | task 3599 | total time = 9903.53 ms / 342 tokens 4.14.947.958 I slot print_timing: id 0 | task 3599 | graphs reused = 2978 4.14.947.959 I slot print_timing: id 0 | task 3599 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.948.030 I slot release: id 0 | task 3599 | stop processing: n_tokens = 1456, truncated = 0 4.14.992.647 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.766 4.14.992.673 I slot launch_slot_: id 0 | task 3799 | processing task, is_child = 0 4.17.257.511 I slot print_timing: id 1 | task 3754 | prompt eval time = 544.99 ms / 95 tokens ( 5.74 ms per token, 174.32 tokens per second) 4.17.257.518 I slot print_timing: id 1 | task 3754 | eval time = 4254.27 ms / 92 tokens ( 46.75 ms per token, 21.39 tokens per second) 4.17.257.518 I slot print_timing: id 1 | task 3754 | total time = 4799.26 ms / 187 tokens 4.17.257.519 I slot print_timing: id 1 | task 3754 | graphs reused = 3026 4.17.257.519 I slot print_timing: id 1 | task 3754 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.257.593 I slot release: id 1 | task 3754 | stop processing: n_tokens = 1301, truncated = 0 4.17.318.859 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.857 4.17.318.883 I slot launch_slot_: id 1 | task 3852 | processing task, is_child = 0 4.17.902.970 I slot print_timing: id 3 | task 3755 | prompt eval time = 545.32 ms / 63 tokens ( 8.66 ms per token, 115.53 tokens per second) 4.17.902.975 I slot print_timing: id 3 | task 3755 | eval time = 4897.56 ms / 99 tokens ( 49.98 ms per token, 20.01 tokens per second) 4.17.902.976 I slot print_timing: id 3 | task 3755 | total time = 5442.87 ms / 162 tokens 4.17.902.976 I slot print_timing: id 3 | task 3755 | graphs reused = 3029 4.17.902.977 I slot print_timing: id 3 | task 3755 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.903.037 I slot release: id 3 | task 3755 | stop processing: n_tokens = 1276, truncated = 0 4.17.941.417 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.874 4.17.941.440 I slot launch_slot_: id 3 | task 3860 | processing task, is_child = 0 4.18.821.077 I slot print_timing: id 0 | task 3799 | prompt eval time = 255.18 ms / 62 tokens ( 4.12 ms per token, 242.97 tokens per second) 4.18.821.083 I slot print_timing: id 0 | task 3799 | eval time = 3573.22 ms / 74 tokens ( 48.95 ms per token, 20.43 tokens per second) 4.18.821.083 I slot print_timing: id 0 | task 3799 | total time = 3828.40 ms / 136 tokens 4.18.821.084 I slot print_timing: id 0 | task 3799 | graphs reused = 3042 4.18.821.085 I slot print_timing: id 0 | task 3799 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.821.140 I slot release: id 0 | task 3799 | stop processing: n_tokens = 1250, truncated = 0 4.18.865.488 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.892 4.18.865.514 I slot launch_slot_: id 0 | task 3878 | processing task, is_child = 0 4.19.411.045 I slot print_timing: id 2 | task 3781 | n_gen = 100, tg = 19.66 t/s, tg_3s = 19.86 t/s 4.20.078.309 I slot print_timing: id 2 | task 3781 | prompt eval time = 403.67 ms / 105 tokens ( 3.84 ms per token, 260.12 tokens per second) 4.20.078.313 I slot print_timing: id 2 | task 3781 | eval time = 5702.06 ms / 116 tokens ( 49.58 ms per token, 20.17 tokens per second) 4.20.078.315 I slot print_timing: id 2 | task 3781 | total time = 6105.73 ms / 221 tokens 4.20.078.316 I slot print_timing: id 2 | task 3781 | graphs reused = 3064 4.20.078.316 I slot print_timing: id 2 | task 3781 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.078.386 I slot release: id 2 | task 3781 | stop processing: n_tokens = 1335, truncated = 0 4.20.138.365 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.835 4.20.138.395 I slot launch_slot_: id 2 | task 3904 | processing task, is_child = 0 4.22.598.857 I slot print_timing: id 1 | task 3852 | n_gen = 100, tg = 20.40 t/s, tg_3s = 20.60 t/s 4.22.890.407 I slot print_timing: id 3 | task 3860 | n_gen = 100, tg = 21.37 t/s, tg_3s = 21.58 t/s 4.23.383.064 I slot print_timing: id 3 | task 3860 | prompt eval time = 315.59 ms / 94 tokens ( 3.36 ms per token, 297.85 tokens per second) 4.23.383.068 I slot print_timing: id 3 | task 3860 | eval time = 5126.02 ms / 112 tokens ( 46.18 ms per token, 21.65 tokens per second) 4.23.383.068 I slot print_timing: id 3 | task 3860 | total time = 5441.62 ms / 206 tokens 4.23.383.069 I slot print_timing: id 3 | task 3860 | graphs reused = 3132 4.23.383.070 I slot print_timing: id 3 | task 3860 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.383.123 I slot release: id 3 | task 3860 | stop processing: n_tokens = 1320, truncated = 0 4.23.422.621 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.845 4.23.422.646 I slot launch_slot_: id 3 | task 3977 | processing task, is_child = 0 4.23.756.304 I slot print_timing: id 0 | task 3878 | n_gen = 100, tg = 21.61 t/s, tg_3s = 21.83 t/s 4.24.208.265 I slot print_timing: id 1 | task 3852 | prompt eval time = 426.33 ms / 133 tokens ( 3.21 ms per token, 311.97 tokens per second) 4.24.208.272 I slot print_timing: id 1 | task 3852 | eval time = 6463.04 ms / 135 tokens ( 48.23 ms per token, 20.73 tokens per second) 4.24.208.273 I slot print_timing: id 1 | task 3852 | total time = 6889.37 ms / 268 tokens 4.24.208.274 I slot print_timing: id 1 | task 3852 | graphs reused = 3144 4.24.208.274 I slot print_timing: id 1 | task 3852 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.208.354 I slot release: id 1 | task 3852 | stop processing: n_tokens = 1382, truncated = 0 4.24.269.538 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.807 4.24.269.564 I slot launch_slot_: id 1 | task 3994 | processing task, is_child = 0 4.25.091.937 I slot print_timing: id 2 | task 3904 | n_gen = 100, tg = 21.76 t/s, tg_3s = 21.98 t/s 4.25.175.036 I slot print_timing: id 2 | task 3904 | prompt eval time = 404.80 ms / 110 tokens ( 3.68 ms per token, 271.74 tokens per second) 4.25.175.043 I slot print_timing: id 2 | task 3904 | eval time = 4631.83 ms / 102 tokens ( 45.86 ms per token, 21.81 tokens per second) 4.25.175.044 I slot print_timing: id 2 | task 3904 | total time = 5036.63 ms / 212 tokens 4.25.175.044 I slot print_timing: id 2 | task 3904 | graphs reused = 3156 4.25.175.045 I slot print_timing: id 2 | task 3904 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.175.127 I slot release: id 2 | task 3904 | stop processing: n_tokens = 1326, truncated = 0 4.25.235.193 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.841 4.25.235.225 I slot launch_slot_: id 2 | task 4011 | processing task, is_child = 0 4.26.534.699 I slot print_timing: id 0 | task 3878 | prompt eval time = 309.26 ms / 85 tokens ( 3.64 ms per token, 274.85 tokens per second) 4.26.534.705 I slot print_timing: id 0 | task 3878 | eval time = 7359.91 ms / 152 tokens ( 48.74 ms per token, 20.52 tokens per second) 4.26.534.705 I slot print_timing: id 0 | task 3878 | total time = 7669.18 ms / 237 tokens 4.26.534.706 I slot print_timing: id 0 | task 3878 | graphs reused = 3177 4.26.534.706 I slot print_timing: id 0 | task 3878 | graph reallocs = 0 / 0 (same size) / (changed size) 4.26.534.776 I slot release: id 0 | task 3878 | stop processing: n_tokens = 1351, truncated = 0 4.26.579.435 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.825 4.26.579.462 I slot launch_slot_: id 0 | task 4037 | processing task, is_child = 0 4.27.706.745 I slot print_timing: id 3 | task 3977 | prompt eval time = 258.42 ms / 68 tokens ( 3.80 ms per token, 263.14 tokens per second) 4.27.706.751 I slot print_timing: id 3 | task 3977 | eval time = 4025.68 ms / 78 tokens ( 52.28 ms per token, 19.13 tokens per second) 4.27.706.752 I slot print_timing: id 3 | task 3977 | total time = 4284.09 ms / 146 tokens 4.27.706.753 I slot print_timing: id 3 | task 3977 | graphs reused = 3197 4.27.706.753 I slot print_timing: id 3 | task 3977 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.706.806 I slot release: id 3 | task 3977 | stop processing: n_tokens = 1260, truncated = 0 4.27.746.236 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.885 4.27.746.264 I slot launch_slot_: id 3 | task 4061 | processing task, is_child = 0 4.29.490.291 I slot print_timing: id 1 | task 3994 | n_gen = 100, tg = 20.41 t/s, tg_3s = 20.62 t/s 4.30.023.937 I slot print_timing: id 1 | task 3994 | prompt eval time = 370.18 ms / 100 tokens ( 3.70 ms per token, 270.14 tokens per second) 4.30.023.941 I slot print_timing: id 1 | task 3994 | eval time = 5384.19 ms / 113 tokens ( 48.07 ms per token, 20.80 tokens per second) 4.30.023.941 I slot print_timing: id 1 | task 3994 | total time = 5754.37 ms / 213 tokens 4.30.023.942 I slot print_timing: id 1 | task 3994 | graphs reused = 3243 4.30.023.942 I slot print_timing: id 1 | task 3994 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.024.000 I slot release: id 1 | task 3994 | stop processing: n_tokens = 1327, truncated = 0 4.30.085.139 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.840 4.30.085.163 I slot launch_slot_: id 1 | task 4113 | processing task, is_child = 0 4.30.454.696 I slot print_timing: id 2 | task 4011 | n_gen = 100, tg = 20.55 t/s, tg_3s = 20.76 t/s 4.31.476.294 I slot print_timing: id 0 | task 4037 | n_gen = 100, tg = 21.56 t/s, tg_3s = 21.78 t/s 4.32.221.321 I slot print_timing: id 3 | task 4061 | prompt eval time = 311.09 ms / 73 tokens ( 4.26 ms per token, 234.66 tokens per second) 4.32.221.326 I slot print_timing: id 3 | task 4061 | eval time = 4163.96 ms / 95 tokens ( 44.30 ms per token, 22.57 tokens per second) 4.32.221.327 I slot print_timing: id 3 | task 4061 | total time = 4475.05 ms / 168 tokens 4.32.221.328 I slot print_timing: id 3 | task 4061 | graphs reused = 3285 4.32.221.328 I slot print_timing: id 3 | task 4061 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.221.397 I slot release: id 3 | task 4061 | stop processing: n_tokens = 1282, truncated = 0 4.32.261.016 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.870 4.32.261.037 I slot launch_slot_: id 3 | task 4160 | processing task, is_child = 0 4.33.487.222 I slot print_timing: id 2 | task 4011 | n_gen = 167, tg = 21.15 t/s, tg_3s = 22.09 t/s 4.34.511.562 I slot print_timing: id 0 | task 4037 | n_gen = 167, tg = 21.76 t/s, tg_3s = 22.07 t/s 4.34.800.300 I slot print_timing: id 1 | task 4113 | n_gen = 100, tg = 22.78 t/s, tg_3s = 23.01 t/s 4.36.155.973 I slot print_timing: id 0 | task 4037 | prompt eval time = 305.04 ms / 70 tokens ( 4.36 ms per token, 229.48 tokens per second) 4.36.155.980 I slot print_timing: id 0 | task 4037 | eval time = 9271.46 ms / 207 tokens ( 45.01 ms per token, 22.22 tokens per second) 4.36.155.981 I slot print_timing: id 0 | task 4037 | total time = 9576.50 ms / 277 tokens 4.36.155.981 I slot print_timing: id 0 | task 4037 | graphs reused = 3370 4.36.155.982 I slot print_timing: id 0 | task 4037 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.156.036 I slot release: id 0 | task 4037 | stop processing: n_tokens = 1391, truncated = 0 4.36.200.437 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.802 4.36.200.458 I slot launch_slot_: id 0 | task 4250 | processing task, is_child = 0 4.36.510.339 I slot print_timing: id 2 | task 4011 | n_gen = 235, tg = 21.52 t/s, tg_3s = 22.49 t/s 4.36.913.619 I slot print_timing: id 3 | task 4160 | n_gen = 100, tg = 23.11 t/s, tg_3s = 23.34 t/s 4.37.822.745 I slot print_timing: id 1 | task 4113 | n_gen = 168, tg = 22.66 t/s, tg_3s = 22.50 t/s 4.38.523.512 I slot print_timing: id 1 | task 4113 | prompt eval time = 368.50 ms / 91 tokens ( 4.05 ms per token, 246.95 tokens per second) 4.38.523.520 I slot print_timing: id 1 | task 4113 | eval time = 8069.85 ms / 185 tokens ( 43.86 ms per token, 22.80 tokens per second) 4.38.523.521 I slot print_timing: id 1 | task 4113 | total time = 8438.34 ms / 276 tokens 4.38.523.521 I slot print_timing: id 1 | task 4113 | graphs reused = 3419 4.38.523.522 I slot print_timing: id 1 | task 4113 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.523.591 I slot release: id 1 | task 4113 | stop processing: n_tokens = 1390, truncated = 0 4.38.584.983 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.802 4.38.585.012 I slot launch_slot_: id 1 | task 4303 | processing task, is_child = 0 4.39.530.806 I slot print_timing: id 2 | task 4011 | n_gen = 301, tg = 21.59 t/s, tg_3s = 21.85 t/s 4.39.943.182 I slot print_timing: id 3 | task 4160 | n_gen = 166, tg = 22.56 t/s, tg_3s = 21.79 t/s 4.40.108.087 I slot print_timing: id 3 | task 4160 | prompt eval time = 368.52 ms / 105 tokens ( 3.51 ms per token, 284.92 tokens per second) 4.40.108.093 I slot print_timing: id 3 | task 4160 | eval time = 7478.52 ms / 170 tokens ( 44.25 ms per token, 22.60 tokens per second) 4.40.108.094 I slot print_timing: id 3 | task 4160 | total time = 7847.04 ms / 275 tokens 4.40.108.095 I slot print_timing: id 3 | task 4160 | graphs reused = 3446 4.40.108.095 I slot print_timing: id 3 | task 4160 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.108.162 I slot release: id 3 | task 4160 | stop processing: n_tokens = 1389, truncated = 0 4.40.147.673 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.803 4.40.147.695 I slot launch_slot_: id 3 | task 4335 | processing task, is_child = 0 4.41.161.225 I slot print_timing: id 0 | task 4250 | n_gen = 100, tg = 21.28 t/s, tg_3s = 21.49 t/s 4.41.284.460 I slot print_timing: id 0 | task 4250 | prompt eval time = 307.76 ms / 79 tokens ( 3.90 ms per token, 256.69 tokens per second) 4.41.284.463 I slot print_timing: id 0 | task 4250 | eval time = 4776.24 ms / 103 tokens ( 46.83 ms per token, 21.36 tokens per second) 4.41.284.465 I slot print_timing: id 0 | task 4250 | total time = 5083.99 ms / 182 tokens 4.41.284.468 I slot print_timing: id 0 | task 4250 | graphs reused = 3464 4.41.284.468 I slot print_timing: id 0 | task 4250 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.284.533 I slot release: id 0 | task 4250 | stop processing: n_tokens = 1296, truncated = 0 4.41.329.127 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.860 4.41.329.154 I slot launch_slot_: id 0 | task 4358 | processing task, is_child = 0 4.42.541.700 I slot print_timing: id 2 | task 4011 | n_gen = 362, tg = 21.36 t/s, tg_3s = 20.26 t/s 4.43.533.017 I slot print_timing: id 1 | task 4303 | n_gen = 100, tg = 21.62 t/s, tg_3s = 21.84 t/s 4.44.821.958 I slot print_timing: id 3 | task 4335 | n_gen = 100, tg = 22.99 t/s, tg_3s = 23.22 t/s 4.45.147.537 I slot print_timing: id 0 | task 4358 | prompt eval time = 310.15 ms / 98 tokens ( 3.16 ms per token, 315.98 tokens per second) 4.45.147.540 I slot print_timing: id 0 | task 4358 | eval time = 3508.22 ms / 86 tokens ( 41.27 ms per token, 24.23 tokens per second) 4.45.147.541 I slot print_timing: id 0 | task 4358 | total time = 3818.37 ms / 184 tokens 4.45.147.541 I slot print_timing: id 0 | task 4358 | graphs reused = 3549 4.45.147.542 I slot print_timing: id 0 | task 4358 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.147.608 I slot release: id 0 | task 4358 | stop processing: n_tokens = 1298, truncated = 0 4.45.192.258 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.859 4.45.192.280 I slot launch_slot_: id 0 | task 4447 | processing task, is_child = 0 4.45.545.272 I slot print_timing: id 2 | task 4011 | n_gen = 429, tg = 21.50 t/s, tg_3s = 22.31 t/s 4.46.536.321 I slot print_timing: id 1 | task 4303 | n_gen = 167, tg = 21.90 t/s, tg_3s = 22.31 t/s 4.47.860.552 I slot print_timing: id 3 | task 4335 | n_gen = 168, tg = 22.74 t/s, tg_3s = 22.38 t/s 4.48.560.863 I slot print_timing: id 2 | task 4011 | n_gen = 502, tg = 21.86 t/s, tg_3s = 24.21 t/s 4.49.512.446 I slot print_timing: id 1 | task 4303 | prompt eval time = 369.84 ms / 97 tokens ( 3.81 ms per token, 262.27 tokens per second) 4.49.512.454 I slot print_timing: id 1 | task 4303 | eval time = 10557.58 ms / 239 tokens ( 44.36 ms per token, 22.54 tokens per second) 4.49.512.454 I slot print_timing: id 1 | task 4303 | total time = 10927.42 ms / 336 tokens 4.49.512.455 I slot print_timing: id 1 | task 4303 | graphs reused = 3646 4.49.512.455 I slot print_timing: id 1 | task 4303 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.512.534 I slot release: id 1 | task 4303 | stop processing: n_tokens = 1450, truncated = 0 4.49.574.175 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.769 4.49.574.199 I slot launch_slot_: id 1 | task 4548 | processing task, is_child = 0 4.49.836.329 I slot print_timing: id 0 | task 4447 | n_gen = 100, tg = 22.85 t/s, tg_3s = 23.08 t/s 4.50.802.712 I slot print_timing: id 3 | task 4335 | prompt eval time = 368.20 ms / 108 tokens ( 3.41 ms per token, 293.32 tokens per second) 4.50.802.715 I slot print_timing: id 3 | task 4335 | eval time = 10286.81 ms / 232 tokens ( 44.53 ms per token, 22.46 tokens per second) 4.50.802.715 I slot print_timing: id 3 | task 4335 | total time = 10655.01 ms / 340 tokens 4.50.802.716 I slot print_timing: id 3 | task 4335 | graphs reused = 3666 4.50.802.717 I slot print_timing: id 3 | task 4335 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.802.777 I slot release: id 3 | task 4335 | stop processing: n_tokens = 1454, truncated = 0 4.50.842.512 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.767 4.50.842.533 I slot launch_slot_: id 3 | task 4573 | processing task, is_child = 0 4.51.592.359 I slot print_timing: id 2 | task 4011 | n_gen = 563, tg = 21.65 t/s, tg_3s = 20.12 t/s 4.52.832.433 I slot print_timing: id 0 | task 4447 | prompt eval time = 311.05 ms / 93 tokens ( 3.34 ms per token, 298.99 tokens per second) 4.52.832.440 I slot print_timing: id 0 | task 4447 | eval time = 7329.10 ms / 166 tokens ( 44.42 ms per token, 22.51 tokens per second) 4.52.832.441 I slot print_timing: id 0 | task 4447 | total time = 7640.14 ms / 259 tokens 4.52.832.441 I slot print_timing: id 0 | task 4447 | graphs reused = 3705 4.52.832.442 I slot print_timing: id 0 | task 4447 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.832.499 I slot release: id 0 | task 4447 | stop processing: n_tokens = 1373, truncated = 0 4.52.877.090 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.812 4.52.877.115 I slot launch_slot_: id 0 | task 4618 | processing task, is_child = 0 4.54.521.130 I slot print_timing: id 1 | task 4548 | n_gen = 100, tg = 21.61 t/s, tg_3s = 21.83 t/s 4.54.605.069 I slot print_timing: id 2 | task 4011 | n_gen = 629, tg = 21.68 t/s, tg_3s = 21.91 t/s 4.55.140.263 I slot print_timing: id 1 | task 4548 | prompt eval time = 365.30 ms / 76 tokens ( 4.81 ms per token, 208.05 tokens per second) 4.55.140.270 I slot print_timing: id 1 | task 4548 | eval time = 5200.75 ms / 115 tokens ( 45.62 ms per token, 21.92 tokens per second) 4.55.140.271 I slot print_timing: id 1 | task 4548 | total time = 5566.05 ms / 191 tokens 4.55.140.272 I slot print_timing: id 1 | task 4548 | graphs reused = 3751 4.55.140.272 I slot print_timing: id 1 | task 4548 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.140.340 I slot release: id 1 | task 4548 | stop processing: n_tokens = 1305, truncated = 0 4.55.201.795 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.854 4.55.201.820 I slot launch_slot_: id 1 | task 4668 | processing task, is_child = 0 4.55.635.798 I slot print_timing: id 3 | task 4573 | prompt eval time = 310.96 ms / 71 tokens ( 4.38 ms per token, 228.33 tokens per second) 4.55.635.805 I slot print_timing: id 3 | task 4573 | eval time = 4482.30 ms / 97 tokens ( 46.69 ms per token, 21.42 tokens per second) 4.55.635.805 I slot print_timing: id 3 | task 4573 | total time = 4793.26 ms / 168 tokens 4.55.635.806 I slot print_timing: id 3 | task 4573 | graphs reused = 3753 4.55.635.806 I slot print_timing: id 3 | task 4573 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.635.859 I slot release: id 3 | task 4573 | stop processing: n_tokens = 1282, truncated = 0 4.55.674.503 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.870 4.55.674.522 I slot launch_slot_: id 3 | task 4675 | processing task, is_child = 0 4.57.624.141 I slot print_timing: id 2 | task 4011 | n_gen = 691, tg = 21.57 t/s, tg_3s = 20.54 t/s 4.57.787.766 I slot print_timing: id 0 | task 4618 | n_gen = 100, tg = 21.79 t/s, tg_3s = 22.01 t/s 4.58.247.381 I slot print_timing: id 1 | task 4668 | prompt eval time = 314.02 ms / 64 tokens ( 4.91 ms per token, 203.81 tokens per second) 4.58.247.388 I slot print_timing: id 1 | task 4668 | eval time = 2731.53 ms / 62 tokens ( 44.78 ms per token, 22.33 tokens per second) 4.58.247.388 I slot print_timing: id 1 | task 4668 | total time = 3045.55 ms / 126 tokens 4.58.247.389 I slot print_timing: id 1 | task 4668 | graphs reused = 3807 4.58.247.390 I slot print_timing: id 1 | task 4668 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.247.467 I slot release: id 1 | task 4668 | stop processing: n_tokens = 1240, truncated = 0 4.58.309.091 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.899 4.58.309.118 I slot launch_slot_: id 1 | task 4734 | processing task, is_child = 0 5.00.316.163 I slot print_timing: id 3 | task 4675 | prompt eval time = 311.49 ms / 74 tokens ( 4.21 ms per token, 237.57 tokens per second) 5.00.316.171 I slot print_timing: id 3 | task 4675 | eval time = 4330.14 ms / 100 tokens ( 43.74 ms per token, 22.86 tokens per second) 5.00.316.171 I slot print_timing: id 3 | task 4675 | total time = 4641.63 ms / 174 tokens 5.00.316.172 I slot print_timing: id 3 | task 4675 | graphs reused = 3847 5.00.316.173 I slot print_timing: id 3 | task 4675 | graph reallocs = 0 / 0 (same size) / (changed size) 5.00.316.251 I slot release: id 3 | task 4675 | stop processing: n_tokens = 1288, truncated = 0 5.00.356.325 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.866 5.00.356.346 I slot launch_slot_: id 3 | task 4779 | processing task, is_child = 0 5.00.670.519 I slot print_timing: id 2 | task 4011 | n_gen = 753, tg = 21.47 t/s, tg_3s = 20.35 t/s 5.00.825.639 I slot print_timing: id 0 | task 4618 | n_gen = 162, tg = 21.24 t/s, tg_3s = 20.41 t/s 5.01.569.194 I slot print_timing: id 1 | task 4734 | prompt eval time = 312.55 ms / 69 tokens ( 4.53 ms per token, 220.76 tokens per second) 5.01.569.201 I slot print_timing: id 1 | task 4734 | eval time = 2947.52 ms / 67 tokens ( 44.66 ms per token, 22.39 tokens per second) 5.01.569.201 I slot print_timing: id 1 | task 4734 | total time = 3260.07 ms / 136 tokens 5.01.569.202 I slot print_timing: id 1 | task 4734 | graphs reused = 3868 5.01.569.202 I slot print_timing: id 1 | task 4734 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.569.262 I slot release: id 1 | task 4734 | stop processing: n_tokens = 1250, truncated = 0 5.01.630.767 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.892 5.01.630.790 I slot launch_slot_: id 1 | task 4805 | processing task, is_child = 0 5.03.068.459 I slot print_timing: id 0 | task 4618 | prompt eval time = 368.17 ms / 127 tokens ( 2.90 ms per token, 344.95 tokens per second) 5.03.068.463 I slot print_timing: id 0 | task 4618 | eval time = 9823.17 ms / 209 tokens ( 47.23 ms per token, 21.17 tokens per second) 5.03.068.463 I slot print_timing: id 0 | task 4618 | total time = 10191.34 ms / 336 tokens 5.03.068.464 I slot print_timing: id 0 | task 4618 | graphs reused = 3893 5.03.068.464 I slot print_timing: id 0 | task 4618 | graph reallocs = 0 / 0 (same size) / (changed size) 5.03.068.519 I slot release: id 0 | task 4618 | stop processing: n_tokens = 1450, truncated = 0 5.03.113.140 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.769 5.03.113.163 I slot launch_slot_: id 0 | task 4835 | processing task, is_child = 0 5.03.691.015 I slot print_timing: id 2 | task 4011 | n_gen = 815, tg = 21.39 t/s, tg_3s = 20.53 t/s 5.04.655.773 I slot print_timing: id 3 | task 4779 | prompt eval time = 315.28 ms / 88 tokens ( 3.58 ms per token, 279.12 tokens per second) 5.04.655.781 I slot print_timing: id 3 | task 4779 | eval time = 3984.14 ms / 86 tokens ( 46.87 ms per token, 21.33 tokens per second) 5.04.655.782 I slot print_timing: id 3 | task 4779 | total time = 4299.42 ms / 174 tokens 5.04.655.782 I slot print_timing: id 3 | task 4779 | graphs reused = 3923 5.04.655.783 I slot print_timing: id 3 | task 4779 | graph reallocs = 0 / 0 (same size) / (changed size) 5.04.655.872 I slot release: id 3 | task 4779 | stop processing: n_tokens = 1288, truncated = 0 5.04.696.342 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.866 5.04.696.362 I slot launch_slot_: id 3 | task 4870 | processing task, is_child = 0 5.06.396.802 I slot print_timing: id 0 | task 4835 | prompt eval time = 256.52 ms / 65 tokens ( 3.95 ms per token, 253.39 tokens per second) 5.06.396.809 I slot print_timing: id 0 | task 4835 | eval time = 3027.11 ms / 66 tokens ( 46.57 ms per token, 21.47 tokens per second) 5.06.396.810 I slot print_timing: id 0 | task 4835 | total time = 3283.63 ms / 131 tokens 5.06.396.810 I slot print_timing: id 0 | task 4835 | graphs reused = 3953 5.06.396.811 I slot print_timing: id 0 | task 4835 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.396.865 I slot release: id 0 | task 4835 | stop processing: n_tokens = 1245, truncated = 0 5.06.441.558 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.896 5.06.441.580 I slot launch_slot_: id 0 | task 4905 | processing task, is_child = 0 5.06.752.327 I slot print_timing: id 2 | task 4011 | n_gen = 875, tg = 21.26 t/s, tg_3s = 19.60 t/s 5.06.830.609 I slot print_timing: id 1 | task 4805 | n_gen = 100, tg = 20.50 t/s, tg_3s = 20.70 t/s 5.09.446.562 I slot print_timing: id 3 | task 4870 | n_gen = 100, tg = 22.90 t/s, tg_3s = 23.13 t/s 5.09.779.044 I slot print_timing: id 2 | task 4011 | n_gen = 948, tg = 21.45 t/s, tg_3s = 24.12 t/s 5.09.860.245 I slot print_timing: id 1 | task 4805 | n_gen = 173, tg = 21.88 t/s, tg_3s = 24.10 t/s 5.10.857.713 I slot print_timing: id 0 | task 4905 | n_gen = 100, tg = 24.10 t/s, tg_3s = 24.35 t/s 5.11.192.093 I slot print_timing: id 1 | task 4805 | prompt eval time = 369.94 ms / 95 tokens ( 3.89 ms per token, 256.80 tokens per second) 5.11.192.100 I slot print_timing: id 1 | task 4805 | eval time = 9191.36 ms / 205 tokens ( 45.06 ms per token, 22.19 tokens per second) 5.11.192.102 I slot print_timing: id 1 | task 4805 | total time = 9561.30 ms / 300 tokens 5.11.192.102 I slot print_timing: id 1 | task 4805 | graphs reused = 4060 5.11.192.103 I slot print_timing: id 1 | task 4805 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.192.161 I slot release: id 1 | task 4805 | stop processing: n_tokens = 1414, truncated = 0 5.11.253.691 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.789 5.11.253.714 I slot launch_slot_: id 1 | task 5016 | processing task, is_child = 0 5.12.461.335 I slot print_timing: id 0 | task 4905 | prompt eval time = 308.65 ms / 82 tokens ( 3.76 ms per token, 265.67 tokens per second) 5.12.461.342 I slot print_timing: id 0 | task 4905 | eval time = 5711.09 ms / 130 tokens ( 44.27 ms per token, 22.59 tokens per second) 5.12.461.343 I slot print_timing: id 0 | task 4905 | total time = 6019.74 ms / 212 tokens 5.12.461.343 I slot print_timing: id 0 | task 4905 | graphs reused = 4078 5.12.461.344 I slot print_timing: id 0 | task 4905 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.461.399 I slot release: id 0 | task 4905 | stop processing: n_tokens = 1326, truncated = 0 5.12.466.210 I slot print_timing: id 3 | task 4870 | n_gen = 164, tg = 22.20 t/s, tg_3s = 21.19 t/s 5.12.506.183 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.841 5.12.506.209 I slot launch_slot_: id 0 | task 5039 | processing task, is_child = 0 5.12.817.860 I slot print_timing: id 2 | task 4011 | n_gen = 1007, tg = 21.32 t/s, tg_3s = 19.42 t/s 5.13.517.570 I slot print_timing: id 2 | task 4011 | prompt eval time = 402.62 ms / 106 tokens ( 3.80 ms per token, 263.28 tokens per second) 5.13.517.574 I slot print_timing: id 2 | task 4011 | eval time = 47879.72 ms / 1024 tokens ( 46.80 ms per token, 21.37 tokens per second) 5.13.517.575 I slot print_timing: id 2 | task 4011 | total time = 48282.34 ms / 1130 tokens 5.13.517.576 I slot print_timing: id 2 | task 4011 | graphs reused = 4095 5.13.517.576 I slot print_timing: id 2 | task 4011 | graph reallocs = 0 / 0 (same size) / (changed size) 5.13.517.636 I slot release: id 2 | task 4011 | stop processing: n_tokens = 2244, truncated = 0 5.13.577.414 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.497 5.13.612.787 I slot launch_slot_: id 2 | task 5060 | processing task, is_child = 0 5.14.722.317 I slot print_timing: id 3 | task 4870 | prompt eval time = 427.18 ms / 145 tokens ( 2.95 ms per token, 339.44 tokens per second) 5.14.722.324 I slot print_timing: id 3 | task 4870 | eval time = 9598.77 ms / 204 tokens ( 47.28 ms per token, 21.15 tokens per second) 5.14.722.324 I slot print_timing: id 3 | task 4870 | total time = 10025.95 ms / 349 tokens 5.14.722.325 I slot print_timing: id 3 | task 4870 | graphs reused = 4111 5.14.722.326 I slot print_timing: id 3 | task 4870 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.722.382 I slot release: id 3 | task 4870 | stop processing: n_tokens = 1463, truncated = 0 5.14.761.839 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.762 5.14.761.863 I slot launch_slot_: id 3 | task 5081 | processing task, is_child = 0 5.16.295.972 I slot print_timing: id 0 | task 5039 | prompt eval time = 309.54 ms / 85 tokens ( 3.64 ms per token, 274.60 tokens per second) 5.16.295.980 I slot print_timing: id 0 | task 5039 | eval time = 3480.21 ms / 71 tokens ( 49.72 ms per token, 20.11 tokens per second) 5.16.295.982 I slot print_timing: id 0 | task 5039 | total time = 3789.76 ms / 156 tokens 5.16.295.983 I slot print_timing: id 0 | task 5039 | graphs reused = 4140 5.16.295.983 I slot print_timing: id 0 | task 5039 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.296.061 I slot release: id 0 | task 5039 | stop processing: n_tokens = 1270, truncated = 0 5.16.340.582 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.878 5.16.340.607 I slot launch_slot_: id 0 | task 5115 | processing task, is_child = 0 5.16.862.675 I slot print_timing: id 1 | task 5016 | n_gen = 100, tg = 19.10 t/s, tg_3s = 19.30 t/s 5.18.265.237 I slot print_timing: id 1 | task 5016 | prompt eval time = 426.46 ms / 123 tokens ( 3.47 ms per token, 288.42 tokens per second) 5.18.265.244 I slot print_timing: id 1 | task 5016 | eval time = 6585.06 ms / 134 tokens ( 49.51 ms per token, 20.20 tokens per second) 5.18.265.246 I slot print_timing: id 1 | task 5016 | total time = 7011.52 ms / 257 tokens 5.18.265.247 I slot print_timing: id 1 | task 5016 | graphs reused = 4178 5.18.265.248 I slot print_timing: id 1 | task 5016 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.265.317 I slot release: id 1 | task 5016 | stop processing: n_tokens = 1371, truncated = 0 5.18.326.641 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.813 5.18.326.666 I slot launch_slot_: id 1 | task 5157 | processing task, is_child = 0 5.18.893.233 I slot print_timing: id 2 | task 5060 | n_gen = 100, tg = 20.32 t/s, tg_3s = 20.53 t/s 5.19.720.268 I slot print_timing: id 3 | task 5081 | n_gen = 100, tg = 21.31 t/s, tg_3s = 21.52 t/s 5.20.623.042 I slot print_timing: id 3 | task 5081 | prompt eval time = 312.07 ms / 85 tokens ( 3.67 ms per token, 272.38 tokens per second) 5.20.623.045 I slot print_timing: id 3 | task 5081 | eval time = 5549.11 ms / 122 tokens ( 45.86 ms per token, 21.81 tokens per second) 5.20.623.046 I slot print_timing: id 3 | task 5081 | total time = 5861.17 ms / 207 tokens 5.20.623.046 I slot print_timing: id 3 | task 5081 | graphs reused = 4224 5.20.623.047 I slot print_timing: id 3 | task 5081 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.623.103 I slot release: id 3 | task 5081 | stop processing: n_tokens = 1321, truncated = 0 5.20.662.811 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.844 5.20.662.833 I slot launch_slot_: id 3 | task 5208 | processing task, is_child = 0 5.21.298.168 I slot print_timing: id 0 | task 5115 | n_gen = 100, tg = 21.56 t/s, tg_3s = 21.78 t/s 5.21.919.574 I slot print_timing: id 2 | task 5060 | n_gen = 168, tg = 21.14 t/s, tg_3s = 22.47 t/s 5.22.986.247 I slot print_timing: id 1 | task 5157 | n_gen = 100, tg = 23.08 t/s, tg_3s = 23.31 t/s 5.24.218.061 I slot print_timing: id 1 | task 5157 | prompt eval time = 369.26 ms / 96 tokens ( 3.85 ms per token, 259.98 tokens per second) 5.24.218.067 I slot print_timing: id 1 | task 5157 | eval time = 5522.13 ms / 130 tokens ( 42.81 ms per token, 23.36 tokens per second) 5.24.218.068 I slot print_timing: id 1 | task 5157 | total time = 5891.39 ms / 226 tokens 5.24.218.069 I slot print_timing: id 1 | task 5157 | graphs reused = 4302 5.24.218.069 I slot print_timing: id 1 | task 5157 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.218.135 I slot release: id 1 | task 5157 | stop processing: n_tokens = 1340, truncated = 0 5.24.279.443 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.832 5.24.279.471 I slot launch_slot_: id 1 | task 5291 | processing task, is_child = 0 5.24.544.191 I slot print_timing: id 0 | task 5115 | n_gen = 173, tg = 21.94 t/s, tg_3s = 22.49 t/s 5.24.546.342 I slot print_timing: id 3 | task 5208 | prompt eval time = 311.08 ms / 71 tokens ( 4.38 ms per token, 228.24 tokens per second) 5.24.546.344 I slot print_timing: id 3 | task 5208 | eval time = 3572.43 ms / 82 tokens ( 44.10 ms per token, 22.67 tokens per second) 5.24.546.347 I slot print_timing: id 3 | task 5208 | total time = 3883.51 ms / 153 tokens 5.24.546.347 I slot print_timing: id 3 | task 5208 | graphs reused = 4302 5.24.546.348 I slot print_timing: id 3 | task 5208 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.546.414 I slot release: id 3 | task 5208 | stop processing: n_tokens = 1267, truncated = 0 5.24.635.593 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.880 5.24.635.611 I slot launch_slot_: id 3 | task 5294 | processing task, is_child = 0 5.24.869.629 I slot print_timing: id 0 | task 5115 | prompt eval time = 365.19 ms / 111 tokens ( 3.29 ms per token, 303.95 tokens per second) 5.24.869.634 I slot print_timing: id 0 | task 5115 | eval time = 8163.83 ms / 175 tokens ( 46.92 ms per token, 21.31 tokens per second) 5.24.869.635 I slot print_timing: id 0 | task 5115 | total time = 8529.02 ms / 286 tokens 5.24.869.635 I slot print_timing: id 0 | task 5115 | graphs reused = 4302 5.24.869.635 I slot print_timing: id 0 | task 5115 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.869.681 I slot release: id 0 | task 5115 | stop processing: n_tokens = 1400, truncated = 0 5.24.941.598 I slot print_timing: id 2 | task 5060 | n_gen = 229, tg = 20.88 t/s, tg_3s = 20.19 t/s 5.24.942.681 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.796 5.24.942.698 I slot launch_slot_: id 0 | task 5297 | processing task, is_child = 0 5.25.821.508 I slot print_timing: id 2 | task 5060 | prompt eval time = 408.63 ms / 121 tokens ( 3.38 ms per token, 296.11 tokens per second) 5.25.821.513 I slot print_timing: id 2 | task 5060 | eval time = 11800.06 ms / 245 tokens ( 48.36 ms per token, 20.68 tokens per second) 5.25.821.513 I slot print_timing: id 2 | task 5060 | total time = 12208.69 ms / 366 tokens 5.25.821.514 I slot print_timing: id 2 | task 5060 | graphs reused = 4315 5.25.821.514 I slot print_timing: id 2 | task 5060 | graph reallocs = 0 / 0 (same size) / (changed size) 5.25.821.581 I slot release: id 2 | task 5060 | stop processing: n_tokens = 1479, truncated = 0 5.25.881.384 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.754 5.25.881.406 I slot launch_slot_: id 2 | task 5315 | processing task, is_child = 0 5.29.542.306 I slot print_timing: id 1 | task 5291 | n_gen = 100, tg = 20.17 t/s, tg_3s = 20.38 t/s 5.29.627.434 I slot print_timing: id 3 | task 5294 | prompt eval time = 307.06 ms / 76 tokens ( 4.04 ms per token, 247.50 tokens per second) 5.29.627.441 I slot print_timing: id 3 | task 5294 | eval time = 4684.75 ms / 100 tokens ( 47.32 ms per token, 21.13 tokens per second) 5.29.627.442 I slot print_timing: id 3 | task 5294 | total time = 4991.81 ms / 176 tokens 5.29.627.442 I slot print_timing: id 3 | task 5294 | graphs reused = 4393 5.29.627.443 I slot print_timing: id 3 | task 5294 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.627.509 I slot release: id 3 | task 5294 | stop processing: n_tokens = 1290, truncated = 0 5.29.667.448 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.864 5.29.667.478 I slot launch_slot_: id 3 | task 5399 | processing task, is_child = 0 5.29.904.427 I slot print_timing: id 0 | task 5297 | n_gen = 100, tg = 21.28 t/s, tg_3s = 21.50 t/s 5.30.305.484 I slot print_timing: id 1 | task 5291 | prompt eval time = 355.10 ms / 86 tokens ( 4.13 ms per token, 242.19 tokens per second) 5.30.305.488 I slot print_timing: id 1 | task 5291 | eval time = 5670.91 ms / 113 tokens ( 50.63 ms per token, 19.75 tokens per second) 5.30.305.489 I slot print_timing: id 1 | task 5291 | total time = 6026.00 ms / 199 tokens 5.30.305.490 I slot print_timing: id 1 | task 5291 | graphs reused = 4400 5.30.305.490 I slot print_timing: id 1 | task 5291 | graph reallocs = 0 / 0 (same size) / (changed size) 5.30.305.561 I slot release: id 1 | task 5291 | stop processing: n_tokens = 1313, truncated = 0 5.30.367.701 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.849 5.30.367.729 I slot launch_slot_: id 1 | task 5411 | processing task, is_child = 0 5.30.985.369 I slot print_timing: id 2 | task 5315 | n_gen = 100, tg = 21.32 t/s, tg_3s = 21.53 t/s 5.31.813.196 I slot print_timing: id 0 | task 5297 | prompt eval time = 310.14 ms / 83 tokens ( 3.74 ms per token, 267.62 tokens per second) 5.31.813.203 I slot print_timing: id 0 | task 5297 | eval time = 6560.35 ms / 137 tokens ( 48.24 ms per token, 20.73 tokens per second) 5.31.813.204 I slot print_timing: id 0 | task 5297 | total time = 6870.49 ms / 220 tokens 5.31.813.204 I slot print_timing: id 0 | task 5297 | graphs reused = 4424 5.31.813.205 I slot print_timing: id 0 | task 5297 | graph reallocs = 0 / 0 (same size) / (changed size) 5.31.813.284 I slot release: id 0 | task 5297 | stop processing: n_tokens = 1334, truncated = 0 5.31.857.763 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.836 5.31.857.784 I slot launch_slot_: id 0 | task 5440 | processing task, is_child = 0 5.32.484.602 I slot print_timing: id 2 | task 5315 | prompt eval time = 459.64 ms / 142 tokens ( 3.24 ms per token, 308.94 tokens per second) 5.32.484.610 I slot print_timing: id 2 | task 5315 | eval time = 6143.55 ms / 131 tokens ( 47.26 ms per token, 21.16 tokens per second) 5.32.484.611 I slot print_timing: id 2 | task 5315 | total time = 6603.19 ms / 273 tokens 5.32.484.611 I slot print_timing: id 2 | task 5315 | graphs reused = 4432 5.32.484.612 I slot print_timing: id 2 | task 5315 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.484.681 I slot release: id 2 | task 5315 | stop processing: n_tokens = 1387, truncated = 0 5.32.546.634 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.804 5.32.546.661 I slot launch_slot_: id 2 | task 5452 | processing task, is_child = 0 5.34.963.773 I slot print_timing: id 3 | task 5399 | n_gen = 100, tg = 19.87 t/s, tg_3s = 20.07 t/s 5.35.410.728 I slot print_timing: id 0 | task 5440 | prompt eval time = 306.81 ms / 71 tokens ( 4.32 ms per token, 231.42 tokens per second) 5.35.410.731 I slot print_timing: id 0 | task 5440 | eval time = 3246.13 ms / 72 tokens ( 45.72 ms per token, 21.87 tokens per second) 5.35.410.732 I slot print_timing: id 0 | task 5440 | total time = 3552.94 ms / 143 tokens 5.35.410.732 I slot print_timing: id 0 | task 5440 | graphs reused = 4490 5.35.410.733 I slot print_timing: id 0 | task 5440 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.410.794 I slot release: id 0 | task 5440 | stop processing: n_tokens = 1257, truncated = 0 5.35.412.373 I slot print_timing: id 1 | task 5411 | n_gen = 100, tg = 21.41 t/s, tg_3s = 21.63 t/s 5.35.454.994 I slot print_timing: id 3 | task 5399 | prompt eval time = 314.17 ms / 86 tokens ( 3.65 ms per token, 273.74 tokens per second) 5.35.455.001 I slot print_timing: id 3 | task 5399 | eval time = 5473.34 ms / 112 tokens ( 49.31 ms per token, 20.28 tokens per second) 5.35.455.002 I slot print_timing: id 3 | task 5399 | total time = 5787.51 ms / 198 tokens 5.35.455.003 I slot print_timing: id 3 | task 5399 | graphs reused = 4490 5.35.455.004 I slot print_timing: id 3 | task 5399 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.455.058 I slot release: id 3 | task 5399 | stop processing: n_tokens = 1312, truncated = 0 5.35.455.065 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.888 5.35.455.085 I slot launch_slot_: id 0 | task 5516 | processing task, is_child = 0 5.35.829.389 I slot print_timing: id 1 | task 5411 | prompt eval time = 421.00 ms / 103 tokens ( 4.09 ms per token, 244.65 tokens per second) 5.35.829.392 I slot print_timing: id 1 | task 5411 | eval time = 5040.64 ms / 104 tokens ( 48.94 ms per token, 20.43 tokens per second) 5.35.829.393 I slot print_timing: id 1 | task 5411 | total time = 5461.65 ms / 207 tokens 5.35.829.393 I slot print_timing: id 1 | task 5411 | graphs reused = 4490 5.35.829.393 I slot print_timing: id 1 | task 5411 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.829.447 I slot release: id 1 | task 5411 | stop processing: n_tokens = 1321, truncated = 0 5.37.286.497 I slot print_timing: id 2 | task 5452 | n_gen = 100, tg = 22.85 t/s, tg_3s = 23.09 t/s 5.38.945.893 I slot print_timing: id 0 | task 5516 | prompt eval time = 306.86 ms / 70 tokens ( 4.38 ms per token, 228.12 tokens per second) 5.38.945.898 I slot print_timing: id 0 | task 5516 | eval time = 3155.18 ms / 77 tokens ( 41.52 ms per token, 24.09 tokens per second) 5.38.945.903 I slot print_timing: id 0 | task 5516 | total time = 3462.03 ms / 147 tokens 5.38.945.903 I slot print_timing: id 0 | task 5516 | graphs reused = 4490 5.38.945.904 I slot print_timing: id 0 | task 5516 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.945.948 I slot release: id 0 | task 5516 | stop processing: n_tokens = 1262, truncated = 0 5.39.323.634 I slot print_timing: id 2 | task 5452 | prompt eval time = 408.13 ms / 118 tokens ( 3.46 ms per token, 289.12 tokens per second) 5.39.323.637 I slot print_timing: id 2 | task 5452 | eval time = 6368.84 ms / 158 tokens ( 40.57 ms per token, 24.65 tokens per second) 5.39.323.639 I slot print_timing: id 2 | task 5452 | total time = 6776.97 ms / 276 tokens 5.39.323.639 I slot print_timing: id 2 | task 5452 | graphs reused = 4507 5.39.323.640 I slot print_timing: id 2 | task 5452 | graph reallocs = 0 / 0 (same size) / (changed size) 5.39.323.689 I slot release: id 2 | task 5452 | stop processing: n_tokens = 1389, truncated = 0 5.39.341.283 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1312, t_last = 328990739162 5.39.342.097 I slot launch_slot_: id 3 | task 5613 | processing task, is_child = 0 5.39.414.539 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1321, t_last = 328991113551 5.39.415.289 I slot launch_slot_: id 1 | task 5614 | processing task, is_child = 0 5.39.415.461 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1262, t_last = 328994230052 5.39.416.105 I slot launch_slot_: id 0 | task 5615 | processing task, is_child = 0 5.39.416.192 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1389, t_last = 328994607793 5.39.416.904 I slot launch_slot_: id 2 | task 5616 | processing task, is_child = 0 5.45.077.756 I slot print_timing: id 0 | task 5615 | prompt processing, n_tokens = 842, progress = 0.88, t = 5.66 s / 148.74 tokens per second 5.45.130.492 I slot print_timing: id 1 | task 5614 | prompt processing, n_tokens = 616, progress = 0.79, t = 5.66 s / 108.82 tokens per second 5.45.134.094 I slot print_timing: id 2 | task 5616 | prompt processing, n_tokens = 865, progress = 0.89, t = 5.66 s / 152.81 tokens per second 5.45.135.751 I slot print_timing: id 3 | task 5613 | prompt processing, n_tokens = 642, progress = 0.84, t = 5.66 s / 113.42 tokens per second 5.46.167.137 I slot print_timing: id 0 | task 5615 | prompt processing, n_tokens = 955, progress = 1.00, t = 6.75 s / 141.48 tokens per second 5.46.219.608 I slot print_timing: id 1 | task 5614 | prompt processing, n_tokens = 774, progress = 0.99, t = 6.75 s / 114.66 tokens per second 5.46.222.398 I slot print_timing: id 2 | task 5616 | prompt processing, n_tokens = 972, progress = 1.00, t = 6.75 s / 144.00 tokens per second 5.46.224.389 I slot print_timing: id 3 | task 5613 | prompt processing, n_tokens = 762, progress = 0.99, t = 6.75 s / 112.89 tokens per second 5.46.327.189 I slot print_timing: id 0 | task 5615 | prompt eval time = 6870.64 ms / 959 tokens ( 7.16 ms per token, 139.58 tokens per second) 5.46.327.191 I slot print_timing: id 0 | task 5615 | eval time = 39.63 ms / 2 tokens ( 39.63 ms per token, 25.24 tokens per second) 5.46.327.192 I slot print_timing: id 0 | task 5615 | total time = 6910.27 ms / 961 tokens 5.46.327.192 I slot print_timing: id 0 | task 5615 | graphs reused = 4508 5.46.327.193 I slot print_timing: id 0 | task 5615 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.327.235 I slot release: id 0 | task 5615 | stop processing: n_tokens = 969, truncated = 0 5.46.328.342 I slot print_timing: id 1 | task 5614 | prompt eval time = 6871.69 ms / 778 tokens ( 8.83 ms per token, 113.22 tokens per second) 5.46.328.344 I slot print_timing: id 1 | task 5614 | eval time = 39.67 ms / 2 tokens ( 39.67 ms per token, 25.21 tokens per second) 5.46.328.344 I slot print_timing: id 1 | task 5614 | total time = 6911.35 ms / 780 tokens 5.46.328.345 I slot print_timing: id 1 | task 5614 | graphs reused = 4508 5.46.328.345 I slot print_timing: id 1 | task 5614 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.328.370 I slot release: id 1 | task 5614 | stop processing: n_tokens = 788, truncated = 0 5.46.329.462 I slot print_timing: id 2 | task 5616 | prompt eval time = 6872.71 ms / 976 tokens ( 7.04 ms per token, 142.01 tokens per second) 5.46.329.464 I slot print_timing: id 2 | task 5616 | eval time = 39.70 ms / 2 tokens ( 39.70 ms per token, 25.19 tokens per second) 5.46.329.464 I slot print_timing: id 2 | task 5616 | total time = 6912.41 ms / 978 tokens 5.46.329.464 I slot print_timing: id 2 | task 5616 | graphs reused = 4508 5.46.329.465 I slot print_timing: id 2 | task 5616 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.329.492 I slot release: id 2 | task 5616 | stop processing: n_tokens = 986, truncated = 0 5.46.330.579 I slot print_timing: id 3 | task 5613 | prompt eval time = 6873.75 ms / 766 tokens ( 8.97 ms per token, 111.44 tokens per second) 5.46.330.581 I slot print_timing: id 3 | task 5613 | eval time = 39.71 ms / 2 tokens ( 39.71 ms per token, 25.18 tokens per second) 5.46.330.581 I slot print_timing: id 3 | task 5613 | total time = 6913.46 ms / 768 tokens 5.46.330.582 I slot print_timing: id 3 | task 5613 | graphs reused = 4508 5.46.330.582 I slot print_timing: id 3 | task 5613 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.330.603 I slot release: id 3 | task 5613 | stop processing: n_tokens = 776, truncated = 0 5.46.334.992 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 969, t_last = 329001611339 5.46.346.620 I slot launch_slot_: id 0 | task 5622 | processing task, is_child = 0 5.46.382.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.075 MiB) 5.46.399.628 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 788, t_last = 329001612474 5.46.399.781 I slot launch_slot_: id 1 | task 5623 | processing task, is_child = 0 5.46.399.920 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 329001613596 5.46.400.026 I slot launch_slot_: id 2 | task 5624 | processing task, is_child = 0 5.46.400.092 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 776, t_last = 329001614707 5.46.400.187 I slot launch_slot_: id 3 | task 5625 | processing task, is_child = 0 5.51.505.062 I slot print_timing: id 0 | task 5622 | prompt processing, n_tokens = 690, progress = 0.87, t = 5.10 s / 135.17 tokens per second 5.51.534.357 I slot print_timing: id 1 | task 5623 | prompt processing, n_tokens = 690, progress = 0.87, t = 5.10 s / 135.17 tokens per second 5.51.537.994 I slot print_timing: id 2 | task 5624 | prompt processing, n_tokens = 690, progress = 0.82, t = 5.10 s / 135.18 tokens per second 5.51.540.093 I slot print_timing: id 3 | task 5625 | prompt processing, n_tokens = 690, progress = 0.81, t = 5.10 s / 135.18 tokens per second 5.52.545.669 I slot print_timing: id 0 | task 5622 | prompt processing, n_tokens = 792, progress = 1.00, t = 6.15 s / 128.88 tokens per second 5.52.579.030 I slot print_timing: id 1 | task 5623 | prompt processing, n_tokens = 794, progress = 1.00, t = 6.15 s / 129.21 tokens per second 5.52.582.561 I slot print_timing: id 2 | task 5624 | prompt processing, n_tokens = 837, progress = 1.00, t = 6.15 s / 136.21 tokens per second 5.52.584.321 I slot print_timing: id 3 | task 5625 | prompt processing, n_tokens = 845, progress = 1.00, t = 6.14 s / 137.51 tokens per second 5.52.687.113 I slot print_timing: id 0 | task 5622 | prompt eval time = 6247.16 ms / 796 tokens ( 7.85 ms per token, 127.42 tokens per second) 5.52.687.116 I slot print_timing: id 0 | task 5622 | eval time = 39.76 ms / 2 tokens ( 39.76 ms per token, 25.15 tokens per second) 5.52.687.117 I slot print_timing: id 0 | task 5622 | total time = 6286.91 ms / 798 tokens 5.52.687.118 I slot print_timing: id 0 | task 5622 | graphs reused = 4508 5.52.687.118 I slot print_timing: id 0 | task 5622 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.687.168 I slot release: id 0 | task 5622 | stop processing: n_tokens = 806, truncated = 0 5.52.688.308 I slot print_timing: id 1 | task 5623 | prompt eval time = 6248.05 ms / 798 tokens ( 7.83 ms per token, 127.72 tokens per second) 5.52.688.310 I slot print_timing: id 1 | task 5623 | eval time = 39.84 ms / 2 tokens ( 39.84 ms per token, 25.10 tokens per second) 5.52.688.310 I slot print_timing: id 1 | task 5623 | total time = 6287.89 ms / 800 tokens 5.52.688.310 I slot print_timing: id 1 | task 5623 | graphs reused = 4508 5.52.688.311 I slot print_timing: id 1 | task 5623 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.688.333 I slot release: id 1 | task 5623 | stop processing: n_tokens = 808, truncated = 0 5.52.689.454 I slot print_timing: id 2 | task 5624 | prompt eval time = 6248.97 ms / 841 tokens ( 7.43 ms per token, 134.58 tokens per second) 5.52.689.458 I slot print_timing: id 2 | task 5624 | eval time = 39.89 ms / 2 tokens ( 39.89 ms per token, 25.07 tokens per second) 5.52.689.459 I slot print_timing: id 2 | task 5624 | total time = 6288.86 ms / 843 tokens 5.52.689.459 I slot print_timing: id 2 | task 5624 | graphs reused = 4508 5.52.689.459 I slot print_timing: id 2 | task 5624 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.689.482 I slot release: id 2 | task 5624 | stop processing: n_tokens = 851, truncated = 0 5.52.690.629 I slot print_timing: id 3 | task 5625 | prompt eval time = 6250.06 ms / 849 tokens ( 7.36 ms per token, 135.84 tokens per second) 5.52.690.631 I slot print_timing: id 3 | task 5625 | eval time = 39.81 ms / 2 tokens ( 39.81 ms per token, 25.12 tokens per second) 5.52.690.631 I slot print_timing: id 3 | task 5625 | total time = 6289.87 ms / 851 tokens 5.52.690.631 I slot print_timing: id 3 | task 5625 | graphs reused = 4508 5.52.690.632 I slot print_timing: id 3 | task 5625 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.690.651 I slot release: id 3 | task 5625 | stop processing: n_tokens = 859, truncated = 0 5.52.695.278 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 5.52.695.321 I slot launch_slot_: id 0 | task 5631 | processing task, is_child = 0 5.52.695.436 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.306 MiB) 5.52.695.439 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.151 MiB) 5.52.695.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.106 MiB) 5.52.695.444 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 49.228 MiB) 5.52.695.446 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.629 MiB) 5.52.713.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.614 MiB) 5.52.713.294 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.490 MiB) 5.52.713.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.524 MiB) 5.52.713.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 5.52.713.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.368 MiB) 5.52.739.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 51.690 MiB) 5.52.739.827 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.922 MiB) 5.52.739.830 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.490 MiB) 5.52.739.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.290 MiB) 5.52.739.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.029 MiB) 5.52.762.195 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 808, t_last = 329007972437 5.52.762.384 I slot launch_slot_: id 1 | task 5632 | processing task, is_child = 0 5.52.762.517 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 851, t_last = 329007973586 5.52.762.632 I slot launch_slot_: id 2 | task 5633 | processing task, is_child = 0 5.52.762.701 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 859, t_last = 329007974755 5.52.762.804 I slot launch_slot_: id 3 | task 5634 | processing task, is_child = 0 5.57.427.814 I slot print_timing: id 1 | task 5632 | prompt processing, n_tokens = 739, progress = 0.85, t = 4.66 s / 158.52 tokens per second 5.57.431.331 I slot print_timing: id 2 | task 5633 | prompt processing, n_tokens = 739, progress = 0.84, t = 4.66 s / 158.52 tokens per second 5.57.433.007 I slot print_timing: id 3 | task 5634 | prompt processing, n_tokens = 817, progress = 0.86, t = 4.66 s / 175.26 tokens per second 5.58.247.232 I slot print_timing: id 0 | task 5631 | prompt eval time = 4664.95 ms / 105 tokens ( 44.43 ms per token, 22.51 tokens per second) 5.58.247.239 I slot print_timing: id 0 | task 5631 | eval time = 819.46 ms / 2 tokens ( 819.46 ms per token, 1.22 tokens per second) 5.58.247.239 I slot print_timing: id 0 | task 5631 | total time = 5484.41 ms / 107 tokens 5.58.247.240 I slot print_timing: id 0 | task 5631 | graphs reused = 4508 5.58.247.240 I slot print_timing: id 0 | task 5631 | graph reallocs = 0 / 0 (same size) / (changed size) 5.58.247.309 I slot release: id 0 | task 5631 | stop processing: n_tokens = 832, truncated = 0 5.58.247.337 I slot print_timing: id 1 | task 5632 | prompt processing, n_tokens = 864, progress = 1.00, t = 5.48 s / 157.62 tokens per second 5.58.251.217 I slot print_timing: id 2 | task 5633 | prompt processing, n_tokens = 874, progress = 1.00, t = 5.48 s / 159.45 tokens per second 5.58.252.998 I slot print_timing: id 3 | task 5634 | prompt processing, n_tokens = 945, progress = 1.00, t = 5.48 s / 172.41 tokens per second 5.58.321.174 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 329013531413 5.58.321.258 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 5.58.321.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.798 MiB) 5.58.321.264 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 5.58.321.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.044 MiB) 5.58.321.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.783 MiB) 5.58.321.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.321 MiB) 5.58.321.277 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.368 MiB) 5.58.349.726 I slot launch_slot_: id 0 | task 5639 | processing task, is_child = 0 5.59.232.819 I slot print_timing: id 1 | task 5632 | prompt eval time = 5554.34 ms / 868 tokens ( 6.40 ms per token, 156.27 tokens per second) 5.59.232.822 I slot print_timing: id 1 | task 5632 | eval time = 913.85 ms / 2 tokens ( 913.85 ms per token, 1.09 tokens per second) 5.59.232.823 I slot print_timing: id 1 | task 5632 | total time = 6468.19 ms / 870 tokens 5.59.232.823 I slot print_timing: id 1 | task 5632 | graphs reused = 4508 5.59.232.824 I slot print_timing: id 1 | task 5632 | graph reallocs = 0 / 0 (same size) / (changed size) 5.59.232.869 I slot release: id 1 | task 5632 | stop processing: n_tokens = 878, truncated = 0 5.59.234.131 I slot print_timing: id 2 | task 5633 | prompt eval time = 5555.26 ms / 878 tokens ( 6.33 ms per token, 158.05 tokens per second) 5.59.234.134 I slot print_timing: id 2 | task 5633 | eval time = 914.04 ms / 2 tokens ( 914.04 ms per token, 1.09 tokens per second) 5.59.234.134 I slot print_timing: id 2 | task 5633 | total time = 6469.30 ms / 880 tokens 5.59.234.135 I slot print_timing: id 2 | task 5633 | graphs reused = 4508 5.59.234.135 I slot print_timing: id 2 | task 5633 | graph reallocs = 0 / 0 (same size) / (changed size) 5.59.234.175 I slot release: id 2 | task 5633 | stop processing: n_tokens = 888, truncated = 0 5.59.235.381 I slot print_timing: id 3 | task 5634 | prompt eval time = 5556.18 ms / 949 tokens ( 5.85 ms per token, 170.80 tokens per second) 5.59.235.383 I slot print_timing: id 3 | task 5634 | eval time = 914.21 ms / 2 tokens ( 914.21 ms per token, 1.09 tokens per second) 5.59.235.384 I slot print_timing: id 3 | task 5634 | total time = 6470.39 ms / 951 tokens 5.59.235.384 I slot print_timing: id 3 | task 5634 | graphs reused = 4508 5.59.235.384 I slot print_timing: id 3 | task 5634 | graph reallocs = 0 / 0 (same size) / (changed size) 5.59.235.429 I slot release: id 3 | task 5634 | stop processing: n_tokens = 959, truncated = 0 6.00.008.042 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 878, t_last = 329014516974 6.00.008.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 6.00.008.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.414 MiB) 6.00.008.336 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.215 MiB) 6.00.008.511 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.013 MiB) 6.00.008.722 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.735 MiB) 6.00.264.755 I slot launch_slot_: id 1 | task 5643 | processing task, is_child = 0 6.00.264.834 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.736 MiB) 6.00.264.837 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.829 MiB) 6.00.265.163 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.629 MiB) 6.00.265.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.130 MiB) 6.00.265.535 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.304 MiB) 6.00.284.248 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.951 MiB) 6.00.284.507 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 6.00.284.818 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.013 MiB) 6.00.285.031 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.399 MiB) 6.00.285.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.361 MiB) 6.00.285.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.507 MiB) 6.00.303.468 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 888, t_last = 329014518279 6.00.303.621 I slot launch_slot_: id 2 | task 5644 | processing task, is_child = 0 6.00.303.703 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 959, t_last = 329014519533 6.00.303.814 I slot launch_slot_: id 3 | task 5645 | processing task, is_child = 0 6.03.426.277 I slot print_timing: id 1 | task 5643 | prompt processing, n_tokens = 507, progress = 0.50, t = 3.12 s / 162.73 tokens per second 6.03.429.993 I slot print_timing: id 2 | task 5644 | prompt processing, n_tokens = 402, progress = 0.44, t = 3.12 s / 129.05 tokens per second 6.03.432.223 I slot print_timing: id 3 | task 5645 | prompt processing, n_tokens = 747, progress = 0.42, t = 3.11 s / 239.84 tokens per second 6.05.929.091 I slot print_timing: id 0 | task 5639 | prompt eval time = 5076.51 ms / 988 tokens ( 5.14 ms per token, 194.62 tokens per second) 6.05.929.093 I slot print_timing: id 0 | task 5639 | eval time = 2502.84 ms / 2 tokens ( 2502.84 ms per token, 0.40 tokens per second) 6.05.929.094 I slot print_timing: id 0 | task 5639 | total time = 7579.35 ms / 990 tokens 6.05.929.094 I slot print_timing: id 0 | task 5639 | graphs reused = 4508 6.05.929.095 I slot print_timing: id 0 | task 5639 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.929.147 I slot release: id 0 | task 5639 | stop processing: n_tokens = 998, truncated = 0 6.05.929.182 I slot print_timing: id 1 | task 5643 | prompt processing, n_tokens = 871, progress = 0.85, t = 5.62 s / 155.02 tokens per second 6.05.932.754 I slot print_timing: id 2 | task 5644 | prompt processing, n_tokens = 747, progress = 0.82, t = 5.62 s / 132.97 tokens per second 6.05.934.480 I slot print_timing: id 3 | task 5645 | prompt processing, n_tokens = 1294, progress = 0.72, t = 5.62 s / 230.35 tokens per second 6.06.932.944 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 998, t_last = 329021213252 6.06.933.035 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.814 MiB) 6.06.933.039 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.660 MiB) 6.06.933.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.907 MiB) 6.06.933.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.982 MiB) 6.06.933.328 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.570 MiB) 6.06.933.628 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 48.982 MiB) 6.07.605.343 I slot launch_slot_: id 0 | task 5649 | processing task, is_child = 0 6.07.605.585 I slot print_timing: id 1 | task 5643 | prompt processing, n_tokens = 1019, progress = 1.00, t = 6.62 s / 153.85 tokens per second 6.07.607.399 I slot print_timing: id 2 | task 5644 | prompt processing, n_tokens = 914, progress = 1.00, t = 6.62 s / 138.01 tokens per second 6.07.609.182 I slot print_timing: id 3 | task 5645 | prompt processing, n_tokens = 1806, progress = 1.00, t = 6.62 s / 272.71 tokens per second 6.09.099.153 I slot print_timing: id 1 | task 5643 | prompt eval time = 8099.06 ms / 1023 tokens ( 7.92 ms per token, 126.31 tokens per second) 6.09.099.159 I slot print_timing: id 1 | task 5643 | eval time = 690.55 ms / 2 tokens ( 690.55 ms per token, 1.45 tokens per second) 6.09.099.160 I slot print_timing: id 1 | task 5643 | total time = 8789.61 ms / 1025 tokens 6.09.099.160 I slot print_timing: id 1 | task 5643 | graphs reused = 4508 6.09.099.161 I slot print_timing: id 1 | task 5643 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.099.213 I slot release: id 1 | task 5643 | stop processing: n_tokens = 1033, truncated = 0 6.09.100.355 I slot print_timing: id 2 | task 5644 | prompt eval time = 8099.74 ms / 918 tokens ( 8.82 ms per token, 113.34 tokens per second) 6.09.100.358 I slot print_timing: id 2 | task 5644 | eval time = 690.48 ms / 2 tokens ( 690.48 ms per token, 1.45 tokens per second) 6.09.100.360 I slot print_timing: id 2 | task 5644 | total time = 8790.23 ms / 920 tokens 6.09.100.360 I slot print_timing: id 2 | task 5644 | graphs reused = 4508 6.09.100.361 I slot print_timing: id 2 | task 5644 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.100.410 I slot release: id 2 | task 5644 | stop processing: n_tokens = 928, truncated = 0 6.09.101.538 I slot print_timing: id 3 | task 5645 | prompt eval time = 8100.44 ms / 1810 tokens ( 4.48 ms per token, 223.44 tokens per second) 6.09.101.541 I slot print_timing: id 3 | task 5645 | eval time = 690.51 ms / 2 tokens ( 690.51 ms per token, 1.45 tokens per second) 6.09.101.542 I slot print_timing: id 3 | task 5645 | total time = 8790.95 ms / 1812 tokens 6.09.101.542 I slot print_timing: id 3 | task 5645 | graphs reused = 4508 6.09.101.542 I slot print_timing: id 3 | task 5645 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.101.630 I slot release: id 3 | task 5645 | stop processing: n_tokens = 1820, truncated = 0 6.09.109.817 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1033, t_last = 329024383317 6.09.109.911 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 6.09.109.917 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 47.752 MiB) 6.09.110.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 6.09.110.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 6.09.110.558 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 6.09.110.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.430 MiB) 6.09.488.148 I slot launch_slot_: id 1 | task 5653 | processing task, is_child = 0 6.09.488.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 6.09.488.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.784 MiB) 6.09.488.949 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.321 MiB) 6.09.489.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.521 MiB) 6.09.489.512 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.137 MiB) 6.09.489.766 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.568 MiB) 6.09.506.796 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.753 MiB) 6.09.507.025 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.507 MiB) 6.09.507.280 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 6.09.507.606 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.507 MiB) 6.09.507.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.091 MiB) 6.09.508.110 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.999 MiB) 6.09.508.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 33.722 MiB) 6.09.508.687 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.783 MiB) 6.09.528.949 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 329024384514 6.09.529.111 I slot launch_slot_: id 2 | task 5654 | processing task, is_child = 0 6.09.529.207 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1820, t_last = 329024385734 6.09.529.339 I slot launch_slot_: id 3 | task 5655 | processing task, is_child = 0 6.13.316.246 I slot print_timing: id 0 | task 5649 | prompt eval time = 3395.15 ms / 934 tokens ( 3.64 ms per token, 275.10 tokens per second) 6.13.316.252 I slot print_timing: id 0 | task 5649 | eval time = 2315.74 ms / 2 tokens ( 2315.74 ms per token, 0.43 tokens per second) 6.13.316.252 I slot print_timing: id 0 | task 5649 | total time = 5710.89 ms / 936 tokens 6.13.316.253 I slot print_timing: id 0 | task 5649 | graphs reused = 4509 6.13.316.253 I slot print_timing: id 0 | task 5649 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.316.307 I slot release: id 0 | task 5649 | stop processing: n_tokens = 944, truncated = 0 6.13.316.341 I slot print_timing: id 1 | task 5653 | prompt processing, n_tokens = 590, progress = 0.84, t = 3.78 s / 156.02 tokens per second 6.13.320.101 I slot print_timing: id 2 | task 5654 | prompt processing, n_tokens = 590, progress = 0.81, t = 3.78 s / 156.05 tokens per second 6.13.322.210 I slot print_timing: id 3 | task 5655 | prompt processing, n_tokens = 759, progress = 0.87, t = 3.78 s / 200.78 tokens per second 6.13.960.048 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 944, t_last = 329028600411 6.13.960.139 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 6.13.960.143 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.075 MiB) 6.13.960.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.015 MiB) 6.13.960.147 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 36.184 MiB) 6.13.960.449 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.213 MiB) 6.13.960.722 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.091 MiB) 6.14.047.923 I slot launch_slot_: id 0 | task 5659 | processing task, is_child = 0 6.14.048.152 I slot print_timing: id 1 | task 5653 | prompt processing, n_tokens = 696, progress = 0.99, t = 4.43 s / 157.24 tokens per second 6.14.049.888 I slot print_timing: id 2 | task 5654 | prompt processing, n_tokens = 724, progress = 0.99, t = 4.43 s / 163.59 tokens per second 6.14.051.617 I slot print_timing: id 3 | task 5655 | prompt processing, n_tokens = 868, progress = 1.00, t = 4.43 s / 196.15 tokens per second 6.15.257.272 I slot print_timing: id 1 | task 5653 | prompt eval time = 4933.88 ms / 700 tokens ( 7.05 ms per token, 141.88 tokens per second) 6.15.257.275 I slot print_timing: id 1 | task 5653 | eval time = 789.75 ms / 2 tokens ( 789.75 ms per token, 1.27 tokens per second) 6.15.257.276 I slot print_timing: id 1 | task 5653 | total time = 5723.62 ms / 702 tokens 6.15.257.277 I slot print_timing: id 1 | task 5653 | graphs reused = 4509 6.15.257.277 I slot print_timing: id 1 | task 5653 | graph reallocs = 0 / 0 (same size) / (changed size) 6.15.257.316 I slot release: id 1 | task 5653 | stop processing: n_tokens = 710, truncated = 0 6.15.258.463 I slot print_timing: id 2 | task 5654 | prompt eval time = 4934.34 ms / 728 tokens ( 6.78 ms per token, 147.54 tokens per second) 6.15.258.467 I slot print_timing: id 2 | task 5654 | eval time = 789.80 ms / 2 tokens ( 789.80 ms per token, 1.27 tokens per second) 6.15.258.467 I slot print_timing: id 2 | task 5654 | total time = 5724.15 ms / 730 tokens 6.15.258.468 I slot print_timing: id 2 | task 5654 | graphs reused = 4509 6.15.258.468 I slot print_timing: id 2 | task 5654 | graph reallocs = 0 / 0 (same size) / (changed size) 6.15.258.502 I slot release: id 2 | task 5654 | stop processing: n_tokens = 738, truncated = 0 6.15.259.652 I slot print_timing: id 3 | task 5655 | prompt eval time = 4934.96 ms / 872 tokens ( 5.66 ms per token, 176.70 tokens per second) 6.15.259.658 I slot print_timing: id 3 | task 5655 | eval time = 789.85 ms / 2 tokens ( 789.85 ms per token, 1.27 tokens per second) 6.15.259.659 I slot print_timing: id 3 | task 5655 | total time = 5724.81 ms / 874 tokens 6.15.259.659 I slot print_timing: id 3 | task 5655 | graphs reused = 4509 6.15.259.659 I slot print_timing: id 3 | task 5655 | graph reallocs = 0 / 0 (same size) / (changed size) 6.15.259.702 I slot release: id 3 | task 5655 | stop processing: n_tokens = 882, truncated = 0 6.15.550.830 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 329030541420 6.15.550.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.738 MiB) 6.15.550.916 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 40.368 MiB) 6.15.550.918 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.660 MiB) 6.15.551.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.216 MiB) 6.15.551.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 6.15.551.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.414 MiB) 6.15.566.572 I slot launch_slot_: id 1 | task 5664 | processing task, is_child = 0 6.15.566.642 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 6.15.566.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.075 MiB) 6.15.567.005 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.306 MiB) 6.15.567.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.352 MiB) 6.15.567.551 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 41.845 MiB) 6.15.581.755 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 42.829 MiB) 6.15.581.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 32.738 MiB) 6.15.582.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.213 MiB) 6.15.582.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.292 MiB) 6.15.582.535 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.707 MiB) 6.15.582.751 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 31.753 MiB) 6.15.597.780 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.848 6.15.597.854 I slot launch_slot_: id 2 | task 5665 | processing task, is_child = 0 6.15.597.932 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 329030543806 6.15.600.521 I slot launch_slot_: id 3 | task 5666 | processing task, is_child = 0 6.16.520.371 I slot print_timing: id 0 | task 5659 | prompt eval time = 1502.89 ms / 703 tokens ( 2.14 ms per token, 467.76 tokens per second) 6.16.520.377 I slot print_timing: id 0 | task 5659 | eval time = 969.53 ms / 2 tokens ( 969.53 ms per token, 1.03 tokens per second) 6.16.520.377 I slot print_timing: id 0 | task 5659 | total time = 2472.42 ms / 705 tokens 6.16.520.378 I slot print_timing: id 0 | task 5659 | graphs reused = 4509 6.16.520.379 I slot print_timing: id 0 | task 5659 | graph reallocs = 0 / 0 (same size) / (changed size) 6.16.520.441 I slot release: id 0 | task 5659 | stop processing: n_tokens = 713, truncated = 0 6.17.593.801 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 713, t_last = 329031804545 6.17.605.015 I slot launch_slot_: id 0 | task 5669 | processing task, is_child = 0 6.18.777.579 I slot print_timing: id 2 | task 5665 | prompt eval time = 1992.76 ms / 89 tokens ( 22.39 ms per token, 44.66 tokens per second) 6.18.777.582 I slot print_timing: id 2 | task 5665 | eval time = 1183.79 ms / 2 tokens ( 1183.79 ms per token, 0.84 tokens per second) 6.18.777.582 I slot print_timing: id 2 | task 5665 | total time = 3176.55 ms / 91 tokens 6.18.777.583 I slot print_timing: id 2 | task 5665 | graphs reused = 4509 6.18.777.583 I slot print_timing: id 2 | task 5665 | graph reallocs = 0 / 0 (same size) / (changed size) 6.18.777.625 I slot release: id 2 | task 5665 | stop processing: n_tokens = 716, truncated = 0 6.18.781.077 I slot print_timing: id 1 | task 5664 | prompt processing, n_tokens = 860, progress = 1.00, t = 3.18 s / 270.79 tokens per second 6.19.550.621 I slot print_timing: id 3 | task 5666 | prompt eval time = 3176.12 ms / 123 tokens ( 25.82 ms per token, 38.73 tokens per second) 6.19.550.627 I slot print_timing: id 3 | task 5666 | eval time = 771.73 ms / 2 tokens ( 771.73 ms per token, 1.30 tokens per second) 6.19.550.627 I slot print_timing: id 3 | task 5666 | total time = 3947.84 ms / 125 tokens 6.19.550.628 I slot print_timing: id 3 | task 5666 | graphs reused = 4509 6.19.550.628 I slot print_timing: id 3 | task 5666 | graph reallocs = 0 / 0 (same size) / (changed size) 6.19.550.693 I slot release: id 3 | task 5666 | stop processing: n_tokens = 722, truncated = 0 6.19.550.711 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 329034061729 6.19.550.839 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.798 MiB) 6.19.550.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 35.340 MiB) 6.19.550.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.629 MiB) 6.19.550.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.153 MiB) 6.19.551.134 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.461 MiB) 6.19.551.491 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.568 MiB) 6.19.551.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 38.891 MiB) 6.19.572.107 I slot launch_slot_: id 2 | task 5672 | processing task, is_child = 0 6.19.572.179 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.521 MiB) 6.19.572.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 33.969 MiB) 6.19.572.483 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.705 MiB) 6.19.572.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 43.814 MiB) 6.19.572.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.784 MiB) 6.19.573.205 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 37.414 MiB) 6.19.573.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.953 MiB) 6.19.590.942 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 722, t_last = 329034834797 6.19.591.062 I slot launch_slot_: id 3 | task 5673 | processing task, is_child = 0 6.21.667.837 I slot print_timing: id 1 | task 5664 | prompt eval time = 3948.95 ms / 864 tokens ( 4.57 ms per token, 218.79 tokens per second) 6.21.667.844 I slot print_timing: id 1 | task 5664 | eval time = 2118.34 ms / 2 tokens ( 2118.34 ms per token, 0.47 tokens per second) 6.21.667.844 I slot print_timing: id 1 | task 5664 | total time = 6067.29 ms / 866 tokens 6.21.667.845 I slot print_timing: id 1 | task 5664 | graphs reused = 4509 6.21.667.846 I slot print_timing: id 1 | task 5664 | graph reallocs = 0 / 0 (same size) / (changed size) 6.21.667.918 I slot release: id 1 | task 5664 | stop processing: n_tokens = 874, truncated = 0 6.21.667.950 I slot print_timing: id 0 | task 5669 | prompt processing, n_tokens = 977, progress = 1.00, t = 4.06 s / 240.54 tokens per second 6.23.098.155 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 874, t_last = 329036952022 6.23.098.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 39.876 MiB) 6.23.098.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.238 MiB) 6.23.105.436 I slot launch_slot_: id 1 | task 5676 | processing task, is_child = 0 6.23.105.646 I slot print_timing: id 2 | task 5672 | prompt processing, n_tokens = 850, progress = 0.83, t = 3.50 s / 242.74 tokens per second 6.23.107.339 I slot print_timing: id 3 | task 5673 | prompt processing, n_tokens = 850, progress = 0.86, t = 3.50 s / 242.78 tokens per second 6.24.686.302 I slot print_timing: id 0 | task 5669 | prompt eval time = 5493.11 ms / 981 tokens ( 5.60 ms per token, 178.59 tokens per second) 6.24.686.305 I slot print_timing: id 0 | task 5669 | eval time = 1588.16 ms / 2 tokens ( 1588.16 ms per token, 0.63 tokens per second) 6.24.686.305 I slot print_timing: id 0 | task 5669 | total time = 7081.27 ms / 983 tokens 6.24.686.306 I slot print_timing: id 0 | task 5669 | graphs reused = 4509 6.24.686.306 I slot print_timing: id 0 | task 5669 | graph reallocs = 0 / 0 (same size) / (changed size) 6.24.686.371 I slot release: id 0 | task 5669 | stop processing: n_tokens = 991, truncated = 0 6.24.690.097 I slot print_timing: id 2 | task 5672 | prompt processing, n_tokens = 1021, progress = 1.00, t = 5.09 s / 200.59 tokens per second 6.24.691.939 I slot print_timing: id 3 | task 5673 | prompt processing, n_tokens = 991, progress = 1.00, t = 5.09 s / 194.72 tokens per second 6.25.462.879 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 6.25.463.027 I slot launch_slot_: id 0 | task 5679 | processing task, is_child = 0 6.26.020.245 I slot print_timing: id 2 | task 5672 | prompt eval time = 5866.39 ms / 1025 tokens ( 5.72 ms per token, 174.72 tokens per second) 6.26.020.247 I slot print_timing: id 2 | task 5672 | eval time = 558.55 ms / 2 tokens ( 558.55 ms per token, 1.79 tokens per second) 6.26.020.247 I slot print_timing: id 2 | task 5672 | total time = 6424.94 ms / 1027 tokens 6.26.020.248 I slot print_timing: id 2 | task 5672 | graphs reused = 4509 6.26.020.248 I slot print_timing: id 2 | task 5672 | graph reallocs = 0 / 0 (same size) / (changed size) 6.26.020.310 I slot release: id 2 | task 5672 | stop processing: n_tokens = 1035, truncated = 0 6.26.021.471 I slot print_timing: id 3 | task 5673 | prompt eval time = 5867.02 ms / 995 tokens ( 5.90 ms per token, 169.59 tokens per second) 6.26.021.473 I slot print_timing: id 3 | task 5673 | eval time = 558.60 ms / 2 tokens ( 558.60 ms per token, 1.79 tokens per second) 6.26.021.474 I slot print_timing: id 3 | task 5673 | total time = 6425.62 ms / 997 tokens 6.26.021.474 I slot print_timing: id 3 | task 5673 | graphs reused = 4509 6.26.021.475 I slot print_timing: id 3 | task 5673 | graph reallocs = 0 / 0 (same size) / (changed size) 6.26.021.515 I slot release: id 3 | task 5673 | stop processing: n_tokens = 1005, truncated = 0 6.26.068.399 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 329041304414 6.26.068.494 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.174 MiB) 6.26.074.791 I slot launch_slot_: id 2 | task 5682 | processing task, is_child = 0 6.26.074.869 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.983 MiB) 6.26.081.000 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1005, t_last = 329041305619 6.26.081.123 I slot launch_slot_: id 3 | task 5683 | processing task, is_child = 0 6.27.715.871 I slot print_timing: id 0 | task 5679 | prompt eval time = 604.27 ms / 105 tokens ( 5.75 ms per token, 173.76 tokens per second) 6.27.715.876 I slot print_timing: id 0 | task 5679 | eval time = 1648.55 ms / 2 tokens ( 1648.55 ms per token, 0.61 tokens per second) 6.27.715.877 I slot print_timing: id 0 | task 5679 | total time = 2252.82 ms / 107 tokens 6.27.715.877 I slot print_timing: id 0 | task 5679 | graphs reused = 4509 6.27.715.878 I slot print_timing: id 0 | task 5679 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.715.952 I slot release: id 0 | task 5679 | stop processing: n_tokens = 992, truncated = 0 6.27.717.111 I slot print_timing: id 1 | task 5676 | prompt eval time = 2962.95 ms / 987 tokens ( 3.00 ms per token, 333.11 tokens per second) 6.27.717.114 I slot print_timing: id 1 | task 5676 | eval time = 1648.71 ms / 2 tokens ( 1648.71 ms per token, 0.61 tokens per second) 6.27.717.114 I slot print_timing: id 1 | task 5676 | total time = 4611.66 ms / 989 tokens 6.27.717.114 I slot print_timing: id 1 | task 5676 | graphs reused = 4509 6.27.717.115 I slot print_timing: id 1 | task 5676 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.717.156 I slot release: id 1 | task 5676 | stop processing: n_tokens = 997, truncated = 0 6.28.744.433 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 992, t_last = 329043000056 6.28.744.535 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.319 MiB) 6.28.943.259 I slot launch_slot_: id 0 | task 5686 | processing task, is_child = 0 6.28.953.624 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 997, t_last = 329043001260 6.28.953.748 I slot launch_slot_: id 1 | task 5687 | processing task, is_child = 0 6.31.361.737 I slot print_timing: id 2 | task 5682 | prompt processing, n_tokens = 871, progress = 1.00, t = 5.08 s / 171.53 tokens per second 6.31.363.523 I slot print_timing: id 3 | task 5683 | prompt processing, n_tokens = 1010, progress = 1.00, t = 5.08 s / 198.91 tokens per second 6.32.743.963 I slot print_timing: id 0 | task 5686 | prompt processing, n_tokens = 768, progress = 0.86, t = 3.79 s / 202.76 tokens per second 6.32.747.379 I slot print_timing: id 1 | task 5687 | prompt processing, n_tokens = 768, progress = 0.77, t = 3.79 s / 202.77 tokens per second 6.33.524.090 I slot print_timing: id 2 | task 5682 | prompt eval time = 6661.56 ms / 875 tokens ( 7.61 ms per token, 131.35 tokens per second) 6.33.524.093 I slot print_timing: id 2 | task 5682 | eval time = 781.38 ms / 2 tokens ( 781.38 ms per token, 1.28 tokens per second) 6.33.524.094 I slot print_timing: id 2 | task 5682 | total time = 7442.95 ms / 877 tokens 6.33.524.094 I slot print_timing: id 2 | task 5682 | graphs reused = 4509 6.33.524.094 I slot print_timing: id 2 | task 5682 | graph reallocs = 0 / 0 (same size) / (changed size) 6.33.524.132 I slot release: id 2 | task 5682 | stop processing: n_tokens = 885, truncated = 0 6.33.525.255 I slot print_timing: id 3 | task 5683 | prompt eval time = 6662.59 ms / 1014 tokens ( 6.57 ms per token, 152.19 tokens per second) 6.33.525.256 I slot print_timing: id 3 | task 5683 | eval time = 781.31 ms / 2 tokens ( 781.31 ms per token, 1.28 tokens per second) 6.33.525.257 I slot print_timing: id 3 | task 5683 | total time = 7443.90 ms / 1016 tokens 6.33.525.258 I slot print_timing: id 3 | task 5683 | graphs reused = 4509 6.33.525.258 I slot print_timing: id 3 | task 5683 | graph reallocs = 0 / 0 (same size) / (changed size) 6.33.525.300 I slot release: id 3 | task 5683 | stop processing: n_tokens = 1024, truncated = 0 6.33.525.308 I slot print_timing: id 0 | task 5686 | prompt processing, n_tokens = 890, progress = 1.00, t = 4.57 s / 194.78 tokens per second 6.33.527.457 I slot print_timing: id 1 | task 5687 | prompt processing, n_tokens = 998, progress = 1.00, t = 4.57 s / 218.43 tokens per second 6.33.569.445 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.810 (> 0.100 thold), f_keep = 0.785 6.33.569.509 I slot launch_slot_: id 3 | task 5692 | processing task, is_child = 0 6.33.569.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 350.955 MiB) 6.33.576.155 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 329048808236 6.33.576.291 I slot launch_slot_: id 2 | task 5693 | processing task, is_child = 0 6.34.721.213 I slot print_timing: id 0 | task 5686 | prompt eval time = 4614.52 ms / 894 tokens ( 5.16 ms per token, 193.74 tokens per second) 6.34.721.217 I slot print_timing: id 0 | task 5686 | eval time = 1152.92 ms / 2 tokens ( 1152.92 ms per token, 0.87 tokens per second) 6.34.721.218 I slot print_timing: id 0 | task 5686 | total time = 5767.44 ms / 896 tokens 6.34.721.218 I slot print_timing: id 0 | task 5686 | graphs reused = 4509 6.34.721.219 I slot print_timing: id 0 | task 5686 | graph reallocs = 0 / 0 (same size) / (changed size) 6.34.721.285 I slot release: id 0 | task 5686 | stop processing: n_tokens = 904, truncated = 0 6.34.722.443 I slot print_timing: id 1 | task 5687 | prompt eval time = 4615.47 ms / 1002 tokens ( 4.61 ms per token, 217.10 tokens per second) 6.34.722.446 I slot print_timing: id 1 | task 5687 | eval time = 1153.00 ms / 2 tokens ( 1153.00 ms per token, 0.87 tokens per second) 6.34.722.446 I slot print_timing: id 1 | task 5687 | total time = 5768.47 ms / 1004 tokens 6.34.722.447 I slot print_timing: id 1 | task 5687 | graphs reused = 4509 6.34.722.447 I slot print_timing: id 1 | task 5687 | graph reallocs = 0 / 0 (same size) / (changed size) 6.34.722.500 I slot release: id 1 | task 5687 | stop processing: n_tokens = 1012, truncated = 0 6.35.472.581 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 329050005389 6.35.472.675 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.178 MiB) 6.35.481.148 I slot launch_slot_: id 0 | task 5696 | processing task, is_child = 0 6.35.491.807 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.794 6.35.491.864 I slot launch_slot_: id 1 | task 5697 | processing task, is_child = 0 6.36.759.241 I slot print_timing: id 3 | task 5692 | prompt eval time = 1896.07 ms / 188 tokens ( 10.09 ms per token, 99.15 tokens per second) 6.36.759.244 I slot print_timing: id 3 | task 5692 | eval time = 1286.66 ms / 2 tokens ( 1286.66 ms per token, 0.78 tokens per second) 6.36.759.245 I slot print_timing: id 3 | task 5692 | total time = 3182.73 ms / 190 tokens 6.36.759.246 I slot print_timing: id 3 | task 5692 | graphs reused = 4509 6.36.759.246 I slot print_timing: id 3 | task 5692 | graph reallocs = 0 / 0 (same size) / (changed size) 6.36.759.309 I slot release: id 3 | task 5692 | stop processing: n_tokens = 993, truncated = 0 6.36.764.504 I slot print_timing: id 2 | task 5693 | prompt processing, n_tokens = 893, progress = 1.00, t = 3.18 s / 280.65 tokens per second 6.37.475.300 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 993, t_last = 329052043413 6.37.475.434 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 370.426 MiB) 6.37.483.403 I slot launch_slot_: id 3 | task 5700 | processing task, is_child = 0 6.38.572.401 I slot print_timing: id 1 | task 5697 | prompt eval time = 1981.97 ms / 81 tokens ( 24.47 ms per token, 40.87 tokens per second) 6.38.572.405 I slot print_timing: id 1 | task 5697 | eval time = 1098.32 ms / 2 tokens ( 1098.32 ms per token, 0.91 tokens per second) 6.38.572.406 I slot print_timing: id 1 | task 5697 | total time = 3080.30 ms / 83 tokens 6.38.572.407 I slot print_timing: id 1 | task 5697 | graphs reused = 4509 6.38.572.407 I slot print_timing: id 1 | task 5697 | graph reallocs = 0 / 0 (same size) / (changed size) 6.38.572.455 I slot release: id 1 | task 5697 | stop processing: n_tokens = 886, truncated = 0 6.38.573.607 I slot print_timing: id 2 | task 5693 | prompt eval time = 3898.99 ms / 897 tokens ( 4.35 ms per token, 230.06 tokens per second) 6.38.573.615 I slot print_timing: id 2 | task 5693 | eval time = 1098.31 ms / 2 tokens ( 1098.31 ms per token, 0.91 tokens per second) 6.38.573.616 I slot print_timing: id 2 | task 5693 | total time = 4997.31 ms / 899 tokens 6.38.573.616 I slot print_timing: id 2 | task 5693 | graphs reused = 4509 6.38.573.617 I slot print_timing: id 2 | task 5693 | graph reallocs = 0 / 0 (same size) / (changed size) 6.38.573.654 I slot release: id 2 | task 5693 | stop processing: n_tokens = 907, truncated = 0 6.38.573.671 I slot print_timing: id 0 | task 5696 | prompt processing, n_tokens = 927, progress = 1.00, t = 3.08 s / 301.03 tokens per second 6.39.369.759 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 886, t_last = 329053856559 6.39.369.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.185 MiB) 6.39.382.101 I slot launch_slot_: id 1 | task 5703 | processing task, is_child = 0 6.39.382.177 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.576 MiB) 6.39.390.541 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 329053857758 6.39.390.662 I slot launch_slot_: id 2 | task 5704 | processing task, is_child = 0 6.41.986.115 I slot print_timing: id 0 | task 5696 | prompt eval time = 3877.88 ms / 931 tokens ( 4.17 ms per token, 240.08 tokens per second) 6.41.986.118 I slot print_timing: id 0 | task 5696 | eval time = 2616.35 ms / 2 tokens ( 2616.35 ms per token, 0.38 tokens per second) 6.41.986.118 I slot print_timing: id 0 | task 5696 | total time = 6494.23 ms / 933 tokens 6.41.986.119 I slot print_timing: id 0 | task 5696 | graphs reused = 4509 6.41.986.120 I slot print_timing: id 0 | task 5696 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.986.208 I slot release: id 0 | task 5696 | stop processing: n_tokens = 941, truncated = 0 6.41.993.300 I slot print_timing: id 3 | task 5700 | prompt processing, n_tokens = 880, progress = 1.00, t = 4.50 s / 195.56 tokens per second 6.43.372.474 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 329057270312 6.43.386.283 I slot launch_slot_: id 0 | task 5707 | processing task, is_child = 0 6.43.386.529 I slot print_timing: id 1 | task 5703 | prompt processing, n_tokens = 753, progress = 0.82, t = 3.98 s / 189.16 tokens per second 6.43.388.195 I slot print_timing: id 2 | task 5704 | prompt processing, n_tokens = 1148, progress = 0.85, t = 3.98 s / 288.41 tokens per second 6.45.703.941 I slot print_timing: id 3 | task 5700 | prompt eval time = 5887.39 ms / 884 tokens ( 6.66 ms per token, 150.15 tokens per second) 6.45.703.944 I slot print_timing: id 3 | task 5700 | eval time = 2331.48 ms / 2 tokens ( 2331.48 ms per token, 0.43 tokens per second) 6.45.703.945 I slot print_timing: id 3 | task 5700 | total time = 8218.87 ms / 886 tokens 6.45.703.945 I slot print_timing: id 3 | task 5700 | graphs reused = 4509 6.45.703.946 I slot print_timing: id 3 | task 5700 | graph reallocs = 0 / 0 (same size) / (changed size) 6.45.703.992 I slot release: id 3 | task 5700 | stop processing: n_tokens = 894, truncated = 0 6.45.706.797 I slot print_timing: id 1 | task 5703 | prompt processing, n_tokens = 914, progress = 1.00, t = 6.31 s / 144.80 tokens per second 6.45.708.834 I slot print_timing: id 2 | task 5704 | prompt processing, n_tokens = 1349, progress = 1.00, t = 6.31 s / 213.72 tokens per second 6.46.368.359 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 329060988096 6.46.368.475 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 245.780 MiB) 6.46.376.308 I slot launch_slot_: id 3 | task 5710 | processing task, is_child = 0 6.48.172.094 I slot print_timing: id 1 | task 5703 | prompt eval time = 6976.49 ms / 918 tokens ( 7.60 ms per token, 131.58 tokens per second) 6.48.172.096 I slot print_timing: id 1 | task 5703 | eval time = 1804.93 ms / 2 tokens ( 1804.93 ms per token, 0.55 tokens per second) 6.48.172.097 I slot print_timing: id 1 | task 5703 | total time = 8781.42 ms / 920 tokens 6.48.172.097 I slot print_timing: id 1 | task 5703 | graphs reused = 4509 6.48.172.098 I slot print_timing: id 1 | task 5703 | graph reallocs = 0 / 0 (same size) / (changed size) 6.48.172.171 I slot release: id 1 | task 5703 | stop processing: n_tokens = 928, truncated = 0 6.48.173.300 I slot print_timing: id 2 | task 5704 | prompt eval time = 6977.45 ms / 1353 tokens ( 5.16 ms per token, 193.91 tokens per second) 6.48.173.303 I slot print_timing: id 2 | task 5704 | eval time = 1804.95 ms / 2 tokens ( 1804.95 ms per token, 0.55 tokens per second) 6.48.173.304 I slot print_timing: id 2 | task 5704 | total time = 8782.40 ms / 1355 tokens 6.48.173.304 I slot print_timing: id 2 | task 5704 | graphs reused = 4509 6.48.173.304 I slot print_timing: id 2 | task 5704 | graph reallocs = 0 / 0 (same size) / (changed size) 6.48.173.375 I slot release: id 2 | task 5704 | stop processing: n_tokens = 1363, truncated = 0 6.48.173.398 I slot print_timing: id 0 | task 5707 | prompt processing, n_tokens = 1336, progress = 1.00, t = 4.78 s / 279.22 tokens per second 6.48.987.116 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 329063456275 6.48.987.235 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.323 MiB) 6.49.005.045 I slot launch_slot_: id 1 | task 5713 | processing task, is_child = 0 6.49.005.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 248.171 MiB) 6.49.022.125 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 6.49.022.186 I slot launch_slot_: id 2 | task 5714 | processing task, is_child = 0 6.50.044.029 I slot print_timing: id 0 | task 5707 | prompt eval time = 5600.81 ms / 1340 tokens ( 4.18 ms per token, 239.25 tokens per second) 6.50.044.035 I slot print_timing: id 0 | task 5707 | eval time = 1056.92 ms / 2 tokens ( 1056.92 ms per token, 0.95 tokens per second) 6.50.044.036 I slot print_timing: id 0 | task 5707 | total time = 6657.72 ms / 1342 tokens 6.50.044.036 I slot print_timing: id 0 | task 5707 | graphs reused = 4509 6.50.044.037 I slot print_timing: id 0 | task 5707 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.044.139 I slot release: id 0 | task 5707 | stop processing: n_tokens = 1350, truncated = 0 6.50.048.910 I slot print_timing: id 3 | task 5710 | prompt processing, n_tokens = 1251, progress = 1.00, t = 3.66 s / 341.35 tokens per second 6.50.865.174 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1350, t_last = 329065328243 6.50.865.300 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.635 MiB) 6.50.865.316 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.136 MiB) 6.50.895.387 I slot launch_slot_: id 0 | task 5717 | processing task, is_child = 0 6.51.710.646 I slot print_timing: id 2 | task 5714 | prompt eval time = 1841.58 ms / 121 tokens ( 15.22 ms per token, 65.70 tokens per second) 6.51.710.648 I slot print_timing: id 2 | task 5714 | eval time = 846.64 ms / 2 tokens ( 846.64 ms per token, 1.18 tokens per second) 6.51.710.649 I slot print_timing: id 2 | task 5714 | total time = 2688.22 ms / 123 tokens 6.51.710.649 I slot print_timing: id 2 | task 5714 | graphs reused = 4509 6.51.710.650 I slot print_timing: id 2 | task 5714 | graph reallocs = 0 / 0 (same size) / (changed size) 6.51.710.742 I slot release: id 2 | task 5714 | stop processing: n_tokens = 1306, truncated = 0 6.51.711.894 I slot print_timing: id 3 | task 5710 | prompt eval time = 4487.12 ms / 1255 tokens ( 3.58 ms per token, 279.69 tokens per second) 6.51.711.897 I slot print_timing: id 3 | task 5710 | eval time = 846.73 ms / 2 tokens ( 846.73 ms per token, 1.18 tokens per second) 6.51.711.899 I slot print_timing: id 3 | task 5710 | total time = 5333.85 ms / 1257 tokens 6.51.711.900 I slot print_timing: id 3 | task 5710 | graphs reused = 4509 6.51.711.900 I slot print_timing: id 3 | task 5710 | graph reallocs = 0 / 0 (same size) / (changed size) 6.51.711.945 I slot release: id 3 | task 5710 | stop processing: n_tokens = 1265, truncated = 0 6.52.457.039 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1306, t_last = 329066994847 6.52.457.173 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.184 MiB) 6.52.484.634 I slot launch_slot_: id 2 | task 5720 | processing task, is_child = 0 6.52.484.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 230.309 MiB) 6.52.505.082 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1265, t_last = 329066996049 6.52.505.216 I slot launch_slot_: id 3 | task 5721 | processing task, is_child = 0 6.54.125.376 I slot print_timing: id 1 | task 5713 | prompt eval time = 3434.83 ms / 782 tokens ( 4.39 ms per token, 227.67 tokens per second) 6.54.125.383 I slot print_timing: id 1 | task 5713 | eval time = 1668.34 ms / 2 tokens ( 1668.34 ms per token, 0.60 tokens per second) 6.54.125.383 I slot print_timing: id 1 | task 5713 | total time = 5103.18 ms / 784 tokens 6.54.125.384 I slot print_timing: id 1 | task 5713 | graphs reused = 4509 6.54.125.384 I slot print_timing: id 1 | task 5713 | graph reallocs = 0 / 0 (same size) / (changed size) 6.54.125.429 I slot release: id 1 | task 5713 | stop processing: n_tokens = 792, truncated = 0 6.54.125.466 I slot print_timing: id 0 | task 5717 | prompt processing, n_tokens = 797, progress = 1.00, t = 3.23 s / 246.84 tokens per second 6.55.603.165 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 792, t_last = 329069409533 6.55.603.295 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.776 MiB) 6.55.618.302 I slot launch_slot_: id 1 | task 5724 | processing task, is_child = 0 6.55.618.494 I slot print_timing: id 2 | task 5720 | prompt processing, n_tokens = 736, progress = 0.83, t = 3.10 s / 237.79 tokens per second 6.55.620.155 I slot print_timing: id 3 | task 5721 | prompt processing, n_tokens = 736, progress = 0.86, t = 3.09 s / 237.81 tokens per second 6.56.689.012 I slot print_timing: id 0 | task 5717 | prompt eval time = 4707.75 ms / 801 tokens ( 5.88 ms per token, 170.14 tokens per second) 6.56.689.018 I slot print_timing: id 0 | task 5717 | eval time = 1085.86 ms / 2 tokens ( 1085.86 ms per token, 0.92 tokens per second) 6.56.689.018 I slot print_timing: id 0 | task 5717 | total time = 5793.61 ms / 803 tokens 6.56.689.019 I slot print_timing: id 0 | task 5717 | graphs reused = 4509 6.56.689.019 I slot print_timing: id 0 | task 5717 | graph reallocs = 0 / 0 (same size) / (changed size) 6.56.689.086 I slot release: id 0 | task 5717 | stop processing: n_tokens = 811, truncated = 0 6.56.692.208 I slot print_timing: id 2 | task 5720 | prompt processing, n_tokens = 882, progress = 1.00, t = 4.18 s / 210.95 tokens per second 6.56.696.953 I slot print_timing: id 3 | task 5721 | prompt processing, n_tokens = 853, progress = 1.00, t = 4.18 s / 204.03 tokens per second 6.57.457.581 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 811, t_last = 329071973190 6.57.457.693 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.981 MiB) 6.57.467.525 I slot launch_slot_: id 0 | task 5727 | processing task, is_child = 0 6.58.439.702 I slot print_timing: id 2 | task 5720 | prompt eval time = 4949.47 ms / 886 tokens ( 5.59 ms per token, 179.01 tokens per second) 6.58.439.705 I slot print_timing: id 2 | task 5720 | eval time = 983.32 ms / 2 tokens ( 983.32 ms per token, 1.02 tokens per second) 6.58.439.705 I slot print_timing: id 2 | task 5720 | total time = 5932.79 ms / 888 tokens 6.58.439.706 I slot print_timing: id 2 | task 5720 | graphs reused = 4509 6.58.439.706 I slot print_timing: id 2 | task 5720 | graph reallocs = 0 / 0 (same size) / (changed size) 6.58.439.786 I slot release: id 2 | task 5720 | stop processing: n_tokens = 896, truncated = 0 6.58.440.957 I slot print_timing: id 3 | task 5721 | prompt eval time = 4950.45 ms / 857 tokens ( 5.78 ms per token, 173.12 tokens per second) 6.58.440.959 I slot print_timing: id 3 | task 5721 | eval time = 983.39 ms / 2 tokens ( 983.39 ms per token, 1.02 tokens per second) 6.58.440.960 I slot print_timing: id 3 | task 5721 | total time = 5933.83 ms / 859 tokens 6.58.440.960 I slot print_timing: id 3 | task 5721 | graphs reused = 4509 6.58.440.961 I slot print_timing: id 3 | task 5721 | graph reallocs = 0 / 0 (same size) / (changed size) 6.58.441.000 I slot release: id 3 | task 5721 | stop processing: n_tokens = 867, truncated = 0 6.59.073.882 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 896, t_last = 329073723890 6.59.074.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 234.388 MiB) 6.59.086.199 I slot launch_slot_: id 2 | task 5730 | processing task, is_child = 0 6.59.086.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.374 MiB) 6.59.091.927 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 867, t_last = 329073725104 6.59.092.046 I slot launch_slot_: id 3 | task 5731 | processing task, is_child = 0 7.00.471.534 I slot print_timing: id 1 | task 5724 | prompt eval time = 3455.56 ms / 778 tokens ( 4.44 ms per token, 225.14 tokens per second) 7.00.471.537 I slot print_timing: id 1 | task 5724 | eval time = 1397.65 ms / 2 tokens ( 1397.65 ms per token, 0.72 tokens per second) 7.00.471.538 I slot print_timing: id 1 | task 5724 | total time = 4853.21 ms / 780 tokens 7.00.471.538 I slot print_timing: id 1 | task 5724 | graphs reused = 4509 7.00.471.539 I slot print_timing: id 1 | task 5724 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.471.602 I slot release: id 1 | task 5724 | stop processing: n_tokens = 788, truncated = 0 7.00.471.638 I slot print_timing: id 0 | task 5727 | prompt processing, n_tokens = 839, progress = 1.00, t = 3.00 s / 279.40 tokens per second 7.01.990.756 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.849 (> 0.100 thold), f_keep = 0.862 7.01.990.863 I slot launch_slot_: id 1 | task 5734 | processing task, is_child = 0 7.02.748.551 I slot print_timing: id 0 | task 5727 | prompt eval time = 4523.21 ms / 843 tokens ( 5.37 ms per token, 186.37 tokens per second) 7.02.748.555 I slot print_timing: id 0 | task 5727 | eval time = 757.80 ms / 2 tokens ( 757.80 ms per token, 1.32 tokens per second) 7.02.748.556 I slot print_timing: id 0 | task 5727 | total time = 5281.01 ms / 845 tokens 7.02.748.556 I slot print_timing: id 0 | task 5727 | graphs reused = 4509 7.02.748.557 I slot print_timing: id 0 | task 5727 | graph reallocs = 0 / 0 (same size) / (changed size) 7.02.748.601 I slot release: id 0 | task 5727 | stop processing: n_tokens = 853, truncated = 0 7.02.752.685 I slot print_timing: id 2 | task 5730 | prompt processing, n_tokens = 764, progress = 0.99, t = 3.65 s / 209.10 tokens per second 7.02.755.224 I slot print_timing: id 3 | task 5731 | prompt processing, n_tokens = 758, progress = 0.99, t = 3.65 s / 207.47 tokens per second 7.02.817.013 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 853, t_last = 329078032705 7.02.817.093 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.859 MiB) 7.02.822.942 I slot launch_slot_: id 0 | task 5737 | processing task, is_child = 0 7.03.657.022 I slot print_timing: id 1 | task 5734 | prompt eval time = 823.96 ms / 121 tokens ( 6.81 ms per token, 146.85 tokens per second) 7.03.657.024 I slot print_timing: id 1 | task 5734 | eval time = 842.18 ms / 2 tokens ( 842.18 ms per token, 1.19 tokens per second) 7.03.657.025 I slot print_timing: id 1 | task 5734 | total time = 1666.14 ms / 123 tokens 7.03.657.026 I slot print_timing: id 1 | task 5734 | graphs reused = 4509 7.03.657.026 I slot print_timing: id 1 | task 5734 | graph reallocs = 0 / 0 (same size) / (changed size) 7.03.657.087 I slot release: id 1 | task 5734 | stop processing: n_tokens = 801, truncated = 0 7.03.658.232 I slot print_timing: id 2 | task 5730 | prompt eval time = 3722.20 ms / 768 tokens ( 4.85 ms per token, 206.33 tokens per second) 7.03.658.236 I slot print_timing: id 2 | task 5730 | eval time = 842.29 ms / 2 tokens ( 842.29 ms per token, 1.19 tokens per second) 7.03.658.237 I slot print_timing: id 2 | task 5730 | total time = 4564.49 ms / 770 tokens 7.03.658.237 I slot print_timing: id 2 | task 5730 | graphs reused = 4509 7.03.658.237 I slot print_timing: id 2 | task 5730 | graph reallocs = 0 / 0 (same size) / (changed size) 7.03.658.267 I slot release: id 2 | task 5730 | stop processing: n_tokens = 778, truncated = 0 7.03.659.423 I slot print_timing: id 3 | task 5731 | prompt eval time = 3723.08 ms / 762 tokens ( 4.89 ms per token, 204.67 tokens per second) 7.03.659.425 I slot print_timing: id 3 | task 5731 | eval time = 842.41 ms / 2 tokens ( 842.41 ms per token, 1.19 tokens per second) 7.03.659.426 I slot print_timing: id 3 | task 5731 | total time = 4565.49 ms / 764 tokens 7.03.659.426 I slot print_timing: id 3 | task 5731 | graphs reused = 4509 7.03.659.426 I slot print_timing: id 3 | task 5731 | graph reallocs = 0 / 0 (same size) / (changed size) 7.03.659.452 I slot release: id 3 | task 5731 | stop processing: n_tokens = 772, truncated = 0 7.04.387.282 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 801, t_last = 329078941191 7.04.387.361 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.360 MiB) 7.04.696.384 I slot launch_slot_: id 1 | task 5741 | processing task, is_child = 0 7.04.696.465 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.014 MiB) 7.04.703.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.037 MiB) 7.04.709.984 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 329078942371 7.04.710.107 I slot launch_slot_: id 2 | task 5742 | processing task, is_child = 0 7.04.710.170 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 329078943556 7.04.710.263 I slot launch_slot_: id 3 | task 5743 | processing task, is_child = 0 7.09.443.862 I slot print_timing: id 0 | task 5737 | prompt eval time = 4272.90 ms / 952 tokens ( 4.49 ms per token, 222.80 tokens per second) 7.09.443.866 I slot print_timing: id 0 | task 5737 | eval time = 2347.99 ms / 2 tokens ( 2347.99 ms per token, 0.43 tokens per second) 7.09.443.867 I slot print_timing: id 0 | task 5737 | total time = 6620.90 ms / 954 tokens 7.09.443.867 I slot print_timing: id 0 | task 5737 | graphs reused = 4509 7.09.443.867 I slot print_timing: id 0 | task 5737 | graph reallocs = 0 / 0 (same size) / (changed size) 7.09.443.945 I slot release: id 0 | task 5737 | stop processing: n_tokens = 962, truncated = 0 7.09.443.977 I slot print_timing: id 1 | task 5741 | prompt processing, n_tokens = 817, progress = 0.88, t = 4.73 s / 172.70 tokens per second 7.09.446.886 I slot print_timing: id 2 | task 5742 | prompt processing, n_tokens = 817, progress = 0.88, t = 4.73 s / 172.71 tokens per second 7.09.448.879 I slot print_timing: id 3 | task 5743 | prompt processing, n_tokens = 817, progress = 0.87, t = 4.73 s / 172.71 tokens per second 7.10.087.082 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.887 7.10.087.160 I slot launch_slot_: id 0 | task 5747 | processing task, is_child = 0 7.10.175.287 I slot print_timing: id 1 | task 5741 | prompt processing, n_tokens = 924, progress = 1.00, t = 5.38 s / 171.91 tokens per second 7.10.178.132 I slot print_timing: id 2 | task 5742 | prompt processing, n_tokens = 922, progress = 1.00, t = 5.37 s / 171.54 tokens per second 7.10.182.854 I slot print_timing: id 3 | task 5743 | prompt processing, n_tokens = 940, progress = 1.00, t = 5.37 s / 174.89 tokens per second 7.10.578.003 I slot print_timing: id 1 | task 5741 | prompt eval time = 5787.17 ms / 928 tokens ( 6.24 ms per token, 160.35 tokens per second) 7.10.578.009 I slot print_timing: id 1 | task 5741 | eval time = 78.81 ms / 2 tokens ( 78.81 ms per token, 12.69 tokens per second) 7.10.578.009 I slot print_timing: id 1 | task 5741 | total time = 5865.98 ms / 930 tokens 7.10.578.009 I slot print_timing: id 1 | task 5741 | graphs reused = 4509 7.10.578.010 I slot print_timing: id 1 | task 5741 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.578.049 I slot release: id 1 | task 5741 | stop processing: n_tokens = 938, truncated = 0 7.10.579.172 I slot print_timing: id 2 | task 5742 | prompt eval time = 5788.15 ms / 926 tokens ( 6.25 ms per token, 159.98 tokens per second) 7.10.579.173 I slot print_timing: id 2 | task 5742 | eval time = 78.79 ms / 2 tokens ( 78.79 ms per token, 12.69 tokens per second) 7.10.579.174 I slot print_timing: id 2 | task 5742 | total time = 5866.94 ms / 928 tokens 7.10.579.174 I slot print_timing: id 2 | task 5742 | graphs reused = 4509 7.10.579.174 I slot print_timing: id 2 | task 5742 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.579.202 I slot release: id 2 | task 5742 | stop processing: n_tokens = 936, truncated = 0 7.10.580.309 I slot print_timing: id 3 | task 5743 | prompt eval time = 5789.30 ms / 944 tokens ( 6.13 ms per token, 163.06 tokens per second) 7.10.580.310 I slot print_timing: id 3 | task 5743 | eval time = 78.63 ms / 2 tokens ( 78.63 ms per token, 12.72 tokens per second) 7.10.580.311 I slot print_timing: id 3 | task 5743 | total time = 5867.93 ms / 946 tokens 7.10.580.311 I slot print_timing: id 3 | task 5743 | graphs reused = 4509 7.10.580.313 I slot print_timing: id 3 | task 5743 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.580.339 I slot release: id 3 | task 5743 | stop processing: n_tokens = 954, truncated = 0 7.10.601.472 I slot print_timing: id 0 | task 5747 | prompt eval time = 489.77 ms / 107 tokens ( 4.58 ms per token, 218.47 tokens per second) 7.10.601.474 I slot print_timing: id 0 | task 5747 | eval time = 24.53 ms / 2 tokens ( 24.53 ms per token, 40.77 tokens per second) 7.10.601.474 I slot print_timing: id 0 | task 5747 | total time = 514.30 ms / 109 tokens 7.10.601.475 I slot print_timing: id 0 | task 5747 | graphs reused = 4509 7.10.601.475 I slot print_timing: id 0 | task 5747 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.601.504 I slot release: id 0 | task 5747 | stop processing: n_tokens = 961, truncated = 0 7.10.601.510 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 329085862153 7.10.601.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 242.264 MiB) 7.10.607.743 I slot launch_slot_: id 1 | task 5751 | processing task, is_child = 0 7.10.607.821 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.291 MiB) 7.10.617.632 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 233.544 MiB) 7.10.627.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 209.775 MiB) 7.10.637.963 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 329085863306 7.10.638.103 I slot launch_slot_: id 2 | task 5752 | processing task, is_child = 0 7.10.638.251 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 329085864443 7.10.638.351 I slot launch_slot_: id 3 | task 5753 | processing task, is_child = 0 7.10.638.420 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 329085885608 7.10.638.517 I slot launch_slot_: id 0 | task 5754 | processing task, is_child = 0 7.16.049.169 I slot print_timing: id 0 | task 5754 | prompt processing, n_tokens = 818, progress = 0.87, t = 5.41 s / 151.18 tokens per second 7.16.191.504 I slot print_timing: id 1 | task 5751 | prompt processing, n_tokens = 818, progress = 0.85, t = 5.41 s / 151.19 tokens per second 7.16.193.809 I slot print_timing: id 2 | task 5752 | prompt processing, n_tokens = 668, progress = 0.85, t = 5.41 s / 123.47 tokens per second 7.16.195.714 I slot print_timing: id 3 | task 5753 | prompt processing, n_tokens = 668, progress = 0.85, t = 5.41 s / 123.47 tokens per second 7.17.141.553 I slot print_timing: id 0 | task 5754 | prompt processing, n_tokens = 943, progress = 1.00, t = 6.50 s / 145.01 tokens per second 7.17.229.245 I slot print_timing: id 1 | task 5751 | prompt processing, n_tokens = 963, progress = 1.00, t = 6.50 s / 148.09 tokens per second 7.17.232.294 I slot print_timing: id 2 | task 5752 | prompt processing, n_tokens = 785, progress = 0.99, t = 6.50 s / 120.72 tokens per second 7.17.234.045 I slot print_timing: id 3 | task 5753 | prompt processing, n_tokens = 785, progress = 0.99, t = 6.50 s / 120.72 tokens per second 7.17.336.725 I slot print_timing: id 0 | task 5754 | prompt eval time = 6658.85 ms / 947 tokens ( 7.03 ms per token, 142.22 tokens per second) 7.17.336.730 I slot print_timing: id 0 | task 5754 | eval time = 39.35 ms / 2 tokens ( 39.35 ms per token, 25.42 tokens per second) 7.17.336.731 I slot print_timing: id 0 | task 5754 | total time = 6698.20 ms / 949 tokens 7.17.336.731 I slot print_timing: id 0 | task 5754 | graphs reused = 4510 7.17.336.732 I slot print_timing: id 0 | task 5754 | graph reallocs = 0 / 0 (same size) / (changed size) 7.17.336.771 I slot release: id 0 | task 5754 | stop processing: n_tokens = 957, truncated = 0 7.17.337.884 I slot print_timing: id 1 | task 5751 | prompt eval time = 6659.76 ms / 967 tokens ( 6.89 ms per token, 145.20 tokens per second) 7.17.337.885 I slot print_timing: id 1 | task 5751 | eval time = 39.39 ms / 2 tokens ( 39.39 ms per token, 25.39 tokens per second) 7.17.337.886 I slot print_timing: id 1 | task 5751 | total time = 6699.15 ms / 969 tokens 7.17.337.886 I slot print_timing: id 1 | task 5751 | graphs reused = 4510 7.17.337.887 I slot print_timing: id 1 | task 5751 | graph reallocs = 0 / 0 (same size) / (changed size) 7.17.337.915 I slot release: id 1 | task 5751 | stop processing: n_tokens = 977, truncated = 0 7.17.339.011 I slot print_timing: id 2 | task 5752 | prompt eval time = 6660.65 ms / 789 tokens ( 8.44 ms per token, 118.46 tokens per second) 7.17.339.014 I slot print_timing: id 2 | task 5752 | eval time = 39.45 ms / 2 tokens ( 39.45 ms per token, 25.35 tokens per second) 7.17.339.014 I slot print_timing: id 2 | task 5752 | total time = 6700.11 ms / 791 tokens 7.17.339.014 I slot print_timing: id 2 | task 5752 | graphs reused = 4510 7.17.339.015 I slot print_timing: id 2 | task 5752 | graph reallocs = 0 / 0 (same size) / (changed size) 7.17.339.040 I slot release: id 2 | task 5752 | stop processing: n_tokens = 799, truncated = 0 7.17.340.138 I slot print_timing: id 3 | task 5753 | prompt eval time = 6661.55 ms / 789 tokens ( 8.44 ms per token, 118.44 tokens per second) 7.17.340.141 I slot print_timing: id 3 | task 5753 | eval time = 39.52 ms / 2 tokens ( 39.52 ms per token, 25.30 tokens per second) 7.17.340.141 I slot print_timing: id 3 | task 5753 | total time = 6701.07 ms / 791 tokens 7.17.340.141 I slot print_timing: id 3 | task 5753 | graphs reused = 4510 7.17.340.142 I slot print_timing: id 3 | task 5753 | graph reallocs = 0 / 0 (same size) / (changed size) 7.17.340.163 I slot release: id 3 | task 5753 | stop processing: n_tokens = 799, truncated = 0 7.17.343.537 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.892 7.17.343.597 I slot launch_slot_: id 0 | task 5760 | processing task, is_child = 0 7.17.343.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.524 MiB) 7.17.354.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.676 MiB) 7.17.359.854 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.419 MiB) 7.17.365.337 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 329092622019 7.17.365.486 I slot launch_slot_: id 1 | task 5761 | processing task, is_child = 0 7.17.365.606 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 329092623144 7.17.365.701 I slot launch_slot_: id 2 | task 5762 | processing task, is_child = 0 7.17.365.763 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 329092624267 7.17.365.853 I slot launch_slot_: id 3 | task 5763 | processing task, is_child = 0 7.21.998.512 I slot print_timing: id 1 | task 5761 | prompt processing, n_tokens = 771, progress = 0.86, t = 4.63 s / 166.53 tokens per second 7.22.002.253 I slot print_timing: id 2 | task 5762 | prompt processing, n_tokens = 771, progress = 0.87, t = 4.63 s / 166.54 tokens per second 7.22.004.165 I slot print_timing: id 3 | task 5763 | prompt processing, n_tokens = 771, progress = 0.84, t = 4.63 s / 166.54 tokens per second 7.22.816.944 I slot print_timing: id 0 | task 5760 | prompt eval time = 4632.62 ms / 108 tokens ( 42.89 ms per token, 23.31 tokens per second) 7.22.816.948 I slot print_timing: id 0 | task 5760 | eval time = 818.46 ms / 2 tokens ( 818.46 ms per token, 1.22 tokens per second) 7.22.816.949 I slot print_timing: id 0 | task 5760 | total time = 5451.08 ms / 110 tokens 7.22.816.950 I slot print_timing: id 0 | task 5760 | graphs reused = 4511 7.22.816.950 I slot print_timing: id 0 | task 5760 | graph reallocs = 0 / 0 (same size) / (changed size) 7.22.817.021 I slot release: id 0 | task 5760 | stop processing: n_tokens = 963, truncated = 0 7.22.817.040 I slot print_timing: id 1 | task 5761 | prompt processing, n_tokens = 890, progress = 1.00, t = 5.45 s / 163.35 tokens per second 7.22.821.140 I slot print_timing: id 2 | task 5762 | prompt processing, n_tokens = 886, progress = 1.00, t = 5.45 s / 162.63 tokens per second 7.22.823.631 I slot print_timing: id 3 | task 5763 | prompt processing, n_tokens = 917, progress = 1.00, t = 5.45 s / 168.32 tokens per second 7.22.885.752 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 963, t_last = 329098101125 7.22.885.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.430 MiB) 7.22.893.076 I slot launch_slot_: id 0 | task 5768 | processing task, is_child = 0 7.23.609.369 I slot print_timing: id 1 | task 5761 | prompt eval time = 5516.02 ms / 894 tokens ( 6.17 ms per token, 162.07 tokens per second) 7.23.609.375 I slot print_timing: id 1 | task 5761 | eval time = 725.78 ms / 2 tokens ( 725.78 ms per token, 1.38 tokens per second) 7.23.609.376 I slot print_timing: id 1 | task 5761 | total time = 6241.80 ms / 896 tokens 7.23.609.377 I slot print_timing: id 1 | task 5761 | graphs reused = 4511 7.23.609.377 I slot print_timing: id 1 | task 5761 | graph reallocs = 0 / 0 (same size) / (changed size) 7.23.609.456 I slot release: id 1 | task 5761 | stop processing: n_tokens = 904, truncated = 0 7.23.610.608 I slot print_timing: id 2 | task 5762 | prompt eval time = 5516.91 ms / 890 tokens ( 6.20 ms per token, 161.32 tokens per second) 7.23.610.611 I slot print_timing: id 2 | task 5762 | eval time = 725.94 ms / 2 tokens ( 725.94 ms per token, 1.38 tokens per second) 7.23.610.611 I slot print_timing: id 2 | task 5762 | total time = 6242.85 ms / 892 tokens 7.23.610.612 I slot print_timing: id 2 | task 5762 | graphs reused = 4511 7.23.610.612 I slot print_timing: id 2 | task 5762 | graph reallocs = 0 / 0 (same size) / (changed size) 7.23.610.663 I slot release: id 2 | task 5762 | stop processing: n_tokens = 900, truncated = 0 7.23.611.828 I slot print_timing: id 3 | task 5763 | prompt eval time = 5517.84 ms / 921 tokens ( 5.99 ms per token, 166.91 tokens per second) 7.23.611.830 I slot print_timing: id 3 | task 5763 | eval time = 726.07 ms / 2 tokens ( 726.07 ms per token, 1.38 tokens per second) 7.23.611.830 I slot print_timing: id 3 | task 5763 | total time = 6243.91 ms / 923 tokens 7.23.611.830 I slot print_timing: id 3 | task 5763 | graphs reused = 4511 7.23.611.831 I slot print_timing: id 3 | task 5763 | graph reallocs = 0 / 0 (same size) / (changed size) 7.23.611.865 I slot release: id 3 | task 5763 | stop processing: n_tokens = 931, truncated = 0 7.23.620.210 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 329098893560 7.23.620.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 250.844 MiB) 7.24.380.926 I slot launch_slot_: id 1 | task 5771 | processing task, is_child = 0 7.24.381.017 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 302.916 MiB) 7.24.387.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.719 MiB) 7.24.393.350 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.897 7.24.393.407 I slot launch_slot_: id 2 | task 5772 | processing task, is_child = 0 7.24.393.481 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 329098895969 7.24.393.583 I slot launch_slot_: id 3 | task 5773 | processing task, is_child = 0 7.27.186.187 I slot print_timing: id 0 | task 5768 | prompt processing, n_tokens = 890, progress = 1.00, t = 4.29 s / 207.31 tokens per second 7.28.820.389 I slot print_timing: id 1 | task 5771 | prompt processing, n_tokens = 1051, progress = 0.87, t = 4.42 s / 237.64 tokens per second 7.28.824.297 I slot print_timing: id 3 | task 5773 | prompt processing, n_tokens = 1051, progress = 0.86, t = 4.42 s / 237.74 tokens per second 7.29.580.535 I slot print_timing: id 0 | task 5768 | prompt eval time = 5926.04 ms / 894 tokens ( 6.63 ms per token, 150.86 tokens per second) 7.29.580.544 I slot print_timing: id 0 | task 5768 | eval time = 761.40 ms / 2 tokens ( 761.40 ms per token, 1.31 tokens per second) 7.29.580.544 I slot print_timing: id 0 | task 5768 | total time = 6687.44 ms / 896 tokens 7.29.580.545 I slot print_timing: id 0 | task 5768 | graphs reused = 4511 7.29.580.545 I slot print_timing: id 0 | task 5768 | graph reallocs = 0 / 0 (same size) / (changed size) 7.29.580.624 I slot release: id 0 | task 5768 | stop processing: n_tokens = 904, truncated = 0 7.29.581.794 I slot print_timing: id 2 | task 5772 | prompt eval time = 4424.86 ms / 83 tokens ( 53.31 ms per token, 18.76 tokens per second) 7.29.581.797 I slot print_timing: id 2 | task 5772 | eval time = 761.43 ms / 2 tokens ( 761.43 ms per token, 1.31 tokens per second) 7.29.581.798 I slot print_timing: id 2 | task 5772 | total time = 5186.29 ms / 85 tokens 7.29.581.798 I slot print_timing: id 2 | task 5772 | graphs reused = 4511 7.29.581.798 I slot print_timing: id 2 | task 5772 | graph reallocs = 0 / 0 (same size) / (changed size) 7.29.581.852 I slot release: id 2 | task 5772 | stop processing: n_tokens = 891, truncated = 0 7.29.581.866 I slot print_timing: id 1 | task 5771 | prompt processing, n_tokens = 1211, progress = 1.00, t = 5.18 s / 233.60 tokens per second 7.29.585.594 I slot print_timing: id 3 | task 5773 | prompt processing, n_tokens = 1222, progress = 1.00, t = 5.18 s / 235.81 tokens per second 7.29.655.564 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 329104864728 7.29.655.645 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 233.966 MiB) 7.29.661.926 I slot launch_slot_: id 0 | task 5778 | processing task, is_child = 0 7.29.662.001 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 7.29.668.859 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 329104865956 7.29.668.981 I slot launch_slot_: id 2 | task 5779 | processing task, is_child = 0 7.33.477.591 I slot print_timing: id 1 | task 5771 | prompt eval time = 5259.15 ms / 1215 tokens ( 4.33 ms per token, 231.03 tokens per second) 7.33.477.594 I slot print_timing: id 1 | task 5771 | eval time = 3823.14 ms / 2 tokens ( 3823.14 ms per token, 0.26 tokens per second) 7.33.477.595 I slot print_timing: id 1 | task 5771 | total time = 9082.29 ms / 1217 tokens 7.33.477.595 I slot print_timing: id 1 | task 5771 | graphs reused = 4511 7.33.477.596 I slot print_timing: id 1 | task 5771 | graph reallocs = 0 / 0 (same size) / (changed size) 7.33.477.685 I slot release: id 1 | task 5771 | stop processing: n_tokens = 1225, truncated = 0 7.33.478.861 I slot print_timing: id 3 | task 5773 | prompt eval time = 5258.36 ms / 1226 tokens ( 4.29 ms per token, 233.15 tokens per second) 7.33.478.864 I slot print_timing: id 3 | task 5773 | eval time = 3823.30 ms / 2 tokens ( 3823.30 ms per token, 0.26 tokens per second) 7.33.478.864 I slot print_timing: id 3 | task 5773 | total time = 9081.66 ms / 1228 tokens 7.33.478.865 I slot print_timing: id 3 | task 5773 | graphs reused = 4511 7.33.478.865 I slot print_timing: id 3 | task 5773 | graph reallocs = 0 / 0 (same size) / (changed size) 7.33.478.919 I slot release: id 3 | task 5773 | stop processing: n_tokens = 1236, truncated = 0 7.33.478.944 I slot print_timing: id 0 | task 5778 | prompt processing, n_tokens = 764, progress = 0.60, t = 3.81 s / 200.66 tokens per second 7.33.482.108 I slot print_timing: id 2 | task 5779 | prompt processing, n_tokens = 1282, progress = 0.48, t = 3.81 s / 336.72 tokens per second 7.34.982.953 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1225, t_last = 329108761789 7.34.983.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 251.828 MiB) 7.35.654.437 I slot launch_slot_: id 1 | task 5782 | processing task, is_child = 0 7.35.654.546 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.432 MiB) 7.35.661.040 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1236, t_last = 329108763023 7.35.661.172 I slot launch_slot_: id 3 | task 5783 | processing task, is_child = 0 7.35.661.180 I slot print_timing: id 0 | task 5778 | prompt processing, n_tokens = 1051, progress = 0.82, t = 5.31 s / 197.78 tokens per second 7.39.339.437 I slot print_timing: id 0 | task 5778 | prompt processing, n_tokens = 1276, progress = 1.00, t = 9.67 s / 131.95 tokens per second 7.39.486.930 I slot print_timing: id 1 | task 5782 | prompt processing, n_tokens = 1823, progress = 0.71, t = 3.68 s / 495.85 tokens per second 7.39.486.951 I slot print_timing: id 2 | task 5779 | prompt processing, n_tokens = 2146, progress = 0.81, t = 5.31 s / 403.86 tokens per second 7.43.430.566 I slot print_timing: id 1 | task 5782 | prompt processing, n_tokens = 2052, progress = 0.80, t = 7.77 s / 264.22 tokens per second 7.43.433.899 I slot print_timing: id 2 | task 5779 | prompt processing, n_tokens = 2353, progress = 0.88, t = 13.76 s / 171.00 tokens per second 7.43.435.889 I slot print_timing: id 3 | task 5783 | prompt processing, n_tokens = 1608, progress = 0.57, t = 3.94 s / 408.11 tokens per second 7.46.078.213 I slot print_timing: id 0 | task 5778 | prompt eval time = 13761.53 ms / 1280 tokens ( 10.75 ms per token, 93.01 tokens per second) 7.46.078.218 I slot print_timing: id 0 | task 5778 | eval time = 2647.68 ms / 2 tokens ( 2647.68 ms per token, 0.38 tokens per second) 7.46.078.218 I slot print_timing: id 0 | task 5778 | total time = 16409.21 ms / 1282 tokens 7.46.078.219 I slot print_timing: id 0 | task 5778 | graphs reused = 4511 7.46.078.219 I slot print_timing: id 0 | task 5778 | graph reallocs = 0 / 0 (same size) / (changed size) 7.46.078.312 I slot release: id 0 | task 5778 | stop processing: n_tokens = 1290, truncated = 0 7.46.078.340 I slot print_timing: id 1 | task 5782 | prompt processing, n_tokens = 2353, progress = 0.92, t = 10.41 s / 225.94 tokens per second 7.46.081.492 I slot print_timing: id 2 | task 5779 | prompt processing, n_tokens = 2658, progress = 1.00, t = 16.41 s / 162.00 tokens per second 7.46.083.698 I slot print_timing: id 3 | task 5783 | prompt processing, n_tokens = 2301, progress = 0.82, t = 6.59 s / 349.27 tokens per second 7.46.735.380 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1290, t_last = 329121362416 7.46.735.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 301.404 MiB) 7.46.745.988 I slot launch_slot_: id 0 | task 5788 | processing task, is_child = 0 7.50.515.354 I slot print_timing: id 2 | task 5779 | prompt eval time = 17066.17 ms / 2662 tokens ( 6.41 ms per token, 155.98 tokens per second) 7.50.515.357 I slot print_timing: id 2 | task 5779 | eval time = 3779.97 ms / 2 tokens ( 3779.97 ms per token, 0.26 tokens per second) 7.50.515.357 I slot print_timing: id 2 | task 5779 | total time = 20846.14 ms / 2664 tokens 7.50.515.358 I slot print_timing: id 2 | task 5779 | graphs reused = 4511 7.50.515.358 I slot print_timing: id 2 | task 5779 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.515.481 I slot release: id 2 | task 5779 | stop processing: n_tokens = 2672, truncated = 0 7.50.515.511 I slot print_timing: id 0 | task 5788 | prompt processing, n_tokens = 2047, progress = 0.75, t = 3.77 s / 543.22 tokens per second 7.50.515.540 I slot print_timing: id 1 | task 5782 | prompt processing, n_tokens = 2564, progress = 1.00, t = 11.07 s / 231.59 tokens per second 7.50.519.624 I slot print_timing: id 3 | task 5783 | prompt processing, n_tokens = 2353, progress = 0.84, t = 7.25 s / 324.78 tokens per second 7.51.865.332 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2672, t_last = 329125799587 7.51.865.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 237.060 MiB) 7.51.883.618 I slot launch_slot_: id 2 | task 5791 | processing task, is_child = 0 7.51.883.634 I slot print_timing: id 0 | task 5788 | prompt processing, n_tokens = 2213, progress = 0.81, t = 5.12 s / 432.38 tokens per second 7.51.885.798 I slot print_timing: id 3 | task 5783 | prompt processing, n_tokens = 2813, progress = 1.00, t = 12.38 s / 227.31 tokens per second 7.54.688.488 I slot print_timing: id 1 | task 5782 | prompt eval time = 16202.42 ms / 2568 tokens ( 6.31 ms per token, 158.49 tokens per second) 7.54.688.492 I slot print_timing: id 1 | task 5782 | eval time = 2823.15 ms / 2 tokens ( 2823.15 ms per token, 0.35 tokens per second) 7.54.688.493 I slot print_timing: id 1 | task 5782 | total time = 19025.57 ms / 2570 tokens 7.54.688.494 I slot print_timing: id 1 | task 5782 | graphs reused = 4511 7.54.688.494 I slot print_timing: id 1 | task 5782 | graph reallocs = 0 / 0 (same size) / (changed size) 7.54.688.695 I slot release: id 1 | task 5782 | stop processing: n_tokens = 2578, truncated = 0 7.54.689.935 I slot print_timing: id 0 | task 5788 | prompt processing, n_tokens = 2353, progress = 0.86, t = 7.94 s / 296.30 tokens per second 7.55.840.378 I slot print_timing: id 3 | task 5783 | prompt eval time = 15200.80 ms / 2817 tokens ( 5.40 ms per token, 185.32 tokens per second) 7.55.840.380 I slot print_timing: id 3 | task 5783 | eval time = 1150.46 ms / 2 tokens ( 1150.46 ms per token, 0.87 tokens per second) 7.55.840.381 I slot print_timing: id 3 | task 5783 | total time = 16351.26 ms / 2819 tokens 7.55.840.381 I slot print_timing: id 3 | task 5783 | graphs reused = 4511 7.55.840.382 I slot print_timing: id 3 | task 5783 | graph reallocs = 0 / 0 (same size) / (changed size) 7.55.840.505 I slot release: id 3 | task 5783 | stop processing: n_tokens = 2827, truncated = 0 7.55.840.517 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2578, t_last = 329129972801 7.55.840.706 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.842 MiB) 7.55.857.779 I slot launch_slot_: id 1 | task 5794 | processing task, is_child = 0 7.55.857.936 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 235.232 MiB) 7.55.875.107 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2827, t_last = 329131124611 7.55.875.313 I slot launch_slot_: id 3 | task 5795 | processing task, is_child = 0 7.55.875.320 I slot print_timing: id 0 | task 5788 | prompt processing, n_tokens = 2725, progress = 1.00, t = 9.09 s / 299.67 tokens per second 7.55.877.596 I slot print_timing: id 2 | task 5791 | prompt processing, n_tokens = 1467, progress = 0.81, t = 3.95 s / 371.03 tokens per second 7.59.713.225 I slot print_timing: id 1 | task 5794 | prompt processing, n_tokens = 1354, progress = 0.73, t = 3.83 s / 353.08 tokens per second 7.59.716.611 I slot print_timing: id 2 | task 5791 | prompt processing, n_tokens = 1806, progress = 1.00, t = 7.83 s / 230.75 tokens per second 7.59.718.713 I slot print_timing: id 3 | task 5795 | prompt processing, n_tokens = 351, progress = 0.17, t = 3.83 s / 91.58 tokens per second 8.02.126.031 I slot print_timing: id 0 | task 5788 | prompt eval time = 12967.18 ms / 2729 tokens ( 4.75 ms per token, 210.45 tokens per second) 8.02.126.034 I slot print_timing: id 0 | task 5788 | eval time = 2412.84 ms / 2 tokens ( 2412.84 ms per token, 0.41 tokens per second) 8.02.126.034 I slot print_timing: id 0 | task 5788 | total time = 15380.02 ms / 2731 tokens 8.02.126.035 I slot print_timing: id 0 | task 5788 | graphs reused = 4511 8.02.126.035 I slot print_timing: id 0 | task 5788 | graph reallocs = 0 / 0 (same size) / (changed size) 8.02.126.226 I slot release: id 0 | task 5788 | stop processing: n_tokens = 2739, truncated = 0 8.02.127.767 I slot print_timing: id 1 | task 5794 | prompt processing, n_tokens = 1467, progress = 0.79, t = 6.25 s / 234.81 tokens per second 8.02.131.520 I slot print_timing: id 3 | task 5795 | prompt processing, n_tokens = 1467, progress = 0.71, t = 6.25 s / 234.89 tokens per second 8.03.205.422 I slot print_timing: id 2 | task 5791 | prompt eval time = 10242.30 ms / 1810 tokens ( 5.66 ms per token, 176.72 tokens per second) 8.03.205.428 I slot print_timing: id 2 | task 5791 | eval time = 1077.66 ms / 2 tokens ( 1077.66 ms per token, 0.93 tokens per second) 8.03.205.429 I slot print_timing: id 2 | task 5791 | total time = 11319.96 ms / 1812 tokens 8.03.205.429 I slot print_timing: id 2 | task 5791 | graphs reused = 4511 8.03.205.430 I slot print_timing: id 2 | task 5791 | graph reallocs = 0 / 0 (same size) / (changed size) 8.03.205.576 I slot release: id 2 | task 5791 | stop processing: n_tokens = 1820, truncated = 0 8.03.205.593 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.799 (> 0.100 thold), f_keep = 0.831 8.03.205.737 I slot launch_slot_: id 2 | task 5799 | processing task, is_child = 0 8.03.205.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.014 MiB) 8.03.205.943 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.965 MiB) 8.03.225.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2739, t_last = 329137410331 8.03.225.243 I slot launch_slot_: id 0 | task 5800 | processing task, is_child = 0 8.03.225.607 I slot print_timing: id 1 | task 5794 | prompt processing, n_tokens = 1866, progress = 1.00, t = 7.33 s / 254.67 tokens per second 8.03.229.247 I slot print_timing: id 3 | task 5795 | prompt processing, n_tokens = 1565, progress = 0.75, t = 7.32 s / 213.65 tokens per second 8.07.134.127 I slot print_timing: id 0 | task 5800 | prompt processing, n_tokens = 1467, progress = 0.74, t = 3.91 s / 375.41 tokens per second 8.07.137.953 I slot print_timing: id 2 | task 5799 | prompt processing, n_tokens = 377, progress = 1.00, t = 3.91 s / 96.53 tokens per second 8.07.140.999 I slot print_timing: id 3 | task 5795 | prompt processing, n_tokens = 1765, progress = 0.85, t = 11.25 s / 156.84 tokens per second 8.07.861.220 I slot print_timing: id 1 | task 5794 | prompt eval time = 11256.82 ms / 1870 tokens ( 6.02 ms per token, 166.12 tokens per second) 8.07.861.226 I slot print_timing: id 1 | task 5794 | eval time = 727.12 ms / 2 tokens ( 727.12 ms per token, 1.38 tokens per second) 8.07.861.226 I slot print_timing: id 1 | task 5794 | total time = 11983.94 ms / 1872 tokens 8.07.861.227 I slot print_timing: id 1 | task 5794 | graphs reused = 4511 8.07.861.227 I slot print_timing: id 1 | task 5794 | graph reallocs = 0 / 0 (same size) / (changed size) 8.07.861.359 I slot release: id 1 | task 5794 | stop processing: n_tokens = 1880, truncated = 0 8.07.862.751 I slot print_timing: id 0 | task 5800 | prompt processing, n_tokens = 1475, progress = 0.74, t = 4.63 s / 318.24 tokens per second 8.07.865.292 I slot print_timing: id 3 | task 5795 | prompt processing, n_tokens = 2077, progress = 1.00, t = 11.98 s / 173.36 tokens per second 8.08.889.897 I slot print_timing: id 2 | task 5799 | prompt eval time = 4635.26 ms / 381 tokens ( 12.17 ms per token, 82.20 tokens per second) 8.08.889.903 I slot print_timing: id 2 | task 5799 | eval time = 1027.15 ms / 2 tokens ( 1027.15 ms per token, 0.97 tokens per second) 8.08.889.903 I slot print_timing: id 2 | task 5799 | total time = 5662.40 ms / 383 tokens 8.08.889.904 I slot print_timing: id 2 | task 5799 | graphs reused = 4511 8.08.889.905 I slot print_timing: id 2 | task 5799 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.890.024 I slot release: id 2 | task 5799 | stop processing: n_tokens = 1894, truncated = 0 8.08.891.545 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.804 8.08.891.694 I slot launch_slot_: id 1 | task 5804 | processing task, is_child = 0 8.08.891.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 265.508 MiB) 8.08.915.007 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1894, t_last = 329144174133 8.08.915.176 I slot launch_slot_: id 2 | task 5805 | processing task, is_child = 0 8.08.915.184 I slot print_timing: id 0 | task 5800 | prompt processing, n_tokens = 1987, progress = 1.00, t = 5.66 s / 350.84 tokens per second 8.10.007.887 I slot print_timing: id 3 | task 5795 | prompt eval time = 13012.20 ms / 2081 tokens ( 6.25 ms per token, 159.93 tokens per second) 8.10.007.889 I slot print_timing: id 3 | task 5795 | eval time = 1116.35 ms / 2 tokens ( 1116.35 ms per token, 0.90 tokens per second) 8.10.007.891 I slot print_timing: id 3 | task 5795 | total time = 14128.55 ms / 2083 tokens 8.10.007.891 I slot print_timing: id 3 | task 5795 | graphs reused = 4511 8.10.007.892 I slot print_timing: id 3 | task 5795 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.007.975 I slot release: id 3 | task 5795 | stop processing: n_tokens = 2091, truncated = 0 8.10.826.858 I slot print_timing: id 0 | task 5800 | prompt eval time = 6781.35 ms / 1991 tokens ( 3.41 ms per token, 293.60 tokens per second) 8.10.826.861 I slot print_timing: id 0 | task 5800 | eval time = 820.25 ms / 2 tokens ( 820.25 ms per token, 1.22 tokens per second) 8.10.826.862 I slot print_timing: id 0 | task 5800 | total time = 7601.60 ms / 1993 tokens 8.10.826.862 I slot print_timing: id 0 | task 5800 | graphs reused = 4511 8.10.826.863 I slot print_timing: id 0 | task 5800 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.826.997 I slot release: id 0 | task 5800 | stop processing: n_tokens = 2001, truncated = 0 8.10.828.406 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2091, t_last = 329145292079 8.10.828.565 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.967 MiB) 8.10.854.217 I slot launch_slot_: id 3 | task 5808 | processing task, is_child = 0 8.10.854.344 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 262.519 MiB) 8.10.872.928 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2001, t_last = 329146111103 8.10.873.087 I slot launch_slot_: id 0 | task 5809 | processing task, is_child = 0 8.12.022.509 I slot print_timing: id 1 | task 5804 | prompt eval time = 1911.35 ms / 301 tokens ( 6.35 ms per token, 157.48 tokens per second) 8.12.022.513 I slot print_timing: id 1 | task 5804 | eval time = 1194.09 ms / 2 tokens ( 1194.09 ms per token, 0.84 tokens per second) 8.12.022.513 I slot print_timing: id 1 | task 5804 | total time = 3105.44 ms / 303 tokens 8.12.022.514 I slot print_timing: id 1 | task 5804 | graphs reused = 4511 8.12.022.514 I slot print_timing: id 1 | task 5804 | graph reallocs = 0 / 0 (same size) / (changed size) 8.12.022.623 I slot release: id 1 | task 5804 | stop processing: n_tokens = 1814, truncated = 0 8.12.024.731 I slot print_timing: id 2 | task 5805 | prompt processing, n_tokens = 712, progress = 0.99, t = 3.10 s / 229.49 tokens per second 8.13.459.555 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1814, t_last = 329147306729 8.13.459.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.886 MiB) 8.13.459.718 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.558 MiB) 8.13.479.570 I slot launch_slot_: id 1 | task 5812 | processing task, is_child = 0 8.14.430.402 I slot print_timing: id 2 | task 5805 | prompt eval time = 4540.73 ms / 716 tokens ( 6.34 ms per token, 157.68 tokens per second) 8.14.430.409 I slot print_timing: id 2 | task 5805 | eval time = 970.85 ms / 2 tokens ( 970.85 ms per token, 1.03 tokens per second) 8.14.430.410 I slot print_timing: id 2 | task 5805 | total time = 5511.58 ms / 718 tokens 8.14.430.410 I slot print_timing: id 2 | task 5805 | graphs reused = 4511 8.14.430.411 I slot print_timing: id 2 | task 5805 | graph reallocs = 0 / 0 (same size) / (changed size) 8.14.430.451 I slot release: id 2 | task 5805 | stop processing: n_tokens = 726, truncated = 0 8.14.430.469 I slot print_timing: id 0 | task 5809 | prompt processing, n_tokens = 744, progress = 0.99, t = 3.56 s / 209.21 tokens per second 8.14.435.821 I slot print_timing: id 3 | task 5808 | prompt processing, n_tokens = 731, progress = 0.99, t = 3.55 s / 205.67 tokens per second 8.15.257.377 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.879 8.15.257.481 I slot launch_slot_: id 2 | task 5815 | processing task, is_child = 0 8.15.735.609 I slot print_timing: id 0 | task 5809 | prompt eval time = 4382.88 ms / 748 tokens ( 5.86 ms per token, 170.66 tokens per second) 8.15.735.615 I slot print_timing: id 0 | task 5809 | eval time = 479.63 ms / 2 tokens ( 479.63 ms per token, 2.08 tokens per second) 8.15.735.616 I slot print_timing: id 0 | task 5809 | total time = 4862.51 ms / 750 tokens 8.15.735.616 I slot print_timing: id 0 | task 5809 | graphs reused = 4511 8.15.735.616 I slot print_timing: id 0 | task 5809 | graph reallocs = 0 / 0 (same size) / (changed size) 8.15.735.679 I slot release: id 0 | task 5809 | stop processing: n_tokens = 758, truncated = 0 8.15.736.835 I slot print_timing: id 3 | task 5808 | prompt eval time = 4382.29 ms / 735 tokens ( 5.96 ms per token, 167.72 tokens per second) 8.15.736.838 I slot print_timing: id 3 | task 5808 | eval time = 479.47 ms / 2 tokens ( 479.47 ms per token, 2.09 tokens per second) 8.15.736.838 I slot print_timing: id 3 | task 5808 | total time = 4861.76 ms / 737 tokens 8.15.736.838 I slot print_timing: id 3 | task 5808 | graphs reused = 4511 8.15.736.839 I slot print_timing: id 3 | task 5808 | graph reallocs = 0 / 0 (same size) / (changed size) 8.15.736.865 I slot release: id 3 | task 5808 | stop processing: n_tokens = 745, truncated = 0 8.15.780.342 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 758, t_last = 329151019783 8.15.780.418 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 235.513 MiB) 8.15.786.598 I slot launch_slot_: id 0 | task 5818 | processing task, is_child = 0 8.15.786.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 231.434 MiB) 8.15.791.885 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 329151020969 8.15.791.989 I slot launch_slot_: id 3 | task 5819 | processing task, is_child = 0 8.17.291.838 I slot print_timing: id 1 | task 5812 | prompt eval time = 2297.89 ms / 712 tokens ( 3.23 ms per token, 309.85 tokens per second) 8.17.291.841 I slot print_timing: id 1 | task 5812 | eval time = 1512.67 ms / 2 tokens ( 1512.67 ms per token, 0.66 tokens per second) 8.17.291.841 I slot print_timing: id 1 | task 5812 | total time = 3810.56 ms / 714 tokens 8.17.291.842 I slot print_timing: id 1 | task 5812 | graphs reused = 4511 8.17.291.842 I slot print_timing: id 1 | task 5812 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.291.890 I slot release: id 1 | task 5812 | stop processing: n_tokens = 722, truncated = 0 8.17.293.060 I slot print_timing: id 2 | task 5815 | prompt eval time = 519.11 ms / 101 tokens ( 5.14 ms per token, 194.56 tokens per second) 8.17.293.063 I slot print_timing: id 2 | task 5815 | eval time = 1512.72 ms / 2 tokens ( 1512.72 ms per token, 0.66 tokens per second) 8.17.293.063 I slot print_timing: id 2 | task 5815 | total time = 2031.83 ms / 103 tokens 8.17.293.064 I slot print_timing: id 2 | task 5815 | graphs reused = 4511 8.17.293.064 I slot print_timing: id 2 | task 5815 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.293.094 I slot release: id 2 | task 5815 | stop processing: n_tokens = 740, truncated = 0 8.17.944.667 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 722, t_last = 329152575994 8.18.653.994 I slot launch_slot_: id 1 | task 5822 | processing task, is_child = 0 8.18.654.076 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.465 MiB) 8.18.654.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.787 MiB) 8.18.660.405 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 329152577198 8.18.660.520 I slot launch_slot_: id 2 | task 5823 | processing task, is_child = 0 8.20.384.790 I slot print_timing: id 0 | task 5818 | prompt processing, n_tokens = 792, progress = 1.00, t = 4.59 s / 172.44 tokens per second 8.20.436.758 I slot print_timing: id 3 | task 5819 | prompt processing, n_tokens = 1039, progress = 1.00, t = 4.59 s / 226.23 tokens per second 8.21.946.745 I slot print_timing: id 1 | task 5822 | prompt processing, n_tokens = 672, progress = 0.85, t = 3.28 s / 204.74 tokens per second 8.21.951.021 I slot print_timing: id 2 | task 5823 | prompt processing, n_tokens = 672, progress = 0.84, t = 3.28 s / 204.75 tokens per second 8.22.537.338 I slot print_timing: id 0 | task 5818 | prompt eval time = 6153.52 ms / 796 tokens ( 7.73 ms per token, 129.36 tokens per second) 8.22.537.341 I slot print_timing: id 0 | task 5818 | eval time = 591.82 ms / 2 tokens ( 591.82 ms per token, 1.69 tokens per second) 8.22.537.342 I slot print_timing: id 0 | task 5818 | total time = 6745.33 ms / 798 tokens 8.22.537.343 I slot print_timing: id 0 | task 5818 | graphs reused = 4511 8.22.537.343 I slot print_timing: id 0 | task 5818 | graph reallocs = 0 / 0 (same size) / (changed size) 8.22.537.413 I slot release: id 0 | task 5818 | stop processing: n_tokens = 806, truncated = 0 8.22.538.565 I slot print_timing: id 3 | task 5819 | prompt eval time = 6154.55 ms / 1043 tokens ( 5.90 ms per token, 169.47 tokens per second) 8.22.538.570 I slot print_timing: id 3 | task 5819 | eval time = 591.84 ms / 2 tokens ( 591.84 ms per token, 1.69 tokens per second) 8.22.538.571 I slot print_timing: id 3 | task 5819 | total time = 6746.38 ms / 1045 tokens 8.22.538.572 I slot print_timing: id 3 | task 5819 | graphs reused = 4511 8.22.538.572 I slot print_timing: id 3 | task 5819 | graph reallocs = 0 / 0 (same size) / (changed size) 8.22.538.631 I slot release: id 3 | task 5819 | stop processing: n_tokens = 1053, truncated = 0 8.22.538.646 I slot print_timing: id 1 | task 5822 | prompt processing, n_tokens = 789, progress = 1.00, t = 3.87 s / 203.67 tokens per second 8.22.541.261 I slot print_timing: id 2 | task 5823 | prompt processing, n_tokens = 799, progress = 1.00, t = 3.87 s / 206.26 tokens per second 8.22.582.978 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 329157821517 8.22.589.250 I slot launch_slot_: id 0 | task 5828 | processing task, is_child = 0 8.22.589.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.917 MiB) 8.22.589.336 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.073 MiB) 8.22.595.635 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 329157822735 8.22.595.754 I slot launch_slot_: id 3 | task 5829 | processing task, is_child = 0 8.23.766.479 I slot print_timing: id 1 | task 5822 | prompt eval time = 3919.66 ms / 793 tokens ( 4.94 ms per token, 202.31 tokens per second) 8.23.766.483 I slot print_timing: id 1 | task 5822 | eval time = 1184.60 ms / 2 tokens ( 1184.60 ms per token, 0.84 tokens per second) 8.23.766.484 I slot print_timing: id 1 | task 5822 | total time = 5104.27 ms / 795 tokens 8.23.766.485 I slot print_timing: id 1 | task 5822 | graphs reused = 4511 8.23.766.485 I slot print_timing: id 1 | task 5822 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.766.558 I slot release: id 1 | task 5822 | stop processing: n_tokens = 803, truncated = 0 8.23.767.777 I slot print_timing: id 2 | task 5823 | prompt eval time = 3920.60 ms / 803 tokens ( 4.88 ms per token, 204.82 tokens per second) 8.23.767.781 I slot print_timing: id 2 | task 5823 | eval time = 1184.80 ms / 2 tokens ( 1184.80 ms per token, 0.84 tokens per second) 8.23.767.781 I slot print_timing: id 2 | task 5823 | total time = 5105.40 ms / 805 tokens 8.23.767.782 I slot print_timing: id 2 | task 5823 | graphs reused = 4511 8.23.767.782 I slot print_timing: id 2 | task 5823 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.767.820 I slot release: id 2 | task 5823 | stop processing: n_tokens = 813, truncated = 0 8.24.529.432 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 329159050662 8.24.529.524 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.420 MiB) 8.25.286.582 I slot launch_slot_: id 1 | task 5832 | processing task, is_child = 0 8.25.292.208 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 813, t_last = 329159051924 8.25.292.320 I slot launch_slot_: id 2 | task 5833 | processing task, is_child = 0 8.27.115.873 I slot print_timing: id 0 | task 5828 | prompt processing, n_tokens = 832, progress = 1.00, t = 4.52 s / 184.07 tokens per second 8.27.150.605 I slot print_timing: id 3 | task 5829 | prompt processing, n_tokens = 824, progress = 1.00, t = 4.52 s / 182.30 tokens per second 8.28.472.268 I slot print_timing: id 1 | task 5832 | prompt processing, n_tokens = 712, progress = 0.79, t = 3.18 s / 224.20 tokens per second 8.28.475.639 I slot print_timing: id 2 | task 5833 | prompt processing, n_tokens = 712, progress = 0.80, t = 3.18 s / 224.21 tokens per second 8.29.210.176 I slot print_timing: id 0 | task 5828 | prompt eval time = 5875.20 ms / 836 tokens ( 7.03 ms per token, 142.29 tokens per second) 8.29.210.179 I slot print_timing: id 0 | task 5828 | eval time = 739.21 ms / 2 tokens ( 739.21 ms per token, 1.35 tokens per second) 8.29.210.179 I slot print_timing: id 0 | task 5828 | total time = 6614.41 ms / 838 tokens 8.29.210.180 I slot print_timing: id 0 | task 5828 | graphs reused = 4511 8.29.210.181 I slot print_timing: id 0 | task 5828 | graph reallocs = 0 / 0 (same size) / (changed size) 8.29.210.273 I slot release: id 0 | task 5828 | stop processing: n_tokens = 846, truncated = 0 8.29.211.523 I slot print_timing: id 3 | task 5829 | prompt eval time = 5876.29 ms / 828 tokens ( 7.10 ms per token, 140.91 tokens per second) 8.29.211.525 I slot print_timing: id 3 | task 5829 | eval time = 739.28 ms / 2 tokens ( 739.28 ms per token, 1.35 tokens per second) 8.29.211.526 I slot print_timing: id 3 | task 5829 | total time = 6615.57 ms / 830 tokens 8.29.211.526 I slot print_timing: id 3 | task 5829 | graphs reused = 4511 8.29.211.526 I slot print_timing: id 3 | task 5829 | graph reallocs = 0 / 0 (same size) / (changed size) 8.29.211.551 I slot release: id 3 | task 5829 | stop processing: n_tokens = 838, truncated = 0 8.29.211.559 I slot print_timing: id 1 | task 5832 | prompt processing, n_tokens = 895, progress = 1.00, t = 3.92 s / 228.61 tokens per second 8.29.213.742 I slot print_timing: id 2 | task 5833 | prompt processing, n_tokens = 889, progress = 1.00, t = 3.91 s / 227.08 tokens per second 8.29.255.590 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 846, t_last = 329164494377 8.29.255.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 298.767 MiB) 8.29.261.575 I slot launch_slot_: id 0 | task 5838 | processing task, is_child = 0 8.29.261.647 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 241.139 MiB) 8.29.267.185 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.869 (> 0.100 thold), f_keep = 0.893 8.29.267.227 I slot launch_slot_: id 3 | task 5839 | processing task, is_child = 0 8.29.908.419 I slot print_timing: id 1 | task 5832 | prompt eval time = 3960.34 ms / 899 tokens ( 4.41 ms per token, 227.00 tokens per second) 8.29.908.422 I slot print_timing: id 1 | task 5832 | eval time = 654.06 ms / 2 tokens ( 654.06 ms per token, 1.53 tokens per second) 8.29.908.422 I slot print_timing: id 1 | task 5832 | total time = 4614.40 ms / 901 tokens 8.29.908.423 I slot print_timing: id 1 | task 5832 | graphs reused = 4511 8.29.908.423 I slot print_timing: id 1 | task 5832 | graph reallocs = 0 / 0 (same size) / (changed size) 8.29.908.469 I slot release: id 1 | task 5832 | stop processing: n_tokens = 909, truncated = 0 8.29.909.680 I slot print_timing: id 2 | task 5833 | prompt eval time = 3961.39 ms / 893 tokens ( 4.44 ms per token, 225.43 tokens per second) 8.29.909.683 I slot print_timing: id 2 | task 5833 | eval time = 654.09 ms / 2 tokens ( 654.09 ms per token, 1.53 tokens per second) 8.29.909.683 I slot print_timing: id 2 | task 5833 | total time = 4615.47 ms / 895 tokens 8.29.909.683 I slot print_timing: id 2 | task 5833 | graphs reused = 4511 8.29.909.684 I slot print_timing: id 2 | task 5833 | graph reallocs = 0 / 0 (same size) / (changed size) 8.29.909.725 I slot release: id 2 | task 5833 | stop processing: n_tokens = 903, truncated = 0 8.30.698.296 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 909, t_last = 329165192573 8.30.698.392 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 243.671 MiB) 8.30.706.524 I slot launch_slot_: id 1 | task 5842 | processing task, is_child = 0 8.30.706.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.906 MiB) 8.30.712.408 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 329165193829 8.30.712.525 I slot launch_slot_: id 2 | task 5843 | processing task, is_child = 0 8.32.132.963 I slot print_timing: id 3 | task 5839 | prompt eval time = 1430.87 ms / 113 tokens ( 12.66 ms per token, 78.97 tokens per second) 8.32.132.965 I slot print_timing: id 3 | task 5839 | eval time = 1434.67 ms / 2 tokens ( 1434.67 ms per token, 0.70 tokens per second) 8.32.132.965 I slot print_timing: id 3 | task 5839 | total time = 2865.54 ms / 115 tokens 8.32.132.966 I slot print_timing: id 3 | task 5839 | graphs reused = 4511 8.32.132.966 I slot print_timing: id 3 | task 5839 | graph reallocs = 0 / 0 (same size) / (changed size) 8.32.133.009 I slot release: id 3 | task 5839 | stop processing: n_tokens = 862, truncated = 0 8.33.624.079 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 329167417113 8.33.624.172 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.870 MiB) 8.33.631.375 I slot launch_slot_: id 3 | task 5846 | processing task, is_child = 0 8.34.643.753 I slot print_timing: id 0 | task 5838 | prompt eval time = 4356.84 ms / 682 tokens ( 6.39 ms per token, 156.54 tokens per second) 8.34.643.756 I slot print_timing: id 0 | task 5838 | eval time = 1019.67 ms / 2 tokens ( 1019.67 ms per token, 0.98 tokens per second) 8.34.643.757 I slot print_timing: id 0 | task 5838 | total time = 5376.51 ms / 684 tokens 8.34.643.757 I slot print_timing: id 0 | task 5838 | graphs reused = 4511 8.34.643.758 I slot print_timing: id 0 | task 5838 | graph reallocs = 0 / 0 (same size) / (changed size) 8.34.643.817 I slot release: id 0 | task 5838 | stop processing: n_tokens = 692, truncated = 0 8.34.643.840 I slot print_timing: id 1 | task 5842 | prompt processing, n_tokens = 818, progress = 1.00, t = 3.93 s / 208.22 tokens per second 8.34.647.987 I slot print_timing: id 2 | task 5843 | prompt processing, n_tokens = 841, progress = 1.00, t = 3.93 s / 214.09 tokens per second 8.35.407.998 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 329169927921 8.35.408.099 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.870 MiB) 8.35.415.038 I slot launch_slot_: id 0 | task 5849 | processing task, is_child = 0 8.36.162.353 I slot print_timing: id 1 | task 5842 | prompt eval time = 4692.48 ms / 822 tokens ( 5.71 ms per token, 175.17 tokens per second) 8.36.162.356 I slot print_timing: id 1 | task 5842 | eval time = 755.67 ms / 2 tokens ( 755.67 ms per token, 1.32 tokens per second) 8.36.162.356 I slot print_timing: id 1 | task 5842 | total time = 5448.15 ms / 824 tokens 8.36.162.357 I slot print_timing: id 1 | task 5842 | graphs reused = 4511 8.36.162.357 I slot print_timing: id 1 | task 5842 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.162.404 I slot release: id 1 | task 5842 | stop processing: n_tokens = 832, truncated = 0 8.36.163.596 I slot print_timing: id 2 | task 5843 | prompt eval time = 4693.60 ms / 845 tokens ( 5.55 ms per token, 180.03 tokens per second) 8.36.163.600 I slot print_timing: id 2 | task 5843 | eval time = 755.60 ms / 2 tokens ( 755.60 ms per token, 1.32 tokens per second) 8.36.163.600 I slot print_timing: id 2 | task 5843 | total time = 5449.20 ms / 847 tokens 8.36.163.600 I slot print_timing: id 2 | task 5843 | graphs reused = 4511 8.36.163.601 I slot print_timing: id 2 | task 5843 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.163.645 I slot release: id 2 | task 5843 | stop processing: n_tokens = 855, truncated = 0 8.36.953.314 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 329171446508 8.36.953.399 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 298.310 MiB) 8.36.961.592 I slot launch_slot_: id 1 | task 5852 | processing task, is_child = 0 8.36.961.662 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 8.36.967.408 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 329171447749 8.36.967.528 I slot launch_slot_: id 2 | task 5853 | processing task, is_child = 0 8.37.997.155 I slot print_timing: id 3 | task 5846 | prompt eval time = 3318.60 ms / 750 tokens ( 4.42 ms per token, 226.00 tokens per second) 8.37.997.159 I slot print_timing: id 3 | task 5846 | eval time = 1043.84 ms / 2 tokens ( 1043.84 ms per token, 0.96 tokens per second) 8.37.997.159 I slot print_timing: id 3 | task 5846 | total time = 4362.44 ms / 752 tokens 8.37.997.160 I slot print_timing: id 3 | task 5846 | graphs reused = 4511 8.37.997.160 I slot print_timing: id 3 | task 5846 | graph reallocs = 0 / 0 (same size) / (changed size) 8.37.997.222 I slot release: id 3 | task 5846 | stop processing: n_tokens = 760, truncated = 0 8.39.529.301 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 329173281326 8.39.529.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.076 MiB) 8.39.538.461 I slot launch_slot_: id 3 | task 5856 | processing task, is_child = 0 8.40.439.116 I slot print_timing: id 0 | task 5849 | prompt eval time = 4114.24 ms / 736 tokens ( 5.59 ms per token, 178.89 tokens per second) 8.40.439.119 I slot print_timing: id 0 | task 5849 | eval time = 909.82 ms / 2 tokens ( 909.82 ms per token, 1.10 tokens per second) 8.40.439.120 I slot print_timing: id 0 | task 5849 | total time = 5024.06 ms / 738 tokens 8.40.439.120 I slot print_timing: id 0 | task 5849 | graphs reused = 4511 8.40.439.120 I slot print_timing: id 0 | task 5849 | graph reallocs = 0 / 0 (same size) / (changed size) 8.40.439.186 I slot release: id 0 | task 5849 | stop processing: n_tokens = 746, truncated = 0 8.40.439.211 I slot print_timing: id 1 | task 5852 | prompt processing, n_tokens = 697, progress = 0.99, t = 3.47 s / 200.94 tokens per second 8.40.443.365 I slot print_timing: id 2 | task 5853 | prompt processing, n_tokens = 719, progress = 0.99, t = 3.47 s / 207.30 tokens per second 8.41.253.323 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 329175723290 8.41.253.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 240.436 MiB) 8.41.262.211 I slot launch_slot_: id 0 | task 5859 | processing task, is_child = 0 8.41.904.042 I slot print_timing: id 1 | task 5852 | prompt eval time = 4282.71 ms / 701 tokens ( 6.11 ms per token, 163.68 tokens per second) 8.41.904.047 I slot print_timing: id 1 | task 5852 | eval time = 652.01 ms / 2 tokens ( 652.01 ms per token, 1.53 tokens per second) 8.41.904.048 I slot print_timing: id 1 | task 5852 | total time = 4934.72 ms / 703 tokens 8.41.904.049 I slot print_timing: id 1 | task 5852 | graphs reused = 4511 8.41.904.049 I slot print_timing: id 1 | task 5852 | graph reallocs = 0 / 0 (same size) / (changed size) 8.41.904.090 I slot release: id 1 | task 5852 | stop processing: n_tokens = 711, truncated = 0 8.41.905.207 I slot print_timing: id 2 | task 5853 | prompt eval time = 4283.79 ms / 723 tokens ( 5.93 ms per token, 168.78 tokens per second) 8.41.905.210 I slot print_timing: id 2 | task 5853 | eval time = 651.89 ms / 2 tokens ( 651.89 ms per token, 1.53 tokens per second) 8.41.905.210 I slot print_timing: id 2 | task 5853 | total time = 4935.68 ms / 725 tokens 8.41.905.211 I slot print_timing: id 2 | task 5853 | graphs reused = 4511 8.41.905.211 I slot print_timing: id 2 | task 5853 | graph reallocs = 0 / 0 (same size) / (changed size) 8.41.905.256 I slot release: id 2 | task 5853 | stop processing: n_tokens = 733, truncated = 0 8.42.693.308 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.880 8.42.693.451 I slot launch_slot_: id 1 | task 5862 | processing task, is_child = 0 8.42.693.574 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.638 MiB) 8.42.701.071 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.854 8.42.701.118 I slot launch_slot_: id 2 | task 5863 | processing task, is_child = 0 8.43.342.843 I slot print_timing: id 3 | task 5856 | prompt eval time = 3151.15 ms / 706 tokens ( 4.46 ms per token, 224.05 tokens per second) 8.43.342.849 I slot print_timing: id 3 | task 5856 | eval time = 649.53 ms / 2 tokens ( 649.53 ms per token, 1.54 tokens per second) 8.43.342.850 I slot print_timing: id 3 | task 5856 | total time = 3800.68 ms / 708 tokens 8.43.342.850 I slot print_timing: id 3 | task 5856 | graphs reused = 4511 8.43.342.851 I slot print_timing: id 3 | task 5856 | graph reallocs = 0 / 0 (same size) / (changed size) 8.43.342.918 I slot release: id 3 | task 5856 | stop processing: n_tokens = 716, truncated = 0 8.43.410.042 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.874 8.43.410.130 I slot launch_slot_: id 3 | task 5866 | processing task, is_child = 0 8.43.640.224 I slot print_timing: id 0 | task 5859 | prompt eval time = 2145.42 ms / 699 tokens ( 3.07 ms per token, 325.81 tokens per second) 8.43.640.226 I slot print_timing: id 0 | task 5859 | eval time = 232.57 ms / 2 tokens ( 232.57 ms per token, 4.30 tokens per second) 8.43.640.228 I slot print_timing: id 0 | task 5859 | total time = 2377.99 ms / 701 tokens 8.43.640.229 I slot print_timing: id 0 | task 5859 | graphs reused = 4511 8.43.640.230 I slot print_timing: id 0 | task 5859 | graph reallocs = 0 / 0 (same size) / (changed size) 8.43.640.292 I slot release: id 0 | task 5859 | stop processing: n_tokens = 709, truncated = 0 8.43.641.414 I slot print_timing: id 1 | task 5862 | prompt eval time = 706.05 ms / 85 tokens ( 8.31 ms per token, 120.39 tokens per second) 8.43.641.420 I slot print_timing: id 1 | task 5862 | eval time = 232.57 ms / 2 tokens ( 232.57 ms per token, 4.30 tokens per second) 8.43.641.421 I slot print_timing: id 1 | task 5862 | total time = 938.61 ms / 87 tokens 8.43.641.421 I slot print_timing: id 1 | task 5862 | graphs reused = 4511 8.43.641.421 I slot print_timing: id 1 | task 5862 | graph reallocs = 0 / 0 (same size) / (changed size) 8.43.641.466 I slot release: id 1 | task 5862 | stop processing: n_tokens = 712, truncated = 0 8.43.642.612 I slot print_timing: id 2 | task 5863 | prompt eval time = 705.56 ms / 79 tokens ( 8.93 ms per token, 111.97 tokens per second) 8.43.642.613 I slot print_timing: id 2 | task 5863 | eval time = 232.57 ms / 2 tokens ( 232.57 ms per token, 4.30 tokens per second) 8.43.642.614 I slot print_timing: id 2 | task 5863 | total time = 938.13 ms / 81 tokens 8.43.642.614 I slot print_timing: id 2 | task 5863 | graphs reused = 4511 8.43.642.614 I slot print_timing: id 2 | task 5863 | graph reallocs = 0 / 0 (same size) / (changed size) 8.43.642.642 I slot release: id 2 | task 5863 | stop processing: n_tokens = 706, truncated = 0 8.43.678.877 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.891 8.43.678.927 I slot launch_slot_: id 2 | task 5869 | processing task, is_child = 0 8.43.679.005 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.766 MiB) 8.43.690.560 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.883 8.43.690.616 I slot launch_slot_: id 0 | task 5870 | processing task, is_child = 0 8.43.690.679 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.879 8.43.690.712 I slot launch_slot_: id 1 | task 5871 | processing task, is_child = 0 8.44.367.167 I slot print_timing: id 3 | task 5866 | prompt eval time = 268.73 ms / 77 tokens ( 3.49 ms per token, 286.53 tokens per second) 8.44.367.170 I slot print_timing: id 3 | task 5866 | eval time = 688.29 ms / 2 tokens ( 688.29 ms per token, 1.45 tokens per second) 8.44.367.171 I slot print_timing: id 3 | task 5866 | total time = 957.03 ms / 79 tokens 8.44.367.172 I slot print_timing: id 3 | task 5866 | graphs reused = 4511 8.44.367.172 I slot print_timing: id 3 | task 5866 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.367.221 I slot release: id 3 | task 5866 | stop processing: n_tokens = 704, truncated = 0 8.44.434.904 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.889 8.44.434.954 I slot launch_slot_: id 3 | task 5874 | processing task, is_child = 0 8.44.666.575 I slot print_timing: id 0 | task 5870 | prompt eval time = 741.97 ms / 87 tokens ( 8.53 ms per token, 117.25 tokens per second) 8.44.666.581 I slot print_timing: id 0 | task 5870 | eval time = 233.88 ms / 2 tokens ( 233.88 ms per token, 4.28 tokens per second) 8.44.666.582 I slot print_timing: id 0 | task 5870 | total time = 975.85 ms / 89 tokens 8.44.666.583 I slot print_timing: id 0 | task 5870 | graphs reused = 4511 8.44.666.583 I slot print_timing: id 0 | task 5870 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.666.633 I slot release: id 0 | task 5870 | stop processing: n_tokens = 714, truncated = 0 8.44.667.744 I slot print_timing: id 1 | task 5871 | prompt eval time = 741.37 ms / 121 tokens ( 6.13 ms per token, 163.21 tokens per second) 8.44.667.748 I slot print_timing: id 1 | task 5871 | eval time = 233.98 ms / 2 tokens ( 233.98 ms per token, 4.27 tokens per second) 8.44.667.748 I slot print_timing: id 1 | task 5871 | total time = 975.35 ms / 123 tokens 8.44.667.748 I slot print_timing: id 1 | task 5871 | graphs reused = 4511 8.44.667.749 I slot print_timing: id 1 | task 5871 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.667.797 I slot release: id 1 | task 5871 | stop processing: n_tokens = 748, truncated = 0 8.44.668.971 I slot print_timing: id 2 | task 5869 | prompt eval time = 740.82 ms / 86 tokens ( 8.61 ms per token, 116.09 tokens per second) 8.44.668.973 I slot print_timing: id 2 | task 5869 | eval time = 234.07 ms / 2 tokens ( 234.07 ms per token, 4.27 tokens per second) 8.44.668.973 I slot print_timing: id 2 | task 5869 | total time = 974.89 ms / 88 tokens 8.44.668.973 I slot print_timing: id 2 | task 5869 | graphs reused = 4511 8.44.668.974 I slot print_timing: id 2 | task 5869 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.669.005 I slot release: id 2 | task 5869 | stop processing: n_tokens = 716, truncated = 0 8.44.705.044 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 329179950737 8.44.705.118 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.112 MiB) 8.44.711.401 I slot launch_slot_: id 0 | task 5877 | processing task, is_child = 0 8.44.711.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.499 MiB) 8.44.719.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.398 MiB) 8.44.719.136 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.000 MiB) 8.44.728.466 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 329179951901 8.44.728.603 I slot launch_slot_: id 1 | task 5878 | processing task, is_child = 0 8.44.728.664 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 329179953109 8.44.728.756 I slot launch_slot_: id 2 | task 5879 | processing task, is_child = 0 8.47.297.583 I slot print_timing: id 3 | task 5874 | prompt eval time = 270.08 ms / 80 tokens ( 3.38 ms per token, 296.21 tokens per second) 8.47.297.588 I slot print_timing: id 3 | task 5874 | eval time = 2592.53 ms / 2 tokens ( 2592.53 ms per token, 0.39 tokens per second) 8.47.297.588 I slot print_timing: id 3 | task 5874 | total time = 2862.62 ms / 82 tokens 8.47.297.589 I slot print_timing: id 3 | task 5874 | graphs reused = 4511 8.47.297.589 I slot print_timing: id 3 | task 5874 | graph reallocs = 0 / 0 (same size) / (changed size) 8.47.297.638 I slot release: id 3 | task 5874 | stop processing: n_tokens = 707, truncated = 0 8.49.378.331 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 329182581742 8.49.466.393 I slot launch_slot_: id 3 | task 5882 | processing task, is_child = 0 8.49.466.407 I slot print_timing: id 0 | task 5877 | prompt processing, n_tokens = 761, progress = 0.87, t = 4.65 s / 163.67 tokens per second 8.49.468.268 I slot print_timing: id 1 | task 5878 | prompt processing, n_tokens = 761, progress = 0.85, t = 4.65 s / 163.68 tokens per second 8.49.469.923 I slot print_timing: id 2 | task 5879 | prompt processing, n_tokens = 909, progress = 0.83, t = 4.65 s / 195.52 tokens per second 8.50.753.112 I slot print_timing: id 0 | task 5877 | prompt processing, n_tokens = 875, progress = 1.00, t = 6.02 s / 145.24 tokens per second 8.51.499.852 I slot print_timing: id 1 | task 5878 | prompt processing, n_tokens = 892, progress = 1.00, t = 6.02 s / 148.07 tokens per second 8.51.502.139 I slot print_timing: id 2 | task 5879 | prompt processing, n_tokens = 1095, progress = 1.00, t = 6.02 s / 181.77 tokens per second 8.52.636.537 I slot print_timing: id 0 | task 5877 | prompt eval time = 7490.32 ms / 879 tokens ( 8.52 ms per token, 117.35 tokens per second) 8.52.636.543 I slot print_timing: id 0 | task 5877 | eval time = 417.45 ms / 2 tokens ( 417.45 ms per token, 2.40 tokens per second) 8.52.636.543 I slot print_timing: id 0 | task 5877 | total time = 7907.77 ms / 881 tokens 8.52.636.544 I slot print_timing: id 0 | task 5877 | graphs reused = 4511 8.52.636.544 I slot print_timing: id 0 | task 5877 | graph reallocs = 0 / 0 (same size) / (changed size) 8.52.636.613 I slot release: id 0 | task 5877 | stop processing: n_tokens = 889, truncated = 0 8.52.637.737 I slot print_timing: id 1 | task 5878 | prompt eval time = 7491.40 ms / 896 tokens ( 8.36 ms per token, 119.60 tokens per second) 8.52.637.743 I slot print_timing: id 1 | task 5878 | eval time = 417.39 ms / 2 tokens ( 417.39 ms per token, 2.40 tokens per second) 8.52.637.743 I slot print_timing: id 1 | task 5878 | total time = 7908.79 ms / 898 tokens 8.52.637.744 I slot print_timing: id 1 | task 5878 | graphs reused = 4511 8.52.637.744 I slot print_timing: id 1 | task 5878 | graph reallocs = 0 / 0 (same size) / (changed size) 8.52.637.787 I slot release: id 1 | task 5878 | stop processing: n_tokens = 906, truncated = 0 8.52.638.952 I slot print_timing: id 2 | task 5879 | prompt eval time = 7492.53 ms / 1099 tokens ( 6.82 ms per token, 146.68 tokens per second) 8.52.638.955 I slot print_timing: id 2 | task 5879 | eval time = 417.32 ms / 2 tokens ( 417.32 ms per token, 2.40 tokens per second) 8.52.638.955 I slot print_timing: id 2 | task 5879 | total time = 7909.85 ms / 1101 tokens 8.52.638.956 I slot print_timing: id 2 | task 5879 | graphs reused = 4511 8.52.638.956 I slot print_timing: id 2 | task 5879 | graph reallocs = 0 / 0 (same size) / (changed size) 8.52.639.002 I slot release: id 2 | task 5879 | stop processing: n_tokens = 1109, truncated = 0 8.52.639.013 I slot print_timing: id 3 | task 5882 | prompt processing, n_tokens = 1085, progress = 1.00, t = 3.16 s / 342.94 tokens per second 8.52.676.722 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.894 8.52.676.781 I slot launch_slot_: id 2 | task 5887 | processing task, is_child = 0 8.52.676.861 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.694 MiB) 8.52.682.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.451 MiB) 8.52.688.503 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 329187920717 8.52.688.637 I slot launch_slot_: id 0 | task 5888 | processing task, is_child = 0 8.52.688.705 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 906, t_last = 329187921891 8.52.688.818 I slot launch_slot_: id 1 | task 5889 | processing task, is_child = 0 8.54.988.149 I slot print_timing: id 3 | task 5882 | prompt eval time = 3205.13 ms / 1089 tokens ( 2.94 ms per token, 339.77 tokens per second) 8.54.988.152 I slot print_timing: id 3 | task 5882 | eval time = 2311.42 ms / 2 tokens ( 2311.42 ms per token, 0.43 tokens per second) 8.54.988.153 I slot print_timing: id 3 | task 5882 | total time = 5516.55 ms / 1091 tokens 8.54.988.153 I slot print_timing: id 3 | task 5882 | graphs reused = 4511 8.54.988.154 I slot print_timing: id 3 | task 5882 | graph reallocs = 0 / 0 (same size) / (changed size) 8.54.988.242 I slot release: id 3 | task 5882 | stop processing: n_tokens = 1099, truncated = 0 8.56.325.818 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.901 8.56.325.993 I slot launch_slot_: id 3 | task 5892 | processing task, is_child = 0 8.56.326.010 I slot print_timing: id 0 | task 5888 | prompt processing, n_tokens = 909, progress = 0.84, t = 3.64 s / 250.01 tokens per second 8.56.329.652 I slot print_timing: id 1 | task 5889 | prompt processing, n_tokens = 909, progress = 0.83, t = 3.64 s / 250.03 tokens per second 8.57.309.773 I slot print_timing: id 2 | task 5887 | prompt eval time = 3636.60 ms / 96 tokens ( 37.88 ms per token, 26.40 tokens per second) 8.57.309.777 I slot print_timing: id 2 | task 5887 | eval time = 983.97 ms / 2 tokens ( 983.97 ms per token, 1.02 tokens per second) 8.57.309.777 I slot print_timing: id 2 | task 5887 | total time = 4620.57 ms / 98 tokens 8.57.309.778 I slot print_timing: id 2 | task 5887 | graphs reused = 4511 8.57.309.778 I slot print_timing: id 2 | task 5887 | graph reallocs = 0 / 0 (same size) / (changed size) 8.57.309.821 I slot release: id 2 | task 5887 | stop processing: n_tokens = 1088, truncated = 0 8.57.309.833 I slot print_timing: id 0 | task 5888 | prompt processing, n_tokens = 1083, progress = 1.00, t = 4.62 s / 234.42 tokens per second 8.57.314.036 I slot print_timing: id 1 | task 5889 | prompt processing, n_tokens = 1088, progress = 1.00, t = 4.62 s / 235.52 tokens per second 8.57.390.889 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.911 8.57.390.972 I slot launch_slot_: id 2 | task 5895 | processing task, is_child = 0 8.57.647.123 I slot print_timing: id 0 | task 5888 | prompt eval time = 4699.78 ms / 1087 tokens ( 4.32 ms per token, 231.29 tokens per second) 8.57.647.126 I slot print_timing: id 0 | task 5888 | eval time = 258.51 ms / 2 tokens ( 258.51 ms per token, 3.87 tokens per second) 8.57.647.127 I slot print_timing: id 0 | task 5888 | total time = 4958.29 ms / 1089 tokens 8.57.647.127 I slot print_timing: id 0 | task 5888 | graphs reused = 4511 8.57.647.128 I slot print_timing: id 0 | task 5888 | graph reallocs = 0 / 0 (same size) / (changed size) 8.57.647.207 I slot release: id 0 | task 5888 | stop processing: n_tokens = 1097, truncated = 0 8.57.648.329 I slot print_timing: id 1 | task 5889 | prompt eval time = 4700.70 ms / 1092 tokens ( 4.30 ms per token, 232.31 tokens per second) 8.57.648.333 I slot print_timing: id 1 | task 5889 | eval time = 258.60 ms / 2 tokens ( 258.60 ms per token, 3.87 tokens per second) 8.57.648.333 I slot print_timing: id 1 | task 5889 | total time = 4959.30 ms / 1094 tokens 8.57.648.334 I slot print_timing: id 1 | task 5889 | graphs reused = 4511 8.57.648.334 I slot print_timing: id 1 | task 5889 | graph reallocs = 0 / 0 (same size) / (changed size) 8.57.648.374 I slot release: id 1 | task 5889 | stop processing: n_tokens = 1102, truncated = 0 8.57.649.545 I slot print_timing: id 3 | task 5892 | prompt eval time = 1059.55 ms / 106 tokens ( 10.00 ms per token, 100.04 tokens per second) 8.57.649.547 I slot print_timing: id 3 | task 5892 | eval time = 258.66 ms / 2 tokens ( 258.66 ms per token, 3.87 tokens per second) 8.57.649.547 I slot print_timing: id 3 | task 5892 | total time = 1318.21 ms / 108 tokens 8.57.649.548 I slot print_timing: id 3 | task 5892 | graphs reused = 4511 8.57.649.548 I slot print_timing: id 3 | task 5892 | graph reallocs = 0 / 0 (same size) / (changed size) 8.57.649.581 I slot release: id 3 | task 5892 | stop processing: n_tokens = 1097, truncated = 0 8.57.687.281 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.903 8.57.687.341 I slot launch_slot_: id 0 | task 5898 | processing task, is_child = 0 8.57.687.429 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.356 MiB) 8.57.694.078 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 338.646 MiB) 8.57.701.705 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.899 8.57.701.766 I slot launch_slot_: id 1 | task 5899 | processing task, is_child = 0 8.57.701.857 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.903 8.57.701.895 I slot launch_slot_: id 3 | task 5900 | processing task, is_child = 0 8.58.457.101 I slot print_timing: id 2 | task 5895 | prompt eval time = 296.30 ms / 98 tokens ( 3.02 ms per token, 330.75 tokens per second) 8.58.457.104 I slot print_timing: id 2 | task 5895 | eval time = 769.82 ms / 2 tokens ( 769.82 ms per token, 1.30 tokens per second) 8.58.457.105 I slot print_timing: id 2 | task 5895 | total time = 1066.12 ms / 100 tokens 8.58.457.105 I slot print_timing: id 2 | task 5895 | graphs reused = 4511 8.58.457.106 I slot print_timing: id 2 | task 5895 | graph reallocs = 0 / 0 (same size) / (changed size) 8.58.457.151 I slot release: id 2 | task 5895 | stop processing: n_tokens = 1090, truncated = 0 8.58.546.189 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.909 8.58.546.282 I slot launch_slot_: id 2 | task 5903 | processing task, is_child = 0 8.58.802.880 I slot print_timing: id 0 | task 5898 | prompt eval time = 842.08 ms / 114 tokens ( 7.39 ms per token, 135.38 tokens per second) 8.58.802.883 I slot print_timing: id 0 | task 5898 | eval time = 258.89 ms / 2 tokens ( 258.89 ms per token, 3.86 tokens per second) 8.58.802.884 I slot print_timing: id 0 | task 5898 | total time = 1100.97 ms / 116 tokens 8.58.802.885 I slot print_timing: id 0 | task 5898 | graphs reused = 4511 8.58.802.885 I slot print_timing: id 0 | task 5898 | graph reallocs = 0 / 0 (same size) / (changed size) 8.58.802.964 I slot release: id 0 | task 5898 | stop processing: n_tokens = 1106, truncated = 0 8.58.804.079 I slot print_timing: id 1 | task 5899 | prompt eval time = 841.40 ms / 107 tokens ( 7.86 ms per token, 127.17 tokens per second) 8.58.804.082 I slot print_timing: id 1 | task 5899 | eval time = 258.96 ms / 2 tokens ( 258.96 ms per token, 3.86 tokens per second) 8.58.804.083 I slot print_timing: id 1 | task 5899 | total time = 1100.36 ms / 109 tokens 8.58.804.083 I slot print_timing: id 1 | task 5899 | graphs reused = 4511 8.58.804.083 I slot print_timing: id 1 | task 5899 | graph reallocs = 0 / 0 (same size) / (changed size) 8.58.804.119 I slot release: id 1 | task 5899 | stop processing: n_tokens = 1099, truncated = 0 8.58.805.296 I slot print_timing: id 3 | task 5900 | prompt eval time = 840.69 ms / 108 tokens ( 7.78 ms per token, 128.47 tokens per second) 8.58.805.298 I slot print_timing: id 3 | task 5900 | eval time = 259.10 ms / 2 tokens ( 259.10 ms per token, 3.86 tokens per second) 8.58.805.298 I slot print_timing: id 3 | task 5900 | total time = 1099.79 ms / 110 tokens 8.58.805.298 I slot print_timing: id 3 | task 5900 | graphs reused = 4511 8.58.805.299 I slot print_timing: id 3 | task 5900 | graph reallocs = 0 / 0 (same size) / (changed size) 8.58.805.333 I slot release: id 3 | task 5900 | stop processing: n_tokens = 1100, truncated = 0 8.58.842.794 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.896 8.58.842.853 I slot launch_slot_: id 0 | task 5906 | processing task, is_child = 0 8.58.842.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 345.574 MiB) 8.58.850.525 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 288.402 MiB) 8.58.864.105 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.902 8.58.864.188 I slot launch_slot_: id 1 | task 5907 | processing task, is_child = 0 8.58.864.270 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.901 8.58.864.308 I slot launch_slot_: id 3 | task 5908 | processing task, is_child = 0 8.59.614.254 I slot print_timing: id 2 | task 5903 | prompt eval time = 296.50 ms / 100 tokens ( 2.96 ms per token, 337.27 tokens per second) 8.59.614.257 I slot print_timing: id 2 | task 5903 | eval time = 771.46 ms / 2 tokens ( 771.46 ms per token, 1.30 tokens per second) 8.59.614.257 I slot print_timing: id 2 | task 5903 | total time = 1067.96 ms / 102 tokens 8.59.614.258 I slot print_timing: id 2 | task 5903 | graphs reused = 4511 8.59.614.258 I slot print_timing: id 2 | task 5903 | graph reallocs = 0 / 0 (same size) / (changed size) 8.59.614.303 I slot release: id 2 | task 5903 | stop processing: n_tokens = 1092, truncated = 0 8.59.695.070 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.908 8.59.695.167 I slot launch_slot_: id 2 | task 5911 | processing task, is_child = 0 9.00.002.828 I slot print_timing: id 0 | task 5906 | prompt eval time = 828.43 ms / 105 tokens ( 7.89 ms per token, 126.75 tokens per second) 9.00.002.831 I slot print_timing: id 0 | task 5906 | eval time = 310.08 ms / 2 tokens ( 310.08 ms per token, 3.22 tokens per second) 9.00.002.831 I slot print_timing: id 0 | task 5906 | total time = 1138.51 ms / 107 tokens 9.00.002.832 I slot print_timing: id 0 | task 5906 | graphs reused = 4511 9.00.002.832 I slot print_timing: id 0 | task 5906 | graph reallocs = 0 / 0 (same size) / (changed size) 9.00.002.880 I slot release: id 0 | task 5906 | stop processing: n_tokens = 1097, truncated = 0 9.00.003.964 I slot print_timing: id 1 | task 5907 | prompt eval time = 827.84 ms / 102 tokens ( 8.12 ms per token, 123.21 tokens per second) 9.00.003.967 I slot print_timing: id 1 | task 5907 | eval time = 310.10 ms / 2 tokens ( 310.10 ms per token, 3.22 tokens per second) 9.00.003.968 I slot print_timing: id 1 | task 5907 | total time = 1137.94 ms / 104 tokens 9.00.003.968 I slot print_timing: id 1 | task 5907 | graphs reused = 4511 9.00.003.968 I slot print_timing: id 1 | task 5907 | graph reallocs = 0 / 0 (same size) / (changed size) 9.00.004.001 I slot release: id 1 | task 5907 | stop processing: n_tokens = 1094, truncated = 0 9.00.005.183 I slot print_timing: id 3 | task 5908 | prompt eval time = 827.34 ms / 104 tokens ( 7.96 ms per token, 125.70 tokens per second) 9.00.005.184 I slot print_timing: id 3 | task 5908 | eval time = 310.12 ms / 2 tokens ( 310.12 ms per token, 3.22 tokens per second) 9.00.005.185 I slot print_timing: id 3 | task 5908 | total time = 1137.45 ms / 106 tokens 9.00.005.185 I slot print_timing: id 3 | task 5908 | graphs reused = 4511 9.00.005.185 I slot print_timing: id 3 | task 5908 | graph reallocs = 0 / 0 (same size) / (changed size) 9.00.005.215 I slot release: id 3 | task 5908 | stop processing: n_tokens = 1096, truncated = 0 9.00.042.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1097, t_last = 329195286984 9.00.043.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.832 MiB) 9.00.051.168 I slot launch_slot_: id 0 | task 5914 | processing task, is_child = 0 9.00.051.259 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.104 MiB) 9.00.061.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.275 MiB) 9.00.061.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.040 MiB) 9.00.070.303 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1094, t_last = 329195288105 9.00.070.460 I slot launch_slot_: id 1 | task 5915 | processing task, is_child = 0 9.00.070.536 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1096, t_last = 329195289319 9.00.070.639 I slot launch_slot_: id 3 | task 5916 | processing task, is_child = 0 9.02.969.817 I slot print_timing: id 2 | task 5911 | prompt eval time = 347.78 ms / 103 tokens ( 3.38 ms per token, 296.17 tokens per second) 9.02.969.820 I slot print_timing: id 2 | task 5911 | eval time = 2926.86 ms / 2 tokens ( 2926.86 ms per token, 0.34 tokens per second) 9.02.969.821 I slot print_timing: id 2 | task 5911 | total time = 3274.64 ms / 105 tokens 9.02.969.821 I slot print_timing: id 2 | task 5911 | graphs reused = 4511 9.02.969.822 I slot print_timing: id 2 | task 5911 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.969.875 I slot release: id 2 | task 5911 | stop processing: n_tokens = 1095, truncated = 0 9.04.424.052 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1095, t_last = 329198253979 9.04.424.153 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.102 MiB) 9.04.969.882 I slot launch_slot_: id 2 | task 5919 | processing task, is_child = 0 9.04.969.902 I slot print_timing: id 0 | task 5914 | prompt processing, n_tokens = 861, progress = 0.84, t = 4.35 s / 197.78 tokens per second 9.04.972.477 I slot print_timing: id 1 | task 5915 | prompt processing, n_tokens = 861, progress = 0.86, t = 4.35 s / 197.79 tokens per second 9.04.974.375 I slot print_timing: id 3 | task 5916 | prompt processing, n_tokens = 861, progress = 0.79, t = 4.35 s / 197.80 tokens per second 9.06.455.298 I slot print_timing: id 0 | task 5914 | prompt processing, n_tokens = 1017, progress = 1.00, t = 6.38 s / 159.29 tokens per second 9.07.042.060 I slot print_timing: id 1 | task 5915 | prompt processing, n_tokens = 996, progress = 1.00, t = 6.38 s / 156.00 tokens per second 9.07.046.141 I slot print_timing: id 3 | task 5916 | prompt processing, n_tokens = 1087, progress = 1.00, t = 6.38 s / 170.26 tokens per second 9.08.148.445 I slot print_timing: id 0 | task 5914 | prompt eval time = 7638.43 ms / 1021 tokens ( 7.48 ms per token, 133.67 tokens per second) 9.08.148.448 I slot print_timing: id 0 | task 5914 | eval time = 439.37 ms / 2 tokens ( 439.37 ms per token, 2.28 tokens per second) 9.08.148.448 I slot print_timing: id 0 | task 5914 | total time = 8077.80 ms / 1023 tokens 9.08.148.449 I slot print_timing: id 0 | task 5914 | graphs reused = 4511 9.08.148.449 I slot print_timing: id 0 | task 5914 | graph reallocs = 0 / 0 (same size) / (changed size) 9.08.148.501 I slot release: id 0 | task 5914 | stop processing: n_tokens = 1031, truncated = 0 9.08.149.592 I slot print_timing: id 1 | task 5915 | prompt eval time = 7639.37 ms / 1000 tokens ( 7.64 ms per token, 130.90 tokens per second) 9.08.149.596 I slot print_timing: id 1 | task 5915 | eval time = 439.35 ms / 2 tokens ( 439.35 ms per token, 2.28 tokens per second) 9.08.149.597 I slot print_timing: id 1 | task 5915 | total time = 8078.72 ms / 1002 tokens 9.08.149.598 I slot print_timing: id 1 | task 5915 | graphs reused = 4511 9.08.149.598 I slot print_timing: id 1 | task 5915 | graph reallocs = 0 / 0 (same size) / (changed size) 9.08.149.653 I slot release: id 1 | task 5915 | stop processing: n_tokens = 1010, truncated = 0 9.08.150.771 I slot print_timing: id 3 | task 5916 | prompt eval time = 7640.33 ms / 1091 tokens ( 7.00 ms per token, 142.79 tokens per second) 9.08.150.774 I slot print_timing: id 3 | task 5916 | eval time = 439.36 ms / 2 tokens ( 439.36 ms per token, 2.28 tokens per second) 9.08.150.774 I slot print_timing: id 3 | task 5916 | total time = 8079.69 ms / 1093 tokens 9.08.150.775 I slot print_timing: id 3 | task 5916 | graphs reused = 4511 9.08.150.775 I slot print_timing: id 3 | task 5916 | graph reallocs = 0 / 0 (same size) / (changed size) 9.08.150.816 I slot release: id 3 | task 5916 | stop processing: n_tokens = 1101, truncated = 0 9.08.150.828 I slot print_timing: id 2 | task 5919 | prompt processing, n_tokens = 1051, progress = 1.00, t = 3.17 s / 331.21 tokens per second 9.08.188.785 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 329203432605 9.08.188.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 222.855 MiB) 9.08.195.252 I slot launch_slot_: id 0 | task 5924 | processing task, is_child = 0 9.08.195.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.063 MiB) 9.08.201.674 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 222.433 MiB) 9.08.207.987 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.888 9.08.208.045 I slot launch_slot_: id 1 | task 5925 | processing task, is_child = 0 9.08.208.124 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.863 (> 0.100 thold), f_keep = 0.815 9.08.208.159 I slot launch_slot_: id 3 | task 5926 | processing task, is_child = 0 9.09.268.517 I slot print_timing: id 2 | task 5919 | prompt eval time = 3214.64 ms / 1055 tokens ( 3.05 ms per token, 328.19 tokens per second) 9.09.268.519 I slot print_timing: id 2 | task 5919 | eval time = 1079.73 ms / 2 tokens ( 1079.73 ms per token, 0.93 tokens per second) 9.09.268.520 I slot print_timing: id 2 | task 5919 | total time = 4294.37 ms / 1057 tokens 9.09.268.520 I slot print_timing: id 2 | task 5919 | graphs reused = 4511 9.09.268.521 I slot print_timing: id 2 | task 5919 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.268.575 I slot release: id 2 | task 5919 | stop processing: n_tokens = 1065, truncated = 0 9.10.044.345 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1065, t_last = 329204552679 9.10.044.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 223.839 MiB) 9.10.056.018 I slot launch_slot_: id 2 | task 5929 | processing task, is_child = 0 9.10.926.520 I slot print_timing: id 1 | task 5925 | prompt eval time = 1834.80 ms / 122 tokens ( 15.04 ms per token, 66.49 tokens per second) 9.10.926.523 I slot print_timing: id 1 | task 5925 | eval time = 883.32 ms / 2 tokens ( 883.32 ms per token, 1.13 tokens per second) 9.10.926.523 I slot print_timing: id 1 | task 5925 | total time = 2718.12 ms / 124 tokens 9.10.926.524 I slot print_timing: id 1 | task 5925 | graphs reused = 4511 9.10.926.524 I slot print_timing: id 1 | task 5925 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.926.585 I slot release: id 1 | task 5925 | stop processing: n_tokens = 1020, truncated = 0 9.10.927.738 I slot print_timing: id 3 | task 5926 | prompt eval time = 1834.26 ms / 143 tokens ( 12.83 ms per token, 77.96 tokens per second) 9.10.927.742 I slot print_timing: id 3 | task 5926 | eval time = 883.40 ms / 2 tokens ( 883.40 ms per token, 1.13 tokens per second) 9.10.927.743 I slot print_timing: id 3 | task 5926 | total time = 2717.65 ms / 145 tokens 9.10.927.743 I slot print_timing: id 3 | task 5926 | graphs reused = 4511 9.10.927.744 I slot print_timing: id 3 | task 5926 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.927.790 I slot release: id 3 | task 5926 | stop processing: n_tokens = 1041, truncated = 0 9.11.606.384 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1020, t_last = 329206210689 9.11.606.518 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 228.481 MiB) 9.11.606.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 227.356 MiB) 9.11.619.707 I slot launch_slot_: id 1 | task 5932 | processing task, is_child = 0 9.11.619.791 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 237.342 MiB) 9.11.631.606 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 329206211894 9.11.631.738 I slot launch_slot_: id 3 | task 5933 | processing task, is_child = 0 9.12.796.747 I slot print_timing: id 0 | task 5924 | prompt eval time = 3398.20 ms / 745 tokens ( 4.56 ms per token, 219.23 tokens per second) 9.12.796.751 I slot print_timing: id 0 | task 5924 | eval time = 1190.37 ms / 2 tokens ( 1190.37 ms per token, 0.84 tokens per second) 9.12.796.751 I slot print_timing: id 0 | task 5924 | total time = 4588.57 ms / 747 tokens 9.12.796.752 I slot print_timing: id 0 | task 5924 | graphs reused = 4511 9.12.796.752 I slot print_timing: id 0 | task 5924 | graph reallocs = 0 / 0 (same size) / (changed size) 9.12.796.836 I slot release: id 0 | task 5924 | stop processing: n_tokens = 755, truncated = 0 9.14.358.658 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 9.14.358.823 I slot launch_slot_: id 0 | task 5936 | processing task, is_child = 0 9.15.106.506 I slot print_timing: id 2 | task 5929 | prompt eval time = 4300.92 ms / 787 tokens ( 5.46 ms per token, 182.98 tokens per second) 9.15.106.509 I slot print_timing: id 2 | task 5929 | eval time = 747.87 ms / 2 tokens ( 747.87 ms per token, 1.34 tokens per second) 9.15.106.509 I slot print_timing: id 2 | task 5929 | total time = 5048.79 ms / 789 tokens 9.15.106.510 I slot print_timing: id 2 | task 5929 | graphs reused = 4511 9.15.106.510 I slot print_timing: id 2 | task 5929 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.106.577 I slot release: id 2 | task 5929 | stop processing: n_tokens = 797, truncated = 0 9.15.110.213 I slot print_timing: id 1 | task 5932 | prompt processing, n_tokens = 726, progress = 0.99, t = 3.47 s / 209.00 tokens per second 9.15.112.219 I slot print_timing: id 3 | task 5933 | prompt processing, n_tokens = 713, progress = 0.99, t = 3.47 s / 205.37 tokens per second 9.15.186.401 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.813 9.15.186.493 I slot launch_slot_: id 2 | task 5939 | processing task, is_child = 0 9.15.437.253 I slot print_timing: id 0 | task 5936 | prompt eval time = 825.21 ms / 97 tokens ( 8.51 ms per token, 117.55 tokens per second) 9.15.437.255 I slot print_timing: id 0 | task 5936 | eval time = 253.20 ms / 2 tokens ( 253.20 ms per token, 3.95 tokens per second) 9.15.437.256 I slot print_timing: id 0 | task 5936 | total time = 1078.41 ms / 99 tokens 9.15.437.256 I slot print_timing: id 0 | task 5936 | graphs reused = 4511 9.15.437.257 I slot print_timing: id 0 | task 5936 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.437.321 I slot release: id 0 | task 5936 | stop processing: n_tokens = 746, truncated = 0 9.15.438.453 I slot print_timing: id 1 | task 5932 | prompt eval time = 3553.42 ms / 730 tokens ( 4.87 ms per token, 205.44 tokens per second) 9.15.438.459 I slot print_timing: id 1 | task 5932 | eval time = 253.29 ms / 2 tokens ( 253.29 ms per token, 3.95 tokens per second) 9.15.438.460 I slot print_timing: id 1 | task 5932 | total time = 3806.71 ms / 732 tokens 9.15.438.460 I slot print_timing: id 1 | task 5932 | graphs reused = 4511 9.15.438.460 I slot print_timing: id 1 | task 5932 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.438.492 I slot release: id 1 | task 5932 | stop processing: n_tokens = 740, truncated = 0 9.15.439.622 I slot print_timing: id 3 | task 5933 | prompt eval time = 3552.76 ms / 717 tokens ( 4.96 ms per token, 201.82 tokens per second) 9.15.439.624 I slot print_timing: id 3 | task 5933 | eval time = 253.23 ms / 2 tokens ( 253.23 ms per token, 3.95 tokens per second) 9.15.439.624 I slot print_timing: id 3 | task 5933 | total time = 3805.98 ms / 719 tokens 9.15.439.624 I slot print_timing: id 3 | task 5933 | graphs reused = 4511 9.15.439.625 I slot print_timing: id 3 | task 5933 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.439.652 I slot release: id 3 | task 5933 | stop processing: n_tokens = 727, truncated = 0 9.15.475.788 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.869 9.15.475.845 I slot launch_slot_: id 0 | task 5942 | processing task, is_child = 0 9.15.475.923 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.498 MiB) 9.15.481.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.206 MiB) 9.15.486.528 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.861 (> 0.100 thold), f_keep = 0.876 9.15.486.581 I slot launch_slot_: id 1 | task 5943 | processing task, is_child = 0 9.15.486.649 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.891 9.15.486.682 I slot launch_slot_: id 3 | task 5944 | processing task, is_child = 0 9.16.112.680 I slot print_timing: id 2 | task 5939 | prompt eval time = 289.29 ms / 89 tokens ( 3.25 ms per token, 307.66 tokens per second) 9.16.112.684 I slot print_timing: id 2 | task 5939 | eval time = 636.89 ms / 2 tokens ( 636.89 ms per token, 1.57 tokens per second) 9.16.112.684 I slot print_timing: id 2 | task 5939 | total time = 926.17 ms / 91 tokens 9.16.112.684 I slot print_timing: id 2 | task 5939 | graphs reused = 4511 9.16.112.685 I slot print_timing: id 2 | task 5939 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.112.754 I slot release: id 2 | task 5939 | stop processing: n_tokens = 738, truncated = 0 9.16.192.841 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 329211396858 9.16.192.919 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 206.821 MiB) 9.16.199.632 I slot launch_slot_: id 2 | task 5947 | processing task, is_child = 0 9.17.100.597 I slot print_timing: id 0 | task 5942 | prompt eval time = 703.84 ms / 84 tokens ( 8.38 ms per token, 119.35 tokens per second) 9.17.100.600 I slot print_timing: id 0 | task 5942 | eval time = 910.07 ms / 2 tokens ( 910.07 ms per token, 1.10 tokens per second) 9.17.100.600 I slot print_timing: id 0 | task 5942 | total time = 1613.90 ms / 86 tokens 9.17.100.601 I slot print_timing: id 0 | task 5942 | graphs reused = 4511 9.17.100.601 I slot print_timing: id 0 | task 5942 | graph reallocs = 0 / 0 (same size) / (changed size) 9.17.100.663 I slot release: id 0 | task 5942 | stop processing: n_tokens = 733, truncated = 0 9.17.101.796 I slot print_timing: id 1 | task 5943 | prompt eval time = 703.26 ms / 105 tokens ( 6.70 ms per token, 149.30 tokens per second) 9.17.101.800 I slot print_timing: id 1 | task 5943 | eval time = 910.15 ms / 2 tokens ( 910.15 ms per token, 1.10 tokens per second) 9.17.101.800 I slot print_timing: id 1 | task 5943 | total time = 1613.41 ms / 107 tokens 9.17.101.801 I slot print_timing: id 1 | task 5943 | graphs reused = 4511 9.17.101.801 I slot print_timing: id 1 | task 5943 | graph reallocs = 0 / 0 (same size) / (changed size) 9.17.101.838 I slot release: id 1 | task 5943 | stop processing: n_tokens = 754, truncated = 0 9.17.102.983 I slot print_timing: id 3 | task 5944 | prompt eval time = 702.78 ms / 100 tokens ( 7.03 ms per token, 142.29 tokens per second) 9.17.102.989 I slot print_timing: id 3 | task 5944 | eval time = 910.15 ms / 2 tokens ( 910.15 ms per token, 1.10 tokens per second) 9.17.102.989 I slot print_timing: id 3 | task 5944 | total time = 1612.93 ms / 102 tokens 9.17.102.989 I slot print_timing: id 3 | task 5944 | graphs reused = 4511 9.17.102.990 I slot print_timing: id 3 | task 5944 | graph reallocs = 0 / 0 (same size) / (changed size) 9.17.103.015 I slot release: id 3 | task 5944 | stop processing: n_tokens = 749, truncated = 0 9.17.763.338 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 733, t_last = 329212384767 9.17.763.444 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 226.512 MiB) 9.18.140.122 I slot launch_slot_: id 0 | task 5951 | processing task, is_child = 0 9.18.140.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.747 MiB) 9.18.147.458 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.385 MiB) 9.18.154.193 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 329212385942 9.18.154.323 I slot launch_slot_: id 1 | task 5952 | processing task, is_child = 0 9.18.154.385 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 749, t_last = 329212387119 9.18.154.483 I slot launch_slot_: id 3 | task 5953 | processing task, is_child = 0 9.22.794.321 I slot print_timing: id 2 | task 5947 | prompt eval time = 4568.93 ms / 985 tokens ( 4.64 ms per token, 215.59 tokens per second) 9.22.794.327 I slot print_timing: id 2 | task 5947 | eval time = 2025.73 ms / 2 tokens ( 2025.73 ms per token, 0.49 tokens per second) 9.22.794.327 I slot print_timing: id 2 | task 5947 | total time = 6594.67 ms / 987 tokens 9.22.794.328 I slot print_timing: id 2 | task 5947 | graphs reused = 4511 9.22.794.329 I slot print_timing: id 2 | task 5947 | graph reallocs = 0 / 0 (same size) / (changed size) 9.22.794.421 I slot release: id 2 | task 5947 | stop processing: n_tokens = 995, truncated = 0 9.22.794.448 I slot print_timing: id 0 | task 5951 | prompt processing, n_tokens = 812, progress = 0.84, t = 4.64 s / 175.05 tokens per second 9.22.797.574 I slot print_timing: id 1 | task 5952 | prompt processing, n_tokens = 812, progress = 0.86, t = 4.64 s / 175.06 tokens per second 9.22.799.511 I slot print_timing: id 3 | task 5953 | prompt processing, n_tokens = 812, progress = 0.78, t = 4.64 s / 175.13 tokens per second 9.23.433.362 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 329218078526 9.23.433.446 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.416 MiB) 9.23.433.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 212.588 MiB) 9.23.918.058 I slot launch_slot_: id 2 | task 5957 | processing task, is_child = 0 9.23.918.072 I slot print_timing: id 0 | task 5951 | prompt processing, n_tokens = 963, progress = 1.00, t = 5.28 s / 182.43 tokens per second 9.23.920.089 I slot print_timing: id 1 | task 5952 | prompt processing, n_tokens = 946, progress = 1.00, t = 5.28 s / 179.21 tokens per second 9.23.922.290 I slot print_timing: id 3 | task 5953 | prompt processing, n_tokens = 1039, progress = 1.00, t = 5.28 s / 196.90 tokens per second 9.25.851.995 I slot print_timing: id 0 | task 5951 | prompt eval time = 6926.42 ms / 967 tokens ( 7.16 ms per token, 139.61 tokens per second) 9.25.852.001 I slot print_timing: id 0 | task 5951 | eval time = 771.07 ms / 2 tokens ( 771.07 ms per token, 1.30 tokens per second) 9.25.852.002 I slot print_timing: id 0 | task 5951 | total time = 7697.50 ms / 969 tokens 9.25.852.002 I slot print_timing: id 0 | task 5951 | graphs reused = 4511 9.25.852.003 I slot print_timing: id 0 | task 5951 | graph reallocs = 0 / 0 (same size) / (changed size) 9.25.852.080 I slot release: id 0 | task 5951 | stop processing: n_tokens = 977, truncated = 0 9.25.853.210 I slot print_timing: id 1 | task 5952 | prompt eval time = 6927.43 ms / 950 tokens ( 7.29 ms per token, 137.14 tokens per second) 9.25.853.214 I slot print_timing: id 1 | task 5952 | eval time = 771.08 ms / 2 tokens ( 771.08 ms per token, 1.30 tokens per second) 9.25.853.214 I slot print_timing: id 1 | task 5952 | total time = 7698.51 ms / 952 tokens 9.25.853.214 I slot print_timing: id 1 | task 5952 | graphs reused = 4511 9.25.853.215 I slot print_timing: id 1 | task 5952 | graph reallocs = 0 / 0 (same size) / (changed size) 9.25.853.267 I slot release: id 1 | task 5952 | stop processing: n_tokens = 960, truncated = 0 9.25.854.404 I slot print_timing: id 3 | task 5953 | prompt eval time = 6926.66 ms / 1043 tokens ( 6.64 ms per token, 150.58 tokens per second) 9.25.854.406 I slot print_timing: id 3 | task 5953 | eval time = 771.06 ms / 2 tokens ( 771.06 ms per token, 1.30 tokens per second) 9.25.854.407 I slot print_timing: id 3 | task 5953 | total time = 7697.71 ms / 1045 tokens 9.25.854.407 I slot print_timing: id 3 | task 5953 | graphs reused = 4511 9.25.854.407 I slot print_timing: id 3 | task 5953 | graph reallocs = 0 / 0 (same size) / (changed size) 9.25.854.446 I slot release: id 3 | task 5953 | stop processing: n_tokens = 1053, truncated = 0 9.26.206.263 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 329221136184 9.26.206.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 209.212 MiB) 9.26.212.527 I slot launch_slot_: id 0 | task 5962 | processing task, is_child = 0 9.26.212.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.535 MiB) 9.26.218.621 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.394 MiB) 9.26.230.052 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 960, t_last = 329221137371 9.26.230.193 I slot launch_slot_: id 1 | task 5963 | processing task, is_child = 0 9.26.230.276 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 329221138550 9.26.230.383 I slot launch_slot_: id 3 | task 5964 | processing task, is_child = 0 9.30.014.320 I slot print_timing: id 2 | task 5957 | prompt eval time = 2284.18 ms / 1127 tokens ( 2.03 ms per token, 493.39 tokens per second) 9.30.014.323 I slot print_timing: id 2 | task 5957 | eval time = 3808.05 ms / 2 tokens ( 3808.05 ms per token, 0.26 tokens per second) 9.30.014.324 I slot print_timing: id 2 | task 5957 | total time = 6092.23 ms / 1129 tokens 9.30.014.325 I slot print_timing: id 2 | task 5957 | graphs reused = 4511 9.30.014.325 I slot print_timing: id 2 | task 5957 | graph reallocs = 0 / 0 (same size) / (changed size) 9.30.014.414 I slot release: id 2 | task 5957 | stop processing: n_tokens = 1137, truncated = 0 9.30.014.459 I slot print_timing: id 0 | task 5962 | prompt processing, n_tokens = 643, progress = 0.56, t = 3.78 s / 169.98 tokens per second 9.30.018.527 I slot print_timing: id 1 | task 5963 | prompt processing, n_tokens = 1404, progress = 0.66, t = 3.78 s / 371.18 tokens per second 9.32.949.057 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1137, t_last = 329225298518 9.32.949.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 264.801 MiB) 9.33.839.201 I slot launch_slot_: id 2 | task 5967 | processing task, is_child = 0 9.33.839.222 I slot print_timing: id 0 | task 5962 | prompt processing, n_tokens = 975, progress = 0.84, t = 6.72 s / 145.12 tokens per second 9.33.840.910 I slot print_timing: id 1 | task 5963 | prompt processing, n_tokens = 1616, progress = 0.76, t = 6.72 s / 240.53 tokens per second 9.36.984.872 I slot print_timing: id 0 | task 5962 | prompt processing, n_tokens = 1155, progress = 1.00, t = 10.75 s / 107.40 tokens per second 9.37.710.929 I slot print_timing: id 1 | task 5963 | prompt processing, n_tokens = 1795, progress = 0.84, t = 10.75 s / 166.91 tokens per second 9.37.713.415 I slot print_timing: id 2 | task 5967 | prompt processing, n_tokens = 1580, progress = 0.75, t = 3.14 s / 502.82 tokens per second 9.37.715.338 I slot print_timing: id 3 | task 5964 | prompt processing, n_tokens = 1613, progress = 0.76, t = 6.97 s / 231.54 tokens per second 9.39.309.652 I slot print_timing: id 1 | task 5963 | prompt processing, n_tokens = 2128, progress = 1.00, t = 13.08 s / 162.72 tokens per second 9.39.313.694 I slot print_timing: id 2 | task 5967 | prompt processing, n_tokens = 1795, progress = 0.86, t = 5.47 s / 328.40 tokens per second 9.39.316.752 I slot print_timing: id 3 | task 5964 | prompt processing, n_tokens = 1795, progress = 0.84, t = 9.29 s / 193.22 tokens per second 9.40.726.070 I slot print_timing: id 0 | task 5962 | prompt eval time = 13079.23 ms / 1159 tokens ( 11.28 ms per token, 88.61 tokens per second) 9.40.726.076 I slot print_timing: id 0 | task 5962 | eval time = 1416.44 ms / 2 tokens ( 1416.44 ms per token, 0.71 tokens per second) 9.40.726.076 I slot print_timing: id 0 | task 5962 | total time = 14495.67 ms / 1161 tokens 9.40.726.077 I slot print_timing: id 0 | task 5962 | graphs reused = 4511 9.40.726.077 I slot print_timing: id 0 | task 5962 | graph reallocs = 0 / 0 (same size) / (changed size) 9.40.726.152 I slot release: id 0 | task 5962 | stop processing: n_tokens = 1169, truncated = 0 9.40.727.435 I slot print_timing: id 2 | task 5967 | prompt processing, n_tokens = 2092, progress = 1.00, t = 6.88 s / 303.97 tokens per second 9.40.731.192 I slot print_timing: id 3 | task 5964 | prompt processing, n_tokens = 2125, progress = 1.00, t = 10.71 s / 198.48 tokens per second 9.40.804.088 I slot print_timing: id 1 | task 5963 | prompt eval time = 14496.80 ms / 2132 tokens ( 6.80 ms per token, 147.07 tokens per second) 9.40.804.090 I slot print_timing: id 1 | task 5963 | eval time = 76.67 ms / 2 tokens ( 76.67 ms per token, 13.04 tokens per second) 9.40.804.090 I slot print_timing: id 1 | task 5963 | total time = 14573.47 ms / 2134 tokens 9.40.804.091 I slot print_timing: id 1 | task 5963 | graphs reused = 4511 9.40.804.091 I slot print_timing: id 1 | task 5963 | graph reallocs = 0 / 0 (same size) / (changed size) 9.40.804.165 I slot release: id 1 | task 5963 | stop processing: n_tokens = 2142, truncated = 0 9.40.806.599 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 9.40.806.680 I slot launch_slot_: id 1 | task 5972 | processing task, is_child = 0 9.40.806.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.003 MiB) 9.40.818.936 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1169, t_last = 329236010256 9.40.819.101 I slot launch_slot_: id 0 | task 5973 | processing task, is_child = 0 9.44.373.031 I slot print_timing: id 2 | task 5967 | prompt eval time = 6962.73 ms / 2096 tokens ( 3.32 ms per token, 301.03 tokens per second) 9.44.373.036 I slot print_timing: id 2 | task 5967 | eval time = 3567.70 ms / 2 tokens ( 3567.70 ms per token, 0.28 tokens per second) 9.44.373.037 I slot print_timing: id 2 | task 5967 | total time = 10530.43 ms / 2098 tokens 9.44.373.038 I slot print_timing: id 2 | task 5967 | graphs reused = 4511 9.44.373.038 I slot print_timing: id 2 | task 5967 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.373.178 I slot release: id 2 | task 5967 | stop processing: n_tokens = 2106, truncated = 0 9.44.374.404 I slot print_timing: id 3 | task 5964 | prompt eval time = 10788.05 ms / 2129 tokens ( 5.07 ms per token, 197.35 tokens per second) 9.44.374.407 I slot print_timing: id 3 | task 5964 | eval time = 3567.81 ms / 2 tokens ( 3567.81 ms per token, 0.28 tokens per second) 9.44.374.408 I slot print_timing: id 3 | task 5964 | total time = 14355.86 ms / 2131 tokens 9.44.374.408 I slot print_timing: id 3 | task 5964 | graphs reused = 4511 9.44.374.409 I slot print_timing: id 3 | task 5964 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.374.490 I slot release: id 3 | task 5964 | stop processing: n_tokens = 2139, truncated = 0 9.44.374.520 I slot print_timing: id 0 | task 5973 | prompt processing, n_tokens = 1627, progress = 0.76, t = 3.55 s / 457.95 tokens per second 9.44.377.984 I slot print_timing: id 1 | task 5972 | prompt processing, n_tokens = 249, progress = 1.00, t = 3.55 s / 70.09 tokens per second 9.44.798.575 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.870 9.44.798.665 I slot launch_slot_: id 2 | task 5976 | processing task, is_child = 0 9.44.798.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.887 MiB) 9.44.816.607 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.869 (> 0.100 thold), f_keep = 0.856 9.44.816.662 I slot launch_slot_: id 3 | task 5977 | processing task, is_child = 0 9.44.816.669 I slot print_timing: id 0 | task 5973 | prompt processing, n_tokens = 1795, progress = 0.84, t = 3.98 s / 451.20 tokens per second 9.46.795.466 I slot print_timing: id 1 | task 5972 | prompt eval time = 3979.20 ms / 253 tokens ( 15.73 ms per token, 63.58 tokens per second) 9.46.795.468 I slot print_timing: id 1 | task 5972 | eval time = 1996.90 ms / 2 tokens ( 1996.90 ms per token, 0.50 tokens per second) 9.46.795.473 I slot print_timing: id 1 | task 5972 | total time = 5976.09 ms / 255 tokens 9.46.795.473 I slot print_timing: id 1 | task 5972 | graphs reused = 4511 9.46.795.474 I slot print_timing: id 1 | task 5972 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.795.634 I slot release: id 1 | task 5972 | stop processing: n_tokens = 2086, truncated = 0 9.46.795.661 I slot print_timing: id 0 | task 5973 | prompt processing, n_tokens = 2139, progress = 1.00, t = 5.98 s / 357.98 tokens per second 9.46.879.503 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 9.46.879.612 I slot launch_slot_: id 1 | task 5980 | processing task, is_child = 0 9.47.626.770 I slot print_timing: id 0 | task 5973 | prompt eval time = 6058.04 ms / 2143 tokens ( 2.83 ms per token, 353.75 tokens per second) 9.47.626.772 I slot print_timing: id 0 | task 5973 | eval time = 749.61 ms / 2 tokens ( 749.61 ms per token, 1.33 tokens per second) 9.47.626.775 I slot print_timing: id 0 | task 5973 | total time = 6807.65 ms / 2145 tokens 9.47.626.775 I slot print_timing: id 0 | task 5973 | graphs reused = 4511 9.47.626.776 I slot print_timing: id 0 | task 5973 | graph reallocs = 0 / 0 (same size) / (changed size) 9.47.626.923 I slot release: id 0 | task 5973 | stop processing: n_tokens = 2153, truncated = 0 9.47.628.138 I slot print_timing: id 2 | task 5976 | prompt eval time = 2059.89 ms / 344 tokens ( 5.99 ms per token, 167.00 tokens per second) 9.47.628.141 I slot print_timing: id 2 | task 5976 | eval time = 749.89 ms / 2 tokens ( 749.89 ms per token, 1.33 tokens per second) 9.47.628.142 I slot print_timing: id 2 | task 5976 | total time = 2809.78 ms / 346 tokens 9.47.628.142 I slot print_timing: id 2 | task 5976 | graphs reused = 4511 9.47.628.142 I slot print_timing: id 2 | task 5976 | graph reallocs = 0 / 0 (same size) / (changed size) 9.47.628.217 I slot release: id 2 | task 5976 | stop processing: n_tokens = 2177, truncated = 0 9.47.629.455 I slot print_timing: id 3 | task 5977 | prompt eval time = 2059.39 ms / 276 tokens ( 7.46 ms per token, 134.02 tokens per second) 9.47.629.457 I slot print_timing: id 3 | task 5977 | eval time = 749.96 ms / 2 tokens ( 749.96 ms per token, 1.33 tokens per second) 9.47.629.458 I slot print_timing: id 3 | task 5977 | total time = 2809.35 ms / 278 tokens 9.47.629.458 I slot print_timing: id 3 | task 5977 | graphs reused = 4511 9.47.629.458 I slot print_timing: id 3 | task 5977 | graph reallocs = 0 / 0 (same size) / (changed size) 9.47.629.509 I slot release: id 3 | task 5977 | stop processing: n_tokens = 2108, truncated = 0 9.47.667.157 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 9.47.667.213 I slot launch_slot_: id 0 | task 5983 | processing task, is_child = 0 9.47.667.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 234.529 MiB) 9.47.683.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.920 MiB) 9.47.702.340 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.842 9.47.702.407 I slot launch_slot_: id 2 | task 5984 | processing task, is_child = 0 9.47.702.521 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.806 (> 0.100 thold), f_keep = 0.869 9.47.702.559 I slot launch_slot_: id 3 | task 5985 | processing task, is_child = 0 9.49.483.543 I slot print_timing: id 1 | task 5980 | prompt eval time = 787.53 ms / 353 tokens ( 2.23 ms per token, 448.24 tokens per second) 9.49.483.556 I slot print_timing: id 1 | task 5980 | eval time = 1816.38 ms / 2 tokens ( 1816.38 ms per token, 0.55 tokens per second) 9.49.483.556 I slot print_timing: id 1 | task 5980 | total time = 2603.92 ms / 355 tokens 9.49.483.557 I slot print_timing: id 1 | task 5980 | graphs reused = 4511 9.49.483.558 I slot print_timing: id 1 | task 5980 | graph reallocs = 0 / 0 (same size) / (changed size) 9.49.483.709 I slot release: id 1 | task 5980 | stop processing: n_tokens = 2186, truncated = 0 9.49.567.324 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 9.49.567.391 I slot launch_slot_: id 1 | task 5988 | processing task, is_child = 0 9.50.080.765 I slot print_timing: id 0 | task 5983 | prompt eval time = 1862.51 ms / 189 tokens ( 9.85 ms per token, 101.48 tokens per second) 9.50.080.771 I slot print_timing: id 0 | task 5983 | eval time = 515.68 ms / 2 tokens ( 515.68 ms per token, 1.94 tokens per second) 9.50.080.771 I slot print_timing: id 0 | task 5983 | total time = 2378.19 ms / 191 tokens 9.50.080.772 I slot print_timing: id 0 | task 5983 | graphs reused = 4511 9.50.080.772 I slot print_timing: id 0 | task 5983 | graph reallocs = 0 / 0 (same size) / (changed size) 9.50.080.907 I slot release: id 0 | task 5983 | stop processing: n_tokens = 2022, truncated = 0 9.50.082.141 I slot print_timing: id 2 | task 5984 | prompt eval time = 1861.87 ms / 232 tokens ( 8.03 ms per token, 124.61 tokens per second) 9.50.082.144 I slot print_timing: id 2 | task 5984 | eval time = 515.95 ms / 2 tokens ( 515.95 ms per token, 1.94 tokens per second) 9.50.082.144 I slot print_timing: id 2 | task 5984 | total time = 2377.82 ms / 234 tokens 9.50.082.145 I slot print_timing: id 2 | task 5984 | graphs reused = 4511 9.50.082.145 I slot print_timing: id 2 | task 5984 | graph reallocs = 0 / 0 (same size) / (changed size) 9.50.082.216 I slot release: id 2 | task 5984 | stop processing: n_tokens = 2064, truncated = 0 9.50.083.484 I slot print_timing: id 3 | task 5985 | prompt eval time = 1859.98 ms / 441 tokens ( 4.22 ms per token, 237.10 tokens per second) 9.50.083.486 I slot print_timing: id 3 | task 5985 | eval time = 516.16 ms / 2 tokens ( 516.16 ms per token, 1.94 tokens per second) 9.50.083.486 I slot print_timing: id 3 | task 5985 | total time = 2376.15 ms / 443 tokens 9.50.083.486 I slot print_timing: id 3 | task 5985 | graphs reused = 4511 9.50.083.487 I slot print_timing: id 3 | task 5985 | graph reallocs = 0 / 0 (same size) / (changed size) 9.50.083.553 I slot release: id 3 | task 5985 | stop processing: n_tokens = 2273, truncated = 0 9.50.121.189 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.852 (> 0.100 thold), f_keep = 0.906 9.50.121.235 I slot launch_slot_: id 0 | task 5991 | processing task, is_child = 0 9.50.121.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 256.787 MiB) 9.50.121.371 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.617 MiB) 9.50.146.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.688 MiB) 9.50.168.590 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.887 9.50.168.687 I slot launch_slot_: id 2 | task 5992 | processing task, is_child = 0 9.50.168.818 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.806 9.50.168.857 I slot launch_slot_: id 3 | task 5993 | processing task, is_child = 0 9.51.768.538 I slot print_timing: id 1 | task 5988 | prompt eval time = 553.79 ms / 226 tokens ( 2.45 ms per token, 408.10 tokens per second) 9.51.768.544 I slot print_timing: id 1 | task 5988 | eval time = 1647.35 ms / 2 tokens ( 1647.35 ms per token, 0.61 tokens per second) 9.51.768.544 I slot print_timing: id 1 | task 5988 | total time = 2201.13 ms / 228 tokens 9.51.768.545 I slot print_timing: id 1 | task 5988 | graphs reused = 4511 9.51.768.546 I slot print_timing: id 1 | task 5988 | graph reallocs = 0 / 0 (same size) / (changed size) 9.51.768.688 I slot release: id 1 | task 5988 | stop processing: n_tokens = 2058, truncated = 0 9.51.851.206 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 9.51.851.294 I slot launch_slot_: id 1 | task 5996 | processing task, is_child = 0 9.52.479.759 I slot print_timing: id 0 | task 5991 | prompt eval time = 1680.16 ms / 318 tokens ( 5.28 ms per token, 189.27 tokens per second) 9.52.479.762 I slot print_timing: id 0 | task 5991 | eval time = 630.73 ms / 2 tokens ( 630.73 ms per token, 1.59 tokens per second) 9.52.479.762 I slot print_timing: id 0 | task 5991 | total time = 2310.89 ms / 320 tokens 9.52.479.763 I slot print_timing: id 0 | task 5991 | graphs reused = 4511 9.52.479.763 I slot print_timing: id 0 | task 5991 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.479.879 I slot release: id 0 | task 5991 | stop processing: n_tokens = 2151, truncated = 0 9.52.481.111 I slot print_timing: id 2 | task 5992 | prompt eval time = 1679.40 ms / 193 tokens ( 8.70 ms per token, 114.92 tokens per second) 9.52.481.113 I slot print_timing: id 2 | task 5992 | eval time = 630.98 ms / 2 tokens ( 630.98 ms per token, 1.58 tokens per second) 9.52.481.114 I slot print_timing: id 2 | task 5992 | total time = 2310.37 ms / 195 tokens 9.52.481.114 I slot print_timing: id 2 | task 5992 | graphs reused = 4511 9.52.481.114 I slot print_timing: id 2 | task 5992 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.481.177 I slot release: id 2 | task 5992 | stop processing: n_tokens = 2025, truncated = 0 9.52.482.410 I slot print_timing: id 3 | task 5993 | prompt eval time = 1678.60 ms / 282 tokens ( 5.95 ms per token, 168.00 tokens per second) 9.52.482.411 I slot print_timing: id 3 | task 5993 | eval time = 631.21 ms / 2 tokens ( 631.21 ms per token, 1.58 tokens per second) 9.52.482.412 I slot print_timing: id 3 | task 5993 | total time = 2309.80 ms / 284 tokens 9.52.482.412 I slot print_timing: id 3 | task 5993 | graphs reused = 4511 9.52.482.413 I slot print_timing: id 3 | task 5993 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.482.460 I slot release: id 3 | task 5993 | stop processing: n_tokens = 2113, truncated = 0 9.52.519.845 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.852 9.52.519.905 I slot launch_slot_: id 0 | task 5999 | processing task, is_child = 0 9.52.520.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.729 MiB) 9.52.528.627 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.617 MiB) 9.52.554.388 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 9.52.554.463 I slot launch_slot_: id 2 | task 6000 | processing task, is_child = 0 9.52.554.585 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.845 (> 0.100 thold), f_keep = 0.867 9.52.554.620 I slot launch_slot_: id 3 | task 6001 | processing task, is_child = 0 9.54.410.804 I slot print_timing: id 1 | task 5996 | prompt eval time = 668.53 ms / 289 tokens ( 2.31 ms per token, 432.29 tokens per second) 9.54.410.807 I slot print_timing: id 1 | task 5996 | eval time = 1890.96 ms / 2 tokens ( 1890.96 ms per token, 0.53 tokens per second) 9.54.410.807 I slot print_timing: id 1 | task 5996 | total time = 2559.50 ms / 291 tokens 9.54.410.808 I slot print_timing: id 1 | task 5996 | graphs reused = 4511 9.54.410.808 I slot print_timing: id 1 | task 5996 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.410.942 I slot release: id 1 | task 5996 | stop processing: n_tokens = 2121, truncated = 0 9.54.493.759 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 9.54.493.838 I slot launch_slot_: id 1 | task 6004 | processing task, is_child = 0 9.55.351.963 I slot print_timing: id 0 | task 5999 | prompt eval time = 1936.94 ms / 189 tokens ( 10.25 ms per token, 97.58 tokens per second) 9.55.351.969 I slot print_timing: id 0 | task 5999 | eval time = 860.38 ms / 2 tokens ( 860.38 ms per token, 1.16 tokens per second) 9.55.351.969 I slot print_timing: id 0 | task 5999 | total time = 2797.32 ms / 191 tokens 9.55.351.970 I slot print_timing: id 0 | task 5999 | graphs reused = 4511 9.55.351.970 I slot print_timing: id 0 | task 5999 | graph reallocs = 0 / 0 (same size) / (changed size) 9.55.352.115 I slot release: id 0 | task 5999 | stop processing: n_tokens = 2022, truncated = 0 9.55.353.393 I slot print_timing: id 2 | task 6000 | prompt eval time = 1936.27 ms / 387 tokens ( 5.00 ms per token, 199.87 tokens per second) 9.55.353.394 I slot print_timing: id 2 | task 6000 | eval time = 860.72 ms / 2 tokens ( 860.72 ms per token, 1.16 tokens per second) 9.55.353.395 I slot print_timing: id 2 | task 6000 | total time = 2796.99 ms / 389 tokens 9.55.353.395 I slot print_timing: id 2 | task 6000 | graphs reused = 4511 9.55.353.395 I slot print_timing: id 2 | task 6000 | graph reallocs = 0 / 0 (same size) / (changed size) 9.55.353.473 I slot release: id 2 | task 6000 | stop processing: n_tokens = 2219, truncated = 0 9.55.354.699 I slot print_timing: id 3 | task 6001 | prompt eval time = 1935.65 ms / 336 tokens ( 5.76 ms per token, 173.59 tokens per second) 9.55.354.704 I slot print_timing: id 3 | task 6001 | eval time = 860.95 ms / 2 tokens ( 860.95 ms per token, 1.16 tokens per second) 9.55.354.704 I slot print_timing: id 3 | task 6001 | total time = 2796.59 ms / 338 tokens 9.55.354.705 I slot print_timing: id 3 | task 6001 | graphs reused = 4511 9.55.354.705 I slot print_timing: id 3 | task 6001 | graph reallocs = 0 / 0 (same size) / (changed size) 9.55.354.772 I slot release: id 3 | task 6001 | stop processing: n_tokens = 2169, truncated = 0 9.55.392.536 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.906 9.55.392.591 I slot launch_slot_: id 0 | task 6007 | processing task, is_child = 0 9.55.392.738 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.512 MiB) 9.55.401.419 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.589 MiB) 9.55.401.424 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.547 MiB) 9.55.412.538 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 9.55.412.608 I slot launch_slot_: id 3 | task 6008 | processing task, is_child = 0 9.55.412.733 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.825 9.55.412.772 I slot launch_slot_: id 2 | task 6009 | processing task, is_child = 0 9.56.432.482 I slot print_timing: id 1 | task 6004 | prompt eval time = 898.67 ms / 399 tokens ( 2.25 ms per token, 443.99 tokens per second) 9.56.432.485 I slot print_timing: id 1 | task 6004 | eval time = 1039.95 ms / 2 tokens ( 1039.95 ms per token, 0.96 tokens per second) 9.56.432.486 I slot print_timing: id 1 | task 6004 | total time = 1938.63 ms / 401 tokens 9.56.432.486 I slot print_timing: id 1 | task 6004 | graphs reused = 4511 9.56.432.487 I slot print_timing: id 1 | task 6004 | graph reallocs = 0 / 0 (same size) / (changed size) 9.56.432.568 I slot release: id 1 | task 6004 | stop processing: n_tokens = 2231, truncated = 0 9.56.975.900 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 9.56.975.982 I slot launch_slot_: id 1 | task 6012 | processing task, is_child = 0 9.57.314.188 I slot print_timing: id 2 | task 6009 | prompt eval time = 1558.94 ms / 249 tokens ( 6.26 ms per token, 159.72 tokens per second) 9.57.314.194 I slot print_timing: id 2 | task 6009 | eval time = 339.49 ms / 2 tokens ( 339.49 ms per token, 2.95 tokens per second) 9.57.314.194 I slot print_timing: id 2 | task 6009 | total time = 1898.43 ms / 251 tokens 9.57.314.195 I slot print_timing: id 2 | task 6009 | graphs reused = 4511 9.57.314.195 I slot print_timing: id 2 | task 6009 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.314.322 I slot release: id 2 | task 6009 | stop processing: n_tokens = 2081, truncated = 0 9.57.315.480 I slot print_timing: id 3 | task 6008 | prompt eval time = 1558.40 ms / 238 tokens ( 6.55 ms per token, 152.72 tokens per second) 9.57.315.483 I slot print_timing: id 3 | task 6008 | eval time = 339.59 ms / 2 tokens ( 339.59 ms per token, 2.94 tokens per second) 9.57.315.483 I slot print_timing: id 3 | task 6008 | total time = 1897.99 ms / 240 tokens 9.57.315.483 I slot print_timing: id 3 | task 6008 | graphs reused = 4511 9.57.315.484 I slot print_timing: id 3 | task 6008 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.315.549 I slot release: id 3 | task 6008 | stop processing: n_tokens = 2071, truncated = 0 9.57.384.341 I slot print_timing: id 0 | task 6007 | prompt eval time = 1900.28 ms / 240 tokens ( 7.92 ms per token, 126.30 tokens per second) 9.57.384.350 I slot print_timing: id 0 | task 6007 | eval time = 71.28 ms / 2 tokens ( 71.28 ms per token, 14.03 tokens per second) 9.57.384.351 I slot print_timing: id 0 | task 6007 | total time = 1971.56 ms / 242 tokens 9.57.384.351 I slot print_timing: id 0 | task 6007 | graphs reused = 4511 9.57.384.351 I slot print_timing: id 0 | task 6007 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.384.419 I slot release: id 0 | task 6007 | stop processing: n_tokens = 2044, truncated = 0 9.57.385.597 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.896 9.57.385.663 I slot launch_slot_: id 0 | task 6015 | processing task, is_child = 0 9.57.385.814 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 254.290 MiB) 9.57.410.005 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 251.547 MiB) 9.57.410.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 256.751 MiB) 9.57.421.003 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 9.57.421.077 I slot launch_slot_: id 3 | task 6016 | processing task, is_child = 0 9.57.421.191 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2081, t_last = 329252598427 9.57.421.335 I slot launch_slot_: id 2 | task 6017 | processing task, is_child = 0 9.59.998.649 I slot print_timing: id 1 | task 6012 | prompt eval time = 405.73 ms / 123 tokens ( 3.30 ms per token, 303.16 tokens per second) 9.59.998.652 I slot print_timing: id 1 | task 6012 | eval time = 2613.05 ms / 2 tokens ( 2613.05 ms per token, 0.38 tokens per second) 9.59.998.652 I slot print_timing: id 1 | task 6012 | total time = 3018.78 ms / 125 tokens 9.59.998.653 I slot print_timing: id 1 | task 6012 | graphs reused = 4511 9.59.998.653 I slot print_timing: id 1 | task 6012 | graph reallocs = 0 / 0 (same size) / (changed size) 9.59.998.761 I slot release: id 1 | task 6012 | stop processing: n_tokens = 1955, truncated = 0 10.00.680.411 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1955, t_last = 329255282867 10.00.680.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.485 MiB) 10.00.692.729 I slot launch_slot_: id 1 | task 6020 | processing task, is_child = 0 10.00.693.007 I slot print_timing: id 2 | task 6017 | prompt processing, n_tokens = 1264, progress = 0.86, t = 3.26 s / 388.32 tokens per second 10.03.257.090 I slot print_timing: id 0 | task 6015 | prompt eval time = 3257.88 ms / 172 tokens ( 18.94 ms per token, 52.80 tokens per second) 10.03.257.093 I slot print_timing: id 0 | task 6015 | eval time = 2577.86 ms / 2 tokens ( 2577.86 ms per token, 0.39 tokens per second) 10.03.257.094 I slot print_timing: id 0 | task 6015 | total time = 5835.74 ms / 174 tokens 10.03.257.094 I slot print_timing: id 0 | task 6015 | graphs reused = 4511 10.03.257.095 I slot print_timing: id 0 | task 6015 | graph reallocs = 0 / 0 (same size) / (changed size) 10.03.257.175 I slot release: id 0 | task 6015 | stop processing: n_tokens = 2004, truncated = 0 10.03.258.348 I slot print_timing: id 3 | task 6016 | prompt eval time = 3257.03 ms / 208 tokens ( 15.66 ms per token, 63.86 tokens per second) 10.03.258.350 I slot print_timing: id 3 | task 6016 | eval time = 2577.94 ms / 2 tokens ( 2577.94 ms per token, 0.39 tokens per second) 10.03.258.350 I slot print_timing: id 3 | task 6016 | total time = 5834.97 ms / 210 tokens 10.03.258.351 I slot print_timing: id 3 | task 6016 | graphs reused = 4511 10.03.258.351 I slot print_timing: id 3 | task 6016 | graph reallocs = 0 / 0 (same size) / (changed size) 10.03.258.407 I slot release: id 3 | task 6016 | stop processing: n_tokens = 2041, truncated = 0 10.03.260.591 I slot print_timing: id 2 | task 6017 | prompt processing, n_tokens = 1462, progress = 1.00, t = 5.83 s / 250.65 tokens per second 10.03.555.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2004, t_last = 329258541280 10.03.555.516 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 305.905 MiB) 10.03.582.489 I slot launch_slot_: id 0 | task 6023 | processing task, is_child = 0 10.03.582.618 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.648 MiB) 10.03.582.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.572 MiB) 10.03.605.634 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2041, t_last = 329258542511 10.03.605.813 I slot launch_slot_: id 3 | task 6024 | processing task, is_child = 0 10.07.187.774 I slot print_timing: id 2 | task 6017 | prompt eval time = 6132.26 ms / 1466 tokens ( 4.18 ms per token, 239.06 tokens per second) 10.07.187.781 I slot print_timing: id 2 | task 6017 | eval time = 3632.41 ms / 2 tokens ( 3632.41 ms per token, 0.28 tokens per second) 10.07.187.782 I slot print_timing: id 2 | task 6017 | total time = 9764.67 ms / 1468 tokens 10.07.187.782 I slot print_timing: id 2 | task 6017 | graphs reused = 4511 10.07.187.783 I slot print_timing: id 2 | task 6017 | graph reallocs = 0 / 0 (same size) / (changed size) 10.07.187.888 I slot release: id 2 | task 6017 | stop processing: n_tokens = 1476, truncated = 0 10.07.187.925 I slot print_timing: id 0 | task 6023 | prompt processing, n_tokens = 479, progress = 0.49, t = 3.58 s / 133.77 tokens per second 10.07.191.817 I slot print_timing: id 1 | task 6020 | prompt processing, n_tokens = 1667, progress = 1.00, t = 6.49 s / 256.70 tokens per second 10.07.193.872 I slot print_timing: id 3 | task 6024 | prompt processing, n_tokens = 1021, progress = 0.67, t = 3.58 s / 285.29 tokens per second 10.08.430.231 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 329262471992 10.08.430.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.744 MiB) 10.08.441.016 I slot launch_slot_: id 2 | task 6027 | processing task, is_child = 0 10.08.441.026 I slot print_timing: id 0 | task 6023 | prompt processing, n_tokens = 848, progress = 0.85, t = 4.82 s / 175.81 tokens per second 10.08.443.020 I slot print_timing: id 3 | task 6024 | prompt processing, n_tokens = 1264, progress = 0.82, t = 4.82 s / 262.17 tokens per second 10.10.211.735 I slot print_timing: id 1 | task 6020 | prompt eval time = 7737.48 ms / 1671 tokens ( 4.63 ms per token, 215.96 tokens per second) 10.10.211.742 I slot print_timing: id 1 | task 6020 | eval time = 1781.51 ms / 2 tokens ( 1781.51 ms per token, 0.56 tokens per second) 10.10.211.742 I slot print_timing: id 1 | task 6020 | total time = 9518.98 ms / 1673 tokens 10.10.211.744 I slot print_timing: id 1 | task 6020 | graphs reused = 4511 10.10.211.744 I slot print_timing: id 1 | task 6020 | graph reallocs = 0 / 0 (same size) / (changed size) 10.10.211.873 I slot release: id 1 | task 6020 | stop processing: n_tokens = 1681, truncated = 0 10.10.211.927 I slot print_timing: id 0 | task 6023 | prompt processing, n_tokens = 991, progress = 1.00, t = 6.60 s / 150.04 tokens per second 10.10.218.092 I slot print_timing: id 3 | task 6024 | prompt processing, n_tokens = 1533, progress = 1.00, t = 6.60 s / 232.18 tokens per second 10.11.000.285 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1681, t_last = 329265495980 10.11.000.422 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.521 MiB) 10.11.010.341 I slot launch_slot_: id 1 | task 6030 | processing task, is_child = 0 10.12.221.418 I slot print_timing: id 0 | task 6023 | prompt eval time = 7393.30 ms / 995 tokens ( 7.43 ms per token, 134.58 tokens per second) 10.12.221.424 I slot print_timing: id 0 | task 6023 | eval time = 1222.29 ms / 2 tokens ( 1222.29 ms per token, 0.82 tokens per second) 10.12.221.425 I slot print_timing: id 0 | task 6023 | total time = 8615.59 ms / 997 tokens 10.12.221.432 I slot print_timing: id 0 | task 6023 | graphs reused = 4511 10.12.221.432 I slot print_timing: id 0 | task 6023 | graph reallocs = 0 / 0 (same size) / (changed size) 10.12.221.517 I slot release: id 0 | task 6023 | stop processing: n_tokens = 1005, truncated = 0 10.12.222.694 I slot print_timing: id 3 | task 6024 | prompt eval time = 7392.48 ms / 1537 tokens ( 4.81 ms per token, 207.91 tokens per second) 10.12.222.702 I slot print_timing: id 3 | task 6024 | eval time = 1222.41 ms / 2 tokens ( 1222.41 ms per token, 0.82 tokens per second) 10.12.222.703 I slot print_timing: id 3 | task 6024 | total time = 8614.89 ms / 1539 tokens 10.12.222.703 I slot print_timing: id 3 | task 6024 | graphs reused = 4511 10.12.222.704 I slot print_timing: id 3 | task 6024 | graph reallocs = 0 / 0 (same size) / (changed size) 10.12.222.778 I slot release: id 3 | task 6024 | stop processing: n_tokens = 1547, truncated = 0 10.12.224.725 I slot print_timing: id 2 | task 6027 | prompt processing, n_tokens = 981, progress = 1.00, t = 3.78 s / 259.69 tokens per second 10.13.024.660 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.880 10.13.024.746 I slot launch_slot_: id 0 | task 6033 | processing task, is_child = 0 10.13.024.867 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.915 MiB) 10.13.032.095 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1547, t_last = 329267506883 10.13.032.237 I slot launch_slot_: id 3 | task 6034 | processing task, is_child = 0 10.14.384.569 I slot print_timing: id 2 | task 6027 | prompt eval time = 4581.88 ms / 985 tokens ( 4.65 ms per token, 214.98 tokens per second) 10.14.384.573 I slot print_timing: id 2 | task 6027 | eval time = 1359.91 ms / 2 tokens ( 1359.91 ms per token, 0.74 tokens per second) 10.14.384.574 I slot print_timing: id 2 | task 6027 | total time = 5941.79 ms / 987 tokens 10.14.384.579 I slot print_timing: id 2 | task 6027 | graphs reused = 4511 10.14.384.580 I slot print_timing: id 2 | task 6027 | graph reallocs = 0 / 0 (same size) / (changed size) 10.14.384.666 I slot release: id 2 | task 6027 | stop processing: n_tokens = 995, truncated = 0 10.14.388.286 I slot print_timing: id 1 | task 6030 | prompt processing, n_tokens = 969, progress = 1.00, t = 3.37 s / 287.28 tokens per second 10.15.198.241 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.888 10.15.198.318 I slot launch_slot_: id 2 | task 6037 | processing task, is_child = 0 10.15.697.695 I slot print_timing: id 0 | task 6033 | prompt eval time = 2164.72 ms / 103 tokens ( 21.02 ms per token, 47.58 tokens per second) 10.15.697.698 I slot print_timing: id 0 | task 6033 | eval time = 500.72 ms / 2 tokens ( 500.72 ms per token, 2.00 tokens per second) 10.15.697.699 I slot print_timing: id 0 | task 6033 | total time = 2665.44 ms / 105 tokens 10.15.697.699 I slot print_timing: id 0 | task 6033 | graphs reused = 4511 10.15.697.700 I slot print_timing: id 0 | task 6033 | graph reallocs = 0 / 0 (same size) / (changed size) 10.15.697.750 I slot release: id 0 | task 6033 | stop processing: n_tokens = 988, truncated = 0 10.15.698.982 I slot print_timing: id 1 | task 6030 | prompt eval time = 4187.88 ms / 973 tokens ( 4.30 ms per token, 232.34 tokens per second) 10.15.698.986 I slot print_timing: id 1 | task 6030 | eval time = 500.75 ms / 2 tokens ( 500.75 ms per token, 2.00 tokens per second) 10.15.698.986 I slot print_timing: id 1 | task 6030 | total time = 4688.63 ms / 975 tokens 10.15.698.986 I slot print_timing: id 1 | task 6030 | graphs reused = 4511 10.15.698.987 I slot print_timing: id 1 | task 6030 | graph reallocs = 0 / 0 (same size) / (changed size) 10.15.699.038 I slot release: id 1 | task 6030 | stop processing: n_tokens = 983, truncated = 0 10.15.744.871 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 329270981854 10.15.744.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.071 MiB) 10.15.752.429 I slot launch_slot_: id 0 | task 6040 | processing task, is_child = 0 10.15.752.507 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 266.524 MiB) 10.15.758.744 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.899 10.15.758.789 I slot launch_slot_: id 1 | task 6041 | processing task, is_child = 0 10.16.573.723 I slot print_timing: id 2 | task 6037 | prompt eval time = 545.44 ms / 93 tokens ( 5.86 ms per token, 170.51 tokens per second) 10.16.573.726 I slot print_timing: id 2 | task 6037 | eval time = 829.95 ms / 2 tokens ( 829.95 ms per token, 1.20 tokens per second) 10.16.573.727 I slot print_timing: id 2 | task 6037 | total time = 1375.39 ms / 95 tokens 10.16.573.728 I slot print_timing: id 2 | task 6037 | graphs reused = 4511 10.16.573.728 I slot print_timing: id 2 | task 6037 | graph reallocs = 0 / 0 (same size) / (changed size) 10.16.573.808 I slot release: id 2 | task 6037 | stop processing: n_tokens = 978, truncated = 0 10.16.575.033 I slot print_timing: id 3 | task 6034 | prompt eval time = 2709.26 ms / 958 tokens ( 2.83 ms per token, 353.60 tokens per second) 10.16.575.038 I slot print_timing: id 3 | task 6034 | eval time = 830.17 ms / 2 tokens ( 830.17 ms per token, 1.20 tokens per second) 10.16.575.040 I slot print_timing: id 3 | task 6034 | total time = 3539.43 ms / 960 tokens 10.16.575.040 I slot print_timing: id 3 | task 6034 | graphs reused = 4511 10.16.575.041 I slot print_timing: id 3 | task 6034 | graph reallocs = 0 / 0 (same size) / (changed size) 10.16.575.082 I slot release: id 3 | task 6034 | stop processing: n_tokens = 968, truncated = 0 10.17.371.472 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 978, t_last = 329271857914 10.17.371.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 249.437 MiB) 10.17.371.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.906 MiB) 10.17.380.963 I slot launch_slot_: id 2 | task 6044 | processing task, is_child = 0 10.17.381.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.515 MiB) 10.17.387.102 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 968, t_last = 329271859186 10.17.387.220 I slot launch_slot_: id 3 | task 6045 | processing task, is_child = 0 10.21.196.148 I slot print_timing: id 1 | task 6041 | prompt eval time = 1612.45 ms / 98 tokens ( 16.45 ms per token, 60.78 tokens per second) 10.21.196.151 I slot print_timing: id 1 | task 6041 | eval time = 3824.67 ms / 2 tokens ( 3824.67 ms per token, 0.26 tokens per second) 10.21.196.152 I slot print_timing: id 1 | task 6041 | total time = 5437.12 ms / 100 tokens 10.21.196.156 I slot print_timing: id 1 | task 6041 | graphs reused = 4511 10.21.196.156 I slot print_timing: id 1 | task 6041 | graph reallocs = 0 / 0 (same size) / (changed size) 10.21.196.243 I slot release: id 1 | task 6041 | stop processing: n_tokens = 983, truncated = 0 10.21.196.276 I slot print_timing: id 0 | task 6040 | prompt processing, n_tokens = 810, progress = 1.00, t = 5.44 s / 149.00 tokens per second 10.21.200.494 I slot print_timing: id 2 | task 6044 | prompt processing, n_tokens = 1131, progress = 0.69, t = 3.81 s / 297.15 tokens per second 10.21.202.865 I slot print_timing: id 3 | task 6045 | prompt processing, n_tokens = 801, progress = 0.50, t = 3.81 s / 210.46 tokens per second 10.22.295.633 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 983, t_last = 329276480347 10.22.295.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 255.063 MiB) 10.22.305.730 I slot launch_slot_: id 1 | task 6048 | processing task, is_child = 0 10.22.305.971 I slot print_timing: id 2 | task 6044 | prompt processing, n_tokens = 1388, progress = 0.84, t = 4.91 s / 282.94 tokens per second 10.22.307.703 I slot print_timing: id 3 | task 6045 | prompt processing, n_tokens = 1086, progress = 0.68, t = 4.91 s / 221.39 tokens per second 10.25.491.175 I slot print_timing: id 0 | task 6040 | prompt eval time = 6536.83 ms / 814 tokens ( 8.03 ms per token, 124.53 tokens per second) 10.25.491.178 I slot print_timing: id 0 | task 6040 | eval time = 3195.54 ms / 2 tokens ( 3195.54 ms per token, 0.31 tokens per second) 10.25.491.178 I slot print_timing: id 0 | task 6040 | total time = 9732.37 ms / 816 tokens 10.25.491.179 I slot print_timing: id 0 | task 6040 | graphs reused = 4511 10.25.491.179 I slot print_timing: id 0 | task 6040 | graph reallocs = 0 / 0 (same size) / (changed size) 10.25.491.226 I slot release: id 0 | task 6040 | stop processing: n_tokens = 824, truncated = 0 10.25.491.244 I slot print_timing: id 1 | task 6048 | prompt processing, n_tokens = 1114, progress = 0.69, t = 3.18 s / 349.84 tokens per second 10.25.495.162 I slot print_timing: id 2 | task 6044 | prompt processing, n_tokens = 1643, progress = 1.00, t = 8.10 s / 202.81 tokens per second 10.25.497.050 I slot print_timing: id 3 | task 6045 | prompt processing, n_tokens = 1388, progress = 0.87, t = 8.10 s / 171.34 tokens per second 10.26.539.874 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 329280775330 10.26.540.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.017 MiB) 10.26.549.269 I slot launch_slot_: id 0 | task 6051 | processing task, is_child = 0 10.26.549.473 I slot print_timing: id 1 | task 6048 | prompt processing, n_tokens = 1388, progress = 0.85, t = 4.23 s / 327.90 tokens per second 10.26.551.306 I slot print_timing: id 3 | task 6045 | prompt processing, n_tokens = 1598, progress = 1.00, t = 9.15 s / 174.65 tokens per second 10.29.178.645 I slot print_timing: id 2 | task 6044 | prompt eval time = 9150.98 ms / 1647 tokens ( 5.56 ms per token, 179.98 tokens per second) 10.29.178.651 I slot print_timing: id 2 | task 6044 | eval time = 2638.77 ms / 2 tokens ( 2638.77 ms per token, 0.38 tokens per second) 10.29.178.651 I slot print_timing: id 2 | task 6044 | total time = 11789.75 ms / 1649 tokens 10.29.178.652 I slot print_timing: id 2 | task 6044 | graphs reused = 4511 10.29.178.652 I slot print_timing: id 2 | task 6044 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.178.749 I slot release: id 2 | task 6044 | stop processing: n_tokens = 1657, truncated = 0 10.29.182.470 I slot print_timing: id 1 | task 6048 | prompt processing, n_tokens = 1626, progress = 1.00, t = 6.87 s / 236.62 tokens per second 10.29.743.820 I slot print_timing: id 3 | task 6045 | prompt eval time = 11790.86 ms / 1602 tokens ( 7.36 ms per token, 135.87 tokens per second) 10.29.743.824 I slot print_timing: id 3 | task 6045 | eval time = 563.83 ms / 2 tokens ( 563.83 ms per token, 1.77 tokens per second) 10.29.743.824 I slot print_timing: id 3 | task 6045 | total time = 12354.69 ms / 1604 tokens 10.29.743.825 I slot print_timing: id 3 | task 6045 | graphs reused = 4511 10.29.743.825 I slot print_timing: id 3 | task 6045 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.743.890 I slot release: id 3 | task 6045 | stop processing: n_tokens = 1612, truncated = 0 10.29.743.900 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.814 (> 0.100 thold), f_keep = 0.859 10.29.743.962 I slot launch_slot_: id 2 | task 6054 | processing task, is_child = 0 10.29.744.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.143 MiB) 10.29.756.371 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1612, t_last = 329285027994 10.29.756.535 I slot launch_slot_: id 3 | task 6055 | processing task, is_child = 0 10.29.756.545 I slot print_timing: id 0 | task 6051 | prompt processing, n_tokens = 1388, progress = 0.84, t = 3.18 s / 436.23 tokens per second 10.31.547.047 I slot print_timing: id 1 | task 6048 | prompt eval time = 7437.03 ms / 1630 tokens ( 4.56 ms per token, 219.17 tokens per second) 10.31.547.051 I slot print_timing: id 1 | task 6048 | eval time = 1804.26 ms / 2 tokens ( 1804.26 ms per token, 0.55 tokens per second) 10.31.547.051 I slot print_timing: id 1 | task 6048 | total time = 9241.28 ms / 1632 tokens 10.31.547.052 I slot print_timing: id 1 | task 6048 | graphs reused = 4511 10.31.547.052 I slot print_timing: id 1 | task 6048 | graph reallocs = 0 / 0 (same size) / (changed size) 10.31.547.176 I slot release: id 1 | task 6048 | stop processing: n_tokens = 1640, truncated = 0 10.31.547.201 I slot print_timing: id 0 | task 6051 | prompt processing, n_tokens = 1652, progress = 1.00, t = 5.00 s / 330.62 tokens per second 10.32.381.522 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1640, t_last = 329286831280 10.32.381.655 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.255 MiB) 10.32.392.050 I slot launch_slot_: id 1 | task 6058 | processing task, is_child = 0 10.33.334.043 I slot print_timing: id 0 | task 6051 | prompt eval time = 5830.96 ms / 1656 tokens ( 3.52 ms per token, 284.00 tokens per second) 10.33.334.049 I slot print_timing: id 0 | task 6051 | eval time = 953.80 ms / 2 tokens ( 953.80 ms per token, 1.05 tokens per second) 10.33.334.050 I slot print_timing: id 0 | task 6051 | total time = 6784.76 ms / 1658 tokens 10.33.334.050 I slot print_timing: id 0 | task 6051 | graphs reused = 4511 10.33.334.051 I slot print_timing: id 0 | task 6051 | graph reallocs = 0 / 0 (same size) / (changed size) 10.33.334.181 I slot release: id 0 | task 6051 | stop processing: n_tokens = 1666, truncated = 0 10.33.335.338 I slot print_timing: id 2 | task 6054 | prompt eval time = 2623.20 ms / 325 tokens ( 8.07 ms per token, 123.89 tokens per second) 10.33.335.343 I slot print_timing: id 2 | task 6054 | eval time = 953.82 ms / 2 tokens ( 953.82 ms per token, 1.05 tokens per second) 10.33.335.343 I slot print_timing: id 2 | task 6054 | total time = 3577.02 ms / 327 tokens 10.33.335.344 I slot print_timing: id 2 | task 6054 | graphs reused = 4511 10.33.335.344 I slot print_timing: id 2 | task 6054 | graph reallocs = 0 / 0 (same size) / (changed size) 10.33.335.408 I slot release: id 2 | task 6054 | stop processing: n_tokens = 1750, truncated = 0 10.33.337.366 I slot print_timing: id 3 | task 6055 | prompt processing, n_tokens = 831, progress = 1.00, t = 3.57 s / 232.59 tokens per second 10.34.078.524 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1666, t_last = 329288618287 10.34.078.663 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 348.598 MiB) 10.34.089.692 I slot launch_slot_: id 0 | task 6061 | processing task, is_child = 0 10.34.089.799 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 346.172 MiB) 10.34.099.143 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1750, t_last = 329288619517 10.34.099.294 I slot launch_slot_: id 2 | task 6062 | processing task, is_child = 0 10.35.643.917 I slot print_timing: id 3 | task 6055 | prompt eval time = 4318.41 ms / 835 tokens ( 5.17 ms per token, 193.36 tokens per second) 10.35.643.920 I slot print_timing: id 3 | task 6055 | eval time = 1565.39 ms / 2 tokens ( 1565.39 ms per token, 0.64 tokens per second) 10.35.643.920 I slot print_timing: id 3 | task 6055 | total time = 5883.80 ms / 837 tokens 10.35.643.921 I slot print_timing: id 3 | task 6055 | graphs reused = 4511 10.35.643.921 I slot print_timing: id 3 | task 6055 | graph reallocs = 0 / 0 (same size) / (changed size) 10.35.644.009 I slot release: id 3 | task 6055 | stop processing: n_tokens = 845, truncated = 0 10.35.646.464 I slot print_timing: id 1 | task 6058 | prompt processing, n_tokens = 858, progress = 1.00, t = 3.25 s / 263.94 tokens per second 10.37.161.754 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 329290928113 10.37.170.579 I slot launch_slot_: id 3 | task 6065 | processing task, is_child = 0 10.37.170.594 I slot print_timing: id 0 | task 6061 | prompt processing, n_tokens = 714, progress = 0.85, t = 3.06 s / 233.23 tokens per second 10.37.172.270 I slot print_timing: id 2 | task 6062 | prompt processing, n_tokens = 714, progress = 0.83, t = 3.06 s / 233.38 tokens per second 10.38.458.326 I slot print_timing: id 1 | task 6058 | prompt eval time = 4769.68 ms / 862 tokens ( 5.53 ms per token, 180.72 tokens per second) 10.38.458.331 I slot print_timing: id 1 | task 6058 | eval time = 1296.58 ms / 2 tokens ( 1296.58 ms per token, 0.77 tokens per second) 10.38.458.332 I slot print_timing: id 1 | task 6058 | total time = 6066.26 ms / 864 tokens 10.38.458.342 I slot print_timing: id 1 | task 6058 | graphs reused = 4511 10.38.458.342 I slot print_timing: id 1 | task 6058 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.458.413 I slot release: id 1 | task 6058 | stop processing: n_tokens = 872, truncated = 0 10.38.458.436 I slot print_timing: id 0 | task 6061 | prompt processing, n_tokens = 836, progress = 1.00, t = 4.36 s / 191.83 tokens per second 10.38.461.813 I slot print_timing: id 2 | task 6062 | prompt processing, n_tokens = 855, progress = 1.00, t = 4.36 s / 196.28 tokens per second 10.39.184.447 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 872, t_last = 329293742518 10.39.184.548 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 398.525 MiB) 10.39.192.731 I slot launch_slot_: id 1 | task 6068 | processing task, is_child = 0 10.40.087.662 I slot print_timing: id 0 | task 6061 | prompt eval time = 5083.77 ms / 840 tokens ( 6.05 ms per token, 165.23 tokens per second) 10.40.087.665 I slot print_timing: id 0 | task 6061 | eval time = 904.59 ms / 2 tokens ( 904.59 ms per token, 1.11 tokens per second) 10.40.087.666 I slot print_timing: id 0 | task 6061 | total time = 5988.35 ms / 842 tokens 10.40.087.667 I slot print_timing: id 0 | task 6061 | graphs reused = 4511 10.40.087.667 I slot print_timing: id 0 | task 6061 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.087.745 I slot release: id 0 | task 6061 | stop processing: n_tokens = 850, truncated = 0 10.40.088.894 I slot print_timing: id 2 | task 6062 | prompt eval time = 5083.23 ms / 859 tokens ( 5.92 ms per token, 168.99 tokens per second) 10.40.088.897 I slot print_timing: id 2 | task 6062 | eval time = 904.45 ms / 2 tokens ( 904.45 ms per token, 1.11 tokens per second) 10.40.088.898 I slot print_timing: id 2 | task 6062 | total time = 5987.68 ms / 861 tokens 10.40.088.898 I slot print_timing: id 2 | task 6062 | graphs reused = 4511 10.40.088.899 I slot print_timing: id 2 | task 6062 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.088.942 I slot release: id 2 | task 6062 | stop processing: n_tokens = 869, truncated = 0 10.40.824.949 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 329295371849 10.40.835.050 I slot launch_slot_: id 0 | task 6071 | processing task, is_child = 0 10.40.835.128 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 351.974 MiB) 10.40.840.916 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 329295373046 10.40.841.030 I slot launch_slot_: id 2 | task 6072 | processing task, is_child = 0 10.41.938.491 I slot print_timing: id 3 | task 6065 | prompt eval time = 3650.95 ms / 884 tokens ( 4.13 ms per token, 242.13 tokens per second) 10.41.938.494 I slot print_timing: id 3 | task 6065 | eval time = 1113.55 ms / 2 tokens ( 1113.55 ms per token, 0.90 tokens per second) 10.41.938.494 I slot print_timing: id 3 | task 6065 | total time = 4764.50 ms / 886 tokens 10.41.938.495 I slot print_timing: id 3 | task 6065 | graphs reused = 4511 10.41.938.495 I slot print_timing: id 3 | task 6065 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.938.539 I slot release: id 3 | task 6065 | stop processing: n_tokens = 894, truncated = 0 10.43.494.726 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 329297222643 10.43.494.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 343.147 MiB) 10.43.503.729 I slot launch_slot_: id 3 | task 6075 | processing task, is_child = 0 10.44.446.756 I slot print_timing: id 1 | task 6068 | prompt eval time = 4301.97 ms / 762 tokens ( 5.65 ms per token, 177.13 tokens per second) 10.44.446.761 I slot print_timing: id 1 | task 6068 | eval time = 952.04 ms / 2 tokens ( 952.04 ms per token, 1.05 tokens per second) 10.44.446.762 I slot print_timing: id 1 | task 6068 | total time = 5254.01 ms / 764 tokens 10.44.446.762 I slot print_timing: id 1 | task 6068 | graphs reused = 4511 10.44.446.763 I slot print_timing: id 1 | task 6068 | graph reallocs = 0 / 0 (same size) / (changed size) 10.44.446.802 I slot release: id 1 | task 6068 | stop processing: n_tokens = 772, truncated = 0 10.44.446.814 I slot print_timing: id 0 | task 6071 | prompt processing, n_tokens = 684, progress = 0.99, t = 3.60 s / 189.76 tokens per second 10.44.450.842 I slot print_timing: id 2 | task 6072 | prompt processing, n_tokens = 729, progress = 0.99, t = 3.60 s / 202.34 tokens per second 10.45.217.989 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 329299730906 10.45.227.751 I slot launch_slot_: id 1 | task 6078 | processing task, is_child = 0 10.45.888.347 I slot print_timing: id 0 | task 6071 | prompt eval time = 4375.58 ms / 688 tokens ( 6.36 ms per token, 157.24 tokens per second) 10.45.888.351 I slot print_timing: id 0 | task 6071 | eval time = 671.71 ms / 2 tokens ( 671.71 ms per token, 1.49 tokens per second) 10.45.888.351 I slot print_timing: id 0 | task 6071 | total time = 5047.30 ms / 690 tokens 10.45.888.352 I slot print_timing: id 0 | task 6071 | graphs reused = 4511 10.45.888.353 I slot print_timing: id 0 | task 6071 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.888.418 I slot release: id 0 | task 6071 | stop processing: n_tokens = 698, truncated = 0 10.45.889.589 I slot print_timing: id 2 | task 6072 | prompt eval time = 4375.08 ms / 733 tokens ( 5.97 ms per token, 167.54 tokens per second) 10.45.889.596 I slot print_timing: id 2 | task 6072 | eval time = 671.61 ms / 2 tokens ( 671.61 ms per token, 1.49 tokens per second) 10.45.889.597 I slot print_timing: id 2 | task 6072 | total time = 5046.69 ms / 735 tokens 10.45.889.597 I slot print_timing: id 2 | task 6072 | graphs reused = 4511 10.45.889.598 I slot print_timing: id 2 | task 6072 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.889.631 I slot release: id 2 | task 6072 | stop processing: n_tokens = 743, truncated = 0 10.46.954.027 I slot print_timing: id 3 | task 6075 | prompt eval time = 3170.70 ms / 707 tokens ( 4.48 ms per token, 222.98 tokens per second) 10.46.954.030 I slot print_timing: id 3 | task 6075 | eval time = 276.27 ms / 2 tokens ( 276.27 ms per token, 3.62 tokens per second) 10.46.954.031 I slot print_timing: id 3 | task 6075 | total time = 3446.97 ms / 709 tokens 10.46.954.031 I slot print_timing: id 3 | task 6075 | graphs reused = 4511 10.46.954.032 I slot print_timing: id 3 | task 6075 | graph reallocs = 0 / 0 (same size) / (changed size) 10.46.954.069 I slot release: id 3 | task 6075 | stop processing: n_tokens = 717, truncated = 0 10.47.015.733 I slot print_timing: id 1 | task 6078 | prompt eval time = 1766.94 ms / 673 tokens ( 2.63 ms per token, 380.88 tokens per second) 10.47.015.739 I slot print_timing: id 1 | task 6078 | eval time = 21.03 ms / 2 tokens ( 21.03 ms per token, 47.56 tokens per second) 10.47.015.739 I slot print_timing: id 1 | task 6078 | total time = 1787.97 ms / 675 tokens 10.47.015.740 I slot print_timing: id 1 | task 6078 | graphs reused = 4511 10.47.015.740 I slot print_timing: id 1 | task 6078 | graph reallocs = 0 / 0 (same size) / (changed size) 10.47.015.766 I slot release: id 1 | task 6078 | stop processing: n_tokens = 683, truncated = 0 10.49.470.407 I srv operator(): operator(): cleaning up before exit...