$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--bartowski--granite-4.2-8b-GGUF\snapshots\a592100df8fe4931c7cffbac7b28e8176a1d52da\granite-4.2-8b-Q2_K.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.092.989 I srv llama_server: initializing ... 0.00.092.995 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.093.104 I srv init_listene: The UI is disabled 0.00.093.106 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.093.181 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) 0.00.104.512 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--bartowski--granite-4.2-8b-GGUF\snapshots\a592100df8fe4931c7cffbac7b28e8176a1d52da\granite-4.2-8b-Q2_K.gguf' 0.01.644.552 I cmn init: llama threadpool init, n_threads = 8 0.01.708.379 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.713.077 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.713.097 I srv llama_server: model loaded 0.01.713.099 I srv llama_server: listening on http://127.0.0.1:8089 0.02.547.317 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.547.491 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.116.807 I slot print_timing: id 0 | task 0 | prompt eval time = 136.38 ms / 368 tokens ( 0.37 ms per token, 2698.38 tokens per second) 0.03.116.813 I slot print_timing: id 0 | task 0 | eval time = 432.92 ms / 61 tokens ( 7.22 ms per token, 138.59 tokens per second) 0.03.116.814 I slot print_timing: id 0 | task 0 | total time = 569.30 ms / 429 tokens 0.03.116.820 I slot print_timing: id 0 | task 0 | graphs reused = 60 0.03.116.821 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.116.850 I slot release: id 0 | task 0 | stop processing: n_tokens = 428, truncated = 0 0.03.131.619 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 3025781 0.03.145.991 I slot launch_slot_: id 0 | task 62 | processing task, is_child = 0 0.03.556.740 I slot print_timing: id 0 | task 62 | prompt eval time = 101.94 ms / 292 tokens ( 0.35 ms per token, 2864.46 tokens per second) 0.03.556.746 I slot print_timing: id 0 | task 62 | eval time = 308.80 ms / 44 tokens ( 7.18 ms per token, 139.25 tokens per second) 0.03.556.747 I slot print_timing: id 0 | task 62 | total time = 410.73 ms / 336 tokens 0.03.556.747 I slot print_timing: id 0 | task 62 | graphs reused = 102 0.03.556.748 I slot print_timing: id 0 | task 62 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.556.773 I slot release: id 0 | task 62 | stop processing: n_tokens = 360, truncated = 0 0.03.584.234 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 360, t_last = 3465704 0.03.596.845 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.04.035.959 I slot print_timing: id 0 | task 107 | prompt eval time = 114.05 ms / 338 tokens ( 0.34 ms per token, 2963.59 tokens per second) 0.04.035.965 I slot print_timing: id 0 | task 107 | eval time = 325.05 ms / 45 tokens ( 7.39 ms per token, 135.37 tokens per second) 0.04.035.966 I slot print_timing: id 0 | task 107 | total time = 439.10 ms / 383 tokens 0.04.035.966 I slot print_timing: id 0 | task 107 | graphs reused = 145 0.04.035.967 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.035.997 I slot release: id 0 | task 107 | stop processing: n_tokens = 407, truncated = 0 0.04.049.625 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 3944928 0.04.063.510 I slot launch_slot_: id 0 | task 153 | processing task, is_child = 0 0.04.500.458 I slot print_timing: id 0 | task 153 | prompt eval time = 114.20 ms / 371 tokens ( 0.31 ms per token, 3248.60 tokens per second) 0.04.500.463 I slot print_timing: id 0 | task 153 | eval time = 322.73 ms / 46 tokens ( 7.17 ms per token, 139.44 tokens per second) 0.04.500.464 I slot print_timing: id 0 | task 153 | total time = 436.93 ms / 417 tokens 0.04.500.465 I slot print_timing: id 0 | task 153 | graphs reused = 189 0.04.500.466 I slot print_timing: id 0 | task 153 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.500.496 I slot release: id 0 | task 153 | stop processing: n_tokens = 441, truncated = 0 0.04.514.088 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.091 0.04.529.255 I slot launch_slot_: id 0 | task 200 | processing task, is_child = 0 0.05.071.952 I slot print_timing: id 0 | task 200 | prompt eval time = 114.27 ms / 345 tokens ( 0.33 ms per token, 3019.14 tokens per second) 0.05.071.957 I slot print_timing: id 0 | task 200 | eval time = 428.41 ms / 61 tokens ( 7.14 ms per token, 140.05 tokens per second) 0.05.071.958 I slot print_timing: id 0 | task 200 | total time = 542.68 ms / 406 tokens 0.05.071.959 I slot print_timing: id 0 | task 200 | graphs reused = 248 0.05.071.960 I slot print_timing: id 0 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.071.990 I slot release: id 0 | task 200 | stop processing: n_tokens = 445, truncated = 0 0.05.096.661 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 445, t_last = 4980921 0.05.111.530 I slot launch_slot_: id 0 | task 262 | processing task, is_child = 0 0.05.676.542 I slot print_timing: id 0 | task 262 | prompt eval time = 114.40 ms / 351 tokens ( 0.33 ms per token, 3068.10 tokens per second) 0.05.676.547 I slot print_timing: id 0 | task 262 | eval time = 450.59 ms / 64 tokens ( 7.15 ms per token, 139.82 tokens per second) 0.05.676.548 I slot print_timing: id 0 | task 262 | total time = 564.99 ms / 415 tokens 0.05.676.549 I slot print_timing: id 0 | task 262 | graphs reused = 310 0.05.676.551 I slot print_timing: id 0 | task 262 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.676.577 I slot release: id 0 | task 262 | stop processing: n_tokens = 439, truncated = 0 0.05.703.348 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 5585508 0.05.718.185 I slot launch_slot_: id 0 | task 327 | processing task, is_child = 0 0.06.411.189 I slot print_timing: id 0 | task 327 | prompt eval time = 137.10 ms / 395 tokens ( 0.35 ms per token, 2881.02 tokens per second) 0.06.411.195 I slot print_timing: id 0 | task 327 | eval time = 555.88 ms / 79 tokens ( 7.13 ms per token, 140.32 tokens per second) 0.06.411.196 I slot print_timing: id 0 | task 327 | total time = 692.99 ms / 474 tokens 0.06.411.196 I slot print_timing: id 0 | task 327 | graphs reused = 387 0.06.411.197 I slot print_timing: id 0 | task 327 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.411.231 I slot release: id 0 | task 327 | stop processing: n_tokens = 498, truncated = 0 0.06.415.588 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 6320162 0.06.432.191 I slot launch_slot_: id 0 | task 407 | processing task, is_child = 0 0.07.085.651 I slot print_timing: id 0 | task 407 | prompt eval time = 139.68 ms / 446 tokens ( 0.31 ms per token, 3193.06 tokens per second) 0.07.085.656 I slot print_timing: id 0 | task 407 | eval time = 513.76 ms / 72 tokens ( 7.24 ms per token, 138.20 tokens per second) 0.07.085.657 I slot print_timing: id 0 | task 407 | total time = 653.44 ms / 518 tokens 0.07.085.658 I slot print_timing: id 0 | task 407 | graphs reused = 456 0.07.085.659 I slot print_timing: id 0 | task 407 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.085.689 I slot release: id 0 | task 407 | stop processing: n_tokens = 542, truncated = 0 0.07.108.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 6994620 0.07.126.393 I slot launch_slot_: id 0 | task 480 | processing task, is_child = 0 0.07.593.923 I slot print_timing: id 0 | task 480 | prompt eval time = 102.33 ms / 319 tokens ( 0.32 ms per token, 3117.24 tokens per second) 0.07.593.929 I slot print_timing: id 0 | task 480 | eval time = 365.18 ms / 52 tokens ( 7.16 ms per token, 139.66 tokens per second) 0.07.593.930 I slot print_timing: id 0 | task 480 | total time = 467.52 ms / 371 tokens 0.07.593.931 I slot print_timing: id 0 | task 480 | graphs reused = 506 0.07.593.932 I slot print_timing: id 0 | task 480 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.593.959 I slot release: id 0 | task 480 | stop processing: n_tokens = 395, truncated = 0 0.07.608.801 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 7502890 0.07.622.339 I slot launch_slot_: id 0 | task 533 | processing task, is_child = 0 0.08.018.979 I slot print_timing: id 0 | task 533 | prompt eval time = 102.69 ms / 336 tokens ( 0.31 ms per token, 3271.95 tokens per second) 0.08.018.985 I slot print_timing: id 0 | task 533 | eval time = 293.93 ms / 42 tokens ( 7.17 ms per token, 139.49 tokens per second) 0.08.018.986 I slot print_timing: id 0 | task 533 | total time = 396.62 ms / 378 tokens 0.08.018.987 I slot print_timing: id 0 | task 533 | graphs reused = 546 0.08.018.988 I slot print_timing: id 0 | task 533 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.019.013 I slot release: id 0 | task 533 | stop processing: n_tokens = 402, truncated = 0 0.08.045.430 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 7927944 0.08.059.386 I slot launch_slot_: id 0 | task 576 | processing task, is_child = 0 0.08.661.265 I slot print_timing: id 0 | task 576 | prompt eval time = 114.54 ms / 352 tokens ( 0.33 ms per token, 3073.16 tokens per second) 0.08.661.271 I slot print_timing: id 0 | task 576 | eval time = 487.32 ms / 68 tokens ( 7.27 ms per token, 137.49 tokens per second) 0.08.661.272 I slot print_timing: id 0 | task 576 | total time = 601.86 ms / 420 tokens 0.08.661.273 I slot print_timing: id 0 | task 576 | graphs reused = 612 0.08.661.274 I slot print_timing: id 0 | task 576 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.661.301 I slot release: id 0 | task 576 | stop processing: n_tokens = 444, truncated = 0 0.08.687.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 8570232 0.08.702.392 I slot launch_slot_: id 0 | task 645 | processing task, is_child = 0 0.09.204.276 I slot print_timing: id 0 | task 645 | prompt eval time = 136.76 ms / 387 tokens ( 0.35 ms per token, 2829.75 tokens per second) 0.09.204.283 I slot print_timing: id 0 | task 645 | eval time = 365.11 ms / 52 tokens ( 7.16 ms per token, 139.69 tokens per second) 0.09.204.284 I slot print_timing: id 0 | task 645 | total time = 501.87 ms / 439 tokens 0.09.204.285 I slot print_timing: id 0 | task 645 | graphs reused = 662 0.09.204.287 I slot print_timing: id 0 | task 645 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.204.319 I slot release: id 0 | task 645 | stop processing: n_tokens = 463, truncated = 0 0.09.218.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 463, t_last = 9113250 0.09.233.835 I slot launch_slot_: id 0 | task 698 | processing task, is_child = 0 0.09.797.697 I slot print_timing: id 0 | task 698 | prompt eval time = 114.23 ms / 349 tokens ( 0.33 ms per token, 3055.13 tokens per second) 0.09.797.702 I slot print_timing: id 0 | task 698 | eval time = 449.61 ms / 64 tokens ( 7.14 ms per token, 140.12 tokens per second) 0.09.797.703 I slot print_timing: id 0 | task 698 | total time = 563.85 ms / 413 tokens 0.09.797.704 I slot print_timing: id 0 | task 698 | graphs reused = 724 0.09.797.705 I slot print_timing: id 0 | task 698 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.797.733 I slot release: id 0 | task 698 | stop processing: n_tokens = 437, truncated = 0 0.09.811.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 9706664 0.09.826.246 I slot launch_slot_: id 0 | task 763 | processing task, is_child = 0 0.10.340.464 I slot print_timing: id 0 | task 763 | prompt eval time = 114.32 ms / 352 tokens ( 0.32 ms per token, 3079.02 tokens per second) 0.10.340.469 I slot print_timing: id 0 | task 763 | eval time = 399.88 ms / 57 tokens ( 7.14 ms per token, 140.04 tokens per second) 0.10.340.471 I slot print_timing: id 0 | task 763 | total time = 514.20 ms / 409 tokens 0.10.340.471 I slot print_timing: id 0 | task 763 | graphs reused = 779 0.10.340.472 I slot print_timing: id 0 | task 763 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.340.500 I slot release: id 0 | task 763 | stop processing: n_tokens = 433, truncated = 0 0.10.361.287 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 10249431 0.10.376.111 I slot launch_slot_: id 0 | task 821 | processing task, is_child = 0 0.10.978.179 I slot print_timing: id 0 | task 821 | prompt eval time = 114.35 ms / 347 tokens ( 0.33 ms per token, 3034.62 tokens per second) 0.10.978.185 I slot print_timing: id 0 | task 821 | eval time = 487.71 ms / 68 tokens ( 7.28 ms per token, 137.38 tokens per second) 0.10.978.186 I slot print_timing: id 0 | task 821 | total time = 602.05 ms / 415 tokens 0.10.978.187 I slot print_timing: id 0 | task 821 | graphs reused = 845 0.10.978.188 I slot print_timing: id 0 | task 821 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.978.215 I slot release: id 0 | task 821 | stop processing: n_tokens = 439, truncated = 0 0.10.982.424 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 10887146 0.10.997.398 I slot launch_slot_: id 0 | task 890 | processing task, is_child = 0 0.11.486.027 I slot print_timing: id 0 | task 890 | prompt eval time = 102.26 ms / 320 tokens ( 0.32 ms per token, 3129.31 tokens per second) 0.11.486.032 I slot print_timing: id 0 | task 890 | eval time = 386.36 ms / 55 tokens ( 7.15 ms per token, 139.77 tokens per second) 0.11.486.033 I slot print_timing: id 0 | task 890 | total time = 488.62 ms / 375 tokens 0.11.486.034 I slot print_timing: id 0 | task 890 | graphs reused = 898 0.11.486.035 I slot print_timing: id 0 | task 890 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.486.062 I slot release: id 0 | task 890 | stop processing: n_tokens = 399, truncated = 0 0.11.506.521 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 399, t_last = 11394993 0.11.520.237 I slot launch_slot_: id 0 | task 946 | processing task, is_child = 0 0.11.943.294 I slot print_timing: id 0 | task 946 | prompt eval time = 114.23 ms / 343 tokens ( 0.33 ms per token, 3002.82 tokens per second) 0.11.943.299 I slot print_timing: id 0 | task 946 | eval time = 308.82 ms / 44 tokens ( 7.18 ms per token, 139.24 tokens per second) 0.11.943.300 I slot print_timing: id 0 | task 946 | total time = 423.04 ms / 387 tokens 0.11.943.301 I slot print_timing: id 0 | task 946 | graphs reused = 940 0.11.943.302 I slot print_timing: id 0 | task 946 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.943.328 I slot release: id 0 | task 946 | stop processing: n_tokens = 411, truncated = 0 0.11.958.139 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 11852259 0.11.972.066 I slot launch_slot_: id 0 | task 991 | processing task, is_child = 0 0.12.475.085 I slot print_timing: id 0 | task 991 | prompt eval time = 102.56 ms / 325 tokens ( 0.32 ms per token, 3168.97 tokens per second) 0.12.475.091 I slot print_timing: id 0 | task 991 | eval time = 400.45 ms / 57 tokens ( 7.15 ms per token, 139.84 tokens per second) 0.12.475.092 I slot print_timing: id 0 | task 991 | total time = 503.00 ms / 382 tokens 0.12.475.092 I slot print_timing: id 0 | task 991 | graphs reused = 995 0.12.475.093 I slot print_timing: id 0 | task 991 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.475.120 I slot release: id 0 | task 991 | stop processing: n_tokens = 406, truncated = 0 0.12.504.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 12384051 0.12.518.149 I slot launch_slot_: id 0 | task 1049 | processing task, is_child = 0 0.12.922.493 I slot print_timing: id 0 | task 1049 | prompt eval time = 102.52 ms / 323 tokens ( 0.32 ms per token, 3150.64 tokens per second) 0.12.922.499 I slot print_timing: id 0 | task 1049 | eval time = 301.81 ms / 43 tokens ( 7.19 ms per token, 139.16 tokens per second) 0.12.922.500 I slot print_timing: id 0 | task 1049 | total time = 404.33 ms / 366 tokens 0.12.922.501 I slot print_timing: id 0 | task 1049 | graphs reused = 1036 0.12.922.502 I slot print_timing: id 0 | task 1049 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.922.530 I slot release: id 0 | task 1049 | stop processing: n_tokens = 390, truncated = 0 0.12.941.732 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 390, t_last = 12831461 0.12.955.004 I slot launch_slot_: id 0 | task 1093 | processing task, is_child = 0 0.13.574.042 I slot print_timing: id 0 | task 1093 | prompt eval time = 115.19 ms / 359 tokens ( 0.32 ms per token, 3116.70 tokens per second) 0.13.574.048 I slot print_timing: id 0 | task 1093 | eval time = 503.83 ms / 69 tokens ( 7.41 ms per token, 134.96 tokens per second) 0.13.574.049 I slot print_timing: id 0 | task 1093 | total time = 619.02 ms / 428 tokens 0.13.574.050 I slot print_timing: id 0 | task 1093 | graphs reused = 1103 0.13.574.050 I slot print_timing: id 0 | task 1093 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.574.079 I slot release: id 0 | task 1093 | stop processing: n_tokens = 452, truncated = 0 0.13.602.148 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 13483010 0.13.617.533 I slot launch_slot_: id 0 | task 1163 | processing task, is_child = 0 0.14.163.075 I slot print_timing: id 0 | task 1163 | prompt eval time = 102.62 ms / 334 tokens ( 0.31 ms per token, 3254.76 tokens per second) 0.14.163.081 I slot print_timing: id 0 | task 1163 | eval time = 442.91 ms / 63 tokens ( 7.14 ms per token, 139.98 tokens per second) 0.14.163.082 I slot print_timing: id 0 | task 1163 | total time = 545.52 ms / 397 tokens 0.14.163.082 I slot print_timing: id 0 | task 1163 | graphs reused = 1164 0.14.163.083 I slot print_timing: id 0 | task 1163 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.163.110 I slot release: id 0 | task 1163 | stop processing: n_tokens = 421, truncated = 0 0.14.189.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 14072041 0.14.204.137 I slot launch_slot_: id 0 | task 1227 | processing task, is_child = 0 0.14.832.072 I slot print_timing: id 0 | task 1227 | prompt eval time = 114.60 ms / 382 tokens ( 0.30 ms per token, 3333.33 tokens per second) 0.14.832.078 I slot print_timing: id 0 | task 1227 | eval time = 513.32 ms / 73 tokens ( 7.13 ms per token, 140.26 tokens per second) 0.14.832.079 I slot print_timing: id 0 | task 1227 | total time = 627.92 ms / 455 tokens 0.14.832.080 I slot print_timing: id 0 | task 1227 | graphs reused = 1235 0.14.832.080 I slot print_timing: id 0 | task 1227 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.832.107 I slot release: id 0 | task 1227 | stop processing: n_tokens = 479, truncated = 0 0.14.847.768 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 14741038 0.14.863.740 I slot launch_slot_: id 0 | task 1301 | processing task, is_child = 0 0.15.435.382 I slot print_timing: id 0 | task 1301 | prompt eval time = 115.38 ms / 368 tokens ( 0.31 ms per token, 3189.54 tokens per second) 0.15.435.388 I slot print_timing: id 0 | task 1301 | eval time = 456.25 ms / 65 tokens ( 7.13 ms per token, 140.27 tokens per second) 0.15.435.390 I slot print_timing: id 0 | task 1301 | total time = 571.63 ms / 433 tokens 0.15.435.391 I slot print_timing: id 0 | task 1301 | graphs reused = 1298 0.15.435.392 I slot print_timing: id 0 | task 1301 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.435.422 I slot release: id 0 | task 1301 | stop processing: n_tokens = 457, truncated = 0 0.15.455.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 15344354 0.15.471.124 I slot launch_slot_: id 0 | task 1367 | processing task, is_child = 0 0.16.203.708 I slot print_timing: id 0 | task 1367 | prompt eval time = 117.31 ms / 382 tokens ( 0.31 ms per token, 3256.27 tokens per second) 0.16.203.713 I slot print_timing: id 0 | task 1367 | eval time = 615.26 ms / 87 tokens ( 7.15 ms per token, 139.78 tokens per second) 0.16.203.714 I slot print_timing: id 0 | task 1367 | total time = 732.57 ms / 469 tokens 0.16.203.715 I slot print_timing: id 0 | task 1367 | graphs reused = 1383 0.16.203.716 I slot print_timing: id 0 | task 1367 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.203.746 I slot release: id 0 | task 1367 | stop processing: n_tokens = 493, truncated = 0 0.16.231.427 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 16112677 0.16.247.973 I slot launch_slot_: id 0 | task 1455 | processing task, is_child = 0 0.16.841.851 I slot print_timing: id 0 | task 1455 | prompt eval time = 137.72 ms / 410 tokens ( 0.34 ms per token, 2977.14 tokens per second) 0.16.841.857 I slot print_timing: id 0 | task 1455 | eval time = 456.15 ms / 65 tokens ( 7.13 ms per token, 140.31 tokens per second) 0.16.841.859 I slot print_timing: id 0 | task 1455 | total time = 593.86 ms / 475 tokens 0.16.841.859 I slot print_timing: id 0 | task 1455 | graphs reused = 1446 0.16.841.860 I slot print_timing: id 0 | task 1455 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.841.890 I slot release: id 0 | task 1455 | stop processing: n_tokens = 499, truncated = 0 0.16.865.794 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 16750821 0.16.882.352 I slot launch_slot_: id 0 | task 1521 | processing task, is_child = 0 0.17.453.833 I slot print_timing: id 0 | task 1521 | prompt eval time = 115.08 ms / 367 tokens ( 0.31 ms per token, 3189.06 tokens per second) 0.17.453.839 I slot print_timing: id 0 | task 1521 | eval time = 456.39 ms / 65 tokens ( 7.13 ms per token, 140.23 tokens per second) 0.17.453.841 I slot print_timing: id 0 | task 1521 | total time = 571.47 ms / 432 tokens 0.17.453.841 I slot print_timing: id 0 | task 1521 | graphs reused = 1509 0.17.453.842 I slot print_timing: id 0 | task 1521 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.453.871 I slot release: id 0 | task 1521 | stop processing: n_tokens = 458, truncated = 0 0.17.475.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 17362802 0.17.491.131 I slot launch_slot_: id 0 | task 1587 | processing task, is_child = 0 0.17.973.276 I slot print_timing: id 0 | task 1587 | prompt eval time = 103.14 ms / 326 tokens ( 0.32 ms per token, 3160.60 tokens per second) 0.17.973.282 I slot print_timing: id 0 | task 1587 | eval time = 378.99 ms / 54 tokens ( 7.15 ms per token, 139.85 tokens per second) 0.17.973.283 I slot print_timing: id 0 | task 1587 | total time = 482.13 ms / 380 tokens 0.17.973.284 I slot print_timing: id 0 | task 1587 | graphs reused = 1561 0.17.973.284 I slot print_timing: id 0 | task 1587 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.973.311 I slot release: id 0 | task 1587 | stop processing: n_tokens = 404, truncated = 0 0.17.995.429 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 17882242 0.18.009.162 I slot launch_slot_: id 0 | task 1642 | processing task, is_child = 0 0.18.574.610 I slot print_timing: id 0 | task 1642 | prompt eval time = 114.60 ms / 351 tokens ( 0.33 ms per token, 3062.80 tokens per second) 0.18.574.617 I slot print_timing: id 0 | task 1642 | eval time = 450.83 ms / 64 tokens ( 7.16 ms per token, 139.74 tokens per second) 0.18.574.618 I slot print_timing: id 0 | task 1642 | total time = 565.43 ms / 415 tokens 0.18.574.619 I slot print_timing: id 0 | task 1642 | graphs reused = 1623 0.18.574.620 I slot print_timing: id 0 | task 1642 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.574.652 I slot release: id 0 | task 1642 | stop processing: n_tokens = 441, truncated = 0 0.18.588.655 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 441, t_last = 18483583 0.18.603.573 I slot launch_slot_: id 0 | task 1707 | processing task, is_child = 0 0.19.275.691 I slot print_timing: id 0 | task 1707 | prompt eval time = 114.63 ms / 379 tokens ( 0.30 ms per token, 3306.32 tokens per second) 0.19.275.697 I slot print_timing: id 0 | task 1707 | eval time = 557.48 ms / 78 tokens ( 7.24 ms per token, 138.12 tokens per second) 0.19.275.698 I slot print_timing: id 0 | task 1707 | total time = 672.10 ms / 457 tokens 0.19.275.699 I slot print_timing: id 0 | task 1707 | graphs reused = 1699 0.19.275.699 I slot print_timing: id 0 | task 1707 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.275.729 I slot release: id 0 | task 1707 | stop processing: n_tokens = 481, truncated = 0 0.19.299.754 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 19184660 0.19.315.994 I slot launch_slot_: id 0 | task 1786 | processing task, is_child = 0 0.19.930.958 I slot print_timing: id 0 | task 1786 | prompt eval time = 114.71 ms / 356 tokens ( 0.32 ms per token, 3103.42 tokens per second) 0.19.930.965 I slot print_timing: id 0 | task 1786 | eval time = 500.24 ms / 70 tokens ( 7.25 ms per token, 137.93 tokens per second) 0.19.930.966 I slot print_timing: id 0 | task 1786 | total time = 614.95 ms / 426 tokens 0.19.930.967 I slot print_timing: id 0 | task 1786 | graphs reused = 1767 0.19.930.969 I slot print_timing: id 0 | task 1786 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.931.000 I slot release: id 0 | task 1786 | stop processing: n_tokens = 450, truncated = 0 0.19.935.454 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 19839931 0.19.950.599 I slot launch_slot_: id 0 | task 1857 | processing task, is_child = 0 0.20.481.391 I slot print_timing: id 0 | task 1857 | prompt eval time = 102.82 ms / 331 tokens ( 0.31 ms per token, 3219.25 tokens per second) 0.20.481.396 I slot print_timing: id 0 | task 1857 | eval time = 427.96 ms / 61 tokens ( 7.13 ms per token, 140.20 tokens per second) 0.20.481.397 I slot print_timing: id 0 | task 1857 | total time = 530.78 ms / 392 tokens 0.20.481.398 I slot print_timing: id 0 | task 1857 | graphs reused = 1826 0.20.481.399 I slot print_timing: id 0 | task 1857 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.481.425 I slot release: id 0 | task 1857 | stop processing: n_tokens = 416, truncated = 0 0.20.485.531 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 20390357 0.20.499.583 I slot launch_slot_: id 0 | task 1919 | processing task, is_child = 0 0.21.055.702 I slot print_timing: id 0 | task 1919 | prompt eval time = 103.01 ms / 334 tokens ( 0.31 ms per token, 3242.53 tokens per second) 0.21.055.707 I slot print_timing: id 0 | task 1919 | eval time = 453.10 ms / 62 tokens ( 7.43 ms per token, 134.63 tokens per second) 0.21.055.709 I slot print_timing: id 0 | task 1919 | total time = 556.10 ms / 396 tokens 0.21.055.709 I slot print_timing: id 0 | task 1919 | graphs reused = 1886 0.21.055.710 I slot print_timing: id 0 | task 1919 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.055.737 I slot release: id 0 | task 1919 | stop processing: n_tokens = 420, truncated = 0 0.21.084.022 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 20964668 0.21.098.117 I slot launch_slot_: id 0 | task 1982 | processing task, is_child = 0 0.21.690.649 I slot print_timing: id 0 | task 1982 | prompt eval time = 114.90 ms / 362 tokens ( 0.32 ms per token, 3150.65 tokens per second) 0.21.690.654 I slot print_timing: id 0 | task 1982 | eval time = 477.62 ms / 68 tokens ( 7.13 ms per token, 140.28 tokens per second) 0.21.690.655 I slot print_timing: id 0 | task 1982 | total time = 592.52 ms / 430 tokens 0.21.690.656 I slot print_timing: id 0 | task 1982 | graphs reused = 1952 0.21.690.657 I slot print_timing: id 0 | task 1982 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.690.685 I slot release: id 0 | task 1982 | stop processing: n_tokens = 454, truncated = 0 0.21.719.685 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 21599616 0.21.735.598 I slot launch_slot_: id 0 | task 2051 | processing task, is_child = 0 0.22.313.853 I slot print_timing: id 0 | task 2051 | prompt eval time = 114.58 ms / 384 tokens ( 0.30 ms per token, 3351.25 tokens per second) 0.22.313.859 I slot print_timing: id 0 | task 2051 | eval time = 463.65 ms / 66 tokens ( 7.13 ms per token, 140.19 tokens per second) 0.22.313.860 I slot print_timing: id 0 | task 2051 | total time = 578.23 ms / 450 tokens 0.22.313.861 I slot print_timing: id 0 | task 2051 | graphs reused = 2016 0.22.313.862 I slot print_timing: id 0 | task 2051 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.313.892 I slot release: id 0 | task 2051 | stop processing: n_tokens = 474, truncated = 0 0.22.331.611 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 22222823 0.22.347.295 I slot launch_slot_: id 0 | task 2118 | processing task, is_child = 0 0.22.844.447 I slot print_timing: id 0 | task 2118 | prompt eval time = 102.83 ms / 325 tokens ( 0.32 ms per token, 3160.68 tokens per second) 0.22.844.454 I slot print_timing: id 0 | task 2118 | eval time = 394.31 ms / 55 tokens ( 7.30 ms per token, 136.95 tokens per second) 0.22.844.455 I slot print_timing: id 0 | task 2118 | total time = 497.14 ms / 380 tokens 0.22.844.455 I slot print_timing: id 0 | task 2118 | graphs reused = 2069 0.22.844.456 I slot print_timing: id 0 | task 2118 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.844.484 I slot release: id 0 | task 2118 | stop processing: n_tokens = 404, truncated = 0 0.22.848.607 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 22753415 0.22.862.405 I slot launch_slot_: id 0 | task 2174 | processing task, is_child = 0 0.23.400.726 I slot print_timing: id 0 | task 2174 | prompt eval time = 115.33 ms / 366 tokens ( 0.32 ms per token, 3173.39 tokens per second) 0.23.400.732 I slot print_timing: id 0 | task 2174 | eval time = 422.97 ms / 59 tokens ( 7.29 ms per token, 137.13 tokens per second) 0.23.400.733 I slot print_timing: id 0 | task 2174 | total time = 538.30 ms / 425 tokens 0.23.400.734 I slot print_timing: id 0 | task 2174 | graphs reused = 2126 0.23.400.735 I slot print_timing: id 0 | task 2174 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.400.762 I slot release: id 0 | task 2174 | stop processing: n_tokens = 449, truncated = 0 0.23.425.642 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 23309693 0.23.440.726 I slot launch_slot_: id 0 | task 2234 | processing task, is_child = 0 0.23.794.136 I slot print_timing: id 0 | task 2234 | prompt eval time = 101.68 ms / 295 tokens ( 0.34 ms per token, 2901.32 tokens per second) 0.23.794.141 I slot print_timing: id 0 | task 2234 | eval time = 251.72 ms / 36 tokens ( 7.19 ms per token, 139.05 tokens per second) 0.23.794.142 I slot print_timing: id 0 | task 2234 | total time = 353.39 ms / 331 tokens 0.23.794.143 I slot print_timing: id 0 | task 2234 | graphs reused = 2160 0.23.794.144 I slot print_timing: id 0 | task 2234 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.794.171 I slot release: id 0 | task 2234 | stop processing: n_tokens = 355, truncated = 0 0.23.798.239 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 23703102 0.23.811.256 I slot launch_slot_: id 0 | task 2271 | processing task, is_child = 0 0.24.265.125 I slot print_timing: id 0 | task 2271 | prompt eval time = 102.11 ms / 307 tokens ( 0.33 ms per token, 3006.68 tokens per second) 0.24.265.131 I slot print_timing: id 0 | task 2271 | eval time = 351.75 ms / 50 tokens ( 7.18 ms per token, 139.31 tokens per second) 0.24.265.133 I slot print_timing: id 0 | task 2271 | total time = 453.85 ms / 357 tokens 0.24.265.134 I slot print_timing: id 0 | task 2271 | graphs reused = 2208 0.24.265.135 I slot print_timing: id 0 | task 2271 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.265.165 I slot release: id 0 | task 2271 | stop processing: n_tokens = 381, truncated = 0 0.24.288.410 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 24174096 0.24.301.515 I slot launch_slot_: id 0 | task 2322 | processing task, is_child = 0 0.24.670.039 I slot print_timing: id 0 | task 2322 | prompt eval time = 102.56 ms / 319 tokens ( 0.32 ms per token, 3110.34 tokens per second) 0.24.670.045 I slot print_timing: id 0 | task 2322 | eval time = 265.95 ms / 38 tokens ( 7.19 ms per token, 139.12 tokens per second) 0.24.670.046 I slot print_timing: id 0 | task 2322 | total time = 368.51 ms / 357 tokens 0.24.670.048 I slot print_timing: id 0 | task 2322 | graphs reused = 2244 0.24.670.048 I slot print_timing: id 0 | task 2322 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.670.077 I slot release: id 0 | task 2322 | stop processing: n_tokens = 381, truncated = 0 0.24.693.727 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 24579008 0.24.707.048 I slot launch_slot_: id 0 | task 2361 | processing task, is_child = 0 0.25.181.041 I slot print_timing: id 0 | task 2361 | prompt eval time = 102.34 ms / 315 tokens ( 0.32 ms per token, 3078.07 tokens per second) 0.25.181.047 I slot print_timing: id 0 | task 2361 | eval time = 371.64 ms / 53 tokens ( 7.15 ms per token, 139.92 tokens per second) 0.25.181.049 I slot print_timing: id 0 | task 2361 | total time = 473.98 ms / 368 tokens 0.25.181.049 I slot print_timing: id 0 | task 2361 | graphs reused = 2295 0.25.181.050 I slot print_timing: id 0 | task 2361 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.181.076 I slot release: id 0 | task 2361 | stop processing: n_tokens = 392, truncated = 0 0.25.207.387 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 25090007 0.25.221.261 I slot launch_slot_: id 0 | task 2415 | processing task, is_child = 0 0.25.743.336 I slot print_timing: id 0 | task 2415 | prompt eval time = 115.15 ms / 367 tokens ( 0.31 ms per token, 3187.06 tokens per second) 0.25.743.341 I slot print_timing: id 0 | task 2415 | eval time = 406.91 ms / 58 tokens ( 7.14 ms per token, 140.08 tokens per second) 0.25.743.342 I slot print_timing: id 0 | task 2415 | total time = 522.06 ms / 425 tokens 0.25.743.343 I slot print_timing: id 0 | task 2415 | graphs reused = 2351 0.25.743.344 I slot print_timing: id 0 | task 2415 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.743.373 I slot release: id 0 | task 2415 | stop processing: n_tokens = 449, truncated = 0 0.25.747.897 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 25652304 0.25.763.624 I slot launch_slot_: id 0 | task 2474 | processing task, is_child = 0 0.26.475.535 I slot print_timing: id 0 | task 2474 | prompt eval time = 157.92 ms / 499 tokens ( 0.32 ms per token, 3159.79 tokens per second) 0.26.475.541 I slot print_timing: id 0 | task 2474 | eval time = 553.97 ms / 76 tokens ( 7.39 ms per token, 135.39 tokens per second) 0.26.475.542 I slot print_timing: id 0 | task 2474 | total time = 711.89 ms / 575 tokens 0.26.475.543 I slot print_timing: id 0 | task 2474 | graphs reused = 2425 0.26.475.544 I slot print_timing: id 0 | task 2474 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.475.575 I slot release: id 0 | task 2474 | stop processing: n_tokens = 599, truncated = 0 0.26.500.144 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 599, t_last = 26384506 0.26.519.650 I slot launch_slot_: id 0 | task 2551 | processing task, is_child = 0 0.26.973.502 I slot print_timing: id 0 | task 2551 | prompt eval time = 102.60 ms / 319 tokens ( 0.32 ms per token, 3109.25 tokens per second) 0.26.973.508 I slot print_timing: id 0 | task 2551 | eval time = 351.24 ms / 50 tokens ( 7.17 ms per token, 139.51 tokens per second) 0.26.973.509 I slot print_timing: id 0 | task 2551 | total time = 453.84 ms / 369 tokens 0.26.973.511 I slot print_timing: id 0 | task 2551 | graphs reused = 2473 0.26.973.512 I slot print_timing: id 0 | task 2551 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.973.541 I slot release: id 0 | task 2551 | stop processing: n_tokens = 393, truncated = 0 0.27.000.163 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 26882472 0.27.014.103 I slot launch_slot_: id 0 | task 2602 | processing task, is_child = 0 0.27.535.827 I slot print_timing: id 0 | task 2602 | prompt eval time = 114.61 ms / 348 tokens ( 0.33 ms per token, 3036.28 tokens per second) 0.27.535.833 I slot print_timing: id 0 | task 2602 | eval time = 407.09 ms / 58 tokens ( 7.14 ms per token, 140.02 tokens per second) 0.27.535.834 I slot print_timing: id 0 | task 2602 | total time = 521.71 ms / 406 tokens 0.27.535.835 I slot print_timing: id 0 | task 2602 | graphs reused = 2529 0.27.535.836 I slot print_timing: id 0 | task 2602 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.535.866 I slot release: id 0 | task 2602 | stop processing: n_tokens = 430, truncated = 0 0.27.565.002 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 27444797 0.27.579.855 I slot launch_slot_: id 0 | task 2661 | processing task, is_child = 0 0.28.244.879 I slot print_timing: id 0 | task 2661 | prompt eval time = 137.80 ms / 404 tokens ( 0.34 ms per token, 2931.72 tokens per second) 0.28.244.885 I slot print_timing: id 0 | task 2661 | eval time = 527.21 ms / 75 tokens ( 7.12 ms per token, 140.36 tokens per second) 0.28.244.886 I slot print_timing: id 0 | task 2661 | total time = 665.01 ms / 479 tokens 0.28.244.887 I slot print_timing: id 0 | task 2661 | graphs reused = 2602 0.28.244.888 I slot print_timing: id 0 | task 2661 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.244.917 I slot release: id 0 | task 2661 | stop processing: n_tokens = 503, truncated = 0 0.28.267.433 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 28153848 0.28.284.033 I slot launch_slot_: id 0 | task 2737 | processing task, is_child = 0 0.28.949.170 I slot print_timing: id 0 | task 2737 | prompt eval time = 137.64 ms / 408 tokens ( 0.34 ms per token, 2964.17 tokens per second) 0.28.949.176 I slot print_timing: id 0 | task 2737 | eval time = 527.48 ms / 75 tokens ( 7.13 ms per token, 140.29 tokens per second) 0.28.949.177 I slot print_timing: id 0 | task 2737 | total time = 665.12 ms / 483 tokens 0.28.949.178 I slot print_timing: id 0 | task 2737 | graphs reused = 2675 0.28.949.179 I slot print_timing: id 0 | task 2737 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.949.208 I slot release: id 0 | task 2737 | stop processing: n_tokens = 509, truncated = 0 0.28.974.147 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 509, t_last = 28858139 0.28.990.972 I slot launch_slot_: id 0 | task 2813 | processing task, is_child = 0 0.29.437.624 I slot print_timing: id 0 | task 2813 | prompt eval time = 102.67 ms / 325 tokens ( 0.32 ms per token, 3165.33 tokens per second) 0.29.437.629 I slot print_timing: id 0 | task 2813 | eval time = 343.96 ms / 49 tokens ( 7.17 ms per token, 139.55 tokens per second) 0.29.437.630 I slot print_timing: id 0 | task 2813 | total time = 446.64 ms / 374 tokens 0.29.437.631 I slot print_timing: id 0 | task 2813 | graphs reused = 2722 0.29.437.632 I slot print_timing: id 0 | task 2813 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.437.659 I slot release: id 0 | task 2813 | stop processing: n_tokens = 402, truncated = 0 0.29.460.569 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 29346590 0.29.474.751 I slot launch_slot_: id 0 | task 2863 | processing task, is_child = 0 0.29.961.319 I slot print_timing: id 0 | task 2863 | prompt eval time = 114.64 ms / 345 tokens ( 0.33 ms per token, 3009.45 tokens per second) 0.29.961.324 I slot print_timing: id 0 | task 2863 | eval time = 371.91 ms / 53 tokens ( 7.15 ms per token, 139.82 tokens per second) 0.29.961.326 I slot print_timing: id 0 | task 2863 | total time = 486.55 ms / 398 tokens 0.29.961.326 I slot print_timing: id 0 | task 2863 | graphs reused = 2773 0.29.961.327 I slot print_timing: id 0 | task 2863 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.961.354 I slot release: id 0 | task 2863 | stop processing: n_tokens = 422, truncated = 0 0.29.987.709 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 29870285 0.30.002.337 I slot launch_slot_: id 0 | task 2917 | processing task, is_child = 0 0.30.467.868 I slot print_timing: id 0 | task 2917 | prompt eval time = 114.34 ms / 344 tokens ( 0.33 ms per token, 3008.52 tokens per second) 0.30.467.874 I slot print_timing: id 0 | task 2917 | eval time = 351.18 ms / 50 tokens ( 7.17 ms per token, 139.53 tokens per second) 0.30.467.875 I slot print_timing: id 0 | task 2917 | total time = 465.52 ms / 394 tokens 0.30.467.875 I slot print_timing: id 0 | task 2917 | graphs reused = 2821 0.30.467.876 I slot print_timing: id 0 | task 2917 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.467.905 I slot release: id 0 | task 2917 | stop processing: n_tokens = 418, truncated = 0 0.30.472.310 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 30376836 0.30.486.533 I slot launch_slot_: id 0 | task 2968 | processing task, is_child = 0 0.31.121.636 I slot print_timing: id 0 | task 2968 | prompt eval time = 114.74 ms / 378 tokens ( 0.30 ms per token, 3294.46 tokens per second) 0.31.121.642 I slot print_timing: id 0 | task 2968 | eval time = 520.35 ms / 74 tokens ( 7.13 ms per token, 140.29 tokens per second) 0.31.121.643 I slot print_timing: id 0 | task 2968 | total time = 635.09 ms / 452 tokens 0.31.121.644 I slot print_timing: id 0 | task 2968 | graphs reused = 2893 0.31.121.645 I slot print_timing: id 0 | task 2968 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.121.675 I slot release: id 0 | task 2968 | stop processing: n_tokens = 476, truncated = 0 0.31.137.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 31030606 0.31.153.923 I slot launch_slot_: id 0 | task 3043 | processing task, is_child = 0 0.31.685.102 I slot print_timing: id 0 | task 3043 | prompt eval time = 102.93 ms / 331 tokens ( 0.31 ms per token, 3215.75 tokens per second) 0.31.685.108 I slot print_timing: id 0 | task 3043 | eval time = 428.23 ms / 61 tokens ( 7.14 ms per token, 140.11 tokens per second) 0.31.685.109 I slot print_timing: id 0 | task 3043 | total time = 531.16 ms / 392 tokens 0.31.685.109 I slot print_timing: id 0 | task 3043 | graphs reused = 2952 0.31.685.110 I slot print_timing: id 0 | task 3043 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.685.139 I slot release: id 0 | task 3043 | stop processing: n_tokens = 416, truncated = 0 0.31.711.560 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 31594070 0.31.725.981 I slot launch_slot_: id 0 | task 3105 | processing task, is_child = 0 0.32.292.978 I slot print_timing: id 0 | task 3105 | prompt eval time = 137.28 ms / 387 tokens ( 0.35 ms per token, 2819.08 tokens per second) 0.32.292.983 I slot print_timing: id 0 | task 3105 | eval time = 429.70 ms / 61 tokens ( 7.16 ms per token, 139.63 tokens per second) 0.32.292.985 I slot print_timing: id 0 | task 3105 | total time = 566.98 ms / 448 tokens 0.32.292.986 I slot print_timing: id 0 | task 3105 | graphs reused = 3011 0.32.292.986 I slot print_timing: id 0 | task 3105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.293.016 I slot release: id 0 | task 3105 | stop processing: n_tokens = 472, truncated = 0 0.32.315.770 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 472, t_last = 32201947 0.32.331.732 I slot launch_slot_: id 0 | task 3167 | processing task, is_child = 0 0.32.973.257 I slot print_timing: id 0 | task 3167 | prompt eval time = 114.30 ms / 345 tokens ( 0.33 ms per token, 3018.37 tokens per second) 0.32.973.263 I slot print_timing: id 0 | task 3167 | eval time = 527.21 ms / 75 tokens ( 7.12 ms per token, 140.36 tokens per second) 0.32.973.264 I slot print_timing: id 0 | task 3167 | total time = 641.51 ms / 420 tokens 0.32.973.265 I slot print_timing: id 0 | task 3167 | graphs reused = 3084 0.32.973.265 I slot print_timing: id 0 | task 3167 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.973.292 I slot release: id 0 | task 3167 | stop processing: n_tokens = 444, truncated = 0 0.32.977.492 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 32882223 0.32.992.820 I slot launch_slot_: id 0 | task 3243 | processing task, is_child = 0 0.33.554.051 I slot print_timing: id 0 | task 3243 | prompt eval time = 114.37 ms / 337 tokens ( 0.34 ms per token, 2946.58 tokens per second) 0.33.554.058 I slot print_timing: id 0 | task 3243 | eval time = 446.84 ms / 61 tokens ( 7.45 ms per token, 134.28 tokens per second) 0.33.554.059 I slot print_timing: id 0 | task 3243 | total time = 561.21 ms / 398 tokens 0.33.554.060 I slot print_timing: id 0 | task 3243 | graphs reused = 3143 0.33.554.060 I slot print_timing: id 0 | task 3243 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.554.090 I slot release: id 0 | task 3243 | stop processing: n_tokens = 422, truncated = 0 0.33.579.884 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 33463021 0.33.594.670 I slot launch_slot_: id 0 | task 3305 | processing task, is_child = 0 0.34.431.988 I slot print_timing: id 0 | task 3305 | prompt eval time = 155.19 ms / 463 tokens ( 0.34 ms per token, 2983.48 tokens per second) 0.34.431.994 I slot print_timing: id 0 | task 3305 | eval time = 682.11 ms / 95 tokens ( 7.26 ms per token, 137.81 tokens per second) 0.34.431.995 I slot print_timing: id 0 | task 3305 | total time = 837.30 ms / 558 tokens 0.34.431.997 I slot print_timing: id 0 | task 3305 | graphs reused = 3235 0.34.431.998 I slot print_timing: id 0 | task 3305 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.432.030 I slot release: id 0 | task 3305 | stop processing: n_tokens = 582, truncated = 0 0.34.450.039 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 34340961 0.34.469.452 I slot launch_slot_: id 0 | task 3401 | processing task, is_child = 0 0.35.386.651 I slot print_timing: id 0 | task 3401 | prompt eval time = 138.62 ms / 440 tokens ( 0.32 ms per token, 3174.03 tokens per second) 0.35.386.656 I slot print_timing: id 0 | task 3401 | eval time = 778.56 ms / 109 tokens ( 7.21 ms per token, 138.72 tokens per second) 0.35.386.657 I slot print_timing: id 0 | task 3401 | total time = 917.18 ms / 549 tokens 0.35.386.658 I slot print_timing: id 0 | task 3401 | graphs reused = 3341 0.35.386.659 I slot print_timing: id 0 | task 3401 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.386.690 I slot release: id 0 | task 3401 | stop processing: n_tokens = 573, truncated = 0 0.35.415.912 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 573, t_last = 35295621 0.35.434.950 I slot launch_slot_: id 0 | task 3511 | processing task, is_child = 0 0.35.980.270 I slot print_timing: id 0 | task 3511 | prompt eval time = 102.81 ms / 336 tokens ( 0.31 ms per token, 3268.20 tokens per second) 0.35.980.275 I slot print_timing: id 0 | task 3511 | eval time = 442.50 ms / 63 tokens ( 7.14 ms per token, 140.11 tokens per second) 0.35.980.277 I slot print_timing: id 0 | task 3511 | total time = 545.31 ms / 399 tokens 0.35.980.278 I slot print_timing: id 0 | task 3511 | graphs reused = 3402 0.35.980.278 I slot print_timing: id 0 | task 3511 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.980.307 I slot release: id 0 | task 3511 | stop processing: n_tokens = 423, truncated = 0 0.36.007.739 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 423, t_last = 35889238 0.36.022.422 I slot launch_slot_: id 0 | task 3575 | processing task, is_child = 0 0.36.537.698 I slot print_timing: id 0 | task 3575 | prompt eval time = 115.14 ms / 367 tokens ( 0.31 ms per token, 3187.51 tokens per second) 0.36.537.705 I slot print_timing: id 0 | task 3575 | eval time = 400.12 ms / 57 tokens ( 7.15 ms per token, 139.96 tokens per second) 0.36.537.706 I slot print_timing: id 0 | task 3575 | total time = 515.26 ms / 424 tokens 0.36.537.707 I slot print_timing: id 0 | task 3575 | graphs reused = 3457 0.36.537.708 I slot print_timing: id 0 | task 3575 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.537.739 I slot release: id 0 | task 3575 | stop processing: n_tokens = 448, truncated = 0 0.36.552.212 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 36446670 0.36.567.486 I slot launch_slot_: id 0 | task 3633 | processing task, is_child = 0 0.37.035.153 I slot print_timing: id 0 | task 3633 | prompt eval time = 102.94 ms / 327 tokens ( 0.31 ms per token, 3176.52 tokens per second) 0.37.035.159 I slot print_timing: id 0 | task 3633 | eval time = 364.71 ms / 52 tokens ( 7.15 ms per token, 139.84 tokens per second) 0.37.035.160 I slot print_timing: id 0 | task 3633 | total time = 467.65 ms / 379 tokens 0.37.035.160 I slot print_timing: id 0 | task 3633 | graphs reused = 3507 0.37.035.161 I slot print_timing: id 0 | task 3633 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.035.187 I slot release: id 0 | task 3633 | stop processing: n_tokens = 403, truncated = 0 0.37.056.558 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 36944118 0.37.070.776 I slot launch_slot_: id 0 | task 3686 | processing task, is_child = 0 0.37.751.393 I slot print_timing: id 0 | task 3686 | prompt eval time = 137.45 ms / 393 tokens ( 0.35 ms per token, 2859.20 tokens per second) 0.37.751.399 I slot print_timing: id 0 | task 3686 | eval time = 543.15 ms / 76 tokens ( 7.24 ms per token, 138.08 tokens per second) 0.37.751.400 I slot print_timing: id 0 | task 3686 | total time = 680.60 ms / 469 tokens 0.37.751.401 I slot print_timing: id 0 | task 3686 | graphs reused = 3581 0.37.751.401 I slot print_timing: id 0 | task 3686 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.751.432 I slot release: id 0 | task 3686 | stop processing: n_tokens = 493, truncated = 0 0.37.781.222 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 37660363 0.37.798.070 I slot launch_slot_: id 0 | task 3763 | processing task, is_child = 0 0.38.413.850 I slot print_timing: id 0 | task 3763 | prompt eval time = 174.03 ms / 524 tokens ( 0.33 ms per token, 3010.92 tokens per second) 0.38.413.856 I slot print_timing: id 0 | task 3763 | eval time = 441.73 ms / 62 tokens ( 7.24 ms per token, 138.09 tokens per second) 0.38.413.857 I slot print_timing: id 0 | task 3763 | total time = 615.76 ms / 586 tokens 0.38.413.858 I slot print_timing: id 0 | task 3763 | graphs reused = 3641 0.38.413.859 I slot print_timing: id 0 | task 3763 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.413.890 I slot release: id 0 | task 3763 | stop processing: n_tokens = 610, truncated = 0 0.38.430.985 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 38322821 0.38.451.020 I slot launch_slot_: id 0 | task 3826 | processing task, is_child = 0 0.39.083.639 I slot print_timing: id 0 | task 3826 | prompt eval time = 197.81 ms / 602 tokens ( 0.33 ms per token, 3043.31 tokens per second) 0.39.083.645 I slot print_timing: id 0 | task 3826 | eval time = 434.79 ms / 61 tokens ( 7.25 ms per token, 138.00 tokens per second) 0.39.083.646 I slot print_timing: id 0 | task 3826 | total time = 632.60 ms / 663 tokens 0.39.083.647 I slot print_timing: id 0 | task 3826 | graphs reused = 3700 0.39.083.648 I slot print_timing: id 0 | task 3826 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.083.682 I slot release: id 0 | task 3826 | stop processing: n_tokens = 687, truncated = 0 0.39.105.304 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 38992613 0.39.127.392 I slot launch_slot_: id 0 | task 3888 | processing task, is_child = 0 0.39.778.373 I slot print_timing: id 0 | task 3888 | prompt eval time = 202.02 ms / 640 tokens ( 0.32 ms per token, 3167.94 tokens per second) 0.39.778.378 I slot print_timing: id 0 | task 3888 | eval time = 448.94 ms / 63 tokens ( 7.24 ms per token, 138.10 tokens per second) 0.39.778.380 I slot print_timing: id 0 | task 3888 | total time = 650.97 ms / 703 tokens 0.39.778.380 I slot print_timing: id 0 | task 3888 | graphs reused = 3761 0.39.778.382 I slot print_timing: id 0 | task 3888 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.778.421 I slot release: id 0 | task 3888 | stop processing: n_tokens = 727, truncated = 0 0.39.802.436 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 39687352 0.39.825.553 I slot launch_slot_: id 0 | task 3952 | processing task, is_child = 0 0.40.469.610 I slot print_timing: id 0 | task 3952 | prompt eval time = 202.00 ms / 629 tokens ( 0.32 ms per token, 3113.78 tokens per second) 0.40.469.616 I slot print_timing: id 0 | task 3952 | eval time = 442.04 ms / 62 tokens ( 7.25 ms per token, 138.00 tokens per second) 0.40.469.617 I slot print_timing: id 0 | task 3952 | total time = 644.04 ms / 691 tokens 0.40.469.618 I slot print_timing: id 0 | task 3952 | graphs reused = 3821 0.40.469.619 I slot print_timing: id 0 | task 3952 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.469.653 I slot release: id 0 | task 3952 | stop processing: n_tokens = 715, truncated = 0 0.40.489.460 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 40378584 0.40.512.295 I slot launch_slot_: id 0 | task 4015 | processing task, is_child = 0 0.41.074.220 I slot print_timing: id 0 | task 4015 | prompt eval time = 154.85 ms / 458 tokens ( 0.34 ms per token, 2957.68 tokens per second) 0.41.074.226 I slot print_timing: id 0 | task 4015 | eval time = 407.06 ms / 57 tokens ( 7.27 ms per token, 137.57 tokens per second) 0.41.074.227 I slot print_timing: id 0 | task 4015 | total time = 561.91 ms / 515 tokens 0.41.074.228 I slot print_timing: id 0 | task 4015 | graphs reused = 3875 0.41.074.229 I slot print_timing: id 0 | task 4015 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.074.260 I slot release: id 0 | task 4015 | stop processing: n_tokens = 539, truncated = 0 0.41.080.210 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 40983191 0.41.098.184 I slot launch_slot_: id 0 | task 4073 | processing task, is_child = 0 0.41.739.234 I slot print_timing: id 0 | task 4073 | prompt eval time = 191.82 ms / 594 tokens ( 0.32 ms per token, 3096.62 tokens per second) 0.41.739.240 I slot print_timing: id 0 | task 4073 | eval time = 449.21 ms / 63 tokens ( 7.25 ms per token, 138.02 tokens per second) 0.41.739.241 I slot print_timing: id 0 | task 4073 | total time = 641.04 ms / 657 tokens 0.41.739.242 I slot print_timing: id 0 | task 4073 | graphs reused = 3936 0.41.739.243 I slot print_timing: id 0 | task 4073 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.739.279 I slot release: id 0 | task 4073 | stop processing: n_tokens = 681, truncated = 0 0.41.767.750 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 681, t_last = 41648210 0.41.789.857 I slot launch_slot_: id 0 | task 4137 | processing task, is_child = 0 0.42.336.505 I slot print_timing: id 0 | task 4137 | prompt eval time = 183.52 ms / 572 tokens ( 0.32 ms per token, 3116.88 tokens per second) 0.42.336.511 I slot print_timing: id 0 | task 4137 | eval time = 363.11 ms / 51 tokens ( 7.26 ms per token, 137.70 tokens per second) 0.42.336.512 I slot print_timing: id 0 | task 4137 | total time = 546.63 ms / 623 tokens 0.42.336.513 I slot print_timing: id 0 | task 4137 | graphs reused = 3985 0.42.336.514 I slot print_timing: id 0 | task 4137 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.336.549 I slot release: id 0 | task 4137 | stop processing: n_tokens = 647, truncated = 0 0.42.358.080 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 647, t_last = 42245480 0.42.379.959 I slot launch_slot_: id 0 | task 4189 | processing task, is_child = 0 0.42.893.889 I slot print_timing: id 0 | task 4189 | prompt eval time = 157.87 ms / 502 tokens ( 0.31 ms per token, 3179.77 tokens per second) 0.42.893.894 I slot print_timing: id 0 | task 4189 | eval time = 356.04 ms / 50 tokens ( 7.27 ms per token, 137.62 tokens per second) 0.42.893.895 I slot print_timing: id 0 | task 4189 | total time = 513.91 ms / 552 tokens 0.42.893.897 I slot print_timing: id 0 | task 4189 | graphs reused = 4033 0.42.893.898 I slot print_timing: id 0 | task 4189 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.893.930 I slot release: id 0 | task 4189 | stop processing: n_tokens = 576, truncated = 0 0.42.920.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 42802861 0.42.939.115 I slot launch_slot_: id 0 | task 4240 | processing task, is_child = 0 0.43.503.599 I slot print_timing: id 0 | task 4240 | prompt eval time = 155.24 ms / 479 tokens ( 0.32 ms per token, 3085.58 tokens per second) 0.43.503.605 I slot print_timing: id 0 | task 4240 | eval time = 409.23 ms / 57 tokens ( 7.31 ms per token, 136.84 tokens per second) 0.43.503.606 I slot print_timing: id 0 | task 4240 | total time = 564.47 ms / 536 tokens 0.43.503.607 I slot print_timing: id 0 | task 4240 | graphs reused = 4087 0.43.503.608 I slot print_timing: id 0 | task 4240 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.503.638 I slot release: id 0 | task 4240 | stop processing: n_tokens = 560, truncated = 0 0.43.509.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 43412569 0.43.528.185 I slot launch_slot_: id 0 | task 4298 | processing task, is_child = 0 0.44.046.203 I slot print_timing: id 0 | task 4298 | prompt eval time = 177.65 ms / 552 tokens ( 0.32 ms per token, 3107.25 tokens per second) 0.44.046.208 I slot print_timing: id 0 | task 4298 | eval time = 340.35 ms / 45 tokens ( 7.74 ms per token, 129.28 tokens per second) 0.44.046.209 I slot print_timing: id 0 | task 4298 | total time = 518.00 ms / 597 tokens 0.44.046.210 I slot print_timing: id 0 | task 4298 | graphs reused = 4130 0.44.046.211 I slot print_timing: id 0 | task 4298 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.046.247 I slot release: id 0 | task 4298 | stop processing: n_tokens = 621, truncated = 0 0.44.068.745 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 43955178 0.44.089.123 I slot launch_slot_: id 0 | task 4344 | processing task, is_child = 0 0.44.789.799 I slot print_timing: id 0 | task 4344 | prompt eval time = 164.43 ms / 514 tokens ( 0.32 ms per token, 3126.05 tokens per second) 0.44.789.805 I slot print_timing: id 0 | task 4344 | eval time = 536.24 ms / 75 tokens ( 7.25 ms per token, 138.00 tokens per second) 0.44.789.806 I slot print_timing: id 0 | task 4344 | total time = 700.66 ms / 589 tokens 0.44.789.807 I slot print_timing: id 0 | task 4344 | graphs reused = 4203 0.44.789.808 I slot print_timing: id 0 | task 4344 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.789.840 I slot release: id 0 | task 4344 | stop processing: n_tokens = 613, truncated = 0 0.44.794.580 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 613, t_last = 44698771 0.44.814.854 I slot launch_slot_: id 0 | task 4420 | processing task, is_child = 0 0.45.247.665 I slot print_timing: id 0 | task 4420 | prompt eval time = 138.60 ms / 428 tokens ( 0.32 ms per token, 3088.02 tokens per second) 0.45.247.671 I slot print_timing: id 0 | task 4420 | eval time = 294.19 ms / 42 tokens ( 7.18 ms per token, 139.36 tokens per second) 0.45.247.672 I slot print_timing: id 0 | task 4420 | total time = 432.79 ms / 470 tokens 0.45.247.673 I slot print_timing: id 0 | task 4420 | graphs reused = 4243 0.45.247.673 I slot print_timing: id 0 | task 4420 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.247.704 I slot release: id 0 | task 4420 | stop processing: n_tokens = 494, truncated = 0 0.45.268.038 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 45156635 0.45.284.534 I slot launch_slot_: id 0 | task 4463 | processing task, is_child = 0 0.45.925.423 I slot print_timing: id 0 | task 4463 | prompt eval time = 170.74 ms / 521 tokens ( 0.33 ms per token, 3051.48 tokens per second) 0.45.925.429 I slot print_timing: id 0 | task 4463 | eval time = 470.14 ms / 66 tokens ( 7.23 ms per token, 138.26 tokens per second) 0.45.925.430 I slot print_timing: id 0 | task 4463 | total time = 640.88 ms / 587 tokens 0.45.925.430 I slot print_timing: id 0 | task 4463 | graphs reused = 4307 0.45.925.431 I slot print_timing: id 0 | task 4463 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.925.466 I slot release: id 0 | task 4463 | stop processing: n_tokens = 611, truncated = 0 0.45.940.778 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 45834397 0.45.961.340 I slot launch_slot_: id 0 | task 4530 | processing task, is_child = 0 0.46.482.200 I slot print_timing: id 0 | task 4530 | prompt eval time = 154.65 ms / 472 tokens ( 0.33 ms per token, 3052.09 tokens per second) 0.46.482.206 I slot print_timing: id 0 | task 4530 | eval time = 366.19 ms / 51 tokens ( 7.32 ms per token, 136.54 tokens per second) 0.46.482.207 I slot print_timing: id 0 | task 4530 | total time = 520.84 ms / 523 tokens 0.46.482.207 I slot print_timing: id 0 | task 4530 | graphs reused = 4355 0.46.482.208 I slot print_timing: id 0 | task 4530 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.482.238 I slot release: id 0 | task 4530 | stop processing: n_tokens = 547, truncated = 0 0.46.508.707 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 46391170 0.46.526.880 I slot launch_slot_: id 0 | task 4582 | processing task, is_child = 0 0.46.973.893 I slot print_timing: id 0 | task 4582 | prompt eval time = 138.50 ms / 428 tokens ( 0.32 ms per token, 3090.36 tokens per second) 0.46.973.898 I slot print_timing: id 0 | task 4582 | eval time = 308.50 ms / 44 tokens ( 7.17 ms per token, 139.38 tokens per second) 0.46.973.900 I slot print_timing: id 0 | task 4582 | total time = 447.00 ms / 472 tokens 0.46.973.900 I slot print_timing: id 0 | task 4582 | graphs reused = 4397 0.46.973.902 I slot print_timing: id 0 | task 4582 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.973.932 I slot release: id 0 | task 4582 | stop processing: n_tokens = 496, truncated = 0 0.46.994.918 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 496, t_last = 46882863 0.47.011.738 I slot launch_slot_: id 0 | task 4627 | processing task, is_child = 0 0.47.487.995 I slot print_timing: id 0 | task 4627 | prompt eval time = 154.60 ms / 456 tokens ( 0.34 ms per token, 2949.62 tokens per second) 0.47.488.000 I slot print_timing: id 0 | task 4627 | eval time = 321.64 ms / 45 tokens ( 7.31 ms per token, 136.80 tokens per second) 0.47.488.002 I slot print_timing: id 0 | task 4627 | total time = 476.24 ms / 501 tokens 0.47.488.002 I slot print_timing: id 0 | task 4627 | graphs reused = 4439 0.47.488.003 I slot print_timing: id 0 | task 4627 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.488.035 I slot release: id 0 | task 4627 | stop processing: n_tokens = 525, truncated = 0 0.47.513.066 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 525, t_last = 47396966 0.47.530.975 I slot launch_slot_: id 0 | task 4673 | processing task, is_child = 0 0.47.978.308 I slot print_timing: id 0 | task 4673 | prompt eval time = 139.16 ms / 439 tokens ( 0.32 ms per token, 3154.73 tokens per second) 0.47.978.314 I slot print_timing: id 0 | task 4673 | eval time = 308.16 ms / 44 tokens ( 7.17 ms per token, 139.54 tokens per second) 0.47.978.315 I slot print_timing: id 0 | task 4673 | total time = 447.32 ms / 483 tokens 0.47.978.316 I slot print_timing: id 0 | task 4673 | graphs reused = 4481 0.47.978.316 I slot print_timing: id 0 | task 4673 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.978.349 I slot release: id 0 | task 4673 | stop processing: n_tokens = 507, truncated = 0 0.48.009.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 507, t_last = 47887280 0.48.026.337 I slot launch_slot_: id 0 | task 4718 | processing task, is_child = 0 0.48.645.451 I slot print_timing: id 0 | task 4718 | prompt eval time = 191.94 ms / 600 tokens ( 0.32 ms per token, 3125.99 tokens per second) 0.48.645.457 I slot print_timing: id 0 | task 4718 | eval time = 427.16 ms / 60 tokens ( 7.24 ms per token, 138.12 tokens per second) 0.48.645.458 I slot print_timing: id 0 | task 4718 | total time = 619.10 ms / 660 tokens 0.48.645.459 I slot print_timing: id 0 | task 4718 | graphs reused = 4539 0.48.645.460 I slot print_timing: id 0 | task 4718 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.645.497 I slot release: id 0 | task 4718 | stop processing: n_tokens = 684, truncated = 0 0.48.670.304 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 48554428 0.48.692.599 I slot launch_slot_: id 0 | task 4779 | processing task, is_child = 0 0.49.149.379 I slot print_timing: id 0 | task 4779 | prompt eval time = 155.18 ms / 473 tokens ( 0.33 ms per token, 3048.09 tokens per second) 0.49.149.384 I slot print_timing: id 0 | task 4779 | eval time = 301.58 ms / 42 tokens ( 7.36 ms per token, 135.95 tokens per second) 0.49.149.386 I slot print_timing: id 0 | task 4779 | total time = 456.76 ms / 515 tokens 0.49.149.386 I slot print_timing: id 0 | task 4779 | graphs reused = 4578 0.49.149.387 I slot print_timing: id 0 | task 4779 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.149.419 I slot release: id 0 | task 4779 | stop processing: n_tokens = 539, truncated = 0 0.49.165.700 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 49058350 0.49.183.747 I slot launch_slot_: id 0 | task 4822 | processing task, is_child = 0 0.49.907.557 I slot print_timing: id 0 | task 4822 | prompt eval time = 258.51 ms / 835 tokens ( 0.31 ms per token, 3230.05 tokens per second) 0.49.907.563 I slot print_timing: id 0 | task 4822 | eval time = 465.29 ms / 65 tokens ( 7.27 ms per token, 137.55 tokens per second) 0.49.907.564 I slot print_timing: id 0 | task 4822 | total time = 723.80 ms / 900 tokens 0.49.907.565 I slot print_timing: id 0 | task 4822 | graphs reused = 4641 0.49.907.567 I slot print_timing: id 0 | task 4822 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.907.612 I slot release: id 0 | task 4822 | stop processing: n_tokens = 924, truncated = 0 0.49.927.805 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 49816543 0.49.956.262 I slot launch_slot_: id 0 | task 4888 | processing task, is_child = 0 0.50.430.200 I slot print_timing: id 0 | task 4888 | prompt eval time = 155.15 ms / 454 tokens ( 0.34 ms per token, 2926.24 tokens per second) 0.50.430.205 I slot print_timing: id 0 | task 4888 | eval time = 318.77 ms / 43 tokens ( 7.59 ms per token, 131.76 tokens per second) 0.50.430.206 I slot print_timing: id 0 | task 4888 | total time = 473.92 ms / 497 tokens 0.50.430.207 I slot print_timing: id 0 | task 4888 | graphs reused = 4681 0.50.430.208 I slot print_timing: id 0 | task 4888 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.430.244 I slot release: id 0 | task 4888 | stop processing: n_tokens = 521, truncated = 0 0.50.459.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 50339175 0.50.481.137 I slot launch_slot_: id 0 | task 4932 | processing task, is_child = 0 0.51.035.272 I slot print_timing: id 0 | task 4932 | prompt eval time = 211.86 ms / 667 tokens ( 0.32 ms per token, 3148.36 tokens per second) 0.51.035.277 I slot print_timing: id 0 | task 4932 | eval time = 342.26 ms / 48 tokens ( 7.28 ms per token, 137.32 tokens per second) 0.51.035.278 I slot print_timing: id 0 | task 4932 | total time = 554.11 ms / 715 tokens 0.51.035.279 I slot print_timing: id 0 | task 4932 | graphs reused = 4727 0.51.035.280 I slot print_timing: id 0 | task 4932 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.035.320 I slot release: id 0 | task 4932 | stop processing: n_tokens = 741, truncated = 0 0.51.066.451 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 50944251 0.51.103.065 I slot launch_slot_: id 0 | task 4981 | processing task, is_child = 0 0.51.830.032 I slot print_timing: id 0 | task 4981 | prompt eval time = 203.03 ms / 628 tokens ( 0.32 ms per token, 3093.22 tokens per second) 0.51.830.038 I slot print_timing: id 0 | task 4981 | eval time = 523.92 ms / 69 tokens ( 7.70 ms per token, 129.79 tokens per second) 0.51.830.039 I slot print_timing: id 0 | task 4981 | total time = 726.95 ms / 697 tokens 0.51.830.040 I slot print_timing: id 0 | task 4981 | graphs reused = 4794 0.51.830.041 I slot print_timing: id 0 | task 4981 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.830.084 I slot release: id 0 | task 4981 | stop processing: n_tokens = 858, truncated = 0 0.51.859.302 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 858, t_last = 51739015 0.51.886.111 I slot launch_slot_: id 0 | task 5051 | processing task, is_child = 0 0.52.616.710 I slot print_timing: id 0 | task 5051 | prompt eval time = 187.54 ms / 578 tokens ( 0.32 ms per token, 3082.07 tokens per second) 0.52.616.716 I slot print_timing: id 0 | task 5051 | eval time = 543.05 ms / 76 tokens ( 7.24 ms per token, 138.11 tokens per second) 0.52.616.717 I slot print_timing: id 0 | task 5051 | total time = 730.58 ms / 654 tokens 0.52.616.717 I slot print_timing: id 0 | task 5051 | graphs reused = 4868 0.52.616.718 I slot print_timing: id 0 | task 5051 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.616.755 I slot release: id 0 | task 5051 | stop processing: n_tokens = 678, truncated = 0 0.52.637.589 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 52525686 0.52.659.813 I slot launch_slot_: id 0 | task 5128 | processing task, is_child = 0 0.53.273.812 I slot print_timing: id 0 | task 5128 | prompt eval time = 155.58 ms / 461 tokens ( 0.34 ms per token, 2963.14 tokens per second) 0.53.273.818 I slot print_timing: id 0 | task 5128 | eval time = 458.41 ms / 64 tokens ( 7.28 ms per token, 137.43 tokens per second) 0.53.273.819 I slot print_timing: id 0 | task 5128 | total time = 613.98 ms / 525 tokens 0.53.273.820 I slot print_timing: id 0 | task 5128 | graphs reused = 4929 0.53.273.820 I slot print_timing: id 0 | task 5128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.273.853 I slot release: id 0 | task 5128 | stop processing: n_tokens = 549, truncated = 0 0.53.291.149 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 53182784 0.53.309.751 I slot launch_slot_: id 0 | task 5193 | processing task, is_child = 0 0.53.857.740 I slot print_timing: id 0 | task 5193 | prompt eval time = 197.54 ms / 613 tokens ( 0.32 ms per token, 3103.15 tokens per second) 0.53.857.746 I slot print_timing: id 0 | task 5193 | eval time = 350.43 ms / 48 tokens ( 7.46 ms per token, 134.12 tokens per second) 0.53.857.747 I slot print_timing: id 0 | task 5193 | total time = 547.97 ms / 661 tokens 0.53.857.748 I slot print_timing: id 0 | task 5193 | graphs reused = 4975 0.53.857.749 I slot print_timing: id 0 | task 5193 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.857.787 I slot release: id 0 | task 5193 | stop processing: n_tokens = 685, truncated = 0 0.53.883.567 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 53766718 0.53.905.692 I slot launch_slot_: id 0 | task 5242 | processing task, is_child = 0 0.54.617.935 I slot print_timing: id 0 | task 5242 | prompt eval time = 246.27 ms / 794 tokens ( 0.31 ms per token, 3224.06 tokens per second) 0.54.617.941 I slot print_timing: id 0 | task 5242 | eval time = 465.95 ms / 65 tokens ( 7.28 ms per token, 137.35 tokens per second) 0.54.617.942 I slot print_timing: id 0 | task 5242 | total time = 712.23 ms / 859 tokens 0.54.617.943 I slot print_timing: id 0 | task 5242 | graphs reused = 5038 0.54.617.943 I slot print_timing: id 0 | task 5242 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.617.986 I slot release: id 0 | task 5242 | stop processing: n_tokens = 883, truncated = 0 0.54.623.646 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 54526917 0.54.684.550 I slot launch_slot_: id 0 | task 5308 | processing task, is_child = 0 0.55.238.406 I slot print_timing: id 0 | task 5308 | prompt eval time = 139.70 ms / 431 tokens ( 0.32 ms per token, 3085.20 tokens per second) 0.55.238.412 I slot print_timing: id 0 | task 5308 | eval time = 414.14 ms / 58 tokens ( 7.27 ms per token, 137.64 tokens per second) 0.55.238.413 I slot print_timing: id 0 | task 5308 | total time = 553.84 ms / 489 tokens 0.55.238.413 I slot print_timing: id 0 | task 5308 | graphs reused = 5094 0.55.238.414 I slot print_timing: id 0 | task 5308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.238.451 I slot release: id 0 | task 5308 | stop processing: n_tokens = 687, truncated = 0 0.55.256.838 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 55147382 0.55.279.045 I slot launch_slot_: id 0 | task 5367 | processing task, is_child = 0 0.55.827.191 I slot print_timing: id 0 | task 5367 | prompt eval time = 182.25 ms / 563 tokens ( 0.32 ms per token, 3089.21 tokens per second) 0.55.827.197 I slot print_timing: id 0 | task 5367 | eval time = 365.88 ms / 50 tokens ( 7.47 ms per token, 133.92 tokens per second) 0.55.827.198 I slot print_timing: id 0 | task 5367 | total time = 548.13 ms / 613 tokens 0.55.827.199 I slot print_timing: id 0 | task 5367 | graphs reused = 5142 0.55.827.200 I slot print_timing: id 0 | task 5367 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.827.236 I slot release: id 0 | task 5367 | stop processing: n_tokens = 637, truncated = 0 0.55.848.909 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 55736167 0.55.881.508 I slot launch_slot_: id 0 | task 5418 | processing task, is_child = 0 0.56.333.018 I slot print_timing: id 0 | task 5418 | prompt eval time = 103.24 ms / 331 tokens ( 0.31 ms per token, 3206.12 tokens per second) 0.56.333.025 I slot print_timing: id 0 | task 5418 | eval time = 348.25 ms / 48 tokens ( 7.41 ms per token, 134.96 tokens per second) 0.56.333.026 I slot print_timing: id 0 | task 5418 | total time = 451.49 ms / 379 tokens 0.56.333.027 I slot print_timing: id 0 | task 5418 | graphs reused = 5187 0.56.333.028 I slot print_timing: id 0 | task 5418 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.333.060 I slot release: id 0 | task 5418 | stop processing: n_tokens = 513, truncated = 0 0.56.363.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 56241991 0.56.380.425 I slot launch_slot_: id 0 | task 5467 | processing task, is_child = 0 0.57.015.469 I slot print_timing: id 0 | task 5467 | prompt eval time = 157.35 ms / 489 tokens ( 0.32 ms per token, 3107.76 tokens per second) 0.57.015.475 I slot print_timing: id 0 | task 5467 | eval time = 477.68 ms / 67 tokens ( 7.24 ms per token, 138.17 tokens per second) 0.57.015.476 I slot print_timing: id 0 | task 5467 | total time = 635.03 ms / 556 tokens 0.57.015.477 I slot print_timing: id 0 | task 5467 | graphs reused = 5252 0.57.015.478 I slot print_timing: id 0 | task 5467 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.015.510 I slot release: id 0 | task 5467 | stop processing: n_tokens = 580, truncated = 0 0.57.036.586 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 56924441 0.57.055.896 I slot launch_slot_: id 0 | task 5535 | processing task, is_child = 0 0.57.599.328 I slot print_timing: id 0 | task 5535 | prompt eval time = 158.73 ms / 510 tokens ( 0.31 ms per token, 3212.92 tokens per second) 0.57.599.334 I slot print_timing: id 0 | task 5535 | eval time = 384.68 ms / 54 tokens ( 7.26 ms per token, 137.78 tokens per second) 0.57.599.335 I slot print_timing: id 0 | task 5535 | total time = 543.42 ms / 564 tokens 0.57.599.336 I slot print_timing: id 0 | task 5535 | graphs reused = 5304 0.57.599.336 I slot print_timing: id 0 | task 5535 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.599.369 I slot release: id 0 | task 5535 | stop processing: n_tokens = 588, truncated = 0 0.57.616.978 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 57508301 0.57.636.685 I slot launch_slot_: id 0 | task 5590 | processing task, is_child = 0 0.58.346.320 I slot print_timing: id 0 | task 5590 | prompt eval time = 202.31 ms / 631 tokens ( 0.32 ms per token, 3119.04 tokens per second) 0.58.346.326 I slot print_timing: id 0 | task 5590 | eval time = 507.31 ms / 71 tokens ( 7.25 ms per token, 137.98 tokens per second) 0.58.346.327 I slot print_timing: id 0 | task 5590 | total time = 709.62 ms / 702 tokens 0.58.346.327 I slot print_timing: id 0 | task 5590 | graphs reused = 5373 0.58.346.328 I slot print_timing: id 0 | task 5590 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.346.365 I slot release: id 0 | task 5590 | stop processing: n_tokens = 726, truncated = 0 0.58.365.973 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 58255296 0.58.389.326 I slot launch_slot_: id 0 | task 5662 | processing task, is_child = 0 0.58.957.052 I slot print_timing: id 0 | task 5662 | prompt eval time = 182.53 ms / 570 tokens ( 0.32 ms per token, 3122.76 tokens per second) 0.58.957.058 I slot print_timing: id 0 | task 5662 | eval time = 385.18 ms / 54 tokens ( 7.27 ms per token, 137.60 tokens per second) 0.58.957.059 I slot print_timing: id 0 | task 5662 | total time = 567.71 ms / 624 tokens 0.58.957.060 I slot print_timing: id 0 | task 5662 | graphs reused = 5425 0.58.957.060 I slot print_timing: id 0 | task 5662 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.957.095 I slot release: id 0 | task 5662 | stop processing: n_tokens = 648, truncated = 0 0.58.976.771 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 58866026 0.58.998.242 I slot launch_slot_: id 0 | task 5717 | processing task, is_child = 0 0.59.594.878 I slot print_timing: id 0 | task 5717 | prompt eval time = 245.92 ms / 792 tokens ( 0.31 ms per token, 3220.57 tokens per second) 0.59.594.883 I slot print_timing: id 0 | task 5717 | eval time = 350.70 ms / 49 tokens ( 7.31 ms per token, 136.87 tokens per second) 0.59.594.885 I slot print_timing: id 0 | task 5717 | total time = 596.62 ms / 841 tokens 0.59.594.885 I slot print_timing: id 0 | task 5717 | graphs reused = 5472 0.59.594.886 I slot print_timing: id 0 | task 5717 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.594.928 I slot release: id 0 | task 5717 | stop processing: n_tokens = 867, truncated = 0 0.59.612.508 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 867, t_last = 59503859 0.59.639.439 I slot launch_slot_: id 0 | task 5767 | processing task, is_child = 0 1.00.142.162 I slot print_timing: id 0 | task 5767 | prompt eval time = 182.54 ms / 564 tokens ( 0.32 ms per token, 3089.65 tokens per second) 1.00.142.167 I slot print_timing: id 0 | task 5767 | eval time = 320.16 ms / 45 tokens ( 7.28 ms per token, 137.43 tokens per second) 1.00.142.168 I slot print_timing: id 0 | task 5767 | total time = 502.71 ms / 609 tokens 1.00.142.169 I slot print_timing: id 0 | task 5767 | graphs reused = 5515 1.00.142.170 I slot print_timing: id 0 | task 5767 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.142.207 I slot release: id 0 | task 5767 | stop processing: n_tokens = 635, truncated = 0 1.00.171.765 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 60051138 1.00.192.568 I slot launch_slot_: id 0 | task 5813 | processing task, is_child = 0 1.00.897.185 I slot print_timing: id 0 | task 5813 | prompt eval time = 197.84 ms / 617 tokens ( 0.32 ms per token, 3118.74 tokens per second) 1.00.897.191 I slot print_timing: id 0 | task 5813 | eval time = 506.77 ms / 71 tokens ( 7.24 ms per token, 138.13 tokens per second) 1.00.897.192 I slot print_timing: id 0 | task 5813 | total time = 704.60 ms / 688 tokens 1.00.897.193 I slot print_timing: id 0 | task 5813 | graphs reused = 5584 1.00.897.194 I slot print_timing: id 0 | task 5813 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.897.232 I slot release: id 0 | task 5813 | stop processing: n_tokens = 712, truncated = 0 1.00.903.219 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 712, t_last = 60806163 1.00.926.384 I slot launch_slot_: id 0 | task 5885 | processing task, is_child = 0 1.01.599.139 I slot print_timing: id 0 | task 5885 | prompt eval time = 183.16 ms / 572 tokens ( 0.32 ms per token, 3122.90 tokens per second) 1.01.599.143 I slot print_timing: id 0 | task 5885 | eval time = 489.57 ms / 67 tokens ( 7.42 ms per token, 134.81 tokens per second) 1.01.599.145 I slot print_timing: id 0 | task 5885 | total time = 672.74 ms / 639 tokens 1.01.599.146 I slot print_timing: id 0 | task 5885 | graphs reused = 5649 1.01.599.147 I slot print_timing: id 0 | task 5885 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.599.187 I slot release: id 0 | task 5885 | stop processing: n_tokens = 663, truncated = 0 1.01.625.566 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 663, t_last = 61508118 1.01.648.308 I slot launch_slot_: id 0 | task 5953 | processing task, is_child = 0 1.02.267.989 I slot print_timing: id 0 | task 5953 | prompt eval time = 229.02 ms / 712 tokens ( 0.32 ms per token, 3108.86 tokens per second) 1.02.267.994 I slot print_timing: id 0 | task 5953 | eval time = 390.64 ms / 54 tokens ( 7.37 ms per token, 135.68 tokens per second) 1.02.267.995 I slot print_timing: id 0 | task 5953 | total time = 619.66 ms / 766 tokens 1.02.267.996 I slot print_timing: id 0 | task 5953 | graphs reused = 5700 1.02.267.997 I slot print_timing: id 0 | task 5953 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.268.038 I slot release: id 0 | task 5953 | stop processing: n_tokens = 790, truncated = 0 1.02.285.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 62176969 1.02.311.158 I slot launch_slot_: id 0 | task 6008 | processing task, is_child = 0 1.03.326.755 I slot print_timing: id 0 | task 6008 | prompt eval time = 245.61 ms / 791 tokens ( 0.31 ms per token, 3220.61 tokens per second) 1.03.326.761 I slot print_timing: id 0 | task 6008 | eval time = 769.98 ms / 106 tokens ( 7.33 ms per token, 136.37 tokens per second) 1.03.326.762 I slot print_timing: id 0 | task 6008 | total time = 1015.58 ms / 897 tokens 1.03.326.763 I slot print_timing: id 0 | task 6008 | graphs reused = 5804 1.03.326.764 I slot print_timing: id 0 | task 6008 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.326.806 I slot release: id 0 | task 6008 | stop processing: n_tokens = 921, truncated = 0 1.03.352.595 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 921, t_last = 63235737 1.03.380.861 I slot launch_slot_: id 0 | task 6115 | processing task, is_child = 0 1.06.500.330 I slot print_timing: id 0 | task 6115 | n_gen = 420, tg = 139.44 t/s, tg_3s = 139.77 t/s 1.09.500.485 I slot print_timing: id 0 | task 6115 | n_gen = 832, tg = 138.38 t/s, tg_3s = 137.33 t/s 1.10.925.479 I slot print_timing: id 0 | task 6115 | prompt eval time = 114.48 ms / 369 tokens ( 0.31 ms per token, 3223.33 tokens per second) 1.10.925.485 I slot print_timing: id 0 | task 6115 | eval time = 7430.12 ms / 1024 tokens ( 7.26 ms per token, 137.68 tokens per second) 1.10.925.485 I slot print_timing: id 0 | task 6115 | total time = 7544.60 ms / 1393 tokens 1.10.925.487 I slot print_timing: id 0 | task 6115 | graphs reused = 6822 1.10.925.487 I slot print_timing: id 0 | task 6115 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.925.517 I slot release: id 0 | task 6115 | stop processing: n_tokens = 1417, truncated = 0 1.10.940.322 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1417, t_last = 70834448 1.10.940.429 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.881 MiB) 1.10.987.809 I slot launch_slot_: id 0 | task 7140 | processing task, is_child = 0 1.11.561.811 I slot print_timing: id 0 | task 7140 | prompt eval time = 137.32 ms / 388 tokens ( 0.35 ms per token, 2825.58 tokens per second) 1.11.561.817 I slot print_timing: id 0 | task 7140 | eval time = 436.67 ms / 62 tokens ( 7.16 ms per token, 139.69 tokens per second) 1.11.561.818 I slot print_timing: id 0 | task 7140 | total time = 573.98 ms / 450 tokens 1.11.561.819 I slot print_timing: id 0 | task 7140 | graphs reused = 6882 1.11.561.819 I slot print_timing: id 0 | task 7140 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.561.849 I slot release: id 0 | task 7140 | stop processing: n_tokens = 474, truncated = 0 1.11.581.990 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 71470780 1.11.582.048 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.255 MiB) 1.11.600.197 I slot launch_slot_: id 0 | task 7203 | processing task, is_child = 0 1.12.179.931 I slot print_timing: id 0 | task 7203 | prompt eval time = 114.39 ms / 370 tokens ( 0.31 ms per token, 3234.61 tokens per second) 1.12.179.937 I slot print_timing: id 0 | task 7203 | eval time = 465.33 ms / 66 tokens ( 7.16 ms per token, 139.69 tokens per second) 1.12.179.938 I slot print_timing: id 0 | task 7203 | total time = 579.72 ms / 436 tokens 1.12.179.939 I slot print_timing: id 0 | task 7203 | graphs reused = 6946 1.12.179.940 I slot print_timing: id 0 | task 7203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.179.970 I slot release: id 0 | task 7203 | stop processing: n_tokens = 460, truncated = 0 1.12.194.059 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 72088901 1.12.194.121 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.599 MiB) 1.12.212.022 I slot launch_slot_: id 0 | task 7270 | processing task, is_child = 0 1.12.748.535 I slot print_timing: id 0 | task 7270 | prompt eval time = 114.35 ms / 340 tokens ( 0.34 ms per token, 2973.38 tokens per second) 1.12.748.541 I slot print_timing: id 0 | task 7270 | eval time = 422.15 ms / 60 tokens ( 7.16 ms per token, 139.76 tokens per second) 1.12.748.542 I slot print_timing: id 0 | task 7270 | total time = 536.50 ms / 400 tokens 1.12.748.543 I slot print_timing: id 0 | task 7270 | graphs reused = 7004 1.12.748.544 I slot print_timing: id 0 | task 7270 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.748.572 I slot release: id 0 | task 7270 | stop processing: n_tokens = 424, truncated = 0 1.12.753.158 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 72657503 1.12.753.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 1.12.770.243 I slot launch_slot_: id 0 | task 7331 | processing task, is_child = 0 1.13.458.340 I slot print_timing: id 0 | task 7331 | prompt eval time = 138.17 ms / 409 tokens ( 0.34 ms per token, 2960.08 tokens per second) 1.13.458.346 I slot print_timing: id 0 | task 7331 | eval time = 549.91 ms / 78 tokens ( 7.14 ms per token, 140.02 tokens per second) 1.13.458.347 I slot print_timing: id 0 | task 7331 | total time = 688.08 ms / 487 tokens 1.13.458.348 I slot print_timing: id 0 | task 7331 | graphs reused = 7080 1.13.458.349 I slot print_timing: id 0 | task 7331 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.458.380 I slot release: id 0 | task 7331 | stop processing: n_tokens = 511, truncated = 0 1.13.476.145 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 73367312 1.13.476.199 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.537 MiB) 1.13.478.246 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 1.13.498.635 I slot launch_slot_: id 0 | task 7410 | processing task, is_child = 0 1.14.308.077 I slot print_timing: id 0 | task 7410 | prompt eval time = 138.57 ms / 422 tokens ( 0.33 ms per token, 3045.41 tokens per second) 1.14.308.082 I slot print_timing: id 0 | task 7410 | eval time = 670.86 ms / 94 tokens ( 7.21 ms per token, 138.63 tokens per second) 1.14.308.083 I slot print_timing: id 0 | task 7410 | total time = 809.42 ms / 516 tokens 1.14.308.084 I slot print_timing: id 0 | task 7410 | graphs reused = 7171 1.14.308.085 I slot print_timing: id 0 | task 7410 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.308.116 I slot release: id 0 | task 7410 | stop processing: n_tokens = 540, truncated = 0 1.14.330.837 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 74217047 1.14.330.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.819 MiB) 1.14.351.650 I slot launch_slot_: id 0 | task 7505 | processing task, is_child = 0 1.15.314.457 I slot print_timing: id 0 | task 7505 | prompt eval time = 157.81 ms / 499 tokens ( 0.32 ms per token, 3161.95 tokens per second) 1.15.314.463 I slot print_timing: id 0 | task 7505 | eval time = 804.98 ms / 112 tokens ( 7.25 ms per token, 137.89 tokens per second) 1.15.314.465 I slot print_timing: id 0 | task 7505 | total time = 962.79 ms / 611 tokens 1.15.314.466 I slot print_timing: id 0 | task 7505 | graphs reused = 7281 1.15.314.467 I slot print_timing: id 0 | task 7505 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.314.504 I slot release: id 0 | task 7505 | stop processing: n_tokens = 639, truncated = 0 1.15.342.805 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 75223435 1.15.342.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.695 MiB) 1.15.366.527 I slot launch_slot_: id 0 | task 7618 | processing task, is_child = 0 1.15.790.429 I slot print_timing: id 0 | task 7618 | prompt eval time = 114.44 ms / 345 tokens ( 0.33 ms per token, 3014.81 tokens per second) 1.15.790.435 I slot print_timing: id 0 | task 7618 | eval time = 309.45 ms / 44 tokens ( 7.20 ms per token, 138.96 tokens per second) 1.15.790.436 I slot print_timing: id 0 | task 7618 | total time = 423.89 ms / 389 tokens 1.15.790.437 I slot print_timing: id 0 | task 7618 | graphs reused = 7323 1.15.790.438 I slot print_timing: id 0 | task 7618 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.790.466 I slot release: id 0 | task 7618 | stop processing: n_tokens = 413, truncated = 0 1.15.810.334 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 75699397 1.15.810.382 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.724 MiB) 1.15.826.870 I slot launch_slot_: id 0 | task 7663 | processing task, is_child = 0 1.16.250.923 I slot print_timing: id 0 | task 7663 | prompt eval time = 114.50 ms / 348 tokens ( 0.33 ms per token, 3039.43 tokens per second) 1.16.250.928 I slot print_timing: id 0 | task 7663 | eval time = 309.54 ms / 44 tokens ( 7.20 ms per token, 138.91 tokens per second) 1.16.250.929 I slot print_timing: id 0 | task 7663 | total time = 424.04 ms / 392 tokens 1.16.250.930 I slot print_timing: id 0 | task 7663 | graphs reused = 7365 1.16.250.933 I slot print_timing: id 0 | task 7663 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.250.963 I slot release: id 0 | task 7663 | stop processing: n_tokens = 416, truncated = 0 1.16.274.058 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 76159894 1.16.274.113 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 1.16.290.662 I slot launch_slot_: id 0 | task 7708 | processing task, is_child = 0 1.16.908.619 I slot print_timing: id 0 | task 7708 | prompt eval time = 137.79 ms / 408 tokens ( 0.34 ms per token, 2961.03 tokens per second) 1.16.908.625 I slot print_timing: id 0 | task 7708 | eval time = 480.15 ms / 68 tokens ( 7.17 ms per token, 139.54 tokens per second) 1.16.908.626 I slot print_timing: id 0 | task 7708 | total time = 617.94 ms / 476 tokens 1.16.908.627 I slot print_timing: id 0 | task 7708 | graphs reused = 7431 1.16.908.628 I slot print_timing: id 0 | task 7708 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.908.658 I slot release: id 0 | task 7708 | stop processing: n_tokens = 500, truncated = 0 1.16.933.832 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 76817589 1.16.933.891 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.381 MiB) 1.16.953.285 I slot launch_slot_: id 0 | task 7777 | processing task, is_child = 0 1.17.555.008 I slot print_timing: id 0 | task 7777 | prompt eval time = 155.00 ms / 465 tokens ( 0.33 ms per token, 3000.10 tokens per second) 1.17.555.014 I slot print_timing: id 0 | task 7777 | eval time = 446.71 ms / 61 tokens ( 7.45 ms per token, 134.32 tokens per second) 1.17.555.015 I slot print_timing: id 0 | task 7777 | total time = 601.71 ms / 526 tokens 1.17.555.016 I slot print_timing: id 0 | task 7777 | graphs reused = 7489 1.17.555.017 I slot print_timing: id 0 | task 7777 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.555.047 I slot release: id 0 | task 7777 | stop processing: n_tokens = 550, truncated = 0 1.17.576.090 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 550, t_last = 77463978 1.17.576.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.350 MiB) 1.17.596.986 I slot launch_slot_: id 0 | task 7839 | processing task, is_child = 0 1.18.156.936 I slot print_timing: id 0 | task 7839 | prompt eval time = 137.79 ms / 399 tokens ( 0.35 ms per token, 2895.61 tokens per second) 1.18.156.943 I slot print_timing: id 0 | task 7839 | eval time = 422.14 ms / 60 tokens ( 7.15 ms per token, 139.76 tokens per second) 1.18.156.944 I slot print_timing: id 0 | task 7839 | total time = 559.93 ms / 459 tokens 1.18.156.945 I slot print_timing: id 0 | task 7839 | graphs reused = 7547 1.18.156.946 I slot print_timing: id 0 | task 7839 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.156.980 I slot release: id 0 | task 7839 | stop processing: n_tokens = 500, truncated = 0 1.18.181.866 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 78065911 1.18.181.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.287 MiB) 1.18.200.938 I slot launch_slot_: id 0 | task 7900 | processing task, is_child = 0 1.18.853.187 I slot print_timing: id 0 | task 7900 | prompt eval time = 138.51 ms / 419 tokens ( 0.33 ms per token, 3025.01 tokens per second) 1.18.853.193 I slot print_timing: id 0 | task 7900 | eval time = 513.72 ms / 72 tokens ( 7.24 ms per token, 138.21 tokens per second) 1.18.853.194 I slot print_timing: id 0 | task 7900 | total time = 652.23 ms / 491 tokens 1.18.853.195 I slot print_timing: id 0 | task 7900 | graphs reused = 7616 1.18.853.196 I slot print_timing: id 0 | task 7900 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.853.227 I slot release: id 0 | task 7900 | stop processing: n_tokens = 515, truncated = 0 1.18.867.960 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 78762158 1.18.868.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.662 MiB) 1.18.869.905 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 1.18.891.534 I slot launch_slot_: id 0 | task 7973 | processing task, is_child = 0 1.19.537.716 I slot print_timing: id 0 | task 7973 | prompt eval time = 138.84 ms / 440 tokens ( 0.32 ms per token, 3169.09 tokens per second) 1.19.537.721 I slot print_timing: id 0 | task 7973 | eval time = 507.32 ms / 71 tokens ( 7.25 ms per token, 137.98 tokens per second) 1.19.537.722 I slot print_timing: id 0 | task 7973 | total time = 646.17 ms / 511 tokens 1.19.537.723 I slot print_timing: id 0 | task 7973 | graphs reused = 7684 1.19.537.724 I slot print_timing: id 0 | task 7973 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.537.756 I slot release: id 0 | task 7973 | stop processing: n_tokens = 535, truncated = 0 1.19.551.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 79446687 1.19.551.803 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.349 MiB) 1.19.571.844 I slot launch_slot_: id 0 | task 8045 | processing task, is_child = 0 1.20.053.428 I slot print_timing: id 0 | task 8045 | prompt eval time = 114.52 ms / 372 tokens ( 0.31 ms per token, 3248.40 tokens per second) 1.20.053.434 I slot print_timing: id 0 | task 8045 | eval time = 367.05 ms / 52 tokens ( 7.20 ms per token, 138.95 tokens per second) 1.20.053.435 I slot print_timing: id 0 | task 8045 | total time = 481.57 ms / 424 tokens 1.20.053.436 I slot print_timing: id 0 | task 8045 | graphs reused = 7734 1.20.053.437 I slot print_timing: id 0 | task 8045 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.053.468 I slot release: id 0 | task 8045 | stop processing: n_tokens = 448, truncated = 0 1.20.080.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 79962399 1.20.080.233 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.224 MiB) 1.20.098.653 I slot launch_slot_: id 0 | task 8098 | processing task, is_child = 0 1.20.668.971 I slot print_timing: id 0 | task 8098 | prompt eval time = 155.00 ms / 449 tokens ( 0.35 ms per token, 2896.81 tokens per second) 1.20.668.976 I slot print_timing: id 0 | task 8098 | eval time = 415.30 ms / 58 tokens ( 7.29 ms per token, 137.25 tokens per second) 1.20.668.978 I slot print_timing: id 0 | task 8098 | total time = 570.30 ms / 507 tokens 1.20.668.979 I slot print_timing: id 0 | task 8098 | graphs reused = 7789 1.20.668.980 I slot print_timing: id 0 | task 8098 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.669.013 I slot release: id 0 | task 8098 | stop processing: n_tokens = 531, truncated = 0 1.20.684.796 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 80577944 1.20.684.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.443 MiB) 1.20.704.822 I slot launch_slot_: id 0 | task 8157 | processing task, is_child = 0 1.21.256.348 I slot print_timing: id 0 | task 8157 | prompt eval time = 114.76 ms / 360 tokens ( 0.32 ms per token, 3136.87 tokens per second) 1.21.256.354 I slot print_timing: id 0 | task 8157 | eval time = 436.75 ms / 62 tokens ( 7.16 ms per token, 139.67 tokens per second) 1.21.256.355 I slot print_timing: id 0 | task 8157 | total time = 551.51 ms / 422 tokens 1.21.256.356 I slot print_timing: id 0 | task 8157 | graphs reused = 7849 1.21.256.357 I slot print_timing: id 0 | task 8157 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.256.387 I slot release: id 0 | task 8157 | stop processing: n_tokens = 446, truncated = 0 1.21.276.307 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 81165318 1.21.276.368 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.943 MiB) 1.21.293.901 I slot launch_slot_: id 0 | task 8220 | processing task, is_child = 0 1.21.796.043 I slot print_timing: id 0 | task 8220 | prompt eval time = 114.66 ms / 346 tokens ( 0.33 ms per token, 3017.72 tokens per second) 1.21.796.048 I slot print_timing: id 0 | task 8220 | eval time = 387.47 ms / 55 tokens ( 7.18 ms per token, 139.37 tokens per second) 1.21.796.050 I slot print_timing: id 0 | task 8220 | total time = 502.13 ms / 401 tokens 1.21.796.051 I slot print_timing: id 0 | task 8220 | graphs reused = 7902 1.21.796.052 I slot print_timing: id 0 | task 8220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.796.080 I slot release: id 0 | task 8220 | stop processing: n_tokens = 425, truncated = 0 1.21.822.048 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 81705011 1.21.822.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.631 MiB) 1.21.839.285 I slot launch_slot_: id 0 | task 8276 | processing task, is_child = 0 1.22.344.083 I slot print_timing: id 0 | task 8276 | prompt eval time = 138.85 ms / 434 tokens ( 0.32 ms per token, 3125.74 tokens per second) 1.22.344.089 I slot print_timing: id 0 | task 8276 | eval time = 365.94 ms / 52 tokens ( 7.18 ms per token, 139.37 tokens per second) 1.22.344.090 I slot print_timing: id 0 | task 8276 | total time = 504.78 ms / 486 tokens 1.22.344.092 I slot print_timing: id 0 | task 8276 | graphs reused = 7952 1.22.344.092 I slot print_timing: id 0 | task 8276 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.344.124 I slot release: id 0 | task 8276 | stop processing: n_tokens = 510, truncated = 0 1.22.371.668 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 82253055 1.22.371.724 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.787 MiB) 1.22.373.488 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.850 MiB) 1.22.394.765 I slot launch_slot_: id 0 | task 8329 | processing task, is_child = 0 1.22.932.751 I slot print_timing: id 0 | task 8329 | prompt eval time = 114.39 ms / 369 tokens ( 0.31 ms per token, 3225.75 tokens per second) 1.22.932.758 I slot print_timing: id 0 | task 8329 | eval time = 423.57 ms / 59 tokens ( 7.30 ms per token, 136.93 tokens per second) 1.22.932.759 I slot print_timing: id 0 | task 8329 | total time = 537.97 ms / 428 tokens 1.22.932.759 I slot print_timing: id 0 | task 8329 | graphs reused = 8009 1.22.932.760 I slot print_timing: id 0 | task 8329 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.932.788 I slot release: id 0 | task 8329 | stop processing: n_tokens = 452, truncated = 0 1.22.962.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 82841719 1.22.962.316 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.412 MiB) 1.22.980.333 I slot launch_slot_: id 0 | task 8389 | processing task, is_child = 0 1.23.686.478 I slot print_timing: id 0 | task 8389 | prompt eval time = 139.40 ms / 446 tokens ( 0.31 ms per token, 3199.49 tokens per second) 1.23.686.485 I slot print_timing: id 0 | task 8389 | eval time = 566.73 ms / 79 tokens ( 7.27 ms per token, 137.63 tokens per second) 1.23.686.486 I slot print_timing: id 0 | task 8389 | total time = 706.13 ms / 525 tokens 1.23.686.487 I slot print_timing: id 0 | task 8389 | graphs reused = 8085 1.23.686.488 I slot print_timing: id 0 | task 8389 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.686.524 I slot release: id 0 | task 8389 | stop processing: n_tokens = 549, truncated = 0 1.23.710.251 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 83595455 1.23.710.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 1.23.731.099 I slot launch_slot_: id 0 | task 8469 | processing task, is_child = 0 1.24.205.821 I slot print_timing: id 0 | task 8469 | prompt eval time = 137.26 ms / 396 tokens ( 0.35 ms per token, 2885.08 tokens per second) 1.24.205.827 I slot print_timing: id 0 | task 8469 | eval time = 337.45 ms / 48 tokens ( 7.18 ms per token, 139.28 tokens per second) 1.24.205.828 I slot print_timing: id 0 | task 8469 | total time = 474.71 ms / 444 tokens 1.24.205.829 I slot print_timing: id 0 | task 8469 | graphs reused = 8131 1.24.205.830 I slot print_timing: id 0 | task 8469 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.205.859 I slot release: id 0 | task 8469 | stop processing: n_tokens = 470, truncated = 0 1.24.229.424 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 84114790 1.24.229.480 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.975 MiB) 1.24.248.158 I slot launch_slot_: id 0 | task 8518 | processing task, is_child = 0 1.25.034.735 I slot print_timing: id 0 | task 8518 | prompt eval time = 154.75 ms / 466 tokens ( 0.33 ms per token, 3011.23 tokens per second) 1.25.034.741 I slot print_timing: id 0 | task 8518 | eval time = 631.81 ms / 88 tokens ( 7.26 ms per token, 137.70 tokens per second) 1.25.034.742 I slot print_timing: id 0 | task 8518 | total time = 786.56 ms / 554 tokens 1.25.034.743 I slot print_timing: id 0 | task 8518 | graphs reused = 8216 1.25.034.744 I slot print_timing: id 0 | task 8518 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.034.774 I slot release: id 0 | task 8518 | stop processing: n_tokens = 578, truncated = 0 1.25.060.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 578, t_last = 84943705 1.25.060.336 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.569 MiB) 1.25.082.223 I slot launch_slot_: id 0 | task 8607 | processing task, is_child = 0 1.25.719.951 I slot print_timing: id 0 | task 8607 | prompt eval time = 154.89 ms / 467 tokens ( 0.33 ms per token, 3015.06 tokens per second) 1.25.719.957 I slot print_timing: id 0 | task 8607 | eval time = 482.82 ms / 66 tokens ( 7.43 ms per token, 134.62 tokens per second) 1.25.719.957 I slot print_timing: id 0 | task 8607 | total time = 637.71 ms / 533 tokens 1.25.719.958 I slot print_timing: id 0 | task 8607 | graphs reused = 8279 1.25.719.959 I slot print_timing: id 0 | task 8607 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.719.990 I slot release: id 0 | task 8607 | stop processing: n_tokens = 557, truncated = 0 1.25.724.325 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 85628921 1.25.724.384 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 1.25.744.913 I slot launch_slot_: id 0 | task 8674 | processing task, is_child = 0 1.26.408.646 I slot print_timing: id 0 | task 8674 | prompt eval time = 154.97 ms / 454 tokens ( 0.34 ms per token, 2929.58 tokens per second) 1.26.408.652 I slot print_timing: id 0 | task 8674 | eval time = 508.75 ms / 71 tokens ( 7.27 ms per token, 137.59 tokens per second) 1.26.408.653 I slot print_timing: id 0 | task 8674 | total time = 663.72 ms / 525 tokens 1.26.408.654 I slot print_timing: id 0 | task 8674 | graphs reused = 8347 1.26.408.655 I slot print_timing: id 0 | task 8674 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.408.687 I slot release: id 0 | task 8674 | stop processing: n_tokens = 549, truncated = 0 1.26.430.208 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 86317618 1.26.430.269 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 1.26.451.427 I slot launch_slot_: id 0 | task 8746 | processing task, is_child = 0 1.27.012.475 I slot print_timing: id 0 | task 8746 | prompt eval time = 138.59 ms / 409 tokens ( 0.34 ms per token, 2951.09 tokens per second) 1.27.012.480 I slot print_timing: id 0 | task 8746 | eval time = 422.44 ms / 60 tokens ( 7.16 ms per token, 139.67 tokens per second) 1.27.012.481 I slot print_timing: id 0 | task 8746 | total time = 561.03 ms / 469 tokens 1.27.012.482 I slot print_timing: id 0 | task 8746 | graphs reused = 8405 1.27.012.483 I slot print_timing: id 0 | task 8746 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.012.512 I slot release: id 0 | task 8746 | stop processing: n_tokens = 493, truncated = 0 1.27.038.103 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 86921443 1.27.038.163 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.163 MiB) 1.27.057.980 I slot launch_slot_: id 0 | task 8807 | processing task, is_child = 0 1.27.573.831 I slot print_timing: id 0 | task 8807 | prompt eval time = 114.81 ms / 349 tokens ( 0.33 ms per token, 3039.88 tokens per second) 1.27.573.837 I slot print_timing: id 0 | task 8807 | eval time = 401.03 ms / 57 tokens ( 7.16 ms per token, 139.64 tokens per second) 1.27.573.838 I slot print_timing: id 0 | task 8807 | total time = 515.83 ms / 406 tokens 1.27.573.839 I slot print_timing: id 0 | task 8807 | graphs reused = 8460 1.27.573.840 I slot print_timing: id 0 | task 8807 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.573.868 I slot release: id 0 | task 8807 | stop processing: n_tokens = 430, truncated = 0 1.27.599.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 87482799 1.27.599.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.319 MiB) 1.27.616.558 I slot launch_slot_: id 0 | task 8865 | processing task, is_child = 0 1.28.169.066 I slot print_timing: id 0 | task 8865 | prompt eval time = 139.02 ms / 435 tokens ( 0.32 ms per token, 3128.98 tokens per second) 1.28.169.071 I slot print_timing: id 0 | task 8865 | eval time = 413.46 ms / 58 tokens ( 7.25 ms per token, 137.86 tokens per second) 1.28.169.072 I slot print_timing: id 0 | task 8865 | total time = 552.49 ms / 493 tokens 1.28.169.073 I slot print_timing: id 0 | task 8865 | graphs reused = 8515 1.28.169.074 I slot print_timing: id 0 | task 8865 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.169.104 I slot release: id 0 | task 8865 | stop processing: n_tokens = 517, truncated = 0 1.28.189.724 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 88078035 1.28.189.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 1.28.191.748 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.631 MiB) 1.28.211.957 I slot launch_slot_: id 0 | task 8924 | processing task, is_child = 0 1.28.654.062 I slot print_timing: id 0 | task 8924 | prompt eval time = 102.68 ms / 322 tokens ( 0.32 ms per token, 3135.90 tokens per second) 1.28.654.067 I slot print_timing: id 0 | task 8924 | eval time = 339.41 ms / 47 tokens ( 7.38 ms per token, 135.53 tokens per second) 1.28.654.068 I slot print_timing: id 0 | task 8924 | total time = 442.09 ms / 369 tokens 1.28.654.069 I slot print_timing: id 0 | task 8924 | graphs reused = 8560 1.28.654.070 I slot print_timing: id 0 | task 8924 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.654.097 I slot release: id 0 | task 8924 | stop processing: n_tokens = 393, truncated = 0 1.28.672.162 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 88563028 1.28.672.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.944 MiB) 1.28.688.570 I slot launch_slot_: id 0 | task 8972 | processing task, is_child = 0 1.29.197.843 I slot print_timing: id 0 | task 8972 | prompt eval time = 115.06 ms / 360 tokens ( 0.32 ms per token, 3128.94 tokens per second) 1.29.197.849 I slot print_timing: id 0 | task 8972 | eval time = 394.20 ms / 56 tokens ( 7.17 ms per token, 139.52 tokens per second) 1.29.197.850 I slot print_timing: id 0 | task 8972 | total time = 509.26 ms / 416 tokens 1.29.197.851 I slot print_timing: id 0 | task 8972 | graphs reused = 8614 1.29.197.852 I slot print_timing: id 0 | task 8972 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.197.881 I slot release: id 0 | task 8972 | stop processing: n_tokens = 440, truncated = 0 1.29.221.107 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 89106812 1.29.221.160 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.069 MiB) 1.29.238.786 I slot launch_slot_: id 0 | task 9029 | processing task, is_child = 0 1.29.900.226 I slot print_timing: id 0 | task 9029 | prompt eval time = 139.15 ms / 443 tokens ( 0.31 ms per token, 3183.59 tokens per second) 1.29.900.232 I slot print_timing: id 0 | task 9029 | eval time = 522.27 ms / 73 tokens ( 7.25 ms per token, 137.86 tokens per second) 1.29.900.233 I slot print_timing: id 0 | task 9029 | total time = 661.42 ms / 516 tokens 1.29.900.234 I slot print_timing: id 0 | task 9029 | graphs reused = 8684 1.29.900.235 I slot print_timing: id 0 | task 9029 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.900.263 I slot release: id 0 | task 9029 | stop processing: n_tokens = 540, truncated = 0 1.29.921.682 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 89809194 1.29.921.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 1.29.942.346 I slot launch_slot_: id 0 | task 9103 | processing task, is_child = 0 1.30.390.647 I slot print_timing: id 0 | task 9103 | prompt eval time = 139.43 ms / 442 tokens ( 0.32 ms per token, 3170.09 tokens per second) 1.30.390.653 I slot print_timing: id 0 | task 9103 | eval time = 308.86 ms / 44 tokens ( 7.18 ms per token, 139.22 tokens per second) 1.30.390.654 I slot print_timing: id 0 | task 9103 | total time = 448.28 ms / 486 tokens 1.30.390.654 I slot print_timing: id 0 | task 9103 | graphs reused = 8726 1.30.390.656 I slot print_timing: id 0 | task 9103 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.390.687 I slot release: id 0 | task 9103 | stop processing: n_tokens = 510, truncated = 0 1.30.416.786 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 90299618 1.30.416.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 1.30.436.544 I slot launch_slot_: id 0 | task 9148 | processing task, is_child = 0 1.30.907.790 I slot print_timing: id 0 | task 9148 | prompt eval time = 154.96 ms / 470 tokens ( 0.33 ms per token, 3033.12 tokens per second) 1.30.907.796 I slot print_timing: id 0 | task 9148 | eval time = 316.27 ms / 44 tokens ( 7.36 ms per token, 135.96 tokens per second) 1.30.907.797 I slot print_timing: id 0 | task 9148 | total time = 471.23 ms / 514 tokens 1.30.907.798 I slot print_timing: id 0 | task 9148 | graphs reused = 8767 1.30.907.799 I slot print_timing: id 0 | task 9148 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.907.830 I slot release: id 0 | task 9148 | stop processing: n_tokens = 538, truncated = 0 1.30.913.086 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 538, t_last = 90816761 1.30.913.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.474 MiB) 1.30.933.226 I slot launch_slot_: id 0 | task 9193 | processing task, is_child = 0 1.31.334.949 I slot print_timing: id 0 | task 9193 | prompt eval time = 156.01 ms / 483 tokens ( 0.32 ms per token, 3095.94 tokens per second) 1.31.334.954 I slot print_timing: id 0 | task 9193 | eval time = 245.69 ms / 34 tokens ( 7.45 ms per token, 134.31 tokens per second) 1.31.334.956 I slot print_timing: id 0 | task 9193 | total time = 401.71 ms / 517 tokens 1.31.334.956 I slot print_timing: id 0 | task 9193 | graphs reused = 8798 1.31.334.957 I slot print_timing: id 0 | task 9193 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.334.990 I slot release: id 0 | task 9193 | stop processing: n_tokens = 541, truncated = 0 1.31.363.026 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 91243921 1.31.363.084 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 1.31.364.832 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 1.31.385.604 I slot launch_slot_: id 0 | task 9228 | processing task, is_child = 0 1.31.949.605 I slot print_timing: id 0 | task 9228 | prompt eval time = 155.10 ms / 463 tokens ( 0.33 ms per token, 2985.09 tokens per second) 1.31.949.612 I slot print_timing: id 0 | task 9228 | eval time = 408.87 ms / 55 tokens ( 7.57 ms per token, 132.07 tokens per second) 1.31.949.614 I slot print_timing: id 0 | task 9228 | total time = 563.98 ms / 518 tokens 1.31.949.616 I slot print_timing: id 0 | task 9228 | graphs reused = 8850 1.31.949.617 I slot print_timing: id 0 | task 9228 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.949.669 I slot release: id 0 | task 9228 | stop processing: n_tokens = 542, truncated = 0 1.31.955.151 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 91858600 1.31.955.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.255 MiB) 1.31.976.938 I slot launch_slot_: id 0 | task 9284 | processing task, is_child = 0 1.32.470.313 I slot print_timing: id 0 | task 9284 | prompt eval time = 139.21 ms / 421 tokens ( 0.33 ms per token, 3024.29 tokens per second) 1.32.470.319 I slot print_timing: id 0 | task 9284 | eval time = 354.15 ms / 50 tokens ( 7.23 ms per token, 138.36 tokens per second) 1.32.470.320 I slot print_timing: id 0 | task 9284 | total time = 493.36 ms / 471 tokens 1.32.470.321 I slot print_timing: id 0 | task 9284 | graphs reused = 8898 1.32.470.322 I slot print_timing: id 0 | task 9284 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.470.352 I slot release: id 0 | task 9284 | stop processing: n_tokens = 495, truncated = 0 1.32.491.043 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 92379283 1.32.491.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 1.32.512.112 I slot launch_slot_: id 0 | task 9335 | processing task, is_child = 0 1.32.930.767 I slot print_timing: id 0 | task 9335 | prompt eval time = 115.14 ms / 360 tokens ( 0.32 ms per token, 3126.52 tokens per second) 1.32.930.772 I slot print_timing: id 0 | task 9335 | eval time = 303.49 ms / 43 tokens ( 7.23 ms per token, 138.39 tokens per second) 1.32.930.774 I slot print_timing: id 0 | task 9335 | total time = 418.64 ms / 403 tokens 1.32.930.775 I slot print_timing: id 0 | task 9335 | graphs reused = 8939 1.32.930.775 I slot print_timing: id 0 | task 9335 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.930.808 I slot release: id 0 | task 9335 | stop processing: n_tokens = 427, truncated = 0 1.32.959.087 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 92839739 1.32.959.139 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 93.602 MiB) 1.32.980.901 I slot launch_slot_: id 0 | task 9379 | processing task, is_child = 0 1.33.944.132 I slot print_timing: id 0 | task 9379 | prompt eval time = 179.85 ms / 547 tokens ( 0.33 ms per token, 3041.36 tokens per second) 1.33.944.138 I slot print_timing: id 0 | task 9379 | eval time = 783.36 ms / 108 tokens ( 7.32 ms per token, 136.59 tokens per second) 1.33.944.139 I slot print_timing: id 0 | task 9379 | total time = 963.22 ms / 655 tokens 1.33.944.140 I slot print_timing: id 0 | task 9379 | graphs reused = 9045 1.33.944.141 I slot print_timing: id 0 | task 9379 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.944.176 I slot release: id 0 | task 9379 | stop processing: n_tokens = 679, truncated = 0 1.33.960.752 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 679, t_last = 93853107 1.33.960.812 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 1.33.964.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.193 MiB) 1.33.993.980 I slot launch_slot_: id 0 | task 9488 | processing task, is_child = 0 1.35.006.358 I slot print_timing: id 0 | task 9488 | prompt eval time = 241.67 ms / 749 tokens ( 0.32 ms per token, 3099.28 tokens per second) 1.35.006.364 I slot print_timing: id 0 | task 9488 | eval time = 770.69 ms / 107 tokens ( 7.27 ms per token, 137.54 tokens per second) 1.35.006.365 I slot print_timing: id 0 | task 9488 | total time = 1012.36 ms / 856 tokens 1.35.006.366 I slot print_timing: id 0 | task 9488 | graphs reused = 9150 1.35.006.367 I slot print_timing: id 0 | task 9488 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.006.406 I slot release: id 0 | task 9488 | stop processing: n_tokens = 880, truncated = 0 1.35.033.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 94915337 1.35.034.007 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.600 MiB) 1.35.066.175 I slot launch_slot_: id 0 | task 9596 | processing task, is_child = 0 1.35.627.766 I slot print_timing: id 0 | task 9596 | prompt eval time = 218.39 ms / 678 tokens ( 0.32 ms per token, 3104.59 tokens per second) 1.35.627.772 I slot print_timing: id 0 | task 9596 | eval time = 343.19 ms / 48 tokens ( 7.30 ms per token, 136.95 tokens per second) 1.35.627.773 I slot print_timing: id 0 | task 9596 | total time = 561.58 ms / 726 tokens 1.35.627.774 I slot print_timing: id 0 | task 9596 | graphs reused = 9196 1.35.627.775 I slot print_timing: id 0 | task 9596 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.627.813 I slot release: id 0 | task 9596 | stop processing: n_tokens = 750, truncated = 0 1.35.645.988 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 95536744 1.35.646.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.538 MiB) 1.35.651.113 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 1.35.679.278 I slot launch_slot_: id 0 | task 9645 | processing task, is_child = 0 1.36.285.639 I slot print_timing: id 0 | task 9645 | prompt eval time = 182.28 ms / 567 tokens ( 0.32 ms per token, 3110.63 tokens per second) 1.36.285.645 I slot print_timing: id 0 | task 9645 | eval time = 424.07 ms / 57 tokens ( 7.57 ms per token, 132.05 tokens per second) 1.36.285.646 I slot print_timing: id 0 | task 9645 | total time = 606.34 ms / 624 tokens 1.36.285.647 I slot print_timing: id 0 | task 9645 | graphs reused = 9251 1.36.285.648 I slot print_timing: id 0 | task 9645 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.285.683 I slot release: id 0 | task 9645 | stop processing: n_tokens = 648, truncated = 0 1.36.302.229 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 96194614 1.36.302.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 1.36.306.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.381 MiB) 1.36.332.206 I slot launch_slot_: id 0 | task 9703 | processing task, is_child = 0 1.36.904.597 I slot print_timing: id 0 | task 9703 | prompt eval time = 158.05 ms / 501 tokens ( 0.32 ms per token, 3169.82 tokens per second) 1.36.904.602 I slot print_timing: id 0 | task 9703 | eval time = 414.32 ms / 58 tokens ( 7.27 ms per token, 137.57 tokens per second) 1.36.904.604 I slot print_timing: id 0 | task 9703 | total time = 572.37 ms / 559 tokens 1.36.904.604 I slot print_timing: id 0 | task 9703 | graphs reused = 9307 1.36.904.605 I slot print_timing: id 0 | task 9703 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.904.637 I slot release: id 0 | task 9703 | stop processing: n_tokens = 583, truncated = 0 1.36.926.719 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 96813568 1.36.926.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 1.36.950.808 I slot launch_slot_: id 0 | task 9762 | processing task, is_child = 0 1.37.643.298 I slot print_timing: id 0 | task 9762 | prompt eval time = 246.24 ms / 769 tokens ( 0.32 ms per token, 3122.92 tokens per second) 1.37.643.305 I slot print_timing: id 0 | task 9762 | eval time = 446.23 ms / 62 tokens ( 7.32 ms per token, 136.70 tokens per second) 1.37.643.305 I slot print_timing: id 0 | task 9762 | total time = 692.47 ms / 831 tokens 1.37.643.306 I slot print_timing: id 0 | task 9762 | graphs reused = 9367 1.37.643.307 I slot print_timing: id 0 | task 9762 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.643.347 I slot release: id 0 | task 9762 | stop processing: n_tokens = 855, truncated = 0 1.37.670.532 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 97552278 1.37.670.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 73.756 MiB) 1.37.675.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 1.37.706.241 I slot launch_slot_: id 0 | task 9825 | processing task, is_child = 0 1.38.309.947 I slot print_timing: id 0 | task 9825 | prompt eval time = 157.80 ms / 500 tokens ( 0.32 ms per token, 3168.53 tokens per second) 1.38.309.953 I slot print_timing: id 0 | task 9825 | eval time = 445.89 ms / 61 tokens ( 7.43 ms per token, 134.56 tokens per second) 1.38.309.954 I slot print_timing: id 0 | task 9825 | total time = 603.69 ms / 561 tokens 1.38.309.955 I slot print_timing: id 0 | task 9825 | graphs reused = 9426 1.38.309.957 I slot print_timing: id 0 | task 9825 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.309.989 I slot release: id 0 | task 9825 | stop processing: n_tokens = 585, truncated = 0 1.38.327.876 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 98218920 1.38.327.938 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.945 MiB) 1.38.353.019 I slot launch_slot_: id 0 | task 9887 | processing task, is_child = 0 1.38.978.493 I slot print_timing: id 0 | task 9887 | prompt eval time = 201.94 ms / 632 tokens ( 0.32 ms per token, 3129.61 tokens per second) 1.38.978.498 I slot print_timing: id 0 | task 9887 | eval time = 423.52 ms / 58 tokens ( 7.43 ms per token, 134.59 tokens per second) 1.38.978.500 I slot print_timing: id 0 | task 9887 | total time = 625.46 ms / 690 tokens 1.38.978.501 I slot print_timing: id 0 | task 9887 | graphs reused = 9482 1.38.978.501 I slot print_timing: id 0 | task 9887 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.978.537 I slot release: id 0 | task 9887 | stop processing: n_tokens = 714, truncated = 0 1.39.003.829 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 98887468 1.39.003.896 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.539 MiB) 1.39.032.369 I slot launch_slot_: id 0 | task 9946 | processing task, is_child = 0 1.39.429.884 I slot print_timing: id 0 | task 9946 | prompt eval time = 137.64 ms / 395 tokens ( 0.35 ms per token, 2869.89 tokens per second) 1.39.429.889 I slot print_timing: id 0 | task 9946 | eval time = 259.86 ms / 37 tokens ( 7.22 ms per token, 138.53 tokens per second) 1.39.429.891 I slot print_timing: id 0 | task 9946 | total time = 397.50 ms / 432 tokens 1.39.429.891 I slot print_timing: id 0 | task 9946 | graphs reused = 9517 1.39.429.892 I slot print_timing: id 0 | task 9946 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.429.922 I slot release: id 0 | task 9946 | stop processing: n_tokens = 456, truncated = 0 1.39.435.166 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 99338853 1.39.435.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.100 MiB) 1.39.455.134 I slot launch_slot_: id 0 | task 9984 | processing task, is_child = 0 1.40.083.080 I slot print_timing: id 0 | task 9984 | prompt eval time = 187.88 ms / 579 tokens ( 0.32 ms per token, 3081.72 tokens per second) 1.40.083.086 I slot print_timing: id 0 | task 9984 | eval time = 440.05 ms / 59 tokens ( 7.59 ms per token, 131.80 tokens per second) 1.40.083.087 I slot print_timing: id 0 | task 9984 | total time = 627.93 ms / 638 tokens 1.40.083.087 I slot print_timing: id 0 | task 9984 | graphs reused = 9574 1.40.083.088 I slot print_timing: id 0 | task 9984 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.083.125 I slot release: id 0 | task 9984 | stop processing: n_tokens = 662, truncated = 0 1.40.088.355 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 662, t_last = 99992056 1.40.088.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 1.40.092.902 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.974 MiB) 1.40.118.460 I slot launch_slot_: id 0 | task 10044 | processing task, is_child = 0 1.40.666.585 I slot print_timing: id 0 | task 10044 | prompt eval time = 218.45 ms / 689 tokens ( 0.32 ms per token, 3154.03 tokens per second) 1.40.666.591 I slot print_timing: id 0 | task 10044 | eval time = 329.66 ms / 46 tokens ( 7.33 ms per token, 136.50 tokens per second) 1.40.666.592 I slot print_timing: id 0 | task 10044 | total time = 548.11 ms / 735 tokens 1.40.666.593 I slot print_timing: id 0 | task 10044 | graphs reused = 9618 1.40.666.594 I slot print_timing: id 0 | task 10044 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.666.634 I slot release: id 0 | task 10044 | stop processing: n_tokens = 759, truncated = 0 1.40.688.280 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 759, t_last = 100575565 1.40.688.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 1.40.717.211 I slot launch_slot_: id 0 | task 10091 | processing task, is_child = 0 1.41.430.858 I slot print_timing: id 0 | task 10091 | prompt eval time = 238.03 ms / 752 tokens ( 0.32 ms per token, 3159.24 tokens per second) 1.41.430.864 I slot print_timing: id 0 | task 10091 | eval time = 475.60 ms / 66 tokens ( 7.32 ms per token, 136.67 tokens per second) 1.41.430.865 I slot print_timing: id 0 | task 10091 | total time = 713.63 ms / 818 tokens 1.41.430.866 I slot print_timing: id 0 | task 10091 | graphs reused = 9682 1.41.430.867 I slot print_timing: id 0 | task 10091 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.430.911 I slot release: id 0 | task 10091 | stop processing: n_tokens = 842, truncated = 0 1.41.436.416 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 842, t_last = 101339842 1.41.436.483 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.320 MiB) 1.41.442.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 1.41.476.239 I slot launch_slot_: id 0 | task 10158 | processing task, is_child = 0 1.42.144.222 I slot print_timing: id 0 | task 10158 | prompt eval time = 188.07 ms / 582 tokens ( 0.32 ms per token, 3094.64 tokens per second) 1.42.144.228 I slot print_timing: id 0 | task 10158 | eval time = 479.90 ms / 67 tokens ( 7.27 ms per token, 137.53 tokens per second) 1.42.144.229 I slot print_timing: id 0 | task 10158 | total time = 667.97 ms / 649 tokens 1.42.144.230 I slot print_timing: id 0 | task 10158 | graphs reused = 9747 1.42.144.231 I slot print_timing: id 0 | task 10158 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.144.269 I slot release: id 0 | task 10158 | stop processing: n_tokens = 673, truncated = 0 1.42.172.237 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 673, t_last = 102053200 1.42.172.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.603 MiB) 1.42.201.335 I slot launch_slot_: id 0 | task 10226 | processing task, is_child = 0 1.42.962.171 I slot print_timing: id 0 | task 10226 | prompt eval time = 210.36 ms / 656 tokens ( 0.32 ms per token, 3118.52 tokens per second) 1.42.962.177 I slot print_timing: id 0 | task 10226 | eval time = 550.46 ms / 77 tokens ( 7.24 ms per token, 138.07 tokens per second) 1.42.962.178 I slot print_timing: id 0 | task 10226 | total time = 760.82 ms / 733 tokens 1.42.962.178 I slot print_timing: id 0 | task 10226 | graphs reused = 9822 1.42.962.179 I slot print_timing: id 0 | task 10226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.962.217 I slot release: id 0 | task 10226 | stop processing: n_tokens = 757, truncated = 0 1.42.968.036 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 102871148 1.42.968.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.728 MiB) 1.42.998.929 I slot launch_slot_: id 0 | task 10304 | processing task, is_child = 0 1.43.416.638 I slot print_timing: id 0 | task 10304 | prompt eval time = 197.18 ms / 613 tokens ( 0.32 ms per token, 3108.77 tokens per second) 1.43.416.644 I slot print_timing: id 0 | task 10304 | eval time = 220.51 ms / 31 tokens ( 7.35 ms per token, 136.05 tokens per second) 1.43.416.645 I slot print_timing: id 0 | task 10304 | total time = 417.69 ms / 644 tokens 1.43.416.646 I slot print_timing: id 0 | task 10304 | graphs reused = 9851 1.43.416.647 I slot print_timing: id 0 | task 10304 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.416.683 I slot release: id 0 | task 10304 | stop processing: n_tokens = 668, truncated = 0 1.43.435.827 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 668, t_last = 103325614 1.43.435.891 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 1.43.463.001 I slot launch_slot_: id 0 | task 10336 | processing task, is_child = 0 1.44.387.156 I slot print_timing: id 0 | task 10336 | prompt eval time = 238.12 ms / 766 tokens ( 0.31 ms per token, 3216.87 tokens per second) 1.44.387.161 I slot print_timing: id 0 | task 10336 | eval time = 686.02 ms / 94 tokens ( 7.38 ms per token, 135.57 tokens per second) 1.44.387.163 I slot print_timing: id 0 | task 10336 | total time = 924.14 ms / 860 tokens 1.44.387.164 I slot print_timing: id 0 | task 10336 | graphs reused = 9943 1.44.387.164 I slot print_timing: id 0 | task 10336 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.387.208 I slot release: id 0 | task 10336 | stop processing: n_tokens = 884, truncated = 0 1.44.407.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 884, t_last = 104296139 1.44.408.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.415 MiB) 1.44.442.028 I slot launch_slot_: id 0 | task 10431 | processing task, is_child = 0 1.45.139.419 I slot print_timing: id 0 | task 10431 | prompt eval time = 259.31 ms / 846 tokens ( 0.31 ms per token, 3262.52 tokens per second) 1.45.139.425 I slot print_timing: id 0 | task 10431 | eval time = 438.06 ms / 61 tokens ( 7.30 ms per token, 136.97 tokens per second) 1.45.139.427 I slot print_timing: id 0 | task 10431 | total time = 697.37 ms / 907 tokens 1.45.139.427 I slot print_timing: id 0 | task 10431 | graphs reused = 10002 1.45.139.428 I slot print_timing: id 0 | task 10431 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.139.477 I slot release: id 0 | task 10431 | stop processing: n_tokens = 931, truncated = 0 1.45.158.509 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 105048408 1.45.158.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.102 MiB) 1.45.164.964 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.008 MiB) 1.45.199.685 I slot launch_slot_: id 0 | task 10493 | processing task, is_child = 0 1.45.972.289 I slot print_timing: id 0 | task 10493 | prompt eval time = 209.78 ms / 650 tokens ( 0.32 ms per token, 3098.41 tokens per second) 1.45.972.294 I slot print_timing: id 0 | task 10493 | eval time = 562.80 ms / 77 tokens ( 7.41 ms per token, 135.04 tokens per second) 1.45.972.295 I slot print_timing: id 0 | task 10493 | total time = 772.58 ms / 727 tokens 1.45.972.296 I slot print_timing: id 0 | task 10493 | graphs reused = 10077 1.45.972.297 I slot print_timing: id 0 | task 10493 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.972.336 I slot release: id 0 | task 10493 | stop processing: n_tokens = 751, truncated = 0 1.46.000.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 105881267 1.46.000.338 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.507 MiB) 1.46.029.551 I slot launch_slot_: id 0 | task 10571 | processing task, is_child = 0 1.46.640.296 I slot print_timing: id 0 | task 10571 | prompt eval time = 227.78 ms / 717 tokens ( 0.32 ms per token, 3147.73 tokens per second) 1.46.640.302 I slot print_timing: id 0 | task 10571 | eval time = 382.95 ms / 53 tokens ( 7.36 ms per token, 135.79 tokens per second) 1.46.640.303 I slot print_timing: id 0 | task 10571 | total time = 610.73 ms / 770 tokens 1.46.640.304 I slot print_timing: id 0 | task 10571 | graphs reused = 10127 1.46.640.305 I slot print_timing: id 0 | task 10571 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.640.346 I slot release: id 0 | task 10571 | stop processing: n_tokens = 794, truncated = 0 1.46.656.300 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 794, t_last = 106549277 1.46.656.358 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.039 MiB) 1.46.687.305 I slot launch_slot_: id 0 | task 10625 | processing task, is_child = 0 1.47.265.915 I slot print_timing: id 0 | task 10625 | prompt eval time = 157.58 ms / 494 tokens ( 0.32 ms per token, 3134.94 tokens per second) 1.47.265.920 I slot print_timing: id 0 | task 10625 | eval time = 421.01 ms / 59 tokens ( 7.26 ms per token, 137.76 tokens per second) 1.47.265.921 I slot print_timing: id 0 | task 10625 | total time = 578.59 ms / 553 tokens 1.47.265.922 I slot print_timing: id 0 | task 10625 | graphs reused = 10184 1.47.265.923 I slot print_timing: id 0 | task 10625 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.265.956 I slot release: id 0 | task 10625 | stop processing: n_tokens = 577, truncated = 0 1.47.294.020 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 107174887 1.47.294.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.789 MiB) 1.47.318.980 I slot launch_slot_: id 0 | task 10685 | processing task, is_child = 0 1.47.892.272 I slot print_timing: id 0 | task 10685 | prompt eval time = 187.74 ms / 579 tokens ( 0.32 ms per token, 3084.09 tokens per second) 1.47.892.279 I slot print_timing: id 0 | task 10685 | eval time = 385.54 ms / 54 tokens ( 7.27 ms per token, 137.47 tokens per second) 1.47.892.280 I slot print_timing: id 0 | task 10685 | total time = 573.27 ms / 633 tokens 1.47.892.281 I slot print_timing: id 0 | task 10685 | graphs reused = 10236 1.47.892.282 I slot print_timing: id 0 | task 10685 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.892.323 I slot release: id 0 | task 10685 | stop processing: n_tokens = 657, truncated = 0 1.47.923.095 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 657, t_last = 107801254 1.47.923.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.194 MiB) 1.47.949.714 I slot launch_slot_: id 0 | task 10740 | processing task, is_child = 0 1.48.785.556 I slot print_timing: id 0 | task 10740 | prompt eval time = 294.67 ms / 919 tokens ( 0.32 ms per token, 3118.76 tokens per second) 1.48.785.563 I slot print_timing: id 0 | task 10740 | eval time = 541.16 ms / 73 tokens ( 7.52 ms per token, 133.05 tokens per second) 1.48.785.564 I slot print_timing: id 0 | task 10740 | total time = 835.83 ms / 992 tokens 1.48.785.565 I slot print_timing: id 0 | task 10740 | graphs reused = 10307 1.48.785.566 I slot print_timing: id 0 | task 10740 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.785.612 I slot release: id 0 | task 10740 | stop processing: n_tokens = 1016, truncated = 0 1.48.802.487 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 108694543 1.48.802.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.477 MiB) 1.48.808.645 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.476 MiB) 1.48.845.405 I slot launch_slot_: id 0 | task 10814 | processing task, is_child = 0 1.49.394.732 I slot print_timing: id 0 | task 10814 | prompt eval time = 270.73 ms / 865 tokens ( 0.31 ms per token, 3195.02 tokens per second) 1.49.394.737 I slot print_timing: id 0 | task 10814 | eval time = 278.57 ms / 39 tokens ( 7.33 ms per token, 136.41 tokens per second) 1.49.394.739 I slot print_timing: id 0 | task 10814 | total time = 549.31 ms / 904 tokens 1.49.394.740 I slot print_timing: id 0 | task 10814 | graphs reused = 10344 1.49.394.741 I slot print_timing: id 0 | task 10814 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.394.786 I slot release: id 0 | task 10814 | stop processing: n_tokens = 928, truncated = 0 1.49.421.607 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 109303717 1.49.421.686 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.507 MiB) 1.49.426.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.038 MiB) 1.49.462.933 I slot launch_slot_: id 0 | task 10854 | processing task, is_child = 0 1.50.226.093 I slot print_timing: id 0 | task 10854 | prompt eval time = 137.75 ms / 408 tokens ( 0.34 ms per token, 2961.91 tokens per second) 1.50.226.098 I slot print_timing: id 0 | task 10854 | eval time = 625.39 ms / 88 tokens ( 7.19 ms per token, 139.11 tokens per second) 1.50.226.099 I slot print_timing: id 0 | task 10854 | total time = 763.14 ms / 496 tokens 1.50.226.100 I slot print_timing: id 0 | task 10854 | graphs reused = 10429 1.50.226.101 I slot print_timing: id 0 | task 10854 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.226.131 I slot release: id 0 | task 10854 | stop processing: n_tokens = 520, truncated = 0 1.50.230.222 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 110135062 1.50.230.278 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.225 MiB) 1.50.252.769 I slot launch_slot_: id 0 | task 10943 | processing task, is_child = 0 1.50.866.422 I slot print_timing: id 0 | task 10943 | prompt eval time = 114.24 ms / 338 tokens ( 0.34 ms per token, 2958.71 tokens per second) 1.50.866.427 I slot print_timing: id 0 | task 10943 | eval time = 499.40 ms / 71 tokens ( 7.13 ms per token, 140.17 tokens per second) 1.50.866.428 I slot print_timing: id 0 | task 10943 | total time = 613.64 ms / 409 tokens 1.50.866.429 I slot print_timing: id 0 | task 10943 | graphs reused = 10498 1.50.866.430 I slot print_timing: id 0 | task 10943 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.866.458 I slot release: id 0 | task 10943 | stop processing: n_tokens = 435, truncated = 0 1.50.870.476 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 435, t_last = 110775389 1.50.870.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.884 MiB) 1.50.892.485 I slot launch_slot_: id 0 | task 11015 | processing task, is_child = 0 1.54.010.124 I slot print_timing: id 0 | task 11015 | n_gen = 419, tg = 139.22 t/s, tg_3s = 139.55 t/s 1.57.013.853 I slot print_timing: id 0 | task 11015 | n_gen = 831, tg = 138.19 t/s, tg_3s = 137.16 t/s 1.58.446.317 I slot print_timing: id 0 | task 11015 | prompt eval time = 115.13 ms / 363 tokens ( 0.32 ms per token, 3153.07 tokens per second) 1.58.446.323 I slot print_timing: id 0 | task 11015 | eval time = 7438.69 ms / 1024 tokens ( 7.27 ms per token, 137.52 tokens per second) 1.58.446.324 I slot print_timing: id 0 | task 11015 | total time = 7553.82 ms / 1387 tokens 1.58.446.325 I slot print_timing: id 0 | task 11015 | graphs reused = 11516 1.58.446.325 I slot print_timing: id 0 | task 11015 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.446.353 I slot release: id 0 | task 11015 | stop processing: n_tokens = 1413, truncated = 0 1.58.464.651 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1413, t_last = 118355284 1.58.464.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 1.58.470.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.387 MiB) 1.58.523.223 I slot launch_slot_: id 0 | task 12040 | processing task, is_child = 0 2.01.628.398 I slot print_timing: id 0 | task 12040 | n_gen = 420, tg = 139.56 t/s, tg_3s = 139.89 t/s 2.04.635.605 I slot print_timing: id 0 | task 12040 | n_gen = 832, tg = 138.28 t/s, tg_3s = 137.00 t/s 2.05.804.627 I slot print_timing: id 0 | task 12040 | prompt eval time = 102.82 ms / 317 tokens ( 0.32 ms per token, 3082.94 tokens per second) 2.05.804.634 I slot print_timing: id 0 | task 12040 | eval time = 7178.56 ms / 990 tokens ( 7.26 ms per token, 137.77 tokens per second) 2.05.804.635 I slot print_timing: id 0 | task 12040 | total time = 7281.39 ms / 1307 tokens 2.05.804.636 I slot print_timing: id 0 | task 12040 | graphs reused = 12500 2.05.804.637 I slot print_timing: id 0 | task 12040 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.804.665 I slot release: id 0 | task 12040 | stop processing: n_tokens = 1333, truncated = 0 2.05.819.403 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1333, t_last = 125713596 2.05.819.492 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.413 MiB) 2.05.824.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.791 MiB) 2.05.874.447 I slot launch_slot_: id 0 | task 13031 | processing task, is_child = 0 2.09.012.856 I slot print_timing: id 0 | task 13031 | n_gen = 418, tg = 138.95 t/s, tg_3s = 139.28 t/s 2.09.308.960 I slot print_timing: id 0 | task 13031 | prompt eval time = 137.27 ms / 389 tokens ( 0.35 ms per token, 2833.89 tokens per second) 2.09.308.966 I slot print_timing: id 0 | task 13031 | eval time = 3297.23 ms / 459 tokens ( 7.20 ms per token, 138.90 tokens per second) 2.09.308.967 I slot print_timing: id 0 | task 13031 | total time = 3434.49 ms / 848 tokens 2.09.308.968 I slot print_timing: id 0 | task 13031 | graphs reused = 12955 2.09.308.969 I slot print_timing: id 0 | task 13031 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.308.999 I slot release: id 0 | task 13031 | stop processing: n_tokens = 872, truncated = 0 2.09.326.286 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 872, t_last = 129217930 2.09.326.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.073 MiB) 2.09.362.161 I slot launch_slot_: id 0 | task 13491 | processing task, is_child = 0 2.09.681.626 I slot print_timing: id 0 | task 13491 | prompt eval time = 102.45 ms / 300 tokens ( 0.34 ms per token, 2928.29 tokens per second) 2.09.681.632 I slot print_timing: id 0 | task 13491 | eval time = 217.00 ms / 31 tokens ( 7.23 ms per token, 138.25 tokens per second) 2.09.681.633 I slot print_timing: id 0 | task 13491 | total time = 319.44 ms / 331 tokens 2.09.681.634 I slot print_timing: id 0 | task 13491 | graphs reused = 12984 2.09.681.635 I slot print_timing: id 0 | task 13491 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.681.661 I slot release: id 0 | task 13491 | stop processing: n_tokens = 355, truncated = 0 2.09.703.683 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 129590592 2.09.716.731 I slot launch_slot_: id 0 | task 13523 | processing task, is_child = 0 2.10.154.205 I slot print_timing: id 0 | task 13523 | prompt eval time = 114.58 ms / 341 tokens ( 0.34 ms per token, 2976.11 tokens per second) 2.10.154.210 I slot print_timing: id 0 | task 13523 | eval time = 322.88 ms / 46 tokens ( 7.18 ms per token, 139.37 tokens per second) 2.10.154.211 I slot print_timing: id 0 | task 13523 | total time = 437.46 ms / 387 tokens 2.10.154.212 I slot print_timing: id 0 | task 13523 | graphs reused = 13028 2.10.154.213 I slot print_timing: id 0 | task 13523 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.154.243 I slot release: id 0 | task 13523 | stop processing: n_tokens = 411, truncated = 0 2.10.174.774 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 130063174 2.10.174.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.788 MiB) 2.10.194.065 I slot launch_slot_: id 0 | task 13570 | processing task, is_child = 0 2.11.058.533 I slot print_timing: id 0 | task 13570 | prompt eval time = 103.02 ms / 332 tokens ( 0.31 ms per token, 3222.68 tokens per second) 2.11.058.538 I slot print_timing: id 0 | task 13570 | eval time = 761.43 ms / 108 tokens ( 7.12 ms per token, 140.52 tokens per second) 2.11.058.539 I slot print_timing: id 0 | task 13570 | total time = 864.45 ms / 440 tokens 2.11.058.540 I slot print_timing: id 0 | task 13570 | graphs reused = 13134 2.11.058.541 I slot print_timing: id 0 | task 13570 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.058.569 I slot release: id 0 | task 13570 | stop processing: n_tokens = 464, truncated = 0 2.11.085.621 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 464, t_last = 130967500 2.11.085.675 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.040 MiB) 2.11.107.937 I slot launch_slot_: id 0 | task 13679 | processing task, is_child = 0 2.11.429.342 I slot print_timing: id 0 | task 13679 | prompt eval time = 90.36 ms / 269 tokens ( 0.34 ms per token, 2977.15 tokens per second) 2.11.429.348 I slot print_timing: id 0 | task 13679 | eval time = 231.04 ms / 33 tokens ( 7.22 ms per token, 138.51 tokens per second) 2.11.429.349 I slot print_timing: id 0 | task 13679 | total time = 321.39 ms / 302 tokens 2.11.429.350 I slot print_timing: id 0 | task 13679 | graphs reused = 13165 2.11.429.351 I slot print_timing: id 0 | task 13679 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.429.376 I slot release: id 0 | task 13679 | stop processing: n_tokens = 326, truncated = 0 2.11.457.654 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 326, t_last = 131338307 2.11.469.295 I slot launch_slot_: id 0 | task 13713 | processing task, is_child = 0 2.12.402.097 I slot print_timing: id 0 | task 13713 | prompt eval time = 114.52 ms / 341 tokens ( 0.34 ms per token, 2977.62 tokens per second) 2.12.402.102 I slot print_timing: id 0 | task 13713 | eval time = 818.27 ms / 116 tokens ( 7.12 ms per token, 140.54 tokens per second) 2.12.402.103 I slot print_timing: id 0 | task 13713 | total time = 932.79 ms / 457 tokens 2.12.402.104 I slot print_timing: id 0 | task 13713 | graphs reused = 13279 2.12.402.105 I slot print_timing: id 0 | task 13713 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.402.133 I slot release: id 0 | task 13713 | stop processing: n_tokens = 481, truncated = 0 2.12.423.954 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 132311064 2.12.424.009 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.980 MiB) 2.12.448.998 I slot launch_slot_: id 0 | task 13830 | processing task, is_child = 0 2.13.006.197 I slot print_timing: id 0 | task 13830 | prompt eval time = 114.34 ms / 343 tokens ( 0.33 ms per token, 2999.75 tokens per second) 2.13.006.202 I slot print_timing: id 0 | task 13830 | eval time = 442.84 ms / 63 tokens ( 7.14 ms per token, 140.01 tokens per second) 2.13.006.203 I slot print_timing: id 0 | task 13830 | total time = 557.18 ms / 406 tokens 2.13.006.204 I slot print_timing: id 0 | task 13830 | graphs reused = 13340 2.13.006.205 I slot print_timing: id 0 | task 13830 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.006.231 I slot release: id 0 | task 13830 | stop processing: n_tokens = 430, truncated = 0 2.13.030.570 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 132915163 2.13.045.493 I slot launch_slot_: id 0 | task 13894 | processing task, is_child = 0 2.14.425.362 I slot print_timing: id 0 | task 13894 | prompt eval time = 114.69 ms / 347 tokens ( 0.33 ms per token, 3025.44 tokens per second) 2.14.425.367 I slot print_timing: id 0 | task 13894 | eval time = 1265.16 ms / 178 tokens ( 7.15 ms per token, 139.90 tokens per second) 2.14.425.368 I slot print_timing: id 0 | task 13894 | total time = 1379.85 ms / 525 tokens 2.14.425.369 I slot print_timing: id 0 | task 13894 | graphs reused = 13515 2.14.425.370 I slot print_timing: id 0 | task 13894 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.425.399 I slot release: id 0 | task 13894 | stop processing: n_tokens = 549, truncated = 0 2.14.451.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 134334330 2.14.451.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 2.14.486.374 I slot launch_slot_: id 0 | task 14073 | processing task, is_child = 0 2.17.595.463 I slot print_timing: id 0 | task 14073 | n_gen = 417, tg = 138.37 t/s, tg_3s = 138.71 t/s 2.20.602.499 I slot print_timing: id 0 | task 14073 | n_gen = 830, tg = 137.86 t/s, tg_3s = 137.34 t/s 2.22.040.850 I slot print_timing: id 0 | task 14073 | prompt eval time = 102.74 ms / 332 tokens ( 0.31 ms per token, 3231.43 tokens per second) 2.22.040.856 I slot print_timing: id 0 | task 14073 | eval time = 7451.72 ms / 1024 tokens ( 7.28 ms per token, 137.28 tokens per second) 2.22.040.857 I slot print_timing: id 0 | task 14073 | total time = 7554.46 ms / 1356 tokens 2.22.040.857 I slot print_timing: id 0 | task 14073 | graphs reused = 14533 2.22.040.858 I slot print_timing: id 0 | task 14073 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.040.888 I slot release: id 0 | task 14073 | stop processing: n_tokens = 1380, truncated = 0 2.22.068.794 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1380, t_last = 141949819 2.22.068.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.539 MiB) 2.22.075.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.163 MiB) 2.22.123.498 I slot launch_slot_: id 0 | task 15098 | processing task, is_child = 0 2.22.755.137 I slot print_timing: id 0 | task 15098 | prompt eval time = 102.98 ms / 332 tokens ( 0.31 ms per token, 3224.02 tokens per second) 2.22.755.142 I slot print_timing: id 0 | task 15098 | eval time = 528.64 ms / 75 tokens ( 7.14 ms per token, 139.98 tokens per second) 2.22.755.143 I slot print_timing: id 0 | task 15098 | total time = 631.62 ms / 407 tokens 2.22.755.144 I slot print_timing: id 0 | task 15098 | graphs reused = 14606 2.22.755.145 I slot print_timing: id 0 | task 15098 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.755.172 I slot release: id 0 | task 15098 | stop processing: n_tokens = 431, truncated = 0 2.22.783.295 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 431, t_last = 142664103 2.22.783.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.633 MiB) 2.22.803.951 I slot launch_slot_: id 0 | task 15174 | processing task, is_child = 0 2.23.179.017 I slot print_timing: id 0 | task 15174 | prompt eval time = 114.93 ms / 354 tokens ( 0.32 ms per token, 3080.19 tokens per second) 2.23.179.023 I slot print_timing: id 0 | task 15174 | eval time = 260.12 ms / 37 tokens ( 7.23 ms per token, 138.40 tokens per second) 2.23.179.024 I slot print_timing: id 0 | task 15174 | total time = 375.05 ms / 391 tokens 2.23.179.025 I slot print_timing: id 0 | task 15174 | graphs reused = 14641 2.23.179.026 I slot print_timing: id 0 | task 15174 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.179.055 I slot release: id 0 | task 15174 | stop processing: n_tokens = 415, truncated = 0 2.23.203.570 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 415, t_last = 143087986 2.23.203.623 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.883 MiB) 2.23.223.634 I slot launch_slot_: id 0 | task 15212 | processing task, is_child = 0 2.23.980.832 I slot print_timing: id 0 | task 15212 | prompt eval time = 115.03 ms / 354 tokens ( 0.32 ms per token, 3077.57 tokens per second) 2.23.980.837 I slot print_timing: id 0 | task 15212 | eval time = 642.16 ms / 91 tokens ( 7.14 ms per token, 140.15 tokens per second) 2.23.980.838 I slot print_timing: id 0 | task 15212 | total time = 757.18 ms / 445 tokens 2.23.980.839 I slot print_timing: id 0 | task 15212 | graphs reused = 14730 2.23.980.840 I slot print_timing: id 0 | task 15212 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.980.869 I slot release: id 0 | task 15212 | stop processing: n_tokens = 469, truncated = 0 2.23.984.972 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 143889800 2.23.985.027 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.447 MiB) 2.24.008.091 I slot launch_slot_: id 0 | task 15304 | processing task, is_child = 0 2.24.568.598 I slot print_timing: id 0 | task 15304 | prompt eval time = 115.09 ms / 339 tokens ( 0.34 ms per token, 2945.42 tokens per second) 2.24.568.604 I slot print_timing: id 0 | task 15304 | eval time = 445.40 ms / 62 tokens ( 7.30 ms per token, 136.96 tokens per second) 2.24.568.605 I slot print_timing: id 0 | task 15304 | total time = 560.49 ms / 401 tokens 2.24.568.606 I slot print_timing: id 0 | task 15304 | graphs reused = 14790 2.24.568.606 I slot print_timing: id 0 | task 15304 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.568.635 I slot release: id 0 | task 15304 | stop processing: n_tokens = 425, truncated = 0 2.24.594.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 144477566 2.24.609.469 I slot launch_slot_: id 0 | task 15367 | processing task, is_child = 0 2.27.728.417 I slot print_timing: id 0 | task 15367 | n_gen = 419, tg = 139.14 t/s, tg_3s = 139.48 t/s 2.30.149.720 I slot print_timing: id 0 | task 15367 | prompt eval time = 114.85 ms / 351 tokens ( 0.33 ms per token, 3056.05 tokens per second) 2.30.149.725 I slot print_timing: id 0 | task 15367 | eval time = 5425.38 ms / 752 tokens ( 7.22 ms per token, 138.42 tokens per second) 2.30.149.726 I slot print_timing: id 0 | task 15367 | total time = 5540.24 ms / 1103 tokens 2.30.149.727 I slot print_timing: id 0 | task 15367 | graphs reused = 15537 2.30.149.728 I slot print_timing: id 0 | task 15367 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.149.756 I slot release: id 0 | task 15367 | stop processing: n_tokens = 1127, truncated = 0 2.30.177.347 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1127, t_last = 150058687 2.30.177.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.258 MiB) 2.30.183.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.480 MiB) 2.30.227.800 I slot launch_slot_: id 0 | task 16120 | processing task, is_child = 0 2.31.114.951 I slot print_timing: id 0 | task 16120 | prompt eval time = 102.98 ms / 325 tokens ( 0.32 ms per token, 3156.04 tokens per second) 2.31.114.957 I slot print_timing: id 0 | task 16120 | eval time = 784.16 ms / 111 tokens ( 7.13 ms per token, 140.28 tokens per second) 2.31.114.958 I slot print_timing: id 0 | task 16120 | total time = 887.14 ms / 436 tokens 2.31.114.959 I slot print_timing: id 0 | task 16120 | graphs reused = 15646 2.31.114.960 I slot print_timing: id 0 | task 16120 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.114.985 I slot release: id 0 | task 16120 | stop processing: n_tokens = 460, truncated = 0 2.31.142.179 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 151023916 2.31.158.760 I slot launch_slot_: id 0 | task 16232 | processing task, is_child = 0 2.31.682.247 I slot print_timing: id 0 | task 16232 | prompt eval time = 102.41 ms / 308 tokens ( 0.33 ms per token, 3007.64 tokens per second) 2.31.682.252 I slot print_timing: id 0 | task 16232 | eval time = 421.06 ms / 56 tokens ( 7.66 ms per token, 130.62 tokens per second) 2.31.682.253 I slot print_timing: id 0 | task 16232 | total time = 523.47 ms / 364 tokens 2.31.682.254 I slot print_timing: id 0 | task 16232 | graphs reused = 15700 2.31.682.255 I slot print_timing: id 0 | task 16232 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.682.282 I slot release: id 0 | task 16232 | stop processing: n_tokens = 388, truncated = 0 2.31.702.797 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 151591213 2.31.702.846 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.227 MiB) 2.31.724.103 I slot launch_slot_: id 0 | task 16289 | processing task, is_child = 0 2.33.485.393 I slot print_timing: id 0 | task 16289 | prompt eval time = 115.63 ms / 349 tokens ( 0.33 ms per token, 3018.14 tokens per second) 2.33.485.399 I slot print_timing: id 0 | task 16289 | eval time = 1645.64 ms / 229 tokens ( 7.22 ms per token, 138.55 tokens per second) 2.33.485.400 I slot print_timing: id 0 | task 16289 | total time = 1761.27 ms / 578 tokens 2.33.485.402 I slot print_timing: id 0 | task 16289 | graphs reused = 15926 2.33.485.403 I slot print_timing: id 0 | task 16289 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.485.433 I slot release: id 0 | task 16289 | stop processing: n_tokens = 602, truncated = 0 2.33.513.201 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 153394365 2.33.513.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.259 MiB) 2.33.539.909 I slot launch_slot_: id 0 | task 16519 | processing task, is_child = 0 2.34.176.609 I slot print_timing: id 0 | task 16519 | prompt eval time = 115.34 ms / 371 tokens ( 0.31 ms per token, 3216.66 tokens per second) 2.34.176.614 I slot print_timing: id 0 | task 16519 | eval time = 521.35 ms / 74 tokens ( 7.14 ms per token, 140.02 tokens per second) 2.34.176.615 I slot print_timing: id 0 | task 16519 | total time = 636.68 ms / 445 tokens 2.34.176.616 I slot print_timing: id 0 | task 16519 | graphs reused = 15998 2.34.176.617 I slot print_timing: id 0 | task 16519 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.176.649 I slot release: id 0 | task 16519 | stop processing: n_tokens = 474, truncated = 0 2.34.199.027 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 154085580 2.34.199.083 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.602 MiB) 2.34.221.882 I slot launch_slot_: id 0 | task 16594 | processing task, is_child = 0 2.36.511.812 I slot print_timing: id 0 | task 16594 | prompt eval time = 102.07 ms / 303 tokens ( 0.34 ms per token, 2968.64 tokens per second) 2.36.511.818 I slot print_timing: id 0 | task 16594 | eval time = 2187.85 ms / 307 tokens ( 7.15 ms per token, 139.86 tokens per second) 2.36.511.819 I slot print_timing: id 0 | task 16594 | total time = 2289.91 ms / 610 tokens 2.36.511.820 I slot print_timing: id 0 | task 16594 | graphs reused = 16302 2.36.511.821 I slot print_timing: id 0 | task 16594 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.511.846 I slot release: id 0 | task 16594 | stop processing: n_tokens = 634, truncated = 0 2.36.539.720 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 634, t_last = 156420777 2.36.539.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 123.447 MiB) 2.36.567.959 I slot launch_slot_: id 0 | task 16902 | processing task, is_child = 0 2.37.419.504 I slot print_timing: id 0 | task 16902 | prompt eval time = 102.30 ms / 312 tokens ( 0.33 ms per token, 3049.88 tokens per second) 2.37.419.510 I slot print_timing: id 0 | task 16902 | eval time = 749.23 ms / 106 tokens ( 7.14 ms per token, 140.14 tokens per second) 2.37.419.511 I slot print_timing: id 0 | task 16902 | total time = 851.53 ms / 418 tokens 2.37.419.512 I slot print_timing: id 0 | task 16902 | graphs reused = 16406 2.37.419.513 I slot print_timing: id 0 | task 16902 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.419.538 I slot release: id 0 | task 16902 | stop processing: n_tokens = 442, truncated = 0 2.37.423.495 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 157328469 2.37.438.714 I slot launch_slot_: id 0 | task 17009 | processing task, is_child = 0 2.39.464.858 I slot print_timing: id 0 | task 17009 | prompt eval time = 102.42 ms / 311 tokens ( 0.33 ms per token, 3036.40 tokens per second) 2.39.464.864 I slot print_timing: id 0 | task 17009 | eval time = 1923.71 ms / 270 tokens ( 7.15 ms per token, 139.83 tokens per second) 2.39.464.865 I slot print_timing: id 0 | task 17009 | total time = 2026.13 ms / 581 tokens 2.39.464.866 I slot print_timing: id 0 | task 17009 | graphs reused = 16673 2.39.464.866 I slot print_timing: id 0 | task 17009 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.464.892 I slot release: id 0 | task 17009 | stop processing: n_tokens = 605, truncated = 0 2.39.489.888 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 605, t_last = 159373823 2.39.489.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 143.918 MiB) 2.39.518.526 I slot launch_slot_: id 0 | task 17280 | processing task, is_child = 0 2.40.376.811 I slot print_timing: id 0 | task 17280 | prompt eval time = 103.46 ms / 331 tokens ( 0.31 ms per token, 3199.43 tokens per second) 2.40.376.816 I slot print_timing: id 0 | task 17280 | eval time = 754.81 ms / 107 tokens ( 7.12 ms per token, 140.43 tokens per second) 2.40.376.817 I slot print_timing: id 0 | task 17280 | total time = 858.27 ms / 438 tokens 2.40.376.818 I slot print_timing: id 0 | task 17280 | graphs reused = 16778 2.40.376.819 I slot print_timing: id 0 | task 17280 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.376.846 I slot release: id 0 | task 17280 | stop processing: n_tokens = 462, truncated = 0 2.40.380.879 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 462, t_last = 160285777 2.40.396.928 I slot launch_slot_: id 0 | task 17388 | processing task, is_child = 0 2.43.501.660 I slot print_timing: id 0 | task 17388 | n_gen = 419, tg = 139.29 t/s, tg_3s = 139.63 t/s 2.46.501.798 I slot print_timing: id 0 | task 17388 | n_gen = 831, tg = 138.31 t/s, tg_3s = 137.33 t/s 2.47.932.632 I slot print_timing: id 0 | task 17388 | prompt eval time = 103.85 ms / 335 tokens ( 0.31 ms per token, 3225.93 tokens per second) 2.47.932.637 I slot print_timing: id 0 | task 17388 | eval time = 7431.84 ms / 1024 tokens ( 7.26 ms per token, 137.65 tokens per second) 2.47.932.638 I slot print_timing: id 0 | task 17388 | total time = 7535.69 ms / 1359 tokens 2.47.932.639 I slot print_timing: id 0 | task 17388 | graphs reused = 17796 2.47.932.640 I slot print_timing: id 0 | task 17388 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.932.668 I slot release: id 0 | task 17388 | stop processing: n_tokens = 1383, truncated = 0 2.47.936.788 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1383, t_last = 167841599 2.47.936.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.423 MiB) 2.47.991.806 I slot launch_slot_: id 0 | task 18413 | processing task, is_child = 0 2.51.095.846 I slot print_timing: id 0 | task 18413 | n_gen = 419, tg = 139.29 t/s, tg_3s = 139.62 t/s 2.51.751.813 I slot print_timing: id 0 | task 18413 | prompt eval time = 103.12 ms / 331 tokens ( 0.31 ms per token, 3209.73 tokens per second) 2.51.751.819 I slot print_timing: id 0 | task 18413 | eval time = 3656.87 ms / 510 tokens ( 7.18 ms per token, 139.19 tokens per second) 2.51.751.820 I slot print_timing: id 0 | task 18413 | total time = 3759.99 ms / 841 tokens 2.51.751.820 I slot print_timing: id 0 | task 18413 | graphs reused = 18302 2.51.751.821 I slot print_timing: id 0 | task 18413 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.751.850 I slot release: id 0 | task 18413 | stop processing: n_tokens = 865, truncated = 0 2.51.773.988 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 865, t_last = 171660781 2.51.774.059 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.069 MiB) 2.51.777.643 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 2.51.808.436 I slot launch_slot_: id 0 | task 18924 | processing task, is_child = 0 2.52.616.524 I slot print_timing: id 0 | task 18924 | prompt eval time = 102.73 ms / 328 tokens ( 0.31 ms per token, 3192.77 tokens per second) 2.52.616.530 I slot print_timing: id 0 | task 18924 | eval time = 705.34 ms / 100 tokens ( 7.12 ms per token, 140.36 tokens per second) 2.52.616.531 I slot print_timing: id 0 | task 18924 | total time = 808.07 ms / 428 tokens 2.52.616.532 I slot print_timing: id 0 | task 18924 | graphs reused = 18400 2.52.616.533 I slot print_timing: id 0 | task 18924 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.616.559 I slot release: id 0 | task 18924 | stop processing: n_tokens = 452, truncated = 0 2.52.645.759 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 172525490 2.52.645.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.256 MiB) 2.52.663.655 I slot launch_slot_: id 0 | task 19025 | processing task, is_child = 0 2.54.857.119 I slot print_timing: id 0 | task 19025 | prompt eval time = 103.33 ms / 331 tokens ( 0.31 ms per token, 3203.17 tokens per second) 2.54.857.124 I slot print_timing: id 0 | task 19025 | eval time = 2090.11 ms / 293 tokens ( 7.16 ms per token, 139.71 tokens per second) 2.54.857.125 I slot print_timing: id 0 | task 19025 | total time = 2193.45 ms / 624 tokens 2.54.857.126 I slot print_timing: id 0 | task 19025 | graphs reused = 18690 2.54.857.127 I slot print_timing: id 0 | task 19025 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.857.155 I slot release: id 0 | task 19025 | stop processing: n_tokens = 648, truncated = 0 2.54.872.761 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 174766086 2.54.872.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.851 MiB) 2.54.896.803 I slot launch_slot_: id 0 | task 19319 | processing task, is_child = 0 2.55.391.412 I slot print_timing: id 0 | task 19319 | prompt eval time = 114.72 ms / 348 tokens ( 0.33 ms per token, 3033.58 tokens per second) 2.55.391.418 I slot print_timing: id 0 | task 19319 | eval time = 379.88 ms / 54 tokens ( 7.17 ms per token, 139.52 tokens per second) 2.55.391.419 I slot print_timing: id 0 | task 19319 | total time = 494.59 ms / 402 tokens 2.55.391.420 I slot print_timing: id 0 | task 19319 | graphs reused = 18742 2.55.391.421 I slot print_timing: id 0 | task 19319 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.391.451 I slot release: id 0 | task 19319 | stop processing: n_tokens = 426, truncated = 0 2.55.406.910 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 175300382 2.55.406.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.382 MiB) 2.55.426.551 I slot launch_slot_: id 0 | task 19374 | processing task, is_child = 0 2.55.903.683 I slot print_timing: id 0 | task 19374 | prompt eval time = 103.23 ms / 332 tokens ( 0.31 ms per token, 3216.03 tokens per second) 2.55.903.689 I slot print_timing: id 0 | task 19374 | eval time = 373.87 ms / 53 tokens ( 7.19 ms per token, 139.09 tokens per second) 2.55.903.690 I slot print_timing: id 0 | task 19374 | total time = 477.10 ms / 385 tokens 2.55.903.691 I slot print_timing: id 0 | task 19374 | graphs reused = 18793 2.55.903.692 I slot print_timing: id 0 | task 19374 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.903.719 I slot release: id 0 | task 19374 | stop processing: n_tokens = 411, truncated = 0 2.55.908.158 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 175812650 2.55.908.208 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.852 MiB) 2.55.926.135 I slot launch_slot_: id 0 | task 19428 | processing task, is_child = 0 2.57.119.240 I slot print_timing: id 0 | task 19428 | prompt eval time = 114.72 ms / 339 tokens ( 0.34 ms per token, 2955.10 tokens per second) 2.57.119.246 I slot print_timing: id 0 | task 19428 | eval time = 1078.37 ms / 152 tokens ( 7.14 ms per token, 140.03 tokens per second) 2.57.119.247 I slot print_timing: id 0 | task 19428 | total time = 1193.09 ms / 491 tokens 2.57.119.248 I slot print_timing: id 0 | task 19428 | graphs reused = 18942 2.57.119.249 I slot print_timing: id 0 | task 19428 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.119.275 I slot release: id 0 | task 19428 | stop processing: n_tokens = 515, truncated = 0 2.57.146.939 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 177028206 2.57.146.995 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.537 MiB) 2.57.166.902 I slot launch_slot_: id 0 | task 19581 | processing task, is_child = 0 2.57.980.807 I slot print_timing: id 0 | task 19581 | prompt eval time = 114.64 ms / 343 tokens ( 0.33 ms per token, 2991.97 tokens per second) 2.57.980.812 I slot print_timing: id 0 | task 19581 | eval time = 699.25 ms / 99 tokens ( 7.14 ms per token, 140.15 tokens per second) 2.57.980.814 I slot print_timing: id 0 | task 19581 | total time = 813.88 ms / 442 tokens 2.57.980.815 I slot print_timing: id 0 | task 19581 | graphs reused = 19039 2.57.980.816 I slot print_timing: id 0 | task 19581 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.980.844 I slot release: id 0 | task 19581 | stop processing: n_tokens = 466, truncated = 0 2.58.010.019 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 177889775 2.58.010.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 2.58.028.137 I slot launch_slot_: id 0 | task 19681 | processing task, is_child = 0 2.59.403.739 I slot print_timing: id 0 | task 19681 | prompt eval time = 114.92 ms / 360 tokens ( 0.32 ms per token, 3132.53 tokens per second) 2.59.403.745 I slot print_timing: id 0 | task 19681 | eval time = 1260.66 ms / 177 tokens ( 7.16 ms per token, 139.61 tokens per second) 2.59.403.746 I slot print_timing: id 0 | task 19681 | total time = 1375.59 ms / 537 tokens 2.59.403.747 I slot print_timing: id 0 | task 19681 | graphs reused = 19213 2.59.403.748 I slot print_timing: id 0 | task 19681 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.403.777 I slot release: id 0 | task 19681 | stop processing: n_tokens = 561, truncated = 0 2.59.421.174 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 561, t_last = 179312708 2.59.421.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 2.59.442.512 I slot launch_slot_: id 0 | task 19859 | processing task, is_child = 0 3.00.157.594 I slot print_timing: id 0 | task 19859 | prompt eval time = 114.99 ms / 341 tokens ( 0.34 ms per token, 2965.55 tokens per second) 3.00.157.599 I slot print_timing: id 0 | task 19859 | eval time = 600.08 ms / 85 tokens ( 7.14 ms per token, 139.98 tokens per second) 3.00.157.600 I slot print_timing: id 0 | task 19859 | total time = 715.07 ms / 426 tokens 3.00.157.601 I slot print_timing: id 0 | task 19859 | graphs reused = 19296 3.00.157.602 I slot print_timing: id 0 | task 19859 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.157.630 I slot release: id 0 | task 19859 | stop processing: n_tokens = 450, truncated = 0 3.00.162.006 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 180066561 3.00.162.060 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.945 MiB) 3.00.180.498 I slot launch_slot_: id 0 | task 19945 | processing task, is_child = 0 3.00.576.241 I slot print_timing: id 0 | task 19945 | prompt eval time = 115.12 ms / 358 tokens ( 0.32 ms per token, 3109.66 tokens per second) 3.00.576.246 I slot print_timing: id 0 | task 19945 | eval time = 280.60 ms / 40 tokens ( 7.19 ms per token, 138.99 tokens per second) 3.00.576.247 I slot print_timing: id 0 | task 19945 | total time = 395.73 ms / 398 tokens 3.00.576.248 I slot print_timing: id 0 | task 19945 | graphs reused = 19334 3.00.576.249 I slot print_timing: id 0 | task 19945 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.576.280 I slot release: id 0 | task 19945 | stop processing: n_tokens = 422, truncated = 0 3.00.596.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 180485211 3.00.596.141 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 3.00.614.539 I slot launch_slot_: id 0 | task 19986 | processing task, is_child = 0 3.01.217.886 I slot print_timing: id 0 | task 19986 | prompt eval time = 115.07 ms / 358 tokens ( 0.32 ms per token, 3111.18 tokens per second) 3.01.217.892 I slot print_timing: id 0 | task 19986 | eval time = 488.26 ms / 68 tokens ( 7.29 ms per token, 137.22 tokens per second) 3.01.217.893 I slot print_timing: id 0 | task 19986 | total time = 603.33 ms / 426 tokens 3.01.217.894 I slot print_timing: id 0 | task 19986 | graphs reused = 19400 3.01.217.894 I slot print_timing: id 0 | task 19986 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.217.924 I slot release: id 0 | task 19986 | stop processing: n_tokens = 453, truncated = 0 3.01.233.790 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 181126855 3.01.233.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.476 MiB) 3.01.252.936 I slot launch_slot_: id 0 | task 20055 | processing task, is_child = 0 3.01.649.470 I slot print_timing: id 0 | task 20055 | prompt eval time = 137.20 ms / 387 tokens ( 0.35 ms per token, 2820.78 tokens per second) 3.01.649.476 I slot print_timing: id 0 | task 20055 | eval time = 259.32 ms / 37 tokens ( 7.20 ms per token, 138.82 tokens per second) 3.01.649.477 I slot print_timing: id 0 | task 20055 | total time = 396.52 ms / 424 tokens 3.01.649.478 I slot print_timing: id 0 | task 20055 | graphs reused = 19435 3.01.649.478 I slot print_timing: id 0 | task 20055 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.649.509 I slot release: id 0 | task 20055 | stop processing: n_tokens = 448, truncated = 0 3.01.674.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 181558440 3.01.689.608 I slot launch_slot_: id 0 | task 20093 | processing task, is_child = 0 3.02.222.738 I slot print_timing: id 0 | task 20093 | prompt eval time = 103.43 ms / 333 tokens ( 0.31 ms per token, 3219.63 tokens per second) 3.02.222.744 I slot print_timing: id 0 | task 20093 | eval time = 429.69 ms / 61 tokens ( 7.16 ms per token, 139.64 tokens per second) 3.02.222.745 I slot print_timing: id 0 | task 20093 | total time = 533.12 ms / 394 tokens 3.02.222.746 I slot print_timing: id 0 | task 20093 | graphs reused = 19494 3.02.222.746 I slot print_timing: id 0 | task 20093 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.222.773 I slot release: id 0 | task 20093 | stop processing: n_tokens = 418, truncated = 0