$ 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-IQ3_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.092.574 I srv llama_server: initializing ... 0.00.092.579 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.092.688 I srv init_listene: The UI is disabled 0.00.092.691 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.092.765 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) 0.00.104.527 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--bartowski--granite-4.2-8b-GGUF\snapshots\a592100df8fe4931c7cffbac7b28e8176a1d52da\granite-4.2-8b-IQ3_M.gguf' 0.01.792.247 I cmn init: llama threadpool init, n_threads = 8 0.01.857.006 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.861.897 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.861.916 I srv llama_server: model loaded 0.01.861.919 I srv llama_server: listening on http://127.0.0.1:8089 0.02.505.286 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.505.501 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.131.483 I slot print_timing: id 0 | task 0 | prompt eval time = 107.54 ms / 368 tokens ( 0.29 ms per token, 3421.92 tokens per second) 0.03.131.489 I slot print_timing: id 0 | task 0 | eval time = 518.42 ms / 61 tokens ( 8.64 ms per token, 115.74 tokens per second) 0.03.131.490 I slot print_timing: id 0 | task 0 | total time = 625.96 ms / 429 tokens 0.03.131.496 I slot print_timing: id 0 | task 0 | graphs reused = 60 0.03.131.497 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.131.528 I slot release: id 0 | task 0 | stop processing: n_tokens = 428, truncated = 0 0.03.135.451 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 3040927 0.03.149.947 I slot launch_slot_: id 0 | task 62 | processing task, is_child = 0 0.03.597.679 I slot print_timing: id 0 | task 62 | prompt eval time = 77.84 ms / 292 tokens ( 0.27 ms per token, 3751.19 tokens per second) 0.03.597.685 I slot print_timing: id 0 | task 62 | eval time = 369.87 ms / 44 tokens ( 8.60 ms per token, 116.26 tokens per second) 0.03.597.686 I slot print_timing: id 0 | task 62 | total time = 447.72 ms / 336 tokens 0.03.597.687 I slot print_timing: id 0 | task 62 | graphs reused = 102 0.03.597.688 I slot print_timing: id 0 | task 62 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.597.714 I slot release: id 0 | task 62 | stop processing: n_tokens = 360, truncated = 0 0.03.601.853 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 360, t_last = 3507114 0.03.614.501 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.04.077.215 I slot print_timing: id 0 | task 107 | prompt eval time = 84.83 ms / 338 tokens ( 0.25 ms per token, 3984.67 tokens per second) 0.04.077.221 I slot print_timing: id 0 | task 107 | eval time = 377.88 ms / 45 tokens ( 8.59 ms per token, 116.44 tokens per second) 0.04.077.223 I slot print_timing: id 0 | task 107 | total time = 462.70 ms / 383 tokens 0.04.077.223 I slot print_timing: id 0 | task 107 | graphs reused = 145 0.04.077.224 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.077.250 I slot release: id 0 | task 107 | stop processing: n_tokens = 407, truncated = 0 0.04.091.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 3986650 0.04.105.441 I slot launch_slot_: id 0 | task 153 | processing task, is_child = 0 0.04.578.062 I slot print_timing: id 0 | task 153 | prompt eval time = 85.06 ms / 371 tokens ( 0.23 ms per token, 4361.47 tokens per second) 0.04.578.067 I slot print_timing: id 0 | task 153 | eval time = 387.54 ms / 46 tokens ( 8.61 ms per token, 116.12 tokens per second) 0.04.578.068 I slot print_timing: id 0 | task 153 | total time = 472.61 ms / 417 tokens 0.04.578.069 I slot print_timing: id 0 | task 153 | graphs reused = 189 0.04.578.070 I slot print_timing: id 0 | task 153 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.578.099 I slot release: id 0 | task 153 | stop processing: n_tokens = 441, truncated = 0 0.04.606.505 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 0.04.621.353 I slot launch_slot_: id 0 | task 200 | processing task, is_child = 0 0.05.220.662 I slot print_timing: id 0 | task 200 | prompt eval time = 85.24 ms / 345 tokens ( 0.25 ms per token, 4047.49 tokens per second) 0.05.220.668 I slot print_timing: id 0 | task 200 | eval time = 514.06 ms / 61 tokens ( 8.57 ms per token, 116.72 tokens per second) 0.05.220.669 I slot print_timing: id 0 | task 200 | total time = 599.29 ms / 406 tokens 0.05.220.670 I slot print_timing: id 0 | task 200 | graphs reused = 248 0.05.220.671 I slot print_timing: id 0 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.220.699 I slot release: id 0 | task 200 | stop processing: n_tokens = 445, truncated = 0 0.05.244.758 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 445, t_last = 5130098 0.05.259.752 I slot launch_slot_: id 0 | task 262 | processing task, is_child = 0 0.05.884.267 I slot print_timing: id 0 | task 262 | prompt eval time = 85.15 ms / 351 tokens ( 0.24 ms per token, 4122.09 tokens per second) 0.05.884.273 I slot print_timing: id 0 | task 262 | eval time = 539.35 ms / 64 tokens ( 8.56 ms per token, 116.81 tokens per second) 0.05.884.274 I slot print_timing: id 0 | task 262 | total time = 624.50 ms / 415 tokens 0.05.884.275 I slot print_timing: id 0 | task 262 | graphs reused = 310 0.05.884.277 I slot print_timing: id 0 | task 262 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.884.303 I slot release: id 0 | task 262 | stop processing: n_tokens = 439, truncated = 0 0.05.902.180 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 5793702 0.05.916.966 I slot launch_slot_: id 0 | task 327 | processing task, is_child = 0 0.06.518.903 I slot print_timing: id 0 | task 327 | prompt eval time = 104.46 ms / 395 tokens ( 0.26 ms per token, 3781.21 tokens per second) 0.06.518.909 I slot print_timing: id 0 | task 327 | eval time = 497.46 ms / 58 tokens ( 8.73 ms per token, 114.58 tokens per second) 0.06.518.911 I slot print_timing: id 0 | task 327 | total time = 601.92 ms / 453 tokens 0.06.518.911 I slot print_timing: id 0 | task 327 | graphs reused = 366 0.06.518.912 I slot print_timing: id 0 | task 327 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.518.942 I slot release: id 0 | task 327 | stop processing: n_tokens = 477, truncated = 0 0.06.541.462 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 477, t_last = 6428341 0.06.557.735 I slot launch_slot_: id 0 | task 386 | processing task, is_child = 0 0.07.279.639 I slot print_timing: id 0 | task 386 | prompt eval time = 106.80 ms / 446 tokens ( 0.24 ms per token, 4176.11 tokens per second) 0.07.279.645 I slot print_timing: id 0 | task 386 | eval time = 615.09 ms / 72 tokens ( 8.66 ms per token, 115.43 tokens per second) 0.07.279.646 I slot print_timing: id 0 | task 386 | total time = 721.89 ms / 518 tokens 0.07.279.646 I slot print_timing: id 0 | task 386 | graphs reused = 435 0.07.279.647 I slot print_timing: id 0 | task 386 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.279.678 I slot release: id 0 | task 386 | stop processing: n_tokens = 542, truncated = 0 0.07.305.171 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 7189078 0.07.323.335 I slot launch_slot_: id 0 | task 459 | processing task, is_child = 0 0.07.839.220 I slot print_timing: id 0 | task 459 | prompt eval time = 78.32 ms / 319 tokens ( 0.25 ms per token, 4072.98 tokens per second) 0.07.839.226 I slot print_timing: id 0 | task 459 | eval time = 437.55 ms / 52 tokens ( 8.58 ms per token, 116.56 tokens per second) 0.07.839.227 I slot print_timing: id 0 | task 459 | total time = 515.87 ms / 371 tokens 0.07.839.228 I slot print_timing: id 0 | task 459 | graphs reused = 485 0.07.839.228 I slot print_timing: id 0 | task 459 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.839.255 I slot release: id 0 | task 459 | stop processing: n_tokens = 395, truncated = 0 0.07.867.613 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 7748654 0.07.881.210 I slot launch_slot_: id 0 | task 512 | processing task, is_child = 0 0.08.312.601 I slot print_timing: id 0 | task 512 | prompt eval time = 78.99 ms / 336 tokens ( 0.24 ms per token, 4253.76 tokens per second) 0.08.312.607 I slot print_timing: id 0 | task 512 | eval time = 352.39 ms / 42 tokens ( 8.59 ms per token, 116.35 tokens per second) 0.08.312.609 I slot print_timing: id 0 | task 512 | total time = 431.38 ms / 378 tokens 0.08.312.609 I slot print_timing: id 0 | task 512 | graphs reused = 525 0.08.312.610 I slot print_timing: id 0 | task 512 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.312.638 I slot release: id 0 | task 512 | stop processing: n_tokens = 402, truncated = 0 0.08.334.855 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 8222037 0.08.348.625 I slot launch_slot_: id 0 | task 555 | processing task, is_child = 0 0.09.034.889 I slot print_timing: id 0 | task 555 | prompt eval time = 86.67 ms / 352 tokens ( 0.25 ms per token, 4061.48 tokens per second) 0.09.034.895 I slot print_timing: id 0 | task 555 | eval time = 599.58 ms / 68 tokens ( 8.95 ms per token, 111.74 tokens per second) 0.09.034.896 I slot print_timing: id 0 | task 555 | total time = 686.25 ms / 420 tokens 0.09.034.897 I slot print_timing: id 0 | task 555 | graphs reused = 591 0.09.034.898 I slot print_timing: id 0 | task 555 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.034.927 I slot release: id 0 | task 555 | stop processing: n_tokens = 444, truncated = 0 0.09.040.067 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 8944326 0.09.057.900 I slot launch_slot_: id 0 | task 624 | processing task, is_child = 0 0.09.602.051 I slot print_timing: id 0 | task 624 | prompt eval time = 104.84 ms / 387 tokens ( 0.27 ms per token, 3691.30 tokens per second) 0.09.602.057 I slot print_timing: id 0 | task 624 | eval time = 439.29 ms / 52 tokens ( 8.61 ms per token, 116.10 tokens per second) 0.09.602.058 I slot print_timing: id 0 | task 624 | total time = 544.13 ms / 439 tokens 0.09.602.059 I slot print_timing: id 0 | task 624 | graphs reused = 641 0.09.602.059 I slot print_timing: id 0 | task 624 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.602.090 I slot release: id 0 | task 624 | stop processing: n_tokens = 463, truncated = 0 0.09.627.383 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 463, t_last = 9511489 0.09.643.028 I slot launch_slot_: id 0 | task 677 | processing task, is_child = 0 0.10.269.029 I slot print_timing: id 0 | task 677 | prompt eval time = 85.10 ms / 349 tokens ( 0.24 ms per token, 4100.86 tokens per second) 0.10.269.035 I slot print_timing: id 0 | task 677 | eval time = 540.88 ms / 64 tokens ( 8.59 ms per token, 116.48 tokens per second) 0.10.269.036 I slot print_timing: id 0 | task 677 | total time = 625.99 ms / 413 tokens 0.10.269.037 I slot print_timing: id 0 | task 677 | graphs reused = 703 0.10.269.038 I slot print_timing: id 0 | task 677 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.269.065 I slot release: id 0 | task 677 | stop processing: n_tokens = 437, truncated = 0 0.10.273.439 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 10178464 0.10.288.224 I slot launch_slot_: id 0 | task 742 | processing task, is_child = 0 0.10.854.889 I slot print_timing: id 0 | task 742 | prompt eval time = 85.03 ms / 352 tokens ( 0.24 ms per token, 4139.67 tokens per second) 0.10.854.895 I slot print_timing: id 0 | task 742 | eval time = 481.62 ms / 57 tokens ( 8.60 ms per token, 116.27 tokens per second) 0.10.854.896 I slot print_timing: id 0 | task 742 | total time = 566.65 ms / 409 tokens 0.10.854.897 I slot print_timing: id 0 | task 742 | graphs reused = 758 0.10.854.898 I slot print_timing: id 0 | task 742 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.854.925 I slot release: id 0 | task 742 | stop processing: n_tokens = 433, truncated = 0 0.10.878.747 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 10764324 0.10.893.550 I slot launch_slot_: id 0 | task 800 | processing task, is_child = 0 0.11.562.133 I slot print_timing: id 0 | task 800 | prompt eval time = 85.45 ms / 347 tokens ( 0.25 ms per token, 4060.85 tokens per second) 0.11.562.138 I slot print_timing: id 0 | task 800 | eval time = 583.12 ms / 68 tokens ( 8.70 ms per token, 114.90 tokens per second) 0.11.562.139 I slot print_timing: id 0 | task 800 | total time = 668.57 ms / 415 tokens 0.11.562.140 I slot print_timing: id 0 | task 800 | graphs reused = 824 0.11.562.141 I slot print_timing: id 0 | task 800 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.562.168 I slot release: id 0 | task 800 | stop processing: n_tokens = 439, truncated = 0 0.11.579.616 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 11471567 0.11.594.546 I slot launch_slot_: id 0 | task 869 | processing task, is_child = 0 0.12.145.185 I slot print_timing: id 0 | task 869 | prompt eval time = 78.55 ms / 320 tokens ( 0.25 ms per token, 4073.68 tokens per second) 0.12.145.191 I slot print_timing: id 0 | task 869 | eval time = 472.07 ms / 56 tokens ( 8.58 ms per token, 116.51 tokens per second) 0.12.145.192 I slot print_timing: id 0 | task 869 | total time = 550.62 ms / 376 tokens 0.12.145.193 I slot print_timing: id 0 | task 869 | graphs reused = 878 0.12.145.194 I slot print_timing: id 0 | task 869 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.145.225 I slot release: id 0 | task 869 | stop processing: n_tokens = 400, truncated = 0 0.12.171.243 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 12054624 0.12.185.097 I slot launch_slot_: id 0 | task 926 | processing task, is_child = 0 0.12.640.101 I slot print_timing: id 0 | task 926 | prompt eval time = 84.72 ms / 343 tokens ( 0.25 ms per token, 4048.87 tokens per second) 0.12.640.108 I slot print_timing: id 0 | task 926 | eval time = 370.27 ms / 44 tokens ( 8.61 ms per token, 116.13 tokens per second) 0.12.640.110 I slot print_timing: id 0 | task 926 | total time = 454.99 ms / 387 tokens 0.12.640.110 I slot print_timing: id 0 | task 926 | graphs reused = 920 0.12.640.111 I slot print_timing: id 0 | task 926 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.640.147 I slot release: id 0 | task 926 | stop processing: n_tokens = 411, truncated = 0 0.12.656.998 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 12549546 0.12.670.938 I slot launch_slot_: id 0 | task 971 | processing task, is_child = 0 0.13.120.812 I slot print_timing: id 0 | task 971 | prompt eval time = 79.20 ms / 325 tokens ( 0.24 ms per token, 4103.54 tokens per second) 0.13.120.818 I slot print_timing: id 0 | task 971 | eval time = 370.66 ms / 44 tokens ( 8.62 ms per token, 116.01 tokens per second) 0.13.120.819 I slot print_timing: id 0 | task 971 | total time = 449.86 ms / 369 tokens 0.13.120.820 I slot print_timing: id 0 | task 971 | graphs reused = 962 0.13.120.820 I slot print_timing: id 0 | task 971 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.120.849 I slot release: id 0 | task 971 | stop processing: n_tokens = 393, truncated = 0 0.13.125.083 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 13030248 0.13.138.611 I slot launch_slot_: id 0 | task 1016 | processing task, is_child = 0 0.13.579.244 I slot print_timing: id 0 | task 1016 | prompt eval time = 78.89 ms / 323 tokens ( 0.24 ms per token, 4094.15 tokens per second) 0.13.579.250 I slot print_timing: id 0 | task 1016 | eval time = 361.72 ms / 43 tokens ( 8.61 ms per token, 116.11 tokens per second) 0.13.579.251 I slot print_timing: id 0 | task 1016 | total time = 440.62 ms / 366 tokens 0.13.579.252 I slot print_timing: id 0 | task 1016 | graphs reused = 1003 0.13.579.252 I slot print_timing: id 0 | task 1016 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.579.281 I slot release: id 0 | task 1016 | stop processing: n_tokens = 390, truncated = 0 0.13.604.972 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 390, t_last = 13488680 0.13.618.350 I slot launch_slot_: id 0 | task 1060 | processing task, is_child = 0 0.14.306.881 I slot print_timing: id 0 | task 1060 | prompt eval time = 85.62 ms / 359 tokens ( 0.24 ms per token, 4193.14 tokens per second) 0.14.306.888 I slot print_timing: id 0 | task 1060 | eval time = 602.90 ms / 69 tokens ( 8.87 ms per token, 112.79 tokens per second) 0.14.306.889 I slot print_timing: id 0 | task 1060 | total time = 688.52 ms / 428 tokens 0.14.306.890 I slot print_timing: id 0 | task 1060 | graphs reused = 1070 0.14.306.890 I slot print_timing: id 0 | task 1060 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.306.923 I slot release: id 0 | task 1060 | stop processing: n_tokens = 452, truncated = 0 0.14.322.602 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 14216322 0.14.337.742 I slot launch_slot_: id 0 | task 1130 | processing task, is_child = 0 0.14.948.318 I slot print_timing: id 0 | task 1130 | prompt eval time = 79.06 ms / 334 tokens ( 0.24 ms per token, 4224.85 tokens per second) 0.14.948.324 I slot print_timing: id 0 | task 1130 | eval time = 531.51 ms / 63 tokens ( 8.57 ms per token, 116.65 tokens per second) 0.14.948.325 I slot print_timing: id 0 | task 1130 | total time = 610.56 ms / 397 tokens 0.14.948.326 I slot print_timing: id 0 | task 1130 | graphs reused = 1131 0.14.948.327 I slot print_timing: id 0 | task 1130 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.948.355 I slot release: id 0 | task 1130 | stop processing: n_tokens = 421, truncated = 0 0.14.965.728 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 14857754 0.14.980.530 I slot launch_slot_: id 0 | task 1194 | processing task, is_child = 0 0.15.683.396 I slot print_timing: id 0 | task 1194 | prompt eval time = 85.18 ms / 382 tokens ( 0.22 ms per token, 4484.57 tokens per second) 0.15.683.402 I slot print_timing: id 0 | task 1194 | eval time = 617.67 ms / 73 tokens ( 8.58 ms per token, 116.57 tokens per second) 0.15.683.403 I slot print_timing: id 0 | task 1194 | total time = 702.85 ms / 455 tokens 0.15.683.404 I slot print_timing: id 0 | task 1194 | graphs reused = 1202 0.15.683.405 I slot print_timing: id 0 | task 1194 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.683.433 I slot release: id 0 | task 1194 | stop processing: n_tokens = 479, truncated = 0 0.15.706.132 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 15592833 0.15.721.926 I slot launch_slot_: id 0 | task 1268 | processing task, is_child = 0 0.16.355.878 I slot print_timing: id 0 | task 1268 | prompt eval time = 85.55 ms / 368 tokens ( 0.23 ms per token, 4301.68 tokens per second) 0.16.355.883 I slot print_timing: id 0 | task 1268 | eval time = 548.39 ms / 65 tokens ( 8.57 ms per token, 116.71 tokens per second) 0.16.355.884 I slot print_timing: id 0 | task 1268 | total time = 633.93 ms / 433 tokens 0.16.355.885 I slot print_timing: id 0 | task 1268 | graphs reused = 1265 0.16.355.886 I slot print_timing: id 0 | task 1268 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.355.915 I slot release: id 0 | task 1268 | stop processing: n_tokens = 457, truncated = 0 0.16.360.311 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 16265314 0.16.375.574 I slot launch_slot_: id 0 | task 1334 | processing task, is_child = 0 0.17.195.739 I slot print_timing: id 0 | task 1334 | prompt eval time = 85.22 ms / 382 tokens ( 0.22 ms per token, 4482.67 tokens per second) 0.17.195.746 I slot print_timing: id 0 | task 1334 | eval time = 734.93 ms / 87 tokens ( 8.55 ms per token, 117.02 tokens per second) 0.17.195.747 I slot print_timing: id 0 | task 1334 | total time = 820.15 ms / 469 tokens 0.17.195.748 I slot print_timing: id 0 | task 1334 | graphs reused = 1350 0.17.195.749 I slot print_timing: id 0 | task 1334 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.195.778 I slot release: id 0 | task 1334 | stop processing: n_tokens = 493, truncated = 0 0.17.211.154 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 17105177 0.17.227.807 I slot launch_slot_: id 0 | task 1422 | processing task, is_child = 0 0.17.898.864 I slot print_timing: id 0 | task 1422 | prompt eval time = 105.69 ms / 410 tokens ( 0.26 ms per token, 3879.38 tokens per second) 0.17.898.869 I slot print_timing: id 0 | task 1422 | eval time = 565.36 ms / 67 tokens ( 8.57 ms per token, 116.74 tokens per second) 0.17.898.871 I slot print_timing: id 0 | task 1422 | total time = 671.04 ms / 477 tokens 0.17.898.871 I slot print_timing: id 0 | task 1422 | graphs reused = 1415 0.17.898.872 I slot print_timing: id 0 | task 1422 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.898.903 I slot release: id 0 | task 1422 | stop processing: n_tokens = 501, truncated = 0 0.17.903.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 17808302 0.17.919.618 I slot launch_slot_: id 0 | task 1490 | processing task, is_child = 0 0.18.553.719 I slot print_timing: id 0 | task 1490 | prompt eval time = 85.83 ms / 367 tokens ( 0.23 ms per token, 4275.84 tokens per second) 0.18.553.725 I slot print_timing: id 0 | task 1490 | eval time = 548.26 ms / 65 tokens ( 8.57 ms per token, 116.73 tokens per second) 0.18.553.726 I slot print_timing: id 0 | task 1490 | total time = 634.09 ms / 432 tokens 0.18.553.727 I slot print_timing: id 0 | task 1490 | graphs reused = 1478 0.18.553.728 I slot print_timing: id 0 | task 1490 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.553.755 I slot release: id 0 | task 1490 | stop processing: n_tokens = 458, truncated = 0 0.18.557.715 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 18463154 0.18.573.341 I slot launch_slot_: id 0 | task 1556 | processing task, is_child = 0 0.19.108.446 I slot print_timing: id 0 | task 1556 | prompt eval time = 78.81 ms / 326 tokens ( 0.24 ms per token, 4136.79 tokens per second) 0.19.108.453 I slot print_timing: id 0 | task 1556 | eval time = 456.29 ms / 54 tokens ( 8.61 ms per token, 116.16 tokens per second) 0.19.108.454 I slot print_timing: id 0 | task 1556 | total time = 535.09 ms / 380 tokens 0.19.108.455 I slot print_timing: id 0 | task 1556 | graphs reused = 1530 0.19.108.456 I slot print_timing: id 0 | task 1556 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.108.488 I slot release: id 0 | task 1556 | stop processing: n_tokens = 404, truncated = 0 0.19.131.087 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 19017888 0.19.144.843 I slot launch_slot_: id 0 | task 1611 | processing task, is_child = 0 0.19.770.987 I slot print_timing: id 0 | task 1611 | prompt eval time = 85.26 ms / 351 tokens ( 0.24 ms per token, 4116.72 tokens per second) 0.19.770.993 I slot print_timing: id 0 | task 1611 | eval time = 540.87 ms / 64 tokens ( 8.59 ms per token, 116.48 tokens per second) 0.19.770.995 I slot print_timing: id 0 | task 1611 | total time = 626.13 ms / 415 tokens 0.19.770.995 I slot print_timing: id 0 | task 1611 | graphs reused = 1592 0.19.770.996 I slot print_timing: id 0 | task 1611 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.771.024 I slot release: id 0 | task 1611 | stop processing: n_tokens = 441, truncated = 0 0.19.800.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 441, t_last = 19680423 0.19.815.122 I slot launch_slot_: id 0 | task 1676 | processing task, is_child = 0 0.20.568.963 I slot print_timing: id 0 | task 1676 | prompt eval time = 85.19 ms / 379 tokens ( 0.22 ms per token, 4448.72 tokens per second) 0.20.568.969 I slot print_timing: id 0 | task 1676 | eval time = 668.63 ms / 78 tokens ( 8.68 ms per token, 115.16 tokens per second) 0.20.568.970 I slot print_timing: id 0 | task 1676 | total time = 753.82 ms / 457 tokens 0.20.568.971 I slot print_timing: id 0 | task 1676 | graphs reused = 1668 0.20.568.972 I slot print_timing: id 0 | task 1676 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.568.999 I slot release: id 0 | task 1676 | stop processing: n_tokens = 481, truncated = 0 0.20.592.385 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 20478398 0.20.608.548 I slot launch_slot_: id 0 | task 1755 | processing task, is_child = 0 0.21.285.113 I slot print_timing: id 0 | task 1755 | prompt eval time = 85.43 ms / 356 tokens ( 0.24 ms per token, 4167.25 tokens per second) 0.21.285.119 I slot print_timing: id 0 | task 1755 | eval time = 591.12 ms / 70 tokens ( 8.57 ms per token, 116.73 tokens per second) 0.21.285.120 I slot print_timing: id 0 | task 1755 | total time = 676.55 ms / 426 tokens 0.21.285.121 I slot print_timing: id 0 | task 1755 | graphs reused = 1736 0.21.285.121 I slot print_timing: id 0 | task 1755 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.285.148 I slot release: id 0 | task 1755 | stop processing: n_tokens = 450, truncated = 0 0.21.311.049 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 21194547 0.21.326.749 I slot launch_slot_: id 0 | task 1826 | processing task, is_child = 0 0.21.939.062 I slot print_timing: id 0 | task 1826 | prompt eval time = 78.98 ms / 331 tokens ( 0.24 ms per token, 4190.78 tokens per second) 0.21.939.068 I slot print_timing: id 0 | task 1826 | eval time = 533.31 ms / 63 tokens ( 8.60 ms per token, 116.26 tokens per second) 0.21.939.069 I slot print_timing: id 0 | task 1826 | total time = 612.29 ms / 394 tokens 0.21.939.070 I slot print_timing: id 0 | task 1826 | graphs reused = 1797 0.21.939.071 I slot print_timing: id 0 | task 1826 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.939.106 I slot release: id 0 | task 1826 | stop processing: n_tokens = 418, truncated = 0 0.21.967.919 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 21848505 0.21.982.619 I slot launch_slot_: id 0 | task 1890 | processing task, is_child = 0 0.22.355.621 I slot print_timing: id 0 | task 1890 | prompt eval time = 79.60 ms / 334 tokens ( 0.24 ms per token, 4195.93 tokens per second) 0.22.355.627 I slot print_timing: id 0 | task 1890 | eval time = 293.38 ms / 34 tokens ( 8.89 ms per token, 112.48 tokens per second) 0.22.355.628 I slot print_timing: id 0 | task 1890 | total time = 372.98 ms / 368 tokens 0.22.355.629 I slot print_timing: id 0 | task 1890 | graphs reused = 1829 0.22.355.630 I slot print_timing: id 0 | task 1890 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.355.659 I slot release: id 0 | task 1890 | stop processing: n_tokens = 392, truncated = 0 0.22.373.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 22265058 0.22.386.707 I slot launch_slot_: id 0 | task 1925 | processing task, is_child = 0 0.23.048.192 I slot print_timing: id 0 | task 1925 | prompt eval time = 85.63 ms / 362 tokens ( 0.24 ms per token, 4227.69 tokens per second) 0.23.048.198 I slot print_timing: id 0 | task 1925 | eval time = 575.84 ms / 68 tokens ( 8.59 ms per token, 116.35 tokens per second) 0.23.048.199 I slot print_timing: id 0 | task 1925 | total time = 661.47 ms / 430 tokens 0.23.048.200 I slot print_timing: id 0 | task 1925 | graphs reused = 1895 0.23.048.201 I slot print_timing: id 0 | task 1925 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.048.229 I slot release: id 0 | task 1925 | stop processing: n_tokens = 454, truncated = 0 0.23.076.324 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 22957628 0.23.092.047 I slot launch_slot_: id 0 | task 1994 | processing task, is_child = 0 0.23.607.763 I slot print_timing: id 0 | task 1994 | prompt eval time = 85.57 ms / 384 tokens ( 0.22 ms per token, 4487.34 tokens per second) 0.23.607.769 I slot print_timing: id 0 | task 1994 | eval time = 430.12 ms / 51 tokens ( 8.60 ms per token, 116.25 tokens per second) 0.23.607.771 I slot print_timing: id 0 | task 1994 | total time = 515.70 ms / 435 tokens 0.23.607.772 I slot print_timing: id 0 | task 1994 | graphs reused = 1944 0.23.607.774 I slot print_timing: id 0 | task 1994 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.607.804 I slot release: id 0 | task 1994 | stop processing: n_tokens = 459, truncated = 0 0.23.622.050 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 459, t_last = 23517203 0.23.637.876 I slot launch_slot_: id 0 | task 2046 | processing task, is_child = 0 0.24.181.547 I slot print_timing: id 0 | task 2046 | prompt eval time = 79.07 ms / 325 tokens ( 0.24 ms per token, 4110.28 tokens per second) 0.24.181.553 I slot print_timing: id 0 | task 2046 | eval time = 464.58 ms / 55 tokens ( 8.60 ms per token, 116.23 tokens per second) 0.24.181.554 I slot print_timing: id 0 | task 2046 | total time = 543.65 ms / 380 tokens 0.24.181.555 I slot print_timing: id 0 | task 2046 | graphs reused = 1997 0.24.181.556 I slot print_timing: id 0 | task 2046 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.181.585 I slot release: id 0 | task 2046 | stop processing: n_tokens = 404, truncated = 0 0.24.197.882 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 24090984 0.24.213.753 I slot launch_slot_: id 0 | task 2102 | processing task, is_child = 0 0.24.803.523 I slot print_timing: id 0 | task 2102 | prompt eval time = 88.78 ms / 366 tokens ( 0.24 ms per token, 4122.69 tokens per second) 0.24.803.529 I slot print_timing: id 0 | task 2102 | eval time = 500.97 ms / 59 tokens ( 8.64 ms per token, 115.77 tokens per second) 0.24.803.530 I slot print_timing: id 0 | task 2102 | total time = 589.75 ms / 425 tokens 0.24.803.531 I slot print_timing: id 0 | task 2102 | graphs reused = 2054 0.24.803.532 I slot print_timing: id 0 | task 2102 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.803.563 I slot release: id 0 | task 2102 | stop processing: n_tokens = 449, truncated = 0 0.24.807.492 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 24712962 0.24.822.824 I slot launch_slot_: id 0 | task 2162 | processing task, is_child = 0 0.25.211.735 I slot print_timing: id 0 | task 2162 | prompt eval time = 78.20 ms / 295 tokens ( 0.27 ms per token, 3772.33 tokens per second) 0.25.211.741 I slot print_timing: id 0 | task 2162 | eval time = 310.70 ms / 36 tokens ( 8.88 ms per token, 112.65 tokens per second) 0.25.211.742 I slot print_timing: id 0 | task 2162 | total time = 388.90 ms / 331 tokens 0.25.211.743 I slot print_timing: id 0 | task 2162 | graphs reused = 2088 0.25.211.744 I slot print_timing: id 0 | task 2162 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.211.773 I slot release: id 0 | task 2162 | stop processing: n_tokens = 355, truncated = 0 0.25.239.328 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 25121172 0.25.252.165 I slot launch_slot_: id 0 | task 2199 | processing task, is_child = 0 0.26.318.290 I slot print_timing: id 0 | task 2199 | prompt eval time = 78.43 ms / 307 tokens ( 0.26 ms per token, 3914.22 tokens per second) 0.26.318.296 I slot print_timing: id 0 | task 2199 | eval time = 987.67 ms / 116 tokens ( 8.59 ms per token, 116.44 tokens per second) 0.26.318.297 I slot print_timing: id 0 | task 2199 | total time = 1066.11 ms / 423 tokens 0.26.318.298 I slot print_timing: id 0 | task 2199 | graphs reused = 2202 0.26.318.299 I slot print_timing: id 0 | task 2199 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.318.331 I slot release: id 0 | task 2199 | stop processing: n_tokens = 447, truncated = 0 0.26.344.116 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 26227730 0.26.359.840 I slot launch_slot_: id 0 | task 2316 | processing task, is_child = 0 0.26.758.274 I slot print_timing: id 0 | task 2316 | prompt eval time = 78.60 ms / 319 tokens ( 0.25 ms per token, 4058.73 tokens per second) 0.26.758.280 I slot print_timing: id 0 | task 2316 | eval time = 319.82 ms / 38 tokens ( 8.64 ms per token, 115.69 tokens per second) 0.26.758.281 I slot print_timing: id 0 | task 2316 | total time = 398.41 ms / 357 tokens 0.26.758.281 I slot print_timing: id 0 | task 2316 | graphs reused = 2238 0.26.758.283 I slot print_timing: id 0 | task 2316 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.758.312 I slot release: id 0 | task 2316 | stop processing: n_tokens = 381, truncated = 0 0.26.762.433 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 26667712 0.26.775.649 I slot launch_slot_: id 0 | task 2355 | processing task, is_child = 0 0.27.301.295 I slot print_timing: id 0 | task 2355 | prompt eval time = 78.58 ms / 315 tokens ( 0.25 ms per token, 4008.76 tokens per second) 0.27.301.302 I slot print_timing: id 0 | task 2355 | eval time = 447.05 ms / 53 tokens ( 8.60 ms per token, 116.32 tokens per second) 0.27.301.303 I slot print_timing: id 0 | task 2355 | total time = 525.63 ms / 368 tokens 0.27.301.304 I slot print_timing: id 0 | task 2355 | graphs reused = 2289 0.27.301.304 I slot print_timing: id 0 | task 2355 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.301.332 I slot release: id 0 | task 2355 | stop processing: n_tokens = 392, truncated = 0 0.27.328.325 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 27210731 0.27.341.837 I slot launch_slot_: id 0 | task 2409 | processing task, is_child = 0 0.27.918.682 I slot print_timing: id 0 | task 2409 | prompt eval time = 85.75 ms / 367 tokens ( 0.23 ms per token, 4279.98 tokens per second) 0.27.918.687 I slot print_timing: id 0 | task 2409 | eval time = 491.08 ms / 58 tokens ( 8.62 ms per token, 116.07 tokens per second) 0.27.918.688 I slot print_timing: id 0 | task 2409 | total time = 576.83 ms / 425 tokens 0.27.918.690 I slot print_timing: id 0 | task 2409 | graphs reused = 2345 0.27.918.691 I slot print_timing: id 0 | task 2409 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.918.720 I slot release: id 0 | task 2409 | stop processing: n_tokens = 449, truncated = 0 0.27.923.098 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 27828119 0.27.938.697 I slot launch_slot_: id 0 | task 2468 | processing task, is_child = 0 0.28.680.255 I slot print_timing: id 0 | task 2468 | prompt eval time = 118.50 ms / 499 tokens ( 0.24 ms per token, 4210.83 tokens per second) 0.28.680.261 I slot print_timing: id 0 | task 2468 | eval time = 623.04 ms / 70 tokens ( 9.03 ms per token, 110.75 tokens per second) 0.28.680.263 I slot print_timing: id 0 | task 2468 | total time = 741.54 ms / 569 tokens 0.28.680.264 I slot print_timing: id 0 | task 2468 | graphs reused = 2413 0.28.680.264 I slot print_timing: id 0 | task 2468 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.680.297 I slot release: id 0 | task 2468 | stop processing: n_tokens = 593, truncated = 0 0.28.702.757 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 593, t_last = 28589697 0.28.722.131 I slot launch_slot_: id 0 | task 2539 | processing task, is_child = 0 0.29.224.129 I slot print_timing: id 0 | task 2539 | prompt eval time = 78.73 ms / 319 tokens ( 0.25 ms per token, 4051.93 tokens per second) 0.29.224.135 I slot print_timing: id 0 | task 2539 | eval time = 423.25 ms / 50 tokens ( 8.64 ms per token, 115.77 tokens per second) 0.29.224.137 I slot print_timing: id 0 | task 2539 | total time = 501.98 ms / 369 tokens 0.29.224.137 I slot print_timing: id 0 | task 2539 | graphs reused = 2461 0.29.224.138 I slot print_timing: id 0 | task 2539 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.224.167 I slot release: id 0 | task 2539 | stop processing: n_tokens = 393, truncated = 0 0.29.238.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 29133566 0.29.252.153 I slot launch_slot_: id 0 | task 2590 | processing task, is_child = 0 0.29.827.474 I slot print_timing: id 0 | task 2590 | prompt eval time = 85.22 ms / 348 tokens ( 0.24 ms per token, 4083.69 tokens per second) 0.29.827.481 I slot print_timing: id 0 | task 2590 | eval time = 490.08 ms / 58 tokens ( 8.60 ms per token, 116.31 tokens per second) 0.29.827.482 I slot print_timing: id 0 | task 2590 | total time = 575.30 ms / 406 tokens 0.29.827.483 I slot print_timing: id 0 | task 2590 | graphs reused = 2517 0.29.827.484 I slot print_timing: id 0 | task 2590 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.827.528 I slot release: id 0 | task 2590 | stop processing: n_tokens = 430, truncated = 0 0.29.845.533 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 29736927 0.29.860.120 I slot launch_slot_: id 0 | task 2649 | processing task, is_child = 0 0.30.600.693 I slot print_timing: id 0 | task 2649 | prompt eval time = 105.80 ms / 404 tokens ( 0.26 ms per token, 3818.49 tokens per second) 0.30.600.699 I slot print_timing: id 0 | task 2649 | eval time = 634.76 ms / 75 tokens ( 8.58 ms per token, 116.58 tokens per second) 0.30.600.701 I slot print_timing: id 0 | task 2649 | total time = 740.56 ms / 479 tokens 0.30.600.705 I slot print_timing: id 0 | task 2649 | graphs reused = 2590 0.30.600.706 I slot print_timing: id 0 | task 2649 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.600.736 I slot release: id 0 | task 2649 | stop processing: n_tokens = 503, truncated = 0 0.30.625.568 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 30510136 0.30.642.618 I slot launch_slot_: id 0 | task 2725 | processing task, is_child = 0 0.31.265.012 I slot print_timing: id 0 | task 2725 | prompt eval time = 105.44 ms / 408 tokens ( 0.26 ms per token, 3869.68 tokens per second) 0.31.265.017 I slot print_timing: id 0 | task 2725 | eval time = 516.94 ms / 60 tokens ( 8.76 ms per token, 114.13 tokens per second) 0.31.265.018 I slot print_timing: id 0 | task 2725 | total time = 622.38 ms / 468 tokens 0.31.265.019 I slot print_timing: id 0 | task 2725 | graphs reused = 2648 0.31.265.020 I slot print_timing: id 0 | task 2725 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.265.053 I slot release: id 0 | task 2725 | stop processing: n_tokens = 494, truncated = 0 0.31.282.871 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 31174452 0.31.299.419 I slot launch_slot_: id 0 | task 2786 | processing task, is_child = 0 0.31.800.344 I slot print_timing: id 0 | task 2786 | prompt eval time = 79.03 ms / 325 tokens ( 0.24 ms per token, 4112.36 tokens per second) 0.31.800.349 I slot print_timing: id 0 | task 2786 | eval time = 421.88 ms / 49 tokens ( 8.79 ms per token, 113.78 tokens per second) 0.31.800.350 I slot print_timing: id 0 | task 2786 | total time = 500.91 ms / 374 tokens 0.31.800.351 I slot print_timing: id 0 | task 2786 | graphs reused = 2695 0.31.800.352 I slot print_timing: id 0 | task 2786 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.800.381 I slot release: id 0 | task 2786 | stop processing: n_tokens = 402, truncated = 0 0.31.829.075 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 31709780 0.31.842.920 I slot launch_slot_: id 0 | task 2836 | processing task, is_child = 0 0.32.376.371 I slot print_timing: id 0 | task 2836 | prompt eval time = 85.12 ms / 345 tokens ( 0.25 ms per token, 4053.10 tokens per second) 0.32.376.376 I slot print_timing: id 0 | task 2836 | eval time = 448.32 ms / 53 tokens ( 8.62 ms per token, 115.99 tokens per second) 0.32.376.378 I slot print_timing: id 0 | task 2836 | total time = 533.44 ms / 398 tokens 0.32.376.378 I slot print_timing: id 0 | task 2836 | graphs reused = 2746 0.32.376.379 I slot print_timing: id 0 | task 2836 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.376.407 I slot release: id 0 | task 2836 | stop processing: n_tokens = 422, truncated = 0 0.32.395.873 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 32285806 0.32.410.377 I slot launch_slot_: id 0 | task 2890 | processing task, is_child = 0 0.32.926.054 I slot print_timing: id 0 | task 2890 | prompt eval time = 85.16 ms / 344 tokens ( 0.25 ms per token, 4039.64 tokens per second) 0.32.926.060 I slot print_timing: id 0 | task 2890 | eval time = 430.51 ms / 50 tokens ( 8.79 ms per token, 113.82 tokens per second) 0.32.926.062 I slot print_timing: id 0 | task 2890 | total time = 515.66 ms / 394 tokens 0.32.926.062 I slot print_timing: id 0 | task 2890 | graphs reused = 2794 0.32.926.063 I slot print_timing: id 0 | task 2890 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.926.094 I slot release: id 0 | task 2890 | stop processing: n_tokens = 418, truncated = 0 0.32.941.185 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 32835493 0.32.955.628 I slot launch_slot_: id 0 | task 2941 | processing task, is_child = 0 0.33.669.164 I slot print_timing: id 0 | task 2941 | prompt eval time = 85.70 ms / 378 tokens ( 0.23 ms per token, 4410.79 tokens per second) 0.33.669.170 I slot print_timing: id 0 | task 2941 | eval time = 627.82 ms / 74 tokens ( 8.60 ms per token, 116.28 tokens per second) 0.33.669.171 I slot print_timing: id 0 | task 2941 | total time = 713.52 ms / 452 tokens 0.33.669.173 I slot print_timing: id 0 | task 2941 | graphs reused = 2866 0.33.669.173 I slot print_timing: id 0 | task 2941 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.669.205 I slot release: id 0 | task 2941 | stop processing: n_tokens = 476, truncated = 0 0.33.689.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 33578604 0.33.705.398 I slot launch_slot_: id 0 | task 3016 | processing task, is_child = 0 0.34.300.250 I slot print_timing: id 0 | task 3016 | prompt eval time = 79.44 ms / 331 tokens ( 0.24 ms per token, 4166.40 tokens per second) 0.34.300.256 I slot print_timing: id 0 | task 3016 | eval time = 515.39 ms / 61 tokens ( 8.59 ms per token, 116.42 tokens per second) 0.34.300.257 I slot print_timing: id 0 | task 3016 | total time = 594.84 ms / 392 tokens 0.34.300.258 I slot print_timing: id 0 | task 3016 | graphs reused = 2925 0.34.300.259 I slot print_timing: id 0 | task 3016 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.300.286 I slot release: id 0 | task 3016 | stop processing: n_tokens = 416, truncated = 0 0.34.304.487 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 34209685 0.34.319.061 I slot launch_slot_: id 0 | task 3078 | processing task, is_child = 0 0.34.837.558 I slot print_timing: id 0 | task 3078 | prompt eval time = 104.59 ms / 387 tokens ( 0.27 ms per token, 3700.27 tokens per second) 0.34.837.564 I slot print_timing: id 0 | task 3078 | eval time = 413.89 ms / 49 tokens ( 8.62 ms per token, 115.97 tokens per second) 0.34.837.565 I slot print_timing: id 0 | task 3078 | total time = 518.48 ms / 436 tokens 0.34.837.566 I slot print_timing: id 0 | task 3078 | graphs reused = 2972 0.34.837.567 I slot print_timing: id 0 | task 3078 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.837.598 I slot release: id 0 | task 3078 | stop processing: n_tokens = 460, truncated = 0 0.34.865.084 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 34746998 0.34.881.184 I slot launch_slot_: id 0 | task 3128 | processing task, is_child = 0 0.35.601.658 I slot print_timing: id 0 | task 3128 | prompt eval time = 85.09 ms / 345 tokens ( 0.25 ms per token, 4054.29 tokens per second) 0.35.601.664 I slot print_timing: id 0 | task 3128 | eval time = 635.36 ms / 75 tokens ( 8.59 ms per token, 116.47 tokens per second) 0.35.601.665 I slot print_timing: id 0 | task 3128 | total time = 720.46 ms / 420 tokens 0.35.601.666 I slot print_timing: id 0 | task 3128 | graphs reused = 3045 0.35.601.667 I slot print_timing: id 0 | task 3128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.601.695 I slot release: id 0 | task 3128 | stop processing: n_tokens = 444, truncated = 0 0.35.606.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 35511094 0.35.622.147 I slot launch_slot_: id 0 | task 3204 | processing task, is_child = 0 0.36.239.431 I slot print_timing: id 0 | task 3204 | prompt eval time = 85.04 ms / 337 tokens ( 0.25 ms per token, 3962.65 tokens per second) 0.36.239.436 I slot print_timing: id 0 | task 3204 | eval time = 532.22 ms / 61 tokens ( 8.87 ms per token, 112.74 tokens per second) 0.36.239.437 I slot print_timing: id 0 | task 3204 | total time = 617.26 ms / 398 tokens 0.36.239.438 I slot print_timing: id 0 | task 3204 | graphs reused = 3104 0.36.239.439 I slot print_timing: id 0 | task 3204 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.239.467 I slot release: id 0 | task 3204 | stop processing: n_tokens = 422, truncated = 0 0.36.267.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 36148866 0.36.281.741 I slot launch_slot_: id 0 | task 3266 | processing task, is_child = 0 0.37.214.261 I slot print_timing: id 0 | task 3266 | prompt eval time = 115.95 ms / 463 tokens ( 0.25 ms per token, 3993.03 tokens per second) 0.37.214.267 I slot print_timing: id 0 | task 3266 | eval time = 816.55 ms / 95 tokens ( 8.69 ms per token, 115.12 tokens per second) 0.37.214.268 I slot print_timing: id 0 | task 3266 | total time = 932.50 ms / 558 tokens 0.37.214.269 I slot print_timing: id 0 | task 3266 | graphs reused = 3196 0.37.214.271 I slot print_timing: id 0 | task 3266 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.214.305 I slot release: id 0 | task 3266 | stop processing: n_tokens = 582, truncated = 0 0.37.239.409 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 37123705 0.37.258.658 I slot launch_slot_: id 0 | task 3362 | processing task, is_child = 0 0.38.300.595 I slot print_timing: id 0 | task 3362 | prompt eval time = 107.12 ms / 440 tokens ( 0.24 ms per token, 4107.62 tokens per second) 0.38.300.600 I slot print_timing: id 0 | task 3362 | eval time = 934.80 ms / 109 tokens ( 8.66 ms per token, 115.53 tokens per second) 0.38.300.601 I slot print_timing: id 0 | task 3362 | total time = 1041.92 ms / 549 tokens 0.38.300.602 I slot print_timing: id 0 | task 3362 | graphs reused = 3302 0.38.300.603 I slot print_timing: id 0 | task 3362 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.300.634 I slot release: id 0 | task 3362 | stop processing: n_tokens = 573, truncated = 0 0.38.319.303 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 573, t_last = 38210033 0.38.338.646 I slot launch_slot_: id 0 | task 3472 | processing task, is_child = 0 0.38.959.873 I slot print_timing: id 0 | task 3472 | prompt eval time = 79.84 ms / 336 tokens ( 0.24 ms per token, 4208.31 tokens per second) 0.38.959.879 I slot print_timing: id 0 | task 3472 | eval time = 541.37 ms / 64 tokens ( 8.59 ms per token, 116.37 tokens per second) 0.38.959.880 I slot print_timing: id 0 | task 3472 | total time = 621.21 ms / 400 tokens 0.38.959.881 I slot print_timing: id 0 | task 3472 | graphs reused = 3364 0.38.959.882 I slot print_timing: id 0 | task 3472 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.959.911 I slot release: id 0 | task 3472 | stop processing: n_tokens = 424, truncated = 0 0.38.977.995 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 38869310 0.38.992.439 I slot launch_slot_: id 0 | task 3537 | processing task, is_child = 0 0.39.568.309 I slot print_timing: id 0 | task 3537 | prompt eval time = 85.85 ms / 367 tokens ( 0.23 ms per token, 4275.00 tokens per second) 0.39.568.314 I slot print_timing: id 0 | task 3537 | eval time = 490.01 ms / 57 tokens ( 8.75 ms per token, 114.28 tokens per second) 0.39.568.316 I slot print_timing: id 0 | task 3537 | total time = 575.85 ms / 424 tokens 0.39.568.316 I slot print_timing: id 0 | task 3537 | graphs reused = 3419 0.39.568.317 I slot print_timing: id 0 | task 3537 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.568.347 I slot release: id 0 | task 3537 | stop processing: n_tokens = 448, truncated = 0 0.39.590.337 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 39477746 0.39.605.719 I slot launch_slot_: id 0 | task 3595 | processing task, is_child = 0 0.40.124.085 I slot print_timing: id 0 | task 3595 | prompt eval time = 79.15 ms / 327 tokens ( 0.24 ms per token, 4131.29 tokens per second) 0.40.124.091 I slot print_timing: id 0 | task 3595 | eval time = 439.20 ms / 52 tokens ( 8.61 ms per token, 116.12 tokens per second) 0.40.124.093 I slot print_timing: id 0 | task 3595 | total time = 518.35 ms / 379 tokens 0.40.124.094 I slot print_timing: id 0 | task 3595 | graphs reused = 3469 0.40.124.095 I slot print_timing: id 0 | task 3595 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.124.123 I slot release: id 0 | task 3595 | stop processing: n_tokens = 403, truncated = 0 0.40.142.207 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 40033522 0.40.156.416 I slot launch_slot_: id 0 | task 3648 | processing task, is_child = 0 0.40.913.988 I slot print_timing: id 0 | task 3648 | prompt eval time = 104.79 ms / 393 tokens ( 0.27 ms per token, 3750.43 tokens per second) 0.40.913.993 I slot print_timing: id 0 | task 3648 | eval time = 652.77 ms / 76 tokens ( 8.70 ms per token, 114.89 tokens per second) 0.40.913.994 I slot print_timing: id 0 | task 3648 | total time = 757.56 ms / 469 tokens 0.40.913.995 I slot print_timing: id 0 | task 3648 | graphs reused = 3543 0.40.913.996 I slot print_timing: id 0 | task 3648 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.914.028 I slot release: id 0 | task 3648 | stop processing: n_tokens = 493, truncated = 0 0.40.944.214 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 40823428 0.40.961.206 I slot launch_slot_: id 0 | task 3725 | processing task, is_child = 0 0.41.629.747 I slot print_timing: id 0 | task 3725 | prompt eval time = 137.87 ms / 524 tokens ( 0.26 ms per token, 3800.60 tokens per second) 0.41.629.752 I slot print_timing: id 0 | task 3725 | eval time = 530.65 ms / 62 tokens ( 8.70 ms per token, 114.95 tokens per second) 0.41.629.753 I slot print_timing: id 0 | task 3725 | total time = 668.53 ms / 586 tokens 0.41.629.755 I slot print_timing: id 0 | task 3725 | graphs reused = 3603 0.41.629.755 I slot print_timing: id 0 | task 3725 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.629.788 I slot release: id 0 | task 3725 | stop processing: n_tokens = 610, truncated = 0 0.41.647.594 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 41539187 0.41.667.877 I slot launch_slot_: id 0 | task 3788 | processing task, is_child = 0 0.42.342.540 I slot print_timing: id 0 | task 3788 | prompt eval time = 152.29 ms / 602 tokens ( 0.25 ms per token, 3953.04 tokens per second) 0.42.342.546 I slot print_timing: id 0 | task 3788 | eval time = 522.36 ms / 61 tokens ( 8.71 ms per token, 114.86 tokens per second) 0.42.342.547 I slot print_timing: id 0 | task 3788 | total time = 674.65 ms / 663 tokens 0.42.342.548 I slot print_timing: id 0 | task 3788 | graphs reused = 3662 0.42.342.549 I slot print_timing: id 0 | task 3788 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.342.587 I slot release: id 0 | task 3788 | stop processing: n_tokens = 687, truncated = 0 0.42.368.314 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 42251986 0.42.391.833 I slot launch_slot_: id 0 | task 3850 | processing task, is_child = 0 0.43.085.453 I slot print_timing: id 0 | task 3850 | prompt eval time = 152.49 ms / 640 tokens ( 0.24 ms per token, 4196.89 tokens per second) 0.43.085.460 I slot print_timing: id 0 | task 3850 | eval time = 541.11 ms / 63 tokens ( 8.73 ms per token, 114.58 tokens per second) 0.43.085.461 I slot print_timing: id 0 | task 3850 | total time = 693.60 ms / 703 tokens 0.43.085.462 I slot print_timing: id 0 | task 3850 | graphs reused = 3723 0.43.085.463 I slot print_timing: id 0 | task 3850 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.085.509 I slot release: id 0 | task 3850 | stop processing: n_tokens = 727, truncated = 0 0.43.091.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 42994908 0.43.115.118 I slot launch_slot_: id 0 | task 3914 | processing task, is_child = 0 0.43.801.110 I slot print_timing: id 0 | task 3914 | prompt eval time = 152.94 ms / 629 tokens ( 0.24 ms per token, 4112.80 tokens per second) 0.43.801.116 I slot print_timing: id 0 | task 3914 | eval time = 533.04 ms / 62 tokens ( 8.74 ms per token, 114.44 tokens per second) 0.43.801.117 I slot print_timing: id 0 | task 3914 | total time = 685.97 ms / 691 tokens 0.43.801.118 I slot print_timing: id 0 | task 3914 | graphs reused = 3783 0.43.801.119 I slot print_timing: id 0 | task 3914 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.801.156 I slot release: id 0 | task 3914 | stop processing: n_tokens = 715, truncated = 0 0.43.821.942 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 43710555 0.43.845.567 I slot launch_slot_: id 0 | task 3977 | processing task, is_child = 0 0.44.450.529 I slot print_timing: id 0 | task 3977 | prompt eval time = 115.80 ms / 458 tokens ( 0.25 ms per token, 3954.96 tokens per second) 0.44.450.535 I slot print_timing: id 0 | task 3977 | eval time = 489.14 ms / 57 tokens ( 8.73 ms per token, 114.49 tokens per second) 0.44.450.536 I slot print_timing: id 0 | task 3977 | total time = 604.94 ms / 515 tokens 0.44.450.537 I slot print_timing: id 0 | task 3977 | graphs reused = 3837 0.44.450.538 I slot print_timing: id 0 | task 3977 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.450.568 I slot release: id 0 | task 3977 | stop processing: n_tokens = 539, truncated = 0 0.44.478.302 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 44359967 0.44.496.735 I slot launch_slot_: id 0 | task 4035 | processing task, is_child = 0 0.45.182.105 I slot print_timing: id 0 | task 4035 | prompt eval time = 146.27 ms / 594 tokens ( 0.25 ms per token, 4061.04 tokens per second) 0.45.182.111 I slot print_timing: id 0 | task 4035 | eval time = 539.08 ms / 63 tokens ( 8.69 ms per token, 115.01 tokens per second) 0.45.182.112 I slot print_timing: id 0 | task 4035 | total time = 685.35 ms / 657 tokens 0.45.182.114 I slot print_timing: id 0 | task 4035 | graphs reused = 3898 0.45.182.115 I slot print_timing: id 0 | task 4035 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.182.150 I slot release: id 0 | task 4035 | stop processing: n_tokens = 681, truncated = 0 0.45.209.536 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 681, t_last = 45091549 0.45.231.463 I slot launch_slot_: id 0 | task 4099 | processing task, is_child = 0 0.45.809.120 I slot print_timing: id 0 | task 4099 | prompt eval time = 142.33 ms / 572 tokens ( 0.25 ms per token, 4018.86 tokens per second) 0.45.809.126 I slot print_timing: id 0 | task 4099 | eval time = 435.31 ms / 51 tokens ( 8.71 ms per token, 114.86 tokens per second) 0.45.809.127 I slot print_timing: id 0 | task 4099 | total time = 577.64 ms / 623 tokens 0.45.809.128 I slot print_timing: id 0 | task 4099 | graphs reused = 3947 0.45.809.129 I slot print_timing: id 0 | task 4099 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.809.164 I slot release: id 0 | task 4099 | stop processing: n_tokens = 647, truncated = 0 0.45.832.807 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 647, t_last = 45718563 0.45.854.239 I slot launch_slot_: id 0 | task 4151 | processing task, is_child = 0 0.46.401.050 I slot print_timing: id 0 | task 4151 | prompt eval time = 118.25 ms / 502 tokens ( 0.24 ms per token, 4245.10 tokens per second) 0.46.401.055 I slot print_timing: id 0 | task 4151 | eval time = 428.54 ms / 50 tokens ( 8.75 ms per token, 114.34 tokens per second) 0.46.401.056 I slot print_timing: id 0 | task 4151 | total time = 546.79 ms / 552 tokens 0.46.401.057 I slot print_timing: id 0 | task 4151 | graphs reused = 3995 0.46.401.059 I slot print_timing: id 0 | task 4151 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.401.091 I slot release: id 0 | task 4151 | stop processing: n_tokens = 576, truncated = 0 0.46.406.190 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 46310490 0.46.425.288 I slot launch_slot_: id 0 | task 4202 | processing task, is_child = 0 0.47.032.872 I slot print_timing: id 0 | task 4202 | prompt eval time = 116.18 ms / 479 tokens ( 0.24 ms per token, 4122.91 tokens per second) 0.47.032.878 I slot print_timing: id 0 | task 4202 | eval time = 491.39 ms / 57 tokens ( 8.77 ms per token, 113.96 tokens per second) 0.47.032.879 I slot print_timing: id 0 | task 4202 | total time = 607.57 ms / 536 tokens 0.47.032.880 I slot print_timing: id 0 | task 4202 | graphs reused = 4049 0.47.032.880 I slot print_timing: id 0 | task 4202 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.032.912 I slot release: id 0 | task 4202 | stop processing: n_tokens = 560, truncated = 0 0.47.049.401 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 46942311 0.47.068.022 I slot launch_slot_: id 0 | task 4260 | processing task, is_child = 0 0.47.589.663 I slot print_timing: id 0 | task 4260 | prompt eval time = 137.84 ms / 552 tokens ( 0.25 ms per token, 4004.50 tokens per second) 0.47.589.669 I slot print_timing: id 0 | task 4260 | eval time = 383.78 ms / 45 tokens ( 8.72 ms per token, 114.65 tokens per second) 0.47.589.670 I slot print_timing: id 0 | task 4260 | total time = 521.62 ms / 597 tokens 0.47.589.671 I slot print_timing: id 0 | task 4260 | graphs reused = 4092 0.47.589.672 I slot print_timing: id 0 | task 4260 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.589.706 I slot release: id 0 | task 4260 | stop processing: n_tokens = 621, truncated = 0 0.47.594.864 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 47499106 0.47.615.588 I slot launch_slot_: id 0 | task 4306 | processing task, is_child = 0 0.50.743.723 I slot print_timing: id 0 | task 4306 | n_gen = 347, tg = 115.28 t/s, tg_3s = 115.61 t/s 0.53.748.722 I slot print_timing: id 0 | task 4306 | n_gen = 690, tg = 114.71 t/s, tg_3s = 114.14 t/s 0.56.718.342 I slot print_timing: id 0 | task 4306 | prompt eval time = 126.77 ms / 514 tokens ( 0.25 ms per token, 4054.68 tokens per second) 0.56.718.347 I slot print_timing: id 0 | task 4306 | eval time = 8975.97 ms / 1024 tokens ( 8.77 ms per token, 113.97 tokens per second) 0.56.718.348 I slot print_timing: id 0 | task 4306 | total time = 9102.74 ms / 1538 tokens 0.56.718.349 I slot print_timing: id 0 | task 4306 | graphs reused = 5110 0.56.718.350 I slot print_timing: id 0 | task 4306 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.718.383 I slot release: id 0 | task 4306 | stop processing: n_tokens = 1562, truncated = 0 0.56.745.313 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1562, t_last = 56627782 0.56.794.399 I slot launch_slot_: id 0 | task 5331 | processing task, is_child = 0 0.57.255.716 I slot print_timing: id 0 | task 5331 | prompt eval time = 106.02 ms / 428 tokens ( 0.25 ms per token, 4036.97 tokens per second) 0.57.255.722 I slot print_timing: id 0 | task 5331 | eval time = 355.28 ms / 42 tokens ( 8.67 ms per token, 115.40 tokens per second) 0.57.255.723 I slot print_timing: id 0 | task 5331 | total time = 461.30 ms / 470 tokens 0.57.255.724 I slot print_timing: id 0 | task 5331 | graphs reused = 5150 0.57.255.724 I slot print_timing: id 0 | task 5331 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.255.755 I slot release: id 0 | task 5331 | stop processing: n_tokens = 494, truncated = 0 0.57.276.743 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 57165154 0.57.293.488 I slot launch_slot_: id 0 | task 5374 | processing task, is_child = 0 0.57.994.776 I slot print_timing: id 0 | task 5374 | prompt eval time = 133.61 ms / 521 tokens ( 0.26 ms per token, 3899.32 tokens per second) 0.57.994.782 I slot print_timing: id 0 | task 5374 | eval time = 567.66 ms / 66 tokens ( 8.73 ms per token, 114.51 tokens per second) 0.57.994.783 I slot print_timing: id 0 | task 5374 | total time = 701.27 ms / 587 tokens 0.57.994.784 I slot print_timing: id 0 | task 5374 | graphs reused = 5214 0.57.994.785 I slot print_timing: id 0 | task 5374 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.994.820 I slot release: id 0 | task 5374 | stop processing: n_tokens = 611, truncated = 0 0.58.023.662 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 57904220 0.58.043.809 I slot launch_slot_: id 0 | task 5441 | processing task, is_child = 0 0.58.599.859 I slot print_timing: id 0 | task 5441 | prompt eval time = 115.61 ms / 472 tokens ( 0.24 ms per token, 4082.66 tokens per second) 0.58.599.865 I slot print_timing: id 0 | task 5441 | eval time = 440.42 ms / 51 tokens ( 8.81 ms per token, 113.53 tokens per second) 0.58.599.866 I slot print_timing: id 0 | task 5441 | total time = 556.03 ms / 523 tokens 0.58.599.867 I slot print_timing: id 0 | task 5441 | graphs reused = 5262 0.58.599.867 I slot print_timing: id 0 | task 5441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.599.899 I slot release: id 0 | task 5441 | stop processing: n_tokens = 547, truncated = 0 0.58.628.805 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 58509298 0.58.647.027 I slot launch_slot_: id 0 | task 5493 | processing task, is_child = 0 0.59.124.642 I slot print_timing: id 0 | task 5493 | prompt eval time = 105.97 ms / 428 tokens ( 0.25 ms per token, 4038.99 tokens per second) 0.59.124.648 I slot print_timing: id 0 | task 5493 | eval time = 371.63 ms / 44 tokens ( 8.64 ms per token, 115.71 tokens per second) 0.59.124.649 I slot print_timing: id 0 | task 5493 | total time = 477.60 ms / 472 tokens 0.59.124.650 I slot print_timing: id 0 | task 5493 | graphs reused = 5304 0.59.124.651 I slot print_timing: id 0 | task 5493 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.124.682 I slot release: id 0 | task 5493 | stop processing: n_tokens = 496, truncated = 0 0.59.145.651 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 496, t_last = 59034081 0.59.162.215 I slot launch_slot_: id 0 | task 5538 | processing task, is_child = 0 0.59.663.910 I slot print_timing: id 0 | task 5538 | prompt eval time = 115.42 ms / 456 tokens ( 0.25 ms per token, 3950.65 tokens per second) 0.59.663.916 I slot print_timing: id 0 | task 5538 | eval time = 386.26 ms / 45 tokens ( 8.78 ms per token, 113.91 tokens per second) 0.59.663.917 I slot print_timing: id 0 | task 5538 | total time = 501.68 ms / 501 tokens 0.59.663.918 I slot print_timing: id 0 | task 5538 | graphs reused = 5346 0.59.663.918 I slot print_timing: id 0 | task 5538 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.663.949 I slot release: id 0 | task 5538 | stop processing: n_tokens = 525, truncated = 0 0.59.693.216 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 525, t_last = 59573348 0.59.711.382 I slot launch_slot_: id 0 | task 5584 | processing task, is_child = 0 1.00.189.721 I slot print_timing: id 0 | task 5584 | prompt eval time = 106.54 ms / 439 tokens ( 0.24 ms per token, 4120.63 tokens per second) 1.00.189.728 I slot print_timing: id 0 | task 5584 | eval time = 371.79 ms / 44 tokens ( 8.65 ms per token, 115.66 tokens per second) 1.00.189.729 I slot print_timing: id 0 | task 5584 | total time = 478.32 ms / 483 tokens 1.00.189.730 I slot print_timing: id 0 | task 5584 | graphs reused = 5388 1.00.189.731 I slot print_timing: id 0 | task 5584 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.189.767 I slot release: id 0 | task 5584 | stop processing: n_tokens = 507, truncated = 0 1.00.195.656 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 507, t_last = 60099166 1.00.212.956 I slot launch_slot_: id 0 | task 5629 | processing task, is_child = 0 1.00.873.946 I slot print_timing: id 0 | task 5629 | prompt eval time = 146.72 ms / 600 tokens ( 0.24 ms per token, 4089.56 tokens per second) 1.00.873.952 I slot print_timing: id 0 | task 5629 | eval time = 514.26 ms / 60 tokens ( 8.72 ms per token, 114.73 tokens per second) 1.00.873.953 I slot print_timing: id 0 | task 5629 | total time = 660.97 ms / 660 tokens 1.00.873.954 I slot print_timing: id 0 | task 5629 | graphs reused = 5446 1.00.873.955 I slot print_timing: id 0 | task 5629 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.873.992 I slot release: id 0 | task 5629 | stop processing: n_tokens = 684, truncated = 0 1.00.878.956 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 60783391 1.00.901.755 I slot launch_slot_: id 0 | task 5690 | processing task, is_child = 0 1.01.379.784 I slot print_timing: id 0 | task 5690 | prompt eval time = 115.91 ms / 473 tokens ( 0.25 ms per token, 4080.86 tokens per second) 1.01.379.791 I slot print_timing: id 0 | task 5690 | eval time = 362.10 ms / 42 tokens ( 8.83 ms per token, 113.23 tokens per second) 1.01.379.792 I slot print_timing: id 0 | task 5690 | total time = 478.01 ms / 515 tokens 1.01.379.793 I slot print_timing: id 0 | task 5690 | graphs reused = 5485 1.01.379.794 I slot print_timing: id 0 | task 5690 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.379.827 I slot release: id 0 | task 5690 | stop processing: n_tokens = 539, truncated = 0 1.01.400.358 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 61289226 1.01.419.052 I slot launch_slot_: id 0 | task 5733 | processing task, is_child = 0 1.02.174.690 I slot print_timing: id 0 | task 5733 | prompt eval time = 195.67 ms / 835 tokens ( 0.23 ms per token, 4267.35 tokens per second) 1.02.174.695 I slot print_timing: id 0 | task 5733 | eval time = 559.95 ms / 65 tokens ( 8.75 ms per token, 114.30 tokens per second) 1.02.174.696 I slot print_timing: id 0 | task 5733 | total time = 755.62 ms / 900 tokens 1.02.174.697 I slot print_timing: id 0 | task 5733 | graphs reused = 5548 1.02.174.698 I slot print_timing: id 0 | task 5733 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.174.743 I slot release: id 0 | task 5733 | stop processing: n_tokens = 924, truncated = 0 1.02.193.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 62084142 1.02.222.094 I slot launch_slot_: id 0 | task 5799 | processing task, is_child = 0 1.02.706.620 I slot print_timing: id 0 | task 5799 | prompt eval time = 115.63 ms / 454 tokens ( 0.25 ms per token, 3926.45 tokens per second) 1.02.706.626 I slot print_timing: id 0 | task 5799 | eval time = 368.88 ms / 43 tokens ( 8.78 ms per token, 113.86 tokens per second) 1.02.706.627 I slot print_timing: id 0 | task 5799 | total time = 484.51 ms / 497 tokens 1.02.706.628 I slot print_timing: id 0 | task 5799 | graphs reused = 5588 1.02.706.629 I slot print_timing: id 0 | task 5799 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.706.660 I slot release: id 0 | task 5799 | stop processing: n_tokens = 521, truncated = 0 1.02.712.503 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 62616059 1.02.730.400 I slot launch_slot_: id 0 | task 5843 | processing task, is_child = 0 1.03.305.189 I slot print_timing: id 0 | task 5843 | prompt eval time = 163.51 ms / 667 tokens ( 0.25 ms per token, 4079.24 tokens per second) 1.03.305.195 I slot print_timing: id 0 | task 5843 | eval time = 411.26 ms / 48 tokens ( 8.75 ms per token, 114.28 tokens per second) 1.03.305.196 I slot print_timing: id 0 | task 5843 | total time = 574.77 ms / 715 tokens 1.03.305.197 I slot print_timing: id 0 | task 5843 | graphs reused = 5634 1.03.305.198 I slot print_timing: id 0 | task 5843 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.305.238 I slot release: id 0 | task 5843 | stop processing: n_tokens = 741, truncated = 0 1.03.312.235 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 63214637 1.03.348.934 I slot launch_slot_: id 0 | task 5892 | processing task, is_child = 0 1.04.114.420 I slot print_timing: id 0 | task 5892 | prompt eval time = 152.52 ms / 628 tokens ( 0.24 ms per token, 4117.49 tokens per second) 1.04.114.426 I slot print_timing: id 0 | task 5892 | eval time = 612.94 ms / 69 tokens ( 9.01 ms per token, 110.94 tokens per second) 1.04.114.427 I slot print_timing: id 0 | task 5892 | total time = 765.46 ms / 697 tokens 1.04.114.428 I slot print_timing: id 0 | task 5892 | graphs reused = 5701 1.04.114.429 I slot print_timing: id 0 | task 5892 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.114.472 I slot release: id 0 | task 5892 | stop processing: n_tokens = 858, truncated = 0 1.04.142.185 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 858, t_last = 64023871 1.04.169.066 I slot launch_slot_: id 0 | task 5962 | processing task, is_child = 0 1.04.965.134 I slot print_timing: id 0 | task 5962 | prompt eval time = 143.97 ms / 578 tokens ( 0.25 ms per token, 4014.81 tokens per second) 1.04.965.139 I slot print_timing: id 0 | task 5962 | eval time = 652.09 ms / 76 tokens ( 8.69 ms per token, 115.02 tokens per second) 1.04.965.140 I slot print_timing: id 0 | task 5962 | total time = 796.05 ms / 654 tokens 1.04.965.141 I slot print_timing: id 0 | task 5962 | graphs reused = 5775 1.04.965.142 I slot print_timing: id 0 | task 5962 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.965.178 I slot release: id 0 | task 5962 | stop processing: n_tokens = 678, truncated = 0 1.04.983.920 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 64874578 1.05.006.116 I slot launch_slot_: id 0 | task 6039 | processing task, is_child = 0 1.05.690.756 I slot print_timing: id 0 | task 6039 | prompt eval time = 115.89 ms / 461 tokens ( 0.25 ms per token, 3977.91 tokens per second) 1.05.690.761 I slot print_timing: id 0 | task 6039 | eval time = 568.73 ms / 66 tokens ( 8.75 ms per token, 114.29 tokens per second) 1.05.690.762 I slot print_timing: id 0 | task 6039 | total time = 684.62 ms / 527 tokens 1.05.690.763 I slot print_timing: id 0 | task 6039 | graphs reused = 5838 1.05.690.764 I slot print_timing: id 0 | task 6039 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.690.796 I slot release: id 0 | task 6039 | stop processing: n_tokens = 551, truncated = 0 1.05.719.279 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 551, t_last = 65600195 1.05.737.501 I slot launch_slot_: id 0 | task 6106 | processing task, is_child = 0 1.06.323.594 I slot print_timing: id 0 | task 6106 | prompt eval time = 149.84 ms / 613 tokens ( 0.24 ms per token, 4091.03 tokens per second) 1.06.323.599 I slot print_timing: id 0 | task 6106 | eval time = 436.24 ms / 51 tokens ( 8.72 ms per token, 114.62 tokens per second) 1.06.323.600 I slot print_timing: id 0 | task 6106 | total time = 586.08 ms / 664 tokens 1.06.323.601 I slot print_timing: id 0 | task 6106 | graphs reused = 5887 1.06.323.602 I slot print_timing: id 0 | task 6106 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.323.638 I slot release: id 0 | task 6106 | stop processing: n_tokens = 688, truncated = 0 1.06.340.882 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 688, t_last = 66233037 1.06.363.349 I slot launch_slot_: id 0 | task 6158 | processing task, is_child = 0 1.07.111.326 I slot print_timing: id 0 | task 6158 | prompt eval time = 188.46 ms / 794 tokens ( 0.24 ms per token, 4213.14 tokens per second) 1.07.111.332 I slot print_timing: id 0 | task 6158 | eval time = 559.50 ms / 65 tokens ( 8.74 ms per token, 114.39 tokens per second) 1.07.111.333 I slot print_timing: id 0 | task 6158 | total time = 747.96 ms / 859 tokens 1.07.111.334 I slot print_timing: id 0 | task 6158 | graphs reused = 5950 1.07.111.335 I slot print_timing: id 0 | task 6158 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.111.381 I slot release: id 0 | task 6158 | stop processing: n_tokens = 883, truncated = 0 1.07.136.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 67020780 1.07.182.058 I slot launch_slot_: id 0 | task 6224 | processing task, is_child = 0 1.07.786.610 I slot print_timing: id 0 | task 6224 | prompt eval time = 107.16 ms / 431 tokens ( 0.25 ms per token, 4022.17 tokens per second) 1.07.786.616 I slot print_timing: id 0 | task 6224 | eval time = 497.38 ms / 58 tokens ( 8.73 ms per token, 114.60 tokens per second) 1.07.786.617 I slot print_timing: id 0 | task 6224 | total time = 604.53 ms / 489 tokens 1.07.786.618 I slot print_timing: id 0 | task 6224 | graphs reused = 6006 1.07.786.619 I slot print_timing: id 0 | task 6224 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.786.655 I slot release: id 0 | task 6224 | stop processing: n_tokens = 687, truncated = 0 1.07.808.899 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 67696054 1.07.831.058 I slot launch_slot_: id 0 | task 6283 | processing task, is_child = 0 1.08.415.535 I slot print_timing: id 0 | task 6283 | prompt eval time = 139.96 ms / 563 tokens ( 0.25 ms per token, 4022.49 tokens per second) 1.08.415.542 I slot print_timing: id 0 | task 6283 | eval time = 444.50 ms / 50 tokens ( 9.07 ms per token, 110.24 tokens per second) 1.08.415.543 I slot print_timing: id 0 | task 6283 | total time = 584.46 ms / 613 tokens 1.08.415.543 I slot print_timing: id 0 | task 6283 | graphs reused = 6054 1.08.415.544 I slot print_timing: id 0 | task 6283 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.415.582 I slot release: id 0 | task 6283 | stop processing: n_tokens = 637, truncated = 0 1.08.443.425 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 68324981 1.08.476.330 I slot launch_slot_: id 0 | task 6334 | processing task, is_child = 0 1.08.963.862 I slot print_timing: id 0 | task 6334 | prompt eval time = 79.18 ms / 331 tokens ( 0.24 ms per token, 4180.14 tokens per second) 1.08.963.868 I slot print_timing: id 0 | task 6334 | eval time = 408.33 ms / 48 tokens ( 8.69 ms per token, 115.10 tokens per second) 1.08.963.869 I slot print_timing: id 0 | task 6334 | total time = 487.51 ms / 379 tokens 1.08.963.870 I slot print_timing: id 0 | task 6334 | graphs reused = 6099 1.08.963.871 I slot print_timing: id 0 | task 6334 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.963.902 I slot release: id 0 | task 6334 | stop processing: n_tokens = 513, truncated = 0 1.08.991.092 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 68873301 1.09.008.355 I slot launch_slot_: id 0 | task 6383 | processing task, is_child = 0 1.09.699.896 I slot print_timing: id 0 | task 6383 | prompt eval time = 117.88 ms / 489 tokens ( 0.24 ms per token, 4148.22 tokens per second) 1.09.699.902 I slot print_timing: id 0 | task 6383 | eval time = 573.64 ms / 67 tokens ( 8.69 ms per token, 115.05 tokens per second) 1.09.699.903 I slot print_timing: id 0 | task 6383 | total time = 691.53 ms / 556 tokens 1.09.699.904 I slot print_timing: id 0 | task 6383 | graphs reused = 6164 1.09.699.905 I slot print_timing: id 0 | task 6383 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.699.937 I slot release: id 0 | task 6383 | stop processing: n_tokens = 580, truncated = 0 1.09.717.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 69609336 1.09.736.305 I slot launch_slot_: id 0 | task 6451 | processing task, is_child = 0 1.10.318.587 I slot print_timing: id 0 | task 6451 | prompt eval time = 118.73 ms / 510 tokens ( 0.23 ms per token, 4295.35 tokens per second) 1.10.318.593 I slot print_timing: id 0 | task 6451 | eval time = 463.53 ms / 54 tokens ( 8.75 ms per token, 114.34 tokens per second) 1.10.318.594 I slot print_timing: id 0 | task 6451 | total time = 582.27 ms / 564 tokens 1.10.318.595 I slot print_timing: id 0 | task 6451 | graphs reused = 6216 1.10.318.596 I slot print_timing: id 0 | task 6451 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.318.630 I slot release: id 0 | task 6451 | stop processing: n_tokens = 588, truncated = 0 1.10.339.004 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 70228029 1.10.359.253 I slot launch_slot_: id 0 | task 6506 | processing task, is_child = 0 1.11.136.934 I slot print_timing: id 0 | task 6506 | prompt eval time = 154.07 ms / 631 tokens ( 0.24 ms per token, 4095.46 tokens per second) 1.11.136.940 I slot print_timing: id 0 | task 6506 | eval time = 623.59 ms / 71 tokens ( 8.91 ms per token, 112.25 tokens per second) 1.11.136.941 I slot print_timing: id 0 | task 6506 | total time = 777.66 ms / 702 tokens 1.11.136.942 I slot print_timing: id 0 | task 6506 | graphs reused = 6285 1.11.136.942 I slot print_timing: id 0 | task 6506 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.136.982 I slot release: id 0 | task 6506 | stop processing: n_tokens = 726, truncated = 0 1.11.154.821 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 71046381 1.11.178.094 I slot launch_slot_: id 0 | task 6578 | processing task, is_child = 0 1.11.780.941 I slot print_timing: id 0 | task 6578 | prompt eval time = 140.53 ms / 570 tokens ( 0.25 ms per token, 4056.22 tokens per second) 1.11.780.947 I slot print_timing: id 0 | task 6578 | eval time = 462.31 ms / 54 tokens ( 8.72 ms per token, 114.64 tokens per second) 1.11.780.948 I slot print_timing: id 0 | task 6578 | total time = 602.83 ms / 624 tokens 1.11.780.949 I slot print_timing: id 0 | task 6578 | graphs reused = 6337 1.11.780.950 I slot print_timing: id 0 | task 6578 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.780.986 I slot release: id 0 | task 6578 | stop processing: n_tokens = 648, truncated = 0 1.11.807.957 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 71690385 1.11.829.672 I slot launch_slot_: id 0 | task 6633 | processing task, is_child = 0 1.12.438.213 I slot print_timing: id 0 | task 6633 | prompt eval time = 187.69 ms / 792 tokens ( 0.24 ms per token, 4219.84 tokens per second) 1.12.438.219 I slot print_timing: id 0 | task 6633 | eval time = 420.84 ms / 49 tokens ( 8.77 ms per token, 114.06 tokens per second) 1.12.438.220 I slot print_timing: id 0 | task 6633 | total time = 608.52 ms / 841 tokens 1.12.438.221 I slot print_timing: id 0 | task 6633 | graphs reused = 6384 1.12.438.222 I slot print_timing: id 0 | task 6633 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.438.264 I slot release: id 0 | task 6633 | stop processing: n_tokens = 867, truncated = 0 1.12.444.110 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 867, t_last = 72347663 1.12.481.309 I slot launch_slot_: id 0 | task 6683 | processing task, is_child = 0 1.13.006.243 I slot print_timing: id 0 | task 6683 | prompt eval time = 140.35 ms / 564 tokens ( 0.25 ms per token, 4018.61 tokens per second) 1.13.006.249 I slot print_timing: id 0 | task 6683 | eval time = 384.57 ms / 45 tokens ( 8.74 ms per token, 114.41 tokens per second) 1.13.006.250 I slot print_timing: id 0 | task 6683 | total time = 524.92 ms / 609 tokens 1.13.006.251 I slot print_timing: id 0 | task 6683 | graphs reused = 6427 1.13.006.252 I slot print_timing: id 0 | task 6683 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.006.291 I slot release: id 0 | task 6683 | stop processing: n_tokens = 635, truncated = 0 1.13.035.770 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 72915690 1.13.056.574 I slot launch_slot_: id 0 | task 6729 | processing task, is_child = 0 1.13.816.584 I slot print_timing: id 0 | task 6729 | prompt eval time = 150.11 ms / 617 tokens ( 0.24 ms per token, 4110.37 tokens per second) 1.13.816.590 I slot print_timing: id 0 | task 6729 | eval time = 609.89 ms / 71 tokens ( 8.71 ms per token, 114.78 tokens per second) 1.13.816.591 I slot print_timing: id 0 | task 6729 | total time = 759.99 ms / 688 tokens 1.13.816.592 I slot print_timing: id 0 | task 6729 | graphs reused = 6496 1.13.816.592 I slot print_timing: id 0 | task 6729 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.816.629 I slot release: id 0 | task 6729 | stop processing: n_tokens = 712, truncated = 0 1.13.834.256 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 712, t_last = 73726028 1.13.857.530 I slot launch_slot_: id 0 | task 6801 | processing task, is_child = 0 1.14.574.178 I slot print_timing: id 0 | task 6801 | prompt eval time = 140.93 ms / 572 tokens ( 0.25 ms per token, 4058.84 tokens per second) 1.14.574.184 I slot print_timing: id 0 | task 6801 | eval time = 575.71 ms / 67 tokens ( 8.72 ms per token, 114.64 tokens per second) 1.14.574.185 I slot print_timing: id 0 | task 6801 | total time = 716.63 ms / 639 tokens 1.14.574.186 I slot print_timing: id 0 | task 6801 | graphs reused = 6561 1.14.574.187 I slot print_timing: id 0 | task 6801 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.574.222 I slot release: id 0 | task 6801 | stop processing: n_tokens = 663, truncated = 0 1.14.604.145 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 663, t_last = 74483621 1.14.625.695 I slot launch_slot_: id 0 | task 6869 | processing task, is_child = 0 1.15.266.118 I slot print_timing: id 0 | task 6869 | prompt eval time = 171.80 ms / 712 tokens ( 0.24 ms per token, 4144.28 tokens per second) 1.15.266.124 I slot print_timing: id 0 | task 6869 | eval time = 468.61 ms / 54 tokens ( 8.84 ms per token, 113.10 tokens per second) 1.15.266.125 I slot print_timing: id 0 | task 6869 | total time = 640.41 ms / 766 tokens 1.15.266.126 I slot print_timing: id 0 | task 6869 | graphs reused = 6612 1.15.266.126 I slot print_timing: id 0 | task 6869 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.266.167 I slot release: id 0 | task 6869 | stop processing: n_tokens = 790, truncated = 0 1.15.273.019 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 75175567 1.15.297.999 I slot launch_slot_: id 0 | task 6924 | processing task, is_child = 0 1.16.405.547 I slot print_timing: id 0 | task 6924 | prompt eval time = 188.38 ms / 791 tokens ( 0.24 ms per token, 4198.89 tokens per second) 1.16.405.553 I slot print_timing: id 0 | task 6924 | eval time = 919.15 ms / 106 tokens ( 8.75 ms per token, 114.24 tokens per second) 1.16.405.554 I slot print_timing: id 0 | task 6924 | total time = 1107.53 ms / 897 tokens 1.16.405.555 I slot print_timing: id 0 | task 6924 | graphs reused = 6716 1.16.405.555 I slot print_timing: id 0 | task 6924 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.405.598 I slot release: id 0 | task 6924 | stop processing: n_tokens = 921, truncated = 0 1.16.425.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 921, t_last = 76314997 1.16.454.238 I slot launch_slot_: id 0 | task 7031 | processing task, is_child = 0 1.19.540.205 I slot print_timing: id 0 | task 7031 | n_gen = 349, tg = 115.97 t/s, tg_3s = 116.30 t/s 1.22.540.565 I slot print_timing: id 0 | task 7031 | n_gen = 693, tg = 115.31 t/s, tg_3s = 114.65 t/s 1.25.470.437 I slot print_timing: id 0 | task 7031 | prompt eval time = 85.14 ms / 369 tokens ( 0.23 ms per token, 4334.09 tokens per second) 1.25.470.442 I slot print_timing: id 0 | task 7031 | eval time = 8931.04 ms / 1024 tokens ( 8.73 ms per token, 114.54 tokens per second) 1.25.470.443 I slot print_timing: id 0 | task 7031 | total time = 9016.18 ms / 1393 tokens 1.25.470.444 I slot print_timing: id 0 | task 7031 | graphs reused = 7734 1.25.470.445 I slot print_timing: id 0 | task 7031 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.470.477 I slot release: id 0 | task 7031 | stop processing: n_tokens = 1417, truncated = 0 1.25.499.563 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1417, t_last = 85379876 1.25.499.665 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.881 MiB) 1.25.501.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.255 MiB) 1.25.503.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.599 MiB) 1.25.551.776 I slot launch_slot_: id 0 | task 8056 | processing task, is_child = 0 1.26.183.266 I slot print_timing: id 0 | task 8056 | prompt eval time = 104.64 ms / 388 tokens ( 0.27 ms per token, 3707.84 tokens per second) 1.26.183.271 I slot print_timing: id 0 | task 8056 | eval time = 526.83 ms / 62 tokens ( 8.64 ms per token, 115.79 tokens per second) 1.26.183.272 I slot print_timing: id 0 | task 8056 | total time = 631.47 ms / 450 tokens 1.26.183.273 I slot print_timing: id 0 | task 8056 | graphs reused = 7794 1.26.183.274 I slot print_timing: id 0 | task 8056 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.183.304 I slot release: id 0 | task 8056 | stop processing: n_tokens = 474, truncated = 0 1.26.202.899 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 86092703 1.26.202.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 1.26.205.069 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.537 MiB) 1.26.224.497 I slot launch_slot_: id 0 | task 8119 | processing task, is_child = 0 1.26.870.614 I slot print_timing: id 0 | task 8119 | prompt eval time = 85.19 ms / 370 tokens ( 0.23 ms per token, 4343.18 tokens per second) 1.26.870.620 I slot print_timing: id 0 | task 8119 | eval time = 560.91 ms / 66 tokens ( 8.63 ms per token, 115.88 tokens per second) 1.26.870.621 I slot print_timing: id 0 | task 8119 | total time = 646.10 ms / 436 tokens 1.26.870.621 I slot print_timing: id 0 | task 8119 | graphs reused = 7858 1.26.870.623 I slot print_timing: id 0 | task 8119 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.870.653 I slot release: id 0 | task 8119 | stop processing: n_tokens = 460, truncated = 0 1.26.889.923 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 86780052 1.26.889.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 1.26.907.887 I slot launch_slot_: id 0 | task 8186 | processing task, is_child = 0 1.27.501.574 I slot print_timing: id 0 | task 8186 | prompt eval time = 85.30 ms / 340 tokens ( 0.25 ms per token, 3986.07 tokens per second) 1.27.501.580 I slot print_timing: id 0 | task 8186 | eval time = 508.37 ms / 60 tokens ( 8.62 ms per token, 116.06 tokens per second) 1.27.501.582 I slot print_timing: id 0 | task 8186 | total time = 593.67 ms / 400 tokens 1.27.501.582 I slot print_timing: id 0 | task 8186 | graphs reused = 7916 1.27.501.583 I slot print_timing: id 0 | task 8186 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.501.612 I slot release: id 0 | task 8186 | stop processing: n_tokens = 424, truncated = 0 1.27.529.217 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 87411012 1.27.529.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.538 MiB) 1.27.546.891 I slot launch_slot_: id 0 | task 8247 | processing task, is_child = 0 1.28.315.751 I slot print_timing: id 0 | task 8247 | prompt eval time = 105.48 ms / 409 tokens ( 0.26 ms per token, 3877.40 tokens per second) 1.28.315.756 I slot print_timing: id 0 | task 8247 | eval time = 663.36 ms / 78 tokens ( 8.62 ms per token, 116.08 tokens per second) 1.28.315.757 I slot print_timing: id 0 | task 8247 | total time = 768.84 ms / 487 tokens 1.28.315.758 I slot print_timing: id 0 | task 8247 | graphs reused = 7992 1.28.315.759 I slot print_timing: id 0 | task 8247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.315.789 I slot release: id 0 | task 8247 | stop processing: n_tokens = 511, truncated = 0 1.28.335.915 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 88225188 1.28.335.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.695 MiB) 1.28.356.203 I slot launch_slot_: id 0 | task 8326 | processing task, is_child = 0 1.29.268.723 I slot print_timing: id 0 | task 8326 | prompt eval time = 105.92 ms / 422 tokens ( 0.25 ms per token, 3984.33 tokens per second) 1.29.268.729 I slot print_timing: id 0 | task 8326 | eval time = 806.59 ms / 94 tokens ( 8.67 ms per token, 115.30 tokens per second) 1.29.268.730 I slot print_timing: id 0 | task 8326 | total time = 912.50 ms / 516 tokens 1.29.268.731 I slot print_timing: id 0 | task 8326 | graphs reused = 8083 1.29.268.732 I slot print_timing: id 0 | task 8326 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.268.762 I slot release: id 0 | task 8326 | stop processing: n_tokens = 540, truncated = 0 1.29.294.693 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 89178161 1.29.294.755 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.724 MiB) 1.29.315.356 I slot launch_slot_: id 0 | task 8421 | processing task, is_child = 0 1.30.398.737 I slot print_timing: id 0 | task 8421 | prompt eval time = 118.20 ms / 499 tokens ( 0.24 ms per token, 4221.48 tokens per second) 1.30.398.743 I slot print_timing: id 0 | task 8421 | eval time = 965.16 ms / 112 tokens ( 8.70 ms per token, 115.01 tokens per second) 1.30.398.744 I slot print_timing: id 0 | task 8421 | total time = 1083.36 ms / 611 tokens 1.30.398.744 I slot print_timing: id 0 | task 8421 | graphs reused = 8193 1.30.398.745 I slot print_timing: id 0 | task 8421 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.398.777 I slot release: id 0 | task 8421 | stop processing: n_tokens = 639, truncated = 0 1.30.424.186 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 90308177 1.30.424.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 1.30.447.459 I slot launch_slot_: id 0 | task 8534 | processing task, is_child = 0 1.30.905.119 I slot print_timing: id 0 | task 8534 | prompt eval time = 85.11 ms / 345 tokens ( 0.25 ms per token, 4053.82 tokens per second) 1.30.905.125 I slot print_timing: id 0 | task 8534 | eval time = 372.54 ms / 44 tokens ( 8.66 ms per token, 115.42 tokens per second) 1.30.905.126 I slot print_timing: id 0 | task 8534 | total time = 457.64 ms / 389 tokens 1.30.905.129 I slot print_timing: id 0 | task 8534 | graphs reused = 8235 1.30.905.130 I slot print_timing: id 0 | task 8534 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.905.158 I slot release: id 0 | task 8534 | stop processing: n_tokens = 413, truncated = 0 1.30.922.914 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 90814557 1.30.922.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.381 MiB) 1.30.939.641 I slot launch_slot_: id 0 | task 8579 | processing task, is_child = 0 1.31.397.516 I slot print_timing: id 0 | task 8579 | prompt eval time = 85.39 ms / 348 tokens ( 0.25 ms per token, 4075.51 tokens per second) 1.31.397.522 I slot print_timing: id 0 | task 8579 | eval time = 372.47 ms / 44 tokens ( 8.66 ms per token, 115.44 tokens per second) 1.31.397.523 I slot print_timing: id 0 | task 8579 | total time = 457.86 ms / 392 tokens 1.31.397.524 I slot print_timing: id 0 | task 8579 | graphs reused = 8277 1.31.397.525 I slot print_timing: id 0 | task 8579 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.397.555 I slot release: id 0 | task 8579 | stop processing: n_tokens = 416, truncated = 0 1.31.424.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 91306954 1.31.424.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.350 MiB) 1.31.442.104 I slot launch_slot_: id 0 | task 8624 | processing task, is_child = 0 1.32.124.379 I slot print_timing: id 0 | task 8624 | prompt eval time = 105.28 ms / 408 tokens ( 0.26 ms per token, 3875.23 tokens per second) 1.32.124.385 I slot print_timing: id 0 | task 8624 | eval time = 576.98 ms / 68 tokens ( 8.61 ms per token, 116.12 tokens per second) 1.32.124.386 I slot print_timing: id 0 | task 8624 | total time = 682.26 ms / 476 tokens 1.32.124.387 I slot print_timing: id 0 | task 8624 | graphs reused = 8343 1.32.124.388 I slot print_timing: id 0 | task 8624 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.124.418 I slot release: id 0 | task 8624 | stop processing: n_tokens = 500, truncated = 0 1.32.150.706 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 92033817 1.32.150.773 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.287 MiB) 1.32.170.559 I slot launch_slot_: id 0 | task 8693 | processing task, is_child = 0 1.32.689.763 I slot print_timing: id 0 | task 8693 | prompt eval time = 115.53 ms / 465 tokens ( 0.25 ms per token, 4025.10 tokens per second) 1.32.689.770 I slot print_timing: id 0 | task 8693 | eval time = 403.66 ms / 46 tokens ( 8.97 ms per token, 111.48 tokens per second) 1.32.689.771 I slot print_timing: id 0 | task 8693 | total time = 519.19 ms / 511 tokens 1.32.689.772 I slot print_timing: id 0 | task 8693 | graphs reused = 8386 1.32.689.773 I slot print_timing: id 0 | task 8693 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.689.809 I slot release: id 0 | task 8693 | stop processing: n_tokens = 535, truncated = 0 1.32.709.790 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 92599208 1.32.709.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.662 MiB) 1.32.729.928 I slot launch_slot_: id 0 | task 8740 | processing task, is_child = 0 1.33.342.573 I slot print_timing: id 0 | task 8740 | prompt eval time = 104.96 ms / 399 tokens ( 0.26 ms per token, 3801.38 tokens per second) 1.33.342.578 I slot print_timing: id 0 | task 8740 | eval time = 507.67 ms / 60 tokens ( 8.60 ms per token, 116.22 tokens per second) 1.33.342.579 I slot print_timing: id 0 | task 8740 | total time = 612.63 ms / 459 tokens 1.33.342.580 I slot print_timing: id 0 | task 8740 | graphs reused = 8444 1.33.342.581 I slot print_timing: id 0 | task 8740 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.342.619 I slot release: id 0 | task 8740 | stop processing: n_tokens = 500, truncated = 0 1.33.346.803 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 93252018 1.33.346.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 1.33.348.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.506 MiB) 1.33.368.850 I slot launch_slot_: id 0 | task 8801 | processing task, is_child = 0 1.34.090.866 I slot print_timing: id 0 | task 8801 | prompt eval time = 106.06 ms / 419 tokens ( 0.25 ms per token, 3950.52 tokens per second) 1.34.090.872 I slot print_timing: id 0 | task 8801 | eval time = 615.94 ms / 72 tokens ( 8.68 ms per token, 115.27 tokens per second) 1.34.090.873 I slot print_timing: id 0 | task 8801 | total time = 722.00 ms / 491 tokens 1.34.090.873 I slot print_timing: id 0 | task 8801 | graphs reused = 8513 1.34.090.874 I slot print_timing: id 0 | task 8801 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.090.905 I slot release: id 0 | task 8801 | stop processing: n_tokens = 515, truncated = 0 1.34.118.911 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 94000304 1.34.118.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.224 MiB) 1.34.138.886 I slot launch_slot_: id 0 | task 8874 | processing task, is_child = 0 1.34.854.436 I slot print_timing: id 0 | task 8874 | prompt eval time = 106.83 ms / 440 tokens ( 0.24 ms per token, 4118.89 tokens per second) 1.34.854.442 I slot print_timing: id 0 | task 8874 | eval time = 608.71 ms / 71 tokens ( 8.70 ms per token, 115.00 tokens per second) 1.34.854.443 I slot print_timing: id 0 | task 8874 | total time = 715.54 ms / 511 tokens 1.34.854.444 I slot print_timing: id 0 | task 8874 | graphs reused = 8581 1.34.854.445 I slot print_timing: id 0 | task 8874 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.854.477 I slot release: id 0 | task 8874 | stop processing: n_tokens = 535, truncated = 0 1.34.870.123 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 94763876 1.34.870.182 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 1.34.889.970 I slot launch_slot_: id 0 | task 8946 | processing task, is_child = 0 1.35.414.855 I slot print_timing: id 0 | task 8946 | prompt eval time = 85.56 ms / 372 tokens ( 0.23 ms per token, 4347.93 tokens per second) 1.35.414.861 I slot print_timing: id 0 | task 8946 | eval time = 439.31 ms / 52 tokens ( 8.61 ms per token, 116.09 tokens per second) 1.35.414.862 I slot print_timing: id 0 | task 8946 | total time = 524.87 ms / 424 tokens 1.35.414.863 I slot print_timing: id 0 | task 8946 | graphs reused = 8631 1.35.414.864 I slot print_timing: id 0 | task 8946 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.414.894 I slot release: id 0 | task 8946 | stop processing: n_tokens = 448, truncated = 0 1.35.429.726 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 95324293 1.35.429.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.943 MiB) 1.35.447.066 I slot launch_slot_: id 0 | task 8999 | processing task, is_child = 0 1.36.059.828 I slot print_timing: id 0 | task 8999 | prompt eval time = 115.66 ms / 449 tokens ( 0.26 ms per token, 3881.93 tokens per second) 1.36.059.834 I slot print_timing: id 0 | task 8999 | eval time = 497.08 ms / 58 tokens ( 8.72 ms per token, 114.67 tokens per second) 1.36.059.835 I slot print_timing: id 0 | task 8999 | total time = 612.75 ms / 507 tokens 1.36.059.836 I slot print_timing: id 0 | task 8999 | graphs reused = 8686 1.36.059.837 I slot print_timing: id 0 | task 8999 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.059.870 I slot release: id 0 | task 8999 | stop processing: n_tokens = 531, truncated = 0 1.36.085.829 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 95969269 1.36.085.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.631 MiB) 1.36.088.025 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.787 MiB) 1.36.108.866 I slot launch_slot_: id 0 | task 9058 | processing task, is_child = 0 1.36.719.563 I slot print_timing: id 0 | task 9058 | prompt eval time = 85.41 ms / 360 tokens ( 0.24 ms per token, 4215.21 tokens per second) 1.36.719.570 I slot print_timing: id 0 | task 9058 | eval time = 525.28 ms / 62 tokens ( 8.61 ms per token, 116.13 tokens per second) 1.36.719.571 I slot print_timing: id 0 | task 9058 | total time = 610.68 ms / 422 tokens 1.36.719.571 I slot print_timing: id 0 | task 9058 | graphs reused = 8746 1.36.719.572 I slot print_timing: id 0 | task 9058 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.719.602 I slot release: id 0 | task 9058 | stop processing: n_tokens = 446, truncated = 0 1.36.744.846 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 96629001 1.36.744.906 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.850 MiB) 1.36.762.690 I slot launch_slot_: id 0 | task 9121 | processing task, is_child = 0 1.37.313.133 I slot print_timing: id 0 | task 9121 | prompt eval time = 85.10 ms / 346 tokens ( 0.25 ms per token, 4066.00 tokens per second) 1.37.313.139 I slot print_timing: id 0 | task 9121 | eval time = 465.33 ms / 55 tokens ( 8.62 ms per token, 116.05 tokens per second) 1.37.313.140 I slot print_timing: id 0 | task 9121 | total time = 550.42 ms / 401 tokens 1.37.313.140 I slot print_timing: id 0 | task 9121 | graphs reused = 8799 1.37.313.141 I slot print_timing: id 0 | task 9121 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.313.171 I slot release: id 0 | task 9121 | stop processing: n_tokens = 425, truncated = 0 1.37.340.789 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 97222570 1.37.355.548 I slot launch_slot_: id 0 | task 9177 | processing task, is_child = 0 1.37.902.020 I slot print_timing: id 0 | task 9177 | prompt eval time = 106.47 ms / 434 tokens ( 0.25 ms per token, 4076.34 tokens per second) 1.37.902.025 I slot print_timing: id 0 | task 9177 | eval time = 439.99 ms / 52 tokens ( 8.63 ms per token, 115.91 tokens per second) 1.37.902.027 I slot print_timing: id 0 | task 9177 | total time = 546.46 ms / 486 tokens 1.37.902.027 I slot print_timing: id 0 | task 9177 | graphs reused = 8849 1.37.902.028 I slot print_timing: id 0 | task 9177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.902.059 I slot release: id 0 | task 9177 | stop processing: n_tokens = 510, truncated = 0 1.37.916.923 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 97811458 1.37.916.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.412 MiB) 1.37.919.106 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 1.37.939.742 I slot launch_slot_: id 0 | task 9230 | processing task, is_child = 0 1.38.542.019 I slot print_timing: id 0 | task 9230 | prompt eval time = 85.11 ms / 369 tokens ( 0.23 ms per token, 4335.51 tokens per second) 1.38.542.025 I slot print_timing: id 0 | task 9230 | eval time = 517.15 ms / 59 tokens ( 8.92 ms per token, 112.15 tokens per second) 1.38.542.026 I slot print_timing: id 0 | task 9230 | total time = 602.26 ms / 428 tokens 1.38.542.027 I slot print_timing: id 0 | task 9230 | graphs reused = 8906 1.38.542.028 I slot print_timing: id 0 | task 9230 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.542.058 I slot release: id 0 | task 9230 | stop processing: n_tokens = 452, truncated = 0 1.38.569.655 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 98451457 1.38.584.716 I slot launch_slot_: id 0 | task 9290 | processing task, is_child = 0 1.39.361.997 I slot print_timing: id 0 | task 9290 | prompt eval time = 107.31 ms / 446 tokens ( 0.24 ms per token, 4156.38 tokens per second) 1.39.362.003 I slot print_timing: id 0 | task 9290 | eval time = 669.96 ms / 78 tokens ( 8.70 ms per token, 114.93 tokens per second) 1.39.362.005 I slot print_timing: id 0 | task 9290 | total time = 777.27 ms / 524 tokens 1.39.362.005 I slot print_timing: id 0 | task 9290 | graphs reused = 8981 1.39.362.007 I slot print_timing: id 0 | task 9290 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.362.038 I slot release: id 0 | task 9290 | stop processing: n_tokens = 548, truncated = 0 1.39.385.812 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 548, t_last = 99271437 1.39.385.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.288 MiB) 1.39.388.230 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.569 MiB) 1.39.410.138 I slot launch_slot_: id 0 | task 9369 | processing task, is_child = 0 1.40.185.199 I slot print_timing: id 0 | task 9369 | prompt eval time = 105.11 ms / 396 tokens ( 0.27 ms per token, 3767.34 tokens per second) 1.40.185.206 I slot print_timing: id 0 | task 9369 | eval time = 669.93 ms / 79 tokens ( 8.59 ms per token, 116.43 tokens per second) 1.40.185.207 I slot print_timing: id 0 | task 9369 | total time = 775.04 ms / 475 tokens 1.40.185.208 I slot print_timing: id 0 | task 9369 | graphs reused = 9058 1.40.185.208 I slot print_timing: id 0 | task 9369 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.185.238 I slot release: id 0 | task 9369 | stop processing: n_tokens = 501, truncated = 0 1.40.212.509 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 100094637 1.40.212.569 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 1.40.231.526 I slot launch_slot_: id 0 | task 9449 | processing task, is_child = 0 1.41.113.661 I slot print_timing: id 0 | task 9449 | prompt eval time = 115.89 ms / 466 tokens ( 0.25 ms per token, 4021.16 tokens per second) 1.41.113.667 I slot print_timing: id 0 | task 9449 | eval time = 766.23 ms / 88 tokens ( 8.81 ms per token, 113.54 tokens per second) 1.41.113.668 I slot print_timing: id 0 | task 9449 | total time = 882.12 ms / 554 tokens 1.41.113.669 I slot print_timing: id 0 | task 9449 | graphs reused = 9143 1.41.113.670 I slot print_timing: id 0 | task 9449 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.113.701 I slot release: id 0 | task 9449 | stop processing: n_tokens = 578, truncated = 0 1.41.130.994 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 578, t_last = 101023100 1.41.131.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 1.41.152.805 I slot launch_slot_: id 0 | task 9538 | processing task, is_child = 0 1.41.845.796 I slot print_timing: id 0 | task 9538 | prompt eval time = 115.78 ms / 467 tokens ( 0.25 ms per token, 4033.65 tokens per second) 1.41.845.802 I slot print_timing: id 0 | task 9538 | eval time = 577.20 ms / 66 tokens ( 8.88 ms per token, 112.61 tokens per second) 1.41.845.803 I slot print_timing: id 0 | task 9538 | total time = 692.97 ms / 533 tokens 1.41.845.804 I slot print_timing: id 0 | task 9538 | graphs reused = 9206 1.41.845.805 I slot print_timing: id 0 | task 9538 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.845.841 I slot release: id 0 | task 9538 | stop processing: n_tokens = 557, truncated = 0 1.41.850.037 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 101755240 1.41.850.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.163 MiB) 1.41.871.242 I slot launch_slot_: id 0 | task 9605 | processing task, is_child = 0 1.42.605.733 I slot print_timing: id 0 | task 9605 | prompt eval time = 115.83 ms / 454 tokens ( 0.26 ms per token, 3919.50 tokens per second) 1.42.605.739 I slot print_timing: id 0 | task 9605 | eval time = 618.64 ms / 71 tokens ( 8.84 ms per token, 113.15 tokens per second) 1.42.605.740 I slot print_timing: id 0 | task 9605 | total time = 734.48 ms / 525 tokens 1.42.605.740 I slot print_timing: id 0 | task 9605 | graphs reused = 9274 1.42.605.741 I slot print_timing: id 0 | task 9605 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.605.773 I slot release: id 0 | task 9605 | stop processing: n_tokens = 549, truncated = 0 1.42.629.613 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 102515172 1.42.629.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.319 MiB) 1.42.651.148 I slot launch_slot_: id 0 | task 9677 | processing task, is_child = 0 1.43.281.857 I slot print_timing: id 0 | task 9677 | prompt eval time = 105.53 ms / 409 tokens ( 0.26 ms per token, 3875.79 tokens per second) 1.43.281.863 I slot print_timing: id 0 | task 9677 | eval time = 525.17 ms / 62 tokens ( 8.61 ms per token, 116.15 tokens per second) 1.43.281.864 I slot print_timing: id 0 | task 9677 | total time = 630.69 ms / 471 tokens 1.43.281.865 I slot print_timing: id 0 | task 9677 | graphs reused = 9334 1.43.281.866 I slot print_timing: id 0 | task 9677 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.281.897 I slot release: id 0 | task 9677 | stop processing: n_tokens = 495, truncated = 0 1.43.310.152 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 103191296 1.43.310.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.318 MiB) 1.43.314.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.255 MiB) 1.43.334.750 I slot launch_slot_: id 0 | task 9740 | processing task, is_child = 0 1.43.902.387 I slot print_timing: id 0 | task 9740 | prompt eval time = 85.21 ms / 349 tokens ( 0.24 ms per token, 4095.67 tokens per second) 1.43.902.393 I slot print_timing: id 0 | task 9740 | eval time = 482.41 ms / 57 tokens ( 8.61 ms per token, 116.08 tokens per second) 1.43.902.394 I slot print_timing: id 0 | task 9740 | total time = 567.62 ms / 406 tokens 1.43.902.395 I slot print_timing: id 0 | task 9740 | graphs reused = 9389 1.43.902.395 I slot print_timing: id 0 | task 9740 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.902.425 I slot release: id 0 | task 9740 | stop processing: n_tokens = 430, truncated = 0 1.43.906.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 103811824 1.43.906.607 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.944 MiB) 1.43.926.316 I slot launch_slot_: id 0 | task 9798 | processing task, is_child = 0 1.44.529.247 I slot print_timing: id 0 | task 9798 | prompt eval time = 107.17 ms / 435 tokens ( 0.25 ms per token, 4059.16 tokens per second) 1.44.529.252 I slot print_timing: id 0 | task 9798 | eval time = 495.75 ms / 58 tokens ( 8.70 ms per token, 114.98 tokens per second) 1.44.529.253 I slot print_timing: id 0 | task 9798 | total time = 602.91 ms / 493 tokens 1.44.529.255 I slot print_timing: id 0 | task 9798 | graphs reused = 9444 1.44.529.255 I slot print_timing: id 0 | task 9798 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.529.286 I slot release: id 0 | task 9798 | stop processing: n_tokens = 517, truncated = 0 1.44.546.671 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 104438685 1.44.546.729 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.725 MiB) 1.44.568.592 I slot launch_slot_: id 0 | task 9857 | processing task, is_child = 0 1.45.061.879 I slot print_timing: id 0 | task 9857 | prompt eval time = 78.87 ms / 322 tokens ( 0.24 ms per token, 4082.72 tokens per second) 1.45.061.885 I slot print_timing: id 0 | task 9857 | eval time = 414.40 ms / 47 tokens ( 9.01 ms per token, 111.00 tokens per second) 1.45.061.886 I slot print_timing: id 0 | task 9857 | total time = 493.27 ms / 369 tokens 1.45.061.886 I slot print_timing: id 0 | task 9857 | graphs reused = 9489 1.45.061.887 I slot print_timing: id 0 | task 9857 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.061.915 I slot release: id 0 | task 9857 | stop processing: n_tokens = 393, truncated = 0 1.45.082.012 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 104971314 1.45.082.063 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 1.45.099.750 I slot launch_slot_: id 0 | task 9905 | processing task, is_child = 0 1.45.659.399 I slot print_timing: id 0 | task 9905 | prompt eval time = 85.97 ms / 360 tokens ( 0.24 ms per token, 4187.60 tokens per second) 1.45.659.405 I slot print_timing: id 0 | task 9905 | eval time = 473.67 ms / 56 tokens ( 8.61 ms per token, 116.12 tokens per second) 1.45.659.406 I slot print_timing: id 0 | task 9905 | total time = 559.63 ms / 416 tokens 1.45.659.407 I slot print_timing: id 0 | task 9905 | graphs reused = 9543 1.45.659.408 I slot print_timing: id 0 | task 9905 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.659.438 I slot release: id 0 | task 9905 | stop processing: n_tokens = 440, truncated = 0 1.45.688.629 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 105568837 1.45.688.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 1.45.707.979 I slot launch_slot_: id 0 | task 9962 | processing task, is_child = 0 1.46.450.106 I slot print_timing: id 0 | task 9962 | prompt eval time = 106.62 ms / 443 tokens ( 0.24 ms per token, 4154.75 tokens per second) 1.46.450.112 I slot print_timing: id 0 | task 9962 | eval time = 635.49 ms / 73 tokens ( 8.83 ms per token, 113.30 tokens per second) 1.46.450.113 I slot print_timing: id 0 | task 9962 | total time = 742.11 ms / 516 tokens 1.46.450.114 I slot print_timing: id 0 | task 9962 | graphs reused = 9613 1.46.450.114 I slot print_timing: id 0 | task 9962 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.450.144 I slot release: id 0 | task 9962 | stop processing: n_tokens = 540, truncated = 0 1.46.474.993 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 106359544 1.46.475.048 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.474 MiB) 1.46.496.406 I slot launch_slot_: id 0 | task 10036 | processing task, is_child = 0 1.46.974.467 I slot print_timing: id 0 | task 10036 | prompt eval time = 106.73 ms / 442 tokens ( 0.24 ms per token, 4141.41 tokens per second) 1.46.974.473 I slot print_timing: id 0 | task 10036 | eval time = 371.32 ms / 44 tokens ( 8.64 ms per token, 115.80 tokens per second) 1.46.974.474 I slot print_timing: id 0 | task 10036 | total time = 478.04 ms / 486 tokens 1.46.974.475 I slot print_timing: id 0 | task 10036 | graphs reused = 9655 1.46.974.476 I slot print_timing: id 0 | task 10036 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.974.506 I slot release: id 0 | task 10036 | stop processing: n_tokens = 510, truncated = 0 1.46.990.636 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 106883905 1.46.990.687 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.850 MiB) 1.47.020.017 I slot launch_slot_: id 0 | task 10081 | processing task, is_child = 0 1.47.514.128 I slot print_timing: id 0 | task 10081 | prompt eval time = 115.76 ms / 470 tokens ( 0.25 ms per token, 4060.23 tokens per second) 1.47.514.134 I slot print_timing: id 0 | task 10081 | eval time = 378.34 ms / 44 tokens ( 8.80 ms per token, 113.65 tokens per second) 1.47.514.135 I slot print_timing: id 0 | task 10081 | total time = 494.10 ms / 514 tokens 1.47.514.136 I slot print_timing: id 0 | task 10081 | graphs reused = 9696 1.47.514.137 I slot print_timing: id 0 | task 10081 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.514.169 I slot release: id 0 | task 10081 | stop processing: n_tokens = 538, truncated = 0 1.47.531.993 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 538, t_last = 107423568 1.47.532.053 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 1.47.535.843 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.255 MiB) 1.47.557.392 I slot launch_slot_: id 0 | task 10126 | processing task, is_child = 0 1.47.967.365 I slot print_timing: id 0 | task 10126 | prompt eval time = 117.17 ms / 483 tokens ( 0.24 ms per token, 4122.07 tokens per second) 1.47.967.371 I slot print_timing: id 0 | task 10126 | eval time = 292.78 ms / 34 tokens ( 8.87 ms per token, 112.71 tokens per second) 1.47.967.372 I slot print_timing: id 0 | task 10126 | total time = 409.96 ms / 517 tokens 1.47.967.373 I slot print_timing: id 0 | task 10126 | graphs reused = 9727 1.47.967.374 I slot print_timing: id 0 | task 10126 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.967.409 I slot release: id 0 | task 10126 | stop processing: n_tokens = 541, truncated = 0 1.47.984.523 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 107876809 1.47.984.588 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 1.48.007.356 I slot launch_slot_: id 0 | task 10161 | processing task, is_child = 0 1.48.596.440 I slot print_timing: id 0 | task 10161 | prompt eval time = 115.88 ms / 463 tokens ( 0.25 ms per token, 3995.44 tokens per second) 1.48.596.445 I slot print_timing: id 0 | task 10161 | eval time = 473.19 ms / 55 tokens ( 8.76 ms per token, 114.12 tokens per second) 1.48.596.446 I slot print_timing: id 0 | task 10161 | total time = 589.07 ms / 518 tokens 1.48.596.447 I slot print_timing: id 0 | task 10161 | graphs reused = 9779 1.48.596.448 I slot print_timing: id 0 | task 10161 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.596.479 I slot release: id 0 | task 10161 | stop processing: n_tokens = 542, truncated = 0 1.48.619.267 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 108505878 1.48.619.328 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.664 MiB) 1.48.643.006 I slot launch_slot_: id 0 | task 10217 | processing task, is_child = 0 1.49.171.425 I slot print_timing: id 0 | task 10217 | prompt eval time = 106.29 ms / 421 tokens ( 0.25 ms per token, 3960.75 tokens per second) 1.49.171.432 I slot print_timing: id 0 | task 10217 | eval time = 422.11 ms / 50 tokens ( 8.61 ms per token, 116.08 tokens per second) 1.49.171.433 I slot print_timing: id 0 | task 10217 | total time = 528.40 ms / 471 tokens 1.49.171.434 I slot print_timing: id 0 | task 10217 | graphs reused = 9827 1.49.171.435 I slot print_timing: id 0 | task 10217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.171.465 I slot release: id 0 | task 10217 | stop processing: n_tokens = 495, truncated = 0 1.49.201.073 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 109080864 1.49.201.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 1.49.221.986 I slot launch_slot_: id 0 | task 10268 | processing task, is_child = 0 1.50.511.780 I slot print_timing: id 0 | task 10268 | prompt eval time = 86.33 ms / 360 tokens ( 0.24 ms per token, 4170.19 tokens per second) 1.50.511.786 I slot print_timing: id 0 | task 10268 | eval time = 1203.45 ms / 141 tokens ( 8.60 ms per token, 116.33 tokens per second) 1.50.511.787 I slot print_timing: id 0 | task 10268 | total time = 1289.78 ms / 501 tokens 1.50.511.787 I slot print_timing: id 0 | task 10268 | graphs reused = 9965 1.50.511.788 I slot print_timing: id 0 | task 10268 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.511.818 I slot release: id 0 | task 10268 | stop processing: n_tokens = 525, truncated = 0 1.50.534.883 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 525, t_last = 110421217 1.50.534.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.193 MiB) 1.50.556.481 I slot launch_slot_: id 0 | task 10410 | processing task, is_child = 0 1.51.287.988 I slot print_timing: id 0 | task 10410 | prompt eval time = 139.89 ms / 547 tokens ( 0.26 ms per token, 3910.10 tokens per second) 1.51.287.994 I slot print_timing: id 0 | task 10410 | eval time = 591.60 ms / 69 tokens ( 8.70 ms per token, 114.94 tokens per second) 1.51.287.995 I slot print_timing: id 0 | task 10410 | total time = 731.49 ms / 616 tokens 1.51.287.996 I slot print_timing: id 0 | task 10410 | graphs reused = 10032 1.51.287.996 I slot print_timing: id 0 | task 10410 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.288.032 I slot release: id 0 | task 10410 | stop processing: n_tokens = 640, truncated = 0 1.51.318.946 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 640, t_last = 111197431 1.51.319.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.600 MiB) 1.51.323.996 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.194 MiB) 1.51.350.232 I slot launch_slot_: id 0 | task 10480 | processing task, is_child = 0 1.52.455.234 I slot print_timing: id 0 | task 10480 | prompt eval time = 181.32 ms / 749 tokens ( 0.24 ms per token, 4130.82 tokens per second) 1.52.455.240 I slot print_timing: id 0 | task 10480 | eval time = 923.67 ms / 107 tokens ( 8.71 ms per token, 114.76 tokens per second) 1.52.455.241 I slot print_timing: id 0 | task 10480 | total time = 1104.99 ms / 856 tokens 1.52.455.241 I slot print_timing: id 0 | task 10480 | graphs reused = 10137 1.52.455.242 I slot print_timing: id 0 | task 10480 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.455.284 I slot release: id 0 | task 10480 | stop processing: n_tokens = 880, truncated = 0 1.52.473.116 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 112364683 1.52.473.194 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 1.52.477.199 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 1.52.508.604 I slot launch_slot_: id 0 | task 10588 | processing task, is_child = 0 1.53.085.407 I slot print_timing: id 0 | task 10588 | prompt eval time = 166.46 ms / 678 tokens ( 0.25 ms per token, 4073.12 tokens per second) 1.53.085.413 I slot print_timing: id 0 | task 10588 | eval time = 410.33 ms / 48 tokens ( 8.73 ms per token, 114.54 tokens per second) 1.53.085.414 I slot print_timing: id 0 | task 10588 | total time = 576.79 ms / 726 tokens 1.53.085.415 I slot print_timing: id 0 | task 10588 | graphs reused = 10183 1.53.085.416 I slot print_timing: id 0 | task 10588 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.085.455 I slot release: id 0 | task 10588 | stop processing: n_tokens = 750, truncated = 0 1.53.108.005 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 112994854 1.53.108.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.381 MiB) 1.53.137.030 I slot launch_slot_: id 0 | task 10637 | processing task, is_child = 0 1.53.784.622 I slot print_timing: id 0 | task 10637 | prompt eval time = 140.27 ms / 567 tokens ( 0.25 ms per token, 4042.12 tokens per second) 1.53.784.628 I slot print_timing: id 0 | task 10637 | eval time = 507.30 ms / 57 tokens ( 9.06 ms per token, 110.39 tokens per second) 1.53.784.629 I slot print_timing: id 0 | task 10637 | total time = 647.57 ms / 624 tokens 1.53.784.630 I slot print_timing: id 0 | task 10637 | graphs reused = 10238 1.53.784.630 I slot print_timing: id 0 | task 10637 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.784.666 I slot release: id 0 | task 10637 | stop processing: n_tokens = 648, truncated = 0 1.53.789.694 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 113694065 1.53.789.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 1.53.793.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 1.53.820.004 I slot launch_slot_: id 0 | task 10695 | processing task, is_child = 0 1.54.441.420 I slot print_timing: id 0 | task 10695 | prompt eval time = 118.37 ms / 501 tokens ( 0.24 ms per token, 4232.49 tokens per second) 1.54.441.426 I slot print_timing: id 0 | task 10695 | eval time = 503.03 ms / 58 tokens ( 8.83 ms per token, 113.31 tokens per second) 1.54.441.427 I slot print_timing: id 0 | task 10695 | total time = 621.40 ms / 559 tokens 1.54.441.428 I slot print_timing: id 0 | task 10695 | graphs reused = 10294 1.54.441.428 I slot print_timing: id 0 | task 10695 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.441.463 I slot release: id 0 | task 10695 | stop processing: n_tokens = 583, truncated = 0 1.54.461.743 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 114350862 1.54.461.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 1.54.484.906 I slot launch_slot_: id 0 | task 10754 | processing task, is_child = 0 1.55.206.443 I slot print_timing: id 0 | task 10754 | prompt eval time = 188.25 ms / 769 tokens ( 0.24 ms per token, 4084.95 tokens per second) 1.55.206.448 I slot print_timing: id 0 | task 10754 | eval time = 533.27 ms / 62 tokens ( 8.74 ms per token, 114.39 tokens per second) 1.55.206.449 I slot print_timing: id 0 | task 10754 | total time = 721.52 ms / 831 tokens 1.55.206.450 I slot print_timing: id 0 | task 10754 | graphs reused = 10354 1.55.206.451 I slot print_timing: id 0 | task 10754 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.206.492 I slot release: id 0 | task 10754 | stop processing: n_tokens = 855, truncated = 0 1.55.211.529 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 115115891 1.55.211.602 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.945 MiB) 1.55.217.369 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.539 MiB) 1.55.250.685 I slot launch_slot_: id 0 | task 10817 | processing task, is_child = 0 1.55.891.360 I slot print_timing: id 0 | task 10817 | prompt eval time = 118.36 ms / 500 tokens ( 0.24 ms per token, 4224.36 tokens per second) 1.55.891.366 I slot print_timing: id 0 | task 10817 | eval time = 522.29 ms / 61 tokens ( 8.70 ms per token, 114.88 tokens per second) 1.55.891.367 I slot print_timing: id 0 | task 10817 | total time = 640.65 ms / 561 tokens 1.55.891.367 I slot print_timing: id 0 | task 10817 | graphs reused = 10413 1.55.891.368 I slot print_timing: id 0 | task 10817 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.891.403 I slot release: id 0 | task 10817 | stop processing: n_tokens = 585, truncated = 0 1.55.912.359 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 115800802 1.55.912.422 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.256 MiB) 1.55.935.975 I slot launch_slot_: id 0 | task 10879 | processing task, is_child = 0 1.56.584.963 I slot print_timing: id 0 | task 10879 | prompt eval time = 152.10 ms / 632 tokens ( 0.24 ms per token, 4155.22 tokens per second) 1.56.584.969 I slot print_timing: id 0 | task 10879 | eval time = 496.87 ms / 58 tokens ( 8.72 ms per token, 114.72 tokens per second) 1.56.584.970 I slot print_timing: id 0 | task 10879 | total time = 648.97 ms / 690 tokens 1.56.584.971 I slot print_timing: id 0 | task 10879 | graphs reused = 10469 1.56.584.972 I slot print_timing: id 0 | task 10879 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.585.009 I slot release: id 0 | task 10879 | stop processing: n_tokens = 714, truncated = 0 1.56.613.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 116494408 1.56.613.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 1.56.640.464 I slot launch_slot_: id 0 | task 10938 | processing task, is_child = 0 1.57.057.826 I slot print_timing: id 0 | task 10938 | prompt eval time = 105.24 ms / 395 tokens ( 0.27 ms per token, 3753.18 tokens per second) 1.57.057.832 I slot print_timing: id 0 | task 10938 | eval time = 312.10 ms / 37 tokens ( 8.67 ms per token, 115.35 tokens per second) 1.57.057.833 I slot print_timing: id 0 | task 10938 | total time = 417.35 ms / 432 tokens 1.57.057.834 I slot print_timing: id 0 | task 10938 | graphs reused = 10504 1.57.057.834 I slot print_timing: id 0 | task 10938 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.057.861 I slot release: id 0 | task 10938 | stop processing: n_tokens = 456, truncated = 0 1.57.083.660 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 116967260 1.57.083.714 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.974 MiB) 1.57.087.691 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 1.57.119.010 I slot launch_slot_: id 0 | task 10976 | processing task, is_child = 0 1.57.785.375 I slot print_timing: id 0 | task 10976 | prompt eval time = 143.96 ms / 579 tokens ( 0.25 ms per token, 4021.84 tokens per second) 1.57.785.382 I slot print_timing: id 0 | task 10976 | eval time = 522.38 ms / 59 tokens ( 9.01 ms per token, 111.03 tokens per second) 1.57.785.383 I slot print_timing: id 0 | task 10976 | total time = 666.35 ms / 638 tokens 1.57.785.384 I slot print_timing: id 0 | task 10976 | graphs reused = 10561 1.57.785.384 I slot print_timing: id 0 | task 10976 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.785.420 I slot release: id 0 | task 10976 | stop processing: n_tokens = 662, truncated = 0 1.57.808.153 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 662, t_last = 117694820 1.57.808.217 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.320 MiB) 1.57.835.241 I slot launch_slot_: id 0 | task 11036 | processing task, is_child = 0 1.58.510.923 I slot print_timing: id 0 | task 11036 | prompt eval time = 166.37 ms / 689 tokens ( 0.24 ms per token, 4141.27 tokens per second) 1.58.510.929 I slot print_timing: id 0 | task 11036 | eval time = 509.29 ms / 59 tokens ( 8.78 ms per token, 113.88 tokens per second) 1.58.510.931 I slot print_timing: id 0 | task 11036 | total time = 675.67 ms / 748 tokens 1.58.510.933 I slot print_timing: id 0 | task 11036 | graphs reused = 10617 1.58.510.934 I slot print_timing: id 0 | task 11036 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.510.976 I slot release: id 0 | task 11036 | stop processing: n_tokens = 772, truncated = 0 1.58.530.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 118420375 1.58.530.140 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 1.58.562.237 I slot launch_slot_: id 0 | task 11096 | processing task, is_child = 0 1.59.315.893 I slot print_timing: id 0 | task 11096 | prompt eval time = 177.25 ms / 752 tokens ( 0.24 ms per token, 4242.67 tokens per second) 1.59.315.898 I slot print_timing: id 0 | task 11096 | eval time = 576.39 ms / 66 tokens ( 8.87 ms per token, 112.77 tokens per second) 1.59.315.900 I slot print_timing: id 0 | task 11096 | total time = 753.64 ms / 818 tokens 1.59.315.901 I slot print_timing: id 0 | task 11096 | graphs reused = 10681 1.59.315.901 I slot print_timing: id 0 | task 11096 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.315.942 I slot release: id 0 | task 11096 | stop processing: n_tokens = 842, truncated = 0 1.59.339.859 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 842, t_last = 119225341 1.59.339.923 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.603 MiB) 1.59.373.368 I slot launch_slot_: id 0 | task 11163 | processing task, is_child = 0 2.00.091.377 I slot print_timing: id 0 | task 11163 | prompt eval time = 144.20 ms / 582 tokens ( 0.25 ms per token, 4036.17 tokens per second) 2.00.091.383 I slot print_timing: id 0 | task 11163 | eval time = 573.80 ms / 67 tokens ( 8.69 ms per token, 115.02 tokens per second) 2.00.091.384 I slot print_timing: id 0 | task 11163 | total time = 717.99 ms / 649 tokens 2.00.091.385 I slot print_timing: id 0 | task 11163 | graphs reused = 10746 2.00.091.385 I slot print_timing: id 0 | task 11163 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.091.420 I slot release: id 0 | task 11163 | stop processing: n_tokens = 673, truncated = 0 2.00.108.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 673, t_last = 120000819 2.00.108.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.728 MiB) 2.00.137.678 I slot launch_slot_: id 0 | task 11231 | processing task, is_child = 0 2.00.960.461 I slot print_timing: id 0 | task 11231 | prompt eval time = 161.90 ms / 656 tokens ( 0.25 ms per token, 4051.93 tokens per second) 2.00.960.467 I slot print_timing: id 0 | task 11231 | eval time = 660.87 ms / 77 tokens ( 8.70 ms per token, 115.00 tokens per second) 2.00.960.468 I slot print_timing: id 0 | task 11231 | total time = 822.77 ms / 733 tokens 2.00.960.469 I slot print_timing: id 0 | task 11231 | graphs reused = 10821 2.00.960.470 I slot print_timing: id 0 | task 11231 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.960.507 I slot release: id 0 | task 11231 | stop processing: n_tokens = 757, truncated = 0 2.00.966.562 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 120869907 2.00.966.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 2.00.996.110 I slot launch_slot_: id 0 | task 11309 | processing task, is_child = 0 2.01.409.681 I slot print_timing: id 0 | task 11309 | prompt eval time = 150.14 ms / 613 tokens ( 0.24 ms per token, 4082.91 tokens per second) 2.01.409.687 I slot print_timing: id 0 | task 11309 | eval time = 263.42 ms / 31 tokens ( 8.78 ms per token, 113.89 tokens per second) 2.01.409.688 I slot print_timing: id 0 | task 11309 | total time = 413.56 ms / 644 tokens 2.01.409.689 I slot print_timing: id 0 | task 11309 | graphs reused = 10850 2.01.409.690 I slot print_timing: id 0 | task 11309 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.409.728 I slot release: id 0 | task 11309 | stop processing: n_tokens = 668, truncated = 0 2.01.415.836 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 668, t_last = 121319127 2.01.415.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.415 MiB) 2.01.444.186 I slot launch_slot_: id 0 | task 11341 | processing task, is_child = 0 2.02.460.159 I slot print_timing: id 0 | task 11341 | prompt eval time = 178.47 ms / 766 tokens ( 0.23 ms per token, 4292.16 tokens per second) 2.02.460.165 I slot print_timing: id 0 | task 11341 | eval time = 837.49 ms / 97 tokens ( 8.72 ms per token, 114.63 tokens per second) 2.02.460.166 I slot print_timing: id 0 | task 11341 | total time = 1015.96 ms / 863 tokens 2.02.460.167 I slot print_timing: id 0 | task 11341 | graphs reused = 10945 2.02.460.168 I slot print_timing: id 0 | task 11341 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.460.210 I slot release: id 0 | task 11341 | stop processing: n_tokens = 887, truncated = 0 2.02.487.058 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 122369609 2.02.487.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.102 MiB) 2.02.493.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.008 MiB) 2.02.527.965 I slot launch_slot_: id 0 | task 11439 | processing task, is_child = 0 2.03.247.438 I slot print_timing: id 0 | task 11439 | prompt eval time = 195.60 ms / 846 tokens ( 0.23 ms per token, 4325.24 tokens per second) 2.03.247.444 I slot print_timing: id 0 | task 11439 | eval time = 523.86 ms / 61 tokens ( 8.73 ms per token, 114.53 tokens per second) 2.03.247.445 I slot print_timing: id 0 | task 11439 | total time = 719.46 ms / 907 tokens 2.03.247.446 I slot print_timing: id 0 | task 11439 | graphs reused = 11004 2.03.247.447 I slot print_timing: id 0 | task 11439 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.247.492 I slot release: id 0 | task 11439 | stop processing: n_tokens = 931, truncated = 0 2.03.263.125 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 123156891 2.03.263.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.507 MiB) 2.03.298.643 I slot launch_slot_: id 0 | task 11501 | processing task, is_child = 0 2.04.121.124 I slot print_timing: id 0 | task 11501 | prompt eval time = 162.13 ms / 650 tokens ( 0.25 ms per token, 4009.10 tokens per second) 2.04.121.130 I slot print_timing: id 0 | task 11501 | eval time = 660.33 ms / 77 tokens ( 8.69 ms per token, 115.09 tokens per second) 2.04.121.131 I slot print_timing: id 0 | task 11501 | total time = 822.46 ms / 727 tokens 2.04.121.132 I slot print_timing: id 0 | task 11501 | graphs reused = 11079 2.04.121.133 I slot print_timing: id 0 | task 11501 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.121.171 I slot release: id 0 | task 11501 | stop processing: n_tokens = 751, truncated = 0 2.04.152.218 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 124030570 2.04.152.286 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.039 MiB) 2.04.158.423 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.081 MiB) 2.04.197.243 I slot launch_slot_: id 0 | task 11579 | processing task, is_child = 0 2.04.828.967 I slot print_timing: id 0 | task 11579 | prompt eval time = 172.10 ms / 717 tokens ( 0.24 ms per token, 4166.21 tokens per second) 2.04.828.973 I slot print_timing: id 0 | task 11579 | eval time = 459.61 ms / 53 tokens ( 8.84 ms per token, 113.14 tokens per second) 2.04.828.974 I slot print_timing: id 0 | task 11579 | total time = 631.71 ms / 770 tokens 2.04.828.975 I slot print_timing: id 0 | task 11579 | graphs reused = 11129 2.04.828.976 I slot print_timing: id 0 | task 11579 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.829.017 I slot release: id 0 | task 11579 | stop processing: n_tokens = 794, truncated = 0 2.04.857.915 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 794, t_last = 124738416 2.04.882.758 I slot launch_slot_: id 0 | task 11633 | processing task, is_child = 0 2.05.506.972 I slot print_timing: id 0 | task 11633 | prompt eval time = 117.99 ms / 494 tokens ( 0.24 ms per token, 4186.65 tokens per second) 2.05.506.977 I slot print_timing: id 0 | task 11633 | eval time = 506.20 ms / 59 tokens ( 8.73 ms per token, 114.58 tokens per second) 2.05.506.978 I slot print_timing: id 0 | task 11633 | total time = 624.20 ms / 553 tokens 2.05.506.980 I slot print_timing: id 0 | task 11633 | graphs reused = 11186 2.05.506.981 I slot print_timing: id 0 | task 11633 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.507.015 I slot release: id 0 | task 11633 | stop processing: n_tokens = 577, truncated = 0 2.05.527.942 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 125416414 2.05.547.279 I slot launch_slot_: id 0 | task 11693 | processing task, is_child = 0 2.06.154.001 I slot print_timing: id 0 | task 11693 | prompt eval time = 144.38 ms / 579 tokens ( 0.25 ms per token, 4010.25 tokens per second) 2.06.154.007 I slot print_timing: id 0 | task 11693 | eval time = 462.33 ms / 54 tokens ( 8.72 ms per token, 114.64 tokens per second) 2.06.154.008 I slot print_timing: id 0 | task 11693 | total time = 606.71 ms / 633 tokens 2.06.154.009 I slot print_timing: id 0 | task 11693 | graphs reused = 11238 2.06.154.010 I slot print_timing: id 0 | task 11693 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.154.048 I slot release: id 0 | task 11693 | stop processing: n_tokens = 657, truncated = 0 2.06.170.942 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 657, t_last = 126063447 2.06.170.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.194 MiB) 2.06.175.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.477 MiB) 2.06.203.346 I slot launch_slot_: id 0 | task 11748 | processing task, is_child = 0 2.07.055.300 I slot print_timing: id 0 | task 11748 | prompt eval time = 222.33 ms / 919 tokens ( 0.24 ms per token, 4133.57 tokens per second) 2.07.055.306 I slot print_timing: id 0 | task 11748 | eval time = 629.61 ms / 73 tokens ( 8.74 ms per token, 114.36 tokens per second) 2.07.055.307 I slot print_timing: id 0 | task 11748 | total time = 851.94 ms / 992 tokens 2.07.055.308 I slot print_timing: id 0 | task 11748 | graphs reused = 11309 2.07.055.309 I slot print_timing: id 0 | task 11748 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.055.362 I slot release: id 0 | task 11748 | stop processing: n_tokens = 1016, truncated = 0 2.07.086.695 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 126964762 2.07.086.775 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.476 MiB) 2.07.123.007 I slot launch_slot_: id 0 | task 11822 | processing task, is_child = 0 2.07.659.139 I slot print_timing: id 0 | task 11822 | prompt eval time = 201.93 ms / 865 tokens ( 0.23 ms per token, 4283.68 tokens per second) 2.07.659.145 I slot print_timing: id 0 | task 11822 | eval time = 334.19 ms / 39 tokens ( 8.79 ms per token, 113.71 tokens per second) 2.07.659.146 I slot print_timing: id 0 | task 11822 | total time = 536.12 ms / 904 tokens 2.07.659.146 I slot print_timing: id 0 | task 11822 | graphs reused = 11346 2.07.659.147 I slot print_timing: id 0 | task 11822 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.659.191 I slot release: id 0 | task 11822 | stop processing: n_tokens = 928, truncated = 0 2.07.687.275 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 127568590 2.07.687.358 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.507 MiB) 2.07.692.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.038 MiB) 2.07.726.346 I slot launch_slot_: id 0 | task 11862 | processing task, is_child = 0 2.10.839.964 I slot print_timing: id 0 | task 11862 | n_gen = 349, tg = 115.68 t/s, tg_3s = 116.01 t/s 2.12.679.085 I slot print_timing: id 0 | task 11862 | prompt eval time = 105.23 ms / 408 tokens ( 0.26 ms per token, 3877.15 tokens per second) 2.12.679.091 I slot print_timing: id 0 | task 11862 | eval time = 4847.49 ms / 561 tokens ( 8.66 ms per token, 115.52 tokens per second) 2.12.679.092 I slot print_timing: id 0 | task 11862 | total time = 4952.72 ms / 969 tokens 2.12.679.093 I slot print_timing: id 0 | task 11862 | graphs reused = 11903 2.12.679.094 I slot print_timing: id 0 | task 11862 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.679.125 I slot release: id 0 | task 11862 | stop processing: n_tokens = 993, truncated = 0 2.12.698.077 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 993, t_last = 132588524 2.12.698.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.225 MiB) 2.12.703.227 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.884 MiB) 2.12.740.365 I slot launch_slot_: id 0 | task 12424 | processing task, is_child = 0 2.14.829.015 I slot print_timing: id 0 | task 12424 | prompt eval time = 84.72 ms / 338 tokens ( 0.25 ms per token, 3989.75 tokens per second) 2.14.829.021 I slot print_timing: id 0 | task 12424 | eval time = 2003.92 ms / 234 tokens ( 8.60 ms per token, 116.27 tokens per second) 2.14.829.022 I slot print_timing: id 0 | task 12424 | total time = 2088.63 ms / 572 tokens 2.14.829.023 I slot print_timing: id 0 | task 12424 | graphs reused = 12134 2.14.829.024 I slot print_timing: id 0 | task 12424 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.829.052 I slot release: id 0 | task 12424 | stop processing: n_tokens = 598, truncated = 0 2.14.849.850 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 598, t_last = 134738451 2.14.849.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 2.14.876.585 I slot launch_slot_: id 0 | task 12659 | processing task, is_child = 0 2.17.969.253 I slot print_timing: id 0 | task 12659 | n_gen = 350, tg = 116.08 t/s, tg_3s = 116.41 t/s 2.20.974.400 I slot print_timing: id 0 | task 12659 | n_gen = 695, tg = 115.44 t/s, tg_3s = 114.80 t/s 2.23.881.842 I slot print_timing: id 0 | task 12659 | prompt eval time = 86.06 ms / 363 tokens ( 0.24 ms per token, 4218.13 tokens per second) 2.23.881.848 I slot print_timing: id 0 | task 12659 | eval time = 8919.18 ms / 1024 tokens ( 8.72 ms per token, 114.70 tokens per second) 2.23.881.849 I slot print_timing: id 0 | task 12659 | total time = 9005.24 ms / 1387 tokens 2.23.881.850 I slot print_timing: id 0 | task 12659 | graphs reused = 13152 2.23.881.850 I slot print_timing: id 0 | task 12659 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.881.879 I slot release: id 0 | task 12659 | stop processing: n_tokens = 1413, truncated = 0 2.23.886.242 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1413, t_last = 143791279 2.23.886.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.387 MiB) 2.23.895.379 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.413 MiB) 2.23.951.222 I slot launch_slot_: id 0 | task 13684 | processing task, is_child = 0 2.25.388.993 I slot print_timing: id 0 | task 13684 | prompt eval time = 78.72 ms / 317 tokens ( 0.25 ms per token, 4026.73 tokens per second) 2.25.388.998 I slot print_timing: id 0 | task 13684 | eval time = 1359.03 ms / 160 tokens ( 8.55 ms per token, 117.00 tokens per second) 2.25.389.000 I slot print_timing: id 0 | task 13684 | total time = 1437.75 ms / 477 tokens 2.25.389.000 I slot print_timing: id 0 | task 13684 | graphs reused = 13310 2.25.389.001 I slot print_timing: id 0 | task 13684 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.389.028 I slot release: id 0 | task 13684 | stop processing: n_tokens = 503, truncated = 0 2.25.408.926 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 145298427 2.25.408.986 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.791 MiB) 2.25.433.569 I slot launch_slot_: id 0 | task 13845 | processing task, is_child = 0 2.28.545.825 I slot print_timing: id 0 | task 13845 | n_gen = 350, tg = 116.05 t/s, tg_3s = 116.38 t/s 2.31.546.781 I slot print_timing: id 0 | task 13845 | n_gen = 692, tg = 115.01 t/s, tg_3s = 113.96 t/s 2.33.670.902 I slot print_timing: id 0 | task 13845 | prompt eval time = 104.79 ms / 389 tokens ( 0.27 ms per token, 3712.12 tokens per second) 2.33.670.909 I slot print_timing: id 0 | task 13845 | eval time = 8132.52 ms / 932 tokens ( 8.74 ms per token, 114.48 tokens per second) 2.33.670.910 I slot print_timing: id 0 | task 13845 | total time = 8237.32 ms / 1321 tokens 2.33.670.912 I slot print_timing: id 0 | task 13845 | graphs reused = 14236 2.33.670.913 I slot print_timing: id 0 | task 13845 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.670.943 I slot release: id 0 | task 13845 | stop processing: n_tokens = 1345, truncated = 0 2.33.675.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1345, t_last = 153580342 2.33.675.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.073 MiB) 2.33.735.206 I slot launch_slot_: id 0 | task 14778 | processing task, is_child = 0 2.34.186.080 I slot print_timing: id 0 | task 14778 | prompt eval time = 78.54 ms / 300 tokens ( 0.26 ms per token, 3819.52 tokens per second) 2.34.186.086 I slot print_timing: id 0 | task 14778 | eval time = 372.31 ms / 44 tokens ( 8.66 ms per token, 115.49 tokens per second) 2.34.186.087 I slot print_timing: id 0 | task 14778 | total time = 450.86 ms / 344 tokens 2.34.186.088 I slot print_timing: id 0 | task 14778 | graphs reused = 14278 2.34.186.089 I slot print_timing: id 0 | task 14778 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.186.115 I slot release: id 0 | task 14778 | stop processing: n_tokens = 368, truncated = 0 2.34.190.260 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 368, t_last = 154095514 2.34.190.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 86.101 MiB) 2.34.208.685 I slot launch_slot_: id 0 | task 14823 | processing task, is_child = 0 2.37.300.662 I slot print_timing: id 0 | task 14823 | n_gen = 350, tg = 116.08 t/s, tg_3s = 116.41 t/s 2.38.716.263 I slot print_timing: id 0 | task 14823 | prompt eval time = 85.47 ms / 341 tokens ( 0.25 ms per token, 3989.94 tokens per second) 2.38.716.269 I slot print_timing: id 0 | task 14823 | eval time = 4422.10 ms / 512 tokens ( 8.65 ms per token, 115.56 tokens per second) 2.38.716.271 I slot print_timing: id 0 | task 14823 | total time = 4507.57 ms / 853 tokens 2.38.716.271 I slot print_timing: id 0 | task 14823 | graphs reused = 14786 2.38.716.273 I slot print_timing: id 0 | task 14823 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.716.301 I slot release: id 0 | task 14823 | stop processing: n_tokens = 877, truncated = 0 2.38.744.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 158625700 2.38.744.647 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.509 MiB) 2.38.780.034 I slot launch_slot_: id 0 | task 15336 | processing task, is_child = 0 2.40.021.720 I slot print_timing: id 0 | task 15336 | prompt eval time = 79.17 ms / 332 tokens ( 0.24 ms per token, 4193.72 tokens per second) 2.40.021.726 I slot print_timing: id 0 | task 15336 | eval time = 1162.51 ms / 137 tokens ( 8.55 ms per token, 116.99 tokens per second) 2.40.021.727 I slot print_timing: id 0 | task 15336 | total time = 1241.67 ms / 469 tokens 2.40.021.728 I slot print_timing: id 0 | task 15336 | graphs reused = 14921 2.40.021.728 I slot print_timing: id 0 | task 15336 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.021.757 I slot release: id 0 | task 15336 | stop processing: n_tokens = 493, truncated = 0 2.40.040.533 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 159931156 2.40.040.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.980 MiB) 2.40.065.953 I slot launch_slot_: id 0 | task 15474 | processing task, is_child = 0 2.40.678.947 I slot print_timing: id 0 | task 15474 | prompt eval time = 72.15 ms / 269 tokens ( 0.27 ms per token, 3728.19 tokens per second) 2.40.678.952 I slot print_timing: id 0 | task 15474 | eval time = 540.82 ms / 64 tokens ( 8.58 ms per token, 116.49 tokens per second) 2.40.678.954 I slot print_timing: id 0 | task 15474 | total time = 612.98 ms / 333 tokens 2.40.678.955 I slot print_timing: id 0 | task 15474 | graphs reused = 14983 2.40.678.956 I slot print_timing: id 0 | task 15474 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.678.982 I slot release: id 0 | task 15474 | stop processing: n_tokens = 357, truncated = 0 2.40.695.364 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 357, t_last = 160588381 2.40.708.217 I slot launch_slot_: id 0 | task 15539 | processing task, is_child = 0 2.43.794.454 I slot print_timing: id 0 | task 15539 | n_gen = 349, tg = 115.97 t/s, tg_3s = 116.30 t/s 2.46.268.810 I slot print_timing: id 0 | task 15539 | prompt eval time = 85.36 ms / 341 tokens ( 0.25 ms per token, 3994.66 tokens per second) 2.46.268.815 I slot print_timing: id 0 | task 15539 | eval time = 5475.21 ms / 634 tokens ( 8.65 ms per token, 115.61 tokens per second) 2.46.268.816 I slot print_timing: id 0 | task 15539 | total time = 5560.58 ms / 975 tokens 2.46.268.817 I slot print_timing: id 0 | task 15539 | graphs reused = 15613 2.46.268.818 I slot print_timing: id 0 | task 15539 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.268.846 I slot release: id 0 | task 15539 | stop processing: n_tokens = 999, truncated = 0 2.46.288.661 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 999, t_last = 166178246 2.46.288.727 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 2.46.295.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.539 MiB) 2.46.332.410 I slot launch_slot_: id 0 | task 16174 | processing task, is_child = 0 2.49.418.474 I slot print_timing: id 0 | task 16174 | n_gen = 349, tg = 115.98 t/s, tg_3s = 116.31 t/s 2.49.461.718 I slot print_timing: id 0 | task 16174 | prompt eval time = 85.43 ms / 343 tokens ( 0.25 ms per token, 4015.03 tokens per second) 2.49.461.723 I slot print_timing: id 0 | task 16174 | eval time = 3043.86 ms / 354 tokens ( 8.62 ms per token, 115.97 tokens per second) 2.49.461.724 I slot print_timing: id 0 | task 16174 | total time = 3129.29 ms / 697 tokens 2.49.461.725 I slot print_timing: id 0 | task 16174 | graphs reused = 15964 2.49.461.725 I slot print_timing: id 0 | task 16174 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.461.754 I slot release: id 0 | task 16174 | stop processing: n_tokens = 721, truncated = 0 2.49.489.162 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 721, t_last = 169371153 2.49.489.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.163 MiB) 2.49.517.345 I slot launch_slot_: id 0 | task 16529 | processing task, is_child = 0 2.52.610.549 I slot print_timing: id 0 | task 16529 | n_gen = 350, tg = 116.03 t/s, tg_3s = 116.37 t/s 2.55.617.281 I slot print_timing: id 0 | task 16529 | n_gen = 695, tg = 115.39 t/s, tg_3s = 114.74 t/s 2.57.562.341 I slot print_timing: id 0 | task 16529 | prompt eval time = 85.47 ms / 347 tokens ( 0.25 ms per token, 4059.67 tokens per second) 2.57.562.347 I slot print_timing: id 0 | task 16529 | eval time = 7959.51 ms / 915 tokens ( 8.71 ms per token, 114.83 tokens per second) 2.57.562.348 I slot print_timing: id 0 | task 16529 | total time = 8044.98 ms / 1262 tokens 2.57.562.349 I slot print_timing: id 0 | task 16529 | graphs reused = 16873 2.57.562.350 I slot print_timing: id 0 | task 16529 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.562.378 I slot release: id 0 | task 16529 | stop processing: n_tokens = 1286, truncated = 0 2.57.566.566 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1286, t_last = 177471777 2.57.566.676 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.633 MiB) 2.57.572.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.883 MiB) 2.57.620.243 I slot launch_slot_: id 0 | task 17445 | processing task, is_child = 0 3.00.707.813 I slot print_timing: id 0 | task 17445 | n_gen = 350, tg = 116.02 t/s, tg_3s = 116.35 t/s 3.01.088.309 I slot print_timing: id 0 | task 17445 | prompt eval time = 79.37 ms / 332 tokens ( 0.24 ms per token, 4182.94 tokens per second) 3.01.088.315 I slot print_timing: id 0 | task 17445 | eval time = 3388.68 ms / 394 tokens ( 8.62 ms per token, 115.97 tokens per second) 3.01.088.316 I slot print_timing: id 0 | task 17445 | total time = 3468.05 ms / 726 tokens 3.01.088.317 I slot print_timing: id 0 | task 17445 | graphs reused = 17264 3.01.088.318 I slot print_timing: id 0 | task 17445 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.088.344 I slot release: id 0 | task 17445 | stop processing: n_tokens = 750, truncated = 0 3.01.108.727 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 180997743 3.01.108.795 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.447 MiB) 3.01.140.611 I slot launch_slot_: id 0 | task 17840 | processing task, is_child = 0 3.04.227.684 I slot print_timing: id 0 | task 17840 | n_gen = 350, tg = 116.03 t/s, tg_3s = 116.36 t/s 3.05.271.837 I slot print_timing: id 0 | task 17840 | prompt eval time = 79.20 ms / 332 tokens ( 0.24 ms per token, 4191.76 tokens per second) 3.05.271.843 I slot print_timing: id 0 | task 17840 | eval time = 4052.01 ms / 470 tokens ( 8.64 ms per token, 115.75 tokens per second) 3.05.271.844 I slot print_timing: id 0 | task 17840 | total time = 4131.21 ms / 802 tokens 3.05.271.845 I slot print_timing: id 0 | task 17840 | graphs reused = 17730 3.05.271.846 I slot print_timing: id 0 | task 17840 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.271.873 I slot release: id 0 | task 17840 | stop processing: n_tokens = 826, truncated = 0 3.05.291.329 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 185181272 3.05.291.398 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.258 MiB) 3.05.297.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.480 MiB) 3.05.332.189 I slot launch_slot_: id 0 | task 18311 | processing task, is_child = 0 3.08.418.684 I slot print_timing: id 0 | task 18311 | n_gen = 349, tg = 115.97 t/s, tg_3s = 116.31 t/s 3.09.342.802 I slot print_timing: id 0 | task 18311 | prompt eval time = 85.78 ms / 354 tokens ( 0.24 ms per token, 4126.98 tokens per second) 3.09.342.807 I slot print_timing: id 0 | task 18311 | eval time = 3924.82 ms / 453 tokens ( 8.68 ms per token, 115.16 tokens per second) 3.09.342.809 I slot print_timing: id 0 | task 18311 | total time = 4010.60 ms / 807 tokens 3.09.342.809 I slot print_timing: id 0 | task 18311 | graphs reused = 18179 3.09.342.810 I slot print_timing: id 0 | task 18311 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.342.838 I slot release: id 0 | task 18311 | stop processing: n_tokens = 831, truncated = 0 3.09.365.785 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 831, t_last = 189252238 3.09.365.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.227 MiB) 3.09.398.088 I slot launch_slot_: id 0 | task 18765 | processing task, is_child = 0 3.10.018.737 I slot print_timing: id 0 | task 18765 | prompt eval time = 86.04 ms / 354 tokens ( 0.24 ms per token, 4114.56 tokens per second) 3.10.018.743 I slot print_timing: id 0 | task 18765 | eval time = 534.60 ms / 63 tokens ( 8.62 ms per token, 115.98 tokens per second) 3.10.018.744 I slot print_timing: id 0 | task 18765 | total time = 620.63 ms / 417 tokens 3.10.018.745 I slot print_timing: id 0 | task 18765 | graphs reused = 18240 3.10.018.745 I slot print_timing: id 0 | task 18765 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.018.776 I slot release: id 0 | task 18765 | stop processing: n_tokens = 441, truncated = 0 3.10.037.403 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 441, t_last = 189928175 3.10.053.332 I slot launch_slot_: id 0 | task 18829 | processing task, is_child = 0 3.10.656.793 I slot print_timing: id 0 | task 18829 | prompt eval time = 85.14 ms / 339 tokens ( 0.25 ms per token, 3981.44 tokens per second) 3.10.656.799 I slot print_timing: id 0 | task 18829 | eval time = 518.30 ms / 61 tokens ( 8.64 ms per token, 115.76 tokens per second) 3.10.656.800 I slot print_timing: id 0 | task 18829 | total time = 603.44 ms / 400 tokens 3.10.656.801 I slot print_timing: id 0 | task 18829 | graphs reused = 18299 3.10.656.802 I slot print_timing: id 0 | task 18829 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.656.829 I slot release: id 0 | task 18829 | stop processing: n_tokens = 424, truncated = 0 3.10.676.795 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 190566229 3.10.676.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.259 MiB) 3.10.703.369 I slot launch_slot_: id 0 | task 18891 | processing task, is_child = 0 3.12.463.875 I slot print_timing: id 0 | task 18891 | prompt eval time = 85.66 ms / 351 tokens ( 0.24 ms per token, 4097.60 tokens per second) 3.12.463.880 I slot print_timing: id 0 | task 18891 | eval time = 1674.83 ms / 195 tokens ( 8.63 ms per token, 115.83 tokens per second) 3.12.463.881 I slot print_timing: id 0 | task 18891 | total time = 1760.49 ms / 546 tokens 3.12.463.882 I slot print_timing: id 0 | task 18891 | graphs reused = 18491 3.12.463.883 I slot print_timing: id 0 | task 18891 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.463.910 I slot release: id 0 | task 18891 | stop processing: n_tokens = 570, truncated = 0 3.12.485.334 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 570, t_last = 192373310 3.12.485.395 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.602 MiB) 3.12.512.583 I slot launch_slot_: id 0 | task 19087 | processing task, is_child = 0 3.13.817.942 I slot print_timing: id 0 | task 19087 | prompt eval time = 79.55 ms / 325 tokens ( 0.24 ms per token, 4085.58 tokens per second) 3.13.817.947 I slot print_timing: id 0 | task 19087 | eval time = 1225.80 ms / 144 tokens ( 8.57 ms per token, 116.66 tokens per second) 3.13.817.948 I slot print_timing: id 0 | task 19087 | total time = 1305.34 ms / 469 tokens 3.13.817.949 I slot print_timing: id 0 | task 19087 | graphs reused = 18633 3.13.817.950 I slot print_timing: id 0 | task 19087 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.817.977 I slot release: id 0 | task 19087 | stop processing: n_tokens = 493, truncated = 0 3.13.838.424 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 193727376 3.13.855.048 I slot launch_slot_: id 0 | task 19232 | processing task, is_child = 0 3.14.288.961 I slot print_timing: id 0 | task 19232 | prompt eval time = 78.58 ms / 308 tokens ( 0.26 ms per token, 3919.72 tokens per second) 3.14.288.967 I slot print_timing: id 0 | task 19232 | eval time = 355.32 ms / 42 tokens ( 8.67 ms per token, 115.39 tokens per second) 3.14.288.968 I slot print_timing: id 0 | task 19232 | total time = 433.90 ms / 350 tokens 3.14.288.970 I slot print_timing: id 0 | task 19232 | graphs reused = 18673 3.14.288.971 I slot print_timing: id 0 | task 19232 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.289.000 I slot release: id 0 | task 19232 | stop processing: n_tokens = 374, truncated = 0 3.14.307.521 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 374, t_last = 194198399 3.14.307.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 123.447 MiB) 3.14.328.548 I slot launch_slot_: id 0 | task 19275 | processing task, is_child = 0 3.17.263.019 I slot print_timing: id 0 | task 19275 | prompt eval time = 85.69 ms / 349 tokens ( 0.25 ms per token, 4072.73 tokens per second) 3.17.263.025 I slot print_timing: id 0 | task 19275 | eval time = 2848.76 ms / 331 tokens ( 8.63 ms per token, 115.84 tokens per second) 3.17.263.026 I slot print_timing: id 0 | task 19275 | total time = 2934.45 ms / 680 tokens 3.17.263.027 I slot print_timing: id 0 | task 19275 | graphs reused = 19001 3.17.263.028 I slot print_timing: id 0 | task 19275 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.263.061 I slot release: id 0 | task 19275 | stop processing: n_tokens = 704, truncated = 0 3.17.291.445 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 704, t_last = 197172460 3.17.291.511 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 143.918 MiB) 3.17.322.881 I slot launch_slot_: id 0 | task 19607 | processing task, is_child = 0 3.18.293.764 I slot print_timing: id 0 | task 19607 | prompt eval time = 85.49 ms / 371 tokens ( 0.23 ms per token, 4339.54 tokens per second) 3.18.293.770 I slot print_timing: id 0 | task 19607 | eval time = 885.37 ms / 104 tokens ( 8.60 ms per token, 116.34 tokens per second) 3.18.293.771 I slot print_timing: id 0 | task 19607 | total time = 970.87 ms / 475 tokens 3.18.293.772 I slot print_timing: id 0 | task 19607 | graphs reused = 19103 3.18.293.772 I slot print_timing: id 0 | task 19607 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.293.803 I slot release: id 0 | task 19607 | stop processing: n_tokens = 504, truncated = 0 3.18.316.319 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 198203202 3.18.333.103 I slot launch_slot_: id 0 | task 19712 | processing task, is_child = 0 3.21.412.796 I slot print_timing: id 0 | task 19712 | n_gen = 349, tg = 115.97 t/s, tg_3s = 116.30 t/s 3.24.412.841 I slot print_timing: id 0 | task 19712 | n_gen = 693, tg = 115.32 t/s, tg_3s = 114.66 t/s 3.25.035.113 I slot print_timing: id 0 | task 19712 | prompt eval time = 78.94 ms / 303 tokens ( 0.26 ms per token, 3838.46 tokens per second) 3.25.035.118 I slot print_timing: id 0 | task 19712 | eval time = 6623.06 ms / 763 tokens ( 8.69 ms per token, 115.05 tokens per second) 3.25.035.119 I slot print_timing: id 0 | task 19712 | total time = 6702.00 ms / 1066 tokens 3.25.035.120 I slot print_timing: id 0 | task 19712 | graphs reused = 19861 3.25.035.121 I slot print_timing: id 0 | task 19712 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.035.146 I slot release: id 0 | task 19712 | stop processing: n_tokens = 1090, truncated = 0 3.25.062.574 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1090, t_last = 204944546 3.25.062.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.423 MiB) 3.25.106.044 I slot launch_slot_: id 0 | task 20476 | processing task, is_child = 0 3.27.214.353 I slot print_timing: id 0 | task 20476 | prompt eval time = 78.61 ms / 312 tokens ( 0.25 ms per token, 3968.96 tokens per second) 3.27.214.358 I slot print_timing: id 0 | task 20476 | eval time = 2029.68 ms / 237 tokens ( 8.60 ms per token, 116.27 tokens per second) 3.27.214.359 I slot print_timing: id 0 | task 20476 | total time = 2108.29 ms / 549 tokens 3.27.214.360 I slot print_timing: id 0 | task 20476 | graphs reused = 20095 3.27.214.361 I slot print_timing: id 0 | task 20476 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.214.389 I slot release: id 0 | task 20476 | stop processing: n_tokens = 573, truncated = 0 3.27.237.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 573, t_last = 207123788 3.27.238.031 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.069 MiB) 3.27.259.523 I slot launch_slot_: id 0 | task 20714 | processing task, is_child = 0 3.30.110.688 I slot print_timing: id 0 | task 20714 | prompt eval time = 78.68 ms / 311 tokens ( 0.25 ms per token, 3952.77 tokens per second) 3.30.110.693 I slot print_timing: id 0 | task 20714 | eval time = 2772.47 ms / 323 tokens ( 8.61 ms per token, 116.14 tokens per second) 3.30.110.694 I slot print_timing: id 0 | task 20714 | total time = 2851.15 ms / 634 tokens 3.30.110.695 I slot print_timing: id 0 | task 20714 | graphs reused = 20415 3.30.110.696 I slot print_timing: id 0 | task 20714 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.110.721 I slot release: id 0 | task 20714 | stop processing: n_tokens = 658, truncated = 0 3.30.134.550 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 658, t_last = 210020120 3.30.134.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 3.30.158.515 I slot launch_slot_: id 0 | task 21038 | processing task, is_child = 0 3.33.246.272 I slot print_timing: id 0 | task 21038 | n_gen = 350, tg = 116.01 t/s, tg_3s = 116.34 t/s 3.35.634.263 I slot print_timing: id 0 | task 21038 | prompt eval time = 79.45 ms / 331 tokens ( 0.24 ms per token, 4166.30 tokens per second) 3.35.634.269 I slot print_timing: id 0 | task 21038 | eval time = 5396.29 ms / 625 tokens ( 8.65 ms per token, 115.64 tokens per second) 3.35.634.270 I slot print_timing: id 0 | task 21038 | total time = 5475.73 ms / 956 tokens 3.35.634.271 I slot print_timing: id 0 | task 21038 | graphs reused = 21036 3.35.634.271 I slot print_timing: id 0 | task 21038 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.634.299 I slot release: id 0 | task 21038 | stop processing: n_tokens = 980, truncated = 0 3.35.638.390 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 980, t_last = 215543698 3.35.638.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.256 MiB) 3.35.640.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.851 MiB) 3.35.673.577 I slot launch_slot_: id 0 | task 21664 | processing task, is_child = 0 3.36.961.184 I slot print_timing: id 0 | task 21664 | prompt eval time = 79.39 ms / 335 tokens ( 0.24 ms per token, 4219.52 tokens per second) 3.36.961.190 I slot print_timing: id 0 | task 21664 | eval time = 1208.20 ms / 142 tokens ( 8.57 ms per token, 116.70 tokens per second) 3.36.961.191 I slot print_timing: id 0 | task 21664 | total time = 1287.59 ms / 477 tokens 3.36.961.192 I slot print_timing: id 0 | task 21664 | graphs reused = 21176 3.36.961.193 I slot print_timing: id 0 | task 21664 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.961.221 I slot release: id 0 | task 21664 | stop processing: n_tokens = 501, truncated = 0 3.36.980.867 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 216870620 3.36.980.922 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.382 MiB) 3.37.000.711 I slot launch_slot_: id 0 | task 21807 | processing task, is_child = 0 3.40.087.562 I slot print_timing: id 0 | task 21807 | n_gen = 350, tg = 116.05 t/s, tg_3s = 116.38 t/s 3.42.978.791 I slot print_timing: id 0 | task 21807 | prompt eval time = 79.41 ms / 331 tokens ( 0.24 ms per token, 4168.08 tokens per second) 3.42.978.796 I slot print_timing: id 0 | task 21807 | eval time = 5898.65 ms / 682 tokens ( 8.66 ms per token, 115.45 tokens per second) 3.42.978.798 I slot print_timing: id 0 | task 21807 | total time = 5978.07 ms / 1013 tokens 3.42.978.798 I slot print_timing: id 0 | task 21807 | graphs reused = 21853 3.42.978.799 I slot print_timing: id 0 | task 21807 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.978.826 I slot release: id 0 | task 21807 | stop processing: n_tokens = 1037, truncated = 0 3.42.996.771 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1037, t_last = 222888225 3.42.996.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.852 MiB) 3.42.999.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.537 MiB) 3.43.035.953 I slot launch_slot_: id 0 | task 22490 | processing task, is_child = 0 3.43.871.829 I slot print_timing: id 0 | task 22490 | prompt eval time = 79.37 ms / 328 tokens ( 0.24 ms per token, 4132.60 tokens per second) 3.43.871.835 I slot print_timing: id 0 | task 22490 | eval time = 756.49 ms / 89 tokens ( 8.60 ms per token, 116.33 tokens per second) 3.43.871.836 I slot print_timing: id 0 | task 22490 | total time = 835.86 ms / 417 tokens 3.43.871.837 I slot print_timing: id 0 | task 22490 | graphs reused = 21940 3.43.871.838 I slot print_timing: id 0 | task 22490 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.871.864 I slot release: id 0 | task 22490 | stop processing: n_tokens = 441, truncated = 0 3.43.875.979 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 441, t_last = 223781264 3.43.876.033 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 3.43.893.404 I slot launch_slot_: id 0 | task 22580 | processing task, is_child = 0 3.46.977.140 I slot print_timing: id 0 | task 22580 | n_gen = 349, tg = 115.84 t/s, tg_3s = 116.17 t/s 3.49.984.183 I slot print_timing: id 0 | task 22580 | n_gen = 694, tg = 115.28 t/s, tg_3s = 114.73 t/s 3.51.431.498 I slot print_timing: id 0 | task 22580 | prompt eval time = 79.47 ms / 331 tokens ( 0.24 ms per token, 4165.09 tokens per second) 3.51.431.504 I slot print_timing: id 0 | task 22580 | eval time = 7458.61 ms / 858 tokens ( 8.70 ms per token, 114.90 tokens per second) 3.51.431.505 I slot print_timing: id 0 | task 22580 | total time = 7538.08 ms / 1189 tokens 3.51.431.505 I slot print_timing: id 0 | task 22580 | graphs reused = 22793 3.51.431.506 I slot print_timing: id 0 | task 22580 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.431.532 I slot release: id 0 | task 22580 | stop processing: n_tokens = 1213, truncated = 0 3.51.435.909 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1213, t_last = 231340931 3.51.436.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 3.51.438.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.601 MiB) 3.51.440.896 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 3.51.483.397 I slot launch_slot_: id 0 | task 23439 | processing task, is_child = 0 3.52.026.728 I slot print_timing: id 0 | task 23439 | prompt eval time = 85.75 ms / 348 tokens ( 0.25 ms per token, 4058.55 tokens per second) 3.52.026.735 I slot print_timing: id 0 | task 23439 | eval time = 457.57 ms / 54 tokens ( 8.63 ms per token, 115.83 tokens per second) 3.52.026.736 I slot print_timing: id 0 | task 23439 | total time = 543.31 ms / 402 tokens 3.52.026.737 I slot print_timing: id 0 | task 23439 | graphs reused = 22845 3.52.026.738 I slot print_timing: id 0 | task 23439 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.026.770 I slot release: id 0 | task 23439 | stop processing: n_tokens = 426, truncated = 0 3.52.042.990 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 231936169 3.52.057.707 I slot launch_slot_: id 0 | task 23494 | processing task, is_child = 0 3.52.585.915 I slot print_timing: id 0 | task 23494 | prompt eval time = 79.53 ms / 332 tokens ( 0.24 ms per token, 4174.26 tokens per second) 3.52.585.922 I slot print_timing: id 0 | task 23494 | eval time = 448.66 ms / 53 tokens ( 8.63 ms per token, 115.90 tokens per second) 3.52.585.923 I slot print_timing: id 0 | task 23494 | total time = 528.19 ms / 385 tokens 3.52.585.923 I slot print_timing: id 0 | task 23494 | graphs reused = 22896 3.52.585.924 I slot print_timing: id 0 | task 23494 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.585.953 I slot release: id 0 | task 23494 | stop processing: n_tokens = 411, truncated = 0 3.52.602.191 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 232495352 3.52.602.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.476 MiB) 3.52.619.652 I slot launch_slot_: id 0 | task 23548 | processing task, is_child = 0 3.55.706.182 I slot print_timing: id 0 | task 23548 | n_gen = 349, tg = 115.95 t/s, tg_3s = 116.29 t/s 3.56.121.383 I slot print_timing: id 0 | task 23548 | prompt eval time = 85.29 ms / 339 tokens ( 0.25 ms per token, 3974.53 tokens per second) 3.56.121.389 I slot print_timing: id 0 | task 23548 | eval time = 3416.42 ms / 397 tokens ( 8.63 ms per token, 115.91 tokens per second) 3.56.121.390 I slot print_timing: id 0 | task 23548 | total time = 3501.71 ms / 736 tokens 3.56.121.391 I slot print_timing: id 0 | task 23548 | graphs reused = 23290 3.56.121.391 I slot print_timing: id 0 | task 23548 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.121.419 I slot release: id 0 | task 23548 | stop processing: n_tokens = 760, truncated = 0 3.56.141.114 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 236030818 3.56.141.187 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.601 MiB) 3.56.143.724 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 3.56.170.915 I slot launch_slot_: id 0 | task 23946 | processing task, is_child = 0 3.56.764.825 I slot print_timing: id 0 | task 23946 | prompt eval time = 85.42 ms / 343 tokens ( 0.25 ms per token, 4015.69 tokens per second) 3.56.764.831 I slot print_timing: id 0 | task 23946 | eval time = 508.48 ms / 60 tokens ( 8.62 ms per token, 116.03 tokens per second) 3.56.764.832 I slot print_timing: id 0 | task 23946 | total time = 593.89 ms / 403 tokens 3.56.764.833 I slot print_timing: id 0 | task 23946 | graphs reused = 23348 3.56.764.833 I slot print_timing: id 0 | task 23946 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.764.866 I slot release: id 0 | task 23946 | stop processing: n_tokens = 427, truncated = 0 3.56.781.961 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 236674265 3.56.782.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.976 MiB) 3.56.799.723 I slot launch_slot_: id 0 | task 24007 | processing task, is_child = 0 3.59.892.802 I slot print_timing: id 0 | task 24007 | n_gen = 348, tg = 115.39 t/s, tg_3s = 115.72 t/s 4.01.158.932 I slot print_timing: id 0 | task 24007 | prompt eval time = 85.92 ms / 360 tokens ( 0.24 ms per token, 4190.09 tokens per second) 4.01.158.937 I slot print_timing: id 0 | task 24007 | eval time = 4273.28 ms / 493 tokens ( 8.69 ms per token, 115.13 tokens per second) 4.01.158.938 I slot print_timing: id 0 | task 24007 | total time = 4359.20 ms / 853 tokens 4.01.158.939 I slot print_timing: id 0 | task 24007 | graphs reused = 23837 4.01.158.940 I slot print_timing: id 0 | task 24007 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.158.970 I slot release: id 0 | task 24007 | stop processing: n_tokens = 877, truncated = 0 4.01.163.183 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 241068369 4.01.163.255 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.694 MiB) 4.01.192.993 I slot launch_slot_: id 0 | task 24501 | processing task, is_child = 0 4.01.967.561 I slot print_timing: id 0 | task 24501 | prompt eval time = 85.35 ms / 341 tokens ( 0.25 ms per token, 3995.22 tokens per second) 4.01.967.566 I slot print_timing: id 0 | task 24501 | eval time = 689.20 ms / 81 tokens ( 8.61 ms per token, 116.08 tokens per second) 4.01.967.568 I slot print_timing: id 0 | task 24501 | total time = 774.55 ms / 422 tokens 4.01.967.569 I slot print_timing: id 0 | task 24501 | graphs reused = 23916 4.01.967.569 I slot print_timing: id 0 | task 24501 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.967.600 I slot release: id 0 | task 24501 | stop processing: n_tokens = 446, truncated = 0 4.01.992.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 241876999 4.01.992.548 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.412 MiB) 4.02.010.376 I slot launch_slot_: id 0 | task 24583 | processing task, is_child = 0 4.03.804.040 I slot print_timing: id 0 | task 24583 | prompt eval time = 85.90 ms / 358 tokens ( 0.24 ms per token, 4167.44 tokens per second) 4.03.804.046 I slot print_timing: id 0 | task 24583 | eval time = 1707.74 ms / 199 tokens ( 8.62 ms per token, 115.94 tokens per second) 4.03.804.048 I slot print_timing: id 0 | task 24583 | total time = 1793.65 ms / 557 tokens 4.03.804.048 I slot print_timing: id 0 | task 24583 | graphs reused = 24112 4.03.804.049 I slot print_timing: id 0 | task 24583 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.804.081 I slot release: id 0 | task 24583 | stop processing: n_tokens = 581, truncated = 0 4.03.808.249 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 581, t_last = 243713480 4.03.808.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.694 MiB) 4.03.810.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.631 MiB) 4.03.833.312 I slot launch_slot_: id 0 | task 24783 | processing task, is_child = 0 4.04.771.128 I slot print_timing: id 0 | task 24783 | prompt eval time = 85.94 ms / 358 tokens ( 0.24 ms per token, 4165.79 tokens per second) 4.04.771.135 I slot print_timing: id 0 | task 24783 | eval time = 851.86 ms / 99 tokens ( 8.69 ms per token, 115.04 tokens per second) 4.04.771.136 I slot print_timing: id 0 | task 24783 | total time = 937.80 ms / 457 tokens 4.04.771.137 I slot print_timing: id 0 | task 24783 | graphs reused = 24209 4.04.771.138 I slot print_timing: id 0 | task 24783 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.771.171 I slot release: id 0 | task 24783 | stop processing: n_tokens = 484, truncated = 0 4.04.797.138 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 484, t_last = 244680570 4.04.797.191 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.632 MiB) 4.04.816.826 I slot launch_slot_: id 0 | task 24883 | processing task, is_child = 0 4.05.915.154 I slot print_timing: id 0 | task 24883 | prompt eval time = 104.78 ms / 387 tokens ( 0.27 ms per token, 3693.42 tokens per second) 4.05.915.159 I slot print_timing: id 0 | task 24883 | eval time = 993.53 ms / 116 tokens ( 8.64 ms per token, 115.75 tokens per second) 4.05.915.160 I slot print_timing: id 0 | task 24883 | total time = 1098.31 ms / 503 tokens 4.05.915.161 I slot print_timing: id 0 | task 24883 | graphs reused = 24322 4.05.915.162 I slot print_timing: id 0 | task 24883 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.915.191 I slot release: id 0 | task 24883 | stop processing: n_tokens = 527, truncated = 0 4.05.943.282 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 527, t_last = 245824590 4.05.943.339 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.288 MiB) 4.05.963.565 I slot launch_slot_: id 0 | task 25000 | processing task, is_child = 0 4.06.560.294 I slot print_timing: id 0 | task 25000 | prompt eval time = 79.39 ms / 333 tokens ( 0.24 ms per token, 4194.38 tokens per second) 4.06.560.300 I slot print_timing: id 0 | task 25000 | eval time = 517.32 ms / 61 tokens ( 8.62 ms per token, 115.98 tokens per second) 4.06.560.301 I slot print_timing: id 0 | task 25000 | total time = 596.71 ms / 394 tokens 4.06.560.302 I slot print_timing: id 0 | task 25000 | graphs reused = 24381 4.06.560.303 I slot print_timing: id 0 | task 25000 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.560.329 I slot release: id 0 | task 25000 | stop processing: n_tokens = 418, truncated = 0