$ 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-Q8_0.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.087.694 I srv llama_server: initializing ... 0.00.087.700 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.087.903 I srv init_listene: The UI is disabled 0.00.087.906 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.087.986 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) 0.00.103.310 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--bartowski--granite-4.2-8b-GGUF\snapshots\a592100df8fe4931c7cffbac7b28e8176a1d52da\granite-4.2-8b-Q8_0.gguf' 0.03.599.651 I cmn init: llama threadpool init, n_threads = 8 0.03.680.256 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.03.685.021 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.03.685.040 I srv llama_server: model loaded 0.03.685.043 I srv llama_server: listening on http://127.0.0.1:8089 0.04.584.912 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.585.085 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.617.370 I slot print_timing: id 0 | task 0 | prompt eval time = 89.00 ms / 368 tokens ( 0.24 ms per token, 4134.60 tokens per second) 0.05.617.376 I slot print_timing: id 0 | task 0 | eval time = 943.26 ms / 61 tokens ( 15.72 ms per token, 63.61 tokens per second) 0.05.617.377 I slot print_timing: id 0 | task 0 | total time = 1032.26 ms / 429 tokens 0.05.617.384 I slot print_timing: id 0 | task 0 | graphs reused = 60 0.05.617.384 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.617.414 I slot release: id 0 | task 0 | stop processing: n_tokens = 428, truncated = 0 0.05.621.410 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 5531656 0.05.640.230 I slot launch_slot_: id 0 | task 62 | processing task, is_child = 0 0.06.387.751 I slot print_timing: id 0 | task 62 | prompt eval time = 73.38 ms / 292 tokens ( 0.25 ms per token, 3979.29 tokens per second) 0.06.387.757 I slot print_timing: id 0 | task 62 | eval time = 674.13 ms / 44 tokens ( 15.68 ms per token, 63.79 tokens per second) 0.06.387.758 I slot print_timing: id 0 | task 62 | total time = 747.51 ms / 336 tokens 0.06.387.758 I slot print_timing: id 0 | task 62 | graphs reused = 102 0.06.387.759 I slot print_timing: id 0 | task 62 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.387.784 I slot release: id 0 | task 62 | stop processing: n_tokens = 360, truncated = 0 0.06.413.587 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 360, t_last = 6302026 0.06.426.056 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.07.194.838 I slot print_timing: id 0 | task 107 | prompt eval time = 79.79 ms / 338 tokens ( 0.24 ms per token, 4236.23 tokens per second) 0.07.194.844 I slot print_timing: id 0 | task 107 | eval time = 688.98 ms / 45 tokens ( 15.66 ms per token, 63.86 tokens per second) 0.07.194.845 I slot print_timing: id 0 | task 107 | total time = 768.77 ms / 383 tokens 0.07.194.846 I slot print_timing: id 0 | task 107 | graphs reused = 145 0.07.194.848 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.194.878 I slot release: id 0 | task 107 | stop processing: n_tokens = 407, truncated = 0 0.07.208.616 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 7109120 0.07.222.333 I slot launch_slot_: id 0 | task 153 | processing task, is_child = 0 0.08.007.643 I slot print_timing: id 0 | task 153 | prompt eval time = 80.38 ms / 371 tokens ( 0.22 ms per token, 4615.81 tokens per second) 0.08.007.650 I slot print_timing: id 0 | task 153 | eval time = 704.92 ms / 46 tokens ( 15.66 ms per token, 63.84 tokens per second) 0.08.007.651 I slot print_timing: id 0 | task 153 | total time = 785.30 ms / 417 tokens 0.08.007.651 I slot print_timing: id 0 | task 153 | graphs reused = 189 0.08.007.652 I slot print_timing: id 0 | task 153 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.007.681 I slot release: id 0 | task 153 | stop processing: n_tokens = 441, truncated = 0 0.08.021.305 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 0.08.036.916 I slot launch_slot_: id 0 | task 200 | processing task, is_child = 0 0.09.055.946 I slot print_timing: id 0 | task 200 | prompt eval time = 80.54 ms / 345 tokens ( 0.23 ms per token, 4283.59 tokens per second) 0.09.055.951 I slot print_timing: id 0 | task 200 | eval time = 938.47 ms / 61 tokens ( 15.64 ms per token, 63.93 tokens per second) 0.09.055.952 I slot print_timing: id 0 | task 200 | total time = 1019.01 ms / 406 tokens 0.09.055.954 I slot print_timing: id 0 | task 200 | graphs reused = 248 0.09.055.955 I slot print_timing: id 0 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.055.983 I slot release: id 0 | task 200 | stop processing: n_tokens = 445, truncated = 0 0.09.060.113 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 445, t_last = 8970225 0.09.076.209 I slot launch_slot_: id 0 | task 262 | processing task, is_child = 0 0.10.144.690 I slot print_timing: id 0 | task 262 | prompt eval time = 80.85 ms / 351 tokens ( 0.23 ms per token, 4341.27 tokens per second) 0.10.144.696 I slot print_timing: id 0 | task 262 | eval time = 987.61 ms / 64 tokens ( 15.68 ms per token, 63.79 tokens per second) 0.10.144.697 I slot print_timing: id 0 | task 262 | total time = 1068.46 ms / 415 tokens 0.10.144.698 I slot print_timing: id 0 | task 262 | graphs reused = 310 0.10.144.699 I slot print_timing: id 0 | task 262 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.144.726 I slot release: id 0 | task 262 | stop processing: n_tokens = 439, truncated = 0 0.10.168.948 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 10058968 0.10.184.338 I slot launch_slot_: id 0 | task 327 | processing task, is_child = 0 0.11.190.315 I slot print_timing: id 0 | task 327 | prompt eval time = 101.02 ms / 395 tokens ( 0.26 ms per token, 3910.23 tokens per second) 0.11.190.321 I slot print_timing: id 0 | task 327 | eval time = 904.94 ms / 58 tokens ( 15.88 ms per token, 62.99 tokens per second) 0.11.190.322 I slot print_timing: id 0 | task 327 | total time = 1005.96 ms / 453 tokens 0.11.190.323 I slot print_timing: id 0 | task 327 | graphs reused = 366 0.11.190.324 I slot print_timing: id 0 | task 327 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.190.352 I slot release: id 0 | task 327 | stop processing: n_tokens = 477, truncated = 0 0.11.208.479 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 477, t_last = 11104594 0.11.224.081 I slot launch_slot_: id 0 | task 386 | processing task, is_child = 0 0.12.445.584 I slot print_timing: id 0 | task 386 | prompt eval time = 103.02 ms / 446 tokens ( 0.23 ms per token, 4329.09 tokens per second) 0.12.445.590 I slot print_timing: id 0 | task 386 | eval time = 1118.46 ms / 72 tokens ( 15.75 ms per token, 63.48 tokens per second) 0.12.445.591 I slot print_timing: id 0 | task 386 | total time = 1221.49 ms / 518 tokens 0.12.445.592 I slot print_timing: id 0 | task 386 | graphs reused = 435 0.12.445.593 I slot print_timing: id 0 | task 386 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.445.623 I slot release: id 0 | task 386 | stop processing: n_tokens = 542, truncated = 0 0.12.470.780 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 12359865 0.12.488.922 I slot launch_slot_: id 0 | task 459 | processing task, is_child = 0 0.13.360.911 I slot print_timing: id 0 | task 459 | prompt eval time = 73.72 ms / 319 tokens ( 0.23 ms per token, 4327.36 tokens per second) 0.13.360.916 I slot print_timing: id 0 | task 459 | eval time = 798.25 ms / 52 tokens ( 15.65 ms per token, 63.89 tokens per second) 0.13.360.917 I slot print_timing: id 0 | task 459 | total time = 871.97 ms / 371 tokens 0.13.360.918 I slot print_timing: id 0 | task 459 | graphs reused = 485 0.13.360.919 I slot print_timing: id 0 | task 459 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.360.948 I slot release: id 0 | task 459 | stop processing: n_tokens = 395, truncated = 0 0.13.376.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 13275190 0.13.390.198 I slot launch_slot_: id 0 | task 512 | processing task, is_child = 0 0.14.107.284 I slot print_timing: id 0 | task 512 | prompt eval time = 74.46 ms / 336 tokens ( 0.22 ms per token, 4512.67 tokens per second) 0.14.107.289 I slot print_timing: id 0 | task 512 | eval time = 642.61 ms / 42 tokens ( 15.67 ms per token, 63.80 tokens per second) 0.14.107.290 I slot print_timing: id 0 | task 512 | total time = 717.07 ms / 378 tokens 0.14.107.291 I slot print_timing: id 0 | task 512 | graphs reused = 525 0.14.107.292 I slot print_timing: id 0 | task 512 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.107.318 I slot release: id 0 | task 512 | stop processing: n_tokens = 402, truncated = 0 0.14.125.706 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 14021561 0.14.139.644 I slot launch_slot_: id 0 | task 555 | processing task, is_child = 0 0.15.277.428 I slot print_timing: id 0 | task 555 | prompt eval time = 80.41 ms / 352 tokens ( 0.23 ms per token, 4377.78 tokens per second) 0.15.277.433 I slot print_timing: id 0 | task 555 | eval time = 1057.36 ms / 68 tokens ( 15.78 ms per token, 63.37 tokens per second) 0.15.277.434 I slot print_timing: id 0 | task 555 | total time = 1137.77 ms / 420 tokens 0.15.277.436 I slot print_timing: id 0 | task 555 | graphs reused = 591 0.15.277.436 I slot print_timing: id 0 | task 555 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.277.464 I slot release: id 0 | task 555 | stop processing: n_tokens = 444, truncated = 0 0.15.294.246 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 15191706 0.15.309.772 I slot launch_slot_: id 0 | task 624 | processing task, is_child = 0 0.16.211.129 I slot print_timing: id 0 | task 624 | prompt eval time = 100.72 ms / 387 tokens ( 0.26 ms per token, 3842.30 tokens per second) 0.16.211.134 I slot print_timing: id 0 | task 624 | eval time = 800.62 ms / 52 tokens ( 15.70 ms per token, 63.70 tokens per second) 0.16.211.135 I slot print_timing: id 0 | task 624 | total time = 901.34 ms / 439 tokens 0.16.211.136 I slot print_timing: id 0 | task 624 | graphs reused = 641 0.16.211.137 I slot print_timing: id 0 | task 624 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.211.167 I slot release: id 0 | task 624 | stop processing: n_tokens = 463, truncated = 0 0.16.230.640 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 463, t_last = 16125409 0.16.247.214 I slot launch_slot_: id 0 | task 677 | processing task, is_child = 0 0.17.313.025 I slot print_timing: id 0 | task 677 | prompt eval time = 80.52 ms / 349 tokens ( 0.23 ms per token, 4334.54 tokens per second) 0.17.313.030 I slot print_timing: id 0 | task 677 | eval time = 985.27 ms / 64 tokens ( 15.64 ms per token, 63.94 tokens per second) 0.17.313.032 I slot print_timing: id 0 | task 677 | total time = 1065.79 ms / 413 tokens 0.17.313.032 I slot print_timing: id 0 | task 677 | graphs reused = 703 0.17.313.033 I slot print_timing: id 0 | task 677 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.313.061 I slot release: id 0 | task 677 | stop processing: n_tokens = 437, truncated = 0 0.17.338.483 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 17227304 0.17.353.730 I slot launch_slot_: id 0 | task 742 | processing task, is_child = 0 0.18.329.063 I slot print_timing: id 0 | task 742 | prompt eval time = 80.40 ms / 352 tokens ( 0.23 ms per token, 4378.33 tokens per second) 0.18.329.068 I slot print_timing: id 0 | task 742 | eval time = 894.92 ms / 57 tokens ( 15.98 ms per token, 62.58 tokens per second) 0.18.329.069 I slot print_timing: id 0 | task 742 | total time = 975.32 ms / 409 tokens 0.18.329.070 I slot print_timing: id 0 | task 742 | graphs reused = 758 0.18.329.071 I slot print_timing: id 0 | task 742 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.329.099 I slot release: id 0 | task 742 | stop processing: n_tokens = 433, truncated = 0 0.18.348.836 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 18243341 0.18.363.662 I slot launch_slot_: id 0 | task 800 | processing task, is_child = 0 0.19.500.382 I slot print_timing: id 0 | task 800 | prompt eval time = 80.10 ms / 347 tokens ( 0.23 ms per token, 4331.92 tokens per second) 0.19.500.387 I slot print_timing: id 0 | task 800 | eval time = 1056.60 ms / 68 tokens ( 15.77 ms per token, 63.41 tokens per second) 0.19.500.388 I slot print_timing: id 0 | task 800 | total time = 1136.70 ms / 415 tokens 0.19.500.389 I slot print_timing: id 0 | task 800 | graphs reused = 824 0.19.500.390 I slot print_timing: id 0 | task 800 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.500.417 I slot release: id 0 | task 800 | stop processing: n_tokens = 439, truncated = 0 0.19.522.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 19414660 0.19.536.993 I slot launch_slot_: id 0 | task 869 | processing task, is_child = 0 0.20.471.356 I slot print_timing: id 0 | task 869 | prompt eval time = 73.64 ms / 320 tokens ( 0.23 ms per token, 4345.46 tokens per second) 0.20.471.361 I slot print_timing: id 0 | task 869 | eval time = 860.71 ms / 56 tokens ( 15.65 ms per token, 63.90 tokens per second) 0.20.471.362 I slot print_timing: id 0 | task 869 | total time = 934.35 ms / 376 tokens 0.20.471.363 I slot print_timing: id 0 | task 869 | graphs reused = 878 0.20.471.364 I slot print_timing: id 0 | task 869 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.471.398 I slot release: id 0 | task 869 | stop processing: n_tokens = 400, truncated = 0 0.20.497.752 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 20385640 0.20.511.467 I slot launch_slot_: id 0 | task 926 | processing task, is_child = 0 0.21.265.005 I slot print_timing: id 0 | task 926 | prompt eval time = 80.08 ms / 343 tokens ( 0.23 ms per token, 4283.27 tokens per second) 0.21.265.011 I slot print_timing: id 0 | task 926 | eval time = 673.44 ms / 44 tokens ( 15.66 ms per token, 63.85 tokens per second) 0.21.265.012 I slot print_timing: id 0 | task 926 | total time = 753.52 ms / 387 tokens 0.21.265.012 I slot print_timing: id 0 | task 926 | graphs reused = 920 0.21.265.013 I slot print_timing: id 0 | task 926 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.265.040 I slot release: id 0 | task 926 | stop processing: n_tokens = 411, truncated = 0 0.21.283.494 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 21179282 0.21.297.257 I slot launch_slot_: id 0 | task 971 | processing task, is_child = 0 0.22.045.672 I slot print_timing: id 0 | task 971 | prompt eval time = 74.32 ms / 325 tokens ( 0.23 ms per token, 4373.10 tokens per second) 0.22.045.678 I slot print_timing: id 0 | task 971 | eval time = 674.08 ms / 44 tokens ( 15.68 ms per token, 63.79 tokens per second) 0.22.045.679 I slot print_timing: id 0 | task 971 | total time = 748.40 ms / 369 tokens 0.22.045.679 I slot print_timing: id 0 | task 971 | graphs reused = 962 0.22.045.680 I slot print_timing: id 0 | task 971 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.045.707 I slot release: id 0 | task 971 | stop processing: n_tokens = 393, truncated = 0 0.22.065.676 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 21959949 0.22.079.254 I slot launch_slot_: id 0 | task 1016 | processing task, is_child = 0 0.22.818.021 I slot print_timing: id 0 | task 1016 | prompt eval time = 74.41 ms / 323 tokens ( 0.23 ms per token, 4341.11 tokens per second) 0.22.818.027 I slot print_timing: id 0 | task 1016 | eval time = 664.34 ms / 43 tokens ( 15.82 ms per token, 63.22 tokens per second) 0.22.818.028 I slot print_timing: id 0 | task 1016 | total time = 738.75 ms / 366 tokens 0.22.818.029 I slot print_timing: id 0 | task 1016 | graphs reused = 1003 0.22.818.030 I slot print_timing: id 0 | task 1016 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.818.064 I slot release: id 0 | task 1016 | stop processing: n_tokens = 390, truncated = 0 0.22.822.622 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 390, t_last = 22732306 0.22.838.342 I slot launch_slot_: id 0 | task 1060 | processing task, is_child = 0 0.24.030.408 I slot print_timing: id 0 | task 1060 | prompt eval time = 84.28 ms / 359 tokens ( 0.23 ms per token, 4259.61 tokens per second) 0.24.030.414 I slot print_timing: id 0 | task 1060 | eval time = 1107.76 ms / 69 tokens ( 16.29 ms per token, 61.38 tokens per second) 0.24.030.415 I slot print_timing: id 0 | task 1060 | total time = 1192.04 ms / 428 tokens 0.24.030.416 I slot print_timing: id 0 | task 1060 | graphs reused = 1070 0.24.030.417 I slot print_timing: id 0 | task 1060 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.030.447 I slot release: id 0 | task 1060 | stop processing: n_tokens = 452, truncated = 0 0.24.052.516 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 23944689 0.24.068.124 I slot launch_slot_: id 0 | task 1130 | processing task, is_child = 0 0.25.114.666 I slot print_timing: id 0 | task 1130 | prompt eval time = 74.53 ms / 334 tokens ( 0.22 ms per token, 4481.54 tokens per second) 0.25.114.672 I slot print_timing: id 0 | task 1130 | eval time = 972.00 ms / 63 tokens ( 15.68 ms per token, 63.79 tokens per second) 0.25.114.673 I slot print_timing: id 0 | task 1130 | total time = 1046.52 ms / 397 tokens 0.25.114.674 I slot print_timing: id 0 | task 1130 | graphs reused = 1131 0.25.114.675 I slot print_timing: id 0 | task 1130 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.114.703 I slot release: id 0 | task 1130 | stop processing: n_tokens = 421, truncated = 0 0.25.118.931 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 25028945 0.25.133.408 I slot launch_slot_: id 0 | task 1194 | processing task, is_child = 0 0.26.341.677 I slot print_timing: id 0 | task 1194 | prompt eval time = 80.40 ms / 382 tokens ( 0.21 ms per token, 4751.24 tokens per second) 0.26.341.683 I slot print_timing: id 0 | task 1194 | eval time = 1127.85 ms / 73 tokens ( 15.66 ms per token, 63.84 tokens per second) 0.26.341.684 I slot print_timing: id 0 | task 1194 | total time = 1208.25 ms / 455 tokens 0.26.341.685 I slot print_timing: id 0 | task 1194 | graphs reused = 1202 0.26.341.686 I slot print_timing: id 0 | task 1194 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.341.717 I slot release: id 0 | task 1194 | stop processing: n_tokens = 479, truncated = 0 0.26.359.939 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 26255959 0.26.376.153 I slot launch_slot_: id 0 | task 1268 | processing task, is_child = 0 0.27.459.603 I slot print_timing: id 0 | task 1268 | prompt eval time = 80.80 ms / 368 tokens ( 0.22 ms per token, 4554.29 tokens per second) 0.27.459.608 I slot print_timing: id 0 | task 1268 | eval time = 1002.63 ms / 65 tokens ( 15.67 ms per token, 63.83 tokens per second) 0.27.459.609 I slot print_timing: id 0 | task 1268 | total time = 1083.43 ms / 433 tokens 0.27.459.610 I slot print_timing: id 0 | task 1268 | graphs reused = 1265 0.27.459.611 I slot print_timing: id 0 | task 1268 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.459.644 I slot release: id 0 | task 1268 | stop processing: n_tokens = 457, truncated = 0 0.27.481.036 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 27373887 0.27.496.811 I slot launch_slot_: id 0 | task 1334 | processing task, is_child = 0 0.28.922.509 I slot print_timing: id 0 | task 1334 | prompt eval time = 80.53 ms / 382 tokens ( 0.21 ms per token, 4743.40 tokens per second) 0.28.922.515 I slot print_timing: id 0 | task 1334 | eval time = 1345.15 ms / 87 tokens ( 15.64 ms per token, 63.93 tokens per second) 0.28.922.516 I slot print_timing: id 0 | task 1334 | total time = 1425.68 ms / 469 tokens 0.28.922.517 I slot print_timing: id 0 | task 1334 | graphs reused = 1350 0.28.922.518 I slot print_timing: id 0 | task 1334 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.922.549 I slot release: id 0 | task 1334 | stop processing: n_tokens = 493, truncated = 0 0.28.947.874 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 28836791 0.28.964.999 I slot launch_slot_: id 0 | task 1422 | processing task, is_child = 0 0.30.100.440 I slot print_timing: id 0 | task 1422 | prompt eval time = 101.72 ms / 410 tokens ( 0.25 ms per token, 4030.55 tokens per second) 0.30.100.445 I slot print_timing: id 0 | task 1422 | eval time = 1033.70 ms / 67 tokens ( 15.66 ms per token, 63.85 tokens per second) 0.30.100.447 I slot print_timing: id 0 | task 1422 | total time = 1135.43 ms / 477 tokens 0.30.100.448 I slot print_timing: id 0 | task 1422 | graphs reused = 1415 0.30.100.449 I slot print_timing: id 0 | task 1422 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.100.478 I slot release: id 0 | task 1422 | stop processing: n_tokens = 501, truncated = 0 0.30.104.745 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 30014720 0.30.127.012 I slot launch_slot_: id 0 | task 1490 | processing task, is_child = 0 0.31.211.170 I slot print_timing: id 0 | task 1490 | prompt eval time = 80.79 ms / 367 tokens ( 0.22 ms per token, 4542.87 tokens per second) 0.31.211.176 I slot print_timing: id 0 | task 1490 | eval time = 1003.36 ms / 65 tokens ( 15.68 ms per token, 63.79 tokens per second) 0.31.211.177 I slot print_timing: id 0 | task 1490 | total time = 1084.14 ms / 432 tokens 0.31.211.178 I slot print_timing: id 0 | task 1490 | graphs reused = 1478 0.31.211.179 I slot print_timing: id 0 | task 1490 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.211.207 I slot release: id 0 | task 1490 | stop processing: n_tokens = 458, truncated = 0 0.31.215.936 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 31125449 0.31.231.323 I slot launch_slot_: id 0 | task 1556 | processing task, is_child = 0 0.32.136.839 I slot print_timing: id 0 | task 1556 | prompt eval time = 73.97 ms / 326 tokens ( 0.23 ms per token, 4406.95 tokens per second) 0.32.136.846 I slot print_timing: id 0 | task 1556 | eval time = 831.53 ms / 54 tokens ( 15.69 ms per token, 63.74 tokens per second) 0.32.136.847 I slot print_timing: id 0 | task 1556 | total time = 905.50 ms / 380 tokens 0.32.136.849 I slot print_timing: id 0 | task 1556 | graphs reused = 1530 0.32.136.850 I slot print_timing: id 0 | task 1556 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.136.881 I slot release: id 0 | task 1556 | stop processing: n_tokens = 404, truncated = 0 0.32.165.666 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 32051123 0.32.181.398 I slot launch_slot_: id 0 | task 1611 | processing task, is_child = 0 0.33.249.290 I slot print_timing: id 0 | task 1611 | prompt eval time = 80.77 ms / 351 tokens ( 0.23 ms per token, 4345.78 tokens per second) 0.33.249.296 I slot print_timing: id 0 | task 1611 | eval time = 987.10 ms / 64 tokens ( 15.67 ms per token, 63.82 tokens per second) 0.33.249.297 I slot print_timing: id 0 | task 1611 | total time = 1067.87 ms / 415 tokens 0.33.249.297 I slot print_timing: id 0 | task 1611 | graphs reused = 1592 0.33.249.298 I slot print_timing: id 0 | task 1611 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.249.327 I slot release: id 0 | task 1611 | stop processing: n_tokens = 441, truncated = 0 0.33.273.148 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 441, t_last = 33163569 0.33.288.031 I slot launch_slot_: id 0 | task 1676 | processing task, is_child = 0 0.34.583.629 I slot print_timing: id 0 | task 1676 | prompt eval time = 80.40 ms / 379 tokens ( 0.21 ms per token, 4713.87 tokens per second) 0.34.583.634 I slot print_timing: id 0 | task 1676 | eval time = 1215.18 ms / 78 tokens ( 15.78 ms per token, 63.37 tokens per second) 0.34.583.635 I slot print_timing: id 0 | task 1676 | total time = 1295.58 ms / 457 tokens 0.34.583.636 I slot print_timing: id 0 | task 1676 | graphs reused = 1668 0.34.583.637 I slot print_timing: id 0 | task 1676 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.583.667 I slot release: id 0 | task 1676 | stop processing: n_tokens = 481, truncated = 0 0.34.612.303 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 34497909 0.34.628.754 I slot launch_slot_: id 0 | task 1755 | processing task, is_child = 0 0.35.797.834 I slot print_timing: id 0 | task 1755 | prompt eval time = 80.35 ms / 356 tokens ( 0.23 ms per token, 4430.40 tokens per second) 0.35.797.840 I slot print_timing: id 0 | task 1755 | eval time = 1088.71 ms / 70 tokens ( 15.78 ms per token, 63.38 tokens per second) 0.35.797.842 I slot print_timing: id 0 | task 1755 | total time = 1169.07 ms / 426 tokens 0.35.797.843 I slot print_timing: id 0 | task 1755 | graphs reused = 1736 0.35.797.844 I slot print_timing: id 0 | task 1755 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.797.873 I slot release: id 0 | task 1755 | stop processing: n_tokens = 450, truncated = 0 0.35.814.516 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 35712115 0.35.829.615 I slot launch_slot_: id 0 | task 1826 | processing task, is_child = 0 0.36.849.859 I slot print_timing: id 0 | task 1826 | prompt eval time = 74.39 ms / 331 tokens ( 0.22 ms per token, 4449.34 tokens per second) 0.36.849.864 I slot print_timing: id 0 | task 1826 | eval time = 945.84 ms / 61 tokens ( 15.76 ms per token, 63.44 tokens per second) 0.36.849.865 I slot print_timing: id 0 | task 1826 | total time = 1020.23 ms / 392 tokens 0.36.849.866 I slot print_timing: id 0 | task 1826 | graphs reused = 1795 0.36.849.867 I slot print_timing: id 0 | task 1826 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.849.894 I slot release: id 0 | task 1826 | stop processing: n_tokens = 416, truncated = 0 0.36.864.871 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 36764136 0.36.879.274 I slot launch_slot_: id 0 | task 1888 | processing task, is_child = 0 0.37.480.865 I slot print_timing: id 0 | task 1888 | prompt eval time = 74.50 ms / 334 tokens ( 0.22 ms per token, 4482.98 tokens per second) 0.37.480.872 I slot print_timing: id 0 | task 1888 | eval time = 527.07 ms / 34 tokens ( 15.97 ms per token, 62.61 tokens per second) 0.37.480.873 I slot print_timing: id 0 | task 1888 | total time = 601.58 ms / 368 tokens 0.37.480.875 I slot print_timing: id 0 | task 1888 | graphs reused = 1827 0.37.480.876 I slot print_timing: id 0 | task 1888 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.480.902 I slot release: id 0 | task 1888 | stop processing: n_tokens = 392, truncated = 0 0.37.509.003 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 37395145 0.37.522.517 I slot launch_slot_: id 0 | task 1923 | processing task, is_child = 0 0.38.651.441 I slot print_timing: id 0 | task 1923 | prompt eval time = 80.81 ms / 362 tokens ( 0.22 ms per token, 4479.92 tokens per second) 0.38.651.447 I slot print_timing: id 0 | task 1923 | eval time = 1048.10 ms / 68 tokens ( 15.64 ms per token, 63.93 tokens per second) 0.38.651.449 I slot print_timing: id 0 | task 1923 | total time = 1128.90 ms / 430 tokens 0.38.651.449 I slot print_timing: id 0 | task 1923 | graphs reused = 1893 0.38.651.450 I slot print_timing: id 0 | task 1923 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.651.481 I slot release: id 0 | task 1923 | stop processing: n_tokens = 454, truncated = 0 0.38.676.670 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 38565723 0.38.692.518 I slot launch_slot_: id 0 | task 1992 | processing task, is_child = 0 0.39.789.953 I slot print_timing: id 0 | task 1992 | prompt eval time = 80.67 ms / 384 tokens ( 0.21 ms per token, 4759.90 tokens per second) 0.39.789.959 I slot print_timing: id 0 | task 1992 | eval time = 1016.74 ms / 66 tokens ( 15.64 ms per token, 63.93 tokens per second) 0.39.789.960 I slot print_timing: id 0 | task 1992 | total time = 1097.42 ms / 450 tokens 0.39.789.961 I slot print_timing: id 0 | task 1992 | graphs reused = 1957 0.39.789.962 I slot print_timing: id 0 | task 1992 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.789.994 I slot release: id 0 | task 1992 | stop processing: n_tokens = 474, truncated = 0 0.39.806.867 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 39704236 0.39.822.850 I slot launch_slot_: id 0 | task 2059 | processing task, is_child = 0 0.40.743.042 I slot print_timing: id 0 | task 2059 | prompt eval time = 74.35 ms / 325 tokens ( 0.23 ms per token, 4371.22 tokens per second) 0.40.743.049 I slot print_timing: id 0 | task 2059 | eval time = 845.83 ms / 55 tokens ( 15.66 ms per token, 63.84 tokens per second) 0.40.743.050 I slot print_timing: id 0 | task 2059 | total time = 920.18 ms / 380 tokens 0.40.743.051 I slot print_timing: id 0 | task 2059 | graphs reused = 2010 0.40.743.052 I slot print_timing: id 0 | task 2059 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.743.083 I slot release: id 0 | task 2059 | stop processing: n_tokens = 404, truncated = 0 0.40.761.563 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 40657326 0.40.775.484 I slot launch_slot_: id 0 | task 2115 | processing task, is_child = 0 0.41.772.075 I slot print_timing: id 0 | task 2115 | prompt eval time = 80.64 ms / 366 tokens ( 0.22 ms per token, 4538.75 tokens per second) 0.41.772.081 I slot print_timing: id 0 | task 2115 | eval time = 915.94 ms / 59 tokens ( 15.79 ms per token, 63.32 tokens per second) 0.41.772.082 I slot print_timing: id 0 | task 2115 | total time = 996.58 ms / 425 tokens 0.41.772.083 I slot print_timing: id 0 | task 2115 | graphs reused = 2067 0.41.772.084 I slot print_timing: id 0 | task 2115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.772.113 I slot release: id 0 | task 2115 | stop processing: n_tokens = 449, truncated = 0 0.41.796.869 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 41686355 0.41.812.439 I slot launch_slot_: id 0 | task 2175 | processing task, is_child = 0 0.42.435.386 I slot print_timing: id 0 | task 2175 | prompt eval time = 73.36 ms / 295 tokens ( 0.25 ms per token, 4021.54 tokens per second) 0.42.435.391 I slot print_timing: id 0 | task 2175 | eval time = 549.58 ms / 36 tokens ( 15.70 ms per token, 63.69 tokens per second) 0.42.435.392 I slot print_timing: id 0 | task 2175 | total time = 622.93 ms / 331 tokens 0.42.435.393 I slot print_timing: id 0 | task 2175 | graphs reused = 2101 0.42.435.394 I slot print_timing: id 0 | task 2175 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.435.421 I slot release: id 0 | task 2175 | stop processing: n_tokens = 355, truncated = 0 0.42.439.635 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 42349663 0.42.452.336 I slot launch_slot_: id 0 | task 2212 | processing task, is_child = 0 0.43.293.086 I slot print_timing: id 0 | task 2212 | prompt eval time = 73.56 ms / 307 tokens ( 0.24 ms per token, 4173.24 tokens per second) 0.43.293.092 I slot print_timing: id 0 | task 2212 | eval time = 767.17 ms / 50 tokens ( 15.66 ms per token, 63.87 tokens per second) 0.43.293.093 I slot print_timing: id 0 | task 2212 | total time = 840.73 ms / 357 tokens 0.43.293.094 I slot print_timing: id 0 | task 2212 | graphs reused = 2149 0.43.293.094 I slot print_timing: id 0 | task 2212 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.293.125 I slot release: id 0 | task 2212 | stop processing: n_tokens = 381, truncated = 0 0.43.307.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 43207367 0.43.321.111 I slot launch_slot_: id 0 | task 2263 | processing task, is_child = 0 0.43.976.087 I slot print_timing: id 0 | task 2263 | prompt eval time = 74.05 ms / 319 tokens ( 0.23 ms per token, 4308.13 tokens per second) 0.43.976.093 I slot print_timing: id 0 | task 2263 | eval time = 580.91 ms / 38 tokens ( 15.70 ms per token, 63.69 tokens per second) 0.43.976.094 I slot print_timing: id 0 | task 2263 | total time = 654.96 ms / 357 tokens 0.43.976.095 I slot print_timing: id 0 | task 2263 | graphs reused = 2185 0.43.976.095 I slot print_timing: id 0 | task 2263 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.976.126 I slot release: id 0 | task 2263 | stop processing: n_tokens = 381, truncated = 0 0.43.992.510 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 43890368 0.44.005.769 I slot launch_slot_: id 0 | task 2302 | processing task, is_child = 0 0.44.894.630 I slot print_timing: id 0 | task 2302 | prompt eval time = 73.72 ms / 315 tokens ( 0.23 ms per token, 4272.92 tokens per second) 0.44.894.636 I slot print_timing: id 0 | task 2302 | eval time = 815.12 ms / 53 tokens ( 15.68 ms per token, 63.79 tokens per second) 0.44.894.637 I slot print_timing: id 0 | task 2302 | total time = 888.84 ms / 368 tokens 0.44.894.638 I slot print_timing: id 0 | task 2302 | graphs reused = 2236 0.44.894.639 I slot print_timing: id 0 | task 2302 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.894.667 I slot release: id 0 | task 2302 | stop processing: n_tokens = 392, truncated = 0 0.44.910.197 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 44808909 0.44.923.869 I slot launch_slot_: id 0 | task 2356 | processing task, is_child = 0 0.45.896.517 I slot print_timing: id 0 | task 2356 | prompt eval time = 81.01 ms / 367 tokens ( 0.22 ms per token, 4530.53 tokens per second) 0.45.896.523 I slot print_timing: id 0 | task 2356 | eval time = 891.63 ms / 58 tokens ( 15.64 ms per token, 63.93 tokens per second) 0.45.896.524 I slot print_timing: id 0 | task 2356 | total time = 972.63 ms / 425 tokens 0.45.896.525 I slot print_timing: id 0 | task 2356 | graphs reused = 2292 0.45.896.526 I slot print_timing: id 0 | task 2356 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.896.556 I slot release: id 0 | task 2356 | stop processing: n_tokens = 449, truncated = 0 0.45.925.204 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 45810799 0.45.941.203 I slot launch_slot_: id 0 | task 2415 | processing task, is_child = 0 0.47.170.717 I slot print_timing: id 0 | task 2415 | prompt eval time = 113.95 ms / 499 tokens ( 0.23 ms per token, 4378.92 tokens per second) 0.47.170.723 I slot print_timing: id 0 | task 2415 | eval time = 1115.54 ms / 70 tokens ( 16.17 ms per token, 61.85 tokens per second) 0.47.170.724 I slot print_timing: id 0 | task 2415 | total time = 1229.49 ms / 569 tokens 0.47.170.725 I slot print_timing: id 0 | task 2415 | graphs reused = 2360 0.47.170.726 I slot print_timing: id 0 | task 2415 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.170.759 I slot release: id 0 | task 2415 | stop processing: n_tokens = 593, truncated = 0 0.47.175.031 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 593, t_last = 47085001 0.47.194.452 I slot launch_slot_: id 0 | task 2486 | processing task, is_child = 0 0.48.036.020 I slot print_timing: id 0 | task 2486 | prompt eval time = 73.96 ms / 319 tokens ( 0.23 ms per token, 4312.97 tokens per second) 0.48.036.025 I slot print_timing: id 0 | task 2486 | eval time = 767.59 ms / 50 tokens ( 15.67 ms per token, 63.84 tokens per second) 0.48.036.027 I slot print_timing: id 0 | task 2486 | total time = 841.55 ms / 369 tokens 0.48.036.028 I slot print_timing: id 0 | task 2486 | graphs reused = 2408 0.48.036.028 I slot print_timing: id 0 | task 2486 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.036.058 I slot release: id 0 | task 2486 | stop processing: n_tokens = 393, truncated = 0 0.48.052.700 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 47950300 0.48.066.372 I slot launch_slot_: id 0 | task 2537 | processing task, is_child = 0 0.49.038.378 I slot print_timing: id 0 | task 2537 | prompt eval time = 80.21 ms / 348 tokens ( 0.23 ms per token, 4338.50 tokens per second) 0.49.038.384 I slot print_timing: id 0 | task 2537 | eval time = 891.78 ms / 58 tokens ( 15.65 ms per token, 63.92 tokens per second) 0.49.038.385 I slot print_timing: id 0 | task 2537 | total time = 971.99 ms / 406 tokens 0.49.038.386 I slot print_timing: id 0 | task 2537 | graphs reused = 2464 0.49.038.386 I slot print_timing: id 0 | task 2537 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.038.417 I slot release: id 0 | task 2537 | stop processing: n_tokens = 430, truncated = 0 0.49.055.930 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 48952659 0.49.070.822 I slot launch_slot_: id 0 | task 2596 | processing task, is_child = 0 0.50.328.715 I slot print_timing: id 0 | task 2596 | prompt eval time = 101.43 ms / 404 tokens ( 0.25 ms per token, 3982.92 tokens per second) 0.50.328.721 I slot print_timing: id 0 | task 2596 | eval time = 1156.44 ms / 75 tokens ( 15.63 ms per token, 63.99 tokens per second) 0.50.328.722 I slot print_timing: id 0 | task 2596 | total time = 1257.88 ms / 479 tokens 0.50.328.723 I slot print_timing: id 0 | task 2596 | graphs reused = 2537 0.50.328.724 I slot print_timing: id 0 | task 2596 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.328.754 I slot release: id 0 | task 2596 | stop processing: n_tokens = 503, truncated = 0 0.50.350.999 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 50242996 0.50.367.658 I slot launch_slot_: id 0 | task 2672 | processing task, is_child = 0 0.51.406.590 I slot print_timing: id 0 | task 2672 | prompt eval time = 101.56 ms / 408 tokens ( 0.25 ms per token, 4017.45 tokens per second) 0.51.406.596 I slot print_timing: id 0 | task 2672 | eval time = 937.36 ms / 60 tokens ( 15.89 ms per token, 62.94 tokens per second) 0.51.406.597 I slot print_timing: id 0 | task 2672 | total time = 1038.92 ms / 468 tokens 0.51.406.598 I slot print_timing: id 0 | task 2672 | graphs reused = 2595 0.51.406.598 I slot print_timing: id 0 | task 2672 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.406.628 I slot release: id 0 | task 2672 | stop processing: n_tokens = 494, truncated = 0 0.51.410.674 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 51320870 0.51.426.913 I slot launch_slot_: id 0 | task 2733 | processing task, is_child = 0 0.52.261.633 I slot print_timing: id 0 | task 2733 | prompt eval time = 74.13 ms / 325 tokens ( 0.23 ms per token, 4384.37 tokens per second) 0.52.261.638 I slot print_timing: id 0 | task 2733 | eval time = 760.58 ms / 49 tokens ( 15.85 ms per token, 63.11 tokens per second) 0.52.261.639 I slot print_timing: id 0 | task 2733 | total time = 834.70 ms / 374 tokens 0.52.261.640 I slot print_timing: id 0 | task 2733 | graphs reused = 2642 0.52.261.641 I slot print_timing: id 0 | task 2733 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.261.670 I slot release: id 0 | task 2733 | stop processing: n_tokens = 402, truncated = 0 0.52.291.025 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 52175912 0.52.304.443 I slot launch_slot_: id 0 | task 2783 | processing task, is_child = 0 0.53.199.753 I slot print_timing: id 0 | task 2783 | prompt eval time = 80.38 ms / 345 tokens ( 0.23 ms per token, 4292.06 tokens per second) 0.53.199.759 I slot print_timing: id 0 | task 2783 | eval time = 814.91 ms / 53 tokens ( 15.67 ms per token, 63.81 tokens per second) 0.53.199.760 I slot print_timing: id 0 | task 2783 | total time = 895.29 ms / 398 tokens 0.53.199.761 I slot print_timing: id 0 | task 2783 | graphs reused = 2693 0.53.199.762 I slot print_timing: id 0 | task 2783 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.199.790 I slot release: id 0 | task 2783 | stop processing: n_tokens = 422, truncated = 0 0.53.227.745 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 53114032 0.53.242.712 I slot launch_slot_: id 0 | task 2837 | processing task, is_child = 0 0.54.090.387 I slot print_timing: id 0 | task 2837 | prompt eval time = 80.09 ms / 344 tokens ( 0.23 ms per token, 4294.95 tokens per second) 0.54.090.393 I slot print_timing: id 0 | task 2837 | eval time = 767.56 ms / 50 tokens ( 15.66 ms per token, 63.84 tokens per second) 0.54.090.394 I slot print_timing: id 0 | task 2837 | total time = 847.66 ms / 394 tokens 0.54.090.395 I slot print_timing: id 0 | task 2837 | graphs reused = 2741 0.54.090.396 I slot print_timing: id 0 | task 2837 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.090.426 I slot release: id 0 | task 2837 | stop processing: n_tokens = 418, truncated = 0 0.54.104.050 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 54004669 0.54.118.826 I slot launch_slot_: id 0 | task 2888 | processing task, is_child = 0 0.55.340.483 I slot print_timing: id 0 | task 2888 | prompt eval time = 80.40 ms / 378 tokens ( 0.21 ms per token, 4701.38 tokens per second) 0.55.340.489 I slot print_timing: id 0 | task 2888 | eval time = 1141.24 ms / 74 tokens ( 15.63 ms per token, 63.97 tokens per second) 0.55.340.490 I slot print_timing: id 0 | task 2888 | total time = 1221.64 ms / 452 tokens 0.55.340.491 I slot print_timing: id 0 | task 2888 | graphs reused = 2813 0.55.340.491 I slot print_timing: id 0 | task 2888 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.340.533 I slot release: id 0 | task 2888 | stop processing: n_tokens = 476, truncated = 0 0.55.356.104 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 55254775 0.55.372.271 I slot launch_slot_: id 0 | task 2963 | processing task, is_child = 0 0.56.385.386 I slot print_timing: id 0 | task 2963 | prompt eval time = 74.42 ms / 331 tokens ( 0.22 ms per token, 4447.67 tokens per second) 0.56.385.393 I slot print_timing: id 0 | task 2963 | eval time = 938.68 ms / 61 tokens ( 15.64 ms per token, 63.92 tokens per second) 0.56.385.394 I slot print_timing: id 0 | task 2963 | total time = 1013.10 ms / 392 tokens 0.56.385.395 I slot print_timing: id 0 | task 2963 | graphs reused = 2872 0.56.385.396 I slot print_timing: id 0 | task 2963 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.385.426 I slot release: id 0 | task 2963 | stop processing: n_tokens = 416, truncated = 0 0.56.413.337 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 56299668 0.56.428.154 I slot launch_slot_: id 0 | task 3025 | processing task, is_child = 0 0.57.280.536 I slot print_timing: id 0 | task 3025 | prompt eval time = 100.85 ms / 387 tokens ( 0.26 ms per token, 3837.34 tokens per second) 0.57.280.542 I slot print_timing: id 0 | task 3025 | eval time = 751.51 ms / 49 tokens ( 15.66 ms per token, 63.87 tokens per second) 0.57.280.543 I slot print_timing: id 0 | task 3025 | total time = 852.37 ms / 436 tokens 0.57.280.544 I slot print_timing: id 0 | task 3025 | graphs reused = 2919 0.57.280.545 I slot print_timing: id 0 | task 3025 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.280.576 I slot release: id 0 | task 3025 | stop processing: n_tokens = 460, truncated = 0 0.57.306.310 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 57194818 0.57.322.056 I slot launch_slot_: id 0 | task 3075 | processing task, is_child = 0 0.58.558.796 I slot print_timing: id 0 | task 3075 | prompt eval time = 80.20 ms / 345 tokens ( 0.23 ms per token, 4301.96 tokens per second) 0.58.558.802 I slot print_timing: id 0 | task 3075 | eval time = 1156.53 ms / 75 tokens ( 15.63 ms per token, 63.98 tokens per second) 0.58.558.803 I slot print_timing: id 0 | task 3075 | total time = 1236.72 ms / 420 tokens 0.58.558.804 I slot print_timing: id 0 | task 3075 | graphs reused = 2992 0.58.558.805 I slot print_timing: id 0 | task 3075 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.558.833 I slot release: id 0 | task 3075 | stop processing: n_tokens = 444, truncated = 0 0.58.588.023 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 58473075 0.58.603.047 I slot launch_slot_: id 0 | task 3151 | processing task, is_child = 0 0.59.640.571 I slot print_timing: id 0 | task 3151 | prompt eval time = 79.83 ms / 337 tokens ( 0.24 ms per token, 4221.31 tokens per second) 0.59.640.576 I slot print_timing: id 0 | task 3151 | eval time = 957.67 ms / 61 tokens ( 15.96 ms per token, 62.65 tokens per second) 0.59.640.577 I slot print_timing: id 0 | task 3151 | total time = 1037.51 ms / 398 tokens 0.59.640.580 I slot print_timing: id 0 | task 3151 | graphs reused = 3051 0.59.640.581 I slot print_timing: id 0 | task 3151 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.640.609 I slot release: id 0 | task 3151 | stop processing: n_tokens = 422, truncated = 0 0.59.660.665 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 59554852 0.59.675.558 I slot launch_slot_: id 0 | task 3213 | processing task, is_child = 0 1.01.267.184 I slot print_timing: id 0 | task 3213 | prompt eval time = 111.36 ms / 463 tokens ( 0.24 ms per token, 4157.87 tokens per second) 1.01.267.189 I slot print_timing: id 0 | task 3213 | eval time = 1480.25 ms / 95 tokens ( 15.75 ms per token, 63.50 tokens per second) 1.01.267.191 I slot print_timing: id 0 | task 3213 | total time = 1591.60 ms / 558 tokens 1.01.267.191 I slot print_timing: id 0 | task 3213 | graphs reused = 3143 1.01.267.192 I slot print_timing: id 0 | task 3213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.267.224 I slot release: id 0 | task 3213 | stop processing: n_tokens = 582, truncated = 0 1.01.281.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 61181467 1.01.300.822 I slot launch_slot_: id 0 | task 3309 | processing task, is_child = 0 1.03.101.280 I slot print_timing: id 0 | task 3309 | prompt eval time = 102.76 ms / 440 tokens ( 0.23 ms per token, 4281.66 tokens per second) 1.03.101.286 I slot print_timing: id 0 | task 3309 | eval time = 1697.68 ms / 109 tokens ( 15.72 ms per token, 63.62 tokens per second) 1.03.101.288 I slot print_timing: id 0 | task 3309 | total time = 1800.44 ms / 549 tokens 1.03.101.288 I slot print_timing: id 0 | task 3309 | graphs reused = 3249 1.03.101.289 I slot print_timing: id 0 | task 3309 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.101.322 I slot release: id 0 | task 3309 | stop processing: n_tokens = 573, truncated = 0 1.03.115.958 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 573, t_last = 63015564 1.03.135.253 I slot launch_slot_: id 0 | task 3419 | processing task, is_child = 0 1.04.196.010 I slot print_timing: id 0 | task 3419 | prompt eval time = 74.39 ms / 336 tokens ( 0.22 ms per token, 4516.74 tokens per second) 1.04.196.015 I slot print_timing: id 0 | task 3419 | eval time = 986.35 ms / 64 tokens ( 15.66 ms per token, 63.87 tokens per second) 1.04.196.016 I slot print_timing: id 0 | task 3419 | total time = 1060.74 ms / 400 tokens 1.04.196.017 I slot print_timing: id 0 | task 3419 | graphs reused = 3311 1.04.196.018 I slot print_timing: id 0 | task 3419 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.196.048 I slot release: id 0 | task 3419 | stop processing: n_tokens = 424, truncated = 0 1.04.223.703 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 64110290 1.04.238.433 I slot launch_slot_: id 0 | task 3484 | processing task, is_child = 0 1.05.205.409 I slot print_timing: id 0 | task 3484 | prompt eval time = 81.10 ms / 367 tokens ( 0.22 ms per token, 4525.11 tokens per second) 1.05.205.414 I slot print_timing: id 0 | task 3484 | eval time = 885.86 ms / 57 tokens ( 15.82 ms per token, 63.22 tokens per second) 1.05.205.415 I slot print_timing: id 0 | task 3484 | total time = 966.96 ms / 424 tokens 1.05.205.416 I slot print_timing: id 0 | task 3484 | graphs reused = 3366 1.05.205.417 I slot print_timing: id 0 | task 3484 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.205.448 I slot release: id 0 | task 3484 | stop processing: n_tokens = 448, truncated = 0 1.05.224.857 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 65119690 1.05.240.154 I slot launch_slot_: id 0 | task 3542 | processing task, is_child = 0 1.06.114.271 I slot print_timing: id 0 | task 3542 | prompt eval time = 74.37 ms / 327 tokens ( 0.23 ms per token, 4396.70 tokens per second) 1.06.114.277 I slot print_timing: id 0 | task 3542 | eval time = 799.73 ms / 52 tokens ( 15.68 ms per token, 63.77 tokens per second) 1.06.114.278 I slot print_timing: id 0 | task 3542 | total time = 874.10 ms / 379 tokens 1.06.114.279 I slot print_timing: id 0 | task 3542 | graphs reused = 3416 1.06.114.280 I slot print_timing: id 0 | task 3542 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.114.307 I slot release: id 0 | task 3542 | stop processing: n_tokens = 403, truncated = 0 1.06.141.719 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 66028549 1.06.156.423 I slot launch_slot_: id 0 | task 3595 | processing task, is_child = 0 1.07.461.070 I slot print_timing: id 0 | task 3595 | prompt eval time = 101.34 ms / 393 tokens ( 0.26 ms per token, 3878.03 tokens per second) 1.07.461.076 I slot print_timing: id 0 | task 3595 | eval time = 1203.28 ms / 76 tokens ( 16.04 ms per token, 62.33 tokens per second) 1.07.461.077 I slot print_timing: id 0 | task 3595 | total time = 1304.62 ms / 469 tokens 1.07.461.078 I slot print_timing: id 0 | task 3595 | graphs reused = 3490 1.07.461.079 I slot print_timing: id 0 | task 3595 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.461.117 I slot release: id 0 | task 3595 | stop processing: n_tokens = 493, truncated = 0 1.07.478.717 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 67375359 1.07.496.022 I slot launch_slot_: id 0 | task 3672 | processing task, is_child = 0 1.08.597.069 I slot print_timing: id 0 | task 3672 | prompt eval time = 135.84 ms / 524 tokens ( 0.26 ms per token, 3857.56 tokens per second) 1.08.597.074 I slot print_timing: id 0 | task 3672 | eval time = 965.19 ms / 62 tokens ( 15.82 ms per token, 63.20 tokens per second) 1.08.597.075 I slot print_timing: id 0 | task 3672 | total time = 1101.03 ms / 586 tokens 1.08.597.076 I slot print_timing: id 0 | task 3672 | graphs reused = 3550 1.08.597.077 I slot print_timing: id 0 | task 3672 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.597.111 I slot release: id 0 | task 3672 | stop processing: n_tokens = 610, truncated = 0 1.08.614.306 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 68511353 1.08.635.108 I slot launch_slot_: id 0 | task 3735 | processing task, is_child = 0 1.09.730.495 I slot print_timing: id 0 | task 3735 | prompt eval time = 148.24 ms / 602 tokens ( 0.25 ms per token, 4061.12 tokens per second) 1.09.730.501 I slot print_timing: id 0 | task 3735 | eval time = 947.14 ms / 61 tokens ( 15.79 ms per token, 63.35 tokens per second) 1.09.730.502 I slot print_timing: id 0 | task 3735 | total time = 1095.37 ms / 663 tokens 1.09.730.503 I slot print_timing: id 0 | task 3735 | graphs reused = 3609 1.09.730.504 I slot print_timing: id 0 | task 3735 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.730.541 I slot release: id 0 | task 3735 | stop processing: n_tokens = 687, truncated = 0 1.09.755.326 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 69644783 1.09.778.477 I slot launch_slot_: id 0 | task 3797 | processing task, is_child = 0 1.10.903.991 I slot print_timing: id 0 | task 3797 | prompt eval time = 148.28 ms / 640 tokens ( 0.23 ms per token, 4316.01 tokens per second) 1.10.903.998 I slot print_timing: id 0 | task 3797 | eval time = 977.21 ms / 63 tokens ( 15.76 ms per token, 63.45 tokens per second) 1.10.903.999 I slot print_timing: id 0 | task 3797 | total time = 1125.50 ms / 703 tokens 1.10.904.001 I slot print_timing: id 0 | task 3797 | graphs reused = 3670 1.10.904.002 I slot print_timing: id 0 | task 3797 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.904.038 I slot release: id 0 | task 3797 | stop processing: n_tokens = 727, truncated = 0 1.10.927.495 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 70818281 1.10.958.360 I slot launch_slot_: id 0 | task 3861 | processing task, is_child = 0 1.12.131.033 I slot print_timing: id 0 | task 3861 | prompt eval time = 147.55 ms / 629 tokens ( 0.23 ms per token, 4262.96 tokens per second) 1.12.131.039 I slot print_timing: id 0 | task 3861 | eval time = 1025.11 ms / 66 tokens ( 15.77 ms per token, 63.41 tokens per second) 1.12.131.040 I slot print_timing: id 0 | task 3861 | total time = 1172.66 ms / 695 tokens 1.12.131.041 I slot print_timing: id 0 | task 3861 | graphs reused = 3734 1.12.131.042 I slot print_timing: id 0 | task 3861 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.131.076 I slot release: id 0 | task 3861 | stop processing: n_tokens = 719, truncated = 0 1.12.156.376 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 719, t_last = 72045318 1.12.186.938 I slot launch_slot_: id 0 | task 3928 | processing task, is_child = 0 1.13.184.234 I slot print_timing: id 0 | task 3928 | prompt eval time = 111.29 ms / 458 tokens ( 0.24 ms per token, 4115.23 tokens per second) 1.13.184.240 I slot print_timing: id 0 | task 3928 | eval time = 885.99 ms / 57 tokens ( 15.82 ms per token, 63.21 tokens per second) 1.13.184.241 I slot print_timing: id 0 | task 3928 | total time = 997.28 ms / 515 tokens 1.13.184.242 I slot print_timing: id 0 | task 3928 | graphs reused = 3788 1.13.184.243 I slot print_timing: id 0 | task 3928 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.184.274 I slot release: id 0 | task 3928 | stop processing: n_tokens = 539, truncated = 0 1.13.204.352 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 73098516 1.13.231.466 I slot launch_slot_: id 0 | task 3986 | processing task, is_child = 0 1.14.350.427 I slot print_timing: id 0 | task 3986 | prompt eval time = 141.99 ms / 594 tokens ( 0.24 ms per token, 4183.33 tokens per second) 1.14.350.432 I slot print_timing: id 0 | task 3986 | eval time = 976.95 ms / 63 tokens ( 15.76 ms per token, 63.46 tokens per second) 1.14.350.433 I slot print_timing: id 0 | task 3986 | total time = 1118.94 ms / 657 tokens 1.14.350.434 I slot print_timing: id 0 | task 3986 | graphs reused = 3849 1.14.350.435 I slot print_timing: id 0 | task 3986 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.350.472 I slot release: id 0 | task 3986 | stop processing: n_tokens = 681, truncated = 0 1.14.367.266 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 681, t_last = 74264714 1.14.397.521 I slot launch_slot_: id 0 | task 4050 | processing task, is_child = 0 1.15.326.006 I slot print_timing: id 0 | task 4050 | prompt eval time = 138.49 ms / 572 tokens ( 0.24 ms per token, 4130.29 tokens per second) 1.15.326.012 I slot print_timing: id 0 | task 4050 | eval time = 789.98 ms / 51 tokens ( 15.80 ms per token, 63.29 tokens per second) 1.15.326.013 I slot print_timing: id 0 | task 4050 | total time = 928.47 ms / 623 tokens 1.15.326.014 I slot print_timing: id 0 | task 4050 | graphs reused = 3898 1.15.326.014 I slot print_timing: id 0 | task 4050 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.326.048 I slot release: id 0 | task 4050 | stop processing: n_tokens = 647, truncated = 0 1.15.349.726 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 647, t_last = 75240290 1.15.375.731 I slot launch_slot_: id 0 | task 4102 | processing task, is_child = 0 1.16.264.581 I slot print_timing: id 0 | task 4102 | prompt eval time = 113.82 ms / 502 tokens ( 0.23 ms per token, 4410.43 tokens per second) 1.16.264.588 I slot print_timing: id 0 | task 4102 | eval time = 775.01 ms / 50 tokens ( 15.82 ms per token, 63.22 tokens per second) 1.16.264.589 I slot print_timing: id 0 | task 4102 | total time = 888.83 ms / 552 tokens 1.16.264.590 I slot print_timing: id 0 | task 4102 | graphs reused = 3946 1.16.264.591 I slot print_timing: id 0 | task 4102 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.264.630 I slot release: id 0 | task 4102 | stop processing: n_tokens = 576, truncated = 0 1.16.291.853 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 76178873 1.16.316.552 I slot launch_slot_: id 0 | task 4153 | processing task, is_child = 0 1.17.314.883 I slot print_timing: id 0 | task 4153 | prompt eval time = 111.40 ms / 479 tokens ( 0.23 ms per token, 4299.78 tokens per second) 1.17.314.889 I slot print_timing: id 0 | task 4153 | eval time = 886.91 ms / 57 tokens ( 15.84 ms per token, 63.14 tokens per second) 1.17.314.890 I slot print_timing: id 0 | task 4153 | total time = 998.31 ms / 536 tokens 1.17.314.890 I slot print_timing: id 0 | task 4153 | graphs reused = 4000 1.17.314.891 I slot print_timing: id 0 | task 4153 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.314.922 I slot release: id 0 | task 4153 | stop processing: n_tokens = 560, truncated = 0 1.17.335.693 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 77229164 1.17.360.830 I slot launch_slot_: id 0 | task 4211 | processing task, is_child = 0 1.18.190.891 I slot print_timing: id 0 | task 4211 | prompt eval time = 135.37 ms / 552 tokens ( 0.25 ms per token, 4077.77 tokens per second) 1.18.190.897 I slot print_timing: id 0 | task 4211 | eval time = 694.67 ms / 45 tokens ( 15.79 ms per token, 63.34 tokens per second) 1.18.190.898 I slot print_timing: id 0 | task 4211 | total time = 830.04 ms / 597 tokens 1.18.190.899 I slot print_timing: id 0 | task 4211 | graphs reused = 4043 1.18.190.900 I slot print_timing: id 0 | task 4211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.190.938 I slot release: id 0 | task 4211 | stop processing: n_tokens = 621, truncated = 0 1.18.207.478 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 78105181 1.18.233.896 I slot launch_slot_: id 0 | task 4257 | processing task, is_child = 0 1.20.157.674 I slot print_timing: id 0 | task 4257 | prompt eval time = 129.26 ms / 514 tokens ( 0.25 ms per token, 3976.51 tokens per second) 1.20.157.680 I slot print_timing: id 0 | task 4257 | eval time = 1794.50 ms / 115 tokens ( 15.74 ms per token, 63.53 tokens per second) 1.20.157.681 I slot print_timing: id 0 | task 4257 | total time = 1923.76 ms / 629 tokens 1.20.157.682 I slot print_timing: id 0 | task 4257 | graphs reused = 4156 1.20.157.683 I slot print_timing: id 0 | task 4257 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.157.715 I slot release: id 0 | task 4257 | stop processing: n_tokens = 653, truncated = 0 1.20.175.040 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 653, t_last = 80071957 1.20.203.789 I slot launch_slot_: id 0 | task 4373 | processing task, is_child = 0 1.20.950.603 I slot print_timing: id 0 | task 4373 | prompt eval time = 102.62 ms / 428 tokens ( 0.24 ms per token, 4170.85 tokens per second) 1.20.950.609 I slot print_timing: id 0 | task 4373 | eval time = 644.18 ms / 42 tokens ( 15.71 ms per token, 63.65 tokens per second) 1.20.950.610 I slot print_timing: id 0 | task 4373 | total time = 746.80 ms / 470 tokens 1.20.950.611 I slot print_timing: id 0 | task 4373 | graphs reused = 4196 1.20.950.612 I slot print_timing: id 0 | task 4373 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.950.647 I slot release: id 0 | task 4373 | stop processing: n_tokens = 494, truncated = 0 1.20.969.483 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 80864889 1.20.990.964 I slot launch_slot_: id 0 | task 4416 | processing task, is_child = 0 1.22.158.155 I slot print_timing: id 0 | task 4416 | prompt eval time = 132.65 ms / 521 tokens ( 0.25 ms per token, 3927.69 tokens per second) 1.22.158.161 I slot print_timing: id 0 | task 4416 | eval time = 1034.53 ms / 66 tokens ( 15.92 ms per token, 62.83 tokens per second) 1.22.158.162 I slot print_timing: id 0 | task 4416 | total time = 1167.18 ms / 587 tokens 1.22.158.163 I slot print_timing: id 0 | task 4416 | graphs reused = 4260 1.22.158.164 I slot print_timing: id 0 | task 4416 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.158.198 I slot release: id 0 | task 4416 | stop processing: n_tokens = 611, truncated = 0 1.22.163.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 82072440 1.22.189.806 I slot launch_slot_: id 0 | task 4483 | processing task, is_child = 0 1.23.103.597 I slot print_timing: id 0 | task 4483 | prompt eval time = 111.39 ms / 472 tokens ( 0.24 ms per token, 4237.17 tokens per second) 1.23.103.604 I slot print_timing: id 0 | task 4483 | eval time = 802.38 ms / 51 tokens ( 16.05 ms per token, 62.31 tokens per second) 1.23.103.605 I slot print_timing: id 0 | task 4483 | total time = 913.77 ms / 523 tokens 1.23.103.606 I slot print_timing: id 0 | task 4483 | graphs reused = 4308 1.23.103.607 I slot print_timing: id 0 | task 4483 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.103.645 I slot release: id 0 | task 4483 | stop processing: n_tokens = 547, truncated = 0 1.23.129.018 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 83017887 1.23.153.650 I slot launch_slot_: id 0 | task 4535 | processing task, is_child = 0 1.23.930.666 I slot print_timing: id 0 | task 4535 | prompt eval time = 102.54 ms / 428 tokens ( 0.24 ms per token, 4173.98 tokens per second) 1.23.930.671 I slot print_timing: id 0 | task 4535 | eval time = 674.46 ms / 44 tokens ( 15.69 ms per token, 63.75 tokens per second) 1.23.930.672 I slot print_timing: id 0 | task 4535 | total time = 777.00 ms / 472 tokens 1.23.930.673 I slot print_timing: id 0 | task 4535 | graphs reused = 4350 1.23.930.674 I slot print_timing: id 0 | task 4535 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.930.707 I slot release: id 0 | task 4535 | stop processing: n_tokens = 496, truncated = 0 1.23.948.946 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 496, t_last = 83844949 1.23.970.484 I slot launch_slot_: id 0 | task 4580 | processing task, is_child = 0 1.24.777.217 I slot print_timing: id 0 | task 4580 | prompt eval time = 111.13 ms / 456 tokens ( 0.24 ms per token, 4103.19 tokens per second) 1.24.777.223 I slot print_timing: id 0 | task 4580 | eval time = 695.59 ms / 45 tokens ( 15.81 ms per token, 63.26 tokens per second) 1.24.777.224 I slot print_timing: id 0 | task 4580 | total time = 806.72 ms / 501 tokens 1.24.777.225 I slot print_timing: id 0 | task 4580 | graphs reused = 4392 1.24.777.226 I slot print_timing: id 0 | task 4580 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.777.259 I slot release: id 0 | task 4580 | stop processing: n_tokens = 525, truncated = 0 1.24.806.835 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 525, t_last = 84691502 1.24.829.915 I slot launch_slot_: id 0 | task 4626 | processing task, is_child = 0 1.25.606.560 I slot print_timing: id 0 | task 4626 | prompt eval time = 102.93 ms / 439 tokens ( 0.23 ms per token, 4264.87 tokens per second) 1.25.606.566 I slot print_timing: id 0 | task 4626 | eval time = 673.70 ms / 44 tokens ( 15.67 ms per token, 63.83 tokens per second) 1.25.606.567 I slot print_timing: id 0 | task 4626 | total time = 776.63 ms / 483 tokens 1.25.606.568 I slot print_timing: id 0 | task 4626 | graphs reused = 4434 1.25.606.569 I slot print_timing: id 0 | task 4626 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.606.601 I slot release: id 0 | task 4626 | stop processing: n_tokens = 507, truncated = 0 1.25.636.999 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 507, t_last = 85520843 1.25.658.889 I slot launch_slot_: id 0 | task 4671 | processing task, is_child = 0 1.26.730.436 I slot print_timing: id 0 | task 4671 | prompt eval time = 142.50 ms / 600 tokens ( 0.24 ms per token, 4210.44 tokens per second) 1.26.730.441 I slot print_timing: id 0 | task 4671 | eval time = 929.03 ms / 60 tokens ( 15.75 ms per token, 63.51 tokens per second) 1.26.730.443 I slot print_timing: id 0 | task 4671 | total time = 1071.53 ms / 660 tokens 1.26.730.443 I slot print_timing: id 0 | task 4671 | graphs reused = 4492 1.26.730.444 I slot print_timing: id 0 | task 4671 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.730.480 I slot release: id 0 | task 4671 | stop processing: n_tokens = 684, truncated = 0 1.26.746.212 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 86644723 1.26.774.422 I slot launch_slot_: id 0 | task 4732 | processing task, is_child = 0 1.27.535.548 I slot print_timing: id 0 | task 4732 | prompt eval time = 111.26 ms / 473 tokens ( 0.24 ms per token, 4251.19 tokens per second) 1.27.535.553 I slot print_timing: id 0 | task 4732 | eval time = 649.84 ms / 42 tokens ( 15.85 ms per token, 63.09 tokens per second) 1.27.535.554 I slot print_timing: id 0 | task 4732 | total time = 761.11 ms / 515 tokens 1.27.535.555 I slot print_timing: id 0 | task 4732 | graphs reused = 4531 1.27.535.556 I slot print_timing: id 0 | task 4732 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.535.590 I slot release: id 0 | task 4732 | stop processing: n_tokens = 539, truncated = 0 1.27.557.460 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 87449832 1.27.583.589 I slot launch_slot_: id 0 | task 4775 | processing task, is_child = 0 1.28.779.723 I slot print_timing: id 0 | task 4775 | prompt eval time = 186.12 ms / 835 tokens ( 0.22 ms per token, 4486.40 tokens per second) 1.28.779.728 I slot print_timing: id 0 | task 4775 | eval time = 1010.00 ms / 65 tokens ( 15.78 ms per token, 63.37 tokens per second) 1.28.779.729 I slot print_timing: id 0 | task 4775 | total time = 1196.12 ms / 900 tokens 1.28.779.730 I slot print_timing: id 0 | task 4775 | graphs reused = 4594 1.28.779.731 I slot print_timing: id 0 | task 4775 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.779.776 I slot release: id 0 | task 4775 | stop processing: n_tokens = 924, truncated = 0 1.28.784.933 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 88694018 1.28.823.743 I slot launch_slot_: id 0 | task 4841 | processing task, is_child = 0 1.29.598.742 I slot print_timing: id 0 | task 4841 | prompt eval time = 110.83 ms / 454 tokens ( 0.24 ms per token, 4096.44 tokens per second) 1.29.598.748 I slot print_timing: id 0 | task 4841 | eval time = 664.15 ms / 43 tokens ( 15.81 ms per token, 63.24 tokens per second) 1.29.598.750 I slot print_timing: id 0 | task 4841 | total time = 774.98 ms / 497 tokens 1.29.598.751 I slot print_timing: id 0 | task 4841 | graphs reused = 4634 1.29.598.752 I slot print_timing: id 0 | task 4841 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.598.787 I slot release: id 0 | task 4841 | stop processing: n_tokens = 521, truncated = 0 1.29.620.133 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 89513029 1.29.642.335 I slot launch_slot_: id 0 | task 4885 | processing task, is_child = 0 1.30.540.693 I slot print_timing: id 0 | task 4885 | prompt eval time = 157.32 ms / 667 tokens ( 0.24 ms per token, 4239.79 tokens per second) 1.30.540.698 I slot print_timing: id 0 | task 4885 | eval time = 741.02 ms / 48 tokens ( 15.77 ms per token, 63.43 tokens per second) 1.30.540.699 I slot print_timing: id 0 | task 4885 | total time = 898.34 ms / 715 tokens 1.30.540.700 I slot print_timing: id 0 | task 4885 | graphs reused = 4680 1.30.540.700 I slot print_timing: id 0 | task 4885 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.540.742 I slot release: id 0 | task 4885 | stop processing: n_tokens = 741, truncated = 0 1.30.571.020 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 90454984 1.30.613.469 I slot launch_slot_: id 0 | task 4934 | processing task, is_child = 0 1.31.862.984 I slot print_timing: id 0 | task 4934 | prompt eval time = 148.03 ms / 628 tokens ( 0.24 ms per token, 4242.35 tokens per second) 1.31.862.990 I slot print_timing: id 0 | task 4934 | eval time = 1101.47 ms / 69 tokens ( 16.20 ms per token, 61.74 tokens per second) 1.31.862.992 I slot print_timing: id 0 | task 4934 | total time = 1249.50 ms / 697 tokens 1.31.862.993 I slot print_timing: id 0 | task 4934 | graphs reused = 4747 1.31.862.994 I slot print_timing: id 0 | task 4934 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.863.035 I slot release: id 0 | task 4934 | stop processing: n_tokens = 858, truncated = 0 1.31.892.132 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 858, t_last = 91777278 1.31.925.726 I slot launch_slot_: id 0 | task 5004 | processing task, is_child = 0 1.33.247.226 I slot print_timing: id 0 | task 5004 | prompt eval time = 140.27 ms / 578 tokens ( 0.24 ms per token, 4120.62 tokens per second) 1.33.247.232 I slot print_timing: id 0 | task 5004 | eval time = 1181.21 ms / 76 tokens ( 15.75 ms per token, 63.49 tokens per second) 1.33.247.233 I slot print_timing: id 0 | task 5004 | total time = 1321.48 ms / 654 tokens 1.33.247.234 I slot print_timing: id 0 | task 5004 | graphs reused = 4821 1.33.247.235 I slot print_timing: id 0 | task 5004 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.247.272 I slot release: id 0 | task 5004 | stop processing: n_tokens = 678, truncated = 0 1.33.264.288 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 93161514 1.33.291.785 I slot launch_slot_: id 0 | task 5081 | processing task, is_child = 0 1.34.427.789 I slot print_timing: id 0 | task 5081 | prompt eval time = 111.45 ms / 461 tokens ( 0.24 ms per token, 4136.27 tokens per second) 1.34.427.795 I slot print_timing: id 0 | task 5081 | eval time = 1024.53 ms / 66 tokens ( 15.76 ms per token, 63.44 tokens per second) 1.34.427.796 I slot print_timing: id 0 | task 5081 | total time = 1135.98 ms / 527 tokens 1.34.427.797 I slot print_timing: id 0 | task 5081 | graphs reused = 4884 1.34.427.797 I slot print_timing: id 0 | task 5081 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.427.831 I slot release: id 0 | task 5081 | stop processing: n_tokens = 551, truncated = 0 1.34.433.785 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 551, t_last = 94342073 1.34.456.442 I slot launch_slot_: id 0 | task 5148 | processing task, is_child = 0 1.35.352.676 I slot print_timing: id 0 | task 5148 | prompt eval time = 145.67 ms / 613 tokens ( 0.24 ms per token, 4208.26 tokens per second) 1.35.352.682 I slot print_timing: id 0 | task 5148 | eval time = 750.55 ms / 48 tokens ( 15.97 ms per token, 62.62 tokens per second) 1.35.352.683 I slot print_timing: id 0 | task 5148 | total time = 896.22 ms / 661 tokens 1.35.352.684 I slot print_timing: id 0 | task 5148 | graphs reused = 4930 1.35.352.685 I slot print_timing: id 0 | task 5148 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.352.725 I slot release: id 0 | task 5148 | stop processing: n_tokens = 685, truncated = 0 1.35.380.844 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 95266967 1.35.407.427 I slot launch_slot_: id 0 | task 5197 | processing task, is_child = 0 1.36.595.857 I slot print_timing: id 0 | task 5197 | prompt eval time = 177.97 ms / 794 tokens ( 0.22 ms per token, 4461.55 tokens per second) 1.36.595.863 I slot print_timing: id 0 | task 5197 | eval time = 1010.45 ms / 65 tokens ( 15.79 ms per token, 63.34 tokens per second) 1.36.595.864 I slot print_timing: id 0 | task 5197 | total time = 1188.42 ms / 859 tokens 1.36.595.865 I slot print_timing: id 0 | task 5197 | graphs reused = 4993 1.36.595.865 I slot print_timing: id 0 | task 5197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.595.908 I slot release: id 0 | task 5197 | stop processing: n_tokens = 883, truncated = 0 1.36.621.469 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 96510150 1.36.671.579 I slot launch_slot_: id 0 | task 5263 | processing task, is_child = 0 1.37.672.616 I slot print_timing: id 0 | task 5263 | prompt eval time = 103.43 ms / 431 tokens ( 0.24 ms per token, 4166.99 tokens per second) 1.37.672.621 I slot print_timing: id 0 | task 5263 | eval time = 897.58 ms / 58 tokens ( 15.75 ms per token, 63.50 tokens per second) 1.37.672.622 I slot print_timing: id 0 | task 5263 | total time = 1001.02 ms / 489 tokens 1.37.672.623 I slot print_timing: id 0 | task 5263 | graphs reused = 5049 1.37.672.624 I slot print_timing: id 0 | task 5263 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.672.659 I slot release: id 0 | task 5263 | stop processing: n_tokens = 687, truncated = 0 1.37.688.607 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 97586901 1.37.711.170 I slot launch_slot_: id 0 | task 5322 | processing task, is_child = 0 1.38.630.822 I slot print_timing: id 0 | task 5322 | prompt eval time = 137.25 ms / 563 tokens ( 0.24 ms per token, 4101.97 tokens per second) 1.38.630.828 I slot print_timing: id 0 | task 5322 | eval time = 782.39 ms / 50 tokens ( 15.97 ms per token, 62.63 tokens per second) 1.38.630.829 I slot print_timing: id 0 | task 5322 | total time = 919.64 ms / 613 tokens 1.38.630.830 I slot print_timing: id 0 | task 5322 | graphs reused = 5097 1.38.630.830 I slot print_timing: id 0 | task 5322 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.630.869 I slot release: id 0 | task 5322 | stop processing: n_tokens = 637, truncated = 0 1.38.646.994 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 98545111 1.38.684.959 I slot launch_slot_: id 0 | task 5373 | processing task, is_child = 0 1.39.498.260 I slot print_timing: id 0 | task 5373 | prompt eval time = 74.50 ms / 331 tokens ( 0.23 ms per token, 4443.13 tokens per second) 1.39.498.266 I slot print_timing: id 0 | task 5373 | eval time = 738.79 ms / 48 tokens ( 15.72 ms per token, 63.62 tokens per second) 1.39.498.267 I slot print_timing: id 0 | task 5373 | total time = 813.28 ms / 379 tokens 1.39.498.268 I slot print_timing: id 0 | task 5373 | graphs reused = 5142 1.39.498.268 I slot print_timing: id 0 | task 5373 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.498.301 I slot release: id 0 | task 5373 | stop processing: n_tokens = 513, truncated = 0 1.39.521.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 99412543 1.39.539.955 I slot launch_slot_: id 0 | task 5422 | processing task, is_child = 0 1.40.695.546 I slot print_timing: id 0 | task 5422 | prompt eval time = 113.67 ms / 489 tokens ( 0.23 ms per token, 4301.96 tokens per second) 1.40.695.552 I slot print_timing: id 0 | task 5422 | eval time = 1041.91 ms / 67 tokens ( 15.79 ms per token, 63.35 tokens per second) 1.40.695.553 I slot print_timing: id 0 | task 5422 | total time = 1155.58 ms / 556 tokens 1.40.695.554 I slot print_timing: id 0 | task 5422 | graphs reused = 5207 1.40.695.555 I slot print_timing: id 0 | task 5422 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.695.588 I slot release: id 0 | task 5422 | stop processing: n_tokens = 580, truncated = 0 1.40.721.515 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 100609830 1.40.745.532 I slot launch_slot_: id 0 | task 5490 | processing task, is_child = 0 1.41.695.912 I slot print_timing: id 0 | task 5490 | prompt eval time = 114.20 ms / 510 tokens ( 0.22 ms per token, 4465.77 tokens per second) 1.41.695.918 I slot print_timing: id 0 | task 5490 | eval time = 836.16 ms / 54 tokens ( 15.78 ms per token, 63.38 tokens per second) 1.41.695.919 I slot print_timing: id 0 | task 5490 | total time = 950.37 ms / 564 tokens 1.41.695.920 I slot print_timing: id 0 | task 5490 | graphs reused = 5259 1.41.695.921 I slot print_timing: id 0 | task 5490 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.695.953 I slot release: id 0 | task 5490 | stop processing: n_tokens = 588, truncated = 0 1.41.725.548 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 101610196 1.41.749.757 I slot launch_slot_: id 0 | task 5545 | processing task, is_child = 0 1.43.000.183 I slot print_timing: id 0 | task 5545 | prompt eval time = 147.88 ms / 631 tokens ( 0.23 ms per token, 4266.97 tokens per second) 1.43.000.189 I slot print_timing: id 0 | task 5545 | eval time = 1102.53 ms / 71 tokens ( 15.75 ms per token, 63.49 tokens per second) 1.43.000.190 I slot print_timing: id 0 | task 5545 | total time = 1250.41 ms / 702 tokens 1.43.000.191 I slot print_timing: id 0 | task 5545 | graphs reused = 5328 1.43.000.192 I slot print_timing: id 0 | task 5545 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.000.228 I slot release: id 0 | task 5545 | stop processing: n_tokens = 726, truncated = 0 1.43.021.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 102914470 1.43.051.159 I slot launch_slot_: id 0 | task 5617 | processing task, is_child = 0 1.44.024.093 I slot print_timing: id 0 | task 5617 | prompt eval time = 137.53 ms / 570 tokens ( 0.24 ms per token, 4144.64 tokens per second) 1.44.024.099 I slot print_timing: id 0 | task 5617 | eval time = 835.39 ms / 54 tokens ( 15.76 ms per token, 63.44 tokens per second) 1.44.024.100 I slot print_timing: id 0 | task 5617 | total time = 972.92 ms / 624 tokens 1.44.024.101 I slot print_timing: id 0 | task 5617 | graphs reused = 5380 1.44.024.102 I slot print_timing: id 0 | task 5617 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.024.138 I slot release: id 0 | task 5617 | stop processing: n_tokens = 648, truncated = 0 1.44.044.982 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 103938380 1.44.071.411 I slot launch_slot_: id 0 | task 5672 | processing task, is_child = 0 1.45.008.998 I slot print_timing: id 0 | task 5672 | prompt eval time = 177.79 ms / 792 tokens ( 0.22 ms per token, 4454.64 tokens per second) 1.45.009.005 I slot print_timing: id 0 | task 5672 | eval time = 759.78 ms / 49 tokens ( 15.83 ms per token, 63.18 tokens per second) 1.45.009.006 I slot print_timing: id 0 | task 5672 | total time = 937.57 ms / 841 tokens 1.45.009.006 I slot print_timing: id 0 | task 5672 | graphs reused = 5427 1.45.009.007 I slot print_timing: id 0 | task 5672 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.009.050 I slot release: id 0 | task 5672 | stop processing: n_tokens = 867, truncated = 0 1.45.025.924 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 867, t_last = 104923292 1.45.060.184 I slot launch_slot_: id 0 | task 5722 | processing task, is_child = 0 1.45.891.261 I slot print_timing: id 0 | task 5722 | prompt eval time = 137.01 ms / 564 tokens ( 0.24 ms per token, 4116.34 tokens per second) 1.45.891.267 I slot print_timing: id 0 | task 5722 | eval time = 694.04 ms / 45 tokens ( 15.77 ms per token, 63.40 tokens per second) 1.45.891.269 I slot print_timing: id 0 | task 5722 | total time = 831.06 ms / 609 tokens 1.45.891.270 I slot print_timing: id 0 | task 5722 | graphs reused = 5470 1.45.891.271 I slot print_timing: id 0 | task 5722 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.891.311 I slot release: id 0 | task 5722 | stop processing: n_tokens = 635, truncated = 0 1.45.916.949 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 105805553 1.45.942.722 I slot launch_slot_: id 0 | task 5768 | processing task, is_child = 0 1.46.939.361 I slot print_timing: id 0 | task 5768 | prompt eval time = 145.63 ms / 617 tokens ( 0.24 ms per token, 4236.76 tokens per second) 1.46.939.367 I slot print_timing: id 0 | task 5768 | eval time = 850.99 ms / 55 tokens ( 15.76 ms per token, 63.46 tokens per second) 1.46.939.368 I slot print_timing: id 0 | task 5768 | total time = 996.62 ms / 672 tokens 1.46.939.369 I slot print_timing: id 0 | task 5768 | graphs reused = 5523 1.46.939.370 I slot print_timing: id 0 | task 5768 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.939.406 I slot release: id 0 | task 5768 | stop processing: n_tokens = 696, truncated = 0 1.46.956.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 696, t_last = 106853649 1.46.984.777 I slot launch_slot_: id 0 | task 5824 | processing task, is_child = 0 1.48.161.416 I slot print_timing: id 0 | task 5824 | prompt eval time = 137.62 ms / 572 tokens ( 0.24 ms per token, 4156.28 tokens per second) 1.48.161.422 I slot print_timing: id 0 | task 5824 | eval time = 1039.00 ms / 67 tokens ( 15.74 ms per token, 63.52 tokens per second) 1.48.161.423 I slot print_timing: id 0 | task 5824 | total time = 1176.62 ms / 639 tokens 1.48.161.424 I slot print_timing: id 0 | task 5824 | graphs reused = 5588 1.48.161.425 I slot print_timing: id 0 | task 5824 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.161.460 I slot release: id 0 | task 5824 | stop processing: n_tokens = 663, truncated = 0 1.48.187.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 663, t_last = 108075702 1.48.214.759 I slot launch_slot_: id 0 | task 5892 | processing task, is_child = 0 1.49.220.997 I slot print_timing: id 0 | task 5892 | prompt eval time = 166.14 ms / 712 tokens ( 0.23 ms per token, 4285.57 tokens per second) 1.49.221.002 I slot print_timing: id 0 | task 5892 | eval time = 840.08 ms / 54 tokens ( 15.85 ms per token, 63.09 tokens per second) 1.49.221.003 I slot print_timing: id 0 | task 5892 | total time = 1006.22 ms / 766 tokens 1.49.221.004 I slot print_timing: id 0 | task 5892 | graphs reused = 5639 1.49.221.005 I slot print_timing: id 0 | task 5892 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.221.044 I slot release: id 0 | task 5892 | stop processing: n_tokens = 790, truncated = 0 1.49.253.157 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 109135286 1.49.284.303 I slot launch_slot_: id 0 | task 5947 | processing task, is_child = 0 1.51.137.027 I slot print_timing: id 0 | task 5947 | prompt eval time = 177.86 ms / 791 tokens ( 0.22 ms per token, 4447.24 tokens per second) 1.51.137.033 I slot print_timing: id 0 | task 5947 | eval time = 1674.84 ms / 106 tokens ( 15.95 ms per token, 62.69 tokens per second) 1.51.137.034 I slot print_timing: id 0 | task 5947 | total time = 1852.71 ms / 897 tokens 1.51.137.034 I slot print_timing: id 0 | task 5947 | graphs reused = 5743 1.51.137.035 I slot print_timing: id 0 | task 5947 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.137.079 I slot release: id 0 | task 5947 | stop processing: n_tokens = 921, truncated = 0 1.51.163.816 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 921, t_last = 111051321 1.51.200.116 I slot launch_slot_: id 0 | task 6054 | processing task, is_child = 0 1.54.176.654 I slot print_timing: id 0 | task 6054 | prompt eval time = 80.13 ms / 369 tokens ( 0.22 ms per token, 4605.02 tokens per second) 1.54.176.660 I slot print_timing: id 0 | task 6054 | eval time = 2896.39 ms / 186 tokens ( 15.66 ms per token, 63.87 tokens per second) 1.54.176.661 I slot print_timing: id 0 | task 6054 | total time = 2976.52 ms / 555 tokens 1.54.176.662 I slot print_timing: id 0 | task 6054 | graphs reused = 5926 1.54.176.663 I slot print_timing: id 0 | task 6054 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.176.692 I slot release: id 0 | task 6054 | stop processing: n_tokens = 579, truncated = 0 1.54.180.859 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 114090934 1.54.206.585 I slot launch_slot_: id 0 | task 6241 | processing task, is_child = 0 1.55.262.127 I slot print_timing: id 0 | task 6241 | prompt eval time = 101.11 ms / 388 tokens ( 0.26 ms per token, 3837.22 tokens per second) 1.55.262.133 I slot print_timing: id 0 | task 6241 | eval time = 954.41 ms / 62 tokens ( 15.65 ms per token, 63.91 tokens per second) 1.55.262.134 I slot print_timing: id 0 | task 6241 | total time = 1055.53 ms / 450 tokens 1.55.262.135 I slot print_timing: id 0 | task 6241 | graphs reused = 5986 1.55.262.136 I slot print_timing: id 0 | task 6241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.262.166 I slot release: id 0 | task 6241 | stop processing: n_tokens = 474, truncated = 0 1.55.289.862 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 115176408 1.55.308.592 I slot launch_slot_: id 0 | task 6304 | processing task, is_child = 0 1.56.405.611 I slot print_timing: id 0 | task 6304 | prompt eval time = 80.24 ms / 370 tokens ( 0.22 ms per token, 4611.28 tokens per second) 1.56.405.616 I slot print_timing: id 0 | task 6304 | eval time = 1016.76 ms / 66 tokens ( 15.64 ms per token, 63.93 tokens per second) 1.56.405.618 I slot print_timing: id 0 | task 6304 | total time = 1097.00 ms / 436 tokens 1.56.405.618 I slot print_timing: id 0 | task 6304 | graphs reused = 6050 1.56.405.619 I slot print_timing: id 0 | task 6304 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.405.648 I slot release: id 0 | task 6304 | stop processing: n_tokens = 460, truncated = 0 1.56.430.384 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 116319890 1.56.430.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.881 MiB) 1.56.455.161 I slot launch_slot_: id 0 | task 6371 | processing task, is_child = 0 1.57.459.935 I slot print_timing: id 0 | task 6371 | prompt eval time = 80.26 ms / 340 tokens ( 0.24 ms per token, 4236.39 tokens per second) 1.57.459.940 I slot print_timing: id 0 | task 6371 | eval time = 924.50 ms / 60 tokens ( 15.67 ms per token, 63.82 tokens per second) 1.57.459.941 I slot print_timing: id 0 | task 6371 | total time = 1004.76 ms / 400 tokens 1.57.459.942 I slot print_timing: id 0 | task 6371 | graphs reused = 6108 1.57.459.943 I slot print_timing: id 0 | task 6371 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.459.973 I slot release: id 0 | task 6371 | stop processing: n_tokens = 424, truncated = 0 1.57.477.828 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 117374215 1.57.477.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.255 MiB) 1.57.500.694 I slot launch_slot_: id 0 | task 6432 | processing task, is_child = 0 1.58.817.321 I slot print_timing: id 0 | task 6432 | prompt eval time = 101.91 ms / 409 tokens ( 0.25 ms per token, 4013.46 tokens per second) 1.58.817.326 I slot print_timing: id 0 | task 6432 | eval time = 1214.70 ms / 78 tokens ( 15.78 ms per token, 63.39 tokens per second) 1.58.817.328 I slot print_timing: id 0 | task 6432 | total time = 1316.61 ms / 487 tokens 1.58.817.329 I slot print_timing: id 0 | task 6432 | graphs reused = 6184 1.58.817.329 I slot print_timing: id 0 | task 6432 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.817.362 I slot release: id 0 | task 6432 | stop processing: n_tokens = 511, truncated = 0 1.58.836.348 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 118731604 1.58.836.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.599 MiB) 1.58.840.259 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 1.58.868.504 I slot launch_slot_: id 0 | task 6511 | processing task, is_child = 0 2.00.435.068 I slot print_timing: id 0 | task 6511 | prompt eval time = 102.47 ms / 422 tokens ( 0.24 ms per token, 4118.12 tokens per second) 2.00.435.073 I slot print_timing: id 0 | task 6511 | eval time = 1464.07 ms / 94 tokens ( 15.74 ms per token, 63.52 tokens per second) 2.00.435.074 I slot print_timing: id 0 | task 6511 | total time = 1566.54 ms / 516 tokens 2.00.435.075 I slot print_timing: id 0 | task 6511 | graphs reused = 6275 2.00.435.076 I slot print_timing: id 0 | task 6511 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.435.107 I slot release: id 0 | task 6511 | stop processing: n_tokens = 540, truncated = 0 2.00.455.954 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 120349349 2.00.456.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.537 MiB) 2.00.478.725 I slot launch_slot_: id 0 | task 6606 | processing task, is_child = 0 2.02.342.004 I slot print_timing: id 0 | task 6606 | prompt eval time = 113.69 ms / 499 tokens ( 0.23 ms per token, 4388.94 tokens per second) 2.02.342.010 I slot print_timing: id 0 | task 6606 | eval time = 1749.57 ms / 112 tokens ( 15.76 ms per token, 63.44 tokens per second) 2.02.342.010 I slot print_timing: id 0 | task 6606 | total time = 1863.26 ms / 611 tokens 2.02.342.011 I slot print_timing: id 0 | task 6606 | graphs reused = 6385 2.02.342.012 I slot print_timing: id 0 | task 6606 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.342.046 I slot release: id 0 | task 6606 | stop processing: n_tokens = 639, truncated = 0 2.02.360.169 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 122256288 2.02.360.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 2.02.388.093 I slot launch_slot_: id 0 | task 6719 | processing task, is_child = 0 2.03.143.317 I slot print_timing: id 0 | task 6719 | prompt eval time = 80.49 ms / 345 tokens ( 0.23 ms per token, 4286.09 tokens per second) 2.03.143.323 I slot print_timing: id 0 | task 6719 | eval time = 674.72 ms / 44 tokens ( 15.69 ms per token, 63.73 tokens per second) 2.03.143.324 I slot print_timing: id 0 | task 6719 | total time = 755.21 ms / 389 tokens 2.03.143.325 I slot print_timing: id 0 | task 6719 | graphs reused = 6427 2.03.143.326 I slot print_timing: id 0 | task 6719 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.143.355 I slot release: id 0 | task 6719 | stop processing: n_tokens = 413, truncated = 0 2.03.169.560 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 123057597 2.03.169.609 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.538 MiB) 2.03.192.723 I slot launch_slot_: id 0 | task 6764 | processing task, is_child = 0 2.03.949.307 I slot print_timing: id 0 | task 6764 | prompt eval time = 80.89 ms / 348 tokens ( 0.23 ms per token, 4302.35 tokens per second) 2.03.949.313 I slot print_timing: id 0 | task 6764 | eval time = 675.68 ms / 44 tokens ( 15.71 ms per token, 63.64 tokens per second) 2.03.949.314 I slot print_timing: id 0 | task 6764 | total time = 756.57 ms / 392 tokens 2.03.949.315 I slot print_timing: id 0 | task 6764 | graphs reused = 6469 2.03.949.316 I slot print_timing: id 0 | task 6764 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.949.345 I slot release: id 0 | task 6764 | stop processing: n_tokens = 416, truncated = 0 2.03.966.803 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 123863587 2.03.966.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.695 MiB) 2.03.988.016 I slot launch_slot_: id 0 | task 6809 | processing task, is_child = 0 2.05.141.274 I slot print_timing: id 0 | task 6809 | prompt eval time = 101.71 ms / 408 tokens ( 0.25 ms per token, 4011.37 tokens per second) 2.05.141.279 I slot print_timing: id 0 | task 6809 | eval time = 1051.53 ms / 68 tokens ( 15.69 ms per token, 63.72 tokens per second) 2.05.141.280 I slot print_timing: id 0 | task 6809 | total time = 1153.24 ms / 476 tokens 2.05.141.281 I slot print_timing: id 0 | task 6809 | graphs reused = 6535 2.05.141.282 I slot print_timing: id 0 | task 6809 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.141.312 I slot release: id 0 | task 6809 | stop processing: n_tokens = 500, truncated = 0 2.05.159.081 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 125055554 2.05.159.140 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.724 MiB) 2.05.180.734 I slot launch_slot_: id 0 | task 6878 | processing task, is_child = 0 2.06.240.155 I slot print_timing: id 0 | task 6878 | prompt eval time = 111.08 ms / 465 tokens ( 0.24 ms per token, 4186.29 tokens per second) 2.06.240.162 I slot print_timing: id 0 | task 6878 | eval time = 948.33 ms / 61 tokens ( 15.81 ms per token, 63.27 tokens per second) 2.06.240.163 I slot print_timing: id 0 | task 6878 | total time = 1059.41 ms / 526 tokens 2.06.240.164 I slot print_timing: id 0 | task 6878 | graphs reused = 6593 2.06.240.165 I slot print_timing: id 0 | task 6878 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.240.197 I slot release: id 0 | task 6878 | stop processing: n_tokens = 550, truncated = 0 2.06.257.736 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 550, t_last = 126154439 2.06.257.797 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 2.06.282.868 I slot launch_slot_: id 0 | task 6940 | processing task, is_child = 0 2.07.323.380 I slot print_timing: id 0 | task 6940 | prompt eval time = 101.53 ms / 399 tokens ( 0.25 ms per token, 3929.80 tokens per second) 2.07.323.385 I slot print_timing: id 0 | task 6940 | eval time = 938.96 ms / 60 tokens ( 15.91 ms per token, 62.84 tokens per second) 2.07.323.387 I slot print_timing: id 0 | task 6940 | total time = 1040.50 ms / 459 tokens 2.07.323.388 I slot print_timing: id 0 | task 6940 | graphs reused = 6651 2.07.323.388 I slot print_timing: id 0 | task 6940 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.323.420 I slot release: id 0 | task 6940 | stop processing: n_tokens = 500, truncated = 0 2.07.346.181 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 127237662 2.07.346.240 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.381 MiB) 2.07.350.471 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.350 MiB) 2.07.382.344 I slot launch_slot_: id 0 | task 7001 | processing task, is_child = 0 2.08.600.167 I slot print_timing: id 0 | task 7001 | prompt eval time = 102.29 ms / 419 tokens ( 0.24 ms per token, 4096.28 tokens per second) 2.08.600.173 I slot print_timing: id 0 | task 7001 | eval time = 1115.52 ms / 72 tokens ( 15.71 ms per token, 63.65 tokens per second) 2.08.600.175 I slot print_timing: id 0 | task 7001 | total time = 1217.81 ms / 491 tokens 2.08.600.176 I slot print_timing: id 0 | task 7001 | graphs reused = 6720 2.08.600.177 I slot print_timing: id 0 | task 7001 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.600.219 I slot release: id 0 | task 7001 | stop processing: n_tokens = 515, truncated = 0 2.08.628.027 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 128514461 2.08.628.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.287 MiB) 2.08.649.595 I slot launch_slot_: id 0 | task 7074 | processing task, is_child = 0 2.09.853.145 I slot print_timing: id 0 | task 7074 | prompt eval time = 102.87 ms / 440 tokens ( 0.23 ms per token, 4277.41 tokens per second) 2.09.853.150 I slot print_timing: id 0 | task 7074 | eval time = 1100.67 ms / 71 tokens ( 15.72 ms per token, 63.60 tokens per second) 2.09.853.151 I slot print_timing: id 0 | task 7074 | total time = 1203.53 ms / 511 tokens 2.09.853.152 I slot print_timing: id 0 | task 7074 | graphs reused = 6788 2.09.853.153 I slot print_timing: id 0 | task 7074 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.853.184 I slot release: id 0 | task 7074 | stop processing: n_tokens = 535, truncated = 0 2.09.875.732 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 129767426 2.09.875.793 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.662 MiB) 2.09.898.759 I slot launch_slot_: id 0 | task 7146 | processing task, is_child = 0 2.10.777.660 I slot print_timing: id 0 | task 7146 | prompt eval time = 80.19 ms / 372 tokens ( 0.22 ms per token, 4639.10 tokens per second) 2.10.777.666 I slot print_timing: id 0 | task 7146 | eval time = 798.70 ms / 52 tokens ( 15.66 ms per token, 63.85 tokens per second) 2.10.777.667 I slot print_timing: id 0 | task 7146 | total time = 878.88 ms / 424 tokens 2.10.777.668 I slot print_timing: id 0 | task 7146 | graphs reused = 6838 2.10.777.668 I slot print_timing: id 0 | task 7146 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.777.699 I slot release: id 0 | task 7146 | stop processing: n_tokens = 448, truncated = 0 2.10.798.520 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 130691941 2.10.798.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 2.10.819.144 I slot launch_slot_: id 0 | task 7199 | processing task, is_child = 0 2.11.827.495 I slot print_timing: id 0 | task 7199 | prompt eval time = 110.55 ms / 449 tokens ( 0.25 ms per token, 4061.47 tokens per second) 2.11.827.501 I slot print_timing: id 0 | task 7199 | eval time = 897.78 ms / 58 tokens ( 15.75 ms per token, 63.49 tokens per second) 2.11.827.502 I slot print_timing: id 0 | task 7199 | total time = 1008.34 ms / 507 tokens 2.11.827.502 I slot print_timing: id 0 | task 7199 | graphs reused = 6893 2.11.827.503 I slot print_timing: id 0 | task 7199 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.827.535 I slot release: id 0 | task 7199 | stop processing: n_tokens = 531, truncated = 0 2.11.842.515 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 131741777 2.11.842.565 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.506 MiB) 2.11.865.784 I slot launch_slot_: id 0 | task 7258 | processing task, is_child = 0 2.12.901.323 I slot print_timing: id 0 | task 7258 | prompt eval time = 80.98 ms / 360 tokens ( 0.22 ms per token, 4445.71 tokens per second) 2.12.901.328 I slot print_timing: id 0 | task 7258 | eval time = 954.55 ms / 62 tokens ( 15.65 ms per token, 63.90 tokens per second) 2.12.901.329 I slot print_timing: id 0 | task 7258 | total time = 1035.53 ms / 422 tokens 2.12.901.331 I slot print_timing: id 0 | task 7258 | graphs reused = 6953 2.12.901.331 I slot print_timing: id 0 | task 7258 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.901.361 I slot release: id 0 | task 7258 | stop processing: n_tokens = 446, truncated = 0 2.12.918.034 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 132815603 2.12.918.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.224 MiB) 2.12.939.645 I slot launch_slot_: id 0 | task 7321 | processing task, is_child = 0 2.13.866.318 I slot print_timing: id 0 | task 7321 | prompt eval time = 80.23 ms / 346 tokens ( 0.23 ms per token, 4312.60 tokens per second) 2.13.866.324 I slot print_timing: id 0 | task 7321 | eval time = 846.43 ms / 55 tokens ( 15.67 ms per token, 63.80 tokens per second) 2.13.866.325 I slot print_timing: id 0 | task 7321 | total time = 926.66 ms / 401 tokens 2.13.866.326 I slot print_timing: id 0 | task 7321 | graphs reused = 7006 2.13.866.327 I slot print_timing: id 0 | task 7321 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.866.355 I slot release: id 0 | task 7321 | stop processing: n_tokens = 425, truncated = 0 2.13.892.908 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 133780597 2.13.892.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 2.13.913.867 I slot launch_slot_: id 0 | task 7377 | processing task, is_child = 0 2.14.815.358 I slot print_timing: id 0 | task 7377 | prompt eval time = 102.89 ms / 434 tokens ( 0.24 ms per token, 4218.10 tokens per second) 2.14.815.363 I slot print_timing: id 0 | task 7377 | eval time = 798.59 ms / 52 tokens ( 15.66 ms per token, 63.86 tokens per second) 2.14.815.364 I slot print_timing: id 0 | task 7377 | total time = 901.48 ms / 486 tokens 2.14.815.365 I slot print_timing: id 0 | task 7377 | graphs reused = 7056 2.14.815.366 I slot print_timing: id 0 | task 7377 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.815.398 I slot release: id 0 | task 7377 | stop processing: n_tokens = 510, truncated = 0 2.14.836.073 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 134729640 2.14.836.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.943 MiB) 2.14.839.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.631 MiB) 2.14.867.140 I slot launch_slot_: id 0 | task 7430 | processing task, is_child = 0 2.15.865.995 I slot print_timing: id 0 | task 7430 | prompt eval time = 80.34 ms / 369 tokens ( 0.22 ms per token, 4593.21 tokens per second) 2.15.866.001 I slot print_timing: id 0 | task 7430 | eval time = 918.50 ms / 59 tokens ( 15.84 ms per token, 63.15 tokens per second) 2.15.866.002 I slot print_timing: id 0 | task 7430 | total time = 998.84 ms / 428 tokens 2.15.866.003 I slot print_timing: id 0 | task 7430 | graphs reused = 7113 2.15.866.004 I slot print_timing: id 0 | task 7430 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.866.035 I slot release: id 0 | task 7430 | stop processing: n_tokens = 452, truncated = 0 2.15.884.879 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 135780277 2.15.884.935 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.787 MiB) 2.15.905.664 I slot launch_slot_: id 0 | task 7490 | processing task, is_child = 0 2.17.220.882 I slot print_timing: id 0 | task 7490 | prompt eval time = 103.70 ms / 446 tokens ( 0.23 ms per token, 4301.03 tokens per second) 2.17.220.887 I slot print_timing: id 0 | task 7490 | eval time = 1211.51 ms / 78 tokens ( 15.73 ms per token, 63.56 tokens per second) 2.17.220.888 I slot print_timing: id 0 | task 7490 | total time = 1315.20 ms / 524 tokens 2.17.220.889 I slot print_timing: id 0 | task 7490 | graphs reused = 7188 2.17.220.890 I slot print_timing: id 0 | task 7490 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.220.924 I slot release: id 0 | task 7490 | stop processing: n_tokens = 548, truncated = 0 2.17.249.517 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 548, t_last = 137135166 2.17.249.580 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.850 MiB) 2.17.282.318 I slot launch_slot_: id 0 | task 7569 | processing task, is_child = 0 2.18.119.713 I slot print_timing: id 0 | task 7569 | prompt eval time = 101.53 ms / 396 tokens ( 0.26 ms per token, 3900.21 tokens per second) 2.18.119.725 I slot print_timing: id 0 | task 7569 | eval time = 735.84 ms / 48 tokens ( 15.66 ms per token, 63.87 tokens per second) 2.18.119.726 I slot print_timing: id 0 | task 7569 | total time = 837.38 ms / 444 tokens 2.18.119.727 I slot print_timing: id 0 | task 7569 | graphs reused = 7234 2.18.119.728 I slot print_timing: id 0 | task 7569 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.119.758 I slot release: id 0 | task 7569 | stop processing: n_tokens = 470, truncated = 0 2.18.124.081 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 138034000 2.18.124.140 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.412 MiB) 2.18.150.547 I slot launch_slot_: id 0 | task 7618 | processing task, is_child = 0 2.19.631.654 I slot print_timing: id 0 | task 7618 | prompt eval time = 111.21 ms / 466 tokens ( 0.24 ms per token, 4190.27 tokens per second) 2.19.631.660 I slot print_timing: id 0 | task 7618 | eval time = 1369.87 ms / 88 tokens ( 15.75 ms per token, 63.51 tokens per second) 2.19.631.661 I slot print_timing: id 0 | task 7618 | total time = 1481.08 ms / 554 tokens 2.19.631.662 I slot print_timing: id 0 | task 7618 | graphs reused = 7319 2.19.631.663 I slot print_timing: id 0 | task 7618 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.631.699 I slot release: id 0 | task 7618 | stop processing: n_tokens = 578, truncated = 0 2.19.636.060 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 578, t_last = 139545941 2.19.636.121 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 2.19.666.955 I slot launch_slot_: id 0 | task 7707 | processing task, is_child = 0 2.20.822.482 I slot print_timing: id 0 | task 7707 | prompt eval time = 111.33 ms / 467 tokens ( 0.24 ms per token, 4194.92 tokens per second) 2.20.822.488 I slot print_timing: id 0 | task 7707 | eval time = 1044.18 ms / 66 tokens ( 16.06 ms per token, 62.25 tokens per second) 2.20.822.490 I slot print_timing: id 0 | task 7707 | total time = 1155.51 ms / 533 tokens 2.20.822.490 I slot print_timing: id 0 | task 7707 | graphs reused = 7382 2.20.822.491 I slot print_timing: id 0 | task 7707 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.822.524 I slot release: id 0 | task 7707 | stop processing: n_tokens = 557, truncated = 0 2.20.844.066 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 140736766 2.20.844.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.288 MiB) 2.20.881.348 I slot launch_slot_: id 0 | task 7774 | processing task, is_child = 0 2.22.102.976 I slot print_timing: id 0 | task 7774 | prompt eval time = 111.02 ms / 454 tokens ( 0.24 ms per token, 4089.46 tokens per second) 2.22.102.982 I slot print_timing: id 0 | task 7774 | eval time = 1110.60 ms / 71 tokens ( 15.87 ms per token, 63.03 tokens per second) 2.22.102.983 I slot print_timing: id 0 | task 7774 | total time = 1221.61 ms / 525 tokens 2.22.102.984 I slot print_timing: id 0 | task 7774 | graphs reused = 7450 2.22.102.985 I slot print_timing: id 0 | task 7774 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.103.016 I slot release: id 0 | task 7774 | stop processing: n_tokens = 549, truncated = 0 2.22.118.669 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 142017259 2.22.118.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.569 MiB) 2.22.145.570 I slot launch_slot_: id 0 | task 7846 | processing task, is_child = 0 2.23.201.322 I slot print_timing: id 0 | task 7846 | prompt eval time = 102.00 ms / 409 tokens ( 0.25 ms per token, 4009.73 tokens per second) 2.23.201.328 I slot print_timing: id 0 | task 7846 | eval time = 953.73 ms / 62 tokens ( 15.63 ms per token, 63.96 tokens per second) 2.23.201.329 I slot print_timing: id 0 | task 7846 | total time = 1055.74 ms / 471 tokens 2.23.201.330 I slot print_timing: id 0 | task 7846 | graphs reused = 7510 2.23.201.331 I slot print_timing: id 0 | task 7846 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.201.366 I slot release: id 0 | task 7846 | stop processing: n_tokens = 495, truncated = 0 2.23.226.558 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 143115608 2.23.226.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 2.23.230.532 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 2.23.256.000 I slot launch_slot_: id 0 | task 7909 | processing task, is_child = 0 2.24.213.590 I slot print_timing: id 0 | task 7909 | prompt eval time = 80.60 ms / 349 tokens ( 0.23 ms per token, 4329.81 tokens per second) 2.24.213.596 I slot print_timing: id 0 | task 7909 | eval time = 876.97 ms / 57 tokens ( 15.66 ms per token, 63.86 tokens per second) 2.24.213.597 I slot print_timing: id 0 | task 7909 | total time = 957.57 ms / 406 tokens 2.24.213.598 I slot print_timing: id 0 | task 7909 | graphs reused = 7565 2.24.213.599 I slot print_timing: id 0 | task 7909 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.213.628 I slot release: id 0 | task 7909 | stop processing: n_tokens = 430, truncated = 0 2.24.240.218 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 144127870 2.24.240.267 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.163 MiB) 2.24.260.437 I slot launch_slot_: id 0 | task 7967 | processing task, is_child = 0 2.25.262.073 I slot print_timing: id 0 | task 7967 | prompt eval time = 103.34 ms / 435 tokens ( 0.24 ms per token, 4209.57 tokens per second) 2.25.262.079 I slot print_timing: id 0 | task 7967 | eval time = 898.28 ms / 58 tokens ( 15.76 ms per token, 63.45 tokens per second) 2.25.262.080 I slot print_timing: id 0 | task 7967 | total time = 1001.62 ms / 493 tokens 2.25.262.081 I slot print_timing: id 0 | task 7967 | graphs reused = 7620 2.25.262.082 I slot print_timing: id 0 | task 7967 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.262.114 I slot release: id 0 | task 7967 | stop processing: n_tokens = 517, truncated = 0 2.25.280.869 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 145176356 2.25.280.927 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.319 MiB) 2.25.303.841 I slot launch_slot_: id 0 | task 8026 | processing task, is_child = 0 2.26.117.951 I slot print_timing: id 0 | task 8026 | prompt eval time = 74.12 ms / 322 tokens ( 0.23 ms per token, 4344.07 tokens per second) 2.26.117.957 I slot print_timing: id 0 | task 8026 | eval time = 739.97 ms / 47 tokens ( 16.09 ms per token, 62.16 tokens per second) 2.26.117.958 I slot print_timing: id 0 | task 8026 | total time = 814.10 ms / 369 tokens 2.26.117.959 I slot print_timing: id 0 | task 8026 | graphs reused = 7665 2.26.117.959 I slot print_timing: id 0 | task 8026 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.117.988 I slot release: id 0 | task 8026 | stop processing: n_tokens = 393, truncated = 0 2.26.137.571 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 146032230 2.26.155.915 I slot launch_slot_: id 0 | task 8074 | processing task, is_child = 0 2.27.097.341 I slot print_timing: id 0 | task 8074 | prompt eval time = 80.59 ms / 360 tokens ( 0.22 ms per token, 4467.28 tokens per second) 2.27.097.347 I slot print_timing: id 0 | task 8074 | eval time = 860.83 ms / 56 tokens ( 15.65 ms per token, 63.89 tokens per second) 2.27.097.348 I slot print_timing: id 0 | task 8074 | total time = 941.41 ms / 416 tokens 2.27.097.349 I slot print_timing: id 0 | task 8074 | graphs reused = 7719 2.27.097.350 I slot print_timing: id 0 | task 8074 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.097.380 I slot release: id 0 | task 8074 | stop processing: n_tokens = 440, truncated = 0 2.27.119.034 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 147011622 2.27.119.090 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 2.27.123.053 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.255 MiB) 2.27.145.236 I slot launch_slot_: id 0 | task 8131 | processing task, is_child = 0 2.28.381.542 I slot print_timing: id 0 | task 8131 | prompt eval time = 103.50 ms / 443 tokens ( 0.23 ms per token, 4279.99 tokens per second) 2.28.381.548 I slot print_timing: id 0 | task 8131 | eval time = 1132.79 ms / 73 tokens ( 15.73 ms per token, 63.56 tokens per second) 2.28.381.549 I slot print_timing: id 0 | task 8131 | total time = 1236.29 ms / 516 tokens 2.28.381.550 I slot print_timing: id 0 | task 8131 | graphs reused = 7789 2.28.381.550 I slot print_timing: id 0 | task 8131 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.381.584 I slot release: id 0 | task 8131 | stop processing: n_tokens = 540, truncated = 0 2.28.401.105 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 148295826 2.28.401.168 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.944 MiB) 2.28.425.468 I slot launch_slot_: id 0 | task 8205 | processing task, is_child = 0 2.29.202.638 I slot print_timing: id 0 | task 8205 | prompt eval time = 103.07 ms / 442 tokens ( 0.23 ms per token, 4288.26 tokens per second) 2.29.202.644 I slot print_timing: id 0 | task 8205 | eval time = 674.08 ms / 44 tokens ( 15.68 ms per token, 63.79 tokens per second) 2.29.202.646 I slot print_timing: id 0 | task 8205 | total time = 777.15 ms / 486 tokens 2.29.202.646 I slot print_timing: id 0 | task 8205 | graphs reused = 7831 2.29.202.648 I slot print_timing: id 0 | task 8205 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.202.678 I slot release: id 0 | task 8205 | stop processing: n_tokens = 510, truncated = 0 2.29.224.755 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 149116920 2.29.224.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.069 MiB) 2.29.247.510 I slot launch_slot_: id 0 | task 8250 | processing task, is_child = 0 2.30.039.751 I slot print_timing: id 0 | task 8250 | prompt eval time = 111.23 ms / 470 tokens ( 0.24 ms per token, 4225.63 tokens per second) 2.30.039.757 I slot print_timing: id 0 | task 8250 | eval time = 681.00 ms / 44 tokens ( 15.84 ms per token, 63.14 tokens per second) 2.30.039.758 I slot print_timing: id 0 | task 8250 | total time = 792.23 ms / 514 tokens 2.30.039.759 I slot print_timing: id 0 | task 8250 | graphs reused = 7872 2.30.039.760 I slot print_timing: id 0 | task 8250 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.039.793 I slot release: id 0 | task 8250 | stop processing: n_tokens = 538, truncated = 0 2.30.066.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 538, t_last = 149954036 2.30.066.698 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 2.30.094.821 I slot launch_slot_: id 0 | task 8295 | processing task, is_child = 0 2.30.732.548 I slot print_timing: id 0 | task 8295 | prompt eval time = 112.25 ms / 483 tokens ( 0.23 ms per token, 4302.78 tokens per second) 2.30.732.554 I slot print_timing: id 0 | task 8295 | eval time = 525.46 ms / 34 tokens ( 15.92 ms per token, 62.80 tokens per second) 2.30.732.555 I slot print_timing: id 0 | task 8295 | total time = 637.71 ms / 517 tokens 2.30.732.556 I slot print_timing: id 0 | task 8295 | graphs reused = 7903 2.30.732.557 I slot print_timing: id 0 | task 8295 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.732.590 I slot release: id 0 | task 8295 | stop processing: n_tokens = 541, truncated = 0 2.30.753.382 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 150646832 2.30.753.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 2.30.779.183 I slot launch_slot_: id 0 | task 8330 | processing task, is_child = 0 2.31.743.163 I slot print_timing: id 0 | task 8330 | prompt eval time = 111.48 ms / 463 tokens ( 0.24 ms per token, 4153.14 tokens per second) 2.31.743.168 I slot print_timing: id 0 | task 8330 | eval time = 852.48 ms / 55 tokens ( 15.79 ms per token, 63.34 tokens per second) 2.31.743.169 I slot print_timing: id 0 | task 8330 | total time = 963.96 ms / 518 tokens 2.31.743.170 I slot print_timing: id 0 | task 8330 | graphs reused = 7955 2.31.743.171 I slot print_timing: id 0 | task 8330 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.743.203 I slot release: id 0 | task 8330 | stop processing: n_tokens = 542, truncated = 0 2.31.772.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 151657445 2.31.772.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.474 MiB) 2.31.776.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 2.31.802.801 I slot launch_slot_: id 0 | task 8386 | processing task, is_child = 0 2.32.672.231 I slot print_timing: id 0 | task 8386 | prompt eval time = 102.28 ms / 421 tokens ( 0.24 ms per token, 4116.27 tokens per second) 2.32.672.236 I slot print_timing: id 0 | task 8386 | eval time = 767.14 ms / 50 tokens ( 15.66 ms per token, 63.87 tokens per second) 2.32.672.238 I slot print_timing: id 0 | task 8386 | total time = 869.42 ms / 471 tokens 2.32.672.239 I slot print_timing: id 0 | task 8386 | graphs reused = 8003 2.32.672.240 I slot print_timing: id 0 | task 8386 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.672.270 I slot release: id 0 | task 8386 | stop processing: n_tokens = 495, truncated = 0 2.32.694.046 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 152586513 2.32.694.106 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 2.32.717.161 I slot launch_slot_: id 0 | task 8437 | processing task, is_child = 0 2.33.456.450 I slot print_timing: id 0 | task 8437 | prompt eval time = 80.86 ms / 360 tokens ( 0.22 ms per token, 4452.25 tokens per second) 2.33.456.456 I slot print_timing: id 0 | task 8437 | eval time = 658.41 ms / 43 tokens ( 15.68 ms per token, 63.79 tokens per second) 2.33.456.457 I slot print_timing: id 0 | task 8437 | total time = 739.27 ms / 403 tokens 2.33.456.458 I slot print_timing: id 0 | task 8437 | graphs reused = 8044 2.33.456.459 I slot print_timing: id 0 | task 8437 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.456.487 I slot release: id 0 | task 8437 | stop processing: n_tokens = 427, truncated = 0 2.33.476.202 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 153370730 2.33.476.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.255 MiB) 2.33.497.420 I slot launch_slot_: id 0 | task 8481 | processing task, is_child = 0 2.34.705.381 I slot print_timing: id 0 | task 8481 | prompt eval time = 136.99 ms / 547 tokens ( 0.25 ms per token, 3993.14 tokens per second) 2.34.705.387 I slot print_timing: id 0 | task 8481 | eval time = 1070.96 ms / 69 tokens ( 15.75 ms per token, 63.49 tokens per second) 2.34.705.388 I slot print_timing: id 0 | task 8481 | total time = 1207.95 ms / 616 tokens 2.34.705.389 I slot print_timing: id 0 | task 8481 | graphs reused = 8111 2.34.705.390 I slot print_timing: id 0 | task 8481 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.705.425 I slot release: id 0 | task 8481 | stop processing: n_tokens = 640, truncated = 0 2.34.728.750 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 640, t_last = 154619667 2.34.728.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 2.34.733.136 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.664 MiB) 2.34.765.784 I slot launch_slot_: id 0 | task 8551 | processing task, is_child = 0 2.36.612.744 I slot print_timing: id 0 | task 8551 | prompt eval time = 176.94 ms / 749 tokens ( 0.24 ms per token, 4233.12 tokens per second) 2.36.612.750 I slot print_timing: id 0 | task 8551 | eval time = 1670.00 ms / 107 tokens ( 15.75 ms per token, 63.47 tokens per second) 2.36.612.751 I slot print_timing: id 0 | task 8551 | total time = 1846.94 ms / 856 tokens 2.36.612.752 I slot print_timing: id 0 | task 8551 | graphs reused = 8216 2.36.612.753 I slot print_timing: id 0 | task 8551 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.612.793 I slot release: id 0 | task 8551 | stop processing: n_tokens = 880, truncated = 0 2.36.635.920 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 156527035 2.36.635.994 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 2.36.639.774 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.193 MiB) 2.36.676.766 I slot launch_slot_: id 0 | task 8659 | processing task, is_child = 0 2.37.578.950 I slot print_timing: id 0 | task 8659 | prompt eval time = 161.38 ms / 678 tokens ( 0.24 ms per token, 4201.24 tokens per second) 2.37.578.956 I slot print_timing: id 0 | task 8659 | eval time = 740.78 ms / 48 tokens ( 15.76 ms per token, 63.45 tokens per second) 2.37.578.957 I slot print_timing: id 0 | task 8659 | total time = 902.17 ms / 726 tokens 2.37.578.958 I slot print_timing: id 0 | task 8659 | graphs reused = 8262 2.37.578.959 I slot print_timing: id 0 | task 8659 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.578.996 I slot release: id 0 | task 8659 | stop processing: n_tokens = 750, truncated = 0 2.37.607.035 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 157493238 2.37.607.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.600 MiB) 2.37.638.739 I slot launch_slot_: id 0 | task 8708 | processing task, is_child = 0 2.38.666.024 I slot print_timing: id 0 | task 8708 | prompt eval time = 137.43 ms / 567 tokens ( 0.24 ms per token, 4125.86 tokens per second) 2.38.666.029 I slot print_timing: id 0 | task 8708 | eval time = 889.84 ms / 57 tokens ( 15.89 ms per token, 62.93 tokens per second) 2.38.666.030 I slot print_timing: id 0 | task 8708 | total time = 1027.27 ms / 624 tokens 2.38.666.031 I slot print_timing: id 0 | task 8708 | graphs reused = 8317 2.38.666.032 I slot print_timing: id 0 | task 8708 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.666.066 I slot release: id 0 | task 8708 | stop processing: n_tokens = 648, truncated = 0 2.38.696.025 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 158580308 2.38.696.083 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.194 MiB) 2.38.728.555 I slot launch_slot_: id 0 | task 8766 | processing task, is_child = 0 2.39.742.096 I slot print_timing: id 0 | task 8766 | prompt eval time = 114.25 ms / 501 tokens ( 0.23 ms per token, 4385.08 tokens per second) 2.39.742.103 I slot print_timing: id 0 | task 8766 | eval time = 899.27 ms / 58 tokens ( 15.78 ms per token, 63.38 tokens per second) 2.39.742.104 I slot print_timing: id 0 | task 8766 | total time = 1013.52 ms / 559 tokens 2.39.742.107 I slot print_timing: id 0 | task 8766 | graphs reused = 8373 2.39.742.108 I slot print_timing: id 0 | task 8766 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.742.146 I slot release: id 0 | task 8766 | stop processing: n_tokens = 583, truncated = 0 2.39.761.755 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 159656388 2.39.761.819 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 2.39.765.639 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 2.39.794.907 I slot launch_slot_: id 0 | task 8825 | processing task, is_child = 0 2.40.935.411 I slot print_timing: id 0 | task 8825 | prompt eval time = 177.79 ms / 769 tokens ( 0.23 ms per token, 4325.30 tokens per second) 2.40.935.417 I slot print_timing: id 0 | task 8825 | eval time = 962.70 ms / 62 tokens ( 15.78 ms per token, 63.36 tokens per second) 2.40.935.418 I slot print_timing: id 0 | task 8825 | total time = 1140.49 ms / 831 tokens 2.40.935.419 I slot print_timing: id 0 | task 8825 | graphs reused = 8433 2.40.935.420 I slot print_timing: id 0 | task 8825 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.935.461 I slot release: id 0 | task 8825 | stop processing: n_tokens = 855, truncated = 0 2.40.962.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 160849703 2.40.962.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.381 MiB) 2.40.967.531 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 2.41.005.932 I slot launch_slot_: id 0 | task 8888 | processing task, is_child = 0 2.42.074.557 I slot print_timing: id 0 | task 8888 | prompt eval time = 114.02 ms / 500 tokens ( 0.23 ms per token, 4385.04 tokens per second) 2.42.074.563 I slot print_timing: id 0 | task 8888 | eval time = 954.57 ms / 61 tokens ( 15.91 ms per token, 62.86 tokens per second) 2.42.074.564 I slot print_timing: id 0 | task 8888 | total time = 1068.60 ms / 561 tokens 2.42.074.565 I slot print_timing: id 0 | task 8888 | graphs reused = 8492 2.42.074.566 I slot print_timing: id 0 | task 8888 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.074.603 I slot release: id 0 | task 8888 | stop processing: n_tokens = 585, truncated = 0 2.42.104.506 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 161988845 2.42.104.573 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 2.42.135.604 I slot launch_slot_: id 0 | task 8950 | processing task, is_child = 0 2.43.194.858 I slot print_timing: id 0 | task 8950 | prompt eval time = 149.18 ms / 632 tokens ( 0.24 ms per token, 4236.46 tokens per second) 2.43.194.863 I slot print_timing: id 0 | task 8950 | eval time = 910.05 ms / 58 tokens ( 15.97 ms per token, 62.63 tokens per second) 2.43.194.865 I slot print_timing: id 0 | task 8950 | total time = 1059.23 ms / 690 tokens 2.43.194.865 I slot print_timing: id 0 | task 8950 | graphs reused = 8548 2.43.194.866 I slot print_timing: id 0 | task 8950 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.194.904 I slot release: id 0 | task 8950 | stop processing: n_tokens = 714, truncated = 0 2.43.199.735 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 163109146 2.43.199.804 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 2.43.204.424 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.945 MiB) 2.43.234.155 I slot launch_slot_: id 0 | task 9009 | processing task, is_child = 0 2.43.901.002 I slot print_timing: id 0 | task 9009 | prompt eval time = 101.47 ms / 395 tokens ( 0.26 ms per token, 3892.85 tokens per second) 2.43.901.008 I slot print_timing: id 0 | task 9009 | eval time = 565.36 ms / 37 tokens ( 15.70 ms per token, 63.68 tokens per second) 2.43.901.009 I slot print_timing: id 0 | task 9009 | total time = 666.83 ms / 432 tokens 2.43.901.010 I slot print_timing: id 0 | task 9009 | graphs reused = 8583 2.43.901.011 I slot print_timing: id 0 | task 9009 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.901.041 I slot release: id 0 | task 9009 | stop processing: n_tokens = 456, truncated = 0 2.43.928.818 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 163815283 2.43.928.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.539 MiB) 2.43.950.864 I slot launch_slot_: id 0 | task 9047 | processing task, is_child = 0 2.45.023.927 I slot print_timing: id 0 | task 9047 | prompt eval time = 141.25 ms / 579 tokens ( 0.24 ms per token, 4099.12 tokens per second) 2.45.023.932 I slot print_timing: id 0 | task 9047 | eval time = 931.80 ms / 59 tokens ( 16.07 ms per token, 62.25 tokens per second) 2.45.023.933 I slot print_timing: id 0 | task 9047 | total time = 1073.05 ms / 638 tokens 2.45.023.934 I slot print_timing: id 0 | task 9047 | graphs reused = 8640 2.45.023.935 I slot print_timing: id 0 | task 9047 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.023.973 I slot release: id 0 | task 9047 | stop processing: n_tokens = 662, truncated = 0 2.45.030.933 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 662, t_last = 164938216 2.45.030.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.256 MiB) 2.45.059.398 I slot launch_slot_: id 0 | task 9107 | processing task, is_child = 0 2.45.939.148 I slot print_timing: id 0 | task 9107 | prompt eval time = 160.61 ms / 689 tokens ( 0.23 ms per token, 4289.87 tokens per second) 2.45.939.153 I slot print_timing: id 0 | task 9107 | eval time = 719.12 ms / 46 tokens ( 15.98 ms per token, 62.58 tokens per second) 2.45.939.154 I slot print_timing: id 0 | task 9107 | total time = 879.73 ms / 735 tokens 2.45.939.155 I slot print_timing: id 0 | task 9107 | graphs reused = 8684 2.45.939.156 I slot print_timing: id 0 | task 9107 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.939.196 I slot release: id 0 | task 9107 | stop processing: n_tokens = 759, truncated = 0 2.45.956.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 759, t_last = 165853438 2.45.956.994 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 2.45.990.826 I slot launch_slot_: id 0 | task 9154 | processing task, is_child = 0 2.47.198.693 I slot print_timing: id 0 | task 9154 | prompt eval time = 172.00 ms / 752 tokens ( 0.23 ms per token, 4372.14 tokens per second) 2.47.198.699 I slot print_timing: id 0 | task 9154 | eval time = 1035.85 ms / 66 tokens ( 15.94 ms per token, 62.75 tokens per second) 2.47.198.700 I slot print_timing: id 0 | task 9154 | total time = 1207.85 ms / 818 tokens 2.47.198.701 I slot print_timing: id 0 | task 9154 | graphs reused = 8748 2.47.198.702 I slot print_timing: id 0 | task 9154 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.198.745 I slot release: id 0 | task 9154 | stop processing: n_tokens = 842, truncated = 0 2.47.220.831 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 842, t_last = 167112987 2.47.220.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.974 MiB) 2.47.224.676 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 2.47.265.100 I slot launch_slot_: id 0 | task 9221 | processing task, is_child = 0 2.48.445.327 I slot print_timing: id 0 | task 9221 | prompt eval time = 140.22 ms / 582 tokens ( 0.24 ms per token, 4150.62 tokens per second) 2.48.445.333 I slot print_timing: id 0 | task 9221 | eval time = 1039.99 ms / 67 tokens ( 15.76 ms per token, 63.46 tokens per second) 2.48.445.334 I slot print_timing: id 0 | task 9221 | total time = 1180.21 ms / 649 tokens 2.48.445.335 I slot print_timing: id 0 | task 9221 | graphs reused = 8813 2.48.445.336 I slot print_timing: id 0 | task 9221 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.445.372 I slot release: id 0 | task 9221 | stop processing: n_tokens = 673, truncated = 0 2.48.466.100 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 673, t_last = 168359615 2.48.466.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.320 MiB) 2.48.503.505 I slot launch_slot_: id 0 | task 9289 | processing task, is_child = 0 2.49.859.766 I slot print_timing: id 0 | task 9289 | prompt eval time = 157.23 ms / 656 tokens ( 0.24 ms per token, 4172.28 tokens per second) 2.49.859.773 I slot print_timing: id 0 | task 9289 | eval time = 1199.02 ms / 77 tokens ( 15.78 ms per token, 63.39 tokens per second) 2.49.859.774 I slot print_timing: id 0 | task 9289 | total time = 1356.24 ms / 733 tokens 2.49.859.774 I slot print_timing: id 0 | task 9289 | graphs reused = 8888 2.49.859.776 I slot print_timing: id 0 | task 9289 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.859.813 I slot release: id 0 | task 9289 | stop processing: n_tokens = 757, truncated = 0 2.49.890.319 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 169774055 2.49.890.388 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 2.49.896.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.603 MiB) 2.49.936.460 I slot launch_slot_: id 0 | task 9367 | processing task, is_child = 0 2.50.557.500 I slot print_timing: id 0 | task 9367 | prompt eval time = 145.81 ms / 613 tokens ( 0.24 ms per token, 4203.99 tokens per second) 2.50.557.506 I slot print_timing: id 0 | task 9367 | eval time = 475.21 ms / 31 tokens ( 15.84 ms per token, 63.13 tokens per second) 2.50.557.507 I slot print_timing: id 0 | task 9367 | total time = 621.02 ms / 644 tokens 2.50.557.508 I slot print_timing: id 0 | task 9367 | graphs reused = 8917 2.50.557.509 I slot print_timing: id 0 | task 9367 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.557.548 I slot release: id 0 | task 9367 | stop processing: n_tokens = 668, truncated = 0 2.50.579.417 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 668, t_last = 170471790 2.50.601.958 I slot launch_slot_: id 0 | task 9399 | processing task, is_child = 0 2.52.307.950 I slot print_timing: id 0 | task 9399 | prompt eval time = 172.73 ms / 766 tokens ( 0.23 ms per token, 4434.59 tokens per second) 2.52.307.956 I slot print_timing: id 0 | task 9399 | eval time = 1533.24 ms / 97 tokens ( 15.97 ms per token, 62.61 tokens per second) 2.52.307.957 I slot print_timing: id 0 | task 9399 | total time = 1705.98 ms / 863 tokens 2.52.307.959 I slot print_timing: id 0 | task 9399 | graphs reused = 9012 2.52.307.960 I slot print_timing: id 0 | task 9399 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.308.004 I slot release: id 0 | task 9399 | stop processing: n_tokens = 887, truncated = 0 2.52.338.736 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 172222247 2.52.338.811 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 112.353 MiB) 2.52.345.487 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 2.52.386.620 I slot launch_slot_: id 0 | task 9497 | processing task, is_child = 0 2.53.530.340 I slot print_timing: id 0 | task 9497 | prompt eval time = 187.16 ms / 846 tokens ( 0.22 ms per token, 4520.17 tokens per second) 2.53.530.346 I slot print_timing: id 0 | task 9497 | eval time = 956.54 ms / 61 tokens ( 15.94 ms per token, 62.73 tokens per second) 2.53.530.348 I slot print_timing: id 0 | task 9497 | total time = 1143.70 ms / 907 tokens 2.53.530.349 I slot print_timing: id 0 | task 9497 | graphs reused = 9071 2.53.530.350 I slot print_timing: id 0 | task 9497 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.530.397 I slot release: id 0 | task 9497 | stop processing: n_tokens = 931, truncated = 0 2.53.560.219 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 173444639 2.53.560.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.415 MiB) 2.53.606.819 I slot launch_slot_: id 0 | task 9559 | processing task, is_child = 0 2.54.960.669 I slot print_timing: id 0 | task 9559 | prompt eval time = 157.11 ms / 650 tokens ( 0.24 ms per token, 4137.28 tokens per second) 2.54.960.674 I slot print_timing: id 0 | task 9559 | eval time = 1196.73 ms / 77 tokens ( 15.75 ms per token, 63.51 tokens per second) 2.54.960.676 I slot print_timing: id 0 | task 9559 | total time = 1353.83 ms / 727 tokens 2.54.960.676 I slot print_timing: id 0 | task 9559 | graphs reused = 9146 2.54.960.677 I slot print_timing: id 0 | task 9559 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.960.717 I slot release: id 0 | task 9559 | stop processing: n_tokens = 751, truncated = 0 2.54.984.342 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 174874959 2.54.984.409 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.102 MiB) 2.55.025.073 I slot launch_slot_: id 0 | task 9637 | processing task, is_child = 0 2.56.017.494 I slot print_timing: id 0 | task 9637 | prompt eval time = 166.94 ms / 717 tokens ( 0.23 ms per token, 4294.96 tokens per second) 2.56.017.499 I slot print_timing: id 0 | task 9637 | eval time = 825.46 ms / 53 tokens ( 15.87 ms per token, 62.99 tokens per second) 2.56.017.501 I slot print_timing: id 0 | task 9637 | total time = 992.40 ms / 770 tokens 2.56.017.501 I slot print_timing: id 0 | task 9637 | graphs reused = 9196 2.56.017.502 I slot print_timing: id 0 | task 9637 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.017.541 I slot release: id 0 | task 9637 | stop processing: n_tokens = 794, truncated = 0 2.56.036.607 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 794, t_last = 175931783 2.56.036.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.008 MiB) 2.56.042.115 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.507 MiB) 2.56.086.148 I slot launch_slot_: id 0 | task 9691 | processing task, is_child = 0 2.57.114.967 I slot print_timing: id 0 | task 9691 | prompt eval time = 113.64 ms / 494 tokens ( 0.23 ms per token, 4347.25 tokens per second) 2.57.114.972 I slot print_timing: id 0 | task 9691 | eval time = 915.17 ms / 59 tokens ( 15.78 ms per token, 63.38 tokens per second) 2.57.114.974 I slot print_timing: id 0 | task 9691 | total time = 1028.80 ms / 553 tokens 2.57.114.974 I slot print_timing: id 0 | task 9691 | graphs reused = 9253 2.57.114.975 I slot print_timing: id 0 | task 9691 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.115.007 I slot release: id 0 | task 9691 | stop processing: n_tokens = 577, truncated = 0 2.57.142.298 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 177029249 2.57.142.361 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.039 MiB) 2.57.171.717 I slot launch_slot_: id 0 | task 9751 | processing task, is_child = 0 2.58.146.830 I slot print_timing: id 0 | task 9751 | prompt eval time = 140.51 ms / 579 tokens ( 0.24 ms per token, 4120.82 tokens per second) 2.58.146.835 I slot print_timing: id 0 | task 9751 | eval time = 834.59 ms / 54 tokens ( 15.75 ms per token, 63.50 tokens per second) 2.58.146.837 I slot print_timing: id 0 | task 9751 | total time = 975.09 ms / 633 tokens 2.58.146.837 I slot print_timing: id 0 | task 9751 | graphs reused = 9305 2.58.146.838 I slot print_timing: id 0 | task 9751 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.146.876 I slot release: id 0 | task 9751 | stop processing: n_tokens = 657, truncated = 0 2.58.177.915 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 657, t_last = 178061118 2.58.177.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 102.040 MiB) 2.58.209.431 I slot launch_slot_: id 0 | task 9806 | processing task, is_child = 0 2.59.576.816 I slot print_timing: id 0 | task 9806 | prompt eval time = 214.45 ms / 919 tokens ( 0.23 ms per token, 4285.36 tokens per second) 2.59.576.821 I slot print_timing: id 0 | task 9806 | eval time = 1152.91 ms / 73 tokens ( 16.01 ms per token, 62.45 tokens per second) 2.59.576.823 I slot print_timing: id 0 | task 9806 | total time = 1367.37 ms / 992 tokens 2.59.576.823 I slot print_timing: id 0 | task 9806 | graphs reused = 9376 2.59.576.824 I slot print_timing: id 0 | task 9806 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.576.872 I slot release: id 0 | task 9806 | stop processing: n_tokens = 1016, truncated = 0 2.59.583.870 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 179491114 2.59.583.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.194 MiB) 2.59.588.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.477 MiB) 2.59.632.540 I slot launch_slot_: id 0 | task 9880 | processing task, is_child = 0 3.00.427.782 I slot print_timing: id 0 | task 9880 | prompt eval time = 192.54 ms / 865 tokens ( 0.22 ms per token, 4492.55 tokens per second) 3.00.427.788 I slot print_timing: id 0 | task 9880 | eval time = 602.68 ms / 39 tokens ( 15.86 ms per token, 63.05 tokens per second) 3.00.427.789 I slot print_timing: id 0 | task 9880 | total time = 795.23 ms / 904 tokens 3.00.427.790 I slot print_timing: id 0 | task 9880 | graphs reused = 9413 3.00.427.791 I slot print_timing: id 0 | task 9880 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.427.836 I slot release: id 0 | task 9880 | stop processing: n_tokens = 928, truncated = 0 3.00.432.137 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 180342078 3.00.432.217 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.476 MiB) 3.00.470.294 I slot launch_slot_: id 0 | task 9920 | processing task, is_child = 0 3.03.584.961 I slot print_timing: id 0 | task 9920 | n_gen = 193, tg = 63.73 t/s, tg_3s = 64.06 t/s 3.06.587.077 I slot print_timing: id 0 | task 9920 | n_gen = 384, tg = 63.68 t/s, tg_3s = 63.62 t/s 3.09.592.502 I slot print_timing: id 0 | task 9920 | n_gen = 574, tg = 63.52 t/s, tg_3s = 63.22 t/s 3.12.600.217 I slot print_timing: id 0 | task 9920 | n_gen = 763, tg = 63.35 t/s, tg_3s = 62.84 t/s 3.15.615.631 I slot print_timing: id 0 | task 9920 | n_gen = 952, tg = 63.22 t/s, tg_3s = 62.68 t/s 3.16.764.301 I slot print_timing: id 0 | task 9920 | prompt eval time = 101.90 ms / 408 tokens ( 0.25 ms per token, 4003.93 tokens per second) 3.16.764.306 I slot print_timing: id 0 | task 9920 | eval time = 16192.09 ms / 1024 tokens ( 15.83 ms per token, 63.18 tokens per second) 3.16.764.307 I slot print_timing: id 0 | task 9920 | total time = 16293.99 ms / 1432 tokens 3.16.764.307 I slot print_timing: id 0 | task 9920 | graphs reused = 10431 3.16.764.309 I slot print_timing: id 0 | task 9920 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.764.342 I slot release: id 0 | task 9920 | stop processing: n_tokens = 1456, truncated = 0 3.16.788.523 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1456, t_last = 196678584 3.16.788.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.507 MiB) 3.16.793.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.038 MiB) 3.16.798.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.225 MiB) 3.16.865.111 I slot launch_slot_: id 0 | task 10945 | processing task, is_child = 0 3.19.117.052 I slot print_timing: id 0 | task 10945 | prompt eval time = 80.29 ms / 338 tokens ( 0.24 ms per token, 4209.53 tokens per second) 3.19.117.057 I slot print_timing: id 0 | task 10945 | eval time = 2171.63 ms / 140 tokens ( 15.62 ms per token, 64.01 tokens per second) 3.19.117.058 I slot print_timing: id 0 | task 10945 | total time = 2251.93 ms / 478 tokens 3.19.117.059 I slot print_timing: id 0 | task 10945 | graphs reused = 10569 3.19.117.060 I slot print_timing: id 0 | task 10945 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.117.090 I slot release: id 0 | task 10945 | stop processing: n_tokens = 504, truncated = 0 3.19.121.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 199031332 3.19.121.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.884 MiB) 3.19.149.528 I slot launch_slot_: id 0 | task 11086 | processing task, is_child = 0 3.22.242.605 I slot print_timing: id 0 | task 11086 | n_gen = 193, tg = 63.74 t/s, tg_3s = 64.07 t/s 3.25.246.976 I slot print_timing: id 0 | task 11086 | n_gen = 384, tg = 63.66 t/s, tg_3s = 63.57 t/s 3.28.254.588 I slot print_timing: id 0 | task 11086 | n_gen = 575, tg = 63.61 t/s, tg_3s = 63.51 t/s 3.31.268.419 I slot print_timing: id 0 | task 11086 | n_gen = 765, tg = 63.47 t/s, tg_3s = 63.04 t/s 3.34.279.874 I slot print_timing: id 0 | task 11086 | n_gen = 954, tg = 63.32 t/s, tg_3s = 62.76 t/s 3.35.397.610 I slot print_timing: id 0 | task 11086 | prompt eval time = 80.82 ms / 363 tokens ( 0.22 ms per token, 4491.30 tokens per second) 3.35.397.615 I slot print_timing: id 0 | task 11086 | eval time = 16167.25 ms / 1024 tokens ( 15.80 ms per token, 63.28 tokens per second) 3.35.397.616 I slot print_timing: id 0 | task 11086 | total time = 16248.07 ms / 1387 tokens 3.35.397.617 I slot print_timing: id 0 | task 11086 | graphs reused = 11587 3.35.397.618 I slot print_timing: id 0 | task 11086 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.397.645 I slot release: id 0 | task 11086 | stop processing: n_tokens = 1413, truncated = 0 3.35.418.522 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1413, t_last = 215311887 3.35.418.618 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 3.35.423.690 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.387 MiB) 3.35.485.277 I slot launch_slot_: id 0 | task 12111 | processing task, is_child = 0 3.38.571.001 I slot print_timing: id 0 | task 12111 | n_gen = 193, tg = 63.76 t/s, tg_3s = 64.09 t/s 3.41.585.112 I slot print_timing: id 0 | task 12111 | n_gen = 385, tg = 63.73 t/s, tg_3s = 63.70 t/s 3.44.594.404 I slot print_timing: id 0 | task 12111 | n_gen = 576, tg = 63.64 t/s, tg_3s = 63.47 t/s 3.47.600.188 I slot print_timing: id 0 | task 12111 | n_gen = 766, tg = 63.54 t/s, tg_3s = 63.21 t/s 3.50.607.289 I slot print_timing: id 0 | task 12111 | n_gen = 955, tg = 63.40 t/s, tg_3s = 62.85 t/s 3.51.707.832 I slot print_timing: id 0 | task 12111 | prompt eval time = 74.41 ms / 317 tokens ( 0.23 ms per token, 4259.95 tokens per second) 3.51.707.837 I slot print_timing: id 0 | task 12111 | eval time = 16148.12 ms / 1024 tokens ( 15.79 ms per token, 63.35 tokens per second) 3.51.707.838 I slot print_timing: id 0 | task 12111 | total time = 16222.54 ms / 1341 tokens 3.51.707.838 I slot print_timing: id 0 | task 12111 | graphs reused = 12605 3.51.707.839 I slot print_timing: id 0 | task 12111 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.707.867 I slot release: id 0 | task 12111 | stop processing: n_tokens = 1367, truncated = 0 3.51.728.751 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1367, t_last = 231622110 3.51.728.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.413 MiB) 3.51.733.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.791 MiB) 3.51.788.322 I slot launch_slot_: id 0 | task 13136 | processing task, is_child = 0 3.54.902.174 I slot print_timing: id 0 | task 13136 | n_gen = 193, tg = 63.73 t/s, tg_3s = 64.06 t/s 3.57.904.947 I slot print_timing: id 0 | task 13136 | n_gen = 384, tg = 63.67 t/s, tg_3s = 63.61 t/s 3.59.666.787 I slot print_timing: id 0 | task 13136 | prompt eval time = 101.19 ms / 389 tokens ( 0.26 ms per token, 3844.37 tokens per second) 3.59.666.793 I slot print_timing: id 0 | task 13136 | eval time = 7777.26 ms / 496 tokens ( 15.71 ms per token, 63.65 tokens per second) 3.59.666.794 I slot print_timing: id 0 | task 13136 | total time = 7878.45 ms / 885 tokens 3.59.666.795 I slot print_timing: id 0 | task 13136 | graphs reused = 13097 3.59.666.796 I slot print_timing: id 0 | task 13136 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.666.825 I slot release: id 0 | task 13136 | stop processing: n_tokens = 909, truncated = 0 3.59.682.519 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 909, t_last = 239581068 3.59.682.587 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.073 MiB) 3.59.726.750 I slot launch_slot_: id 0 | task 13633 | processing task, is_child = 0 4.00.273.066 I slot print_timing: id 0 | task 13633 | prompt eval time = 73.73 ms / 300 tokens ( 0.25 ms per token, 4068.90 tokens per second) 4.00.273.072 I slot print_timing: id 0 | task 13633 | eval time = 472.57 ms / 31 tokens ( 15.75 ms per token, 63.48 tokens per second) 4.00.273.073 I slot print_timing: id 0 | task 13633 | total time = 546.30 ms / 331 tokens 4.00.273.074 I slot print_timing: id 0 | task 13633 | graphs reused = 13126 4.00.273.075 I slot print_timing: id 0 | task 13633 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.273.102 I slot release: id 0 | task 13633 | stop processing: n_tokens = 355, truncated = 0 4.00.277.384 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 240187344 4.00.277.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 86.101 MiB) 4.00.293.861 I slot launch_slot_: id 0 | task 13665 | processing task, is_child = 0 4.01.080.206 I slot print_timing: id 0 | task 13665 | prompt eval time = 80.17 ms / 341 tokens ( 0.24 ms per token, 4253.25 tokens per second) 4.01.080.212 I slot print_timing: id 0 | task 13665 | eval time = 706.15 ms / 46 tokens ( 15.69 ms per token, 63.73 tokens per second) 4.01.080.213 I slot print_timing: id 0 | task 13665 | total time = 786.33 ms / 387 tokens 4.01.080.214 I slot print_timing: id 0 | task 13665 | graphs reused = 13170 4.01.080.215 I slot print_timing: id 0 | task 13665 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.080.244 I slot release: id 0 | task 13665 | stop processing: n_tokens = 411, truncated = 0 4.01.099.302 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 240994486 4.01.113.651 I slot launch_slot_: id 0 | task 13712 | processing task, is_child = 0 4.03.187.182 I slot print_timing: id 0 | task 13712 | prompt eval time = 74.50 ms / 332 tokens ( 0.22 ms per token, 4456.14 tokens per second) 4.03.187.188 I slot print_timing: id 0 | task 13712 | eval time = 1999.01 ms / 129 tokens ( 15.62 ms per token, 64.03 tokens per second) 4.03.187.189 I slot print_timing: id 0 | task 13712 | total time = 2073.52 ms / 461 tokens 4.03.187.189 I slot print_timing: id 0 | task 13712 | graphs reused = 13297 4.03.187.190 I slot print_timing: id 0 | task 13712 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.187.216 I slot release: id 0 | task 13712 | stop processing: n_tokens = 485, truncated = 0 4.03.216.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 485, t_last = 243101459 4.03.216.326 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.040 MiB) 4.03.238.133 I slot launch_slot_: id 0 | task 13842 | processing task, is_child = 0 4.04.462.046 I slot print_timing: id 0 | task 13842 | prompt eval time = 66.79 ms / 269 tokens ( 0.25 ms per token, 4027.49 tokens per second) 4.04.462.052 I slot print_timing: id 0 | task 13842 | eval time = 1157.11 ms / 75 tokens ( 15.64 ms per token, 63.95 tokens per second) 4.04.462.053 I slot print_timing: id 0 | task 13842 | total time = 1223.90 ms / 344 tokens 4.04.462.054 I slot print_timing: id 0 | task 13842 | graphs reused = 13370 4.04.462.055 I slot print_timing: id 0 | task 13842 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.462.080 I slot release: id 0 | task 13842 | stop processing: n_tokens = 368, truncated = 0 4.04.481.552 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 368, t_last = 244376322 4.04.481.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.980 MiB) 4.04.500.758 I slot launch_slot_: id 0 | task 13918 | processing task, is_child = 0 4.07.588.955 I slot print_timing: id 0 | task 13918 | n_gen = 192, tg = 63.52 t/s, tg_3s = 63.85 t/s 4.10.590.460 I slot print_timing: id 0 | task 13918 | n_gen = 383, tg = 63.58 t/s, tg_3s = 63.63 t/s 4.13.601.548 I slot print_timing: id 0 | task 13918 | n_gen = 574, tg = 63.53 t/s, tg_3s = 63.43 t/s 4.16.615.501 I slot print_timing: id 0 | task 13918 | n_gen = 764, tg = 63.41 t/s, tg_3s = 63.04 t/s 4.19.625.835 I slot print_timing: id 0 | task 13918 | n_gen = 953, tg = 63.28 t/s, tg_3s = 62.78 t/s 4.20.759.652 I slot print_timing: id 0 | task 13918 | prompt eval time = 81.05 ms / 341 tokens ( 0.24 ms per token, 4207.07 tokens per second) 4.20.759.658 I slot print_timing: id 0 | task 13918 | eval time = 16177.82 ms / 1024 tokens ( 15.81 ms per token, 63.23 tokens per second) 4.20.759.659 I slot print_timing: id 0 | task 13918 | total time = 16258.87 ms / 1365 tokens 4.20.759.660 I slot print_timing: id 0 | task 13918 | graphs reused = 14388 4.20.759.660 I slot print_timing: id 0 | task 13918 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.759.688 I slot release: id 0 | task 13918 | stop processing: n_tokens = 1389, truncated = 0 4.20.785.510 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1389, t_last = 260673930 4.20.785.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 4.20.832.540 I slot launch_slot_: id 0 | task 14943 | processing task, is_child = 0 4.23.505.541 I slot print_timing: id 0 | task 14943 | prompt eval time = 80.22 ms / 343 tokens ( 0.23 ms per token, 4275.69 tokens per second) 4.23.505.547 I slot print_timing: id 0 | task 14943 | eval time = 2592.76 ms / 166 tokens ( 15.71 ms per token, 63.64 tokens per second) 4.23.505.548 I slot print_timing: id 0 | task 14943 | total time = 2672.98 ms / 509 tokens 4.23.505.549 I slot print_timing: id 0 | task 14943 | graphs reused = 14551 4.23.505.550 I slot print_timing: id 0 | task 14943 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.505.581 I slot release: id 0 | task 14943 | stop processing: n_tokens = 533, truncated = 0 4.23.521.601 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 263419823 4.23.521.658 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.539 MiB) 4.23.545.083 I slot launch_slot_: id 0 | task 15110 | processing task, is_child = 0 4.26.633.347 I slot print_timing: id 0 | task 15110 | n_gen = 193, tg = 63.83 t/s, tg_3s = 64.17 t/s 4.29.646.974 I slot print_timing: id 0 | task 15110 | n_gen = 385, tg = 63.77 t/s, tg_3s = 63.71 t/s 4.32.656.704 I slot print_timing: id 0 | task 15110 | n_gen = 576, tg = 63.67 t/s, tg_3s = 63.46 t/s 4.35.667.096 I slot print_timing: id 0 | task 15110 | n_gen = 766, tg = 63.53 t/s, tg_3s = 63.11 t/s 4.38.677.846 I slot print_timing: id 0 | task 15110 | n_gen = 955, tg = 63.38 t/s, tg_3s = 62.78 t/s 4.39.780.212 I slot print_timing: id 0 | task 15110 | prompt eval time = 80.41 ms / 347 tokens ( 0.23 ms per token, 4315.49 tokens per second) 4.39.780.217 I slot print_timing: id 0 | task 15110 | eval time = 16154.70 ms / 1024 tokens ( 15.79 ms per token, 63.33 tokens per second) 4.39.780.218 I slot print_timing: id 0 | task 15110 | total time = 16235.11 ms / 1371 tokens 4.39.780.219 I slot print_timing: id 0 | task 15110 | graphs reused = 15569 4.39.780.220 I slot print_timing: id 0 | task 15110 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.780.252 I slot release: id 0 | task 15110 | stop processing: n_tokens = 1395, truncated = 0 4.39.803.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1395, t_last = 279694494 4.39.804.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.163 MiB) 4.39.808.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.633 MiB) 4.39.811.618 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.883 MiB) 4.39.864.632 I slot launch_slot_: id 0 | task 16135 | processing task, is_child = 0 4.42.943.664 I slot print_timing: id 0 | task 16135 | n_gen = 193, tg = 63.90 t/s, tg_3s = 64.24 t/s 4.45.955.973 I slot print_timing: id 0 | task 16135 | n_gen = 385, tg = 63.82 t/s, tg_3s = 63.74 t/s 4.48.966.570 I slot print_timing: id 0 | task 16135 | n_gen = 576, tg = 63.69 t/s, tg_3s = 63.44 t/s 4.51.977.168 I slot print_timing: id 0 | task 16135 | n_gen = 766, tg = 63.55 t/s, tg_3s = 63.11 t/s 4.53.977.084 I slot print_timing: id 0 | task 16135 | prompt eval time = 74.51 ms / 332 tokens ( 0.22 ms per token, 4455.66 tokens per second) 4.53.977.089 I slot print_timing: id 0 | task 16135 | eval time = 14037.92 ms / 892 tokens ( 15.76 ms per token, 63.47 tokens per second) 4.53.977.090 I slot print_timing: id 0 | task 16135 | total time = 14112.43 ms / 1224 tokens 4.53.977.091 I slot print_timing: id 0 | task 16135 | graphs reused = 16456 4.53.977.092 I slot print_timing: id 0 | task 16135 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.977.120 I slot release: id 0 | task 16135 | stop processing: n_tokens = 1248, truncated = 0 4.54.005.423 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1248, t_last = 293891362 4.54.005.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.447 MiB) 4.54.009.929 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.258 MiB) 4.54.058.997 I slot launch_slot_: id 0 | task 17028 | processing task, is_child = 0 4.57.138.356 I slot print_timing: id 0 | task 17028 | n_gen = 193, tg = 63.90 t/s, tg_3s = 64.23 t/s 4.58.487.094 I slot print_timing: id 0 | task 17028 | prompt eval time = 74.59 ms / 332 tokens ( 0.22 ms per token, 4450.76 tokens per second) 4.58.487.099 I slot print_timing: id 0 | task 17028 | eval time = 4353.48 ms / 279 tokens ( 15.66 ms per token, 63.86 tokens per second) 4.58.487.100 I slot print_timing: id 0 | task 17028 | total time = 4428.08 ms / 611 tokens 4.58.487.101 I slot print_timing: id 0 | task 17028 | graphs reused = 16732 4.58.487.102 I slot print_timing: id 0 | task 17028 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.487.129 I slot release: id 0 | task 17028 | stop processing: n_tokens = 635, truncated = 0 4.58.507.053 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 298401371 4.58.507.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.480 MiB) 4.58.535.989 I slot launch_slot_: id 0 | task 17308 | processing task, is_child = 0 5.01.357.261 I slot print_timing: id 0 | task 17308 | prompt eval time = 80.76 ms / 354 tokens ( 0.23 ms per token, 4383.20 tokens per second) 5.01.357.267 I slot print_timing: id 0 | task 17308 | eval time = 2740.48 ms / 176 tokens ( 15.66 ms per token, 63.86 tokens per second) 5.01.357.268 I slot print_timing: id 0 | task 17308 | total time = 2821.24 ms / 530 tokens 5.01.357.269 I slot print_timing: id 0 | task 17308 | graphs reused = 16905 5.01.357.270 I slot print_timing: id 0 | task 17308 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.357.299 I slot release: id 0 | task 17308 | stop processing: n_tokens = 554, truncated = 0 5.01.381.282 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 554, t_last = 301271541 5.01.399.014 I slot launch_slot_: id 0 | task 17485 | processing task, is_child = 0 5.04.487.270 I slot print_timing: id 0 | task 17485 | n_gen = 192, tg = 63.50 t/s, tg_3s = 63.84 t/s 5.05.791.362 I slot print_timing: id 0 | task 17485 | prompt eval time = 80.56 ms / 354 tokens ( 0.23 ms per token, 4394.29 tokens per second) 5.05.791.367 I slot print_timing: id 0 | task 17485 | eval time = 4311.77 ms / 275 tokens ( 15.74 ms per token, 63.55 tokens per second) 5.05.791.368 I slot print_timing: id 0 | task 17485 | total time = 4392.33 ms / 629 tokens 5.05.791.369 I slot print_timing: id 0 | task 17485 | graphs reused = 17177 5.05.791.370 I slot print_timing: id 0 | task 17485 | graph reallocs = 0 / 0 (same size) / (changed size) 5.05.791.402 I slot release: id 0 | task 17485 | stop processing: n_tokens = 653, truncated = 0 5.05.812.324 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 653, t_last = 305705644 5.05.812.384 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.227 MiB) 5.05.838.121 I slot launch_slot_: id 0 | task 17761 | processing task, is_child = 0 5.06.871.147 I slot print_timing: id 0 | task 17761 | prompt eval time = 80.14 ms / 339 tokens ( 0.24 ms per token, 4230.04 tokens per second) 5.06.871.153 I slot print_timing: id 0 | task 17761 | eval time = 952.87 ms / 61 tokens ( 15.88 ms per token, 62.97 tokens per second) 5.06.871.154 I slot print_timing: id 0 | task 17761 | total time = 1033.01 ms / 400 tokens 5.06.871.155 I slot print_timing: id 0 | task 17761 | graphs reused = 17236 5.06.871.156 I slot print_timing: id 0 | task 17761 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.871.183 I slot release: id 0 | task 17761 | stop processing: n_tokens = 424, truncated = 0 5.06.875.501 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 306785425 5.06.875.551 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 108.759 MiB) 5.06.896.255 I slot launch_slot_: id 0 | task 17823 | processing task, is_child = 0 5.09.006.209 I slot print_timing: id 0 | task 17823 | prompt eval time = 80.98 ms / 351 tokens ( 0.23 ms per token, 4334.62 tokens per second) 5.09.006.215 I slot print_timing: id 0 | task 17823 | eval time = 2028.96 ms / 131 tokens ( 15.61 ms per token, 64.07 tokens per second) 5.09.006.216 I slot print_timing: id 0 | task 17823 | total time = 2109.93 ms / 482 tokens 5.09.006.217 I slot print_timing: id 0 | task 17823 | graphs reused = 17365 5.09.006.217 I slot print_timing: id 0 | task 17823 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.006.246 I slot release: id 0 | task 17823 | stop processing: n_tokens = 506, truncated = 0 5.09.034.184 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 308920488 5.09.034.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.602 MiB) 5.09.057.552 I slot launch_slot_: id 0 | task 17955 | processing task, is_child = 0 5.11.378.190 I slot print_timing: id 0 | task 17955 | prompt eval time = 74.31 ms / 325 tokens ( 0.23 ms per token, 4373.81 tokens per second) 5.11.378.196 I slot print_timing: id 0 | task 17955 | eval time = 2246.31 ms / 145 tokens ( 15.60 ms per token, 64.11 tokens per second) 5.11.378.197 I slot print_timing: id 0 | task 17955 | total time = 2320.62 ms / 470 tokens 5.11.378.198 I slot print_timing: id 0 | task 17955 | graphs reused = 17508 5.11.378.199 I slot print_timing: id 0 | task 17955 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.378.227 I slot release: id 0 | task 17955 | stop processing: n_tokens = 494, truncated = 0 5.11.406.080 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 311292469 5.11.422.456 I slot launch_slot_: id 0 | task 18101 | processing task, is_child = 0 5.12.367.009 I slot print_timing: id 0 | task 18101 | prompt eval time = 74.02 ms / 308 tokens ( 0.24 ms per token, 4160.93 tokens per second) 5.12.367.015 I slot print_timing: id 0 | task 18101 | eval time = 870.52 ms / 56 tokens ( 15.83 ms per token, 63.18 tokens per second) 5.12.367.016 I slot print_timing: id 0 | task 18101 | total time = 944.54 ms / 364 tokens 5.12.367.017 I slot print_timing: id 0 | task 18101 | graphs reused = 17562 5.12.367.018 I slot print_timing: id 0 | task 18101 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.367.045 I slot release: id 0 | task 18101 | stop processing: n_tokens = 388, truncated = 0 5.12.390.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 312281288 5.12.390.508 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 123.447 MiB) 5.12.409.913 I slot launch_slot_: id 0 | task 18158 | processing task, is_child = 0 5.15.495.078 I slot print_timing: id 0 | task 18158 | n_gen = 193, tg = 63.90 t/s, tg_3s = 64.23 t/s 5.18.163.376 I slot print_timing: id 0 | task 18158 | prompt eval time = 80.39 ms / 349 tokens ( 0.23 ms per token, 4341.44 tokens per second) 5.18.163.382 I slot print_timing: id 0 | task 18158 | eval time = 5673.05 ms / 363 tokens ( 15.67 ms per token, 63.81 tokens per second) 5.18.163.382 I slot print_timing: id 0 | task 18158 | total time = 5753.44 ms / 712 tokens 5.18.163.384 I slot print_timing: id 0 | task 18158 | graphs reused = 17922 5.18.163.385 I slot print_timing: id 0 | task 18158 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.163.415 I slot release: id 0 | task 18158 | stop processing: n_tokens = 736, truncated = 0 5.18.190.947 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 736, t_last = 318077657 5.18.191.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 143.918 MiB) 5.18.222.556 I slot launch_slot_: id 0 | task 18522 | processing task, is_child = 0 5.19.694.639 I slot print_timing: id 0 | task 18522 | prompt eval time = 80.14 ms / 371 tokens ( 0.22 ms per token, 4629.23 tokens per second) 5.19.694.645 I slot print_timing: id 0 | task 18522 | eval time = 1391.92 ms / 90 tokens ( 15.64 ms per token, 63.94 tokens per second) 5.19.694.646 I slot print_timing: id 0 | task 18522 | total time = 1472.06 ms / 461 tokens 5.19.694.647 I slot print_timing: id 0 | task 18522 | graphs reused = 18010 5.19.694.648 I slot print_timing: id 0 | task 18522 | graph reallocs = 0 / 0 (same size) / (changed size) 5.19.694.678 I slot release: id 0 | task 18522 | stop processing: n_tokens = 490, truncated = 0 5.19.716.628 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 490, t_last = 319608920 5.19.732.553 I slot launch_slot_: id 0 | task 18613 | processing task, is_child = 0 5.21.804.504 I slot print_timing: id 0 | task 18613 | prompt eval time = 73.56 ms / 303 tokens ( 0.24 ms per token, 4119.31 tokens per second) 5.21.804.509 I slot print_timing: id 0 | task 18613 | eval time = 1998.38 ms / 129 tokens ( 15.61 ms per token, 64.05 tokens per second) 5.21.804.510 I slot print_timing: id 0 | task 18613 | total time = 2071.93 ms / 432 tokens 5.21.804.511 I slot print_timing: id 0 | task 18613 | graphs reused = 18137 5.21.804.512 I slot print_timing: id 0 | task 18613 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.804.541 I slot release: id 0 | task 18613 | stop processing: n_tokens = 456, truncated = 0 5.21.808.516 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 321718784 5.21.808.572 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.476 MiB) 5.21.829.027 I slot launch_slot_: id 0 | task 18743 | processing task, is_child = 0 5.24.912.203 I slot print_timing: id 0 | task 18743 | n_gen = 192, tg = 63.47 t/s, tg_3s = 63.80 t/s 5.27.551.838 I slot print_timing: id 0 | task 18743 | prompt eval time = 73.68 ms / 312 tokens ( 0.24 ms per token, 4234.41 tokens per second) 5.27.551.844 I slot print_timing: id 0 | task 18743 | eval time = 5649.11 ms / 360 tokens ( 15.74 ms per token, 63.55 tokens per second) 5.27.551.845 I slot print_timing: id 0 | task 18743 | total time = 5722.80 ms / 672 tokens 5.27.551.846 I slot print_timing: id 0 | task 18743 | graphs reused = 18494 5.27.551.847 I slot print_timing: id 0 | task 18743 | graph reallocs = 0 / 0 (same size) / (changed size) 5.27.551.873 I slot release: id 0 | task 18743 | stop processing: n_tokens = 696, truncated = 0 5.27.578.646 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 696, t_last = 327466115 5.27.578.709 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.069 MiB) 5.27.604.515 I slot launch_slot_: id 0 | task 19104 | processing task, is_child = 0 5.30.686.110 I slot print_timing: id 0 | task 19104 | n_gen = 193, tg = 63.85 t/s, tg_3s = 64.18 t/s 5.33.690.503 I slot print_timing: id 0 | task 19104 | n_gen = 384, tg = 63.71 t/s, tg_3s = 63.57 t/s 5.35.081.023 I slot print_timing: id 0 | task 19104 | prompt eval time = 74.39 ms / 311 tokens ( 0.24 ms per token, 4180.73 tokens per second) 5.35.081.028 I slot print_timing: id 0 | task 19104 | eval time = 7402.10 ms / 472 tokens ( 15.72 ms per token, 63.63 tokens per second) 5.35.081.029 I slot print_timing: id 0 | task 19104 | total time = 7476.49 ms / 783 tokens 5.35.081.032 I slot print_timing: id 0 | task 19104 | graphs reused = 18962 5.35.081.032 I slot print_timing: id 0 | task 19104 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.081.062 I slot release: id 0 | task 19104 | stop processing: n_tokens = 807, truncated = 0 5.35.108.543 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 334995304 5.35.108.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 5.35.113.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.256 MiB) 5.35.143.723 I slot launch_slot_: id 0 | task 19577 | processing task, is_child = 0 5.36.908.473 I slot print_timing: id 0 | task 19577 | prompt eval time = 74.37 ms / 331 tokens ( 0.22 ms per token, 4450.54 tokens per second) 5.36.908.478 I slot print_timing: id 0 | task 19577 | eval time = 1690.36 ms / 109 tokens ( 15.65 ms per token, 63.89 tokens per second) 5.36.908.479 I slot print_timing: id 0 | task 19577 | total time = 1764.73 ms / 440 tokens 5.36.908.480 I slot print_timing: id 0 | task 19577 | graphs reused = 19069 5.36.908.480 I slot print_timing: id 0 | task 19577 | graph reallocs = 0 / 0 (same size) / (changed size) 5.36.908.507 I slot release: id 0 | task 19577 | stop processing: n_tokens = 464, truncated = 0 5.36.912.725 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 464, t_last = 336822749 5.36.912.779 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.851 MiB) 5.36.937.106 I slot launch_slot_: id 0 | task 19687 | processing task, is_child = 0 5.40.022.513 I slot print_timing: id 0 | task 19687 | n_gen = 193, tg = 63.78 t/s, tg_3s = 64.11 t/s 5.43.024.004 I slot print_timing: id 0 | task 19687 | n_gen = 384, tg = 63.71 t/s, tg_3s = 63.64 t/s 5.46.035.124 I slot print_timing: id 0 | task 19687 | n_gen = 575, tg = 63.62 t/s, tg_3s = 63.43 t/s 5.49.046.658 I slot print_timing: id 0 | task 19687 | n_gen = 765, tg = 63.48 t/s, tg_3s = 63.09 t/s 5.52.057.515 I slot print_timing: id 0 | task 19687 | n_gen = 954, tg = 63.34 t/s, tg_3s = 62.77 t/s 5.52.797.671 I slot print_timing: id 0 | task 19687 | prompt eval time = 75.01 ms / 335 tokens ( 0.22 ms per token, 4466.31 tokens per second) 5.52.797.676 I slot print_timing: id 0 | task 19687 | eval time = 15785.54 ms / 1000 tokens ( 15.80 ms per token, 63.29 tokens per second) 5.52.797.677 I slot print_timing: id 0 | task 19687 | total time = 15860.55 ms / 1335 tokens 5.52.797.678 I slot print_timing: id 0 | task 19687 | graphs reused = 20063 5.52.797.679 I slot print_timing: id 0 | task 19687 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.797.710 I slot release: id 0 | task 19687 | stop processing: n_tokens = 1359, truncated = 0 5.52.826.433 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1359, t_last = 352711953 5.52.826.528 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.382 MiB) 5.52.831.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.852 MiB) 5.52.891.558 I slot launch_slot_: id 0 | task 20688 | processing task, is_child = 0 5.54.981.405 I slot print_timing: id 0 | task 20688 | prompt eval time = 75.07 ms / 331 tokens ( 0.23 ms per token, 4409.22 tokens per second) 5.54.981.411 I slot print_timing: id 0 | task 20688 | eval time = 2014.76 ms / 130 tokens ( 15.62 ms per token, 64.03 tokens per second) 5.54.981.412 I slot print_timing: id 0 | task 20688 | total time = 2089.83 ms / 461 tokens 5.54.981.412 I slot print_timing: id 0 | task 20688 | graphs reused = 20191 5.54.981.413 I slot print_timing: id 0 | task 20688 | graph reallocs = 0 / 0 (same size) / (changed size) 5.54.981.441 I slot release: id 0 | task 20688 | stop processing: n_tokens = 485, truncated = 0 5.55.002.000 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 485, t_last = 354895684 5.55.002.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.537 MiB) 5.55.025.186 I slot launch_slot_: id 0 | task 20819 | processing task, is_child = 0 5.57.616.621 I slot print_timing: id 0 | task 20819 | prompt eval time = 74.23 ms / 328 tokens ( 0.23 ms per token, 4418.94 tokens per second) 5.57.616.626 I slot print_timing: id 0 | task 20819 | eval time = 2517.19 ms / 162 tokens ( 15.63 ms per token, 63.96 tokens per second) 5.57.616.627 I slot print_timing: id 0 | task 20819 | total time = 2591.42 ms / 490 tokens 5.57.616.629 I slot print_timing: id 0 | task 20819 | graphs reused = 20350 5.57.616.630 I slot print_timing: id 0 | task 20819 | graph reallocs = 0 / 0 (same size) / (changed size) 5.57.616.657 I slot release: id 0 | task 20819 | stop processing: n_tokens = 514, truncated = 0 5.57.631.088 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 357530899 5.57.631.135 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 5.57.635.055 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 5.57.665.504 I slot launch_slot_: id 0 | task 20982 | processing task, is_child = 0 6.00.743.947 I slot print_timing: id 0 | task 20982 | n_gen = 193, tg = 63.91 t/s, tg_3s = 64.25 t/s 6.01.936.652 I slot print_timing: id 0 | task 20982 | prompt eval time = 74.35 ms / 331 tokens ( 0.22 ms per token, 4452.04 tokens per second) 6.01.936.657 I slot print_timing: id 0 | task 20982 | eval time = 4196.78 ms / 269 tokens ( 15.66 ms per token, 63.86 tokens per second) 6.01.936.658 I slot print_timing: id 0 | task 20982 | total time = 4271.13 ms / 600 tokens 6.01.936.659 I slot print_timing: id 0 | task 20982 | graphs reused = 20616 6.01.936.659 I slot print_timing: id 0 | task 20982 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.936.687 I slot release: id 0 | task 20982 | stop processing: n_tokens = 624, truncated = 0 6.01.949.948 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 624, t_last = 361850929 6.01.950.006 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.945 MiB) 6.01.978.277 I slot launch_slot_: id 0 | task 21252 | processing task, is_child = 0 6.02.889.205 I slot print_timing: id 0 | task 21252 | prompt eval time = 80.54 ms / 348 tokens ( 0.23 ms per token, 4320.83 tokens per second) 6.02.889.211 I slot print_timing: id 0 | task 21252 | eval time = 830.37 ms / 54 tokens ( 15.67 ms per token, 63.83 tokens per second) 6.02.889.212 I slot print_timing: id 0 | task 21252 | total time = 910.91 ms / 402 tokens 6.02.889.213 I slot print_timing: id 0 | task 21252 | graphs reused = 20668 6.02.889.214 I slot print_timing: id 0 | task 21252 | graph reallocs = 0 / 0 (same size) / (changed size) 6.02.889.243 I slot release: id 0 | task 21252 | stop processing: n_tokens = 426, truncated = 0 6.02.917.001 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 362803485 6.02.917.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 6.02.937.059 I slot launch_slot_: id 0 | task 21307 | processing task, is_child = 0 6.03.825.806 I slot print_timing: id 0 | task 21307 | prompt eval time = 74.40 ms / 332 tokens ( 0.22 ms per token, 4462.49 tokens per second) 6.03.825.811 I slot print_timing: id 0 | task 21307 | eval time = 814.33 ms / 53 tokens ( 15.66 ms per token, 63.86 tokens per second) 6.03.825.812 I slot print_timing: id 0 | task 21307 | total time = 888.73 ms / 385 tokens 6.03.825.813 I slot print_timing: id 0 | task 21307 | graphs reused = 20719 6.03.825.814 I slot print_timing: id 0 | task 21307 | graph reallocs = 0 / 0 (same size) / (changed size) 6.03.825.843 I slot release: id 0 | task 21307 | stop processing: n_tokens = 411, truncated = 0 6.03.855.112 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 363740085 6.03.869.312 I slot launch_slot_: id 0 | task 21361 | processing task, is_child = 0 6.06.276.454 I slot print_timing: id 0 | task 21361 | prompt eval time = 79.97 ms / 339 tokens ( 0.24 ms per token, 4239.30 tokens per second) 6.06.276.460 I slot print_timing: id 0 | task 21361 | eval time = 2327.16 ms / 150 tokens ( 15.62 ms per token, 64.03 tokens per second) 6.06.276.460 I slot print_timing: id 0 | task 21361 | total time = 2407.13 ms / 489 tokens 6.06.276.461 I slot print_timing: id 0 | task 21361 | graphs reused = 20866 6.06.276.462 I slot print_timing: id 0 | task 21361 | graph reallocs = 0 / 0 (same size) / (changed size) 6.06.276.490 I slot release: id 0 | task 21361 | stop processing: n_tokens = 513, truncated = 0 6.06.306.135 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 366190732 6.06.306.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.476 MiB) 6.06.331.566 I slot launch_slot_: id 0 | task 21512 | processing task, is_child = 0 6.06.883.934 I slot print_timing: id 0 | task 21512 | prompt eval time = 80.25 ms / 343 tokens ( 0.23 ms per token, 4274.09 tokens per second) 6.06.883.940 I slot print_timing: id 0 | task 21512 | eval time = 472.10 ms / 31 tokens ( 15.74 ms per token, 63.55 tokens per second) 6.06.883.941 I slot print_timing: id 0 | task 21512 | total time = 552.35 ms / 374 tokens 6.06.883.942 I slot print_timing: id 0 | task 21512 | graphs reused = 20895 6.06.883.943 I slot print_timing: id 0 | task 21512 | graph reallocs = 0 / 0 (same size) / (changed size) 6.06.883.970 I slot release: id 0 | task 21512 | stop processing: n_tokens = 398, truncated = 0 6.06.898.157 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 366798212 6.06.898.205 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.601 MiB) 6.06.920.734 I slot launch_slot_: id 0 | task 21544 | processing task, is_child = 0 6.09.068.686 I slot print_timing: id 0 | task 21544 | prompt eval time = 81.17 ms / 360 tokens ( 0.23 ms per token, 4435.41 tokens per second) 6.09.068.692 I slot print_timing: id 0 | task 21544 | eval time = 2066.77 ms / 133 tokens ( 15.66 ms per token, 63.87 tokens per second) 6.09.068.693 I slot print_timing: id 0 | task 21544 | total time = 2147.94 ms / 493 tokens 6.09.068.693 I slot print_timing: id 0 | task 21544 | graphs reused = 21025 6.09.068.694 I slot print_timing: id 0 | task 21544 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.068.722 I slot release: id 0 | task 21544 | stop processing: n_tokens = 517, truncated = 0 6.09.087.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 368982965 6.09.087.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 6.09.112.646 I slot launch_slot_: id 0 | task 21678 | processing task, is_child = 0 6.09.930.367 I slot print_timing: id 0 | task 21678 | prompt eval time = 80.27 ms / 341 tokens ( 0.24 ms per token, 4247.95 tokens per second) 6.09.930.372 I slot print_timing: id 0 | task 21678 | eval time = 737.43 ms / 48 tokens ( 15.69 ms per token, 63.73 tokens per second) 6.09.930.373 I slot print_timing: id 0 | task 21678 | total time = 817.70 ms / 389 tokens 6.09.930.374 I slot print_timing: id 0 | task 21678 | graphs reused = 21071 6.09.930.375 I slot print_timing: id 0 | task 21678 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.930.406 I slot release: id 0 | task 21678 | stop processing: n_tokens = 413, truncated = 0 6.09.959.180 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 369844648 6.09.959.232 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.976 MiB) 6.09.981.167 I slot launch_slot_: id 0 | task 21727 | processing task, is_child = 0 6.12.102.327 I slot print_timing: id 0 | task 21727 | prompt eval time = 80.85 ms / 358 tokens ( 0.23 ms per token, 4428.01 tokens per second) 6.12.102.333 I slot print_timing: id 0 | task 21727 | eval time = 2040.30 ms / 131 tokens ( 15.69 ms per token, 63.72 tokens per second) 6.12.102.335 I slot print_timing: id 0 | task 21727 | total time = 2121.15 ms / 489 tokens 6.12.102.335 I slot print_timing: id 0 | task 21727 | graphs reused = 21199 6.12.102.336 I slot print_timing: id 0 | task 21727 | graph reallocs = 0 / 0 (same size) / (changed size) 6.12.102.366 I slot release: id 0 | task 21727 | stop processing: n_tokens = 513, truncated = 0 6.12.130.813 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 372016608 6.12.130.869 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.694 MiB) 6.12.158.822 I slot launch_slot_: id 0 | task 21859 | processing task, is_child = 0 6.13.291.004 I slot print_timing: id 0 | task 21859 | prompt eval time = 80.92 ms / 358 tokens ( 0.23 ms per token, 4424.01 tokens per second) 6.13.291.011 I slot print_timing: id 0 | task 21859 | eval time = 1051.24 ms / 67 tokens ( 15.93 ms per token, 62.78 tokens per second) 6.13.291.012 I slot print_timing: id 0 | task 21859 | total time = 1132.16 ms / 425 tokens 6.13.291.012 I slot print_timing: id 0 | task 21859 | graphs reused = 21264 6.13.291.013 I slot print_timing: id 0 | task 21859 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.291.041 I slot release: id 0 | task 21859 | stop processing: n_tokens = 452, truncated = 0 6.13.320.194 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 373205284 6.13.320.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.412 MiB) 6.13.344.696 I slot launch_slot_: id 0 | task 21927 | processing task, is_child = 0 6.16.457.060 I slot print_timing: id 0 | task 21927 | n_gen = 193, tg = 63.76 t/s, tg_3s = 64.09 t/s 6.18.218.469 I slot print_timing: id 0 | task 21927 | prompt eval time = 100.83 ms / 387 tokens ( 0.26 ms per token, 3838.18 tokens per second) 6.18.218.475 I slot print_timing: id 0 | task 21927 | eval time = 4772.93 ms / 305 tokens ( 15.70 ms per token, 63.69 tokens per second) 6.18.218.476 I slot print_timing: id 0 | task 21927 | total time = 4873.76 ms / 692 tokens 6.18.218.477 I slot print_timing: id 0 | task 21927 | graphs reused = 21566 6.18.218.478 I slot print_timing: id 0 | task 21927 | graph reallocs = 0 / 0 (same size) / (changed size) 6.18.218.507 I slot release: id 0 | task 21927 | stop processing: n_tokens = 716, truncated = 0 6.18.239.249 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 378132749 6.18.239.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.694 MiB) 6.18.244.153 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.631 MiB) 6.18.274.449 I slot launch_slot_: id 0 | task 22233 | processing task, is_child = 0 6.19.299.096 I slot print_timing: id 0 | task 22233 | prompt eval time = 74.41 ms / 333 tokens ( 0.22 ms per token, 4475.51 tokens per second) 6.19.299.103 I slot print_timing: id 0 | task 22233 | eval time = 950.23 ms / 61 tokens ( 15.84 ms per token, 63.14 tokens per second) 6.19.299.104 I slot print_timing: id 0 | task 22233 | total time = 1024.63 ms / 394 tokens 6.19.299.105 I slot print_timing: id 0 | task 22233 | graphs reused = 21625 6.19.299.106 I slot print_timing: id 0 | task 22233 | graph reallocs = 0 / 0 (same size) / (changed size) 6.19.299.135 I slot release: id 0 | task 22233 | stop processing: n_tokens = 418, truncated = 0