$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--bartowski--Qwen_Qwen3.5-4B-GGUF\snapshots\4168f45a16a1290d65a4ec0fa312ae917a4c15d6\Qwen_Qwen3.5-4B-IQ3_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.098.585 I srv llama_server: initializing ... 0.00.098.590 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.098.699 I srv init_listene: The UI is disabled 0.00.098.701 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.098.781 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) 0.00.102.136 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--bartowski--Qwen_Qwen3.5-4B-GGUF\snapshots\4168f45a16a1290d65a4ec0fa312ae917a4c15d6\Qwen_Qwen3.5-4B-IQ3_M.gguf' 0.00.971.480 W model has unused tensor blk.32.attn_norm.weight (size = 10240 bytes) -- ignoring 0.00.971.495 W model has unused tensor blk.32.post_attention_norm.weight (size = 10240 bytes) -- ignoring 0.00.971.521 W model has unused tensor blk.32.attn_q.weight (size = 22282240 bytes) -- ignoring 0.00.971.529 W model has unused tensor blk.32.attn_k.weight (size = 2785280 bytes) -- ignoring 0.00.971.538 W model has unused tensor blk.32.attn_v.weight (size = 2785280 bytes) -- ignoring 0.00.971.573 W model has unused tensor blk.32.attn_output.weight (size = 11141120 bytes) -- ignoring 0.00.971.583 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.971.591 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.971.601 W model has unused tensor blk.32.ffn_gate.weight (size = 25067520 bytes) -- ignoring 0.00.971.610 W model has unused tensor blk.32.ffn_down.weight (size = 25067520 bytes) -- ignoring 0.00.971.620 W model has unused tensor blk.32.ffn_up.weight (size = 25067520 bytes) -- ignoring 0.00.971.631 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 13926400 bytes) -- ignoring 0.00.971.641 W model has unused tensor blk.32.nextn.enorm.weight (size = 10240 bytes) -- ignoring 0.00.971.651 W model has unused tensor blk.32.nextn.hnorm.weight (size = 10240 bytes) -- ignoring 0.00.971.680 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 10240 bytes) -- ignoring 0.01.783.054 I cmn init: llama threadpool init, n_threads = 8 0.01.861.072 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.865.723 I srv llama_server: model loaded 0.01.865.730 I srv llama_server: listening on http://127.0.0.1:8089 0.02.554.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.554.963 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.092.614 I slot print_timing: id 0 | task 0 | prompt eval time = 187.95 ms / 368 tokens ( 0.51 ms per token, 1957.95 tokens per second) 0.03.092.620 I slot print_timing: id 0 | task 0 | eval time = 349.68 ms / 53 tokens ( 6.72 ms per token, 148.71 tokens per second) 0.03.092.621 I slot print_timing: id 0 | task 0 | total time = 537.63 ms / 421 tokens 0.03.092.628 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.03.092.628 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.092.658 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.03.108.635 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 2996045 0.03.140.233 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.03.504.219 I slot print_timing: id 0 | task 56 | prompt eval time = 90.14 ms / 322 tokens ( 0.28 ms per token, 3572.02 tokens per second) 0.03.504.225 I slot print_timing: id 0 | task 56 | eval time = 273.82 ms / 42 tokens ( 6.68 ms per token, 149.73 tokens per second) 0.03.504.225 I slot print_timing: id 0 | task 56 | total time = 363.97 ms / 364 tokens 0.03.504.226 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.03.504.227 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.504.254 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.03.528.768 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 3407640 0.03.555.105 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.03.915.102 I slot print_timing: id 0 | task 101 | prompt eval time = 91.05 ms / 365 tokens ( 0.25 ms per token, 4008.79 tokens per second) 0.03.915.108 I slot print_timing: id 0 | task 101 | eval time = 268.93 ms / 42 tokens ( 6.56 ms per token, 152.46 tokens per second) 0.03.915.109 I slot print_timing: id 0 | task 101 | total time = 359.98 ms / 407 tokens 0.03.915.110 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.03.915.110 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.915.138 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.03.932.758 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 3818525 0.03.958.029 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.04.331.483 I slot print_timing: id 0 | task 146 | prompt eval time = 94.89 ms / 397 tokens ( 0.24 ms per token, 4183.88 tokens per second) 0.04.331.488 I slot print_timing: id 0 | task 146 | eval time = 278.54 ms / 43 tokens ( 6.63 ms per token, 150.79 tokens per second) 0.04.331.489 I slot print_timing: id 0 | task 146 | total time = 373.43 ms / 440 tokens 0.04.331.490 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.04.331.491 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.331.520 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.04.350.664 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.103 0.04.376.809 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.04.821.306 I slot print_timing: id 0 | task 192 | prompt eval time = 91.66 ms / 383 tokens ( 0.24 ms per token, 4178.67 tokens per second) 0.04.821.312 I slot print_timing: id 0 | task 192 | eval time = 352.82 ms / 55 tokens ( 6.53 ms per token, 153.05 tokens per second) 0.04.821.313 I slot print_timing: id 0 | task 192 | total time = 444.47 ms / 438 tokens 0.04.821.315 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.04.821.316 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.821.350 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.04.847.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 4724736 0.04.873.851 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.05.320.062 I slot print_timing: id 0 | task 250 | prompt eval time = 93.97 ms / 372 tokens ( 0.25 ms per token, 3958.58 tokens per second) 0.05.320.067 I slot print_timing: id 0 | task 250 | eval time = 352.22 ms / 55 tokens ( 6.52 ms per token, 153.31 tokens per second) 0.05.320.068 I slot print_timing: id 0 | task 250 | total time = 446.19 ms / 427 tokens 0.05.320.069 I slot print_timing: id 0 | task 250 | graphs reused = 279 0.05.320.070 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.320.097 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 0.05.342.974 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 5223484 0.05.369.050 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 0.05.819.776 I slot print_timing: id 0 | task 308 | prompt eval time = 100.45 ms / 422 tokens ( 0.24 ms per token, 4201.26 tokens per second) 0.05.819.782 I slot print_timing: id 0 | task 308 | eval time = 350.26 ms / 55 tokens ( 6.49 ms per token, 154.17 tokens per second) 0.05.819.783 I slot print_timing: id 0 | task 308 | total time = 450.71 ms / 477 tokens 0.05.819.784 I slot print_timing: id 0 | task 308 | graphs reused = 332 0.05.819.784 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.819.817 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 0.05.840.376 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 5723203 0.05.867.590 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 0.06.441.281 I slot print_timing: id 0 | task 366 | prompt eval time = 102.94 ms / 470 tokens ( 0.22 ms per token, 4565.99 tokens per second) 0.06.441.287 I slot print_timing: id 0 | task 366 | eval time = 470.74 ms / 72 tokens ( 6.63 ms per token, 150.83 tokens per second) 0.06.441.288 I slot print_timing: id 0 | task 366 | total time = 573.67 ms / 542 tokens 0.06.441.288 I slot print_timing: id 0 | task 366 | graphs reused = 401 0.06.441.289 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.441.319 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 0.06.463.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 6344705 0.06.490.555 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 0.06.888.997 I slot print_timing: id 0 | task 441 | prompt eval time = 91.54 ms / 345 tokens ( 0.27 ms per token, 3769.01 tokens per second) 0.06.889.003 I slot print_timing: id 0 | task 441 | eval time = 306.88 ms / 47 tokens ( 6.67 ms per token, 149.89 tokens per second) 0.06.889.004 I slot print_timing: id 0 | task 441 | total time = 398.42 ms / 392 tokens 0.06.889.005 I slot print_timing: id 0 | task 441 | graphs reused = 446 0.06.889.006 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.889.039 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 0.06.915.475 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 6792426 0.06.941.155 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 0.07.390.825 I slot print_timing: id 0 | task 491 | prompt eval time = 92.44 ms / 364 tokens ( 0.25 ms per token, 3937.86 tokens per second) 0.07.390.831 I slot print_timing: id 0 | task 491 | eval time = 357.21 ms / 55 tokens ( 6.62 ms per token, 151.17 tokens per second) 0.07.390.832 I slot print_timing: id 0 | task 491 | total time = 449.65 ms / 419 tokens 0.07.390.833 I slot print_timing: id 0 | task 491 | graphs reused = 499 0.07.390.834 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.390.862 I slot release: id 0 | task 491 | stop processing: n_tokens = 418, truncated = 0 0.07.413.041 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 7294249 0.07.439.817 I slot launch_slot_: id 0 | task 549 | processing task, is_child = 0 0.07.966.904 I slot print_timing: id 0 | task 549 | prompt eval time = 94.11 ms / 376 tokens ( 0.25 ms per token, 3995.11 tokens per second) 0.07.966.910 I slot print_timing: id 0 | task 549 | eval time = 432.95 ms / 62 tokens ( 7.10 ms per token, 140.89 tokens per second) 0.07.966.911 I slot print_timing: id 0 | task 549 | total time = 527.06 ms / 438 tokens 0.07.966.912 I slot print_timing: id 0 | task 549 | graphs reused = 559 0.07.966.913 I slot print_timing: id 0 | task 549 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.966.944 I slot release: id 0 | task 549 | stop processing: n_tokens = 437, truncated = 0 0.07.986.494 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 7870331 0.08.013.326 I slot launch_slot_: id 0 | task 614 | processing task, is_child = 0 0.08.416.555 I slot print_timing: id 0 | task 614 | prompt eval time = 94.56 ms / 412 tokens ( 0.23 ms per token, 4357.02 tokens per second) 0.08.416.561 I slot print_timing: id 0 | task 614 | eval time = 308.65 ms / 47 tokens ( 6.71 ms per token, 149.03 tokens per second) 0.08.416.562 I slot print_timing: id 0 | task 614 | total time = 403.21 ms / 459 tokens 0.08.416.563 I slot print_timing: id 0 | task 614 | graphs reused = 604 0.08.416.564 I slot print_timing: id 0 | task 614 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.416.595 I slot release: id 0 | task 614 | stop processing: n_tokens = 458, truncated = 0 0.08.440.329 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 8319981 0.08.466.847 I slot launch_slot_: id 0 | task 664 | processing task, is_child = 0 0.08.959.306 I slot print_timing: id 0 | task 664 | prompt eval time = 91.55 ms / 376 tokens ( 0.24 ms per token, 4107.27 tokens per second) 0.08.959.313 I slot print_timing: id 0 | task 664 | eval time = 400.89 ms / 62 tokens ( 6.57 ms per token, 152.16 tokens per second) 0.08.959.314 I slot print_timing: id 0 | task 664 | total time = 492.44 ms / 438 tokens 0.08.959.315 I slot print_timing: id 0 | task 664 | graphs reused = 664 0.08.959.316 I slot print_timing: id 0 | task 664 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.959.347 I slot release: id 0 | task 664 | stop processing: n_tokens = 437, truncated = 0 0.08.973.662 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 8862733 0.08.999.585 I slot launch_slot_: id 0 | task 729 | processing task, is_child = 0 0.09.423.034 I slot print_timing: id 0 | task 729 | prompt eval time = 92.86 ms / 378 tokens ( 0.25 ms per token, 4070.51 tokens per second) 0.09.423.041 I slot print_timing: id 0 | task 729 | eval time = 330.57 ms / 52 tokens ( 6.48 ms per token, 154.28 tokens per second) 0.09.423.042 I slot print_timing: id 0 | task 729 | total time = 423.43 ms / 430 tokens 0.09.423.043 I slot print_timing: id 0 | task 729 | graphs reused = 714 0.09.423.043 I slot print_timing: id 0 | task 729 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.423.071 I slot release: id 0 | task 729 | stop processing: n_tokens = 429, truncated = 0 0.09.442.913 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 9326457 0.09.468.495 I slot launch_slot_: id 0 | task 784 | processing task, is_child = 0 0.09.959.421 I slot print_timing: id 0 | task 784 | prompt eval time = 91.16 ms / 367 tokens ( 0.25 ms per token, 4026.02 tokens per second) 0.09.959.427 I slot print_timing: id 0 | task 784 | eval time = 399.75 ms / 58 tokens ( 7.01 ms per token, 142.59 tokens per second) 0.09.959.428 I slot print_timing: id 0 | task 784 | total time = 490.90 ms / 425 tokens 0.09.959.428 I slot print_timing: id 0 | task 784 | graphs reused = 770 0.09.959.429 I slot print_timing: id 0 | task 784 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.959.457 I slot release: id 0 | task 784 | stop processing: n_tokens = 424, truncated = 0 0.09.984.787 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 9862844 0.10.010.415 I slot launch_slot_: id 0 | task 845 | processing task, is_child = 0 0.10.436.039 I slot print_timing: id 0 | task 845 | prompt eval time = 88.98 ms / 347 tokens ( 0.26 ms per token, 3899.71 tokens per second) 0.10.436.045 I slot print_timing: id 0 | task 845 | eval time = 336.62 ms / 51 tokens ( 6.73 ms per token, 148.53 tokens per second) 0.10.436.046 I slot print_timing: id 0 | task 845 | total time = 425.60 ms / 398 tokens 0.10.436.047 I slot print_timing: id 0 | task 845 | graphs reused = 819 0.10.436.048 I slot print_timing: id 0 | task 845 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.436.075 I slot release: id 0 | task 845 | stop processing: n_tokens = 397, truncated = 0 0.10.453.229 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 10339461 0.10.483.528 I slot launch_slot_: id 0 | task 899 | processing task, is_child = 0 0.10.835.021 I slot print_timing: id 0 | task 899 | prompt eval time = 90.74 ms / 369 tokens ( 0.25 ms per token, 4066.52 tokens per second) 0.10.835.027 I slot print_timing: id 0 | task 899 | eval time = 260.73 ms / 41 tokens ( 6.52 ms per token, 153.41 tokens per second) 0.10.835.028 I slot print_timing: id 0 | task 899 | total time = 351.47 ms / 410 tokens 0.10.835.029 I slot print_timing: id 0 | task 899 | graphs reused = 858 0.10.835.029 I slot print_timing: id 0 | task 899 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.835.059 I slot release: id 0 | task 899 | stop processing: n_tokens = 409, truncated = 0 0.10.858.977 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 10738445 0.10.885.251 I slot launch_slot_: id 0 | task 943 | processing task, is_child = 0 0.11.232.448 I slot print_timing: id 0 | task 943 | prompt eval time = 87.78 ms / 352 tokens ( 0.25 ms per token, 4009.80 tokens per second) 0.11.232.454 I slot print_timing: id 0 | task 943 | eval time = 259.40 ms / 41 tokens ( 6.48 ms per token, 154.20 tokens per second) 0.11.232.455 I slot print_timing: id 0 | task 943 | total time = 347.18 ms / 393 tokens 0.11.232.456 I slot print_timing: id 0 | task 943 | graphs reused = 897 0.11.232.457 I slot print_timing: id 0 | task 943 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.232.483 I slot release: id 0 | task 943 | stop processing: n_tokens = 392, truncated = 0 0.11.246.855 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 11135869 0.11.276.998 I slot launch_slot_: id 0 | task 987 | processing task, is_child = 0 0.11.618.016 I slot print_timing: id 0 | task 987 | prompt eval time = 87.79 ms / 349 tokens ( 0.25 ms per token, 3975.44 tokens per second) 0.11.618.022 I slot print_timing: id 0 | task 987 | eval time = 253.21 ms / 40 tokens ( 6.49 ms per token, 154.02 tokens per second) 0.11.618.023 I slot print_timing: id 0 | task 987 | total time = 341.00 ms / 389 tokens 0.11.618.024 I slot print_timing: id 0 | task 987 | graphs reused = 935 0.11.618.024 I slot print_timing: id 0 | task 987 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.618.051 I slot release: id 0 | task 987 | stop processing: n_tokens = 388, truncated = 0 0.11.640.878 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 11521438 0.11.667.746 I slot launch_slot_: id 0 | task 1030 | processing task, is_child = 0 0.12.188.191 I slot print_timing: id 0 | task 1030 | prompt eval time = 91.85 ms / 384 tokens ( 0.24 ms per token, 4180.87 tokens per second) 0.12.188.197 I slot print_timing: id 0 | task 1030 | eval time = 428.58 ms / 63 tokens ( 6.91 ms per token, 144.66 tokens per second) 0.12.188.198 I slot print_timing: id 0 | task 1030 | total time = 520.43 ms / 447 tokens 0.12.188.198 I slot print_timing: id 0 | task 1030 | graphs reused = 996 0.12.188.199 I slot print_timing: id 0 | task 1030 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.188.228 I slot release: id 0 | task 1030 | stop processing: n_tokens = 446, truncated = 0 0.12.205.031 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 12091614 0.12.230.656 I slot launch_slot_: id 0 | task 1096 | processing task, is_child = 0 0.12.661.049 I slot print_timing: id 0 | task 1096 | prompt eval time = 88.08 ms / 356 tokens ( 0.25 ms per token, 4041.73 tokens per second) 0.12.661.055 I slot print_timing: id 0 | task 1096 | eval time = 342.29 ms / 54 tokens ( 6.46 ms per token, 154.84 tokens per second) 0.12.661.056 I slot print_timing: id 0 | task 1096 | total time = 430.37 ms / 410 tokens 0.12.661.056 I slot print_timing: id 0 | task 1096 | graphs reused = 1048 0.12.661.057 I slot print_timing: id 0 | task 1096 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.661.085 I slot release: id 0 | task 1096 | stop processing: n_tokens = 409, truncated = 0 0.12.677.030 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 12564471 0.12.702.445 I slot launch_slot_: id 0 | task 1153 | processing task, is_child = 0 0.13.240.624 I slot print_timing: id 0 | task 1153 | prompt eval time = 93.33 ms / 410 tokens ( 0.23 ms per token, 4393.20 tokens per second) 0.13.240.629 I slot print_timing: id 0 | task 1153 | eval time = 444.83 ms / 70 tokens ( 6.45 ms per token, 155.11 tokens per second) 0.13.240.630 I slot print_timing: id 0 | task 1153 | total time = 538.16 ms / 480 tokens 0.13.240.631 I slot print_timing: id 0 | task 1153 | graphs reused = 1116 0.13.240.631 I slot print_timing: id 0 | task 1153 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.240.662 I slot release: id 0 | task 1153 | stop processing: n_tokens = 479, truncated = 0 0.13.256.774 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 13144048 0.13.282.386 I slot launch_slot_: id 0 | task 1226 | processing task, is_child = 0 0.13.652.621 I slot print_timing: id 0 | task 1226 | prompt eval time = 91.45 ms / 385 tokens ( 0.24 ms per token, 4210.13 tokens per second) 0.13.652.627 I slot print_timing: id 0 | task 1226 | eval time = 278.77 ms / 44 tokens ( 6.48 ms per token, 154.25 tokens per second) 0.13.652.628 I slot print_timing: id 0 | task 1226 | total time = 370.22 ms / 429 tokens 0.13.652.629 I slot print_timing: id 0 | task 1226 | graphs reused = 1158 0.13.652.630 I slot print_timing: id 0 | task 1226 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.652.658 I slot release: id 0 | task 1226 | stop processing: n_tokens = 428, truncated = 0 0.13.672.812 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 13556045 0.13.698.443 I slot launch_slot_: id 0 | task 1273 | processing task, is_child = 0 0.14.241.281 I slot print_timing: id 0 | task 1273 | prompt eval time = 92.43 ms / 395 tokens ( 0.23 ms per token, 4273.55 tokens per second) 0.14.241.287 I slot print_timing: id 0 | task 1273 | eval time = 450.39 ms / 71 tokens ( 6.43 ms per token, 155.42 tokens per second) 0.14.241.288 I slot print_timing: id 0 | task 1273 | total time = 542.82 ms / 466 tokens 0.14.241.289 I slot print_timing: id 0 | task 1273 | graphs reused = 1227 0.14.241.290 I slot print_timing: id 0 | task 1273 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.241.318 I slot release: id 0 | task 1273 | stop processing: n_tokens = 465, truncated = 0 0.14.262.588 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 14144705 0.14.289.686 I slot launch_slot_: id 0 | task 1347 | processing task, is_child = 0 0.14.757.074 I slot print_timing: id 0 | task 1347 | prompt eval time = 93.29 ms / 430 tokens ( 0.22 ms per token, 4609.48 tokens per second) 0.14.757.080 I slot print_timing: id 0 | task 1347 | eval time = 374.09 ms / 59 tokens ( 6.45 ms per token, 155.04 tokens per second) 0.14.757.081 I slot print_timing: id 0 | task 1347 | total time = 467.37 ms / 489 tokens 0.14.757.082 I slot print_timing: id 0 | task 1347 | graphs reused = 1284 0.14.757.082 I slot print_timing: id 0 | task 1347 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.757.111 I slot release: id 0 | task 1347 | stop processing: n_tokens = 488, truncated = 0 0.14.774.881 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 488, t_last = 14660498 0.14.800.693 I slot launch_slot_: id 0 | task 1409 | processing task, is_child = 0 0.15.287.240 I slot print_timing: id 0 | task 1409 | prompt eval time = 92.30 ms / 392 tokens ( 0.24 ms per token, 4247.16 tokens per second) 0.15.287.246 I slot print_timing: id 0 | task 1409 | eval time = 394.23 ms / 62 tokens ( 6.46 ms per token, 154.73 tokens per second) 0.15.287.247 I slot print_timing: id 0 | task 1409 | total time = 486.53 ms / 454 tokens 0.15.287.248 I slot print_timing: id 0 | task 1409 | graphs reused = 1344 0.15.287.249 I slot print_timing: id 0 | task 1409 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.287.278 I slot release: id 0 | task 1409 | stop processing: n_tokens = 453, truncated = 0 0.15.304.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 15190664 0.15.330.114 I slot launch_slot_: id 0 | task 1474 | processing task, is_child = 0 0.15.728.374 I slot print_timing: id 0 | task 1474 | prompt eval time = 87.91 ms / 350 tokens ( 0.25 ms per token, 3981.30 tokens per second) 0.15.728.380 I slot print_timing: id 0 | task 1474 | eval time = 310.33 ms / 49 tokens ( 6.47 ms per token, 154.67 tokens per second) 0.15.728.381 I slot print_timing: id 0 | task 1474 | total time = 398.24 ms / 399 tokens 0.15.728.382 I slot print_timing: id 0 | task 1474 | graphs reused = 1391 0.15.728.383 I slot print_timing: id 0 | task 1474 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.728.409 I slot release: id 0 | task 1474 | stop processing: n_tokens = 398, truncated = 0 0.15.755.894 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 15631796 0.15.781.048 I slot launch_slot_: id 0 | task 1526 | processing task, is_child = 0 0.16.260.739 I slot print_timing: id 0 | task 1526 | prompt eval time = 92.75 ms / 380 tokens ( 0.24 ms per token, 4096.99 tokens per second) 0.16.260.744 I slot print_timing: id 0 | task 1526 | eval time = 386.92 ms / 61 tokens ( 6.45 ms per token, 155.07 tokens per second) 0.16.260.745 I slot print_timing: id 0 | task 1526 | total time = 479.67 ms / 441 tokens 0.16.260.746 I slot print_timing: id 0 | task 1526 | graphs reused = 1450 0.16.260.747 I slot print_timing: id 0 | task 1526 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.260.774 I slot release: id 0 | task 1526 | stop processing: n_tokens = 440, truncated = 0 0.16.282.897 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 16164161 0.16.308.149 I slot launch_slot_: id 0 | task 1590 | processing task, is_child = 0 0.16.942.069 I slot print_timing: id 0 | task 1590 | prompt eval time = 94.80 ms / 410 tokens ( 0.23 ms per token, 4325.12 tokens per second) 0.16.942.075 I slot print_timing: id 0 | task 1590 | eval time = 539.11 ms / 80 tokens ( 6.82 ms per token, 146.54 tokens per second) 0.16.942.076 I slot print_timing: id 0 | task 1590 | total time = 633.90 ms / 490 tokens 0.16.942.077 I slot print_timing: id 0 | task 1590 | graphs reused = 1528 0.16.942.077 I slot print_timing: id 0 | task 1590 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.942.107 I slot release: id 0 | task 1590 | stop processing: n_tokens = 489, truncated = 0 0.16.966.636 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 16845494 0.16.992.430 I slot launch_slot_: id 0 | task 1673 | processing task, is_child = 0 0.17.515.203 I slot print_timing: id 0 | task 1673 | prompt eval time = 91.55 ms / 387 tokens ( 0.24 ms per token, 4227.24 tokens per second) 0.17.515.209 I slot print_timing: id 0 | task 1673 | eval time = 431.20 ms / 68 tokens ( 6.44 ms per token, 155.38 tokens per second) 0.17.515.210 I slot print_timing: id 0 | task 1673 | total time = 522.75 ms / 455 tokens 0.17.515.211 I slot print_timing: id 0 | task 1673 | graphs reused = 1594 0.17.515.212 I slot print_timing: id 0 | task 1673 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.515.239 I slot release: id 0 | task 1673 | stop processing: n_tokens = 454, truncated = 0 0.17.528.824 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 17418625 0.17.555.698 I slot launch_slot_: id 0 | task 1744 | processing task, is_child = 0 0.18.017.837 I slot print_timing: id 0 | task 1744 | prompt eval time = 87.74 ms / 358 tokens ( 0.25 ms per token, 4080.33 tokens per second) 0.18.017.843 I slot print_timing: id 0 | task 1744 | eval time = 374.38 ms / 59 tokens ( 6.45 ms per token, 154.92 tokens per second) 0.18.017.843 I slot print_timing: id 0 | task 1744 | total time = 462.12 ms / 417 tokens 0.18.017.844 I slot print_timing: id 0 | task 1744 | graphs reused = 1651 0.18.017.845 I slot print_timing: id 0 | task 1744 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.017.872 I slot release: id 0 | task 1744 | stop processing: n_tokens = 416, truncated = 0 0.18.043.091 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 17921258 0.18.068.444 I slot launch_slot_: id 0 | task 1806 | processing task, is_child = 0 0.18.538.587 I slot print_timing: id 0 | task 1806 | prompt eval time = 87.96 ms / 359 tokens ( 0.25 ms per token, 4081.59 tokens per second) 0.18.538.593 I slot print_timing: id 0 | task 1806 | eval time = 382.17 ms / 56 tokens ( 6.95 ms per token, 143.92 tokens per second) 0.18.538.594 I slot print_timing: id 0 | task 1806 | total time = 470.12 ms / 415 tokens 0.18.538.595 I slot print_timing: id 0 | task 1806 | graphs reused = 1705 0.18.538.596 I slot print_timing: id 0 | task 1806 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.538.623 I slot release: id 0 | task 1806 | stop processing: n_tokens = 414, truncated = 0 0.18.556.851 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 18442009 0.18.583.286 I slot launch_slot_: id 0 | task 1865 | processing task, is_child = 0 0.19.061.968 I slot print_timing: id 0 | task 1865 | prompt eval time = 91.53 ms / 387 tokens ( 0.24 ms per token, 4228.08 tokens per second) 0.19.061.974 I slot print_timing: id 0 | task 1865 | eval time = 387.13 ms / 61 tokens ( 6.45 ms per token, 154.99 tokens per second) 0.19.061.975 I slot print_timing: id 0 | task 1865 | total time = 478.66 ms / 448 tokens 0.19.061.976 I slot print_timing: id 0 | task 1865 | graphs reused = 1764 0.19.061.976 I slot print_timing: id 0 | task 1865 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.062.007 I slot release: id 0 | task 1865 | stop processing: n_tokens = 447, truncated = 0 0.19.087.110 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 18965394 0.19.113.863 I slot launch_slot_: id 0 | task 1929 | processing task, is_child = 0 0.19.594.107 I slot print_timing: id 0 | task 1929 | prompt eval time = 92.68 ms / 410 tokens ( 0.23 ms per token, 4423.97 tokens per second) 0.19.594.113 I slot print_timing: id 0 | task 1929 | eval time = 387.55 ms / 61 tokens ( 6.46 ms per token, 154.82 tokens per second) 0.19.594.114 I slot print_timing: id 0 | task 1929 | total time = 480.23 ms / 471 tokens 0.19.594.115 I slot print_timing: id 0 | task 1929 | graphs reused = 1823 0.19.594.116 I slot print_timing: id 0 | task 1929 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.594.145 I slot release: id 0 | task 1929 | stop processing: n_tokens = 470, truncated = 0 0.19.619.038 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 19497531 0.19.645.967 I slot launch_slot_: id 0 | task 1993 | processing task, is_child = 0 0.20.050.934 I slot print_timing: id 0 | task 1993 | prompt eval time = 87.62 ms / 351 tokens ( 0.25 ms per token, 4006.07 tokens per second) 0.20.050.939 I slot print_timing: id 0 | task 1993 | eval time = 317.33 ms / 50 tokens ( 6.48 ms per token, 154.41 tokens per second) 0.20.050.941 I slot print_timing: id 0 | task 1993 | total time = 404.95 ms / 401 tokens 0.20.050.942 I slot print_timing: id 0 | task 1993 | graphs reused = 1871 0.20.050.942 I slot print_timing: id 0 | task 1993 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.050.971 I slot release: id 0 | task 1993 | stop processing: n_tokens = 400, truncated = 0 0.20.054.920 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 19954358 0.20.081.402 I slot launch_slot_: id 0 | task 2046 | processing task, is_child = 0 0.21.606.377 I slot print_timing: id 0 | task 2046 | prompt eval time = 91.48 ms / 393 tokens ( 0.23 ms per token, 4295.97 tokens per second) 0.21.606.383 I slot print_timing: id 0 | task 2046 | eval time = 1433.48 ms / 224 tokens ( 6.43 ms per token, 155.57 tokens per second) 0.21.606.384 I slot print_timing: id 0 | task 2046 | total time = 1524.96 ms / 617 tokens 0.21.606.385 I slot print_timing: id 0 | task 2046 | graphs reused = 2092 0.21.606.385 I slot print_timing: id 0 | task 2046 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.606.415 I slot release: id 0 | task 2046 | stop processing: n_tokens = 616, truncated = 0 0.21.632.448 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 21509802 0.21.672.938 I slot launch_slot_: id 0 | task 2273 | processing task, is_child = 0 0.21.949.383 I slot print_timing: id 0 | task 2273 | prompt eval time = 86.59 ms / 321 tokens ( 0.27 ms per token, 3707.00 tokens per second) 0.21.949.388 I slot print_timing: id 0 | task 2273 | eval time = 189.83 ms / 30 tokens ( 6.55 ms per token, 152.77 tokens per second) 0.21.949.389 I slot print_timing: id 0 | task 2273 | total time = 276.42 ms / 351 tokens 0.21.949.390 I slot print_timing: id 0 | task 2273 | graphs reused = 2120 0.21.949.391 I slot print_timing: id 0 | task 2273 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.949.416 I slot release: id 0 | task 2273 | stop processing: n_tokens = 350, truncated = 0 0.21.977.434 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 21852802 0.22.002.507 I slot launch_slot_: id 0 | task 2306 | processing task, is_child = 0 0.22.381.268 I slot print_timing: id 0 | task 2306 | prompt eval time = 87.03 ms / 330 tokens ( 0.26 ms per token, 3791.97 tokens per second) 0.22.381.273 I slot print_timing: id 0 | task 2306 | eval time = 291.71 ms / 46 tokens ( 6.48 ms per token, 154.26 tokens per second) 0.22.381.274 I slot print_timing: id 0 | task 2306 | total time = 378.74 ms / 376 tokens 0.22.381.275 I slot print_timing: id 0 | task 2306 | graphs reused = 2164 0.22.381.276 I slot print_timing: id 0 | task 2306 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.381.303 I slot release: id 0 | task 2306 | stop processing: n_tokens = 375, truncated = 0 0.22.398.523 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 22284689 0.22.423.713 I slot launch_slot_: id 0 | task 2355 | processing task, is_child = 0 0.22.712.906 I slot print_timing: id 0 | task 2355 | prompt eval time = 87.40 ms / 341 tokens ( 0.26 ms per token, 3901.56 tokens per second) 0.22.712.913 I slot print_timing: id 0 | task 2355 | eval time = 201.77 ms / 32 tokens ( 6.51 ms per token, 153.64 tokens per second) 0.22.712.914 I slot print_timing: id 0 | task 2355 | total time = 289.17 ms / 373 tokens 0.22.712.915 I slot print_timing: id 0 | task 2355 | graphs reused = 2194 0.22.712.916 I slot print_timing: id 0 | task 2355 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.712.946 I slot release: id 0 | task 2355 | stop processing: n_tokens = 372, truncated = 0 0.22.739.829 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 22616332 0.22.765.151 I slot launch_slot_: id 0 | task 2390 | processing task, is_child = 0 0.23.161.580 I slot print_timing: id 0 | task 2390 | prompt eval time = 92.71 ms / 338 tokens ( 0.27 ms per token, 3645.70 tokens per second) 0.23.161.586 I slot print_timing: id 0 | task 2390 | eval time = 303.70 ms / 48 tokens ( 6.46 ms per token, 154.76 tokens per second) 0.23.161.587 I slot print_timing: id 0 | task 2390 | total time = 396.41 ms / 386 tokens 0.23.161.588 I slot print_timing: id 0 | task 2390 | graphs reused = 2240 0.23.161.589 I slot print_timing: id 0 | task 2390 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.161.615 I slot release: id 0 | task 2390 | stop processing: n_tokens = 385, truncated = 0 0.23.177.675 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 23065002 0.23.203.110 I slot launch_slot_: id 0 | task 2441 | processing task, is_child = 0 0.23.651.404 I slot print_timing: id 0 | task 2441 | prompt eval time = 92.94 ms / 395 tokens ( 0.24 ms per token, 4249.92 tokens per second) 0.23.651.410 I slot print_timing: id 0 | task 2441 | eval time = 355.33 ms / 56 tokens ( 6.46 ms per token, 154.78 tokens per second) 0.23.651.411 I slot print_timing: id 0 | task 2441 | total time = 448.28 ms / 451 tokens 0.23.651.412 I slot print_timing: id 0 | task 2441 | graphs reused = 2294 0.23.651.412 I slot print_timing: id 0 | task 2441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.651.441 I slot release: id 0 | task 2441 | stop processing: n_tokens = 450, truncated = 0 0.23.676.992 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 23554827 0.23.703.211 I slot launch_slot_: id 0 | task 2500 | processing task, is_child = 0 0.24.360.588 I slot print_timing: id 0 | task 2500 | prompt eval time = 128.68 ms / 528 tokens ( 0.24 ms per token, 4103.17 tokens per second) 0.24.360.594 I slot print_timing: id 0 | task 2500 | eval time = 528.68 ms / 83 tokens ( 6.45 ms per token, 155.10 tokens per second) 0.24.360.595 I slot print_timing: id 0 | task 2500 | total time = 657.36 ms / 611 tokens 0.24.360.596 I slot print_timing: id 0 | task 2500 | graphs reused = 2375 0.24.360.597 I slot print_timing: id 0 | task 2500 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.360.630 I slot release: id 0 | task 2500 | stop processing: n_tokens = 610, truncated = 0 0.24.378.436 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 24264017 0.24.410.671 I slot launch_slot_: id 0 | task 2587 | processing task, is_child = 0 0.24.802.504 I slot print_timing: id 0 | task 2587 | prompt eval time = 106.36 ms / 331 tokens ( 0.32 ms per token, 3111.93 tokens per second) 0.24.802.510 I slot print_timing: id 0 | task 2587 | eval time = 285.45 ms / 45 tokens ( 6.49 ms per token, 154.14 tokens per second) 0.24.802.511 I slot print_timing: id 0 | task 2587 | total time = 391.81 ms / 376 tokens 0.24.802.512 I slot print_timing: id 0 | task 2587 | graphs reused = 2418 0.24.802.513 I slot print_timing: id 0 | task 2587 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.802.539 I slot release: id 0 | task 2587 | stop processing: n_tokens = 387, truncated = 0 0.24.830.960 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 24705926 0.24.863.440 I slot launch_slot_: id 0 | task 2635 | processing task, is_child = 0 0.25.309.997 I slot print_timing: id 0 | task 2635 | prompt eval time = 110.16 ms / 362 tokens ( 0.30 ms per token, 3286.10 tokens per second) 0.25.310.002 I slot print_timing: id 0 | task 2635 | eval time = 336.38 ms / 53 tokens ( 6.47 ms per token, 154.59 tokens per second) 0.25.310.003 I slot print_timing: id 0 | task 2635 | total time = 446.54 ms / 415 tokens 0.25.310.004 I slot print_timing: id 0 | task 2635 | graphs reused = 2469 0.25.310.005 I slot print_timing: id 0 | task 2635 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.310.034 I slot release: id 0 | task 2635 | stop processing: n_tokens = 426, truncated = 0 0.25.328.132 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 25213420 0.25.366.301 I slot launch_slot_: id 0 | task 2691 | processing task, is_child = 0 0.25.917.070 I slot print_timing: id 0 | task 2691 | prompt eval time = 112.23 ms / 419 tokens ( 0.27 ms per token, 3733.37 tokens per second) 0.25.917.076 I slot print_timing: id 0 | task 2691 | eval time = 438.52 ms / 69 tokens ( 6.45 ms per token, 155.07 tokens per second) 0.25.917.077 I slot print_timing: id 0 | task 2691 | total time = 550.75 ms / 488 tokens 0.25.917.078 I slot print_timing: id 0 | task 2691 | graphs reused = 2536 0.25.917.079 I slot print_timing: id 0 | task 2691 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.917.108 I slot release: id 0 | task 2691 | stop processing: n_tokens = 499, truncated = 0 0.25.945.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 25820495 0.25.980.131 I slot launch_slot_: id 0 | task 2763 | processing task, is_child = 0 0.26.614.054 I slot print_timing: id 0 | task 2763 | prompt eval time = 118.22 ms / 423 tokens ( 0.28 ms per token, 3578.23 tokens per second) 0.26.614.060 I slot print_timing: id 0 | task 2763 | eval time = 515.69 ms / 72 tokens ( 7.26 ms per token, 137.68 tokens per second) 0.26.614.061 I slot print_timing: id 0 | task 2763 | total time = 633.90 ms / 495 tokens 0.26.614.062 I slot print_timing: id 0 | task 2763 | graphs reused = 2606 0.26.614.063 I slot print_timing: id 0 | task 2763 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.614.093 I slot release: id 0 | task 2763 | stop processing: n_tokens = 506, truncated = 0 0.26.629.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 26517480 0.26.663.358 I slot launch_slot_: id 0 | task 2838 | processing task, is_child = 0 0.27.044.065 I slot print_timing: id 0 | task 2838 | prompt eval time = 106.87 ms / 341 tokens ( 0.31 ms per token, 3190.76 tokens per second) 0.27.044.071 I slot print_timing: id 0 | task 2838 | eval time = 273.82 ms / 43 tokens ( 6.52 ms per token, 153.39 tokens per second) 0.27.044.072 I slot print_timing: id 0 | task 2838 | total time = 380.69 ms / 384 tokens 0.27.044.073 I slot print_timing: id 0 | task 2838 | graphs reused = 2647 0.27.044.074 I slot print_timing: id 0 | task 2838 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.044.102 I slot release: id 0 | task 2838 | stop processing: n_tokens = 395, truncated = 0 0.27.066.125 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 26947488 0.27.099.402 I slot launch_slot_: id 0 | task 2884 | processing task, is_child = 0 0.27.504.793 I slot print_timing: id 0 | task 2884 | prompt eval time = 107.24 ms / 356 tokens ( 0.30 ms per token, 3319.75 tokens per second) 0.27.504.799 I slot print_timing: id 0 | task 2884 | eval time = 298.13 ms / 47 tokens ( 6.48 ms per token, 154.29 tokens per second) 0.27.504.800 I slot print_timing: id 0 | task 2884 | total time = 405.37 ms / 403 tokens 0.27.504.801 I slot print_timing: id 0 | task 2884 | graphs reused = 2692 0.27.504.802 I slot print_timing: id 0 | task 2884 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.504.830 I slot release: id 0 | task 2884 | stop processing: n_tokens = 414, truncated = 0 0.27.519.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 27408217 0.27.519.815 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 0.27.565.131 I slot launch_slot_: id 0 | task 2934 | processing task, is_child = 0 0.27.967.812 I slot print_timing: id 0 | task 2934 | prompt eval time = 109.91 ms / 362 tokens ( 0.30 ms per token, 3293.57 tokens per second) 0.27.967.818 I slot print_timing: id 0 | task 2934 | eval time = 292.75 ms / 46 tokens ( 6.51 ms per token, 153.72 tokens per second) 0.27.967.819 I slot print_timing: id 0 | task 2934 | total time = 402.66 ms / 408 tokens 0.27.967.820 I slot print_timing: id 0 | task 2934 | graphs reused = 2736 0.27.967.821 I slot print_timing: id 0 | task 2934 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.967.852 I slot release: id 0 | task 2934 | stop processing: n_tokens = 419, truncated = 0 0.27.990.961 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 27871238 0.27.991.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.28.034.950 I slot launch_slot_: id 0 | task 2983 | processing task, is_child = 0 0.28.578.921 I slot print_timing: id 0 | task 2983 | prompt eval time = 111.46 ms / 391 tokens ( 0.29 ms per token, 3507.86 tokens per second) 0.28.578.927 I slot print_timing: id 0 | task 2983 | eval time = 432.49 ms / 68 tokens ( 6.46 ms per token, 154.92 tokens per second) 0.28.578.928 I slot print_timing: id 0 | task 2983 | total time = 543.95 ms / 459 tokens 0.28.578.928 I slot print_timing: id 0 | task 2983 | graphs reused = 2802 0.28.578.929 I slot print_timing: id 0 | task 2983 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.578.958 I slot release: id 0 | task 2983 | stop processing: n_tokens = 470, truncated = 0 0.28.594.144 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 28482345 0.28.594.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.28.637.504 I slot launch_slot_: id 0 | task 3054 | processing task, is_child = 0 0.29.086.330 I slot print_timing: id 0 | task 3054 | prompt eval time = 106.75 ms / 343 tokens ( 0.31 ms per token, 3213.11 tokens per second) 0.29.086.335 I slot print_timing: id 0 | task 3054 | eval time = 342.06 ms / 54 tokens ( 6.45 ms per token, 154.94 tokens per second) 0.29.086.337 I slot print_timing: id 0 | task 3054 | total time = 448.81 ms / 397 tokens 0.29.086.338 I slot print_timing: id 0 | task 3054 | graphs reused = 2854 0.29.086.338 I slot print_timing: id 0 | task 3054 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.086.366 I slot release: id 0 | task 3054 | stop processing: n_tokens = 408, truncated = 0 0.29.106.099 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 28989753 0.29.106.147 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.29.116.763 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.29.162.764 I slot launch_slot_: id 0 | task 3111 | processing task, is_child = 0 0.29.566.053 I slot print_timing: id 0 | task 3111 | prompt eval time = 111.32 ms / 401 tokens ( 0.28 ms per token, 3602.29 tokens per second) 0.29.566.058 I slot print_timing: id 0 | task 3111 | eval time = 291.95 ms / 46 tokens ( 6.49 ms per token, 154.14 tokens per second) 0.29.566.060 I slot print_timing: id 0 | task 3111 | total time = 403.27 ms / 447 tokens 0.29.566.060 I slot print_timing: id 0 | task 3111 | graphs reused = 2898 0.29.566.061 I slot print_timing: id 0 | task 3111 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.566.090 I slot release: id 0 | task 3111 | stop processing: n_tokens = 458, truncated = 0 0.29.589.132 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 29469476 0.29.589.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.29.633.034 I slot launch_slot_: id 0 | task 3160 | processing task, is_child = 0 0.30.176.976 I slot print_timing: id 0 | task 3160 | prompt eval time = 111.58 ms / 355 tokens ( 0.31 ms per token, 3181.72 tokens per second) 0.30.176.981 I slot print_timing: id 0 | task 3160 | eval time = 432.35 ms / 68 tokens ( 6.45 ms per token, 154.97 tokens per second) 0.30.176.982 I slot print_timing: id 0 | task 3160 | total time = 543.93 ms / 423 tokens 0.30.176.983 I slot print_timing: id 0 | task 3160 | graphs reused = 2964 0.30.176.984 I slot print_timing: id 0 | task 3160 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.177.011 I slot release: id 0 | task 3160 | stop processing: n_tokens = 434, truncated = 0 0.30.192.832 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 30080397 0.30.192.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.30.236.348 I slot launch_slot_: id 0 | task 3231 | processing task, is_child = 0 0.30.731.822 I slot print_timing: id 0 | task 3231 | prompt eval time = 107.17 ms / 351 tokens ( 0.31 ms per token, 3275.11 tokens per second) 0.30.731.828 I slot print_timing: id 0 | task 3231 | eval time = 388.29 ms / 57 tokens ( 6.93 ms per token, 144.22 tokens per second) 0.30.731.829 I slot print_timing: id 0 | task 3231 | total time = 495.46 ms / 408 tokens 0.30.731.829 I slot print_timing: id 0 | task 3231 | graphs reused = 3019 0.30.731.830 I slot print_timing: id 0 | task 3231 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.731.858 I slot release: id 0 | task 3231 | stop processing: n_tokens = 419, truncated = 0 0.30.754.918 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 30635244 0.30.754.970 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.30.765.362 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.30.808.249 I slot launch_slot_: id 0 | task 3291 | processing task, is_child = 0 0.31.528.999 I slot print_timing: id 0 | task 3291 | prompt eval time = 122.74 ms / 475 tokens ( 0.26 ms per token, 3869.94 tokens per second) 0.31.529.004 I slot print_timing: id 0 | task 3291 | eval time = 597.99 ms / 93 tokens ( 6.50 ms per token, 153.85 tokens per second) 0.31.529.005 I slot print_timing: id 0 | task 3291 | total time = 720.73 ms / 568 tokens 0.31.529.006 I slot print_timing: id 0 | task 3291 | graphs reused = 3109 0.31.529.007 I slot print_timing: id 0 | task 3291 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.529.038 I slot release: id 0 | task 3291 | stop processing: n_tokens = 579, truncated = 0 0.31.548.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 31432425 0.31.548.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.824 MiB) 0.31.593.418 I slot launch_slot_: id 0 | task 3387 | processing task, is_child = 0 0.32.301.221 I slot print_timing: id 0 | task 3387 | prompt eval time = 118.23 ms / 440 tokens ( 0.27 ms per token, 3721.50 tokens per second) 0.32.301.227 I slot print_timing: id 0 | task 3387 | eval time = 589.55 ms / 92 tokens ( 6.48 ms per token, 154.35 tokens per second) 0.32.301.228 I slot print_timing: id 0 | task 3387 | total time = 707.78 ms / 532 tokens 0.32.301.229 I slot print_timing: id 0 | task 3387 | graphs reused = 3198 0.32.301.229 I slot print_timing: id 0 | task 3387 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.301.261 I slot release: id 0 | task 3387 | stop processing: n_tokens = 543, truncated = 0 0.32.328.807 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 32204647 0.32.328.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.32.378.818 I slot launch_slot_: id 0 | task 3482 | processing task, is_child = 0 0.32.834.008 I slot print_timing: id 0 | task 3482 | prompt eval time = 106.21 ms / 345 tokens ( 0.31 ms per token, 3248.16 tokens per second) 0.32.834.014 I slot print_timing: id 0 | task 3482 | eval time = 348.96 ms / 55 tokens ( 6.46 ms per token, 154.75 tokens per second) 0.32.834.015 I slot print_timing: id 0 | task 3482 | total time = 455.17 ms / 400 tokens 0.32.834.016 I slot print_timing: id 0 | task 3482 | graphs reused = 3251 0.32.834.016 I slot print_timing: id 0 | task 3482 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.834.047 I slot release: id 0 | task 3482 | stop processing: n_tokens = 411, truncated = 0 0.32.837.951 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 32737433 0.32.838.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.32.849.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.32.896.185 I slot launch_slot_: id 0 | task 3540 | processing task, is_child = 0 0.33.358.064 I slot print_timing: id 0 | task 3540 | prompt eval time = 112.62 ms / 382 tokens ( 0.29 ms per token, 3391.85 tokens per second) 0.33.358.070 I slot print_timing: id 0 | task 3540 | eval time = 349.24 ms / 55 tokens ( 6.47 ms per token, 154.62 tokens per second) 0.33.358.071 I slot print_timing: id 0 | task 3540 | total time = 461.86 ms / 437 tokens 0.33.358.072 I slot print_timing: id 0 | task 3540 | graphs reused = 3304 0.33.358.073 I slot print_timing: id 0 | task 3540 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.358.103 I slot release: id 0 | task 3540 | stop processing: n_tokens = 448, truncated = 0 0.33.380.496 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 33261490 0.33.380.545 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.33.422.645 I slot launch_slot_: id 0 | task 3598 | processing task, is_child = 0 0.33.814.233 I slot print_timing: id 0 | task 3598 | prompt eval time = 106.22 ms / 337 tokens ( 0.32 ms per token, 3172.69 tokens per second) 0.33.814.239 I slot print_timing: id 0 | task 3598 | eval time = 285.35 ms / 45 tokens ( 6.49 ms per token, 154.20 tokens per second) 0.33.814.240 I slot print_timing: id 0 | task 3598 | total time = 391.57 ms / 382 tokens 0.33.814.241 I slot print_timing: id 0 | task 3598 | graphs reused = 3347 0.33.814.241 I slot print_timing: id 0 | task 3598 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.814.267 I slot release: id 0 | task 3598 | stop processing: n_tokens = 393, truncated = 0 0.33.832.857 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 33717654 0.33.832.907 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.33.879.810 I slot launch_slot_: id 0 | task 3646 | processing task, is_child = 0 0.34.466.064 I slot print_timing: id 0 | task 3646 | prompt eval time = 114.29 ms / 402 tokens ( 0.28 ms per token, 3517.40 tokens per second) 0.34.466.070 I slot print_timing: id 0 | task 3646 | eval time = 471.94 ms / 70 tokens ( 6.84 ms per token, 146.20 tokens per second) 0.34.466.071 I slot print_timing: id 0 | task 3646 | total time = 586.23 ms / 472 tokens 0.34.466.072 I slot print_timing: id 0 | task 3646 | graphs reused = 3415 0.34.466.073 I slot print_timing: id 0 | task 3646 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.466.102 I slot release: id 0 | task 3646 | stop processing: n_tokens = 483, truncated = 0 0.34.489.349 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 34369489 0.34.489.400 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.34.499.646 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.34.543.129 I slot launch_slot_: id 0 | task 3719 | processing task, is_child = 0 0.35.034.961 I slot print_timing: id 0 | task 3719 | prompt eval time = 130.21 ms / 549 tokens ( 0.24 ms per token, 4216.30 tokens per second) 0.35.034.966 I slot print_timing: id 0 | task 3719 | eval time = 361.61 ms / 57 tokens ( 6.46 ms per token, 154.87 tokens per second) 0.35.034.967 I slot print_timing: id 0 | task 3719 | total time = 491.81 ms / 606 tokens 0.35.034.968 I slot print_timing: id 0 | task 3719 | graphs reused = 3470 0.35.034.969 I slot print_timing: id 0 | task 3719 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.035.000 I slot release: id 0 | task 3719 | stop processing: n_tokens = 617, truncated = 0 0.35.059.570 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 34938387 0.35.059.627 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.35.110.348 I slot launch_slot_: id 0 | task 3780 | processing task, is_child = 0 0.35.621.648 I slot print_timing: id 0 | task 3780 | prompt eval time = 142.49 ms / 616 tokens ( 0.23 ms per token, 4323.26 tokens per second) 0.35.621.654 I slot print_timing: id 0 | task 3780 | eval time = 368.80 ms / 58 tokens ( 6.47 ms per token, 154.56 tokens per second) 0.35.621.655 I slot print_timing: id 0 | task 3780 | total time = 511.28 ms / 674 tokens 0.35.621.656 I slot print_timing: id 0 | task 3780 | graphs reused = 3526 0.35.621.657 I slot print_timing: id 0 | task 3780 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.621.692 I slot release: id 0 | task 3780 | stop processing: n_tokens = 685, truncated = 0 0.35.647.948 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 35525078 0.35.648.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.886 MiB) 0.35.658.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.35.709.049 I slot launch_slot_: id 0 | task 3842 | processing task, is_child = 0 0.36.253.204 I slot print_timing: id 0 | task 3842 | prompt eval time = 148.89 ms / 665 tokens ( 0.22 ms per token, 4466.50 tokens per second) 0.36.253.209 I slot print_timing: id 0 | task 3842 | eval time = 395.25 ms / 62 tokens ( 6.48 ms per token, 154.33 tokens per second) 0.36.253.210 I slot print_timing: id 0 | task 3842 | total time = 544.14 ms / 727 tokens 0.36.253.211 I slot print_timing: id 0 | task 3842 | graphs reused = 3586 0.36.253.212 I slot print_timing: id 0 | task 3842 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.253.249 I slot release: id 0 | task 3842 | stop processing: n_tokens = 738, truncated = 0 0.36.270.831 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 36156635 0.36.270.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.36.281.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.36.332.497 I slot launch_slot_: id 0 | task 3908 | processing task, is_child = 0 0.36.827.837 I slot print_timing: id 0 | task 3908 | prompt eval time = 145.85 ms / 645 tokens ( 0.23 ms per token, 4422.29 tokens per second) 0.36.827.842 I slot print_timing: id 0 | task 3908 | eval time = 349.47 ms / 55 tokens ( 6.47 ms per token, 154.52 tokens per second) 0.36.827.843 I slot print_timing: id 0 | task 3908 | total time = 495.32 ms / 700 tokens 0.36.827.844 I slot print_timing: id 0 | task 3908 | graphs reused = 3639 0.36.827.845 I slot print_timing: id 0 | task 3908 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.827.882 I slot release: id 0 | task 3908 | stop processing: n_tokens = 711, truncated = 0 0.36.847.333 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 36731269 0.36.847.387 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.137 MiB) 0.36.905.081 I slot launch_slot_: id 0 | task 3967 | processing task, is_child = 0 0.37.367.578 I slot print_timing: id 0 | task 3967 | prompt eval time = 126.69 ms / 474 tokens ( 0.27 ms per token, 3741.36 tokens per second) 0.37.367.583 I slot print_timing: id 0 | task 3967 | eval time = 335.78 ms / 52 tokens ( 6.58 ms per token, 151.88 tokens per second) 0.37.367.584 I slot print_timing: id 0 | task 3967 | total time = 462.48 ms / 526 tokens 0.37.367.585 I slot print_timing: id 0 | task 3967 | graphs reused = 3688 0.37.367.586 I slot print_timing: id 0 | task 3967 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.367.618 I slot release: id 0 | task 3967 | stop processing: n_tokens = 537, truncated = 0 0.37.391.727 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 37271004 0.37.391.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.37.402.144 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.013 MiB) 0.37.445.883 I slot launch_slot_: id 0 | task 4022 | processing task, is_child = 0 0.37.849.453 I slot print_timing: id 0 | task 4022 | prompt eval time = 137.11 ms / 617 tokens ( 0.22 ms per token, 4500.10 tokens per second) 0.37.849.459 I slot print_timing: id 0 | task 4022 | eval time = 266.44 ms / 42 tokens ( 6.50 ms per token, 153.88 tokens per second) 0.37.849.460 I slot print_timing: id 0 | task 4022 | total time = 403.55 ms / 659 tokens 0.37.849.461 I slot print_timing: id 0 | task 4022 | graphs reused = 3728 0.37.849.462 I slot print_timing: id 0 | task 4022 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.849.498 I slot release: id 0 | task 4022 | stop processing: n_tokens = 670, truncated = 0 0.37.877.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 37752885 0.37.877.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 0.37.930.094 I slot launch_slot_: id 0 | task 4068 | processing task, is_child = 0 0.38.376.362 I slot print_timing: id 0 | task 4068 | prompt eval time = 141.19 ms / 601 tokens ( 0.23 ms per token, 4256.62 tokens per second) 0.38.376.367 I slot print_timing: id 0 | task 4068 | eval time = 305.06 ms / 48 tokens ( 6.49 ms per token, 154.07 tokens per second) 0.38.376.368 I slot print_timing: id 0 | task 4068 | total time = 446.25 ms / 649 tokens 0.38.376.369 I slot print_timing: id 0 | task 4068 | graphs reused = 3774 0.38.376.370 I slot print_timing: id 0 | task 4068 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.376.406 I slot release: id 0 | task 4068 | stop processing: n_tokens = 660, truncated = 0 0.38.391.577 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 38279793 0.38.391.637 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 0.38.401.705 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.38.457.632 I slot launch_slot_: id 0 | task 4120 | processing task, is_child = 0 0.38.889.489 I slot print_timing: id 0 | task 4120 | prompt eval time = 132.51 ms / 533 tokens ( 0.25 ms per token, 4022.28 tokens per second) 0.38.889.495 I slot print_timing: id 0 | task 4120 | eval time = 299.33 ms / 47 tokens ( 6.51 ms per token, 153.68 tokens per second) 0.38.889.496 I slot print_timing: id 0 | task 4120 | total time = 431.84 ms / 580 tokens 0.38.889.497 I slot print_timing: id 0 | task 4120 | graphs reused = 3819 0.38.889.497 I slot print_timing: id 0 | task 4120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.889.532 I slot release: id 0 | task 4120 | stop processing: n_tokens = 591, truncated = 0 0.38.904.621 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 38792918 0.38.904.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 0.38.965.379 I slot launch_slot_: id 0 | task 4171 | processing task, is_child = 0 0.39.423.743 I slot print_timing: id 0 | task 4171 | prompt eval time = 122.54 ms / 480 tokens ( 0.26 ms per token, 3916.99 tokens per second) 0.39.423.749 I slot print_timing: id 0 | task 4171 | eval time = 335.80 ms / 52 tokens ( 6.58 ms per token, 151.88 tokens per second) 0.39.423.750 I slot print_timing: id 0 | task 4171 | total time = 458.35 ms / 532 tokens 0.39.423.751 I slot print_timing: id 0 | task 4171 | graphs reused = 3868 0.39.423.752 I slot print_timing: id 0 | task 4171 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.423.782 I slot release: id 0 | task 4171 | stop processing: n_tokens = 560, truncated = 0 0.39.438.795 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 39327169 0.39.438.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 0.39.448.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.39.499.484 I slot launch_slot_: id 0 | task 4226 | processing task, is_child = 0 0.39.897.341 I slot print_timing: id 0 | task 4226 | prompt eval time = 131.62 ms / 567 tokens ( 0.23 ms per token, 4307.76 tokens per second) 0.39.897.346 I slot print_timing: id 0 | task 4226 | eval time = 266.21 ms / 42 tokens ( 6.49 ms per token, 154.01 tokens per second) 0.39.897.348 I slot print_timing: id 0 | task 4226 | total time = 397.84 ms / 609 tokens 0.39.897.348 I slot print_timing: id 0 | task 4226 | graphs reused = 3908 0.39.897.349 I slot print_timing: id 0 | task 4226 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.897.385 I slot release: id 0 | task 4226 | stop processing: n_tokens = 637, truncated = 0 0.39.924.135 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 39800772 0.39.924.194 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 0.39.934.197 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 0.39.991.864 I slot launch_slot_: id 0 | task 4272 | processing task, is_child = 0 0.40.521.120 I slot print_timing: id 0 | task 4272 | prompt eval time = 127.55 ms / 506 tokens ( 0.25 ms per token, 3966.98 tokens per second) 0.40.521.126 I slot print_timing: id 0 | task 4272 | eval time = 401.68 ms / 63 tokens ( 6.48 ms per token, 154.35 tokens per second) 0.40.521.127 I slot print_timing: id 0 | task 4272 | total time = 529.24 ms / 569 tokens 0.40.521.129 I slot print_timing: id 0 | task 4272 | graphs reused = 3969 0.40.521.130 I slot print_timing: id 0 | task 4272 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.521.164 I slot release: id 0 | task 4272 | stop processing: n_tokens = 597, truncated = 0 0.40.545.278 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 40424551 0.40.545.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 0.40.555.569 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 0.40.605.976 I slot launch_slot_: id 0 | task 4338 | processing task, is_child = 0 0.40.976.245 I slot print_timing: id 0 | task 4338 | prompt eval time = 117.30 ms / 436 tokens ( 0.27 ms per token, 3716.87 tokens per second) 0.40.976.251 I slot print_timing: id 0 | task 4338 | eval time = 252.95 ms / 40 tokens ( 6.49 ms per token, 154.18 tokens per second) 0.40.976.252 I slot print_timing: id 0 | task 4338 | total time = 370.25 ms / 476 tokens 0.40.976.253 I slot print_timing: id 0 | task 4338 | graphs reused = 4007 0.40.976.254 I slot print_timing: id 0 | task 4338 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.976.286 I slot release: id 0 | task 4338 | stop processing: n_tokens = 504, truncated = 0 0.41.001.643 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 40879673 0.41.001.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 0.41.052.185 I slot launch_slot_: id 0 | task 4381 | processing task, is_child = 0 0.41.573.923 I slot print_timing: id 0 | task 4381 | prompt eval time = 126.92 ms / 519 tokens ( 0.24 ms per token, 4089.19 tokens per second) 0.41.573.929 I slot print_timing: id 0 | task 4381 | eval time = 394.80 ms / 62 tokens ( 6.47 ms per token, 154.51 tokens per second) 0.41.573.930 I slot print_timing: id 0 | task 4381 | total time = 521.72 ms / 581 tokens 0.41.573.932 I slot print_timing: id 0 | task 4381 | graphs reused = 4067 0.41.573.933 I slot print_timing: id 0 | task 4381 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.573.966 I slot release: id 0 | task 4381 | stop processing: n_tokens = 609, truncated = 0 0.41.597.371 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 41477352 0.41.597.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.697 MiB) 0.41.607.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.479 MiB) 0.41.661.065 I slot launch_slot_: id 0 | task 4447 | processing task, is_child = 0 0.42.077.091 I slot print_timing: id 0 | task 4447 | prompt eval time = 119.02 ms / 465 tokens ( 0.26 ms per token, 3907.07 tokens per second) 0.42.077.097 I slot print_timing: id 0 | task 4447 | eval time = 296.99 ms / 46 tokens ( 6.60 ms per token, 151.52 tokens per second) 0.42.077.098 I slot print_timing: id 0 | task 4447 | total time = 416.00 ms / 511 tokens 0.42.077.099 I slot print_timing: id 0 | task 4447 | graphs reused = 4110 0.42.077.100 I slot print_timing: id 0 | task 4447 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.077.131 I slot release: id 0 | task 4447 | stop processing: n_tokens = 542, truncated = 0 0.42.093.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 41980517 0.42.093.422 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 0.42.103.470 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 0.42.166.069 I slot launch_slot_: id 0 | task 4496 | processing task, is_child = 0 0.42.543.651 I slot print_timing: id 0 | task 4496 | prompt eval time = 118.26 ms / 431 tokens ( 0.27 ms per token, 3644.39 tokens per second) 0.42.543.657 I slot print_timing: id 0 | task 4496 | eval time = 259.30 ms / 41 tokens ( 6.48 ms per token, 154.26 tokens per second) 0.42.543.658 I slot print_timing: id 0 | task 4496 | total time = 377.56 ms / 472 tokens 0.42.543.659 I slot print_timing: id 0 | task 4496 | graphs reused = 4149 0.42.543.660 I slot print_timing: id 0 | task 4496 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.543.691 I slot release: id 0 | task 4496 | stop processing: n_tokens = 503, truncated = 0 0.42.559.004 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 42447078 0.42.559.053 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 0.42.569.224 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 0.42.628.667 I slot launch_slot_: id 0 | task 4540 | processing task, is_child = 0 0.43.031.243 I slot print_timing: id 0 | task 4540 | prompt eval time = 118.86 ms / 457 tokens ( 0.26 ms per token, 3844.73 tokens per second) 0.43.031.249 I slot print_timing: id 0 | task 4540 | eval time = 283.69 ms / 44 tokens ( 6.60 ms per token, 151.57 tokens per second) 0.43.031.250 I slot print_timing: id 0 | task 4540 | total time = 402.56 ms / 501 tokens 0.43.031.251 I slot print_timing: id 0 | task 4540 | graphs reused = 4190 0.43.031.252 I slot print_timing: id 0 | task 4540 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.031.283 I slot release: id 0 | task 4540 | stop processing: n_tokens = 532, truncated = 0 0.43.058.408 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 42934670 0.43.058.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 0.43.117.975 I slot launch_slot_: id 0 | task 4587 | processing task, is_child = 0 0.43.502.219 I slot print_timing: id 0 | task 4587 | prompt eval time = 117.99 ms / 439 tokens ( 0.27 ms per token, 3720.69 tokens per second) 0.43.502.225 I slot print_timing: id 0 | task 4587 | eval time = 266.24 ms / 42 tokens ( 6.49 ms per token, 154.00 tokens per second) 0.43.502.226 I slot print_timing: id 0 | task 4587 | total time = 384.23 ms / 481 tokens 0.43.502.227 I slot print_timing: id 0 | task 4587 | graphs reused = 4230 0.43.502.228 I slot print_timing: id 0 | task 4587 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.502.258 I slot release: id 0 | task 4587 | stop processing: n_tokens = 512, truncated = 0 0.43.530.814 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 43405645 0.43.530.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 0.43.544.106 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 0.43.603.921 I slot launch_slot_: id 0 | task 4632 | processing task, is_child = 0 0.44.094.483 I slot print_timing: id 0 | task 4632 | prompt eval time = 135.49 ms / 606 tokens ( 0.22 ms per token, 4472.62 tokens per second) 0.44.094.489 I slot print_timing: id 0 | task 4632 | eval time = 355.05 ms / 56 tokens ( 6.46 ms per token, 154.91 tokens per second) 0.44.094.490 I slot print_timing: id 0 | task 4632 | total time = 490.54 ms / 662 tokens 0.44.094.491 I slot print_timing: id 0 | task 4632 | graphs reused = 4284 0.44.094.491 I slot print_timing: id 0 | task 4632 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.094.527 I slot release: id 0 | task 4632 | stop processing: n_tokens = 693, truncated = 0 0.44.109.479 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 43997913 0.44.109.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.827 MiB) 0.44.122.986 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 0.44.196.033 I slot launch_slot_: id 0 | task 4692 | processing task, is_child = 0 0.44.583.313 I slot print_timing: id 0 | task 4692 | prompt eval time = 122.82 ms / 477 tokens ( 0.26 ms per token, 3883.64 tokens per second) 0.44.583.319 I slot print_timing: id 0 | task 4692 | eval time = 264.44 ms / 41 tokens ( 6.61 ms per token, 151.26 tokens per second) 0.44.583.320 I slot print_timing: id 0 | task 4692 | total time = 387.26 ms / 518 tokens 0.44.583.321 I slot print_timing: id 0 | task 4692 | graphs reused = 4322 0.44.583.322 I slot print_timing: id 0 | task 4692 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.583.353 I slot release: id 0 | task 4692 | stop processing: n_tokens = 549, truncated = 0 0.44.609.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 44486740 0.44.610.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 0.44.672.877 I slot launch_slot_: id 0 | task 4736 | processing task, is_child = 0 0.45.218.915 I slot print_timing: id 0 | task 4736 | prompt eval time = 163.82 ms / 845 tokens ( 0.19 ms per token, 5157.97 tokens per second) 0.45.218.921 I slot print_timing: id 0 | task 4736 | eval time = 382.19 ms / 60 tokens ( 6.48 ms per token, 154.37 tokens per second) 0.45.218.922 I slot print_timing: id 0 | task 4736 | total time = 546.02 ms / 905 tokens 0.45.218.923 I slot print_timing: id 0 | task 4736 | graphs reused = 4380 0.45.218.924 I slot print_timing: id 0 | task 4736 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.218.968 I slot release: id 0 | task 4736 | stop processing: n_tokens = 936, truncated = 0 0.45.243.035 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 45122354 0.45.243.093 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 0.45.256.204 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 0.45.322.733 I slot launch_slot_: id 0 | task 4800 | processing task, is_child = 0 0.45.740.771 I slot print_timing: id 0 | task 4800 | prompt eval time = 124.71 ms / 459 tokens ( 0.27 ms per token, 3680.45 tokens per second) 0.45.740.777 I slot print_timing: id 0 | task 4800 | eval time = 293.30 ms / 43 tokens ( 6.98 ms per token, 143.20 tokens per second) 0.45.740.778 I slot print_timing: id 0 | task 4800 | total time = 418.02 ms / 502 tokens 0.45.740.779 I slot print_timing: id 0 | task 4800 | graphs reused = 4420 0.45.740.780 I slot print_timing: id 0 | task 4800 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.740.817 I slot release: id 0 | task 4800 | stop processing: n_tokens = 533, truncated = 0 0.45.767.720 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 45644203 0.45.767.773 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 0.45.829.529 I slot launch_slot_: id 0 | task 4846 | processing task, is_child = 0 0.46.288.326 I slot print_timing: id 0 | task 4846 | prompt eval time = 151.34 ms / 670 tokens ( 0.23 ms per token, 4427.03 tokens per second) 0.46.288.333 I slot print_timing: id 0 | task 4846 | eval time = 307.43 ms / 47 tokens ( 6.68 ms per token, 149.63 tokens per second) 0.46.288.334 I slot print_timing: id 0 | task 4846 | total time = 458.78 ms / 717 tokens 0.46.288.335 I slot print_timing: id 0 | task 4846 | graphs reused = 4465 0.46.288.336 I slot print_timing: id 0 | task 4846 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.288.376 I slot release: id 0 | task 4846 | stop processing: n_tokens = 748, truncated = 0 0.46.316.539 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 46191762 0.46.316.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 0.46.329.922 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 0.46.401.599 I slot launch_slot_: id 0 | task 4897 | processing task, is_child = 0 0.47.006.469 I slot print_timing: id 0 | task 4897 | prompt eval time = 165.93 ms / 775 tokens ( 0.21 ms per token, 4670.73 tokens per second) 0.47.006.475 I slot print_timing: id 0 | task 4897 | eval time = 438.92 ms / 63 tokens ( 7.08 ms per token, 141.26 tokens per second) 0.47.006.476 I slot print_timing: id 0 | task 4897 | total time = 604.85 ms / 838 tokens 0.47.006.477 I slot print_timing: id 0 | task 4897 | graphs reused = 4526 0.47.006.478 I slot print_timing: id 0 | task 4897 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.006.522 I slot release: id 0 | task 4897 | stop processing: n_tokens = 869, truncated = 0 0.47.035.830 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 46909909 0.47.035.898 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 0.47.049.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 0.47.118.119 I slot launch_slot_: id 0 | task 4964 | processing task, is_child = 0 0.47.720.883 I slot print_timing: id 0 | task 4964 | prompt eval time = 137.55 ms / 573 tokens ( 0.24 ms per token, 4165.73 tokens per second) 0.47.720.889 I slot print_timing: id 0 | task 4964 | eval time = 465.19 ms / 71 tokens ( 6.65 ms per token, 150.48 tokens per second) 0.47.720.890 I slot print_timing: id 0 | task 4964 | total time = 602.74 ms / 644 tokens 0.47.720.891 I slot print_timing: id 0 | task 4964 | graphs reused = 4595 0.47.720.891 I slot print_timing: id 0 | task 4964 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.720.928 I slot release: id 0 | task 4964 | stop processing: n_tokens = 675, truncated = 0 0.47.724.959 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 47624315 0.47.725.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.984 MiB) 0.47.738.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 0.47.805.631 I slot launch_slot_: id 0 | task 5039 | processing task, is_child = 0 0.48.351.800 I slot print_timing: id 0 | task 5039 | prompt eval time = 127.16 ms / 461 tokens ( 0.28 ms per token, 3625.30 tokens per second) 0.48.351.806 I slot print_timing: id 0 | task 5039 | eval time = 418.99 ms / 64 tokens ( 6.65 ms per token, 150.36 tokens per second) 0.48.351.807 I slot print_timing: id 0 | task 5039 | total time = 546.15 ms / 525 tokens 0.48.351.808 I slot print_timing: id 0 | task 5039 | graphs reused = 4656 0.48.351.809 I slot print_timing: id 0 | task 5039 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.351.840 I slot release: id 0 | task 5039 | stop processing: n_tokens = 556, truncated = 0 0.48.377.681 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 48255227 0.48.377.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 0.48.437.870 I slot launch_slot_: id 0 | task 5106 | processing task, is_child = 0 0.49.145.694 I slot print_timing: id 0 | task 5106 | prompt eval time = 137.03 ms / 609 tokens ( 0.23 ms per token, 4444.25 tokens per second) 0.49.145.700 I slot print_timing: id 0 | task 5106 | eval time = 570.77 ms / 84 tokens ( 6.88 ms per token, 145.42 tokens per second) 0.49.145.701 I slot print_timing: id 0 | task 5106 | total time = 707.80 ms / 693 tokens 0.49.145.701 I slot print_timing: id 0 | task 5106 | graphs reused = 4738 0.49.145.703 I slot print_timing: id 0 | task 5106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.145.741 I slot release: id 0 | task 5106 | stop processing: n_tokens = 724, truncated = 0 0.49.162.103 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 724, t_last = 49049127 0.49.162.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 0.49.175.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 0.49.240.527 I slot launch_slot_: id 0 | task 5194 | processing task, is_child = 0 0.49.804.608 I slot print_timing: id 0 | task 5194 | prompt eval time = 162.27 ms / 791 tokens ( 0.21 ms per token, 4874.71 tokens per second) 0.49.804.614 I slot print_timing: id 0 | task 5194 | eval time = 401.79 ms / 61 tokens ( 6.70 ms per token, 149.33 tokens per second) 0.49.804.615 I slot print_timing: id 0 | task 5194 | total time = 564.06 ms / 852 tokens 0.49.804.616 I slot print_timing: id 0 | task 5194 | graphs reused = 4797 0.49.804.617 I slot print_timing: id 0 | task 5194 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.804.664 I slot release: id 0 | task 5194 | stop processing: n_tokens = 883, truncated = 0 0.49.822.123 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 49708050 0.49.822.199 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 0.49.937.995 I slot launch_slot_: id 0 | task 5259 | processing task, is_child = 0 0.50.436.888 I slot print_timing: id 0 | task 5259 | prompt eval time = 136.09 ms / 533 tokens ( 0.26 ms per token, 3916.55 tokens per second) 0.50.436.894 I slot print_timing: id 0 | task 5259 | eval time = 362.78 ms / 56 tokens ( 6.60 ms per token, 151.61 tokens per second) 0.50.436.895 I slot print_timing: id 0 | task 5259 | total time = 498.87 ms / 589 tokens 0.50.436.896 I slot print_timing: id 0 | task 5259 | graphs reused = 4851 0.50.436.896 I slot print_timing: id 0 | task 5259 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.436.932 I slot release: id 0 | task 5259 | stop processing: n_tokens = 677, truncated = 0 0.50.451.372 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 50340319 0.50.451.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 0.50.528.670 I slot launch_slot_: id 0 | task 5319 | processing task, is_child = 0 0.50.998.175 I slot print_timing: id 0 | task 5319 | prompt eval time = 145.69 ms / 566 tokens ( 0.26 ms per token, 3885.01 tokens per second) 0.50.998.181 I slot print_timing: id 0 | task 5319 | eval time = 323.80 ms / 46 tokens ( 7.20 ms per token, 138.98 tokens per second) 0.50.998.182 I slot print_timing: id 0 | task 5319 | total time = 469.49 ms / 612 tokens 0.50.998.182 I slot print_timing: id 0 | task 5319 | graphs reused = 4895 0.50.998.183 I slot print_timing: id 0 | task 5319 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.998.220 I slot release: id 0 | task 5319 | stop processing: n_tokens = 643, truncated = 0 0.51.022.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 50901607 0.51.023.029 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.332 MiB) 0.51.099.403 I slot launch_slot_: id 0 | task 5369 | processing task, is_child = 0 0.51.507.822 I slot print_timing: id 0 | task 5369 | prompt eval time = 122.18 ms / 443 tokens ( 0.28 ms per token, 3625.77 tokens per second) 0.51.507.828 I slot print_timing: id 0 | task 5369 | eval time = 286.22 ms / 43 tokens ( 6.81 ms per token, 146.74 tokens per second) 0.51.507.829 I slot print_timing: id 0 | task 5369 | total time = 408.40 ms / 486 tokens 0.51.507.830 I slot print_timing: id 0 | task 5369 | graphs reused = 4935 0.51.507.831 I slot print_timing: id 0 | task 5369 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.507.861 I slot release: id 0 | task 5369 | stop processing: n_tokens = 517, truncated = 0 0.51.536.210 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 51411248 0.51.536.261 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 0.51.601.130 I slot launch_slot_: id 0 | task 5415 | processing task, is_child = 0 0.52.146.772 I slot print_timing: id 0 | task 5415 | prompt eval time = 121.54 ms / 487 tokens ( 0.25 ms per token, 4006.94 tokens per second) 0.52.146.778 I slot print_timing: id 0 | task 5415 | eval time = 424.08 ms / 65 tokens ( 6.63 ms per token, 150.91 tokens per second) 0.52.146.779 I slot print_timing: id 0 | task 5415 | total time = 545.62 ms / 552 tokens 0.52.146.780 I slot print_timing: id 0 | task 5415 | graphs reused = 4998 0.52.146.780 I slot print_timing: id 0 | task 5415 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.146.813 I slot release: id 0 | task 5415 | stop processing: n_tokens = 583, truncated = 0 0.52.172.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 52050199 0.52.172.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 0.52.233.338 I slot launch_slot_: id 0 | task 5483 | processing task, is_child = 0 0.52.662.645 I slot print_timing: id 0 | task 5483 | prompt eval time = 129.12 ms / 507 tokens ( 0.25 ms per token, 3926.70 tokens per second) 0.52.662.651 I slot print_timing: id 0 | task 5483 | eval time = 300.17 ms / 47 tokens ( 6.53 ms per token, 153.25 tokens per second) 0.52.662.652 I slot print_timing: id 0 | task 5483 | total time = 429.29 ms / 554 tokens 0.52.662.653 I slot print_timing: id 0 | task 5483 | graphs reused = 5043 0.52.662.654 I slot print_timing: id 0 | task 5483 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.662.690 I slot release: id 0 | task 5483 | stop processing: n_tokens = 585, truncated = 0 0.52.688.251 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 52566076 0.52.688.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 0.52.705.081 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 0.52.774.987 I slot launch_slot_: id 0 | task 5533 | processing task, is_child = 0 0.53.341.284 I slot print_timing: id 0 | task 5533 | prompt eval time = 140.60 ms / 633 tokens ( 0.22 ms per token, 4502.13 tokens per second) 0.53.341.289 I slot print_timing: id 0 | task 5533 | eval time = 425.68 ms / 66 tokens ( 6.55 ms per token, 152.70 tokens per second) 0.53.341.290 I slot print_timing: id 0 | task 5533 | total time = 566.28 ms / 699 tokens 0.53.341.291 I slot print_timing: id 0 | task 5533 | graphs reused = 5107 0.53.341.292 I slot print_timing: id 0 | task 5533 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.341.332 I slot release: id 0 | task 5533 | stop processing: n_tokens = 730, truncated = 0 0.53.345.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 53244719 0.53.345.708 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 0.53.416.722 I slot launch_slot_: id 0 | task 5603 | processing task, is_child = 0 0.53.862.921 I slot print_timing: id 0 | task 5603 | prompt eval time = 139.75 ms / 571 tokens ( 0.24 ms per token, 4085.84 tokens per second) 0.53.862.927 I slot print_timing: id 0 | task 5603 | eval time = 306.43 ms / 47 tokens ( 6.66 ms per token, 150.12 tokens per second) 0.53.862.928 I slot print_timing: id 0 | task 5603 | total time = 446.18 ms / 618 tokens 0.53.862.929 I slot print_timing: id 0 | task 5603 | graphs reused = 5152 0.53.862.930 I slot print_timing: id 0 | task 5603 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.862.973 I slot release: id 0 | task 5603 | stop processing: n_tokens = 649, truncated = 0 0.53.868.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 53766360 0.53.868.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 0.53.944.193 I slot launch_slot_: id 0 | task 5654 | processing task, is_child = 0 0.54.394.825 I slot print_timing: id 0 | task 5654 | prompt eval time = 166.07 ms / 798 tokens ( 0.21 ms per token, 4805.32 tokens per second) 0.54.394.834 I slot print_timing: id 0 | task 5654 | eval time = 284.54 ms / 44 tokens ( 6.62 ms per token, 151.12 tokens per second) 0.54.394.836 I slot print_timing: id 0 | task 5654 | total time = 450.60 ms / 842 tokens 0.54.394.837 I slot print_timing: id 0 | task 5654 | graphs reused = 5194 0.54.394.838 I slot print_timing: id 0 | task 5654 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.394.886 I slot release: id 0 | task 5654 | stop processing: n_tokens = 873, truncated = 0 0.54.414.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 54298272 0.54.414.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 0.54.434.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 0.54.511.305 I slot launch_slot_: id 0 | task 5702 | processing task, is_child = 0 0.54.926.806 I slot print_timing: id 0 | task 5702 | prompt eval time = 140.81 ms / 572 tokens ( 0.25 ms per token, 4062.21 tokens per second) 0.54.926.812 I slot print_timing: id 0 | task 5702 | eval time = 274.67 ms / 43 tokens ( 6.54 ms per token, 152.91 tokens per second) 0.54.926.813 I slot print_timing: id 0 | task 5702 | total time = 415.48 ms / 615 tokens 0.54.926.814 I slot print_timing: id 0 | task 5702 | graphs reused = 5235 0.54.926.815 I slot print_timing: id 0 | task 5702 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.926.855 I slot release: id 0 | task 5702 | stop processing: n_tokens = 646, truncated = 0 0.54.943.726 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 54830242 0.54.943.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 0.55.020.109 I slot launch_slot_: id 0 | task 5749 | processing task, is_child = 0 0.55.592.789 I slot print_timing: id 0 | task 5749 | prompt eval time = 140.46 ms / 613 tokens ( 0.23 ms per token, 4364.26 tokens per second) 0.55.592.795 I slot print_timing: id 0 | task 5749 | eval time = 432.20 ms / 64 tokens ( 6.86 ms per token, 145.77 tokens per second) 0.55.592.796 I slot print_timing: id 0 | task 5749 | total time = 572.66 ms / 677 tokens 0.55.592.797 I slot print_timing: id 0 | task 5749 | graphs reused = 5297 0.55.592.798 I slot print_timing: id 0 | task 5749 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.592.833 I slot release: id 0 | task 5749 | stop processing: n_tokens = 708, truncated = 0 0.55.609.118 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 708, t_last = 55496219 0.55.609.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 0.55.683.832 I slot launch_slot_: id 0 | task 5817 | processing task, is_child = 0 0.56.226.666 I slot print_timing: id 0 | task 5817 | prompt eval time = 135.61 ms / 580 tokens ( 0.23 ms per token, 4277.07 tokens per second) 0.56.226.673 I slot print_timing: id 0 | task 5817 | eval time = 407.20 ms / 64 tokens ( 6.46 ms per token, 154.71 tokens per second) 0.56.226.674 I slot print_timing: id 0 | task 5817 | total time = 542.81 ms / 644 tokens 0.56.226.675 I slot print_timing: id 0 | task 5817 | graphs reused = 5359 0.56.226.676 I slot print_timing: id 0 | task 5817 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.226.717 I slot release: id 0 | task 5817 | stop processing: n_tokens = 675, truncated = 0 0.56.245.927 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 56130104 0.56.245.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 0.56.318.325 I slot launch_slot_: id 0 | task 5885 | processing task, is_child = 0 0.56.793.230 I slot print_timing: id 0 | task 5885 | prompt eval time = 152.11 ms / 716 tokens ( 0.21 ms per token, 4707.18 tokens per second) 0.56.793.236 I slot print_timing: id 0 | task 5885 | eval time = 322.78 ms / 50 tokens ( 6.59 ms per token, 151.81 tokens per second) 0.56.793.237 I slot print_timing: id 0 | task 5885 | total time = 474.88 ms / 766 tokens 0.56.793.238 I slot print_timing: id 0 | task 5885 | graphs reused = 5406 0.56.793.239 I slot print_timing: id 0 | task 5885 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.793.279 I slot release: id 0 | task 5885 | stop processing: n_tokens = 797, truncated = 0 0.56.808.390 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 56696665 0.56.808.456 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 0.56.829.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 0.56.912.910 I slot launch_slot_: id 0 | task 5939 | processing task, is_child = 0 0.57.729.142 I slot print_timing: id 0 | task 5939 | prompt eval time = 164.79 ms / 799 tokens ( 0.21 ms per token, 4848.62 tokens per second) 0.57.729.149 I slot print_timing: id 0 | task 5939 | eval time = 651.42 ms / 102 tokens ( 6.45 ms per token, 155.05 tokens per second) 0.57.729.150 I slot print_timing: id 0 | task 5939 | total time = 816.21 ms / 901 tokens 0.57.729.150 I slot print_timing: id 0 | task 5939 | graphs reused = 5506 0.57.729.151 I slot print_timing: id 0 | task 5939 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.729.192 I slot release: id 0 | task 5939 | stop processing: n_tokens = 932, truncated = 0 0.57.733.299 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 57632579 0.57.733.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 0.57.809.865 I slot launch_slot_: id 0 | task 6045 | processing task, is_child = 0 0.58.637.790 I slot print_timing: id 0 | task 6045 | prompt eval time = 115.57 ms / 361 tokens ( 0.32 ms per token, 3123.68 tokens per second) 0.58.637.795 I slot print_timing: id 0 | task 6045 | eval time = 712.34 ms / 112 tokens ( 6.42 ms per token, 155.83 tokens per second) 0.58.637.796 I slot print_timing: id 0 | task 6045 | total time = 827.90 ms / 473 tokens 0.58.637.797 I slot print_timing: id 0 | task 6045 | graphs reused = 5616 0.58.637.798 I slot print_timing: id 0 | task 6045 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.637.828 I slot release: id 0 | task 6045 | stop processing: n_tokens = 504, truncated = 0 0.58.665.235 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 58541214 0.58.665.286 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 0.58.734.869 I slot launch_slot_: id 0 | task 6160 | processing task, is_child = 0 0.59.536.627 I slot print_timing: id 0 | task 6160 | prompt eval time = 111.06 ms / 381 tokens ( 0.29 ms per token, 3430.70 tokens per second) 0.59.536.633 I slot print_timing: id 0 | task 6160 | eval time = 690.68 ms / 108 tokens ( 6.45 ms per token, 154.92 tokens per second) 0.59.536.634 I slot print_timing: id 0 | task 6160 | total time = 801.74 ms / 489 tokens 0.59.536.635 I slot print_timing: id 0 | task 6160 | graphs reused = 5721 0.59.536.635 I slot print_timing: id 0 | task 6160 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.536.666 I slot release: id 0 | task 6160 | stop processing: n_tokens = 520, truncated = 0 0.59.551.611 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 59440053 0.59.551.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 0.59.617.786 I slot launch_slot_: id 0 | task 6271 | processing task, is_child = 0 1.00.520.707 I slot print_timing: id 0 | task 6271 | prompt eval time = 108.78 ms / 365 tokens ( 0.30 ms per token, 3355.52 tokens per second) 1.00.520.713 I slot print_timing: id 0 | task 6271 | eval time = 794.12 ms / 124 tokens ( 6.46 ms per token, 154.89 tokens per second) 1.00.520.714 I slot print_timing: id 0 | task 6271 | total time = 902.90 ms / 489 tokens 1.00.520.715 I slot print_timing: id 0 | task 6271 | graphs reused = 5842 1.00.520.716 I slot print_timing: id 0 | task 6271 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.520.746 I slot release: id 0 | task 6271 | stop processing: n_tokens = 520, truncated = 0 1.00.540.869 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 60424133 1.00.540.909 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.00.610.372 I slot launch_slot_: id 0 | task 6398 | processing task, is_child = 0 1.01.397.726 I slot print_timing: id 0 | task 6398 | prompt eval time = 106.67 ms / 333 tokens ( 0.32 ms per token, 3121.69 tokens per second) 1.01.397.732 I slot print_timing: id 0 | task 6398 | eval time = 680.66 ms / 107 tokens ( 6.42 ms per token, 155.73 tokens per second) 1.01.397.733 I slot print_timing: id 0 | task 6398 | total time = 787.34 ms / 440 tokens 1.01.397.734 I slot print_timing: id 0 | task 6398 | graphs reused = 5947 1.01.397.735 I slot print_timing: id 0 | task 6398 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.397.762 I slot release: id 0 | task 6398 | stop processing: n_tokens = 471, truncated = 0 1.01.426.624 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 61301149 1.01.469.590 I slot launch_slot_: id 0 | task 6508 | processing task, is_child = 0 1.02.465.791 I slot print_timing: id 0 | task 6508 | prompt eval time = 112.70 ms / 403 tokens ( 0.28 ms per token, 3575.99 tokens per second) 1.02.465.798 I slot print_timing: id 0 | task 6508 | eval time = 883.49 ms / 138 tokens ( 6.45 ms per token, 155.07 tokens per second) 1.02.465.799 I slot print_timing: id 0 | task 6508 | total time = 996.18 ms / 541 tokens 1.02.465.800 I slot print_timing: id 0 | task 6508 | graphs reused = 6082 1.02.465.801 I slot print_timing: id 0 | task 6508 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.465.832 I slot release: id 0 | task 6508 | stop processing: n_tokens = 572, truncated = 0 1.02.491.383 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 62369219 1.02.491.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.02.557.609 I slot launch_slot_: id 0 | task 6649 | processing task, is_child = 0 1.03.855.833 I slot print_timing: id 0 | task 6649 | prompt eval time = 111.54 ms / 411 tokens ( 0.27 ms per token, 3684.91 tokens per second) 1.03.855.839 I slot print_timing: id 0 | task 6649 | eval time = 1186.67 ms / 185 tokens ( 6.45 ms per token, 155.06 tokens per second) 1.03.855.840 I slot print_timing: id 0 | task 6649 | total time = 1298.21 ms / 596 tokens 1.03.855.841 I slot print_timing: id 0 | task 6649 | graphs reused = 6264 1.03.855.842 I slot print_timing: id 0 | task 6649 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.855.872 I slot release: id 0 | task 6649 | stop processing: n_tokens = 627, truncated = 0 1.03.879.888 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 63759258 1.03.879.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.03.950.025 I slot launch_slot_: id 0 | task 6837 | processing task, is_child = 0 1.05.512.059 I slot print_timing: id 0 | task 6837 | prompt eval time = 125.46 ms / 490 tokens ( 0.26 ms per token, 3905.53 tokens per second) 1.05.512.065 I slot print_timing: id 0 | task 6837 | eval time = 1436.55 ms / 225 tokens ( 6.41 ms per token, 155.93 tokens per second) 1.05.512.066 I slot print_timing: id 0 | task 6837 | total time = 1562.02 ms / 715 tokens 1.05.512.067 I slot print_timing: id 0 | task 6837 | graphs reused = 6487 1.05.512.068 I slot print_timing: id 0 | task 6837 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.512.100 I slot release: id 0 | task 6837 | stop processing: n_tokens = 746, truncated = 0 1.05.538.359 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 65415486 1.05.538.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.05.609.800 I slot launch_slot_: id 0 | task 7065 | processing task, is_child = 0 1.08.305.615 I slot print_timing: id 0 | task 7065 | prompt eval time = 106.75 ms / 344 tokens ( 0.31 ms per token, 3222.54 tokens per second) 1.08.305.621 I slot print_timing: id 0 | task 7065 | eval time = 2589.05 ms / 404 tokens ( 6.42 ms per token, 155.66 tokens per second) 1.08.305.622 I slot print_timing: id 0 | task 7065 | total time = 2695.80 ms / 748 tokens 1.08.305.623 I slot print_timing: id 0 | task 7065 | graphs reused = 6887 1.08.305.624 I slot print_timing: id 0 | task 7065 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.305.654 I slot release: id 0 | task 7065 | stop processing: n_tokens = 779, truncated = 0 1.08.322.350 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 68209041 1.08.322.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 1.08.390.464 I slot launch_slot_: id 0 | task 7472 | processing task, is_child = 0 1.09.592.276 I slot print_timing: id 0 | task 7472 | prompt eval time = 106.56 ms / 347 tokens ( 0.31 ms per token, 3256.41 tokens per second) 1.09.592.281 I slot print_timing: id 0 | task 7472 | eval time = 1095.23 ms / 171 tokens ( 6.44 ms per token, 155.22 tokens per second) 1.09.592.282 I slot print_timing: id 0 | task 7472 | total time = 1201.79 ms / 518 tokens 1.09.592.283 I slot print_timing: id 0 | task 7472 | graphs reused = 7055 1.09.592.284 I slot print_timing: id 0 | task 7472 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.592.313 I slot release: id 0 | task 7472 | stop processing: n_tokens = 549, truncated = 0 1.09.619.082 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 69495699 1.09.619.134 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.396 MiB) 1.09.691.646 I slot launch_slot_: id 0 | task 7646 | processing task, is_child = 0 1.10.611.361 I slot print_timing: id 0 | task 7646 | prompt eval time = 111.99 ms / 401 tokens ( 0.28 ms per token, 3580.61 tokens per second) 1.10.611.367 I slot print_timing: id 0 | task 7646 | eval time = 807.70 ms / 126 tokens ( 6.46 ms per token, 154.76 tokens per second) 1.10.611.368 I slot print_timing: id 0 | task 7646 | total time = 919.70 ms / 527 tokens 1.10.611.369 I slot print_timing: id 0 | task 7646 | graphs reused = 7178 1.10.611.370 I slot print_timing: id 0 | task 7646 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.611.400 I slot release: id 0 | task 7646 | stop processing: n_tokens = 558, truncated = 0 1.10.633.461 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 70514787 1.10.633.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.10.703.769 I slot launch_slot_: id 0 | task 7775 | processing task, is_child = 0 1.11.587.640 I slot print_timing: id 0 | task 7775 | prompt eval time = 117.81 ms / 456 tokens ( 0.26 ms per token, 3870.57 tokens per second) 1.11.587.646 I slot print_timing: id 0 | task 7775 | eval time = 766.04 ms / 115 tokens ( 6.72 ms per token, 148.82 tokens per second) 1.11.587.647 I slot print_timing: id 0 | task 7775 | total time = 883.85 ms / 571 tokens 1.11.587.648 I slot print_timing: id 0 | task 7775 | graphs reused = 7290 1.11.587.649 I slot print_timing: id 0 | task 7775 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.587.680 I slot release: id 0 | task 7775 | stop processing: n_tokens = 602, truncated = 0 1.11.614.205 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.078 1.11.614.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.11.689.716 I slot launch_slot_: id 0 | task 7893 | processing task, is_child = 0 1.12.523.674 I slot print_timing: id 0 | task 7893 | prompt eval time = 113.78 ms / 406 tokens ( 0.28 ms per token, 3568.32 tokens per second) 1.12.523.679 I slot print_timing: id 0 | task 7893 | eval time = 720.16 ms / 112 tokens ( 6.49 ms per token, 154.13 tokens per second) 1.12.523.680 I slot print_timing: id 0 | task 7893 | total time = 833.94 ms / 518 tokens 1.12.523.681 I slot print_timing: id 0 | task 7893 | graphs reused = 7399 1.12.523.682 I slot print_timing: id 0 | task 7893 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.523.711 I slot release: id 0 | task 7893 | stop processing: n_tokens = 549, truncated = 0 1.12.545.118 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 72427098 1.12.591.749 I slot launch_slot_: id 0 | task 8008 | processing task, is_child = 0 1.13.819.469 I slot print_timing: id 0 | task 8008 | prompt eval time = 112.03 ms / 406 tokens ( 0.28 ms per token, 3624.00 tokens per second) 1.13.819.475 I slot print_timing: id 0 | task 8008 | eval time = 1115.67 ms / 174 tokens ( 6.45 ms per token, 155.06 tokens per second) 1.13.819.476 I slot print_timing: id 0 | task 8008 | total time = 1227.70 ms / 580 tokens 1.13.819.477 I slot print_timing: id 0 | task 8008 | graphs reused = 7570 1.13.819.478 I slot print_timing: id 0 | task 8008 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.819.507 I slot release: id 0 | task 8008 | stop processing: n_tokens = 611, truncated = 0 1.13.823.541 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 73722894 1.13.823.585 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.13.893.595 I slot launch_slot_: id 0 | task 8185 | processing task, is_child = 0 1.14.932.462 I slot print_timing: id 0 | task 8185 | prompt eval time = 115.79 ms / 444 tokens ( 0.26 ms per token, 3834.56 tokens per second) 1.14.932.468 I slot print_timing: id 0 | task 8185 | eval time = 923.06 ms / 144 tokens ( 6.45 ms per token, 154.92 tokens per second) 1.14.932.469 I slot print_timing: id 0 | task 8185 | total time = 1038.85 ms / 588 tokens 1.14.932.470 I slot print_timing: id 0 | task 8185 | graphs reused = 7711 1.14.932.471 I slot print_timing: id 0 | task 8185 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.932.501 I slot release: id 0 | task 8185 | stop processing: n_tokens = 619, truncated = 0 1.14.946.452 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 74835888 1.14.946.504 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.15.012.909 I slot launch_slot_: id 0 | task 8332 | processing task, is_child = 0 1.15.778.971 I slot print_timing: id 0 | task 8332 | prompt eval time = 111.22 ms / 372 tokens ( 0.30 ms per token, 3344.66 tokens per second) 1.15.778.976 I slot print_timing: id 0 | task 8332 | eval time = 654.82 ms / 103 tokens ( 6.42 ms per token, 155.77 tokens per second) 1.15.778.978 I slot print_timing: id 0 | task 8332 | total time = 766.04 ms / 475 tokens 1.15.778.978 I slot print_timing: id 0 | task 8332 | graphs reused = 7812 1.15.778.979 I slot print_timing: id 0 | task 8332 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.779.007 I slot release: id 0 | task 8332 | stop processing: n_tokens = 506, truncated = 0 1.15.807.389 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 75682394 1.15.807.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.15.881.187 I slot launch_slot_: id 0 | task 8438 | processing task, is_child = 0 1.17.475.297 I slot print_timing: id 0 | task 8438 | prompt eval time = 120.54 ms / 454 tokens ( 0.27 ms per token, 3766.32 tokens per second) 1.17.475.303 I slot print_timing: id 0 | task 8438 | eval time = 1473.55 ms / 230 tokens ( 6.43 ms per token, 155.41 tokens per second) 1.17.475.304 I slot print_timing: id 0 | task 8438 | total time = 1594.09 ms / 684 tokens 1.17.475.305 I slot print_timing: id 0 | task 8438 | graphs reused = 8039 1.17.475.305 I slot print_timing: id 0 | task 8438 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.475.334 I slot release: id 0 | task 8438 | stop processing: n_tokens = 715, truncated = 0 1.17.502.185 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 77378721 1.17.502.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.17.573.393 I slot launch_slot_: id 0 | task 8671 | processing task, is_child = 0 1.19.130.169 I slot print_timing: id 0 | task 8671 | prompt eval time = 109.74 ms / 354 tokens ( 0.31 ms per token, 3225.69 tokens per second) 1.19.130.175 I slot print_timing: id 0 | task 8671 | eval time = 1447.01 ms / 226 tokens ( 6.43 ms per token, 155.49 tokens per second) 1.19.130.177 I slot print_timing: id 0 | task 8671 | total time = 1556.76 ms / 580 tokens 1.19.130.178 I slot print_timing: id 0 | task 8671 | graphs reused = 8262 1.19.130.178 I slot print_timing: id 0 | task 8671 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.130.208 I slot release: id 0 | task 8671 | stop processing: n_tokens = 611, truncated = 0 1.19.157.444 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 79033595 1.19.157.494 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.19.228.178 I slot launch_slot_: id 0 | task 8900 | processing task, is_child = 0 1.20.227.313 I slot print_timing: id 0 | task 8900 | prompt eval time = 107.01 ms / 334 tokens ( 0.32 ms per token, 3121.23 tokens per second) 1.20.227.319 I slot print_timing: id 0 | task 8900 | eval time = 892.11 ms / 140 tokens ( 6.42 ms per token, 155.81 tokens per second) 1.20.227.320 I slot print_timing: id 0 | task 8900 | total time = 999.11 ms / 474 tokens 1.20.227.321 I slot print_timing: id 0 | task 8900 | graphs reused = 8400 1.20.227.322 I slot print_timing: id 0 | task 8900 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.227.349 I slot release: id 0 | task 8900 | stop processing: n_tokens = 505, truncated = 0 1.20.249.086 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 80130736 1.20.249.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.050 MiB) 1.20.315.785 I slot launch_slot_: id 0 | task 9043 | processing task, is_child = 0 1.21.552.836 I slot print_timing: id 0 | task 9043 | prompt eval time = 115.23 ms / 426 tokens ( 0.27 ms per token, 3697.05 tokens per second) 1.21.552.842 I slot print_timing: id 0 | task 9043 | eval time = 1121.81 ms / 175 tokens ( 6.45 ms per token, 155.11 tokens per second) 1.21.552.843 I slot print_timing: id 0 | task 9043 | total time = 1237.03 ms / 601 tokens 1.21.552.844 I slot print_timing: id 0 | task 9043 | graphs reused = 8572 1.21.552.845 I slot print_timing: id 0 | task 9043 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.552.875 I slot release: id 0 | task 9043 | stop processing: n_tokens = 632, truncated = 0 1.21.580.345 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 81456262 1.21.580.398 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 1.21.651.280 I slot launch_slot_: id 0 | task 9221 | processing task, is_child = 0 1.22.510.056 I slot print_timing: id 0 | task 9221 | prompt eval time = 109.11 ms / 366 tokens ( 0.30 ms per token, 3354.54 tokens per second) 1.22.510.060 I slot print_timing: id 0 | task 9221 | eval time = 749.65 ms / 117 tokens ( 6.46 ms per token, 154.74 tokens per second) 1.22.510.062 I slot print_timing: id 0 | task 9221 | total time = 858.75 ms / 483 tokens 1.22.510.062 I slot print_timing: id 0 | task 9221 | graphs reused = 8686 1.22.510.063 I slot print_timing: id 0 | task 9221 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.510.093 I slot release: id 0 | task 9221 | stop processing: n_tokens = 514, truncated = 0 1.22.532.883 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 82413480 1.22.532.931 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 1.22.602.302 I slot launch_slot_: id 0 | task 9341 | processing task, is_child = 0 1.24.390.137 I slot print_timing: id 0 | task 9341 | prompt eval time = 119.78 ms / 462 tokens ( 0.26 ms per token, 3856.97 tokens per second) 1.24.390.143 I slot print_timing: id 0 | task 9341 | eval time = 1668.03 ms / 260 tokens ( 6.44 ms per token, 155.27 tokens per second) 1.24.390.144 I slot print_timing: id 0 | task 9341 | total time = 1787.81 ms / 722 tokens 1.24.390.145 I slot print_timing: id 0 | task 9341 | graphs reused = 8943 1.24.390.146 I slot print_timing: id 0 | task 9341 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.390.178 I slot release: id 0 | task 9341 | stop processing: n_tokens = 753, truncated = 0 1.24.417.634 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 84293565 1.24.417.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.895 MiB) 1.24.491.740 I slot launch_slot_: id 0 | task 9604 | processing task, is_child = 0 1.25.493.140 I slot print_timing: id 0 | task 9604 | prompt eval time = 111.48 ms / 396 tokens ( 0.28 ms per token, 3552.24 tokens per second) 1.25.493.146 I slot print_timing: id 0 | task 9604 | eval time = 889.90 ms / 139 tokens ( 6.45 ms per token, 155.07 tokens per second) 1.25.493.147 I slot print_timing: id 0 | task 9604 | total time = 1001.38 ms / 535 tokens 1.25.493.148 I slot print_timing: id 0 | task 9604 | graphs reused = 9079 1.25.493.149 I slot print_timing: id 0 | task 9604 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.493.178 I slot release: id 0 | task 9604 | stop processing: n_tokens = 566, truncated = 0 1.25.510.708 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 85396565 1.25.554.006 I slot launch_slot_: id 0 | task 9746 | processing task, is_child = 0 1.26.705.529 I slot print_timing: id 0 | task 9746 | prompt eval time = 118.59 ms / 458 tokens ( 0.26 ms per token, 3862.01 tokens per second) 1.26.705.535 I slot print_timing: id 0 | task 9746 | eval time = 1032.91 ms / 161 tokens ( 6.46 ms per token, 154.90 tokens per second) 1.26.705.536 I slot print_timing: id 0 | task 9746 | total time = 1151.50 ms / 619 tokens 1.26.705.537 I slot print_timing: id 0 | task 9746 | graphs reused = 9237 1.26.705.538 I slot print_timing: id 0 | task 9746 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.705.572 I slot release: id 0 | task 9746 | stop processing: n_tokens = 650, truncated = 0 1.26.722.929 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 86608959 1.26.722.986 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.863 MiB) 1.26.793.132 I slot launch_slot_: id 0 | task 9910 | processing task, is_child = 0 1.28.075.209 I slot print_timing: id 0 | task 9910 | prompt eval time = 121.97 ms / 458 tokens ( 0.27 ms per token, 3755.14 tokens per second) 1.28.075.215 I slot print_timing: id 0 | task 9910 | eval time = 1160.09 ms / 176 tokens ( 6.63 ms per token, 150.85 tokens per second) 1.28.075.216 I slot print_timing: id 0 | task 9910 | total time = 1282.06 ms / 634 tokens 1.28.075.217 I slot print_timing: id 0 | task 9910 | graphs reused = 9410 1.28.075.217 I slot print_timing: id 0 | task 9910 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.075.249 I slot release: id 0 | task 9910 | stop processing: n_tokens = 665, truncated = 0 1.28.094.934 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 87978635 1.28.094.988 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 1.28.165.965 I slot launch_slot_: id 0 | task 10089 | processing task, is_child = 0 1.29.663.233 I slot print_timing: id 0 | task 10089 | prompt eval time = 117.67 ms / 452 tokens ( 0.26 ms per token, 3841.28 tokens per second) 1.29.663.239 I slot print_timing: id 0 | task 10089 | eval time = 1379.58 ms / 210 tokens ( 6.60 ms per token, 151.50 tokens per second) 1.29.663.240 I slot print_timing: id 0 | task 10089 | total time = 1497.25 ms / 662 tokens 1.29.663.241 I slot print_timing: id 0 | task 10089 | graphs reused = 9617 1.29.663.242 I slot print_timing: id 0 | task 10089 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.663.276 I slot release: id 0 | task 10089 | stop processing: n_tokens = 693, truncated = 0 1.29.690.965 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 89566663 1.29.691.025 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 1.29.766.812 I slot launch_slot_: id 0 | task 10302 | processing task, is_child = 0 1.30.626.317 I slot print_timing: id 0 | task 10302 | prompt eval time = 115.81 ms / 404 tokens ( 0.29 ms per token, 3488.56 tokens per second) 1.30.626.323 I slot print_timing: id 0 | task 10302 | eval time = 743.68 ms / 114 tokens ( 6.58 ms per token, 151.95 tokens per second) 1.30.626.324 I slot print_timing: id 0 | task 10302 | total time = 859.49 ms / 518 tokens 1.30.626.324 I slot print_timing: id 0 | task 10302 | graphs reused = 9728 1.30.626.325 I slot print_timing: id 0 | task 10302 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.626.353 I slot release: id 0 | task 10302 | stop processing: n_tokens = 549, truncated = 0 1.30.639.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 90529740 1.30.639.909 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 1.30.706.067 I slot launch_slot_: id 0 | task 10419 | processing task, is_child = 0 1.31.496.100 I slot print_timing: id 0 | task 10419 | prompt eval time = 108.99 ms / 345 tokens ( 0.32 ms per token, 3165.37 tokens per second) 1.31.496.105 I slot print_timing: id 0 | task 10419 | eval time = 681.02 ms / 106 tokens ( 6.49 ms per token, 154.18 tokens per second) 1.31.496.106 I slot print_timing: id 0 | task 10419 | total time = 790.01 ms / 451 tokens 1.31.496.107 I slot print_timing: id 0 | task 10419 | graphs reused = 9832 1.31.496.108 I slot print_timing: id 0 | task 10419 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.496.136 I slot release: id 0 | task 10419 | stop processing: n_tokens = 482, truncated = 0 1.31.517.310 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 91399523 1.31.517.352 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 1.31.584.520 I slot launch_slot_: id 0 | task 10528 | processing task, is_child = 0 1.32.401.770 I slot print_timing: id 0 | task 10528 | prompt eval time = 123.22 ms / 430 tokens ( 0.29 ms per token, 3489.58 tokens per second) 1.32.401.776 I slot print_timing: id 0 | task 10528 | eval time = 694.01 ms / 105 tokens ( 6.67 ms per token, 149.85 tokens per second) 1.32.401.777 I slot print_timing: id 0 | task 10528 | total time = 817.23 ms / 535 tokens 1.32.401.777 I slot print_timing: id 0 | task 10528 | graphs reused = 9934 1.32.401.778 I slot print_timing: id 0 | task 10528 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.401.811 I slot release: id 0 | task 10528 | stop processing: n_tokens = 566, truncated = 0 1.32.420.505 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 92305197 1.32.420.554 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 1.32.487.268 I slot launch_slot_: id 0 | task 10636 | processing task, is_child = 0 1.33.176.288 I slot print_timing: id 0 | task 10636 | prompt eval time = 107.34 ms / 316 tokens ( 0.34 ms per token, 2944.03 tokens per second) 1.33.176.294 I slot print_timing: id 0 | task 10636 | eval time = 581.66 ms / 85 tokens ( 6.92 ms per token, 144.41 tokens per second) 1.33.176.295 I slot print_timing: id 0 | task 10636 | total time = 689.00 ms / 401 tokens 1.33.176.296 I slot print_timing: id 0 | task 10636 | graphs reused = 10017 1.33.176.297 I slot print_timing: id 0 | task 10636 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.176.323 I slot release: id 0 | task 10636 | stop processing: n_tokens = 432, truncated = 0 1.33.201.136 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 93079709 1.33.201.179 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 1.33.273.818 I slot launch_slot_: id 0 | task 10724 | processing task, is_child = 0 1.34.080.789 I slot print_timing: id 0 | task 10724 | prompt eval time = 110.96 ms / 354 tokens ( 0.31 ms per token, 3190.25 tokens per second) 1.34.080.795 I slot print_timing: id 0 | task 10724 | eval time = 695.99 ms / 107 tokens ( 6.57 ms per token, 152.30 tokens per second) 1.34.080.796 I slot print_timing: id 0 | task 10724 | total time = 806.95 ms / 461 tokens 1.34.080.797 I slot print_timing: id 0 | task 10724 | graphs reused = 10122 1.34.080.798 I slot print_timing: id 0 | task 10724 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.080.827 I slot release: id 0 | task 10724 | stop processing: n_tokens = 492, truncated = 0 1.34.108.907 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 93984214 1.34.108.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 1.34.178.842 I slot launch_slot_: id 0 | task 10834 | processing task, is_child = 0 1.34.930.370 I slot print_timing: id 0 | task 10834 | prompt eval time = 120.80 ms / 438 tokens ( 0.28 ms per token, 3625.77 tokens per second) 1.34.930.377 I slot print_timing: id 0 | task 10834 | eval time = 630.71 ms / 98 tokens ( 6.50 ms per token, 153.80 tokens per second) 1.34.930.378 I slot print_timing: id 0 | task 10834 | total time = 751.51 ms / 536 tokens 1.34.930.379 I slot print_timing: id 0 | task 10834 | graphs reused = 10217 1.34.930.380 I slot print_timing: id 0 | task 10834 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.930.413 I slot release: id 0 | task 10834 | stop processing: n_tokens = 567, truncated = 0 1.34.947.057 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 94833799 1.34.947.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 1.35.013.564 I slot launch_slot_: id 0 | task 10935 | processing task, is_child = 0 1.35.591.110 I slot print_timing: id 0 | task 10935 | prompt eval time = 121.33 ms / 457 tokens ( 0.27 ms per token, 3766.71 tokens per second) 1.35.591.116 I slot print_timing: id 0 | task 10935 | eval time = 456.20 ms / 70 tokens ( 6.61 ms per token, 151.25 tokens per second) 1.35.591.118 I slot print_timing: id 0 | task 10935 | total time = 577.53 ms / 527 tokens 1.35.591.118 I slot print_timing: id 0 | task 10935 | graphs reused = 10284 1.35.591.119 I slot print_timing: id 0 | task 10935 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.591.151 I slot release: id 0 | task 10935 | stop processing: n_tokens = 558, truncated = 0 1.35.619.764 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 95494537 1.35.619.819 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 1.35.688.753 I slot launch_slot_: id 0 | task 11008 | processing task, is_child = 0 1.36.459.856 I slot print_timing: id 0 | task 11008 | prompt eval time = 126.58 ms / 473 tokens ( 0.27 ms per token, 3736.68 tokens per second) 1.36.459.863 I slot print_timing: id 0 | task 11008 | eval time = 644.50 ms / 98 tokens ( 6.64 ms per token, 150.50 tokens per second) 1.36.459.864 I slot print_timing: id 0 | task 11008 | total time = 771.08 ms / 571 tokens 1.36.459.864 I slot print_timing: id 0 | task 11008 | graphs reused = 10379 1.36.459.865 I slot print_timing: id 0 | task 11008 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.459.897 I slot release: id 0 | task 11008 | stop processing: n_tokens = 602, truncated = 0 1.36.478.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 96363284 1.36.478.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.865 MiB) 1.36.546.734 I slot launch_slot_: id 0 | task 11109 | processing task, is_child = 0 1.36.852.955 I slot print_timing: id 0 | task 11109 | prompt eval time = 126.97 ms / 476 tokens ( 0.27 ms per token, 3748.98 tokens per second) 1.36.852.961 I slot print_timing: id 0 | task 11109 | eval time = 179.23 ms / 27 tokens ( 6.89 ms per token, 145.06 tokens per second) 1.36.852.963 I slot print_timing: id 0 | task 11109 | total time = 306.20 ms / 503 tokens 1.36.852.963 I slot print_timing: id 0 | task 11109 | graphs reused = 10403 1.36.852.964 I slot print_timing: id 0 | task 11109 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.853.002 I slot release: id 0 | task 11109 | stop processing: n_tokens = 534, truncated = 0 1.36.880.497 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 96756388 1.36.880.550 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.36.952.243 I slot launch_slot_: id 0 | task 11139 | processing task, is_child = 0 1.37.774.898 I slot print_timing: id 0 | task 11139 | prompt eval time = 122.39 ms / 466 tokens ( 0.26 ms per token, 3807.38 tokens per second) 1.37.774.904 I slot print_timing: id 0 | task 11139 | eval time = 700.24 ms / 107 tokens ( 6.61 ms per token, 151.38 tokens per second) 1.37.774.905 I slot print_timing: id 0 | task 11139 | total time = 822.64 ms / 573 tokens 1.37.774.906 I slot print_timing: id 0 | task 11139 | graphs reused = 10507 1.37.774.906 I slot print_timing: id 0 | task 11139 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.774.941 I slot release: id 0 | task 11139 | stop processing: n_tokens = 604, truncated = 0 1.37.803.433 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 97678328 1.37.803.485 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 1.37.876.125 I slot launch_slot_: id 0 | task 11249 | processing task, is_child = 0 1.38.503.033 I slot print_timing: id 0 | task 11249 | prompt eval time = 115.97 ms / 415 tokens ( 0.28 ms per token, 3578.60 tokens per second) 1.38.503.039 I slot print_timing: id 0 | task 11249 | eval time = 510.92 ms / 78 tokens ( 6.64 ms per token, 150.71 tokens per second) 1.38.503.040 I slot print_timing: id 0 | task 11249 | total time = 626.89 ms / 493 tokens 1.38.503.041 I slot print_timing: id 0 | task 11249 | graphs reused = 10582 1.38.503.041 I slot print_timing: id 0 | task 11249 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.503.070 I slot release: id 0 | task 11249 | stop processing: n_tokens = 524, truncated = 0 1.38.518.830 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 98406457 1.38.518.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 1.38.585.499 I slot launch_slot_: id 0 | task 11330 | processing task, is_child = 0 1.39.103.950 I slot print_timing: id 0 | task 11330 | prompt eval time = 108.21 ms / 352 tokens ( 0.31 ms per token, 3252.96 tokens per second) 1.39.103.956 I slot print_timing: id 0 | task 11330 | eval time = 410.22 ms / 64 tokens ( 6.51 ms per token, 153.58 tokens per second) 1.39.103.956 I slot print_timing: id 0 | task 11330 | total time = 518.43 ms / 416 tokens 1.39.103.957 I slot print_timing: id 0 | task 11330 | graphs reused = 10644 1.39.103.958 I slot print_timing: id 0 | task 11330 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.103.985 I slot release: id 0 | task 11330 | stop processing: n_tokens = 447, truncated = 0 1.39.126.797 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 99007371 1.39.126.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.39.193.400 I slot launch_slot_: id 0 | task 11397 | processing task, is_child = 0 1.40.194.155 I slot print_timing: id 0 | task 11397 | prompt eval time = 132.25 ms / 550 tokens ( 0.24 ms per token, 4158.92 tokens per second) 1.40.194.161 I slot print_timing: id 0 | task 11397 | eval time = 868.49 ms / 133 tokens ( 6.58 ms per token, 151.99 tokens per second) 1.40.194.162 I slot print_timing: id 0 | task 11397 | total time = 1000.74 ms / 683 tokens 1.40.194.163 I slot print_timing: id 0 | task 11397 | graphs reused = 10775 1.40.194.163 I slot print_timing: id 0 | task 11397 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.194.200 I slot release: id 0 | task 11397 | stop processing: n_tokens = 714, truncated = 0 1.40.215.628 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 100097586 1.40.215.690 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 1.40.300.437 I slot launch_slot_: id 0 | task 11534 | processing task, is_child = 0 1.41.942.222 I slot print_timing: id 0 | task 11534 | prompt eval time = 161.87 ms / 772 tokens ( 0.21 ms per token, 4769.17 tokens per second) 1.41.942.228 I slot print_timing: id 0 | task 11534 | eval time = 1479.89 ms / 226 tokens ( 6.58 ms per token, 152.04 tokens per second) 1.41.942.229 I slot print_timing: id 0 | task 11534 | total time = 1641.76 ms / 998 tokens 1.41.942.230 I slot print_timing: id 0 | task 11534 | graphs reused = 10998 1.41.942.231 I slot print_timing: id 0 | task 11534 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.942.271 I slot release: id 0 | task 11534 | stop processing: n_tokens = 1029, truncated = 0 1.41.964.302 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 101845657 1.41.964.377 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 1.42.040.923 I slot launch_slot_: id 0 | task 11764 | processing task, is_child = 0 1.43.367.476 I slot print_timing: id 0 | task 11764 | prompt eval time = 154.44 ms / 683 tokens ( 0.23 ms per token, 4422.40 tokens per second) 1.43.367.482 I slot print_timing: id 0 | task 11764 | eval time = 1172.09 ms / 181 tokens ( 6.51 ms per token, 153.57 tokens per second) 1.43.367.483 I slot print_timing: id 0 | task 11764 | total time = 1326.53 ms / 864 tokens 1.43.367.484 I slot print_timing: id 0 | task 11764 | graphs reused = 11176 1.43.367.485 I slot print_timing: id 0 | task 11764 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.367.522 I slot release: id 0 | task 11764 | stop processing: n_tokens = 895, truncated = 0 1.43.392.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 103270908 1.43.392.075 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 1.43.469.680 I slot launch_slot_: id 0 | task 11949 | processing task, is_child = 0 1.45.043.645 I slot print_timing: id 0 | task 11949 | prompt eval time = 140.53 ms / 579 tokens ( 0.24 ms per token, 4120.18 tokens per second) 1.45.043.651 I slot print_timing: id 0 | task 11949 | eval time = 1433.42 ms / 218 tokens ( 6.61 ms per token, 151.39 tokens per second) 1.45.043.653 I slot print_timing: id 0 | task 11949 | total time = 1573.94 ms / 797 tokens 1.45.043.654 I slot print_timing: id 0 | task 11949 | graphs reused = 11391 1.45.043.655 I slot print_timing: id 0 | task 11949 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.043.694 I slot release: id 0 | task 11949 | stop processing: n_tokens = 828, truncated = 0 1.45.061.259 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 104947080 1.45.061.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 1.45.081.048 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 1.45.156.186 I slot launch_slot_: id 0 | task 12171 | processing task, is_child = 0 1.45.975.195 I slot print_timing: id 0 | task 12171 | prompt eval time = 129.89 ms / 500 tokens ( 0.26 ms per token, 3849.47 tokens per second) 1.45.975.200 I slot print_timing: id 0 | task 12171 | eval time = 689.10 ms / 106 tokens ( 6.56 ms per token, 152.37 tokens per second) 1.45.975.201 I slot print_timing: id 0 | task 12171 | total time = 818.99 ms / 606 tokens 1.45.975.203 I slot print_timing: id 0 | task 12171 | graphs reused = 11495 1.45.975.203 I slot print_timing: id 0 | task 12171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.975.236 I slot release: id 0 | task 12171 | stop processing: n_tokens = 637, truncated = 0 1.45.993.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 105878623 1.45.993.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 1.46.074.814 I slot launch_slot_: id 0 | task 12280 | processing task, is_child = 0 1.46.967.906 I slot print_timing: id 0 | task 12280 | prompt eval time = 163.10 ms / 776 tokens ( 0.21 ms per token, 4757.85 tokens per second) 1.46.967.912 I slot print_timing: id 0 | task 12280 | eval time = 729.97 ms / 114 tokens ( 6.46 ms per token, 154.80 tokens per second) 1.46.967.913 I slot print_timing: id 0 | task 12280 | total time = 893.07 ms / 890 tokens 1.46.967.914 I slot print_timing: id 0 | task 12280 | graphs reused = 11607 1.46.967.914 I slot print_timing: id 0 | task 12280 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.967.954 I slot release: id 0 | task 12280 | stop processing: n_tokens = 921, truncated = 0 1.46.987.822 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 921, t_last = 106871341 1.46.987.881 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 1.47.065.770 I slot launch_slot_: id 0 | task 12398 | processing task, is_child = 0 1.48.478.730 I slot print_timing: id 0 | task 12398 | prompt eval time = 127.83 ms / 504 tokens ( 0.25 ms per token, 3942.83 tokens per second) 1.48.478.737 I slot print_timing: id 0 | task 12398 | eval time = 1285.11 ms / 197 tokens ( 6.56 ms per token, 152.52 tokens per second) 1.48.478.737 I slot print_timing: id 0 | task 12398 | total time = 1412.94 ms / 701 tokens 1.48.478.738 I slot print_timing: id 0 | task 12398 | graphs reused = 11802 1.48.478.739 I slot print_timing: id 0 | task 12398 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.478.771 I slot release: id 0 | task 12398 | stop processing: n_tokens = 732, truncated = 0 1.48.507.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 108382157 1.48.507.383 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 1.48.578.657 I slot launch_slot_: id 0 | task 12598 | processing task, is_child = 0 1.50.079.742 I slot print_timing: id 0 | task 12598 | prompt eval time = 144.25 ms / 633 tokens ( 0.23 ms per token, 4388.09 tokens per second) 1.50.079.748 I slot print_timing: id 0 | task 12598 | eval time = 1356.81 ms / 207 tokens ( 6.59 ms per token, 151.83 tokens per second) 1.50.079.749 I slot print_timing: id 0 | task 12598 | total time = 1501.06 ms / 840 tokens 1.50.079.750 I slot print_timing: id 0 | task 12598 | graphs reused = 12006 1.50.079.751 I slot print_timing: id 0 | task 12598 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.079.788 I slot release: id 0 | task 12598 | stop processing: n_tokens = 871, truncated = 0 1.50.099.689 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 109983175 1.50.099.755 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.052 MiB) 1.50.174.917 I slot launch_slot_: id 0 | task 12809 | processing task, is_child = 0 1.51.156.836 I slot print_timing: id 0 | task 12809 | prompt eval time = 118.70 ms / 395 tokens ( 0.30 ms per token, 3327.83 tokens per second) 1.51.156.841 I slot print_timing: id 0 | task 12809 | eval time = 863.20 ms / 134 tokens ( 6.49 ms per token, 154.08 tokens per second) 1.51.156.842 I slot print_timing: id 0 | task 12809 | total time = 981.90 ms / 529 tokens 1.51.156.843 I slot print_timing: id 0 | task 12809 | graphs reused = 12137 1.51.156.844 I slot print_timing: id 0 | task 12809 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.156.875 I slot release: id 0 | task 12809 | stop processing: n_tokens = 560, truncated = 0 1.51.171.224 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 111060261 1.51.171.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 1.51.238.650 I slot launch_slot_: id 0 | task 12946 | processing task, is_child = 0 1.52.753.357 I slot print_timing: id 0 | task 12946 | prompt eval time = 136.33 ms / 584 tokens ( 0.23 ms per token, 4283.69 tokens per second) 1.52.753.363 I slot print_timing: id 0 | task 12946 | eval time = 1378.36 ms / 209 tokens ( 6.63 ms per token, 150.90 tokens per second) 1.52.753.364 I slot print_timing: id 0 | task 12946 | total time = 1514.69 ms / 793 tokens 1.52.753.365 I slot print_timing: id 0 | task 12946 | graphs reused = 12343 1.52.753.365 I slot print_timing: id 0 | task 12946 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.753.403 I slot release: id 0 | task 12946 | stop processing: n_tokens = 824, truncated = 0 1.52.781.164 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 112656789 1.52.781.231 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 1.52.861.049 I slot launch_slot_: id 0 | task 13159 | processing task, is_child = 0 1.54.519.999 I slot print_timing: id 0 | task 13159 | prompt eval time = 154.42 ms / 695 tokens ( 0.22 ms per token, 4500.62 tokens per second) 1.54.520.005 I slot print_timing: id 0 | task 13159 | eval time = 1504.51 ms / 230 tokens ( 6.57 ms per token, 152.21 tokens per second) 1.54.520.006 I slot print_timing: id 0 | task 13159 | total time = 1658.93 ms / 925 tokens 1.54.520.007 I slot print_timing: id 0 | task 13159 | graphs reused = 12570 1.54.520.007 I slot print_timing: id 0 | task 13159 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.520.044 I slot release: id 0 | task 13159 | stop processing: n_tokens = 956, truncated = 0 1.54.547.981 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 114423431 1.54.548.039 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.300 MiB) 1.54.623.171 I slot launch_slot_: id 0 | task 13393 | processing task, is_child = 0 1.56.022.290 I slot print_timing: id 0 | task 13393 | prompt eval time = 158.03 ms / 769 tokens ( 0.21 ms per token, 4866.01 tokens per second) 1.56.022.296 I slot print_timing: id 0 | task 13393 | eval time = 1241.07 ms / 191 tokens ( 6.53 ms per token, 153.09 tokens per second) 1.56.022.297 I slot print_timing: id 0 | task 13393 | total time = 1399.10 ms / 960 tokens 1.56.022.298 I slot print_timing: id 0 | task 13393 | graphs reused = 12759 1.56.022.299 I slot print_timing: id 0 | task 13393 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.022.340 I slot release: id 0 | task 13393 | stop processing: n_tokens = 991, truncated = 0 1.56.048.683 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 115925726 1.56.048.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 1.56.068.719 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.56.144.200 I slot launch_slot_: id 0 | task 13588 | processing task, is_child = 0 1.57.133.595 I slot print_timing: id 0 | task 13588 | prompt eval time = 139.93 ms / 576 tokens ( 0.24 ms per token, 4116.23 tokens per second) 1.57.133.601 I slot print_timing: id 0 | task 13588 | eval time = 849.44 ms / 124 tokens ( 6.91 ms per token, 144.80 tokens per second) 1.57.133.602 I slot print_timing: id 0 | task 13588 | total time = 989.37 ms / 700 tokens 1.57.133.603 I slot print_timing: id 0 | task 13588 | graphs reused = 12881 1.57.133.604 I slot print_timing: id 0 | task 13588 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.133.642 I slot release: id 0 | task 13588 | stop processing: n_tokens = 731, truncated = 0 1.57.159.144 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 117037028 1.57.159.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 1.57.237.130 I slot launch_slot_: id 0 | task 13716 | processing task, is_child = 0 1.59.191.724 I slot print_timing: id 0 | task 13716 | prompt eval time = 150.53 ms / 655 tokens ( 0.23 ms per token, 4351.29 tokens per second) 1.59.191.730 I slot print_timing: id 0 | task 13716 | eval time = 1804.04 ms / 275 tokens ( 6.58 ms per token, 151.88 tokens per second) 1.59.191.731 I slot print_timing: id 0 | task 13716 | total time = 1954.57 ms / 930 tokens 1.59.191.731 I slot print_timing: id 0 | task 13716 | graphs reused = 13153 1.59.191.732 I slot print_timing: id 0 | task 13716 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.191.769 I slot release: id 0 | task 13716 | stop processing: n_tokens = 961, truncated = 0 1.59.221.056 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 119095155 1.59.221.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 1.59.298.107 I slot launch_slot_: id 0 | task 13995 | processing task, is_child = 0 2.00.242.252 I slot print_timing: id 0 | task 13995 | prompt eval time = 143.17 ms / 621 tokens ( 0.23 ms per token, 4337.62 tokens per second) 2.00.242.259 I slot print_timing: id 0 | task 13995 | eval time = 800.96 ms / 121 tokens ( 6.67 ms per token, 149.82 tokens per second) 2.00.242.260 I slot print_timing: id 0 | task 13995 | total time = 944.12 ms / 742 tokens 2.00.242.261 I slot print_timing: id 0 | task 13995 | graphs reused = 13271 2.00.242.262 I slot print_timing: id 0 | task 13995 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.242.299 I slot release: id 0 | task 13995 | stop processing: n_tokens = 773, truncated = 0 2.00.265.918 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 120145685 2.00.265.971 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 2.00.340.663 I slot launch_slot_: id 0 | task 14120 | processing task, is_child = 0 2.01.733.834 I slot print_timing: id 0 | task 14120 | prompt eval time = 157.06 ms / 767 tokens ( 0.20 ms per token, 4883.64 tokens per second) 2.01.733.839 I slot print_timing: id 0 | task 14120 | eval time = 1236.10 ms / 184 tokens ( 6.75 ms per token, 148.05 tokens per second) 2.01.733.840 I slot print_timing: id 0 | task 14120 | total time = 1393.15 ms / 951 tokens 2.01.733.841 I slot print_timing: id 0 | task 14120 | graphs reused = 13453 2.01.733.842 I slot print_timing: id 0 | task 14120 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.733.886 I slot release: id 0 | task 14120 | stop processing: n_tokens = 982, truncated = 0 2.01.757.262 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 982, t_last = 121637273 2.01.757.323 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 2.01.834.650 I slot launch_slot_: id 0 | task 14308 | processing task, is_child = 0 2.03.360.348 I slot print_timing: id 0 | task 14308 | prompt eval time = 175.44 ms / 864 tokens ( 0.20 ms per token, 4924.84 tokens per second) 2.03.360.353 I slot print_timing: id 0 | task 14308 | eval time = 1350.24 ms / 203 tokens ( 6.68 ms per token, 149.60 tokens per second) 2.03.360.354 I slot print_timing: id 0 | task 14308 | total time = 1525.68 ms / 1067 tokens 2.03.360.355 I slot print_timing: id 0 | task 14308 | graphs reused = 13653 2.03.360.356 I slot print_timing: id 0 | task 14308 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.360.403 I slot release: id 0 | task 14308 | stop processing: n_tokens = 1098, truncated = 0 2.03.387.855 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 123263790 2.03.387.931 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 2.03.407.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.03.485.006 I slot launch_slot_: id 0 | task 14515 | processing task, is_child = 0 2.04.486.855 I slot print_timing: id 0 | task 14515 | prompt eval time = 150.94 ms / 646 tokens ( 0.23 ms per token, 4279.96 tokens per second) 2.04.486.861 I slot print_timing: id 0 | task 14515 | eval time = 850.89 ms / 129 tokens ( 6.65 ms per token, 150.43 tokens per second) 2.04.486.862 I slot print_timing: id 0 | task 14515 | total time = 1001.83 ms / 775 tokens 2.04.486.863 I slot print_timing: id 0 | task 14515 | graphs reused = 13779 2.04.486.864 I slot print_timing: id 0 | task 14515 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.486.904 I slot release: id 0 | task 14515 | stop processing: n_tokens = 806, truncated = 0 2.04.509.866 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 124390291 2.04.509.932 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.04.588.964 I slot launch_slot_: id 0 | task 14648 | processing task, is_child = 0 2.06.237.404 I slot print_timing: id 0 | task 14648 | prompt eval time = 156.53 ms / 720 tokens ( 0.22 ms per token, 4599.82 tokens per second) 2.06.237.410 I slot print_timing: id 0 | task 14648 | eval time = 1491.89 ms / 219 tokens ( 6.84 ms per token, 146.12 tokens per second) 2.06.237.411 I slot print_timing: id 0 | task 14648 | total time = 1648.42 ms / 939 tokens 2.06.237.412 I slot print_timing: id 0 | task 14648 | graphs reused = 13995 2.06.237.413 I slot print_timing: id 0 | task 14648 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.237.453 I slot release: id 0 | task 14648 | stop processing: n_tokens = 970, truncated = 0 2.06.259.500 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 126140839 2.06.259.572 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.203 MiB) 2.06.334.607 I slot launch_slot_: id 0 | task 14871 | processing task, is_child = 0 2.07.849.607 I slot print_timing: id 0 | task 14871 | prompt eval time = 130.07 ms / 509 tokens ( 0.26 ms per token, 3913.19 tokens per second) 2.07.849.613 I slot print_timing: id 0 | task 14871 | eval time = 1384.91 ms / 214 tokens ( 6.50 ms per token, 153.80 tokens per second) 2.07.849.614 I slot print_timing: id 0 | task 14871 | total time = 1514.98 ms / 723 tokens 2.07.849.615 I slot print_timing: id 0 | task 14871 | graphs reused = 14207 2.07.849.615 I slot print_timing: id 0 | task 14871 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.849.649 I slot release: id 0 | task 14871 | stop processing: n_tokens = 754, truncated = 0 2.07.864.464 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 127753036 2.07.864.522 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 2.07.932.530 I slot launch_slot_: id 0 | task 15088 | processing task, is_child = 0 2.08.810.928 I slot print_timing: id 0 | task 15088 | prompt eval time = 137.35 ms / 581 tokens ( 0.24 ms per token, 4230.13 tokens per second) 2.08.810.933 I slot print_timing: id 0 | task 15088 | eval time = 741.03 ms / 113 tokens ( 6.62 ms per token, 151.14 tokens per second) 2.08.810.935 I slot print_timing: id 0 | task 15088 | total time = 878.38 ms / 694 tokens 2.08.810.936 I slot print_timing: id 0 | task 15088 | graphs reused = 14318 2.08.810.936 I slot print_timing: id 0 | task 15088 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.810.975 I slot release: id 0 | task 15088 | stop processing: n_tokens = 725, truncated = 0 2.08.833.016 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 725, t_last = 128714362 2.08.833.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 2.08.918.229 I slot launch_slot_: id 0 | task 15205 | processing task, is_child = 0 2.10.540.305 I slot print_timing: id 0 | task 15205 | prompt eval time = 179.68 ms / 925 tokens ( 0.19 ms per token, 5148.04 tokens per second) 2.10.540.311 I slot print_timing: id 0 | task 15205 | eval time = 1442.38 ms / 220 tokens ( 6.59 ms per token, 151.83 tokens per second) 2.10.540.312 I slot print_timing: id 0 | task 15205 | total time = 1622.06 ms / 1145 tokens 2.10.540.313 I slot print_timing: id 0 | task 15205 | graphs reused = 14535 2.10.540.313 I slot print_timing: id 0 | task 15205 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.540.362 I slot release: id 0 | task 15205 | stop processing: n_tokens = 1176, truncated = 0 2.10.545.780 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 130443748 2.10.545.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 2.10.622.613 I slot launch_slot_: id 0 | task 15429 | processing task, is_child = 0 2.12.435.215 I slot print_timing: id 0 | task 15429 | prompt eval time = 170.01 ms / 885 tokens ( 0.19 ms per token, 5205.64 tokens per second) 2.12.435.222 I slot print_timing: id 0 | task 15429 | eval time = 1642.57 ms / 245 tokens ( 6.73 ms per token, 148.55 tokens per second) 2.12.435.223 I slot print_timing: id 0 | task 15429 | total time = 1812.58 ms / 1130 tokens 2.12.435.223 I slot print_timing: id 0 | task 15429 | graphs reused = 14777 2.12.435.224 I slot print_timing: id 0 | task 15429 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.435.269 I slot release: id 0 | task 15429 | stop processing: n_tokens = 1161, truncated = 0 2.12.453.264 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 132338655 2.12.453.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 2.12.531.516 I slot launch_slot_: id 0 | task 15678 | processing task, is_child = 0 2.13.853.507 I slot print_timing: id 0 | task 15678 | prompt eval time = 119.12 ms / 392 tokens ( 0.30 ms per token, 3290.74 tokens per second) 2.13.853.512 I slot print_timing: id 0 | task 15678 | eval time = 1202.85 ms / 184 tokens ( 6.57 ms per token, 152.14 tokens per second) 2.13.853.513 I slot print_timing: id 0 | task 15678 | total time = 1321.97 ms / 576 tokens 2.13.853.514 I slot print_timing: id 0 | task 15678 | graphs reused = 14958 2.13.853.515 I slot print_timing: id 0 | task 15678 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.853.544 I slot release: id 0 | task 15678 | stop processing: n_tokens = 607, truncated = 0 2.13.870.838 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 607, t_last = 133756931 2.13.870.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 2.13.942.007 I slot launch_slot_: id 0 | task 15865 | processing task, is_child = 0 2.14.905.627 I slot print_timing: id 0 | task 15865 | prompt eval time = 112.63 ms / 331 tokens ( 0.34 ms per token, 2938.80 tokens per second) 2.14.905.633 I slot print_timing: id 0 | task 15865 | eval time = 850.97 ms / 132 tokens ( 6.50 ms per token, 153.94 tokens per second) 2.14.905.634 I slot print_timing: id 0 | task 15865 | total time = 963.60 ms / 463 tokens 2.14.905.634 I slot print_timing: id 0 | task 15865 | graphs reused = 15088 2.14.905.635 I slot print_timing: id 0 | task 15865 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.905.661 I slot release: id 0 | task 15865 | stop processing: n_tokens = 494, truncated = 0 2.14.932.101 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 134809048 2.14.932.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 2.15.003.078 I slot launch_slot_: id 0 | task 16000 | processing task, is_child = 0 2.15.499.888 I slot print_timing: id 0 | task 16000 | prompt eval time = 108.42 ms / 357 tokens ( 0.30 ms per token, 3292.84 tokens per second) 2.15.499.894 I slot print_timing: id 0 | task 16000 | eval time = 388.37 ms / 55 tokens ( 7.19 ms per token, 139.04 tokens per second) 2.15.499.896 I slot print_timing: id 0 | task 16000 | total time = 496.79 ms / 412 tokens 2.15.499.896 I slot print_timing: id 0 | task 16000 | graphs reused = 15141 2.15.499.897 I slot print_timing: id 0 | task 16000 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.499.924 I slot release: id 0 | task 16000 | stop processing: n_tokens = 443, truncated = 0 2.15.522.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 443, t_last = 135403311 2.15.523.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 2.15.592.963 I slot launch_slot_: id 0 | task 16058 | processing task, is_child = 0 2.16.357.652 I slot print_timing: id 0 | task 16058 | prompt eval time = 111.98 ms / 315 tokens ( 0.36 ms per token, 2812.95 tokens per second) 2.16.357.658 I slot print_timing: id 0 | task 16058 | eval time = 652.69 ms / 100 tokens ( 6.59 ms per token, 151.68 tokens per second) 2.16.357.659 I slot print_timing: id 0 | task 16058 | total time = 764.67 ms / 415 tokens 2.16.357.660 I slot print_timing: id 0 | task 16058 | graphs reused = 15239 2.16.357.661 I slot print_timing: id 0 | task 16058 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.357.688 I slot release: id 0 | task 16058 | stop processing: n_tokens = 446, truncated = 0 2.16.372.332 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 136261074 2.16.372.371 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 2.16.438.999 I slot launch_slot_: id 0 | task 16161 | processing task, is_child = 0 2.16.943.179 I slot print_timing: id 0 | task 16161 | prompt eval time = 111.15 ms / 378 tokens ( 0.29 ms per token, 3400.84 tokens per second) 2.16.943.185 I slot print_timing: id 0 | task 16161 | eval time = 393.01 ms / 60 tokens ( 6.66 ms per token, 150.12 tokens per second) 2.16.943.186 I slot print_timing: id 0 | task 16161 | total time = 504.16 ms / 438 tokens 2.16.943.187 I slot print_timing: id 0 | task 16161 | graphs reused = 15297 2.16.943.187 I slot print_timing: id 0 | task 16161 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.943.218 I slot release: id 0 | task 16161 | stop processing: n_tokens = 469, truncated = 0 2.16.969.636 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 136846605 2.16.969.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.557 MiB) 2.17.039.200 I slot launch_slot_: id 0 | task 16224 | processing task, is_child = 0 2.17.323.556 I slot print_timing: id 0 | task 16224 | prompt eval time = 105.80 ms / 295 tokens ( 0.36 ms per token, 2788.23 tokens per second) 2.17.323.562 I slot print_timing: id 0 | task 16224 | eval time = 178.53 ms / 28 tokens ( 6.61 ms per token, 151.23 tokens per second) 2.17.323.563 I slot print_timing: id 0 | task 16224 | total time = 284.34 ms / 323 tokens 2.17.323.564 I slot print_timing: id 0 | task 16224 | graphs reused = 15323 2.17.323.565 I slot print_timing: id 0 | task 16224 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.323.592 I slot release: id 0 | task 16224 | stop processing: n_tokens = 354, truncated = 0 2.17.342.518 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 137226978 2.17.342.556 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 2.17.408.809 I slot launch_slot_: id 0 | task 16255 | processing task, is_child = 0 2.18.904.647 I slot print_timing: id 0 | task 16255 | prompt eval time = 108.71 ms / 337 tokens ( 0.32 ms per token, 3099.91 tokens per second) 2.18.904.653 I slot print_timing: id 0 | task 16255 | eval time = 1387.11 ms / 214 tokens ( 6.51 ms per token, 153.56 tokens per second) 2.18.904.654 I slot print_timing: id 0 | task 16255 | total time = 1495.82 ms / 551 tokens 2.18.904.654 I slot print_timing: id 0 | task 16255 | graphs reused = 15534 2.18.904.655 I slot print_timing: id 0 | task 16255 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.904.685 I slot release: id 0 | task 16255 | stop processing: n_tokens = 582, truncated = 0 2.18.928.997 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 138808071 2.18.929.050 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 2.18.999.628 I slot launch_slot_: id 0 | task 16472 | processing task, is_child = 0 2.19.795.155 I slot print_timing: id 0 | task 16472 | prompt eval time = 107.14 ms / 325 tokens ( 0.33 ms per token, 3033.30 tokens per second) 2.19.795.161 I slot print_timing: id 0 | task 16472 | eval time = 688.37 ms / 106 tokens ( 6.56 ms per token, 152.54 tokens per second) 2.19.795.162 I slot print_timing: id 0 | task 16472 | total time = 795.51 ms / 431 tokens 2.19.795.163 I slot print_timing: id 0 | task 16472 | graphs reused = 15638 2.19.795.164 I slot print_timing: id 0 | task 16472 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.795.192 I slot release: id 0 | task 16472 | stop processing: n_tokens = 462, truncated = 0 2.19.820.871 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.069 2.19.878.983 I slot launch_slot_: id 0 | task 16581 | processing task, is_child = 0 2.21.016.678 I slot print_timing: id 0 | task 16581 | prompt eval time = 100.24 ms / 264 tokens ( 0.38 ms per token, 2633.57 tokens per second) 2.21.016.684 I slot print_timing: id 0 | task 16581 | eval time = 1037.43 ms / 159 tokens ( 6.57 ms per token, 152.30 tokens per second) 2.21.016.685 I slot print_timing: id 0 | task 16581 | total time = 1137.68 ms / 423 tokens 2.21.016.686 I slot print_timing: id 0 | task 16581 | graphs reused = 15795 2.21.016.686 I slot print_timing: id 0 | task 16581 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.016.714 I slot release: id 0 | task 16581 | stop processing: n_tokens = 454, truncated = 0 2.21.041.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 140920100 2.21.041.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 2.21.107.432 I slot launch_slot_: id 0 | task 16743 | processing task, is_child = 0 2.21.264.867 I slot print_timing: id 0 | task 16743 | prompt eval time = 106.99 ms / 331 tokens ( 0.32 ms per token, 3093.63 tokens per second) 2.21.264.873 I slot print_timing: id 0 | task 16743 | eval time = 50.42 ms / 8 tokens ( 7.20 ms per token, 138.83 tokens per second) 2.21.264.874 I slot print_timing: id 0 | task 16743 | total time = 157.42 ms / 339 tokens 2.21.264.875 I slot print_timing: id 0 | task 16743 | graphs reused = 15801 2.21.264.876 I slot print_timing: id 0 | task 16743 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.264.903 I slot release: id 0 | task 16743 | stop processing: n_tokens = 370, truncated = 0 2.21.289.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 370, t_last = 141168289 2.21.289.946 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 2.21.363.921 I slot launch_slot_: id 0 | task 16754 | processing task, is_child = 0 2.22.198.554 I slot print_timing: id 0 | task 16754 | prompt eval time = 107.74 ms / 333 tokens ( 0.32 ms per token, 3090.72 tokens per second) 2.22.198.559 I slot print_timing: id 0 | task 16754 | eval time = 726.87 ms / 112 tokens ( 6.55 ms per token, 152.71 tokens per second) 2.22.198.560 I slot print_timing: id 0 | task 16754 | total time = 834.61 ms / 445 tokens 2.22.198.561 I slot print_timing: id 0 | task 16754 | graphs reused = 15911 2.22.198.562 I slot print_timing: id 0 | task 16754 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.198.590 I slot release: id 0 | task 16754 | stop processing: n_tokens = 476, truncated = 0 2.22.222.038 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 142101977 2.22.222.086 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 2.22.292.283 I slot launch_slot_: id 0 | task 16869 | processing task, is_child = 0 2.25.404.394 I slot print_timing: id 0 | task 16869 | n_gen = 462, tg = 153.44 t/s, tg_3s = 153.77 t/s 2.28.407.727 I slot print_timing: id 0 | task 16869 | n_gen = 928, tg = 154.30 t/s, tg_3s = 155.16 t/s 2.28.806.616 I slot print_timing: id 0 | task 16869 | prompt eval time = 107.56 ms / 346 tokens ( 0.31 ms per token, 3216.66 tokens per second) 2.28.806.622 I slot print_timing: id 0 | task 16869 | eval time = 6406.75 ms / 990 tokens ( 6.48 ms per token, 154.37 tokens per second) 2.28.806.623 I slot print_timing: id 0 | task 16869 | total time = 6514.31 ms / 1336 tokens 2.28.806.624 I slot print_timing: id 0 | task 16869 | graphs reused = 16895 2.28.806.624 I slot print_timing: id 0 | task 16869 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.806.653 I slot release: id 0 | task 16869 | stop processing: n_tokens = 1367, truncated = 0 2.28.830.422 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1367, t_last = 148710040 2.28.830.493 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 2.28.905.398 I slot launch_slot_: id 0 | task 17862 | processing task, is_child = 0 2.29.265.452 I slot print_timing: id 0 | task 17862 | prompt eval time = 106.61 ms / 325 tokens ( 0.33 ms per token, 3048.49 tokens per second) 2.29.265.458 I slot print_timing: id 0 | task 17862 | eval time = 253.43 ms / 40 tokens ( 6.50 ms per token, 153.89 tokens per second) 2.29.265.459 I slot print_timing: id 0 | task 17862 | total time = 360.04 ms / 365 tokens 2.29.265.460 I slot print_timing: id 0 | task 17862 | graphs reused = 16933 2.29.265.461 I slot print_timing: id 0 | task 17862 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.265.490 I slot release: id 0 | task 17862 | stop processing: n_tokens = 396, truncated = 0 2.29.287.701 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 149168876 2.29.287.744 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 2.29.356.817 I slot launch_slot_: id 0 | task 17905 | processing task, is_child = 0 2.29.982.204 I slot print_timing: id 0 | task 17905 | prompt eval time = 107.29 ms / 322 tokens ( 0.33 ms per token, 3001.16 tokens per second) 2.29.982.210 I slot print_timing: id 0 | task 17905 | eval time = 518.08 ms / 81 tokens ( 6.48 ms per token, 154.42 tokens per second) 2.29.982.211 I slot print_timing: id 0 | task 17905 | total time = 625.37 ms / 403 tokens 2.29.982.212 I slot print_timing: id 0 | task 17905 | graphs reused = 17012 2.29.982.212 I slot print_timing: id 0 | task 17905 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.982.242 I slot release: id 0 | task 17905 | stop processing: n_tokens = 434, truncated = 0 2.30.005.688 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 149885629 2.30.005.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 2.30.076.200 I slot launch_slot_: id 0 | task 17989 | processing task, is_child = 0 2.31.252.136 I slot print_timing: id 0 | task 17989 | prompt eval time = 106.92 ms / 338 tokens ( 0.32 ms per token, 3161.39 tokens per second) 2.31.252.141 I slot print_timing: id 0 | task 17989 | eval time = 1069.00 ms / 167 tokens ( 6.44 ms per token, 155.29 tokens per second) 2.31.252.142 I slot print_timing: id 0 | task 17989 | total time = 1175.92 ms / 505 tokens 2.31.252.143 I slot print_timing: id 0 | task 17989 | graphs reused = 17176 2.31.252.143 I slot print_timing: id 0 | task 17989 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.252.172 I slot release: id 0 | task 17989 | stop processing: n_tokens = 536, truncated = 0 2.31.272.190 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 536, t_last = 151155559 2.31.315.138 I slot launch_slot_: id 0 | task 18159 | processing task, is_child = 0 2.34.423.839 I slot print_timing: id 0 | task 18159 | n_gen = 468, tg = 155.55 t/s, tg_3s = 155.88 t/s 2.37.427.392 I slot print_timing: id 0 | task 18159 | n_gen = 934, tg = 155.35 t/s, tg_3s = 155.15 t/s 2.38.006.456 I slot print_timing: id 0 | task 18159 | prompt eval time = 106.42 ms / 347 tokens ( 0.31 ms per token, 3260.73 tokens per second) 2.38.006.462 I slot print_timing: id 0 | task 18159 | eval time = 6584.88 ms / 1024 tokens ( 6.44 ms per token, 155.36 tokens per second) 2.38.006.463 I slot print_timing: id 0 | task 18159 | total time = 6691.30 ms / 1371 tokens 2.38.006.463 I slot print_timing: id 0 | task 18159 | graphs reused = 18194 2.38.006.465 I slot print_timing: id 0 | task 18159 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.006.494 I slot release: id 0 | task 18159 | stop processing: n_tokens = 1402, truncated = 0 2.38.020.254 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1402, t_last = 157909880 2.38.020.344 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 2.38.096.419 I slot launch_slot_: id 0 | task 19186 | processing task, is_child = 0 2.40.450.680 I slot print_timing: id 0 | task 19186 | prompt eval time = 106.27 ms / 331 tokens ( 0.32 ms per token, 3114.59 tokens per second) 2.40.450.686 I slot print_timing: id 0 | task 19186 | eval time = 2247.97 ms / 351 tokens ( 6.42 ms per token, 155.70 tokens per second) 2.40.450.687 I slot print_timing: id 0 | task 19186 | total time = 2354.24 ms / 682 tokens 2.40.450.688 I slot print_timing: id 0 | task 19186 | graphs reused = 18542 2.40.450.688 I slot print_timing: id 0 | task 19186 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.450.720 I slot release: id 0 | task 19186 | stop processing: n_tokens = 713, truncated = 0 2.40.468.965 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 713, t_last = 160354106 2.40.469.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.464 MiB) 2.40.540.670 I slot launch_slot_: id 0 | task 19540 | processing task, is_child = 0 2.41.674.636 I slot print_timing: id 0 | task 19540 | prompt eval time = 106.11 ms / 345 tokens ( 0.31 ms per token, 3251.37 tokens per second) 2.41.674.642 I slot print_timing: id 0 | task 19540 | eval time = 1027.84 ms / 160 tokens ( 6.46 ms per token, 154.69 tokens per second) 2.41.674.643 I slot print_timing: id 0 | task 19540 | total time = 1133.95 ms / 505 tokens 2.41.674.644 I slot print_timing: id 0 | task 19540 | graphs reused = 18699 2.41.674.645 I slot print_timing: id 0 | task 19540 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.674.671 I slot release: id 0 | task 19540 | stop processing: n_tokens = 536, truncated = 0 2.41.696.761 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 536, t_last = 161578058 2.41.696.805 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 2.41.769.744 I slot launch_slot_: id 0 | task 19703 | processing task, is_child = 0 2.42.388.153 I slot print_timing: id 0 | task 19703 | prompt eval time = 107.03 ms / 320 tokens ( 0.33 ms per token, 2989.96 tokens per second) 2.42.388.159 I slot print_timing: id 0 | task 19703 | eval time = 511.37 ms / 80 tokens ( 6.47 ms per token, 154.49 tokens per second) 2.42.388.160 I slot print_timing: id 0 | task 19703 | total time = 618.39 ms / 400 tokens 2.42.388.162 I slot print_timing: id 0 | task 19703 | graphs reused = 18777 2.42.388.163 I slot print_timing: id 0 | task 19703 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.388.191 I slot release: id 0 | task 19703 | stop processing: n_tokens = 431, truncated = 0 2.42.402.050 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 431, t_last = 162291577 2.42.402.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 2.42.471.911 I slot launch_slot_: id 0 | task 19786 | processing task, is_child = 0 2.42.904.257 I slot print_timing: id 0 | task 19786 | prompt eval time = 103.85 ms / 297 tokens ( 0.35 ms per token, 2859.84 tokens per second) 2.42.904.262 I slot print_timing: id 0 | task 19786 | eval time = 328.47 ms / 47 tokens ( 7.14 ms per token, 140.04 tokens per second) 2.42.904.263 I slot print_timing: id 0 | task 19786 | total time = 432.33 ms / 344 tokens 2.42.904.264 I slot print_timing: id 0 | task 19786 | graphs reused = 18822 2.42.904.265 I slot print_timing: id 0 | task 19786 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.904.293 I slot release: id 0 | task 19786 | stop processing: n_tokens = 375, truncated = 0 2.42.919.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 162807680 2.42.919.409 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.089 MiB) 2.42.996.922 I slot launch_slot_: id 0 | task 19836 | processing task, is_child = 0 2.44.263.826 I slot print_timing: id 0 | task 19836 | prompt eval time = 107.33 ms / 343 tokens ( 0.31 ms per token, 3195.75 tokens per second) 2.44.263.832 I slot print_timing: id 0 | task 19836 | eval time = 1159.56 ms / 181 tokens ( 6.44 ms per token, 155.23 tokens per second) 2.44.263.833 I slot print_timing: id 0 | task 19836 | total time = 1266.88 ms / 524 tokens 2.44.263.834 I slot print_timing: id 0 | task 19836 | graphs reused = 19000 2.44.263.834 I slot print_timing: id 0 | task 19836 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.263.864 I slot release: id 0 | task 19836 | stop processing: n_tokens = 555, truncated = 0 2.44.289.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 164167250 2.44.333.299 I slot launch_slot_: id 0 | task 20020 | processing task, is_child = 0 2.44.889.097 I slot print_timing: id 0 | task 20020 | prompt eval time = 110.81 ms / 371 tokens ( 0.30 ms per token, 3348.13 tokens per second) 2.44.889.103 I slot print_timing: id 0 | task 20020 | eval time = 444.97 ms / 70 tokens ( 6.45 ms per token, 155.07 tokens per second) 2.44.889.104 I slot print_timing: id 0 | task 20020 | total time = 555.78 ms / 441 tokens 2.44.889.105 I slot print_timing: id 0 | task 20020 | graphs reused = 19068 2.44.889.105 I slot print_timing: id 0 | task 20020 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.889.134 I slot release: id 0 | task 20020 | stop processing: n_tokens = 472, truncated = 0 2.44.908.922 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 472, t_last = 164792521 2.44.908.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 2.44.977.492 I slot launch_slot_: id 0 | task 20093 | processing task, is_child = 0 2.45.281.468 I slot print_timing: id 0 | task 20093 | prompt eval time = 101.71 ms / 292 tokens ( 0.35 ms per token, 2870.88 tokens per second) 2.45.281.473 I slot print_timing: id 0 | task 20093 | eval time = 202.25 ms / 32 tokens ( 6.52 ms per token, 153.28 tokens per second) 2.45.281.474 I slot print_timing: id 0 | task 20093 | total time = 303.96 ms / 324 tokens 2.45.281.476 I slot print_timing: id 0 | task 20093 | graphs reused = 19098 2.45.281.477 I slot print_timing: id 0 | task 20093 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.281.502 I slot release: id 0 | task 20093 | stop processing: n_tokens = 355, truncated = 0 2.45.298.389 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 165184889 2.45.298.430 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.427 MiB) 2.45.369.662 I slot launch_slot_: id 0 | task 20128 | processing task, is_child = 0 2.46.006.742 I slot print_timing: id 0 | task 20128 | prompt eval time = 103.19 ms / 301 tokens ( 0.34 ms per token, 2916.92 tokens per second) 2.46.006.748 I slot print_timing: id 0 | task 20128 | eval time = 533.87 ms / 84 tokens ( 6.43 ms per token, 155.47 tokens per second) 2.46.006.749 I slot print_timing: id 0 | task 20128 | total time = 637.06 ms / 385 tokens 2.46.006.750 I slot print_timing: id 0 | task 20128 | graphs reused = 19180 2.46.006.751 I slot print_timing: id 0 | task 20128 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.006.778 I slot release: id 0 | task 20128 | stop processing: n_tokens = 416, truncated = 0 2.46.024.366 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 165910164 2.46.024.417 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 2.46.095.050 I slot launch_slot_: id 0 | task 20215 | processing task, is_child = 0 2.47.305.204 I slot print_timing: id 0 | task 20215 | prompt eval time = 102.24 ms / 303 tokens ( 0.34 ms per token, 2963.64 tokens per second) 2.47.305.209 I slot print_timing: id 0 | task 20215 | eval time = 1107.89 ms / 174 tokens ( 6.40 ms per token, 156.15 tokens per second) 2.47.305.210 I slot print_timing: id 0 | task 20215 | total time = 1210.13 ms / 477 tokens 2.47.305.211 I slot print_timing: id 0 | task 20215 | graphs reused = 19352 2.47.305.212 I slot print_timing: id 0 | task 20215 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.305.237 I slot release: id 0 | task 20215 | stop processing: n_tokens = 508, truncated = 0 2.47.318.998 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 508, t_last = 167208623 2.47.319.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 2.47.396.751 I slot launch_slot_: id 0 | task 20392 | processing task, is_child = 0 2.47.737.538 I slot print_timing: id 0 | task 20392 | prompt eval time = 106.92 ms / 321 tokens ( 0.33 ms per token, 3002.13 tokens per second) 2.47.737.544 I slot print_timing: id 0 | task 20392 | eval time = 233.84 ms / 37 tokens ( 6.50 ms per token, 153.95 tokens per second) 2.47.737.545 I slot print_timing: id 0 | task 20392 | total time = 340.77 ms / 358 tokens 2.47.737.547 I slot print_timing: id 0 | task 20392 | graphs reused = 19387 2.47.737.547 I slot print_timing: id 0 | task 20392 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.737.575 I slot release: id 0 | task 20392 | stop processing: n_tokens = 389, truncated = 0 2.47.755.515 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 389, t_last = 167640962 2.47.755.555 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.486 MiB) 2.47.821.113 I slot launch_slot_: id 0 | task 20432 | processing task, is_child = 0 2.48.255.329 I slot print_timing: id 0 | task 20432 | prompt eval time = 109.72 ms / 322 tokens ( 0.34 ms per token, 2934.82 tokens per second) 2.48.255.335 I slot print_timing: id 0 | task 20432 | eval time = 324.48 ms / 51 tokens ( 6.49 ms per token, 154.09 tokens per second) 2.48.255.336 I slot print_timing: id 0 | task 20432 | total time = 434.20 ms / 373 tokens 2.48.255.337 I slot print_timing: id 0 | task 20432 | graphs reused = 19436 2.48.255.338 I slot print_timing: id 0 | task 20432 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.255.364 I slot release: id 0 | task 20432 | stop processing: n_tokens = 404, truncated = 0 2.48.268.820 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 168158751 2.48.268.861 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.952 MiB) 2.48.334.642 I slot launch_slot_: id 0 | task 20486 | processing task, is_child = 0 2.49.058.489 I slot print_timing: id 0 | task 20486 | prompt eval time = 106.69 ms / 323 tokens ( 0.33 ms per token, 3027.60 tokens per second) 2.49.058.495 I slot print_timing: id 0 | task 20486 | eval time = 617.14 ms / 97 tokens ( 6.43 ms per token, 155.56 tokens per second) 2.49.058.496 I slot print_timing: id 0 | task 20486 | total time = 723.83 ms / 420 tokens 2.49.058.497 I slot print_timing: id 0 | task 20486 | graphs reused = 19531 2.49.058.497 I slot print_timing: id 0 | task 20486 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.058.523 I slot release: id 0 | task 20486 | stop processing: n_tokens = 451, truncated = 0 2.49.074.222 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 451, t_last = 168961910 2.49.074.264 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.358 MiB) 2.49.136.943 I slot launch_slot_: id 0 | task 20586 | processing task, is_child = 0 2.52.245.663 I slot print_timing: id 0 | task 20586 | n_gen = 468, tg = 155.57 t/s, tg_3s = 155.91 t/s 2.53.138.380 I slot print_timing: id 0 | task 20586 | prompt eval time = 106.90 ms / 321 tokens ( 0.33 ms per token, 3002.81 tokens per second) 2.53.138.385 I slot print_timing: id 0 | task 20586 | eval time = 3894.52 ms / 607 tokens ( 6.43 ms per token, 155.60 tokens per second) 2.53.138.386 I slot print_timing: id 0 | task 20586 | total time = 4001.42 ms / 928 tokens 2.53.138.387 I slot print_timing: id 0 | task 20586 | graphs reused = 20134 2.53.138.388 I slot print_timing: id 0 | task 20586 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.138.413 I slot release: id 0 | task 20586 | stop processing: n_tokens = 959, truncated = 0 2.53.157.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 959, t_last = 173041800 2.53.157.194 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.451 MiB) 2.53.225.870 I slot launch_slot_: id 0 | task 21196 | processing task, is_child = 0 2.54.024.780 I slot print_timing: id 0 | task 21196 | prompt eval time = 105.21 ms / 322 tokens ( 0.33 ms per token, 3060.60 tokens per second) 2.54.024.786 I slot print_timing: id 0 | task 21196 | eval time = 693.68 ms / 109 tokens ( 6.42 ms per token, 155.69 tokens per second) 2.54.024.787 I slot print_timing: id 0 | task 21196 | total time = 798.89 ms / 431 tokens 2.54.024.788 I slot print_timing: id 0 | task 21196 | graphs reused = 20241 2.54.024.789 I slot print_timing: id 0 | task 21196 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.024.813 I slot release: id 0 | task 21196 | stop processing: n_tokens = 462, truncated = 0 2.54.047.082 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 462, t_last = 173928200 2.54.047.133 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.171 MiB) 2.54.112.625 I slot launch_slot_: id 0 | task 21308 | processing task, is_child = 0 2.54.511.494 I slot print_timing: id 0 | task 21308 | prompt eval time = 106.68 ms / 337 tokens ( 0.32 ms per token, 3158.89 tokens per second) 2.54.511.499 I slot print_timing: id 0 | task 21308 | eval time = 292.17 ms / 46 tokens ( 6.49 ms per token, 154.02 tokens per second) 2.54.511.500 I slot print_timing: id 0 | task 21308 | total time = 398.85 ms / 383 tokens 2.54.511.501 I slot print_timing: id 0 | task 21308 | graphs reused = 20285 2.54.511.502 I slot print_timing: id 0 | task 21308 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.511.530 I slot release: id 0 | task 21308 | stop processing: n_tokens = 414, truncated = 0 2.54.528.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 174414917 2.54.528.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 2.54.593.113 I slot launch_slot_: id 0 | task 21357 | processing task, is_child = 0 2.55.005.845 I slot print_timing: id 0 | task 21357 | prompt eval time = 108.67 ms / 325 tokens ( 0.33 ms per token, 2990.71 tokens per second) 2.55.005.852 I slot print_timing: id 0 | task 21357 | eval time = 304.04 ms / 47 tokens ( 6.61 ms per token, 151.30 tokens per second) 2.55.005.853 I slot print_timing: id 0 | task 21357 | total time = 412.71 ms / 372 tokens 2.55.005.854 I slot print_timing: id 0 | task 21357 | graphs reused = 20330 2.55.005.854 I slot print_timing: id 0 | task 21357 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.005.883 I slot release: id 0 | task 21357 | stop processing: n_tokens = 403, truncated = 0 2.55.023.904 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 174909270 2.55.023.946 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.704 MiB) 2.55.090.448 I slot launch_slot_: id 0 | task 21407 | processing task, is_child = 0 2.55.614.694 I slot print_timing: id 0 | task 21407 | prompt eval time = 108.96 ms / 331 tokens ( 0.33 ms per token, 3037.87 tokens per second) 2.55.614.700 I slot print_timing: id 0 | task 21407 | eval time = 415.27 ms / 64 tokens ( 6.59 ms per token, 151.71 tokens per second) 2.55.614.701 I slot print_timing: id 0 | task 21407 | total time = 524.23 ms / 395 tokens 2.55.614.702 I slot print_timing: id 0 | task 21407 | graphs reused = 20392 2.55.614.702 I slot print_timing: id 0 | task 21407 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.614.732 I slot release: id 0 | task 21407 | stop processing: n_tokens = 426, truncated = 0 2.55.629.621 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 175518118 2.55.629.670 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.952 MiB) 2.55.698.739 I slot launch_slot_: id 0 | task 21474 | processing task, is_child = 0 2.56.557.427 I slot print_timing: id 0 | task 21474 | prompt eval time = 108.14 ms / 336 tokens ( 0.32 ms per token, 3107.17 tokens per second) 2.56.557.432 I slot print_timing: id 0 | task 21474 | eval time = 750.53 ms / 115 tokens ( 6.58 ms per token, 151.89 tokens per second) 2.56.557.433 I slot print_timing: id 0 | task 21474 | total time = 858.66 ms / 451 tokens 2.56.557.435 I slot print_timing: id 0 | task 21474 | graphs reused = 20505 2.56.557.436 I slot print_timing: id 0 | task 21474 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.557.469 I slot release: id 0 | task 21474 | stop processing: n_tokens = 482, truncated = 0 2.56.581.340 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 176460855 2.56.581.389 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.702 MiB) 2.56.647.432 I slot launch_slot_: id 0 | task 21592 | processing task, is_child = 0 2.56.879.915 I slot print_timing: id 0 | task 21592 | prompt eval time = 106.87 ms / 349 tokens ( 0.31 ms per token, 3265.68 tokens per second) 2.56.879.921 I slot print_timing: id 0 | task 21592 | eval time = 125.59 ms / 20 tokens ( 6.61 ms per token, 151.28 tokens per second) 2.56.879.922 I slot print_timing: id 0 | task 21592 | total time = 232.46 ms / 369 tokens 2.56.879.922 I slot print_timing: id 0 | task 21592 | graphs reused = 20523 2.56.879.923 I slot print_timing: id 0 | task 21592 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.879.951 I slot release: id 0 | task 21592 | stop processing: n_tokens = 400, truncated = 0 2.56.896.432 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 176783337 2.56.896.473 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.075 MiB) 2.56.961.557 I slot launch_slot_: id 0 | task 21615 | processing task, is_child = 0 2.59.381.215 I slot print_timing: id 0 | task 21615 | prompt eval time = 106.34 ms / 336 tokens ( 0.32 ms per token, 3159.68 tokens per second) 2.59.381.221 I slot print_timing: id 0 | task 21615 | eval time = 2313.30 ms / 354 tokens ( 6.55 ms per token, 152.60 tokens per second) 2.59.381.222 I slot print_timing: id 0 | task 21615 | total time = 2419.64 ms / 690 tokens 2.59.381.223 I slot print_timing: id 0 | task 21615 | graphs reused = 20874 2.59.381.224 I slot print_timing: id 0 | task 21615 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.381.251 I slot release: id 0 | task 21615 | stop processing: n_tokens = 721, truncated = 0 2.59.399.092 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 721, t_last = 179284638 2.59.399.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.390 MiB) 2.59.469.240 I slot launch_slot_: id 0 | task 21972 | processing task, is_child = 0 3.00.691.541 I slot print_timing: id 0 | task 21972 | prompt eval time = 108.68 ms / 349 tokens ( 0.31 ms per token, 3211.35 tokens per second) 3.00.691.547 I slot print_timing: id 0 | task 21972 | eval time = 1113.60 ms / 170 tokens ( 6.59 ms per token, 151.76 tokens per second) 3.00.691.548 I slot print_timing: id 0 | task 21972 | total time = 1222.28 ms / 519 tokens 3.00.691.548 I slot print_timing: id 0 | task 21972 | graphs reused = 21041 3.00.691.549 I slot print_timing: id 0 | task 21972 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.691.579 I slot release: id 0 | task 21972 | stop processing: n_tokens = 550, truncated = 0 3.00.710.448 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 550, t_last = 180594965 3.00.710.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 344.254 MiB) 3.00.782.510 I slot launch_slot_: id 0 | task 22145 | processing task, is_child = 0 3.01.260.538 I slot print_timing: id 0 | task 22145 | prompt eval time = 108.51 ms / 349 tokens ( 0.31 ms per token, 3216.26 tokens per second) 3.01.260.543 I slot print_timing: id 0 | task 22145 | eval time = 369.50 ms / 58 tokens ( 6.48 ms per token, 154.26 tokens per second) 3.01.260.544 I slot print_timing: id 0 | task 22145 | total time = 478.01 ms / 407 tokens 3.01.260.546 I slot print_timing: id 0 | task 22145 | graphs reused = 21097 3.01.260.546 I slot print_timing: id 0 | task 22145 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.260.574 I slot release: id 0 | task 22145 | stop processing: n_tokens = 438, truncated = 0 3.01.287.040 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 438, t_last = 181163961 3.01.287.084 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.888 MiB) 3.01.352.425 I slot launch_slot_: id 0 | task 22206 | processing task, is_child = 0 3.01.760.126 I slot print_timing: id 0 | task 22206 | prompt eval time = 111.75 ms / 385 tokens ( 0.29 ms per token, 3445.19 tokens per second) 3.01.760.132 I slot print_timing: id 0 | task 22206 | eval time = 295.93 ms / 46 tokens ( 6.58 ms per token, 152.06 tokens per second) 3.01.760.133 I slot print_timing: id 0 | task 22206 | total time = 407.68 ms / 431 tokens 3.01.760.134 I slot print_timing: id 0 | task 22206 | graphs reused = 21141 3.01.760.135 I slot print_timing: id 0 | task 22206 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.760.162 I slot release: id 0 | task 22206 | stop processing: n_tokens = 462, truncated = 0 3.01.782.651 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 462, t_last = 181663549 3.01.782.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.076 MiB) 3.01.853.718 I slot launch_slot_: id 0 | task 22255 | processing task, is_child = 0 3.02.340.568 I slot print_timing: id 0 | task 22255 | prompt eval time = 112.56 ms / 328 tokens ( 0.34 ms per token, 2914.13 tokens per second) 3.02.340.573 I slot print_timing: id 0 | task 22255 | eval time = 374.27 ms / 57 tokens ( 6.68 ms per token, 149.62 tokens per second) 3.02.340.574 I slot print_timing: id 0 | task 22255 | total time = 486.83 ms / 385 tokens 3.02.340.575 I slot print_timing: id 0 | task 22255 | graphs reused = 21196 3.02.340.576 I slot print_timing: id 0 | task 22255 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.340.602 I slot release: id 0 | task 22255 | stop processing: n_tokens = 416, truncated = 0