$ 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-Q6_K.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.093.556 I srv llama_server: initializing ... 0.00.093.561 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.093.667 I srv init_listene: The UI is disabled 0.00.093.669 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.093.744 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) 0.00.107.491 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--bartowski--Qwen_Qwen3.5-4B-GGUF\snapshots\4168f45a16a1290d65a4ec0fa312ae917a4c15d6\Qwen_Qwen3.5-4B-Q6_K.gguf' 0.00.926.420 W model has unused tensor blk.32.attn_norm.weight (size = 10240 bytes) -- ignoring 0.00.926.435 W model has unused tensor blk.32.post_attention_norm.weight (size = 10240 bytes) -- ignoring 0.00.926.462 W model has unused tensor blk.32.attn_q.weight (size = 22282240 bytes) -- ignoring 0.00.926.470 W model has unused tensor blk.32.attn_k.weight (size = 2785280 bytes) -- ignoring 0.00.926.479 W model has unused tensor blk.32.attn_v.weight (size = 2785280 bytes) -- ignoring 0.00.926.512 W model has unused tensor blk.32.attn_output.weight (size = 11141120 bytes) -- ignoring 0.00.926.523 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.926.531 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.926.541 W model has unused tensor blk.32.ffn_gate.weight (size = 25067520 bytes) -- ignoring 0.00.926.550 W model has unused tensor blk.32.ffn_down.weight (size = 25067520 bytes) -- ignoring 0.00.926.559 W model has unused tensor blk.32.ffn_up.weight (size = 25067520 bytes) -- ignoring 0.00.926.570 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 13926400 bytes) -- ignoring 0.00.926.579 W model has unused tensor blk.32.nextn.enorm.weight (size = 10240 bytes) -- ignoring 0.00.926.590 W model has unused tensor blk.32.nextn.hnorm.weight (size = 10240 bytes) -- ignoring 0.00.926.619 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 10240 bytes) -- ignoring 0.02.224.075 I cmn init: llama threadpool init, n_threads = 8 0.02.303.737 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.308.430 I srv llama_server: model loaded 0.02.308.436 I srv llama_server: listening on http://127.0.0.1:8089 0.02.532.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.532.462 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.138.109 I slot print_timing: id 0 | task 0 | prompt eval time = 186.78 ms / 368 tokens ( 0.51 ms per token, 1970.20 tokens per second) 0.03.138.115 I slot print_timing: id 0 | task 0 | eval time = 418.85 ms / 53 tokens ( 8.05 ms per token, 124.15 tokens per second) 0.03.138.116 I slot print_timing: id 0 | task 0 | total time = 605.63 ms / 421 tokens 0.03.138.121 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.03.138.123 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.138.152 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.03.159.314 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 3046532 0.03.184.756 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.03.608.898 I slot print_timing: id 0 | task 56 | prompt eval time = 96.27 ms / 322 tokens ( 0.30 ms per token, 3344.83 tokens per second) 0.03.608.904 I slot print_timing: id 0 | task 56 | eval time = 327.85 ms / 42 tokens ( 8.00 ms per token, 125.06 tokens per second) 0.03.608.904 I slot print_timing: id 0 | task 56 | total time = 424.12 ms / 364 tokens 0.03.608.906 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.03.608.906 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.608.932 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.03.628.736 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 3517312 0.03.653.808 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.04.080.893 I slot print_timing: id 0 | task 101 | prompt eval time = 98.49 ms / 365 tokens ( 0.27 ms per token, 3706.04 tokens per second) 0.04.080.899 I slot print_timing: id 0 | task 101 | eval time = 328.58 ms / 42 tokens ( 8.01 ms per token, 124.78 tokens per second) 0.04.080.900 I slot print_timing: id 0 | task 101 | total time = 427.06 ms / 407 tokens 0.04.080.900 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.04.080.901 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.080.940 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.04.096.437 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 3989320 0.04.121.721 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.04.559.669 I slot print_timing: id 0 | task 146 | prompt eval time = 102.00 ms / 397 tokens ( 0.26 ms per token, 3891.97 tokens per second) 0.04.559.675 I slot print_timing: id 0 | task 146 | eval time = 335.92 ms / 43 tokens ( 8.00 ms per token, 125.03 tokens per second) 0.04.559.676 I slot print_timing: id 0 | task 146 | total time = 437.93 ms / 440 tokens 0.04.559.677 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.04.559.678 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.559.708 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.04.577.271 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 0.04.602.793 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.05.132.670 I slot print_timing: id 0 | task 192 | prompt eval time = 97.88 ms / 383 tokens ( 0.26 ms per token, 3912.79 tokens per second) 0.05.132.676 I slot print_timing: id 0 | task 192 | eval time = 431.97 ms / 55 tokens ( 8.00 ms per token, 125.01 tokens per second) 0.05.132.677 I slot print_timing: id 0 | task 192 | total time = 529.86 ms / 438 tokens 0.05.132.678 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.05.132.679 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.132.706 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.05.154.410 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 5041086 0.05.180.886 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.05.712.522 I slot print_timing: id 0 | task 250 | prompt eval time = 99.68 ms / 372 tokens ( 0.27 ms per token, 3731.87 tokens per second) 0.05.712.527 I slot print_timing: id 0 | task 250 | eval time = 431.94 ms / 55 tokens ( 8.00 ms per token, 125.02 tokens per second) 0.05.712.528 I slot print_timing: id 0 | task 250 | total time = 531.62 ms / 427 tokens 0.05.712.529 I slot print_timing: id 0 | task 250 | graphs reused = 279 0.05.712.530 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.712.558 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 0.05.734.318 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 5620938 0.05.760.224 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 0.06.300.252 I slot print_timing: id 0 | task 308 | prompt eval time = 108.97 ms / 422 tokens ( 0.26 ms per token, 3872.59 tokens per second) 0.06.300.257 I slot print_timing: id 0 | task 308 | eval time = 431.04 ms / 55 tokens ( 7.98 ms per token, 125.28 tokens per second) 0.06.300.258 I slot print_timing: id 0 | task 308 | total time = 540.01 ms / 477 tokens 0.06.300.259 I slot print_timing: id 0 | task 308 | graphs reused = 332 0.06.300.260 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.300.291 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 0.06.317.098 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 6208671 0.06.342.925 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 0.07.023.733 I slot print_timing: id 0 | task 366 | prompt eval time = 110.31 ms / 470 tokens ( 0.23 ms per token, 4260.57 tokens per second) 0.07.023.738 I slot print_timing: id 0 | task 366 | eval time = 570.47 ms / 72 tokens ( 8.03 ms per token, 124.46 tokens per second) 0.07.023.739 I slot print_timing: id 0 | task 366 | total time = 680.79 ms / 542 tokens 0.07.023.740 I slot print_timing: id 0 | task 366 | graphs reused = 401 0.07.023.741 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.023.774 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 0.07.050.832 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 6932154 0.07.077.068 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 0.07.540.814 I slot print_timing: id 0 | task 441 | prompt eval time = 95.67 ms / 345 tokens ( 0.28 ms per token, 3606.00 tokens per second) 0.07.540.820 I slot print_timing: id 0 | task 441 | eval time = 368.05 ms / 47 tokens ( 8.00 ms per token, 124.98 tokens per second) 0.07.540.821 I slot print_timing: id 0 | task 441 | total time = 463.72 ms / 392 tokens 0.07.540.822 I slot print_timing: id 0 | task 441 | graphs reused = 446 0.07.540.823 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.540.852 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 0.07.569.960 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 7449231 0.07.597.213 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 0.08.124.593 I slot print_timing: id 0 | task 491 | prompt eval time = 96.40 ms / 364 tokens ( 0.26 ms per token, 3775.89 tokens per second) 0.08.124.599 I slot print_timing: id 0 | task 491 | eval time = 430.96 ms / 55 tokens ( 7.98 ms per token, 125.30 tokens per second) 0.08.124.600 I slot print_timing: id 0 | task 491 | total time = 527.36 ms / 419 tokens 0.08.124.601 I slot print_timing: id 0 | task 491 | graphs reused = 499 0.08.124.601 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.124.629 I slot release: id 0 | task 491 | stop processing: n_tokens = 418, truncated = 0 0.08.149.412 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 8033009 0.08.175.712 I slot launch_slot_: id 0 | task 549 | processing task, is_child = 0 0.08.801.411 I slot print_timing: id 0 | task 549 | prompt eval time = 100.15 ms / 376 tokens ( 0.27 ms per token, 3754.22 tokens per second) 0.08.801.417 I slot print_timing: id 0 | task 549 | eval time = 525.52 ms / 62 tokens ( 8.62 ms per token, 116.07 tokens per second) 0.08.801.418 I slot print_timing: id 0 | task 549 | total time = 625.68 ms / 438 tokens 0.08.801.419 I slot print_timing: id 0 | task 549 | graphs reused = 559 0.08.801.420 I slot print_timing: id 0 | task 549 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.801.448 I slot release: id 0 | task 549 | stop processing: n_tokens = 437, truncated = 0 0.08.822.499 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 8709827 0.08.847.796 I slot launch_slot_: id 0 | task 614 | processing task, is_child = 0 0.09.317.000 I slot print_timing: id 0 | task 614 | prompt eval time = 101.37 ms / 412 tokens ( 0.25 ms per token, 4064.48 tokens per second) 0.09.317.006 I slot print_timing: id 0 | task 614 | eval time = 367.82 ms / 47 tokens ( 8.00 ms per token, 125.06 tokens per second) 0.09.317.007 I slot print_timing: id 0 | task 614 | total time = 469.19 ms / 459 tokens 0.09.317.008 I slot print_timing: id 0 | task 614 | graphs reused = 604 0.09.317.009 I slot print_timing: id 0 | task 614 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.317.039 I slot release: id 0 | task 614 | stop processing: n_tokens = 458, truncated = 0 0.09.334.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 9225419 0.09.361.737 I slot launch_slot_: id 0 | task 664 | processing task, is_child = 0 0.09.946.209 I slot print_timing: id 0 | task 664 | prompt eval time = 97.37 ms / 376 tokens ( 0.26 ms per token, 3861.48 tokens per second) 0.09.946.214 I slot print_timing: id 0 | task 664 | eval time = 487.08 ms / 62 tokens ( 7.98 ms per token, 125.24 tokens per second) 0.09.946.215 I slot print_timing: id 0 | task 664 | total time = 584.45 ms / 438 tokens 0.09.946.216 I slot print_timing: id 0 | task 664 | graphs reused = 664 0.09.946.217 I slot print_timing: id 0 | task 664 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.946.243 I slot release: id 0 | task 664 | stop processing: n_tokens = 437, truncated = 0 0.09.972.866 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 9854623 0.09.998.427 I slot launch_slot_: id 0 | task 729 | processing task, is_child = 0 0.10.506.123 I slot print_timing: id 0 | task 729 | prompt eval time = 100.19 ms / 378 tokens ( 0.27 ms per token, 3772.72 tokens per second) 0.10.506.129 I slot print_timing: id 0 | task 729 | eval time = 407.48 ms / 52 tokens ( 7.99 ms per token, 125.16 tokens per second) 0.10.506.130 I slot print_timing: id 0 | task 729 | total time = 507.68 ms / 430 tokens 0.10.506.130 I slot print_timing: id 0 | task 729 | graphs reused = 714 0.10.506.132 I slot print_timing: id 0 | task 729 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.506.160 I slot release: id 0 | task 729 | stop processing: n_tokens = 429, truncated = 0 0.10.519.830 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 10414540 0.10.556.511 I slot launch_slot_: id 0 | task 784 | processing task, is_child = 0 0.11.138.215 I slot print_timing: id 0 | task 784 | prompt eval time = 99.53 ms / 367 tokens ( 0.27 ms per token, 3687.37 tokens per second) 0.11.138.221 I slot print_timing: id 0 | task 784 | eval time = 482.16 ms / 58 tokens ( 8.46 ms per token, 118.22 tokens per second) 0.11.138.222 I slot print_timing: id 0 | task 784 | total time = 581.68 ms / 425 tokens 0.11.138.222 I slot print_timing: id 0 | task 784 | graphs reused = 770 0.11.138.223 I slot print_timing: id 0 | task 784 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.138.250 I slot release: id 0 | task 784 | stop processing: n_tokens = 424, truncated = 0 0.11.163.835 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 11046630 0.11.189.006 I slot launch_slot_: id 0 | task 845 | processing task, is_child = 0 0.11.683.743 I slot print_timing: id 0 | task 845 | prompt eval time = 95.39 ms / 347 tokens ( 0.27 ms per token, 3637.55 tokens per second) 0.11.683.749 I slot print_timing: id 0 | task 845 | eval time = 399.32 ms / 51 tokens ( 7.99 ms per token, 125.21 tokens per second) 0.11.683.750 I slot print_timing: id 0 | task 845 | total time = 494.72 ms / 398 tokens 0.11.683.751 I slot print_timing: id 0 | task 845 | graphs reused = 819 0.11.683.751 I slot print_timing: id 0 | task 845 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.683.778 I slot release: id 0 | task 845 | stop processing: n_tokens = 397, truncated = 0 0.11.708.843 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 11592158 0.11.736.105 I slot launch_slot_: id 0 | task 899 | processing task, is_child = 0 0.13.509.285 I slot print_timing: id 0 | task 899 | prompt eval time = 97.47 ms / 369 tokens ( 0.26 ms per token, 3785.78 tokens per second) 0.13.509.291 I slot print_timing: id 0 | task 899 | eval time = 1675.68 ms / 212 tokens ( 7.94 ms per token, 125.92 tokens per second) 0.13.509.292 I slot print_timing: id 0 | task 899 | total time = 1773.15 ms / 581 tokens 0.13.509.293 I slot print_timing: id 0 | task 899 | graphs reused = 1028 0.13.509.294 I slot print_timing: id 0 | task 899 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.509.324 I slot release: id 0 | task 899 | stop processing: n_tokens = 580, truncated = 0 0.13.513.026 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 13417703 0.13.542.640 I slot launch_slot_: id 0 | task 1114 | processing task, is_child = 0 0.13.965.474 I slot print_timing: id 0 | task 1114 | prompt eval time = 97.30 ms / 352 tokens ( 0.28 ms per token, 3617.71 tokens per second) 0.13.965.480 I slot print_timing: id 0 | task 1114 | eval time = 325.51 ms / 41 tokens ( 8.14 ms per token, 122.88 tokens per second) 0.13.965.481 I slot print_timing: id 0 | task 1114 | total time = 422.81 ms / 393 tokens 0.13.965.482 I slot print_timing: id 0 | task 1114 | graphs reused = 1067 0.13.965.483 I slot print_timing: id 0 | task 1114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.965.514 I slot release: id 0 | task 1114 | stop processing: n_tokens = 392, truncated = 0 0.13.992.217 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 13873893 0.14.017.316 I slot launch_slot_: id 0 | task 1158 | processing task, is_child = 0 0.14.449.410 I slot print_timing: id 0 | task 1158 | prompt eval time = 102.61 ms / 349 tokens ( 0.29 ms per token, 3401.06 tokens per second) 0.14.449.416 I slot print_timing: id 0 | task 1158 | eval time = 329.46 ms / 41 tokens ( 8.24 ms per token, 121.41 tokens per second) 0.14.449.417 I slot print_timing: id 0 | task 1158 | total time = 432.07 ms / 390 tokens 0.14.449.418 I slot print_timing: id 0 | task 1158 | graphs reused = 1106 0.14.449.419 I slot print_timing: id 0 | task 1158 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.449.446 I slot release: id 0 | task 1158 | stop processing: n_tokens = 389, truncated = 0 0.14.473.644 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 389, t_last = 14357826 0.14.499.503 I slot launch_slot_: id 0 | task 1202 | processing task, is_child = 0 0.15.143.880 I slot print_timing: id 0 | task 1202 | prompt eval time = 103.61 ms / 384 tokens ( 0.27 ms per token, 3706.24 tokens per second) 0.15.143.886 I slot print_timing: id 0 | task 1202 | eval time = 540.75 ms / 63 tokens ( 8.72 ms per token, 114.66 tokens per second) 0.15.143.887 I slot print_timing: id 0 | task 1202 | total time = 644.36 ms / 447 tokens 0.15.143.888 I slot print_timing: id 0 | task 1202 | graphs reused = 1167 0.15.143.889 I slot print_timing: id 0 | task 1202 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.143.918 I slot release: id 0 | task 1202 | stop processing: n_tokens = 446, truncated = 0 0.15.157.920 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 15052298 0.15.183.597 I slot launch_slot_: id 0 | task 1268 | processing task, is_child = 0 0.15.708.717 I slot print_timing: id 0 | task 1268 | prompt eval time = 97.27 ms / 356 tokens ( 0.27 ms per token, 3659.84 tokens per second) 0.15.708.723 I slot print_timing: id 0 | task 1268 | eval time = 427.83 ms / 54 tokens ( 8.07 ms per token, 123.88 tokens per second) 0.15.708.724 I slot print_timing: id 0 | task 1268 | total time = 525.10 ms / 410 tokens 0.15.708.725 I slot print_timing: id 0 | task 1268 | graphs reused = 1219 0.15.708.725 I slot print_timing: id 0 | task 1268 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.708.753 I slot release: id 0 | task 1268 | stop processing: n_tokens = 409, truncated = 0 0.15.732.271 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 15617133 0.15.759.035 I slot launch_slot_: id 0 | task 1325 | processing task, is_child = 0 0.16.423.307 I slot print_timing: id 0 | task 1325 | prompt eval time = 105.54 ms / 410 tokens ( 0.26 ms per token, 3884.86 tokens per second) 0.16.423.312 I slot print_timing: id 0 | task 1325 | eval time = 558.71 ms / 70 tokens ( 8.10 ms per token, 123.50 tokens per second) 0.16.423.313 I slot print_timing: id 0 | task 1325 | total time = 664.25 ms / 480 tokens 0.16.423.314 I slot print_timing: id 0 | task 1325 | graphs reused = 1287 0.16.423.315 I slot print_timing: id 0 | task 1325 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.423.344 I slot release: id 0 | task 1325 | stop processing: n_tokens = 479, truncated = 0 0.16.448.132 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 16331724 0.16.474.316 I slot launch_slot_: id 0 | task 1398 | processing task, is_child = 0 0.17.036.424 I slot print_timing: id 0 | task 1398 | prompt eval time = 103.34 ms / 385 tokens ( 0.27 ms per token, 3725.57 tokens per second) 0.17.036.430 I slot print_timing: id 0 | task 1398 | eval time = 458.75 ms / 58 tokens ( 8.05 ms per token, 124.25 tokens per second) 0.17.036.431 I slot print_timing: id 0 | task 1398 | total time = 562.09 ms / 443 tokens 0.17.036.432 I slot print_timing: id 0 | task 1398 | graphs reused = 1343 0.17.036.433 I slot print_timing: id 0 | task 1398 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.036.461 I slot release: id 0 | task 1398 | stop processing: n_tokens = 442, truncated = 0 0.17.054.699 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 16944841 0.17.081.020 I slot launch_slot_: id 0 | task 1459 | processing task, is_child = 0 0.17.747.769 I slot print_timing: id 0 | task 1459 | prompt eval time = 105.31 ms / 395 tokens ( 0.27 ms per token, 3750.83 tokens per second) 0.17.747.775 I slot print_timing: id 0 | task 1459 | eval time = 561.42 ms / 71 tokens ( 8.02 ms per token, 124.68 tokens per second) 0.17.747.776 I slot print_timing: id 0 | task 1459 | total time = 666.73 ms / 466 tokens 0.17.747.776 I slot print_timing: id 0 | task 1459 | graphs reused = 1412 0.17.747.777 I slot print_timing: id 0 | task 1459 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.747.806 I slot release: id 0 | task 1459 | stop processing: n_tokens = 465, truncated = 0 0.17.771.740 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 17656186 0.17.797.765 I slot launch_slot_: id 0 | task 1533 | processing task, is_child = 0 0.18.363.616 I slot print_timing: id 0 | task 1533 | prompt eval time = 104.00 ms / 430 tokens ( 0.24 ms per token, 4134.66 tokens per second) 0.18.363.622 I slot print_timing: id 0 | task 1533 | eval time = 461.83 ms / 59 tokens ( 7.96 ms per token, 125.59 tokens per second) 0.18.363.623 I slot print_timing: id 0 | task 1533 | total time = 565.83 ms / 489 tokens 0.18.363.624 I slot print_timing: id 0 | task 1533 | graphs reused = 1469 0.18.363.624 I slot print_timing: id 0 | task 1533 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.363.654 I slot release: id 0 | task 1533 | stop processing: n_tokens = 488, truncated = 0 0.18.377.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 488, t_last = 18272034 0.18.403.686 I slot launch_slot_: id 0 | task 1595 | processing task, is_child = 0 0.18.992.392 I slot print_timing: id 0 | task 1595 | prompt eval time = 101.63 ms / 392 tokens ( 0.26 ms per token, 3857.01 tokens per second) 0.18.992.397 I slot print_timing: id 0 | task 1595 | eval time = 487.05 ms / 62 tokens ( 7.98 ms per token, 125.24 tokens per second) 0.18.992.398 I slot print_timing: id 0 | task 1595 | total time = 588.68 ms / 454 tokens 0.18.992.399 I slot print_timing: id 0 | task 1595 | graphs reused = 1529 0.18.992.400 I slot print_timing: id 0 | task 1595 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.992.428 I slot release: id 0 | task 1595 | stop processing: n_tokens = 453, truncated = 0 0.19.016.920 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 18900808 0.19.042.783 I slot launch_slot_: id 0 | task 1660 | processing task, is_child = 0 0.19.521.588 I slot print_timing: id 0 | task 1660 | prompt eval time = 94.73 ms / 350 tokens ( 0.27 ms per token, 3694.75 tokens per second) 0.19.521.594 I slot print_timing: id 0 | task 1660 | eval time = 384.06 ms / 49 tokens ( 8.00 ms per token, 124.98 tokens per second) 0.19.521.595 I slot print_timing: id 0 | task 1660 | total time = 478.78 ms / 399 tokens 0.19.521.596 I slot print_timing: id 0 | task 1660 | graphs reused = 1576 0.19.521.597 I slot print_timing: id 0 | task 1660 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.521.624 I slot release: id 0 | task 1660 | stop processing: n_tokens = 398, truncated = 0 0.19.546.046 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 19430004 0.19.571.243 I slot launch_slot_: id 0 | task 1712 | processing task, is_child = 0 0.20.149.160 I slot print_timing: id 0 | task 1712 | prompt eval time = 100.00 ms / 380 tokens ( 0.26 ms per token, 3799.89 tokens per second) 0.20.149.165 I slot print_timing: id 0 | task 1712 | eval time = 477.89 ms / 61 tokens ( 7.96 ms per token, 125.55 tokens per second) 0.20.149.166 I slot print_timing: id 0 | task 1712 | total time = 577.90 ms / 441 tokens 0.20.149.167 I slot print_timing: id 0 | task 1712 | graphs reused = 1635 0.20.149.168 I slot print_timing: id 0 | task 1712 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.149.195 I slot release: id 0 | task 1712 | stop processing: n_tokens = 440, truncated = 0 0.20.170.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 20057575 0.20.196.177 I slot launch_slot_: id 0 | task 1776 | processing task, is_child = 0 0.20.959.859 I slot print_timing: id 0 | task 1776 | prompt eval time = 103.78 ms / 410 tokens ( 0.25 ms per token, 3950.86 tokens per second) 0.20.959.866 I slot print_timing: id 0 | task 1776 | eval time = 659.89 ms / 80 tokens ( 8.35 ms per token, 119.72 tokens per second) 0.20.959.867 I slot print_timing: id 0 | task 1776 | total time = 763.66 ms / 490 tokens 0.20.959.868 I slot print_timing: id 0 | task 1776 | graphs reused = 1713 0.20.959.869 I slot print_timing: id 0 | task 1776 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.959.902 I slot release: id 0 | task 1776 | stop processing: n_tokens = 489, truncated = 0 0.20.963.596 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 20868282 0.20.989.458 I slot launch_slot_: id 0 | task 1859 | processing task, is_child = 0 0.21.625.310 I slot print_timing: id 0 | task 1859 | prompt eval time = 100.95 ms / 387 tokens ( 0.26 ms per token, 3833.66 tokens per second) 0.21.625.316 I slot print_timing: id 0 | task 1859 | eval time = 534.88 ms / 68 tokens ( 7.98 ms per token, 125.26 tokens per second) 0.21.625.318 I slot print_timing: id 0 | task 1859 | total time = 635.83 ms / 455 tokens 0.21.625.319 I slot print_timing: id 0 | task 1859 | graphs reused = 1779 0.21.625.320 I slot print_timing: id 0 | task 1859 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.625.350 I slot release: id 0 | task 1859 | stop processing: n_tokens = 454, truncated = 0 0.21.641.749 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 21533730 0.21.667.492 I slot launch_slot_: id 0 | task 1930 | processing task, is_child = 0 0.22.226.796 I slot print_timing: id 0 | task 1930 | prompt eval time = 96.32 ms / 358 tokens ( 0.27 ms per token, 3716.93 tokens per second) 0.22.226.801 I slot print_timing: id 0 | task 1930 | eval time = 462.97 ms / 59 tokens ( 7.98 ms per token, 125.28 tokens per second) 0.22.226.802 I slot print_timing: id 0 | task 1930 | total time = 559.28 ms / 417 tokens 0.22.226.803 I slot print_timing: id 0 | task 1930 | graphs reused = 1836 0.22.226.804 I slot print_timing: id 0 | task 1930 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.226.837 I slot release: id 0 | task 1930 | stop processing: n_tokens = 416, truncated = 0 0.22.245.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 22135217 0.22.271.277 I slot launch_slot_: id 0 | task 1992 | processing task, is_child = 0 0.22.835.128 I slot print_timing: id 0 | task 1992 | prompt eval time = 95.37 ms / 359 tokens ( 0.27 ms per token, 3764.29 tokens per second) 0.22.835.133 I slot print_timing: id 0 | task 1992 | eval time = 468.46 ms / 56 tokens ( 8.52 ms per token, 117.41 tokens per second) 0.22.835.134 I slot print_timing: id 0 | task 1992 | total time = 563.83 ms / 415 tokens 0.22.835.135 I slot print_timing: id 0 | task 1992 | graphs reused = 1890 0.22.835.136 I slot print_timing: id 0 | task 1992 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.835.162 I slot release: id 0 | task 1992 | stop processing: n_tokens = 414, truncated = 0 0.22.856.350 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 22743542 0.22.881.637 I slot launch_slot_: id 0 | task 2051 | processing task, is_child = 0 0.23.460.283 I slot print_timing: id 0 | task 2051 | prompt eval time = 100.40 ms / 387 tokens ( 0.26 ms per token, 3854.66 tokens per second) 0.23.460.289 I slot print_timing: id 0 | task 2051 | eval time = 478.23 ms / 61 tokens ( 7.97 ms per token, 125.46 tokens per second) 0.23.460.290 I slot print_timing: id 0 | task 2051 | total time = 578.63 ms / 448 tokens 0.23.460.290 I slot print_timing: id 0 | task 2051 | graphs reused = 1949 0.23.460.291 I slot print_timing: id 0 | task 2051 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.460.320 I slot release: id 0 | task 2051 | stop processing: n_tokens = 447, truncated = 0 0.23.483.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 23368699 0.23.515.827 I slot launch_slot_: id 0 | task 2115 | processing task, is_child = 0 0.24.094.843 I slot print_timing: id 0 | task 2115 | prompt eval time = 100.88 ms / 410 tokens ( 0.25 ms per token, 4064.40 tokens per second) 0.24.094.849 I slot print_timing: id 0 | task 2115 | eval time = 478.12 ms / 61 tokens ( 7.97 ms per token, 125.49 tokens per second) 0.24.094.850 I slot print_timing: id 0 | task 2115 | total time = 579.00 ms / 471 tokens 0.24.094.851 I slot print_timing: id 0 | task 2115 | graphs reused = 2008 0.24.094.852 I slot print_timing: id 0 | task 2115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.094.882 I slot release: id 0 | task 2115 | stop processing: n_tokens = 470, truncated = 0 0.24.122.420 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 24003262 0.24.148.764 I slot launch_slot_: id 0 | task 2179 | processing task, is_child = 0 0.24.634.219 I slot print_timing: id 0 | task 2179 | prompt eval time = 94.55 ms / 351 tokens ( 0.27 ms per token, 3712.44 tokens per second) 0.24.634.224 I slot print_timing: id 0 | task 2179 | eval time = 390.89 ms / 50 tokens ( 7.98 ms per token, 125.36 tokens per second) 0.24.634.226 I slot print_timing: id 0 | task 2179 | total time = 485.43 ms / 401 tokens 0.24.634.226 I slot print_timing: id 0 | task 2179 | graphs reused = 2056 0.24.634.227 I slot print_timing: id 0 | task 2179 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.634.259 I slot release: id 0 | task 2179 | stop processing: n_tokens = 400, truncated = 0 0.24.654.089 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 24542639 0.24.679.503 I slot launch_slot_: id 0 | task 2232 | processing task, is_child = 0 0.26.553.722 I slot print_timing: id 0 | task 2232 | prompt eval time = 100.92 ms / 393 tokens ( 0.26 ms per token, 3894.37 tokens per second) 0.26.553.727 I slot print_timing: id 0 | task 2232 | eval time = 1773.28 ms / 224 tokens ( 7.95 ms per token, 125.76 tokens per second) 0.26.553.728 I slot print_timing: id 0 | task 2232 | total time = 1874.20 ms / 617 tokens 0.26.553.729 I slot print_timing: id 0 | task 2232 | graphs reused = 2277 0.26.553.730 I slot print_timing: id 0 | task 2232 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.553.759 I slot release: id 0 | task 2232 | stop processing: n_tokens = 616, truncated = 0 0.26.581.011 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 26462139 0.26.607.543 I slot launch_slot_: id 0 | task 2459 | processing task, is_child = 0 0.26.934.971 I slot print_timing: id 0 | task 2459 | prompt eval time = 94.25 ms / 321 tokens ( 0.29 ms per token, 3405.80 tokens per second) 0.26.934.976 I slot print_timing: id 0 | task 2459 | eval time = 233.16 ms / 30 tokens ( 8.04 ms per token, 124.38 tokens per second) 0.26.934.977 I slot print_timing: id 0 | task 2459 | total time = 327.41 ms / 351 tokens 0.26.934.978 I slot print_timing: id 0 | task 2459 | graphs reused = 2305 0.26.934.979 I slot print_timing: id 0 | task 2459 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.935.004 I slot release: id 0 | task 2459 | stop processing: n_tokens = 350, truncated = 0 0.26.950.097 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 26843384 0.26.975.237 I slot launch_slot_: id 0 | task 2492 | processing task, is_child = 0 0.27.571.939 I slot print_timing: id 0 | task 2492 | prompt eval time = 94.86 ms / 330 tokens ( 0.29 ms per token, 3478.63 tokens per second) 0.27.571.945 I slot print_timing: id 0 | task 2492 | eval time = 501.82 ms / 64 tokens ( 7.97 ms per token, 125.54 tokens per second) 0.27.571.947 I slot print_timing: id 0 | task 2492 | total time = 596.68 ms / 394 tokens 0.27.571.948 I slot print_timing: id 0 | task 2492 | graphs reused = 2367 0.27.571.949 I slot print_timing: id 0 | task 2492 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.571.978 I slot release: id 0 | task 2492 | stop processing: n_tokens = 393, truncated = 0 0.27.588.968 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 27480357 0.27.614.457 I slot launch_slot_: id 0 | task 2559 | processing task, is_child = 0 0.27.958.265 I slot print_timing: id 0 | task 2559 | prompt eval time = 94.23 ms / 341 tokens ( 0.28 ms per token, 3618.88 tokens per second) 0.27.958.271 I slot print_timing: id 0 | task 2559 | eval time = 249.56 ms / 32 tokens ( 8.05 ms per token, 124.22 tokens per second) 0.27.958.272 I slot print_timing: id 0 | task 2559 | total time = 343.79 ms / 373 tokens 0.27.958.273 I slot print_timing: id 0 | task 2559 | graphs reused = 2397 0.27.958.273 I slot print_timing: id 0 | task 2559 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.958.301 I slot release: id 0 | task 2559 | stop processing: n_tokens = 372, truncated = 0 0.27.977.882 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 27866681 0.28.002.867 I slot launch_slot_: id 0 | task 2594 | processing task, is_child = 0 0.28.476.856 I slot print_timing: id 0 | task 2594 | prompt eval time = 98.41 ms / 338 tokens ( 0.29 ms per token, 3434.68 tokens per second) 0.28.476.861 I slot print_timing: id 0 | task 2594 | eval time = 375.56 ms / 48 tokens ( 7.99 ms per token, 125.15 tokens per second) 0.28.476.862 I slot print_timing: id 0 | task 2594 | total time = 473.97 ms / 386 tokens 0.28.476.863 I slot print_timing: id 0 | task 2594 | graphs reused = 2443 0.28.476.864 I slot print_timing: id 0 | task 2594 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.476.890 I slot release: id 0 | task 2594 | stop processing: n_tokens = 385, truncated = 0 0.28.490.032 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 28385270 0.28.525.339 I slot launch_slot_: id 0 | task 2645 | processing task, is_child = 0 0.29.065.728 I slot print_timing: id 0 | task 2645 | prompt eval time = 101.69 ms / 395 tokens ( 0.26 ms per token, 3884.39 tokens per second) 0.29.065.733 I slot print_timing: id 0 | task 2645 | eval time = 438.68 ms / 56 tokens ( 7.98 ms per token, 125.38 tokens per second) 0.29.065.735 I slot print_timing: id 0 | task 2645 | total time = 540.37 ms / 451 tokens 0.29.065.735 I slot print_timing: id 0 | task 2645 | graphs reused = 2497 0.29.065.736 I slot print_timing: id 0 | task 2645 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.065.767 I slot release: id 0 | task 2645 | stop processing: n_tokens = 450, truncated = 0 0.29.080.809 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 28974147 0.29.107.680 I slot launch_slot_: id 0 | task 2704 | processing task, is_child = 0 0.29.902.210 I slot print_timing: id 0 | task 2704 | prompt eval time = 140.30 ms / 528 tokens ( 0.27 ms per token, 3763.36 tokens per second) 0.29.902.216 I slot print_timing: id 0 | task 2704 | eval time = 654.21 ms / 83 tokens ( 7.98 ms per token, 125.34 tokens per second) 0.29.902.217 I slot print_timing: id 0 | task 2704 | total time = 794.51 ms / 611 tokens 0.29.902.218 I slot print_timing: id 0 | task 2704 | graphs reused = 2578 0.29.902.219 I slot print_timing: id 0 | task 2704 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.902.253 I slot release: id 0 | task 2704 | stop processing: n_tokens = 610, truncated = 0 0.29.922.455 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 29810632 0.29.954.796 I slot launch_slot_: id 0 | task 2791 | processing task, is_child = 0 0.30.420.629 I slot print_timing: id 0 | task 2791 | prompt eval time = 113.22 ms / 331 tokens ( 0.34 ms per token, 2923.49 tokens per second) 0.30.420.636 I slot print_timing: id 0 | task 2791 | eval time = 352.59 ms / 45 tokens ( 8.01 ms per token, 124.79 tokens per second) 0.30.420.637 I slot print_timing: id 0 | task 2791 | total time = 465.81 ms / 376 tokens 0.30.420.638 I slot print_timing: id 0 | task 2791 | graphs reused = 2621 0.30.420.639 I slot print_timing: id 0 | task 2791 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.420.671 I slot release: id 0 | task 2791 | stop processing: n_tokens = 387, truncated = 0 0.30.437.372 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 30329050 0.30.470.658 I slot launch_slot_: id 0 | task 2839 | processing task, is_child = 0 0.31.005.496 I slot print_timing: id 0 | task 2839 | prompt eval time = 118.60 ms / 362 tokens ( 0.33 ms per token, 3052.17 tokens per second) 0.31.005.501 I slot print_timing: id 0 | task 2839 | eval time = 416.22 ms / 53 tokens ( 8.00 ms per token, 124.93 tokens per second) 0.31.005.502 I slot print_timing: id 0 | task 2839 | total time = 534.82 ms / 415 tokens 0.31.005.503 I slot print_timing: id 0 | task 2839 | graphs reused = 2672 0.31.005.504 I slot print_timing: id 0 | task 2839 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.005.532 I slot release: id 0 | task 2839 | stop processing: n_tokens = 426, truncated = 0 0.31.028.114 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 30913912 0.31.059.677 I slot launch_slot_: id 0 | task 2895 | processing task, is_child = 0 0.31.723.448 I slot print_timing: id 0 | task 2895 | prompt eval time = 122.12 ms / 419 tokens ( 0.29 ms per token, 3431.14 tokens per second) 0.31.723.454 I slot print_timing: id 0 | task 2895 | eval time = 541.63 ms / 69 tokens ( 7.97 ms per token, 125.55 tokens per second) 0.31.723.456 I slot print_timing: id 0 | task 2895 | total time = 663.74 ms / 488 tokens 0.31.723.458 I slot print_timing: id 0 | task 2895 | graphs reused = 2739 0.31.723.459 I slot print_timing: id 0 | task 2895 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.723.494 I slot release: id 0 | task 2895 | stop processing: n_tokens = 499, truncated = 0 0.31.742.463 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 31631874 0.31.773.809 I slot launch_slot_: id 0 | task 2967 | processing task, is_child = 0 0.32.523.951 I slot print_timing: id 0 | task 2967 | prompt eval time = 126.61 ms / 423 tokens ( 0.30 ms per token, 3340.92 tokens per second) 0.32.523.957 I slot print_timing: id 0 | task 2967 | eval time = 623.51 ms / 72 tokens ( 8.78 ms per token, 113.87 tokens per second) 0.32.523.958 I slot print_timing: id 0 | task 2967 | total time = 750.12 ms / 495 tokens 0.32.523.959 I slot print_timing: id 0 | task 2967 | graphs reused = 2809 0.32.523.960 I slot print_timing: id 0 | task 2967 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.523.991 I slot release: id 0 | task 2967 | stop processing: n_tokens = 506, truncated = 0 0.32.551.326 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 32432371 0.32.583.418 I slot launch_slot_: id 0 | task 3042 | processing task, is_child = 0 0.33.033.379 I slot print_timing: id 0 | task 3042 | prompt eval time = 113.38 ms / 341 tokens ( 0.33 ms per token, 3007.72 tokens per second) 0.33.033.384 I slot print_timing: id 0 | task 3042 | eval time = 336.57 ms / 43 tokens ( 8.01 ms per token, 124.79 tokens per second) 0.33.033.385 I slot print_timing: id 0 | task 3042 | total time = 449.94 ms / 384 tokens 0.33.033.386 I slot print_timing: id 0 | task 3042 | graphs reused = 2850 0.33.033.387 I slot print_timing: id 0 | task 3042 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.033.415 I slot release: id 0 | task 3042 | stop processing: n_tokens = 395, truncated = 0 0.33.054.386 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 32941795 0.33.091.567 I slot launch_slot_: id 0 | task 3088 | processing task, is_child = 0 0.33.574.059 I slot print_timing: id 0 | task 3088 | prompt eval time = 115.17 ms / 356 tokens ( 0.32 ms per token, 3091.08 tokens per second) 0.33.574.065 I slot print_timing: id 0 | task 3088 | eval time = 367.30 ms / 47 tokens ( 7.98 ms per token, 125.24 tokens per second) 0.33.574.066 I slot print_timing: id 0 | task 3088 | total time = 482.47 ms / 403 tokens 0.33.574.067 I slot print_timing: id 0 | task 3088 | graphs reused = 2895 0.33.574.067 I slot print_timing: id 0 | task 3088 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.574.095 I slot release: id 0 | task 3088 | stop processing: n_tokens = 414, truncated = 0 0.33.598.023 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 33482475 0.33.598.071 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 0.33.644.123 I slot launch_slot_: id 0 | task 3138 | processing task, is_child = 0 0.34.124.288 I slot print_timing: id 0 | task 3138 | prompt eval time = 119.45 ms / 362 tokens ( 0.33 ms per token, 3030.66 tokens per second) 0.34.124.294 I slot print_timing: id 0 | task 3138 | eval time = 360.70 ms / 46 tokens ( 8.02 ms per token, 124.76 tokens per second) 0.34.124.295 I slot print_timing: id 0 | task 3138 | total time = 480.15 ms / 408 tokens 0.34.124.296 I slot print_timing: id 0 | task 3138 | graphs reused = 2939 0.34.124.297 I slot print_timing: id 0 | task 3138 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.124.328 I slot release: id 0 | task 3138 | stop processing: n_tokens = 419, truncated = 0 0.34.143.932 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 34032708 0.34.143.986 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.34.187.966 I slot launch_slot_: id 0 | task 3187 | processing task, is_child = 0 0.34.844.367 I slot print_timing: id 0 | task 3187 | prompt eval time = 122.00 ms / 391 tokens ( 0.31 ms per token, 3204.89 tokens per second) 0.34.844.372 I slot print_timing: id 0 | task 3187 | eval time = 534.38 ms / 68 tokens ( 7.98 ms per token, 125.38 tokens per second) 0.34.844.373 I slot print_timing: id 0 | task 3187 | total time = 656.38 ms / 459 tokens 0.34.844.374 I slot print_timing: id 0 | task 3187 | graphs reused = 3005 0.34.844.375 I slot print_timing: id 0 | task 3187 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.844.406 I slot release: id 0 | task 3187 | stop processing: n_tokens = 470, truncated = 0 0.34.861.288 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 34752786 0.34.861.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.34.904.577 I slot launch_slot_: id 0 | task 3258 | processing task, is_child = 0 0.35.440.895 I slot print_timing: id 0 | task 3258 | prompt eval time = 113.33 ms / 343 tokens ( 0.33 ms per token, 3026.53 tokens per second) 0.35.440.900 I slot print_timing: id 0 | task 3258 | eval time = 422.97 ms / 54 tokens ( 7.98 ms per token, 125.30 tokens per second) 0.35.440.901 I slot print_timing: id 0 | task 3258 | total time = 536.30 ms / 397 tokens 0.35.440.902 I slot print_timing: id 0 | task 3258 | graphs reused = 3057 0.35.440.903 I slot print_timing: id 0 | task 3258 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.440.931 I slot release: id 0 | task 3258 | stop processing: n_tokens = 408, truncated = 0 0.35.444.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 35349311 0.35.444.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.35.455.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.35.500.037 I slot launch_slot_: id 0 | task 3315 | processing task, is_child = 0 0.35.981.756 I slot print_timing: id 0 | task 3315 | prompt eval time = 121.57 ms / 401 tokens ( 0.30 ms per token, 3298.57 tokens per second) 0.35.981.762 I slot print_timing: id 0 | task 3315 | eval time = 360.13 ms / 46 tokens ( 8.00 ms per token, 124.95 tokens per second) 0.35.981.763 I slot print_timing: id 0 | task 3315 | total time = 481.70 ms / 447 tokens 0.35.981.764 I slot print_timing: id 0 | task 3315 | graphs reused = 3101 0.35.981.764 I slot print_timing: id 0 | task 3315 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.981.795 I slot release: id 0 | task 3315 | stop processing: n_tokens = 458, truncated = 0 0.36.000.235 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 35890175 0.36.000.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.36.045.917 I slot launch_slot_: id 0 | task 3364 | processing task, is_child = 0 0.36.695.768 I slot print_timing: id 0 | task 3364 | prompt eval time = 114.96 ms / 355 tokens ( 0.32 ms per token, 3087.98 tokens per second) 0.36.695.773 I slot print_timing: id 0 | task 3364 | eval time = 534.87 ms / 68 tokens ( 7.98 ms per token, 125.26 tokens per second) 0.36.695.774 I slot print_timing: id 0 | task 3364 | total time = 649.83 ms / 423 tokens 0.36.695.775 I slot print_timing: id 0 | task 3364 | graphs reused = 3167 0.36.695.776 I slot print_timing: id 0 | task 3364 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.695.805 I slot release: id 0 | task 3364 | stop processing: n_tokens = 434, truncated = 0 0.36.717.283 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 36604185 0.36.717.338 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.36.765.584 I slot launch_slot_: id 0 | task 3435 | processing task, is_child = 0 0.37.362.787 I slot print_timing: id 0 | task 3435 | prompt eval time = 117.71 ms / 351 tokens ( 0.34 ms per token, 2981.83 tokens per second) 0.37.362.794 I slot print_timing: id 0 | task 3435 | eval time = 479.47 ms / 57 tokens ( 8.56 ms per token, 116.80 tokens per second) 0.37.362.795 I slot print_timing: id 0 | task 3435 | total time = 597.18 ms / 408 tokens 0.37.362.796 I slot print_timing: id 0 | task 3435 | graphs reused = 3222 0.37.362.797 I slot print_timing: id 0 | task 3435 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.362.828 I slot release: id 0 | task 3435 | stop processing: n_tokens = 419, truncated = 0 0.37.390.604 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 37271208 0.37.390.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.37.400.881 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.37.441.978 I slot launch_slot_: id 0 | task 3495 | processing task, is_child = 0 0.38.306.766 I slot print_timing: id 0 | task 3495 | prompt eval time = 128.04 ms / 475 tokens ( 0.27 ms per token, 3709.84 tokens per second) 0.38.306.772 I slot print_timing: id 0 | task 3495 | eval time = 736.73 ms / 93 tokens ( 8.01 ms per token, 124.88 tokens per second) 0.38.306.773 I slot print_timing: id 0 | task 3495 | total time = 864.77 ms / 568 tokens 0.38.306.773 I slot print_timing: id 0 | task 3495 | graphs reused = 3312 0.38.306.774 I slot print_timing: id 0 | task 3495 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.306.807 I slot release: id 0 | task 3495 | stop processing: n_tokens = 579, truncated = 0 0.38.335.817 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 38215187 0.38.335.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.824 MiB) 0.38.379.990 I slot launch_slot_: id 0 | task 3591 | processing task, is_child = 0 0.39.348.261 I slot print_timing: id 0 | task 3591 | prompt eval time = 126.95 ms / 440 tokens ( 0.29 ms per token, 3465.82 tokens per second) 0.39.348.268 I slot print_timing: id 0 | task 3591 | eval time = 841.30 ms / 106 tokens ( 8.01 ms per token, 124.81 tokens per second) 0.39.348.269 I slot print_timing: id 0 | task 3591 | total time = 968.25 ms / 546 tokens 0.39.348.270 I slot print_timing: id 0 | task 3591 | graphs reused = 3415 0.39.348.271 I slot print_timing: id 0 | task 3591 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.348.307 I slot release: id 0 | task 3591 | stop processing: n_tokens = 557, truncated = 0 0.39.370.491 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 39256687 0.39.370.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.39.412.187 I slot launch_slot_: id 0 | task 3700 | processing task, is_child = 0 0.39.959.304 I slot print_timing: id 0 | task 3700 | prompt eval time = 114.31 ms / 345 tokens ( 0.33 ms per token, 3018.14 tokens per second) 0.39.959.310 I slot print_timing: id 0 | task 3700 | eval time = 432.79 ms / 55 tokens ( 8.01 ms per token, 124.77 tokens per second) 0.39.959.311 I slot print_timing: id 0 | task 3700 | total time = 547.10 ms / 400 tokens 0.39.959.312 I slot print_timing: id 0 | task 3700 | graphs reused = 3468 0.39.959.312 I slot print_timing: id 0 | task 3700 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.959.340 I slot release: id 0 | task 3700 | stop processing: n_tokens = 411, truncated = 0 0.39.983.594 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 39867720 0.39.983.638 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.39.993.519 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.40.036.178 I slot launch_slot_: id 0 | task 3758 | processing task, is_child = 0 0.40.586.411 I slot print_timing: id 0 | task 3758 | prompt eval time = 119.06 ms / 382 tokens ( 0.31 ms per token, 3208.57 tokens per second) 0.40.586.417 I slot print_timing: id 0 | task 3758 | eval time = 431.16 ms / 55 tokens ( 7.98 ms per token, 125.24 tokens per second) 0.40.586.418 I slot print_timing: id 0 | task 3758 | total time = 550.22 ms / 437 tokens 0.40.586.419 I slot print_timing: id 0 | task 3758 | graphs reused = 3521 0.40.586.420 I slot print_timing: id 0 | task 3758 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.586.451 I slot release: id 0 | task 3758 | stop processing: n_tokens = 448, truncated = 0 0.40.610.451 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 40494830 0.40.610.500 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.40.654.869 I slot launch_slot_: id 0 | task 3816 | processing task, is_child = 0 0.41.123.843 I slot print_timing: id 0 | task 3816 | prompt eval time = 116.96 ms / 337 tokens ( 0.35 ms per token, 2881.43 tokens per second) 0.41.123.849 I slot print_timing: id 0 | task 3816 | eval time = 352.00 ms / 45 tokens ( 8.00 ms per token, 125.00 tokens per second) 0.41.123.850 I slot print_timing: id 0 | task 3816 | total time = 468.95 ms / 382 tokens 0.41.123.850 I slot print_timing: id 0 | task 3816 | graphs reused = 3564 0.41.123.851 I slot print_timing: id 0 | task 3816 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.123.879 I slot release: id 0 | task 3816 | stop processing: n_tokens = 393, truncated = 0 0.41.138.643 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 41032259 0.41.138.691 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.41.179.005 I slot launch_slot_: id 0 | task 3864 | processing task, is_child = 0 0.41.880.212 I slot print_timing: id 0 | task 3864 | prompt eval time = 120.67 ms / 402 tokens ( 0.30 ms per token, 3331.40 tokens per second) 0.41.880.219 I slot print_timing: id 0 | task 3864 | eval time = 580.52 ms / 70 tokens ( 8.41 ms per token, 118.86 tokens per second) 0.41.880.220 I slot print_timing: id 0 | task 3864 | total time = 701.19 ms / 472 tokens 0.41.880.221 I slot print_timing: id 0 | task 3864 | graphs reused = 3632 0.41.880.222 I slot print_timing: id 0 | task 3864 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.880.256 I slot release: id 0 | task 3864 | stop processing: n_tokens = 483, truncated = 0 0.41.905.329 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 41788636 0.41.905.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.41.915.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 168.890 MiB) 0.41.959.056 I slot launch_slot_: id 0 | task 3937 | processing task, is_child = 0 0.42.547.263 I slot print_timing: id 0 | task 3937 | prompt eval time = 141.07 ms / 549 tokens ( 0.26 ms per token, 3891.60 tokens per second) 0.42.547.269 I slot print_timing: id 0 | task 3937 | eval time = 447.12 ms / 57 tokens ( 7.98 ms per token, 125.25 tokens per second) 0.42.547.270 I slot print_timing: id 0 | task 3937 | total time = 588.19 ms / 606 tokens 0.42.547.271 I slot print_timing: id 0 | task 3937 | graphs reused = 3687 0.42.547.272 I slot print_timing: id 0 | task 3937 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.547.304 I slot release: id 0 | task 3937 | stop processing: n_tokens = 617, truncated = 0 0.42.551.912 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 42455684 0.42.551.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.42.605.514 I slot launch_slot_: id 0 | task 3998 | processing task, is_child = 0 0.43.216.837 I slot print_timing: id 0 | task 3998 | prompt eval time = 156.31 ms / 616 tokens ( 0.25 ms per token, 3940.94 tokens per second) 0.43.216.842 I slot print_timing: id 0 | task 3998 | eval time = 454.99 ms / 58 tokens ( 7.98 ms per token, 125.28 tokens per second) 0.43.216.843 I slot print_timing: id 0 | task 3998 | total time = 611.30 ms / 674 tokens 0.43.216.844 I slot print_timing: id 0 | task 3998 | graphs reused = 3743 0.43.216.845 I slot print_timing: id 0 | task 3998 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.216.879 I slot release: id 0 | task 3998 | stop processing: n_tokens = 685, truncated = 0 0.43.246.194 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 43125259 0.43.246.257 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.917 MiB) 0.43.256.311 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.43.307.236 I slot launch_slot_: id 0 | task 4060 | processing task, is_child = 0 0.43.949.051 I slot print_timing: id 0 | task 4060 | prompt eval time = 162.23 ms / 665 tokens ( 0.24 ms per token, 4099.02 tokens per second) 0.43.949.056 I slot print_timing: id 0 | task 4060 | eval time = 479.56 ms / 61 tokens ( 7.99 ms per token, 125.11 tokens per second) 0.43.949.058 I slot print_timing: id 0 | task 4060 | total time = 641.79 ms / 726 tokens 0.43.949.058 I slot print_timing: id 0 | task 4060 | graphs reused = 3802 0.43.949.059 I slot print_timing: id 0 | task 4060 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.949.098 I slot release: id 0 | task 4060 | stop processing: n_tokens = 737, truncated = 0 0.43.974.646 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 43857477 0.43.974.710 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.43.984.791 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.44.040.249 I slot launch_slot_: id 0 | task 4125 | processing task, is_child = 0 0.44.631.316 I slot print_timing: id 0 | task 4125 | prompt eval time = 159.09 ms / 645 tokens ( 0.25 ms per token, 4054.36 tokens per second) 0.44.631.321 I slot print_timing: id 0 | task 4125 | eval time = 431.96 ms / 55 tokens ( 8.00 ms per token, 125.01 tokens per second) 0.44.631.322 I slot print_timing: id 0 | task 4125 | total time = 591.05 ms / 700 tokens 0.44.631.323 I slot print_timing: id 0 | task 4125 | graphs reused = 3855 0.44.631.324 I slot print_timing: id 0 | task 4125 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.631.358 I slot release: id 0 | task 4125 | stop processing: n_tokens = 711, truncated = 0 0.44.659.242 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 44539738 0.44.659.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 0.44.728.282 I slot launch_slot_: id 0 | task 4184 | processing task, is_child = 0 0.45.279.954 I slot print_timing: id 0 | task 4184 | prompt eval time = 138.69 ms / 474 tokens ( 0.29 ms per token, 3417.82 tokens per second) 0.45.279.959 I slot print_timing: id 0 | task 4184 | eval time = 412.96 ms / 52 tokens ( 8.10 ms per token, 123.50 tokens per second) 0.45.279.960 I slot print_timing: id 0 | task 4184 | total time = 551.65 ms / 526 tokens 0.45.279.961 I slot print_timing: id 0 | task 4184 | graphs reused = 3904 0.45.279.962 I slot print_timing: id 0 | task 4184 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.279.992 I slot release: id 0 | task 4184 | stop processing: n_tokens = 537, truncated = 0 0.45.297.554 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 45188372 0.45.297.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.45.307.811 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.013 MiB) 0.45.351.943 I slot launch_slot_: id 0 | task 4239 | processing task, is_child = 0 0.45.831.990 I slot print_timing: id 0 | task 4239 | prompt eval time = 151.20 ms / 617 tokens ( 0.25 ms per token, 4080.61 tokens per second) 0.45.831.996 I slot print_timing: id 0 | task 4239 | eval time = 328.83 ms / 42 tokens ( 8.02 ms per token, 124.69 tokens per second) 0.45.831.997 I slot print_timing: id 0 | task 4239 | total time = 480.03 ms / 659 tokens 0.45.831.998 I slot print_timing: id 0 | task 4239 | graphs reused = 3944 0.45.831.998 I slot print_timing: id 0 | task 4239 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.832.036 I slot release: id 0 | task 4239 | stop processing: n_tokens = 670, truncated = 0 0.45.859.746 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 45740416 0.45.859.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 0.45.910.545 I slot launch_slot_: id 0 | task 4285 | processing task, is_child = 0 0.46.438.153 I slot print_timing: id 0 | task 4285 | prompt eval time = 151.33 ms / 601 tokens ( 0.25 ms per token, 3971.56 tokens per second) 0.46.438.159 I slot print_timing: id 0 | task 4285 | eval time = 376.26 ms / 48 tokens ( 8.01 ms per token, 124.91 tokens per second) 0.46.438.159 I slot print_timing: id 0 | task 4285 | total time = 527.59 ms / 649 tokens 0.46.438.160 I slot print_timing: id 0 | task 4285 | graphs reused = 3990 0.46.438.161 I slot print_timing: id 0 | task 4285 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.438.196 I slot release: id 0 | task 4285 | stop processing: n_tokens = 660, truncated = 0 0.46.452.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 46346575 0.46.452.164 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 0.46.462.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.46.516.685 I slot launch_slot_: id 0 | task 4337 | processing task, is_child = 0 0.47.030.811 I slot print_timing: id 0 | task 4337 | prompt eval time = 143.80 ms / 533 tokens ( 0.27 ms per token, 3706.64 tokens per second) 0.47.030.817 I slot print_timing: id 0 | task 4337 | eval time = 370.31 ms / 47 tokens ( 8.05 ms per token, 124.22 tokens per second) 0.47.030.818 I slot print_timing: id 0 | task 4337 | total time = 514.11 ms / 580 tokens 0.47.030.819 I slot print_timing: id 0 | task 4337 | graphs reused = 4035 0.47.030.819 I slot print_timing: id 0 | task 4337 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.030.853 I slot release: id 0 | task 4337 | stop processing: n_tokens = 591, truncated = 0 0.47.060.109 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 46939232 0.47.060.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 0.47.108.568 I slot launch_slot_: id 0 | task 4388 | processing task, is_child = 0 0.47.654.934 I slot print_timing: id 0 | task 4388 | prompt eval time = 133.01 ms / 480 tokens ( 0.28 ms per token, 3608.67 tokens per second) 0.47.654.940 I slot print_timing: id 0 | task 4388 | eval time = 413.33 ms / 52 tokens ( 8.10 ms per token, 123.39 tokens per second) 0.47.654.941 I slot print_timing: id 0 | task 4388 | total time = 546.35 ms / 532 tokens 0.47.654.941 I slot print_timing: id 0 | task 4388 | graphs reused = 4084 0.47.654.942 I slot print_timing: id 0 | task 4388 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.654.980 I slot release: id 0 | task 4388 | stop processing: n_tokens = 560, truncated = 0 0.47.668.906 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 47563360 0.47.668.960 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 0.47.679.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.47.737.780 I slot launch_slot_: id 0 | task 4443 | processing task, is_child = 0 0.48.214.880 I slot print_timing: id 0 | task 4443 | prompt eval time = 146.82 ms / 567 tokens ( 0.26 ms per token, 3861.82 tokens per second) 0.48.214.886 I slot print_timing: id 0 | task 4443 | eval time = 330.25 ms / 42 tokens ( 8.05 ms per token, 124.15 tokens per second) 0.48.214.888 I slot print_timing: id 0 | task 4443 | total time = 477.08 ms / 609 tokens 0.48.214.889 I slot print_timing: id 0 | task 4443 | graphs reused = 4124 0.48.214.890 I slot print_timing: id 0 | task 4443 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.214.925 I slot release: id 0 | task 4443 | stop processing: n_tokens = 637, truncated = 0 0.48.232.086 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 48123305 0.48.232.140 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 0.48.242.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 0.48.301.697 I slot launch_slot_: id 0 | task 4489 | processing task, is_child = 0 0.48.936.216 I slot print_timing: id 0 | task 4489 | prompt eval time = 138.10 ms / 506 tokens ( 0.27 ms per token, 3663.96 tokens per second) 0.48.936.222 I slot print_timing: id 0 | task 4489 | eval time = 496.40 ms / 63 tokens ( 8.01 ms per token, 124.90 tokens per second) 0.48.936.223 I slot print_timing: id 0 | task 4489 | total time = 634.50 ms / 569 tokens 0.48.936.224 I slot print_timing: id 0 | task 4489 | graphs reused = 4185 0.48.936.224 I slot print_timing: id 0 | task 4489 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.936.257 I slot release: id 0 | task 4489 | stop processing: n_tokens = 597, truncated = 0 0.48.950.186 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 48844637 0.48.950.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 0.48.960.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 0.49.011.074 I slot launch_slot_: id 0 | task 4555 | processing task, is_child = 0 0.49.450.619 I slot print_timing: id 0 | task 4555 | prompt eval time = 126.82 ms / 436 tokens ( 0.29 ms per token, 3437.84 tokens per second) 0.49.450.625 I slot print_timing: id 0 | task 4555 | eval time = 312.70 ms / 40 tokens ( 8.02 ms per token, 124.72 tokens per second) 0.49.450.626 I slot print_timing: id 0 | task 4555 | total time = 439.53 ms / 476 tokens 0.49.450.627 I slot print_timing: id 0 | task 4555 | graphs reused = 4223 0.49.450.628 I slot print_timing: id 0 | task 4555 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.450.656 I slot release: id 0 | task 4555 | stop processing: n_tokens = 504, truncated = 0 0.49.465.846 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 49359036 0.49.465.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 0.49.519.914 I slot launch_slot_: id 0 | task 4598 | processing task, is_child = 0 0.50.146.895 I slot print_timing: id 0 | task 4598 | prompt eval time = 139.67 ms / 519 tokens ( 0.27 ms per token, 3716.01 tokens per second) 0.50.146.901 I slot print_timing: id 0 | task 4598 | eval time = 487.30 ms / 62 tokens ( 7.99 ms per token, 125.18 tokens per second) 0.50.146.902 I slot print_timing: id 0 | task 4598 | total time = 626.96 ms / 581 tokens 0.50.146.902 I slot print_timing: id 0 | task 4598 | graphs reused = 4283 0.50.146.903 I slot print_timing: id 0 | task 4598 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.146.937 I slot release: id 0 | task 4598 | stop processing: n_tokens = 609, truncated = 0 0.50.164.297 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 50055317 0.50.164.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.697 MiB) 0.50.174.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.042 MiB) 0.50.230.925 I slot launch_slot_: id 0 | task 4664 | processing task, is_child = 0 0.50.723.913 I slot print_timing: id 0 | task 4664 | prompt eval time = 127.89 ms / 465 tokens ( 0.28 ms per token, 3635.97 tokens per second) 0.50.723.919 I slot print_timing: id 0 | task 4664 | eval time = 365.08 ms / 46 tokens ( 8.11 ms per token, 123.26 tokens per second) 0.50.723.920 I slot print_timing: id 0 | task 4664 | total time = 492.97 ms / 511 tokens 0.50.723.921 I slot print_timing: id 0 | task 4664 | graphs reused = 4326 0.50.723.921 I slot print_timing: id 0 | task 4664 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.723.955 I slot release: id 0 | task 4664 | stop processing: n_tokens = 542, truncated = 0 0.50.740.098 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 50632335 0.50.740.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 0.50.751.342 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 0.50.816.328 I slot launch_slot_: id 0 | task 4713 | processing task, is_child = 0 0.51.265.471 I slot print_timing: id 0 | task 4713 | prompt eval time = 129.48 ms / 431 tokens ( 0.30 ms per token, 3328.65 tokens per second) 0.51.265.477 I slot print_timing: id 0 | task 4713 | eval time = 319.64 ms / 41 tokens ( 7.99 ms per token, 125.14 tokens per second) 0.51.265.478 I slot print_timing: id 0 | task 4713 | total time = 449.12 ms / 472 tokens 0.51.265.479 I slot print_timing: id 0 | task 4713 | graphs reused = 4365 0.51.265.480 I slot print_timing: id 0 | task 4713 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.265.511 I slot release: id 0 | task 4713 | stop processing: n_tokens = 503, truncated = 0 0.51.288.692 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 51173891 0.51.288.736 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 0.51.298.787 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 0.51.358.166 I slot launch_slot_: id 0 | task 4757 | processing task, is_child = 0 0.51.834.379 I slot print_timing: id 0 | task 4757 | prompt eval time = 127.27 ms / 457 tokens ( 0.28 ms per token, 3590.76 tokens per second) 0.51.834.385 I slot print_timing: id 0 | task 4757 | eval time = 348.93 ms / 44 tokens ( 8.11 ms per token, 123.24 tokens per second) 0.51.834.387 I slot print_timing: id 0 | task 4757 | total time = 476.20 ms / 501 tokens 0.51.834.387 I slot print_timing: id 0 | task 4757 | graphs reused = 4406 0.51.834.388 I slot print_timing: id 0 | task 4757 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.834.421 I slot release: id 0 | task 4757 | stop processing: n_tokens = 532, truncated = 0 0.51.861.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 51742801 0.51.861.230 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 0.51.920.818 I slot launch_slot_: id 0 | task 4804 | processing task, is_child = 0 0.52.376.367 I slot print_timing: id 0 | task 4804 | prompt eval time = 127.06 ms / 439 tokens ( 0.29 ms per token, 3455.09 tokens per second) 0.52.376.373 I slot print_timing: id 0 | task 4804 | eval time = 328.47 ms / 42 tokens ( 8.01 ms per token, 124.82 tokens per second) 0.52.376.374 I slot print_timing: id 0 | task 4804 | total time = 455.53 ms / 481 tokens 0.52.376.374 I slot print_timing: id 0 | task 4804 | graphs reused = 4446 0.52.376.375 I slot print_timing: id 0 | task 4804 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.376.407 I slot release: id 0 | task 4804 | stop processing: n_tokens = 512, truncated = 0 0.52.404.083 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 52284787 0.52.404.136 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 0.52.417.286 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 0.52.485.712 I slot launch_slot_: id 0 | task 4849 | processing task, is_child = 0 0.53.103.791 I slot print_timing: id 0 | task 4849 | prompt eval time = 154.08 ms / 606 tokens ( 0.25 ms per token, 3932.95 tokens per second) 0.53.103.797 I slot print_timing: id 0 | task 4849 | eval time = 463.97 ms / 56 tokens ( 8.44 ms per token, 118.54 tokens per second) 0.53.103.798 I slot print_timing: id 0 | task 4849 | total time = 618.05 ms / 662 tokens 0.53.103.800 I slot print_timing: id 0 | task 4849 | graphs reused = 4500 0.53.103.801 I slot print_timing: id 0 | task 4849 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.103.844 I slot release: id 0 | task 4849 | stop processing: n_tokens = 693, truncated = 0 0.53.132.680 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 53012224 0.53.132.744 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.827 MiB) 0.53.146.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 0.53.215.492 I slot launch_slot_: id 0 | task 4909 | processing task, is_child = 0 0.53.691.766 I slot print_timing: id 0 | task 4909 | prompt eval time = 137.39 ms / 477 tokens ( 0.29 ms per token, 3471.79 tokens per second) 0.53.691.771 I slot print_timing: id 0 | task 4909 | eval time = 338.86 ms / 41 tokens ( 8.47 ms per token, 118.04 tokens per second) 0.53.691.772 I slot print_timing: id 0 | task 4909 | total time = 476.25 ms / 518 tokens 0.53.691.773 I slot print_timing: id 0 | task 4909 | graphs reused = 4538 0.53.691.774 I slot print_timing: id 0 | task 4909 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.691.807 I slot release: id 0 | task 4909 | stop processing: n_tokens = 549, truncated = 0 0.53.697.255 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 53600187 0.53.697.310 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 0.53.787.580 I slot launch_slot_: id 0 | task 4953 | processing task, is_child = 0 0.54.444.447 I slot print_timing: id 0 | task 4953 | prompt eval time = 183.12 ms / 845 tokens ( 0.22 ms per token, 4614.44 tokens per second) 0.54.444.452 I slot print_timing: id 0 | task 4953 | eval time = 473.72 ms / 60 tokens ( 8.03 ms per token, 124.55 tokens per second) 0.54.444.453 I slot print_timing: id 0 | task 4953 | total time = 656.85 ms / 905 tokens 0.54.444.454 I slot print_timing: id 0 | task 4953 | graphs reused = 4596 0.54.444.455 I slot print_timing: id 0 | task 4953 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.444.504 I slot release: id 0 | task 4953 | stop processing: n_tokens = 936, truncated = 0 0.54.461.689 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 54352884 0.54.461.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 0.54.474.791 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 0.54.542.564 I slot launch_slot_: id 0 | task 5017 | processing task, is_child = 0 0.55.031.386 I slot print_timing: id 0 | task 5017 | prompt eval time = 133.50 ms / 459 tokens ( 0.29 ms per token, 3438.31 tokens per second) 0.55.031.392 I slot print_timing: id 0 | task 5017 | eval time = 355.31 ms / 43 tokens ( 8.46 ms per token, 118.21 tokens per second) 0.55.031.393 I slot print_timing: id 0 | task 5017 | total time = 488.80 ms / 502 tokens 0.55.031.393 I slot print_timing: id 0 | task 5017 | graphs reused = 4636 0.55.031.395 I slot print_timing: id 0 | task 5017 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.031.428 I slot release: id 0 | task 5017 | stop processing: n_tokens = 533, truncated = 0 0.55.060.662 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 54939808 0.55.060.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 0.55.117.729 I slot launch_slot_: id 0 | task 5063 | processing task, is_child = 0 0.55.668.755 I slot print_timing: id 0 | task 5063 | prompt eval time = 167.56 ms / 670 tokens ( 0.25 ms per token, 3998.69 tokens per second) 0.55.668.761 I slot print_timing: id 0 | task 5063 | eval time = 383.45 ms / 47 tokens ( 8.34 ms per token, 119.96 tokens per second) 0.55.668.762 I slot print_timing: id 0 | task 5063 | total time = 551.01 ms / 717 tokens 0.55.668.763 I slot print_timing: id 0 | task 5063 | graphs reused = 4681 0.55.668.763 I slot print_timing: id 0 | task 5063 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.668.804 I slot release: id 0 | task 5063 | stop processing: n_tokens = 748, truncated = 0 0.55.687.098 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 55577184 0.55.687.162 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 0.55.700.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 0.55.787.871 I slot launch_slot_: id 0 | task 5114 | processing task, is_child = 0 0.56.516.137 I slot print_timing: id 0 | task 5114 | prompt eval time = 183.07 ms / 775 tokens ( 0.24 ms per token, 4233.45 tokens per second) 0.56.516.143 I slot print_timing: id 0 | task 5114 | eval time = 545.18 ms / 63 tokens ( 8.79 ms per token, 113.72 tokens per second) 0.56.516.144 I slot print_timing: id 0 | task 5114 | total time = 728.24 ms / 838 tokens 0.56.516.144 I slot print_timing: id 0 | task 5114 | graphs reused = 4742 0.56.516.145 I slot print_timing: id 0 | task 5114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.516.190 I slot release: id 0 | task 5114 | stop processing: n_tokens = 869, truncated = 0 0.56.545.061 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 56424570 0.56.545.122 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 0.56.558.537 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 0.56.627.692 I slot launch_slot_: id 0 | task 5181 | processing task, is_child = 0 0.57.355.020 I slot print_timing: id 0 | task 5181 | prompt eval time = 153.88 ms / 573 tokens ( 0.27 ms per token, 3723.70 tokens per second) 0.57.355.025 I slot print_timing: id 0 | task 5181 | eval time = 573.43 ms / 71 tokens ( 8.19 ms per token, 122.07 tokens per second) 0.57.355.027 I slot print_timing: id 0 | task 5181 | total time = 727.31 ms / 644 tokens 0.57.355.027 I slot print_timing: id 0 | task 5181 | graphs reused = 4811 0.57.355.028 I slot print_timing: id 0 | task 5181 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.355.065 I slot release: id 0 | task 5181 | stop processing: n_tokens = 675, truncated = 0 0.57.384.210 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 57263445 0.57.384.261 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.422 MiB) 0.57.397.751 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 0.57.464.364 I slot launch_slot_: id 0 | task 5256 | processing task, is_child = 0 0.58.081.716 I slot print_timing: id 0 | task 5256 | prompt eval time = 131.34 ms / 461 tokens ( 0.28 ms per token, 3510.11 tokens per second) 0.58.081.722 I slot print_timing: id 0 | task 5256 | eval time = 486.00 ms / 61 tokens ( 8.10 ms per token, 123.46 tokens per second) 0.58.081.723 I slot print_timing: id 0 | task 5256 | total time = 617.33 ms / 522 tokens 0.58.081.724 I slot print_timing: id 0 | task 5256 | graphs reused = 4869 0.58.081.725 I slot print_timing: id 0 | task 5256 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.081.760 I slot release: id 0 | task 5256 | stop processing: n_tokens = 553, truncated = 0 0.58.100.684 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 553, t_last = 57990140 0.58.100.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 0.58.167.503 I slot launch_slot_: id 0 | task 5320 | processing task, is_child = 0 0.59.385.606 I slot print_timing: id 0 | task 5320 | prompt eval time = 147.66 ms / 609 tokens ( 0.24 ms per token, 4124.23 tokens per second) 0.59.385.612 I slot print_timing: id 0 | task 5320 | eval time = 1070.42 ms / 130 tokens ( 8.30 ms per token, 120.51 tokens per second) 0.59.385.613 I slot print_timing: id 0 | task 5320 | total time = 1218.08 ms / 739 tokens 0.59.385.614 I slot print_timing: id 0 | task 5320 | graphs reused = 4996 0.59.385.615 I slot print_timing: id 0 | task 5320 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.385.652 I slot release: id 0 | task 5320 | stop processing: n_tokens = 770, truncated = 0 0.59.413.647 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 59294032 0.59.413.708 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 0.59.426.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 0.59.492.690 I slot launch_slot_: id 0 | task 5454 | processing task, is_child = 0 1.00.158.070 I slot print_timing: id 0 | task 5454 | prompt eval time = 177.13 ms / 791 tokens ( 0.22 ms per token, 4465.55 tokens per second) 1.00.158.075 I slot print_timing: id 0 | task 5454 | eval time = 488.22 ms / 61 tokens ( 8.14 ms per token, 122.89 tokens per second) 1.00.158.076 I slot print_timing: id 0 | task 5454 | total time = 665.36 ms / 852 tokens 1.00.158.077 I slot print_timing: id 0 | task 5454 | graphs reused = 5055 1.00.158.078 I slot print_timing: id 0 | task 5454 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.158.122 I slot release: id 0 | task 5454 | stop processing: n_tokens = 883, truncated = 0 1.00.183.229 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 60066502 1.00.183.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 1.00.288.478 I slot launch_slot_: id 0 | task 5519 | processing task, is_child = 0 1.00.883.598 I slot print_timing: id 0 | task 5519 | prompt eval time = 142.41 ms / 533 tokens ( 0.27 ms per token, 3742.58 tokens per second) 1.00.883.604 I slot print_timing: id 0 | task 5519 | eval time = 452.69 ms / 56 tokens ( 8.23 ms per token, 121.50 tokens per second) 1.00.883.605 I slot print_timing: id 0 | task 5519 | total time = 595.10 ms / 589 tokens 1.00.883.606 I slot print_timing: id 0 | task 5519 | graphs reused = 5109 1.00.883.606 I slot print_timing: id 0 | task 5519 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.883.641 I slot release: id 0 | task 5519 | stop processing: n_tokens = 677, truncated = 0 1.00.904.240 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 60792021 1.00.904.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 1.00.983.000 I slot launch_slot_: id 0 | task 5579 | processing task, is_child = 0 1.01.548.718 I slot print_timing: id 0 | task 5579 | prompt eval time = 153.60 ms / 566 tokens ( 0.27 ms per token, 3684.94 tokens per second) 1.01.548.724 I slot print_timing: id 0 | task 5579 | eval time = 412.10 ms / 46 tokens ( 9.16 ms per token, 109.20 tokens per second) 1.01.548.725 I slot print_timing: id 0 | task 5579 | total time = 565.70 ms / 612 tokens 1.01.548.726 I slot print_timing: id 0 | task 5579 | graphs reused = 5153 1.01.548.727 I slot print_timing: id 0 | task 5579 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.548.763 I slot release: id 0 | task 5579 | stop processing: n_tokens = 643, truncated = 0 1.01.552.974 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 61457143 1.01.553.029 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.301 MiB) 1.01.642.291 I slot launch_slot_: id 0 | task 5629 | processing task, is_child = 0 1.02.128.982 I slot print_timing: id 0 | task 5629 | prompt eval time = 136.37 ms / 443 tokens ( 0.31 ms per token, 3248.52 tokens per second) 1.02.128.987 I slot print_timing: id 0 | task 5629 | eval time = 350.30 ms / 43 tokens ( 8.34 ms per token, 119.90 tokens per second) 1.02.128.988 I slot print_timing: id 0 | task 5629 | total time = 486.67 ms / 486 tokens 1.02.128.989 I slot print_timing: id 0 | task 5629 | graphs reused = 5193 1.02.128.990 I slot print_timing: id 0 | task 5629 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.129.021 I slot release: id 0 | task 5629 | stop processing: n_tokens = 517, truncated = 0 1.02.150.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 62037401 1.02.150.446 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.02.214.070 I slot launch_slot_: id 0 | task 5675 | processing task, is_child = 0 1.02.866.818 I slot print_timing: id 0 | task 5675 | prompt eval time = 129.81 ms / 487 tokens ( 0.27 ms per token, 3751.55 tokens per second) 1.02.866.824 I slot print_timing: id 0 | task 5675 | eval time = 522.92 ms / 65 tokens ( 8.17 ms per token, 122.39 tokens per second) 1.02.866.825 I slot print_timing: id 0 | task 5675 | total time = 652.73 ms / 552 tokens 1.02.866.826 I slot print_timing: id 0 | task 5675 | graphs reused = 5256 1.02.866.826 I slot print_timing: id 0 | task 5675 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.866.859 I slot release: id 0 | task 5675 | stop processing: n_tokens = 583, truncated = 0 1.02.883.948 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 62775239 1.02.884.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 1.02.945.597 I slot launch_slot_: id 0 | task 5743 | processing task, is_child = 0 1.03.449.924 I slot print_timing: id 0 | task 5743 | prompt eval time = 135.24 ms / 507 tokens ( 0.27 ms per token, 3748.95 tokens per second) 1.03.449.931 I slot print_timing: id 0 | task 5743 | eval time = 369.07 ms / 47 tokens ( 8.02 ms per token, 124.64 tokens per second) 1.03.449.931 I slot print_timing: id 0 | task 5743 | total time = 504.31 ms / 554 tokens 1.03.449.932 I slot print_timing: id 0 | task 5743 | graphs reused = 5301 1.03.449.933 I slot print_timing: id 0 | task 5743 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.449.966 I slot release: id 0 | task 5743 | stop processing: n_tokens = 585, truncated = 0 1.03.477.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 63358346 1.03.477.689 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 1.03.494.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 1.03.577.313 I slot launch_slot_: id 0 | task 5793 | processing task, is_child = 0 1.04.259.011 I slot print_timing: id 0 | task 5793 | prompt eval time = 153.14 ms / 633 tokens ( 0.24 ms per token, 4133.47 tokens per second) 1.04.259.017 I slot print_timing: id 0 | task 5793 | eval time = 528.54 ms / 66 tokens ( 8.13 ms per token, 122.98 tokens per second) 1.04.259.018 I slot print_timing: id 0 | task 5793 | total time = 681.68 ms / 699 tokens 1.04.259.019 I slot print_timing: id 0 | task 5793 | graphs reused = 5365 1.04.259.020 I slot print_timing: id 0 | task 5793 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.259.061 I slot release: id 0 | task 5793 | stop processing: n_tokens = 730, truncated = 0 1.04.273.274 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 64167441 1.04.273.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.04.344.348 I slot launch_slot_: id 0 | task 5863 | processing task, is_child = 0 1.04.969.039 I slot print_timing: id 0 | task 5863 | prompt eval time = 150.40 ms / 571 tokens ( 0.26 ms per token, 3796.67 tokens per second) 1.04.969.045 I slot print_timing: id 0 | task 5863 | eval time = 474.28 ms / 59 tokens ( 8.18 ms per token, 122.29 tokens per second) 1.04.969.046 I slot print_timing: id 0 | task 5863 | total time = 624.67 ms / 630 tokens 1.04.969.047 I slot print_timing: id 0 | task 5863 | graphs reused = 5422 1.04.969.047 I slot print_timing: id 0 | task 5863 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.969.083 I slot release: id 0 | task 5863 | stop processing: n_tokens = 661, truncated = 0 1.04.987.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 64877463 1.04.987.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.05.059.185 I slot launch_slot_: id 0 | task 5926 | processing task, is_child = 0 1.05.592.600 I slot print_timing: id 0 | task 5926 | prompt eval time = 182.00 ms / 798 tokens ( 0.23 ms per token, 4384.57 tokens per second) 1.05.592.606 I slot print_timing: id 0 | task 5926 | eval time = 351.39 ms / 44 tokens ( 8.17 ms per token, 122.37 tokens per second) 1.05.592.607 I slot print_timing: id 0 | task 5926 | total time = 533.40 ms / 842 tokens 1.05.592.608 I slot print_timing: id 0 | task 5926 | graphs reused = 5464 1.05.592.609 I slot print_timing: id 0 | task 5926 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.592.651 I slot release: id 0 | task 5926 | stop processing: n_tokens = 873, truncated = 0 1.05.609.701 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 65501030 1.05.609.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.05.629.241 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 1.05.726.333 I slot launch_slot_: id 0 | task 5974 | processing task, is_child = 0 1.06.229.336 I slot print_timing: id 0 | task 5974 | prompt eval time = 156.01 ms / 572 tokens ( 0.27 ms per token, 3666.48 tokens per second) 1.06.229.342 I slot print_timing: id 0 | task 5974 | eval time = 346.97 ms / 43 tokens ( 8.26 ms per token, 121.05 tokens per second) 1.06.229.343 I slot print_timing: id 0 | task 5974 | total time = 502.98 ms / 615 tokens 1.06.229.344 I slot print_timing: id 0 | task 5974 | graphs reused = 5505 1.06.229.345 I slot print_timing: id 0 | task 5974 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.229.380 I slot release: id 0 | task 5974 | stop processing: n_tokens = 646, truncated = 0 1.06.246.443 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 66137760 1.06.246.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.06.316.238 I slot launch_slot_: id 0 | task 6021 | processing task, is_child = 0 1.06.983.884 I slot print_timing: id 0 | task 6021 | prompt eval time = 153.40 ms / 613 tokens ( 0.25 ms per token, 3996.19 tokens per second) 1.06.983.890 I slot print_timing: id 0 | task 6021 | eval time = 514.23 ms / 64 tokens ( 8.16 ms per token, 122.51 tokens per second) 1.06.983.891 I slot print_timing: id 0 | task 6021 | total time = 667.63 ms / 677 tokens 1.06.983.892 I slot print_timing: id 0 | task 6021 | graphs reused = 5567 1.06.983.893 I slot print_timing: id 0 | task 6021 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.983.932 I slot release: id 0 | task 6021 | stop processing: n_tokens = 708, truncated = 0 1.06.988.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 708, t_last = 66892312 1.06.988.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.07.067.877 I slot launch_slot_: id 0 | task 6089 | processing task, is_child = 0 1.07.719.843 I slot print_timing: id 0 | task 6089 | prompt eval time = 146.58 ms / 580 tokens ( 0.25 ms per token, 3956.86 tokens per second) 1.07.719.849 I slot print_timing: id 0 | task 6089 | eval time = 505.37 ms / 64 tokens ( 8.02 ms per token, 124.66 tokens per second) 1.07.719.850 I slot print_timing: id 0 | task 6089 | total time = 651.95 ms / 644 tokens 1.07.719.851 I slot print_timing: id 0 | task 6089 | graphs reused = 5629 1.07.719.852 I slot print_timing: id 0 | task 6089 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.719.893 I slot release: id 0 | task 6089 | stop processing: n_tokens = 675, truncated = 0 1.07.735.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 67628273 1.07.735.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.07.825.055 I slot launch_slot_: id 0 | task 6157 | processing task, is_child = 0 1.08.401.942 I slot print_timing: id 0 | task 6157 | prompt eval time = 169.75 ms / 716 tokens ( 0.24 ms per token, 4217.97 tokens per second) 1.08.401.947 I slot print_timing: id 0 | task 6157 | eval time = 407.12 ms / 50 tokens ( 8.31 ms per token, 120.36 tokens per second) 1.08.401.948 I slot print_timing: id 0 | task 6157 | total time = 576.87 ms / 766 tokens 1.08.401.949 I slot print_timing: id 0 | task 6157 | graphs reused = 5676 1.08.401.950 I slot print_timing: id 0 | task 6157 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.401.991 I slot release: id 0 | task 6157 | stop processing: n_tokens = 797, truncated = 0 1.08.427.097 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 68310371 1.08.427.163 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.08.446.931 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.08.522.381 I slot launch_slot_: id 0 | task 6211 | processing task, is_child = 0 1.09.538.058 I slot print_timing: id 0 | task 6211 | prompt eval time = 192.51 ms / 799 tokens ( 0.24 ms per token, 4150.50 tokens per second) 1.09.538.064 I slot print_timing: id 0 | task 6211 | eval time = 823.15 ms / 102 tokens ( 8.15 ms per token, 122.70 tokens per second) 1.09.538.065 I slot print_timing: id 0 | task 6211 | total time = 1015.66 ms / 901 tokens 1.09.538.066 I slot print_timing: id 0 | task 6211 | graphs reused = 5776 1.09.538.066 I slot print_timing: id 0 | task 6211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.538.109 I slot release: id 0 | task 6211 | stop processing: n_tokens = 932, truncated = 0 1.09.560.907 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 69446488 1.09.560.975 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 1.09.636.759 I slot launch_slot_: id 0 | task 6317 | processing task, is_child = 0 1.10.660.381 I slot print_timing: id 0 | task 6317 | prompt eval time = 121.08 ms / 361 tokens ( 0.34 ms per token, 2981.52 tokens per second) 1.10.660.387 I slot print_timing: id 0 | task 6317 | eval time = 902.52 ms / 112 tokens ( 8.13 ms per token, 122.99 tokens per second) 1.10.660.388 I slot print_timing: id 0 | task 6317 | total time = 1023.60 ms / 473 tokens 1.10.660.390 I slot print_timing: id 0 | task 6317 | graphs reused = 5886 1.10.660.391 I slot print_timing: id 0 | task 6317 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.660.420 I slot release: id 0 | task 6317 | stop processing: n_tokens = 504, truncated = 0 1.10.683.323 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 70568800 1.10.683.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.10.757.294 I slot launch_slot_: id 0 | task 6432 | processing task, is_child = 0 1.11.736.339 I slot print_timing: id 0 | task 6432 | prompt eval time = 121.13 ms / 381 tokens ( 0.32 ms per token, 3145.30 tokens per second) 1.11.736.344 I slot print_timing: id 0 | task 6432 | eval time = 857.89 ms / 108 tokens ( 8.02 ms per token, 124.72 tokens per second) 1.11.736.345 I slot print_timing: id 0 | task 6432 | total time = 979.03 ms / 489 tokens 1.11.736.346 I slot print_timing: id 0 | task 6432 | graphs reused = 5991 1.11.736.347 I slot print_timing: id 0 | task 6432 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.736.378 I slot release: id 0 | task 6432 | stop processing: n_tokens = 520, truncated = 0 1.11.760.715 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 71644758 1.11.760.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.11.827.122 I slot launch_slot_: id 0 | task 6543 | processing task, is_child = 0 1.12.952.174 I slot print_timing: id 0 | task 6543 | prompt eval time = 116.69 ms / 365 tokens ( 0.32 ms per token, 3127.87 tokens per second) 1.12.952.180 I slot print_timing: id 0 | task 6543 | eval time = 1008.34 ms / 124 tokens ( 8.20 ms per token, 121.98 tokens per second) 1.12.952.181 I slot print_timing: id 0 | task 6543 | total time = 1125.03 ms / 489 tokens 1.12.952.182 I slot print_timing: id 0 | task 6543 | graphs reused = 6112 1.12.952.183 I slot print_timing: id 0 | task 6543 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.952.215 I slot release: id 0 | task 6543 | stop processing: n_tokens = 520, truncated = 0 1.12.978.885 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 72860594 1.12.978.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.13.054.531 I slot launch_slot_: id 0 | task 6670 | processing task, is_child = 0 1.14.031.349 I slot print_timing: id 0 | task 6670 | prompt eval time = 118.59 ms / 333 tokens ( 0.36 ms per token, 2808.09 tokens per second) 1.14.031.355 I slot print_timing: id 0 | task 6670 | eval time = 858.21 ms / 107 tokens ( 8.10 ms per token, 123.51 tokens per second) 1.14.031.356 I slot print_timing: id 0 | task 6670 | total time = 976.80 ms / 440 tokens 1.14.031.357 I slot print_timing: id 0 | task 6670 | graphs reused = 6217 1.14.031.358 I slot print_timing: id 0 | task 6670 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.031.385 I slot release: id 0 | task 6670 | stop processing: n_tokens = 471, truncated = 0 1.14.054.172 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 73939765 1.14.097.360 I slot launch_slot_: id 0 | task 6780 | processing task, is_child = 0 1.15.325.835 I slot print_timing: id 0 | task 6780 | prompt eval time = 122.46 ms / 403 tokens ( 0.30 ms per token, 3290.95 tokens per second) 1.15.325.841 I slot print_timing: id 0 | task 6780 | eval time = 1106.00 ms / 138 tokens ( 8.07 ms per token, 123.87 tokens per second) 1.15.325.842 I slot print_timing: id 0 | task 6780 | total time = 1228.45 ms / 541 tokens 1.15.325.843 I slot print_timing: id 0 | task 6780 | graphs reused = 6352 1.15.325.843 I slot print_timing: id 0 | task 6780 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.325.877 I slot release: id 0 | task 6780 | stop processing: n_tokens = 572, truncated = 0 1.15.346.206 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 75234257 1.15.346.247 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.15.412.768 I slot launch_slot_: id 0 | task 6921 | processing task, is_child = 0 1.17.028.411 I slot print_timing: id 0 | task 6921 | prompt eval time = 121.03 ms / 411 tokens ( 0.29 ms per token, 3395.77 tokens per second) 1.17.028.417 I slot print_timing: id 0 | task 6921 | eval time = 1494.59 ms / 185 tokens ( 8.12 ms per token, 123.11 tokens per second) 1.17.028.418 I slot print_timing: id 0 | task 6921 | total time = 1615.62 ms / 596 tokens 1.17.028.418 I slot print_timing: id 0 | task 6921 | graphs reused = 6534 1.17.028.419 I slot print_timing: id 0 | task 6921 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.028.450 I slot release: id 0 | task 6921 | stop processing: n_tokens = 627, truncated = 0 1.17.042.147 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 76936829 1.17.042.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.17.114.011 I slot launch_slot_: id 0 | task 7109 | processing task, is_child = 0 1.19.063.276 I slot print_timing: id 0 | task 7109 | prompt eval time = 138.95 ms / 490 tokens ( 0.28 ms per token, 3526.35 tokens per second) 1.19.063.282 I slot print_timing: id 0 | task 7109 | eval time = 1810.29 ms / 225 tokens ( 8.08 ms per token, 123.74 tokens per second) 1.19.063.283 I slot print_timing: id 0 | task 7109 | total time = 1949.24 ms / 715 tokens 1.19.063.284 I slot print_timing: id 0 | task 7109 | graphs reused = 6757 1.19.063.284 I slot print_timing: id 0 | task 7109 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.063.316 I slot release: id 0 | task 7109 | stop processing: n_tokens = 746, truncated = 0 1.19.079.037 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 78971695 1.19.079.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.19.150.732 I slot launch_slot_: id 0 | task 7337 | processing task, is_child = 0 1.22.025.111 I slot print_timing: id 0 | task 7337 | prompt eval time = 116.94 ms / 344 tokens ( 0.34 ms per token, 2941.78 tokens per second) 1.22.025.117 I slot print_timing: id 0 | task 7337 | eval time = 2757.43 ms / 342 tokens ( 8.09 ms per token, 123.67 tokens per second) 1.22.025.118 I slot print_timing: id 0 | task 7337 | total time = 2874.36 ms / 686 tokens 1.22.025.119 I slot print_timing: id 0 | task 7337 | graphs reused = 7096 1.22.025.120 I slot print_timing: id 0 | task 7337 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.025.149 I slot release: id 0 | task 7337 | stop processing: n_tokens = 717, truncated = 0 1.22.039.686 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 81933528 1.22.039.737 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.798 MiB) 1.22.106.701 I slot launch_slot_: id 0 | task 7682 | processing task, is_child = 0 1.24.759.543 I slot print_timing: id 0 | task 7682 | prompt eval time = 116.96 ms / 347 tokens ( 0.34 ms per token, 2966.88 tokens per second) 1.24.759.549 I slot print_timing: id 0 | task 7682 | eval time = 2535.86 ms / 316 tokens ( 8.05 ms per token, 124.22 tokens per second) 1.24.759.550 I slot print_timing: id 0 | task 7682 | total time = 2652.82 ms / 663 tokens 1.24.759.551 I slot print_timing: id 0 | task 7682 | graphs reused = 7409 1.24.759.551 I slot print_timing: id 0 | task 7682 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.759.580 I slot release: id 0 | task 7682 | stop processing: n_tokens = 694, truncated = 0 1.24.773.681 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 694, t_last = 84667960 1.24.773.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.834 MiB) 1.24.844.425 I slot launch_slot_: id 0 | task 8001 | processing task, is_child = 0 1.25.986.435 I slot print_timing: id 0 | task 8001 | prompt eval time = 121.75 ms / 401 tokens ( 0.30 ms per token, 3293.58 tokens per second) 1.25.986.440 I slot print_timing: id 0 | task 8001 | eval time = 1020.24 ms / 126 tokens ( 8.16 ms per token, 122.52 tokens per second) 1.25.986.441 I slot print_timing: id 0 | task 8001 | total time = 1141.99 ms / 527 tokens 1.25.986.442 I slot print_timing: id 0 | task 8001 | graphs reused = 7532 1.25.986.442 I slot print_timing: id 0 | task 8001 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.986.474 I slot release: id 0 | task 8001 | stop processing: n_tokens = 558, truncated = 0 1.26.010.853 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 85894854 1.26.010.907 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.26.081.137 I slot launch_slot_: id 0 | task 8130 | processing task, is_child = 0 1.27.155.052 I slot print_timing: id 0 | task 8130 | prompt eval time = 130.81 ms / 456 tokens ( 0.29 ms per token, 3485.87 tokens per second) 1.27.155.057 I slot print_timing: id 0 | task 8130 | eval time = 943.08 ms / 114 tokens ( 8.35 ms per token, 119.82 tokens per second) 1.27.155.058 I slot print_timing: id 0 | task 8130 | total time = 1073.90 ms / 570 tokens 1.27.155.059 I slot print_timing: id 0 | task 8130 | graphs reused = 7643 1.27.155.060 I slot print_timing: id 0 | task 8130 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.155.093 I slot release: id 0 | task 8130 | stop processing: n_tokens = 601, truncated = 0 1.27.182.202 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 1.27.182.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.27.260.596 I slot launch_slot_: id 0 | task 8247 | processing task, is_child = 0 1.28.286.020 I slot print_timing: id 0 | task 8247 | prompt eval time = 123.48 ms / 406 tokens ( 0.30 ms per token, 3287.85 tokens per second) 1.28.286.027 I slot print_timing: id 0 | task 8247 | eval time = 901.92 ms / 112 tokens ( 8.13 ms per token, 123.07 tokens per second) 1.28.286.028 I slot print_timing: id 0 | task 8247 | total time = 1025.40 ms / 518 tokens 1.28.286.031 I slot print_timing: id 0 | task 8247 | graphs reused = 7752 1.28.286.032 I slot print_timing: id 0 | task 8247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.286.069 I slot release: id 0 | task 8247 | stop processing: n_tokens = 549, truncated = 0 1.28.308.415 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 88194449 1.28.354.924 I slot launch_slot_: id 0 | task 8362 | processing task, is_child = 0 1.29.928.066 I slot print_timing: id 0 | task 8362 | prompt eval time = 122.16 ms / 406 tokens ( 0.30 ms per token, 3323.40 tokens per second) 1.29.928.072 I slot print_timing: id 0 | task 8362 | eval time = 1450.96 ms / 179 tokens ( 8.15 ms per token, 122.68 tokens per second) 1.29.928.073 I slot print_timing: id 0 | task 8362 | total time = 1573.12 ms / 585 tokens 1.29.928.074 I slot print_timing: id 0 | task 8362 | graphs reused = 7928 1.29.928.074 I slot print_timing: id 0 | task 8362 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.928.105 I slot release: id 0 | task 8362 | stop processing: n_tokens = 616, truncated = 0 1.29.950.014 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 89836485 1.29.950.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.30.020.848 I slot launch_slot_: id 0 | task 8544 | processing task, is_child = 0 1.31.249.533 I slot print_timing: id 0 | task 8544 | prompt eval time = 126.80 ms / 444 tokens ( 0.29 ms per token, 3501.60 tokens per second) 1.31.249.539 I slot print_timing: id 0 | task 8544 | eval time = 1101.87 ms / 134 tokens ( 8.28 ms per token, 120.70 tokens per second) 1.31.249.540 I slot print_timing: id 0 | task 8544 | total time = 1228.66 ms / 578 tokens 1.31.249.541 I slot print_timing: id 0 | task 8544 | graphs reused = 8059 1.31.249.542 I slot print_timing: id 0 | task 8544 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.249.575 I slot release: id 0 | task 8544 | stop processing: n_tokens = 609, truncated = 0 1.31.277.998 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 91157955 1.31.278.052 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.31.344.635 I slot launch_slot_: id 0 | task 8681 | processing task, is_child = 0 1.32.296.008 I slot print_timing: id 0 | task 8681 | prompt eval time = 118.74 ms / 372 tokens ( 0.32 ms per token, 3132.79 tokens per second) 1.32.296.014 I slot print_timing: id 0 | task 8681 | eval time = 832.61 ms / 103 tokens ( 8.16 ms per token, 122.51 tokens per second) 1.32.296.015 I slot print_timing: id 0 | task 8681 | total time = 951.35 ms / 475 tokens 1.32.296.016 I slot print_timing: id 0 | task 8681 | graphs reused = 8160 1.32.296.017 I slot print_timing: id 0 | task 8681 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.296.047 I slot release: id 0 | task 8681 | stop processing: n_tokens = 506, truncated = 0 1.32.314.319 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 92204427 1.32.314.369 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.32.387.075 I slot launch_slot_: id 0 | task 8787 | processing task, is_child = 0 1.34.391.920 I slot print_timing: id 0 | task 8787 | prompt eval time = 129.58 ms / 454 tokens ( 0.29 ms per token, 3503.63 tokens per second) 1.34.391.926 I slot print_timing: id 0 | task 8787 | eval time = 1875.25 ms / 230 tokens ( 8.19 ms per token, 122.12 tokens per second) 1.34.391.927 I slot print_timing: id 0 | task 8787 | total time = 2004.83 ms / 684 tokens 1.34.391.928 I slot print_timing: id 0 | task 8787 | graphs reused = 8387 1.34.391.928 I slot print_timing: id 0 | task 8787 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.391.960 I slot release: id 0 | task 8787 | stop processing: n_tokens = 715, truncated = 0 1.34.408.479 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 94300340 1.34.408.537 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.34.478.324 I slot launch_slot_: id 0 | task 9020 | processing task, is_child = 0 1.36.408.505 I slot print_timing: id 0 | task 9020 | prompt eval time = 119.11 ms / 354 tokens ( 0.34 ms per token, 2971.97 tokens per second) 1.36.408.510 I slot print_timing: id 0 | task 9020 | eval time = 1811.04 ms / 226 tokens ( 8.05 ms per token, 124.24 tokens per second) 1.36.408.511 I slot print_timing: id 0 | task 9020 | total time = 1930.15 ms / 580 tokens 1.36.408.512 I slot print_timing: id 0 | task 9020 | graphs reused = 8610 1.36.408.513 I slot print_timing: id 0 | task 9020 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.408.545 I slot release: id 0 | task 9020 | stop processing: n_tokens = 611, truncated = 0 1.36.422.457 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 96316925 1.36.422.512 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.36.496.741 I slot launch_slot_: id 0 | task 9249 | processing task, is_child = 0 1.37.746.699 I slot print_timing: id 0 | task 9249 | prompt eval time = 117.11 ms / 334 tokens ( 0.35 ms per token, 2851.95 tokens per second) 1.37.746.704 I slot print_timing: id 0 | task 9249 | eval time = 1132.83 ms / 140 tokens ( 8.15 ms per token, 122.70 tokens per second) 1.37.746.706 I slot print_timing: id 0 | task 9249 | total time = 1249.94 ms / 474 tokens 1.37.746.706 I slot print_timing: id 0 | task 9249 | graphs reused = 8748 1.37.746.707 I slot print_timing: id 0 | task 9249 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.746.738 I slot release: id 0 | task 9249 | stop processing: n_tokens = 505, truncated = 0 1.37.768.237 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 97655117 1.37.768.290 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.426 MiB) 1.37.838.911 I slot launch_slot_: id 0 | task 9392 | processing task, is_child = 0 1.39.374.274 I slot print_timing: id 0 | task 9392 | prompt eval time = 127.09 ms / 426 tokens ( 0.30 ms per token, 3352.06 tokens per second) 1.39.374.280 I slot print_timing: id 0 | task 9392 | eval time = 1408.26 ms / 175 tokens ( 8.09 ms per token, 123.56 tokens per second) 1.39.374.281 I slot print_timing: id 0 | task 9392 | total time = 1535.34 ms / 601 tokens 1.39.374.282 I slot print_timing: id 0 | task 9392 | graphs reused = 8920 1.39.374.282 I slot print_timing: id 0 | task 9392 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.374.315 I slot release: id 0 | task 9392 | stop processing: n_tokens = 632, truncated = 0 1.39.378.253 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 99282695 1.39.378.306 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 1.39.462.388 I slot launch_slot_: id 0 | task 9570 | processing task, is_child = 0 1.40.516.418 I slot print_timing: id 0 | task 9570 | prompt eval time = 117.89 ms / 366 tokens ( 0.32 ms per token, 3104.54 tokens per second) 1.40.516.423 I slot print_timing: id 0 | task 9570 | eval time = 936.12 ms / 117 tokens ( 8.07 ms per token, 123.92 tokens per second) 1.40.516.424 I slot print_timing: id 0 | task 9570 | total time = 1054.01 ms / 483 tokens 1.40.516.425 I slot print_timing: id 0 | task 9570 | graphs reused = 9034 1.40.516.426 I slot print_timing: id 0 | task 9570 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.516.456 I slot release: id 0 | task 9570 | stop processing: n_tokens = 514, truncated = 0 1.40.535.213 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 100424836 1.40.535.264 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 1.40.605.086 I slot launch_slot_: id 0 | task 9690 | processing task, is_child = 0 1.43.581.182 I slot print_timing: id 0 | task 9690 | prompt eval time = 132.25 ms / 462 tokens ( 0.29 ms per token, 3493.46 tokens per second) 1.43.581.187 I slot print_timing: id 0 | task 9690 | eval time = 2843.83 ms / 352 tokens ( 8.10 ms per token, 123.43 tokens per second) 1.43.581.188 I slot print_timing: id 0 | task 9690 | total time = 2976.08 ms / 814 tokens 1.43.581.190 I slot print_timing: id 0 | task 9690 | graphs reused = 9382 1.43.581.191 I slot print_timing: id 0 | task 9690 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.581.223 I slot release: id 0 | task 9690 | stop processing: n_tokens = 845, truncated = 0 1.43.598.398 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 103489602 1.43.598.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.895 MiB) 1.43.674.756 I slot launch_slot_: id 0 | task 10045 | processing task, is_child = 0 1.44.917.729 I slot print_timing: id 0 | task 10045 | prompt eval time = 121.40 ms / 396 tokens ( 0.31 ms per token, 3262.00 tokens per second) 1.44.917.735 I slot print_timing: id 0 | task 10045 | eval time = 1121.55 ms / 139 tokens ( 8.13 ms per token, 123.04 tokens per second) 1.44.917.735 I slot print_timing: id 0 | task 10045 | total time = 1242.95 ms / 535 tokens 1.44.917.736 I slot print_timing: id 0 | task 10045 | graphs reused = 9518 1.44.917.737 I slot print_timing: id 0 | task 10045 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.917.767 I slot release: id 0 | task 10045 | stop processing: n_tokens = 566, truncated = 0 1.44.942.811 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 104826147 1.44.987.138 I slot launch_slot_: id 0 | task 10187 | processing task, is_child = 0 1.46.421.481 I slot print_timing: id 0 | task 10187 | prompt eval time = 132.60 ms / 458 tokens ( 0.29 ms per token, 3454.08 tokens per second) 1.46.421.487 I slot print_timing: id 0 | task 10187 | eval time = 1301.73 ms / 161 tokens ( 8.14 ms per token, 122.91 tokens per second) 1.46.421.488 I slot print_timing: id 0 | task 10187 | total time = 1434.32 ms / 619 tokens 1.46.421.489 I slot print_timing: id 0 | task 10187 | graphs reused = 9676 1.46.421.489 I slot print_timing: id 0 | task 10187 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.421.521 I slot release: id 0 | task 10187 | stop processing: n_tokens = 650, truncated = 0 1.46.436.472 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 106329900 1.46.436.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.863 MiB) 1.46.507.020 I slot launch_slot_: id 0 | task 10351 | processing task, is_child = 0 1.48.095.678 I slot print_timing: id 0 | task 10351 | prompt eval time = 131.73 ms / 458 tokens ( 0.29 ms per token, 3476.76 tokens per second) 1.48.095.684 I slot print_timing: id 0 | task 10351 | eval time = 1456.90 ms / 176 tokens ( 8.33 ms per token, 120.12 tokens per second) 1.48.095.685 I slot print_timing: id 0 | task 10351 | total time = 1588.64 ms / 634 tokens 1.48.095.686 I slot print_timing: id 0 | task 10351 | graphs reused = 9849 1.48.095.687 I slot print_timing: id 0 | task 10351 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.095.723 I slot release: id 0 | task 10351 | stop processing: n_tokens = 665, truncated = 0 1.48.112.622 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 108004103 1.48.112.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 1.48.191.503 I slot launch_slot_: id 0 | task 10530 | processing task, is_child = 0 1.50.033.011 I slot print_timing: id 0 | task 10530 | prompt eval time = 129.93 ms / 452 tokens ( 0.29 ms per token, 3478.69 tokens per second) 1.50.033.017 I slot print_timing: id 0 | task 10530 | eval time = 1711.55 ms / 210 tokens ( 8.19 ms per token, 122.11 tokens per second) 1.50.033.019 I slot print_timing: id 0 | task 10530 | total time = 1841.49 ms / 662 tokens 1.50.033.020 I slot print_timing: id 0 | task 10530 | graphs reused = 10056 1.50.033.021 I slot print_timing: id 0 | task 10530 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.033.058 I slot release: id 0 | task 10530 | stop processing: n_tokens = 693, truncated = 0 1.50.060.284 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 109941438 1.50.060.345 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 1.50.132.177 I slot launch_slot_: id 0 | task 10743 | processing task, is_child = 0 1.51.178.088 I slot print_timing: id 0 | task 10743 | prompt eval time = 124.61 ms / 404 tokens ( 0.31 ms per token, 3242.09 tokens per second) 1.51.178.094 I slot print_timing: id 0 | task 10743 | eval time = 921.28 ms / 114 tokens ( 8.15 ms per token, 122.66 tokens per second) 1.51.178.095 I slot print_timing: id 0 | task 10743 | total time = 1045.89 ms / 518 tokens 1.51.178.095 I slot print_timing: id 0 | task 10743 | graphs reused = 10167 1.51.178.097 I slot print_timing: id 0 | task 10743 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.178.127 I slot release: id 0 | task 10743 | stop processing: n_tokens = 549, truncated = 0 1.51.192.374 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 111086507 1.51.192.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 1.51.260.878 I slot launch_slot_: id 0 | task 10860 | processing task, is_child = 0 1.52.214.837 I slot print_timing: id 0 | task 10860 | prompt eval time = 117.25 ms / 345 tokens ( 0.34 ms per token, 2942.48 tokens per second) 1.52.214.842 I slot print_timing: id 0 | task 10860 | eval time = 836.69 ms / 106 tokens ( 7.97 ms per token, 125.49 tokens per second) 1.52.214.843 I slot print_timing: id 0 | task 10860 | total time = 953.94 ms / 451 tokens 1.52.214.844 I slot print_timing: id 0 | task 10860 | graphs reused = 10271 1.52.214.845 I slot print_timing: id 0 | task 10860 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.214.874 I slot release: id 0 | task 10860 | stop processing: n_tokens = 482, truncated = 0 1.52.230.436 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 112123254 1.52.230.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 1.52.296.405 I slot launch_slot_: id 0 | task 10969 | processing task, is_child = 0 1.53.282.767 I slot print_timing: id 0 | task 10969 | prompt eval time = 129.81 ms / 430 tokens ( 0.30 ms per token, 3312.61 tokens per second) 1.53.282.772 I slot print_timing: id 0 | task 10969 | eval time = 856.53 ms / 105 tokens ( 8.24 ms per token, 121.42 tokens per second) 1.53.282.773 I slot print_timing: id 0 | task 10969 | total time = 986.34 ms / 535 tokens 1.53.282.775 I slot print_timing: id 0 | task 10969 | graphs reused = 10373 1.53.282.776 I slot print_timing: id 0 | task 10969 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.282.808 I slot release: id 0 | task 10969 | stop processing: n_tokens = 566, truncated = 0 1.53.306.162 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 113191188 1.53.306.218 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 1.53.375.902 I slot launch_slot_: id 0 | task 11077 | processing task, is_child = 0 1.54.207.647 I slot print_timing: id 0 | task 11077 | prompt eval time = 110.57 ms / 316 tokens ( 0.35 ms per token, 2857.94 tokens per second) 1.54.207.653 I slot print_timing: id 0 | task 11077 | eval time = 721.16 ms / 85 tokens ( 8.59 ms per token, 116.48 tokens per second) 1.54.207.654 I slot print_timing: id 0 | task 11077 | total time = 831.72 ms / 401 tokens 1.54.207.654 I slot print_timing: id 0 | task 11077 | graphs reused = 10456 1.54.207.655 I slot print_timing: id 0 | task 11077 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.207.683 I slot release: id 0 | task 11077 | stop processing: n_tokens = 432, truncated = 0 1.54.226.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 114116063 1.54.226.502 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 1.54.292.689 I slot launch_slot_: id 0 | task 11165 | processing task, is_child = 0 1.55.275.282 I slot print_timing: id 0 | task 11165 | prompt eval time = 118.52 ms / 354 tokens ( 0.33 ms per token, 2986.89 tokens per second) 1.55.275.288 I slot print_timing: id 0 | task 11165 | eval time = 864.05 ms / 107 tokens ( 8.15 ms per token, 122.68 tokens per second) 1.55.275.289 I slot print_timing: id 0 | task 11165 | total time = 982.57 ms / 461 tokens 1.55.275.289 I slot print_timing: id 0 | task 11165 | graphs reused = 10561 1.55.275.290 I slot print_timing: id 0 | task 11165 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.275.319 I slot release: id 0 | task 11165 | stop processing: n_tokens = 492, truncated = 0 1.55.289.122 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 115183699 1.55.289.171 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 1.55.355.368 I slot launch_slot_: id 0 | task 11275 | processing task, is_child = 0 1.56.266.238 I slot print_timing: id 0 | task 11275 | prompt eval time = 130.13 ms / 438 tokens ( 0.30 ms per token, 3365.81 tokens per second) 1.56.266.244 I slot print_timing: id 0 | task 11275 | eval time = 780.72 ms / 98 tokens ( 8.05 ms per token, 124.24 tokens per second) 1.56.266.245 I slot print_timing: id 0 | task 11275 | total time = 910.85 ms / 536 tokens 1.56.266.246 I slot print_timing: id 0 | task 11275 | graphs reused = 10656 1.56.266.247 I slot print_timing: id 0 | task 11275 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.266.278 I slot release: id 0 | task 11275 | stop processing: n_tokens = 567, truncated = 0 1.56.290.214 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 116174658 1.56.290.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 1.56.356.991 I slot launch_slot_: id 0 | task 11376 | processing task, is_child = 0 1.57.059.669 I slot print_timing: id 0 | task 11376 | prompt eval time = 129.66 ms / 457 tokens ( 0.28 ms per token, 3524.60 tokens per second) 1.57.059.675 I slot print_timing: id 0 | task 11376 | eval time = 573.00 ms / 70 tokens ( 8.30 ms per token, 120.42 tokens per second) 1.57.059.676 I slot print_timing: id 0 | task 11376 | total time = 702.66 ms / 527 tokens 1.57.059.678 I slot print_timing: id 0 | task 11376 | graphs reused = 10723 1.57.059.679 I slot print_timing: id 0 | task 11376 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.059.711 I slot release: id 0 | task 11376 | stop processing: n_tokens = 558, truncated = 0 1.57.076.168 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 116968091 1.57.076.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 1.57.143.154 I slot launch_slot_: id 0 | task 11449 | processing task, is_child = 0 1.58.070.853 I slot print_timing: id 0 | task 11449 | prompt eval time = 135.16 ms / 473 tokens ( 0.29 ms per token, 3499.53 tokens per second) 1.58.070.859 I slot print_timing: id 0 | task 11449 | eval time = 792.52 ms / 98 tokens ( 8.17 ms per token, 122.39 tokens per second) 1.58.070.860 I slot print_timing: id 0 | task 11449 | total time = 927.68 ms / 571 tokens 1.58.070.861 I slot print_timing: id 0 | task 11449 | graphs reused = 10818 1.58.070.861 I slot print_timing: id 0 | task 11449 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.070.893 I slot release: id 0 | task 11449 | stop processing: n_tokens = 602, truncated = 0 1.58.096.383 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 117979272 1.58.096.439 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.926 MiB) 1.58.174.517 I slot launch_slot_: id 0 | task 11550 | processing task, is_child = 0 1.58.524.143 I slot print_timing: id 0 | task 11550 | prompt eval time = 130.65 ms / 476 tokens ( 0.27 ms per token, 3643.24 tokens per second) 1.58.524.149 I slot print_timing: id 0 | task 11550 | eval time = 218.95 ms / 27 tokens ( 8.42 ms per token, 118.75 tokens per second) 1.58.524.150 I slot print_timing: id 0 | task 11550 | total time = 349.61 ms / 503 tokens 1.58.524.151 I slot print_timing: id 0 | task 11550 | graphs reused = 10842 1.58.524.152 I slot print_timing: id 0 | task 11550 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.524.187 I slot release: id 0 | task 11550 | stop processing: n_tokens = 534, truncated = 0 1.58.546.063 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 118432566 1.58.546.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.207 MiB) 1.58.619.006 I slot launch_slot_: id 0 | task 11580 | processing task, is_child = 0 1.59.622.950 I slot print_timing: id 0 | task 11580 | prompt eval time = 142.85 ms / 466 tokens ( 0.31 ms per token, 3262.21 tokens per second) 1.59.622.956 I slot print_timing: id 0 | task 11580 | eval time = 861.08 ms / 107 tokens ( 8.12 ms per token, 123.10 tokens per second) 1.59.622.957 I slot print_timing: id 0 | task 11580 | total time = 1003.92 ms / 573 tokens 1.59.622.958 I slot print_timing: id 0 | task 11580 | graphs reused = 10946 1.59.622.959 I slot print_timing: id 0 | task 11580 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.622.989 I slot release: id 0 | task 11580 | stop processing: n_tokens = 604, truncated = 0 1.59.640.481 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 119531369 1.59.640.534 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 1.59.707.005 I slot launch_slot_: id 0 | task 11690 | processing task, is_child = 0 2.00.453.901 I slot print_timing: id 0 | task 11690 | prompt eval time = 123.96 ms / 415 tokens ( 0.30 ms per token, 3347.80 tokens per second) 2.00.453.907 I slot print_timing: id 0 | task 11690 | eval time = 622.91 ms / 78 tokens ( 8.09 ms per token, 123.61 tokens per second) 2.00.453.908 I slot print_timing: id 0 | task 11690 | total time = 746.88 ms / 493 tokens 2.00.453.910 I slot print_timing: id 0 | task 11690 | graphs reused = 11021 2.00.453.910 I slot print_timing: id 0 | task 11690 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.453.942 I slot release: id 0 | task 11690 | stop processing: n_tokens = 524, truncated = 0 2.00.472.067 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 120362322 2.00.472.118 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.299 MiB) 2.00.538.257 I slot launch_slot_: id 0 | task 11771 | processing task, is_child = 0 2.01.170.277 I slot print_timing: id 0 | task 11771 | prompt eval time = 116.51 ms / 352 tokens ( 0.33 ms per token, 3021.10 tokens per second) 2.01.170.283 I slot print_timing: id 0 | task 11771 | eval time = 515.49 ms / 64 tokens ( 8.18 ms per token, 122.21 tokens per second) 2.01.170.284 I slot print_timing: id 0 | task 11771 | total time = 632.00 ms / 416 tokens 2.01.170.285 I slot print_timing: id 0 | task 11771 | graphs reused = 11083 2.01.170.285 I slot print_timing: id 0 | task 11771 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.170.314 I slot release: id 0 | task 11771 | stop processing: n_tokens = 447, truncated = 0 2.01.188.793 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 121078693 2.01.188.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.01.255.664 I slot launch_slot_: id 0 | task 11838 | processing task, is_child = 0 2.02.470.177 I slot print_timing: id 0 | task 11838 | prompt eval time = 145.84 ms / 550 tokens ( 0.27 ms per token, 3771.13 tokens per second) 2.02.470.182 I slot print_timing: id 0 | task 11838 | eval time = 1068.65 ms / 133 tokens ( 8.10 ms per token, 123.52 tokens per second) 2.02.470.183 I slot print_timing: id 0 | task 11838 | total time = 1214.49 ms / 683 tokens 2.02.470.184 I slot print_timing: id 0 | task 11838 | graphs reused = 11214 2.02.470.185 I slot print_timing: id 0 | task 11838 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.470.222 I slot release: id 0 | task 11838 | stop processing: n_tokens = 714, truncated = 0 2.02.485.115 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 122378601 2.02.485.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 2.02.559.442 I slot launch_slot_: id 0 | task 11975 | processing task, is_child = 0 2.04.547.800 I slot print_timing: id 0 | task 11975 | prompt eval time = 171.62 ms / 772 tokens ( 0.22 ms per token, 4498.21 tokens per second) 2.04.547.805 I slot print_timing: id 0 | task 11975 | eval time = 1816.71 ms / 226 tokens ( 8.07 ms per token, 123.85 tokens per second) 2.04.547.806 I slot print_timing: id 0 | task 11975 | total time = 1988.34 ms / 998 tokens 2.04.547.807 I slot print_timing: id 0 | task 11975 | graphs reused = 11437 2.04.547.808 I slot print_timing: id 0 | task 11975 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.547.846 I slot release: id 0 | task 11975 | stop processing: n_tokens = 1029, truncated = 0 2.04.574.276 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 124456226 2.04.574.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 2.04.650.689 I slot launch_slot_: id 0 | task 12205 | processing task, is_child = 0 2.06.296.993 I slot print_timing: id 0 | task 12205 | prompt eval time = 169.11 ms / 683 tokens ( 0.25 ms per token, 4038.72 tokens per second) 2.06.297.000 I slot print_timing: id 0 | task 12205 | eval time = 1477.17 ms / 181 tokens ( 8.21 ms per token, 121.85 tokens per second) 2.06.297.001 I slot print_timing: id 0 | task 12205 | total time = 1646.28 ms / 864 tokens 2.06.297.002 I slot print_timing: id 0 | task 12205 | graphs reused = 11615 2.06.297.003 I slot print_timing: id 0 | task 12205 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.297.044 I slot release: id 0 | task 12205 | stop processing: n_tokens = 895, truncated = 0 2.06.318.349 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 126205424 2.06.318.417 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 2.06.396.279 I slot launch_slot_: id 0 | task 12390 | processing task, is_child = 0 2.07.300.117 I slot print_timing: id 0 | task 12390 | prompt eval time = 154.94 ms / 579 tokens ( 0.27 ms per token, 3736.98 tokens per second) 2.07.300.123 I slot print_timing: id 0 | task 12390 | eval time = 748.88 ms / 93 tokens ( 8.14 ms per token, 122.85 tokens per second) 2.07.300.124 I slot print_timing: id 0 | task 12390 | total time = 903.82 ms / 672 tokens 2.07.300.125 I slot print_timing: id 0 | task 12390 | graphs reused = 11706 2.07.300.126 I slot print_timing: id 0 | task 12390 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.300.163 I slot release: id 0 | task 12390 | stop processing: n_tokens = 703, truncated = 0 2.07.328.977 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 703, t_last = 127208543 2.07.329.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 2.07.349.496 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 2.07.420.673 I slot launch_slot_: id 0 | task 12487 | processing task, is_child = 0 2.08.401.428 I slot print_timing: id 0 | task 12487 | prompt eval time = 139.51 ms / 500 tokens ( 0.28 ms per token, 3583.87 tokens per second) 2.08.401.434 I slot print_timing: id 0 | task 12487 | eval time = 841.22 ms / 106 tokens ( 8.01 ms per token, 124.82 tokens per second) 2.08.401.435 I slot print_timing: id 0 | task 12487 | total time = 980.73 ms / 606 tokens 2.08.401.436 I slot print_timing: id 0 | task 12487 | graphs reused = 11810 2.08.401.437 I slot print_timing: id 0 | task 12487 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.401.469 I slot release: id 0 | task 12487 | stop processing: n_tokens = 637, truncated = 0 2.08.406.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 128309849 2.08.406.278 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 2.08.475.880 I slot launch_slot_: id 0 | task 12596 | processing task, is_child = 0 2.10.346.822 I slot print_timing: id 0 | task 12596 | prompt eval time = 176.37 ms / 776 tokens ( 0.23 ms per token, 4399.82 tokens per second) 2.10.346.828 I slot print_timing: id 0 | task 12596 | eval time = 1694.55 ms / 209 tokens ( 8.15 ms per token, 122.75 tokens per second) 2.10.346.829 I slot print_timing: id 0 | task 12596 | total time = 1870.92 ms / 985 tokens 2.10.346.829 I slot print_timing: id 0 | task 12596 | graphs reused = 12017 2.10.346.830 I slot print_timing: id 0 | task 12596 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.346.870 I slot release: id 0 | task 12596 | stop processing: n_tokens = 1016, truncated = 0 2.10.373.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 130255249 2.10.373.167 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 2.10.447.280 I slot launch_slot_: id 0 | task 12809 | processing task, is_child = 0 2.12.161.356 I slot print_timing: id 0 | task 12809 | prompt eval time = 139.61 ms / 504 tokens ( 0.28 ms per token, 3610.11 tokens per second) 2.12.161.361 I slot print_timing: id 0 | task 12809 | eval time = 1574.45 ms / 197 tokens ( 8.03 ms per token, 124.49 tokens per second) 2.12.161.362 I slot print_timing: id 0 | task 12809 | total time = 1714.05 ms / 701 tokens 2.12.161.363 I slot print_timing: id 0 | task 12809 | graphs reused = 12212 2.12.161.364 I slot print_timing: id 0 | task 12809 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.161.398 I slot release: id 0 | task 12809 | stop processing: n_tokens = 732, truncated = 0 2.12.180.932 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 132069778 2.12.180.989 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 2.12.248.143 I slot launch_slot_: id 0 | task 13009 | processing task, is_child = 0 2.14.084.538 I slot print_timing: id 0 | task 13009 | prompt eval time = 155.07 ms / 633 tokens ( 0.24 ms per token, 4081.97 tokens per second) 2.14.084.544 I slot print_timing: id 0 | task 13009 | eval time = 1681.30 ms / 207 tokens ( 8.16 ms per token, 122.52 tokens per second) 2.14.084.545 I slot print_timing: id 0 | task 13009 | total time = 1836.38 ms / 840 tokens 2.14.084.545 I slot print_timing: id 0 | task 13009 | graphs reused = 12416 2.14.084.546 I slot print_timing: id 0 | task 13009 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.084.584 I slot release: id 0 | task 13009 | stop processing: n_tokens = 871, truncated = 0 2.14.110.340 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 133992964 2.14.110.405 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.929 MiB) 2.14.186.369 I slot launch_slot_: id 0 | task 13220 | processing task, is_child = 0 2.15.394.071 I slot print_timing: id 0 | task 13220 | prompt eval time = 126.84 ms / 395 tokens ( 0.32 ms per token, 3114.18 tokens per second) 2.15.394.076 I slot print_timing: id 0 | task 13220 | eval time = 1080.84 ms / 134 tokens ( 8.13 ms per token, 123.05 tokens per second) 2.15.394.077 I slot print_timing: id 0 | task 13220 | total time = 1207.68 ms / 529 tokens 2.15.394.078 I slot print_timing: id 0 | task 13220 | graphs reused = 12547 2.15.394.079 I slot print_timing: id 0 | task 13220 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.394.108 I slot release: id 0 | task 13220 | stop processing: n_tokens = 560, truncated = 0 2.15.420.636 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 135302488 2.15.420.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.15.487.120 I slot launch_slot_: id 0 | task 13357 | processing task, is_child = 0 2.17.320.517 I slot print_timing: id 0 | task 13357 | prompt eval time = 147.14 ms / 584 tokens ( 0.25 ms per token, 3969.01 tokens per second) 2.17.320.523 I slot print_timing: id 0 | task 13357 | eval time = 1686.23 ms / 209 tokens ( 8.11 ms per token, 123.35 tokens per second) 2.17.320.524 I slot print_timing: id 0 | task 13357 | total time = 1833.38 ms / 793 tokens 2.17.320.525 I slot print_timing: id 0 | task 13357 | graphs reused = 12753 2.17.320.526 I slot print_timing: id 0 | task 13357 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.320.562 I slot release: id 0 | task 13357 | stop processing: n_tokens = 824, truncated = 0 2.17.341.990 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 137228942 2.17.342.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 2.17.416.634 I slot launch_slot_: id 0 | task 13570 | processing task, is_child = 0 2.19.447.113 I slot print_timing: id 0 | task 13570 | prompt eval time = 167.22 ms / 695 tokens ( 0.24 ms per token, 4156.23 tokens per second) 2.19.447.119 I slot print_timing: id 0 | task 13570 | eval time = 1863.24 ms / 230 tokens ( 8.14 ms per token, 122.90 tokens per second) 2.19.447.120 I slot print_timing: id 0 | task 13570 | total time = 2030.46 ms / 925 tokens 2.19.447.120 I slot print_timing: id 0 | task 13570 | graphs reused = 12980 2.19.447.121 I slot print_timing: id 0 | task 13570 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.447.159 I slot release: id 0 | task 13570 | stop processing: n_tokens = 956, truncated = 0 2.19.464.763 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 139355539 2.19.464.834 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.300 MiB) 2.19.541.024 I slot launch_slot_: id 0 | task 13804 | processing task, is_child = 0 2.21.252.506 I slot print_timing: id 0 | task 13804 | prompt eval time = 173.05 ms / 769 tokens ( 0.23 ms per token, 4443.83 tokens per second) 2.21.252.512 I slot print_timing: id 0 | task 13804 | eval time = 1538.41 ms / 191 tokens ( 8.10 ms per token, 123.50 tokens per second) 2.21.252.513 I slot print_timing: id 0 | task 13804 | total time = 1711.46 ms / 960 tokens 2.21.252.514 I slot print_timing: id 0 | task 13804 | graphs reused = 13169 2.21.252.514 I slot print_timing: id 0 | task 13804 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.252.556 I slot release: id 0 | task 13804 | stop processing: n_tokens = 991, truncated = 0 2.21.275.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 141160936 2.21.275.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 2.21.295.075 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.21.371.179 I slot launch_slot_: id 0 | task 13999 | processing task, is_child = 0 2.22.518.225 I slot print_timing: id 0 | task 13999 | prompt eval time = 147.53 ms / 576 tokens ( 0.26 ms per token, 3904.21 tokens per second) 2.22.518.230 I slot print_timing: id 0 | task 13999 | eval time = 999.49 ms / 124 tokens ( 8.13 ms per token, 123.06 tokens per second) 2.22.518.231 I slot print_timing: id 0 | task 13999 | total time = 1147.03 ms / 700 tokens 2.22.518.232 I slot print_timing: id 0 | task 13999 | graphs reused = 13291 2.22.518.233 I slot print_timing: id 0 | task 13999 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.518.269 I slot release: id 0 | task 13999 | stop processing: n_tokens = 731, truncated = 0 2.22.534.977 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 142426649 2.22.535.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 2.22.613.335 I slot launch_slot_: id 0 | task 14127 | processing task, is_child = 0 2.24.986.060 I slot print_timing: id 0 | task 14127 | prompt eval time = 163.26 ms / 655 tokens ( 0.25 ms per token, 4011.93 tokens per second) 2.24.986.066 I slot print_timing: id 0 | task 14127 | eval time = 2209.44 ms / 275 tokens ( 8.06 ms per token, 124.01 tokens per second) 2.24.986.068 I slot print_timing: id 0 | task 14127 | total time = 2372.70 ms / 930 tokens 2.24.986.069 I slot print_timing: id 0 | task 14127 | graphs reused = 13563 2.24.986.070 I slot print_timing: id 0 | task 14127 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.986.113 I slot release: id 0 | task 14127 | stop processing: n_tokens = 961, truncated = 0 2.25.007.931 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 144894493 2.25.008.001 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.25.084.223 I slot launch_slot_: id 0 | task 14406 | processing task, is_child = 0 2.26.224.489 I slot print_timing: id 0 | task 14406 | prompt eval time = 158.49 ms / 621 tokens ( 0.26 ms per token, 3918.15 tokens per second) 2.26.224.494 I slot print_timing: id 0 | task 14406 | eval time = 981.75 ms / 121 tokens ( 8.18 ms per token, 122.23 tokens per second) 2.26.224.495 I slot print_timing: id 0 | task 14406 | total time = 1140.25 ms / 742 tokens 2.26.224.496 I slot print_timing: id 0 | task 14406 | graphs reused = 13681 2.26.224.497 I slot print_timing: id 0 | task 14406 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.224.534 I slot release: id 0 | task 14406 | stop processing: n_tokens = 773, truncated = 0 2.26.243.181 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 146132914 2.26.243.240 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 2.26.317.710 I slot launch_slot_: id 0 | task 14531 | processing task, is_child = 0 2.27.946.186 I slot print_timing: id 0 | task 14531 | prompt eval time = 174.37 ms / 767 tokens ( 0.23 ms per token, 4398.69 tokens per second) 2.27.946.192 I slot print_timing: id 0 | task 14531 | eval time = 1454.09 ms / 178 tokens ( 8.22 ms per token, 121.73 tokens per second) 2.27.946.193 I slot print_timing: id 0 | task 14531 | total time = 1628.46 ms / 945 tokens 2.27.946.194 I slot print_timing: id 0 | task 14531 | graphs reused = 13857 2.27.946.195 I slot print_timing: id 0 | task 14531 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.946.243 I slot release: id 0 | task 14531 | stop processing: n_tokens = 976, truncated = 0 2.27.974.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 147854623 2.27.974.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 2.28.050.785 I slot launch_slot_: id 0 | task 14713 | processing task, is_child = 0 2.29.926.206 I slot print_timing: id 0 | task 14713 | prompt eval time = 190.52 ms / 864 tokens ( 0.22 ms per token, 4535.05 tokens per second) 2.29.926.212 I slot print_timing: id 0 | task 14713 | eval time = 1684.88 ms / 203 tokens ( 8.34 ms per token, 119.89 tokens per second) 2.29.926.213 I slot print_timing: id 0 | task 14713 | total time = 1875.40 ms / 1067 tokens 2.29.926.214 I slot print_timing: id 0 | task 14713 | graphs reused = 14057 2.29.926.215 I slot print_timing: id 0 | task 14713 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.926.262 I slot release: id 0 | task 14713 | stop processing: n_tokens = 1098, truncated = 0 2.29.951.278 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 149834642 2.29.951.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 2.29.970.683 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.30.047.408 I slot launch_slot_: id 0 | task 14920 | processing task, is_child = 0 2.31.255.604 I slot print_timing: id 0 | task 14920 | prompt eval time = 163.80 ms / 646 tokens ( 0.25 ms per token, 3943.83 tokens per second) 2.31.255.612 I slot print_timing: id 0 | task 14920 | eval time = 1044.38 ms / 129 tokens ( 8.16 ms per token, 122.56 tokens per second) 2.31.255.613 I slot print_timing: id 0 | task 14920 | total time = 1208.18 ms / 775 tokens 2.31.255.614 I slot print_timing: id 0 | task 14920 | graphs reused = 14183 2.31.255.615 I slot print_timing: id 0 | task 14920 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.255.661 I slot release: id 0 | task 14920 | stop processing: n_tokens = 806, truncated = 0 2.31.273.762 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 151164041 2.31.273.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.31.347.439 I slot launch_slot_: id 0 | task 15053 | processing task, is_child = 0 2.33.312.268 I slot print_timing: id 0 | task 15053 | prompt eval time = 173.34 ms / 720 tokens ( 0.24 ms per token, 4153.61 tokens per second) 2.33.312.274 I slot print_timing: id 0 | task 15053 | eval time = 1791.47 ms / 219 tokens ( 8.22 ms per token, 121.69 tokens per second) 2.33.312.275 I slot print_timing: id 0 | task 15053 | total time = 1964.81 ms / 939 tokens 2.33.312.275 I slot print_timing: id 0 | task 15053 | graphs reused = 14399 2.33.312.276 I slot print_timing: id 0 | task 15053 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.312.316 I slot release: id 0 | task 15053 | stop processing: n_tokens = 970, truncated = 0 2.33.330.007 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 153220696 2.33.330.074 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.203 MiB) 2.33.405.540 I slot launch_slot_: id 0 | task 15276 | processing task, is_child = 0 2.35.231.717 I slot print_timing: id 0 | task 15276 | prompt eval time = 138.04 ms / 509 tokens ( 0.27 ms per token, 3687.36 tokens per second) 2.35.231.723 I slot print_timing: id 0 | task 15276 | eval time = 1688.12 ms / 214 tokens ( 7.93 ms per token, 126.18 tokens per second) 2.35.231.724 I slot print_timing: id 0 | task 15276 | total time = 1826.16 ms / 723 tokens 2.35.231.725 I slot print_timing: id 0 | task 15276 | graphs reused = 14611 2.35.231.726 I slot print_timing: id 0 | task 15276 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.231.760 I slot release: id 0 | task 15276 | stop processing: n_tokens = 754, truncated = 0 2.35.255.463 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 155140140 2.35.255.521 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 2.35.322.506 I slot launch_slot_: id 0 | task 15493 | processing task, is_child = 0 2.37.383.460 I slot print_timing: id 0 | task 15493 | prompt eval time = 146.19 ms / 581 tokens ( 0.25 ms per token, 3974.23 tokens per second) 2.37.383.465 I slot print_timing: id 0 | task 15493 | eval time = 1914.74 ms / 242 tokens ( 7.94 ms per token, 125.87 tokens per second) 2.37.383.466 I slot print_timing: id 0 | task 15493 | total time = 2060.94 ms / 823 tokens 2.37.383.467 I slot print_timing: id 0 | task 15493 | graphs reused = 14850 2.37.383.468 I slot print_timing: id 0 | task 15493 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.383.505 I slot release: id 0 | task 15493 | stop processing: n_tokens = 854, truncated = 0 2.37.402.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 157291885 2.37.403.001 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 2.37.480.111 I slot launch_slot_: id 0 | task 15739 | processing task, is_child = 0 2.39.420.370 I slot print_timing: id 0 | task 15739 | prompt eval time = 192.30 ms / 925 tokens ( 0.21 ms per token, 4810.09 tokens per second) 2.39.420.375 I slot print_timing: id 0 | task 15739 | eval time = 1747.94 ms / 220 tokens ( 7.98 ms per token, 125.29 tokens per second) 2.39.420.376 I slot print_timing: id 0 | task 15739 | total time = 1940.24 ms / 1145 tokens 2.39.420.377 I slot print_timing: id 0 | task 15739 | graphs reused = 15067 2.39.420.378 I slot print_timing: id 0 | task 15739 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.420.424 I slot release: id 0 | task 15739 | stop processing: n_tokens = 1176, truncated = 0 2.39.444.886 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 159328804 2.39.444.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 2.39.520.834 I slot launch_slot_: id 0 | task 15963 | processing task, is_child = 0 2.41.682.470 I slot print_timing: id 0 | task 15963 | prompt eval time = 188.68 ms / 885 tokens ( 0.21 ms per token, 4690.43 tokens per second) 2.41.682.475 I slot print_timing: id 0 | task 15963 | eval time = 1972.94 ms / 245 tokens ( 8.09 ms per token, 123.67 tokens per second) 2.41.682.476 I slot print_timing: id 0 | task 15963 | total time = 2161.62 ms / 1130 tokens 2.41.682.477 I slot print_timing: id 0 | task 15963 | graphs reused = 15309 2.41.682.478 I slot print_timing: id 0 | task 15963 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.682.523 I slot release: id 0 | task 15963 | stop processing: n_tokens = 1161, truncated = 0 2.41.701.794 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 161590903 2.41.701.863 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 2.41.797.556 I slot launch_slot_: id 0 | task 16212 | processing task, is_child = 0 2.42.986.517 I slot print_timing: id 0 | task 16212 | prompt eval time = 122.66 ms / 392 tokens ( 0.31 ms per token, 3195.90 tokens per second) 2.42.986.522 I slot print_timing: id 0 | task 16212 | eval time = 1066.29 ms / 135 tokens ( 7.96 ms per token, 125.67 tokens per second) 2.42.986.523 I slot print_timing: id 0 | task 16212 | total time = 1188.94 ms / 527 tokens 2.42.986.524 I slot print_timing: id 0 | task 16212 | graphs reused = 15441 2.42.986.525 I slot print_timing: id 0 | task 16212 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.986.556 I slot release: id 0 | task 16212 | stop processing: n_tokens = 558, truncated = 0 2.43.012.757 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 162894936 2.43.012.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 2.43.083.295 I slot launch_slot_: id 0 | task 16350 | processing task, is_child = 0 2.43.694.300 I slot print_timing: id 0 | task 16350 | prompt eval time = 117.24 ms / 331 tokens ( 0.35 ms per token, 2823.20 tokens per second) 2.43.694.305 I slot print_timing: id 0 | task 16350 | eval time = 493.74 ms / 63 tokens ( 7.96 ms per token, 125.57 tokens per second) 2.43.694.306 I slot print_timing: id 0 | task 16350 | total time = 610.99 ms / 394 tokens 2.43.694.307 I slot print_timing: id 0 | task 16350 | graphs reused = 15502 2.43.694.308 I slot print_timing: id 0 | task 16350 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.694.335 I slot release: id 0 | task 16350 | stop processing: n_tokens = 425, truncated = 0 2.43.715.961 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 163602715 2.43.716.005 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 2.43.804.837 I slot launch_slot_: id 0 | task 16416 | processing task, is_child = 0 2.44.966.621 I slot print_timing: id 0 | task 16416 | prompt eval time = 119.60 ms / 357 tokens ( 0.34 ms per token, 2984.95 tokens per second) 2.44.966.626 I slot print_timing: id 0 | task 16416 | eval time = 1042.16 ms / 132 tokens ( 7.96 ms per token, 125.70 tokens per second) 2.44.966.627 I slot print_timing: id 0 | task 16416 | total time = 1161.76 ms / 489 tokens 2.44.966.627 I slot print_timing: id 0 | task 16416 | graphs reused = 15631 2.44.966.628 I slot print_timing: id 0 | task 16416 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.966.656 I slot release: id 0 | task 16416 | stop processing: n_tokens = 520, truncated = 0 2.44.993.947 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 164875036 2.44.993.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.739 MiB) 2.45.063.052 I slot launch_slot_: id 0 | task 16551 | processing task, is_child = 0 2.45.555.063 I slot print_timing: id 0 | task 16551 | prompt eval time = 116.72 ms / 315 tokens ( 0.37 ms per token, 2698.65 tokens per second) 2.45.555.069 I slot print_timing: id 0 | task 16551 | eval time = 375.27 ms / 48 tokens ( 7.98 ms per token, 125.24 tokens per second) 2.45.555.070 I slot print_timing: id 0 | task 16551 | total time = 491.99 ms / 363 tokens 2.45.555.070 I slot print_timing: id 0 | task 16551 | graphs reused = 15677 2.45.555.071 I slot print_timing: id 0 | task 16551 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.555.098 I slot release: id 0 | task 16551 | stop processing: n_tokens = 394, truncated = 0 2.45.571.646 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 394, t_last = 165463478 2.45.571.687 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 2.45.645.090 I slot launch_slot_: id 0 | task 16602 | processing task, is_child = 0 2.46.242.117 I slot print_timing: id 0 | task 16602 | prompt eval time = 126.11 ms / 378 tokens ( 0.33 ms per token, 2997.26 tokens per second) 2.46.242.123 I slot print_timing: id 0 | task 16602 | eval time = 470.89 ms / 60 tokens ( 7.98 ms per token, 125.29 tokens per second) 2.46.242.125 I slot print_timing: id 0 | task 16602 | total time = 597.01 ms / 438 tokens 2.46.242.126 I slot print_timing: id 0 | task 16602 | graphs reused = 15735 2.46.242.127 I slot print_timing: id 0 | task 16602 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.242.161 I slot release: id 0 | task 16602 | stop processing: n_tokens = 469, truncated = 0 2.46.269.844 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 166150541 2.46.269.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.527 MiB) 2.46.338.551 I slot launch_slot_: id 0 | task 16665 | processing task, is_child = 0 2.46.664.956 I slot print_timing: id 0 | task 16665 | prompt eval time = 108.56 ms / 295 tokens ( 0.37 ms per token, 2717.39 tokens per second) 2.46.664.962 I slot print_timing: id 0 | task 16665 | eval time = 217.83 ms / 28 tokens ( 8.07 ms per token, 123.95 tokens per second) 2.46.664.963 I slot print_timing: id 0 | task 16665 | total time = 326.39 ms / 323 tokens 2.46.664.964 I slot print_timing: id 0 | task 16665 | graphs reused = 15761 2.46.664.964 I slot print_timing: id 0 | task 16665 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.664.991 I slot release: id 0 | task 16665 | stop processing: n_tokens = 354, truncated = 0 2.46.689.795 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 166573371 2.46.689.834 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 2.46.767.690 I slot launch_slot_: id 0 | task 16696 | processing task, is_child = 0 2.47.634.825 I slot print_timing: id 0 | task 16696 | prompt eval time = 120.50 ms / 337 tokens ( 0.36 ms per token, 2796.59 tokens per second) 2.47.634.831 I slot print_timing: id 0 | task 16696 | eval time = 746.61 ms / 95 tokens ( 7.94 ms per token, 125.90 tokens per second) 2.47.634.832 I slot print_timing: id 0 | task 16696 | total time = 867.12 ms / 432 tokens 2.47.634.832 I slot print_timing: id 0 | task 16696 | graphs reused = 15854 2.47.634.833 I slot print_timing: id 0 | task 16696 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.634.860 I slot release: id 0 | task 16696 | stop processing: n_tokens = 463, truncated = 0 2.47.658.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 463, t_last = 167543240 2.47.700.754 I slot launch_slot_: id 0 | task 16794 | processing task, is_child = 0 2.48.635.143 I slot print_timing: id 0 | task 16794 | prompt eval time = 115.32 ms / 325 tokens ( 0.35 ms per token, 2818.20 tokens per second) 2.48.635.148 I slot print_timing: id 0 | task 16794 | eval time = 819.05 ms / 104 tokens ( 7.95 ms per token, 125.76 tokens per second) 2.48.635.149 I slot print_timing: id 0 | task 16794 | total time = 934.37 ms / 429 tokens 2.48.635.150 I slot print_timing: id 0 | task 16794 | graphs reused = 15956 2.48.635.151 I slot print_timing: id 0 | task 16794 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.635.179 I slot release: id 0 | task 16794 | stop processing: n_tokens = 460, truncated = 0 2.48.655.351 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.070 2.48.655.389 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 2.48.723.948 I slot launch_slot_: id 0 | task 16901 | processing task, is_child = 0 2.51.014.231 I slot print_timing: id 0 | task 16901 | prompt eval time = 107.57 ms / 264 tokens ( 0.41 ms per token, 2454.31 tokens per second) 2.51.014.237 I slot print_timing: id 0 | task 16901 | eval time = 2182.70 ms / 276 tokens ( 7.94 ms per token, 125.99 tokens per second) 2.51.014.238 I slot print_timing: id 0 | task 16901 | total time = 2290.26 ms / 540 tokens 2.51.014.239 I slot print_timing: id 0 | task 16901 | graphs reused = 16229 2.51.014.240 I slot print_timing: id 0 | task 16901 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.014.265 I slot release: id 0 | task 16901 | stop processing: n_tokens = 571, truncated = 0 2.51.039.850 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 571, t_last = 170922645 2.51.039.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 2.51.104.412 I slot launch_slot_: id 0 | task 17180 | processing task, is_child = 0 2.51.269.818 I slot print_timing: id 0 | task 17180 | prompt eval time = 113.56 ms / 331 tokens ( 0.34 ms per token, 2914.63 tokens per second) 2.51.269.824 I slot print_timing: id 0 | task 17180 | eval time = 51.82 ms / 7 tokens ( 8.64 ms per token, 115.78 tokens per second) 2.51.269.825 I slot print_timing: id 0 | task 17180 | total time = 165.39 ms / 338 tokens 2.51.269.826 I slot print_timing: id 0 | task 17180 | graphs reused = 16234 2.51.269.827 I slot print_timing: id 0 | task 17180 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.269.856 I slot release: id 0 | task 17180 | stop processing: n_tokens = 369, truncated = 0 2.51.291.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 369, t_last = 171178236 2.51.291.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 2.51.379.875 I slot launch_slot_: id 0 | task 17190 | processing task, is_child = 0 2.52.448.871 I slot print_timing: id 0 | task 17190 | prompt eval time = 118.10 ms / 333 tokens ( 0.35 ms per token, 2819.74 tokens per second) 2.52.448.876 I slot print_timing: id 0 | task 17190 | eval time = 950.88 ms / 121 tokens ( 7.92 ms per token, 126.20 tokens per second) 2.52.448.877 I slot print_timing: id 0 | task 17190 | total time = 1068.98 ms / 454 tokens 2.52.448.878 I slot print_timing: id 0 | task 17190 | graphs reused = 16353 2.52.448.879 I slot print_timing: id 0 | task 17190 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.448.907 I slot release: id 0 | task 17190 | stop processing: n_tokens = 485, truncated = 0 2.52.462.509 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 485, t_last = 172357287 2.52.462.554 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 2.52.532.040 I slot launch_slot_: id 0 | task 17314 | processing task, is_child = 0 2.55.649.122 I slot print_timing: id 0 | task 17314 | n_gen = 380, tg = 126.29 t/s, tg_3s = 126.63 t/s 2.58.312.437 I slot print_timing: id 0 | task 17314 | prompt eval time = 116.14 ms / 346 tokens ( 0.34 ms per token, 2979.11 tokens per second) 2.58.312.443 I slot print_timing: id 0 | task 17314 | eval time = 5664.24 ms / 715 tokens ( 7.93 ms per token, 126.05 tokens per second) 2.58.312.444 I slot print_timing: id 0 | task 17314 | total time = 5780.38 ms / 1061 tokens 2.58.312.445 I slot print_timing: id 0 | task 17314 | graphs reused = 17063 2.58.312.446 I slot print_timing: id 0 | task 17314 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.312.474 I slot release: id 0 | task 17314 | stop processing: n_tokens = 1092, truncated = 0 2.58.334.020 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1092, t_last = 178220854 2.58.334.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 2.58.407.267 I slot launch_slot_: id 0 | task 18032 | processing task, is_child = 0 2.58.832.714 I slot print_timing: id 0 | task 18032 | prompt eval time = 113.23 ms / 325 tokens ( 0.35 ms per token, 2870.24 tokens per second) 2.58.832.720 I slot print_timing: id 0 | task 18032 | eval time = 312.20 ms / 40 tokens ( 8.01 ms per token, 124.92 tokens per second) 2.58.832.721 I slot print_timing: id 0 | task 18032 | total time = 425.43 ms / 365 tokens 2.58.832.722 I slot print_timing: id 0 | task 18032 | graphs reused = 17101 2.58.832.723 I slot print_timing: id 0 | task 18032 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.832.752 I slot release: id 0 | task 18032 | stop processing: n_tokens = 396, truncated = 0 2.58.849.809 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 178741132 2.58.849.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 2.58.917.967 I slot launch_slot_: id 0 | task 18075 | processing task, is_child = 0 3.00.712.514 I slot print_timing: id 0 | task 18075 | prompt eval time = 112.60 ms / 322 tokens ( 0.35 ms per token, 2859.63 tokens per second) 3.00.712.520 I slot print_timing: id 0 | task 18075 | eval time = 1681.93 ms / 213 tokens ( 7.93 ms per token, 126.05 tokens per second) 3.00.712.521 I slot print_timing: id 0 | task 18075 | total time = 1794.53 ms / 535 tokens 3.00.712.522 I slot print_timing: id 0 | task 18075 | graphs reused = 17311 3.00.712.522 I slot print_timing: id 0 | task 18075 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.712.550 I slot release: id 0 | task 18075 | stop processing: n_tokens = 566, truncated = 0 3.00.729.874 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 180620930 3.00.729.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 3.00.800.511 I slot launch_slot_: id 0 | task 18291 | processing task, is_child = 0 3.02.800.986 I slot print_timing: id 0 | task 18291 | prompt eval time = 113.64 ms / 338 tokens ( 0.34 ms per token, 2974.41 tokens per second) 3.02.800.992 I slot print_timing: id 0 | task 18291 | eval time = 1886.82 ms / 239 tokens ( 7.93 ms per token, 126.14 tokens per second) 3.02.800.993 I slot print_timing: id 0 | task 18291 | total time = 2000.46 ms / 577 tokens 3.02.800.993 I slot print_timing: id 0 | task 18291 | graphs reused = 17547 3.02.800.994 I slot print_timing: id 0 | task 18291 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.801.021 I slot release: id 0 | task 18291 | stop processing: n_tokens = 608, truncated = 0 3.02.822.136 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 608, t_last = 182709401 3.02.866.178 I slot launch_slot_: id 0 | task 18533 | processing task, is_child = 0 3.05.604.920 I slot print_timing: id 0 | task 18533 | prompt eval time = 113.93 ms / 347 tokens ( 0.33 ms per token, 3045.70 tokens per second) 3.05.604.926 I slot print_timing: id 0 | task 18533 | eval time = 2624.79 ms / 332 tokens ( 7.93 ms per token, 126.11 tokens per second) 3.05.604.927 I slot print_timing: id 0 | task 18533 | total time = 2738.72 ms / 679 tokens 3.05.604.927 I slot print_timing: id 0 | task 18533 | graphs reused = 17876 3.05.604.929 I slot print_timing: id 0 | task 18533 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.604.963 I slot release: id 0 | task 18533 | stop processing: n_tokens = 710, truncated = 0 3.05.620.764 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 185513343 3.05.620.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 3.05.696.214 I slot launch_slot_: id 0 | task 18868 | processing task, is_child = 0 3.07.665.963 I slot print_timing: id 0 | task 18868 | prompt eval time = 120.56 ms / 331 tokens ( 0.36 ms per token, 2745.52 tokens per second) 3.07.665.968 I slot print_timing: id 0 | task 18868 | eval time = 1849.17 ms / 229 tokens ( 8.11 ms per token, 123.30 tokens per second) 3.07.665.969 I slot print_timing: id 0 | task 18868 | total time = 1969.73 ms / 560 tokens 3.07.665.970 I slot print_timing: id 0 | task 18868 | graphs reused = 18102 3.07.665.971 I slot print_timing: id 0 | task 18868 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.666.002 I slot release: id 0 | task 18868 | stop processing: n_tokens = 591, truncated = 0 3.07.693.231 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 187574382 3.07.693.283 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.277 MiB) 3.07.772.193 I slot launch_slot_: id 0 | task 19100 | processing task, is_child = 0 3.08.914.888 I slot print_timing: id 0 | task 19100 | prompt eval time = 119.12 ms / 345 tokens ( 0.35 ms per token, 2896.19 tokens per second) 3.08.914.894 I slot print_timing: id 0 | task 19100 | eval time = 1023.55 ms / 127 tokens ( 8.12 ms per token, 123.10 tokens per second) 3.08.914.895 I slot print_timing: id 0 | task 19100 | total time = 1142.67 ms / 472 tokens 3.08.914.895 I slot print_timing: id 0 | task 19100 | graphs reused = 18227 3.08.914.896 I slot print_timing: id 0 | task 19100 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.914.926 I slot release: id 0 | task 19100 | stop processing: n_tokens = 503, truncated = 0 3.08.939.724 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 188823306 3.08.939.766 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 3.09.009.497 I slot launch_slot_: id 0 | task 19230 | processing task, is_child = 0 3.09.642.671 I slot print_timing: id 0 | task 19230 | prompt eval time = 113.47 ms / 320 tokens ( 0.35 ms per token, 2820.20 tokens per second) 3.09.642.676 I slot print_timing: id 0 | task 19230 | eval time = 519.69 ms / 65 tokens ( 8.12 ms per token, 123.15 tokens per second) 3.09.642.677 I slot print_timing: id 0 | task 19230 | total time = 633.15 ms / 385 tokens 3.09.642.678 I slot print_timing: id 0 | task 19230 | graphs reused = 18290 3.09.642.679 I slot print_timing: id 0 | task 19230 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.642.707 I slot release: id 0 | task 19230 | stop processing: n_tokens = 416, truncated = 0 3.09.662.453 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 189551087 3.09.662.492 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 3.09.743.650 I slot launch_slot_: id 0 | task 19298 | processing task, is_child = 0 3.10.270.391 I slot print_timing: id 0 | task 19298 | prompt eval time = 116.31 ms / 297 tokens ( 0.39 ms per token, 2553.61 tokens per second) 3.10.270.397 I slot print_timing: id 0 | task 19298 | eval time = 410.41 ms / 47 tokens ( 8.92 ms per token, 112.08 tokens per second) 3.10.270.398 I slot print_timing: id 0 | task 19298 | total time = 526.72 ms / 344 tokens 3.10.270.399 I slot print_timing: id 0 | task 19298 | graphs reused = 18335 3.10.270.400 I slot print_timing: id 0 | task 19298 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.270.427 I slot release: id 0 | task 19298 | stop processing: n_tokens = 375, truncated = 0 3.10.286.711 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 190178807 3.10.286.754 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.089 MiB) 3.10.354.777 I slot launch_slot_: id 0 | task 19348 | processing task, is_child = 0 3.12.071.549 I slot print_timing: id 0 | task 19348 | prompt eval time = 116.28 ms / 343 tokens ( 0.34 ms per token, 2949.78 tokens per second) 3.12.071.555 I slot print_timing: id 0 | task 19348 | eval time = 1600.47 ms / 197 tokens ( 8.17 ms per token, 122.46 tokens per second) 3.12.071.556 I slot print_timing: id 0 | task 19348 | total time = 1716.75 ms / 540 tokens 3.12.071.557 I slot print_timing: id 0 | task 19348 | graphs reused = 18529 3.12.071.558 I slot print_timing: id 0 | task 19348 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.071.587 I slot release: id 0 | task 19348 | stop processing: n_tokens = 571, truncated = 0 3.12.090.725 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 571, t_last = 191979966 3.12.135.610 I slot launch_slot_: id 0 | task 19548 | processing task, is_child = 0 3.12.912.658 I slot print_timing: id 0 | task 19548 | prompt eval time = 119.38 ms / 371 tokens ( 0.32 ms per token, 3107.80 tokens per second) 3.12.912.665 I slot print_timing: id 0 | task 19548 | eval time = 657.65 ms / 82 tokens ( 8.12 ms per token, 123.17 tokens per second) 3.12.912.666 I slot print_timing: id 0 | task 19548 | total time = 777.03 ms / 453 tokens 3.12.912.667 I slot print_timing: id 0 | task 19548 | graphs reused = 18609 3.12.912.668 I slot print_timing: id 0 | task 19548 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.912.703 I slot release: id 0 | task 19548 | stop processing: n_tokens = 484, truncated = 0 3.12.931.988 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 484, t_last = 192821083 3.12.932.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 3.12.998.579 I slot launch_slot_: id 0 | task 19633 | processing task, is_child = 0 3.14.263.530 I slot print_timing: id 0 | task 19633 | prompt eval time = 109.45 ms / 292 tokens ( 0.37 ms per token, 2667.84 tokens per second) 3.14.263.536 I slot print_timing: id 0 | task 19633 | eval time = 1155.48 ms / 145 tokens ( 8.02 ms per token, 124.62 tokens per second) 3.14.263.537 I slot print_timing: id 0 | task 19633 | total time = 1264.93 ms / 437 tokens 3.14.263.538 I slot print_timing: id 0 | task 19633 | graphs reused = 18752 3.14.263.538 I slot print_timing: id 0 | task 19633 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.263.564 I slot release: id 0 | task 19633 | stop processing: n_tokens = 468, truncated = 0 3.14.285.457 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 468, t_last = 194171944 3.14.285.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 3.14.363.038 I slot launch_slot_: id 0 | task 19781 | processing task, is_child = 0 3.15.017.911 I slot print_timing: id 0 | task 19781 | prompt eval time = 110.46 ms / 301 tokens ( 0.37 ms per token, 2724.89 tokens per second) 3.15.017.918 I slot print_timing: id 0 | task 19781 | eval time = 544.39 ms / 68 tokens ( 8.13 ms per token, 123.07 tokens per second) 3.15.017.919 I slot print_timing: id 0 | task 19781 | total time = 654.85 ms / 369 tokens 3.15.017.920 I slot print_timing: id 0 | task 19781 | graphs reused = 18818 3.15.017.920 I slot print_timing: id 0 | task 19781 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.017.950 I slot release: id 0 | task 19781 | stop processing: n_tokens = 400, truncated = 0 3.15.035.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 194926329 3.15.035.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 3.15.106.098 I slot launch_slot_: id 0 | task 19852 | processing task, is_child = 0 3.15.937.088 I slot print_timing: id 0 | task 19852 | prompt eval time = 111.08 ms / 303 tokens ( 0.37 ms per token, 2727.79 tokens per second) 3.15.937.093 I slot print_timing: id 0 | task 19852 | eval time = 719.89 ms / 89 tokens ( 8.18 ms per token, 122.24 tokens per second) 3.15.937.095 I slot print_timing: id 0 | task 19852 | total time = 830.97 ms / 392 tokens 3.15.937.098 I slot print_timing: id 0 | task 19852 | graphs reused = 18905 3.15.937.099 I slot print_timing: id 0 | task 19852 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.937.126 I slot release: id 0 | task 19852 | stop processing: n_tokens = 423, truncated = 0 3.15.955.103 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 423, t_last = 195845506 3.15.955.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 3.16.025.354 I slot launch_slot_: id 0 | task 19944 | processing task, is_child = 0 3.16.295.435 I slot print_timing: id 0 | task 19944 | prompt eval time = 114.04 ms / 321 tokens ( 0.36 ms per token, 2814.90 tokens per second) 3.16.295.441 I slot print_timing: id 0 | task 19944 | eval time = 156.03 ms / 20 tokens ( 8.21 ms per token, 121.77 tokens per second) 3.16.295.442 I slot print_timing: id 0 | task 19944 | total time = 270.06 ms / 341 tokens 3.16.295.443 I slot print_timing: id 0 | task 19944 | graphs reused = 18923 3.16.295.444 I slot print_timing: id 0 | task 19944 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.295.472 I slot release: id 0 | task 19944 | stop processing: n_tokens = 372, truncated = 0 3.16.316.145 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 196203852 3.16.316.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 3.16.388.305 I slot launch_slot_: id 0 | task 19967 | processing task, is_child = 0 3.16.979.797 I slot print_timing: id 0 | task 19967 | prompt eval time = 119.39 ms / 322 tokens ( 0.37 ms per token, 2696.95 tokens per second) 3.16.979.803 I slot print_timing: id 0 | task 19967 | eval time = 472.08 ms / 59 tokens ( 8.14 ms per token, 122.86 tokens per second) 3.16.979.804 I slot print_timing: id 0 | task 19967 | total time = 591.48 ms / 381 tokens 3.16.979.804 I slot print_timing: id 0 | task 19967 | graphs reused = 18980 3.16.979.805 I slot print_timing: id 0 | task 19967 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.979.835 I slot release: id 0 | task 19967 | stop processing: n_tokens = 412, truncated = 0 3.17.001.238 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 412, t_last = 196888215 3.17.001.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.795 MiB) 3.17.066.768 I slot launch_slot_: id 0 | task 20029 | processing task, is_child = 0 3.18.068.928 I slot print_timing: id 0 | task 20029 | prompt eval time = 118.59 ms / 323 tokens ( 0.37 ms per token, 2723.76 tokens per second) 3.18.068.933 I slot print_timing: id 0 | task 20029 | eval time = 883.55 ms / 112 tokens ( 7.96 ms per token, 125.63 tokens per second) 3.18.068.934 I slot print_timing: id 0 | task 20029 | total time = 1002.14 ms / 435 tokens 3.18.068.935 I slot print_timing: id 0 | task 20029 | graphs reused = 19090 3.18.068.936 I slot print_timing: id 0 | task 20029 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.068.963 I slot release: id 0 | task 20029 | stop processing: n_tokens = 466, truncated = 0 3.18.091.099 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 197977343 3.18.091.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 3.18.158.772 I slot launch_slot_: id 0 | task 20144 | processing task, is_child = 0 3.21.274.383 I slot print_timing: id 0 | task 20144 | n_gen = 380, tg = 126.28 t/s, tg_3s = 126.62 t/s 3.24.189.896 I slot print_timing: id 0 | task 20144 | prompt eval time = 114.38 ms / 321 tokens ( 0.36 ms per token, 2806.39 tokens per second) 3.24.189.901 I slot print_timing: id 0 | task 20144 | eval time = 5916.72 ms / 747 tokens ( 7.93 ms per token, 126.08 tokens per second) 3.24.189.902 I slot print_timing: id 0 | task 20144 | total time = 6031.10 ms / 1068 tokens 3.24.189.903 I slot print_timing: id 0 | task 20144 | graphs reused = 19832 3.24.189.904 I slot print_timing: id 0 | task 20144 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.189.933 I slot release: id 0 | task 20144 | stop processing: n_tokens = 1099, truncated = 0 3.24.208.210 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1099, t_last = 204098312 3.24.208.286 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.825 MiB) 3.24.280.100 I slot launch_slot_: id 0 | task 20894 | processing task, is_child = 0 3.26.343.879 I slot print_timing: id 0 | task 20894 | prompt eval time = 112.93 ms / 322 tokens ( 0.35 ms per token, 2851.35 tokens per second) 3.26.343.884 I slot print_timing: id 0 | task 20894 | eval time = 1950.83 ms / 247 tokens ( 7.93 ms per token, 126.10 tokens per second) 3.26.343.885 I slot print_timing: id 0 | task 20894 | total time = 2063.76 ms / 569 tokens 3.26.343.886 I slot print_timing: id 0 | task 20894 | graphs reused = 20076 3.26.343.887 I slot print_timing: id 0 | task 20894 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.343.916 I slot release: id 0 | task 20894 | stop processing: n_tokens = 600, truncated = 0 3.26.357.321 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 600, t_last = 206252296 3.26.357.372 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.171 MiB) 3.26.424.324 I slot launch_slot_: id 0 | task 21144 | processing task, is_child = 0 3.26.897.305 I slot print_timing: id 0 | task 21144 | prompt eval time = 113.58 ms / 337 tokens ( 0.34 ms per token, 2967.10 tokens per second) 3.26.897.311 I slot print_timing: id 0 | task 21144 | eval time = 359.38 ms / 46 tokens ( 7.99 ms per token, 125.21 tokens per second) 3.26.897.312 I slot print_timing: id 0 | task 21144 | total time = 472.96 ms / 383 tokens 3.26.897.313 I slot print_timing: id 0 | task 21144 | graphs reused = 20120 3.26.897.314 I slot print_timing: id 0 | task 21144 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.897.341 I slot release: id 0 | task 21144 | stop processing: n_tokens = 414, truncated = 0 3.26.916.895 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 206805721 3.26.916.938 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 3.26.985.607 I slot launch_slot_: id 0 | task 21193 | processing task, is_child = 0 3.27.466.351 I slot print_timing: id 0 | task 21193 | prompt eval time = 113.07 ms / 325 tokens ( 0.35 ms per token, 2874.43 tokens per second) 3.27.466.357 I slot print_timing: id 0 | task 21193 | eval time = 367.66 ms / 47 tokens ( 7.99 ms per token, 125.12 tokens per second) 3.27.466.358 I slot print_timing: id 0 | task 21193 | total time = 480.72 ms / 372 tokens 3.27.466.359 I slot print_timing: id 0 | task 21193 | graphs reused = 20165 3.27.466.359 I slot print_timing: id 0 | task 21193 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.466.387 I slot release: id 0 | task 21193 | stop processing: n_tokens = 403, truncated = 0 3.27.491.857 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 207374767 3.27.491.899 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.983 MiB) 3.27.561.063 I slot launch_slot_: id 0 | task 21243 | processing task, is_child = 0 3.28.083.917 I slot print_timing: id 0 | task 21243 | prompt eval time = 116.78 ms / 331 tokens ( 0.35 ms per token, 2834.32 tokens per second) 3.28.083.923 I slot print_timing: id 0 | task 21243 | eval time = 406.05 ms / 52 tokens ( 7.96 ms per token, 125.60 tokens per second) 3.28.083.924 I slot print_timing: id 0 | task 21243 | total time = 522.84 ms / 383 tokens 3.28.083.924 I slot print_timing: id 0 | task 21243 | graphs reused = 20215 3.28.083.925 I slot print_timing: id 0 | task 21243 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.083.955 I slot release: id 0 | task 21243 | stop processing: n_tokens = 414, truncated = 0 3.28.110.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 207992335 3.28.110.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.889 MiB) 3.28.176.272 I slot launch_slot_: id 0 | task 21298 | processing task, is_child = 0 3.29.398.508 I slot print_timing: id 0 | task 21298 | prompt eval time = 113.53 ms / 336 tokens ( 0.34 ms per token, 2959.65 tokens per second) 3.29.398.514 I slot print_timing: id 0 | task 21298 | eval time = 1108.69 ms / 141 tokens ( 7.92 ms per token, 126.28 tokens per second) 3.29.398.515 I slot print_timing: id 0 | task 21298 | total time = 1222.22 ms / 477 tokens 3.29.398.516 I slot print_timing: id 0 | task 21298 | graphs reused = 20354 3.29.398.516 I slot print_timing: id 0 | task 21298 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.398.544 I slot release: id 0 | task 21298 | stop processing: n_tokens = 508, truncated = 0 3.29.417.897 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 508, t_last = 209306924 3.29.417.947 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.360 MiB) 3.29.481.757 I slot launch_slot_: id 0 | task 21442 | processing task, is_child = 0 3.29.742.350 I slot print_timing: id 0 | task 21442 | prompt eval time = 114.19 ms / 349 tokens ( 0.33 ms per token, 3056.23 tokens per second) 3.29.742.356 I slot print_timing: id 0 | task 21442 | eval time = 146.38 ms / 19 tokens ( 8.13 ms per token, 122.97 tokens per second) 3.29.742.356 I slot print_timing: id 0 | task 21442 | total time = 260.57 ms / 368 tokens 3.29.742.357 I slot print_timing: id 0 | task 21442 | graphs reused = 20371 3.29.742.358 I slot print_timing: id 0 | task 21442 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.742.387 I slot release: id 0 | task 21442 | stop processing: n_tokens = 399, truncated = 0 3.29.762.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 399, t_last = 209650767 3.29.762.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.043 MiB) 3.29.834.234 I slot launch_slot_: id 0 | task 21464 | processing task, is_child = 0 3.32.952.114 I slot print_timing: id 0 | task 21464 | n_gen = 380, tg = 126.25 t/s, tg_3s = 126.58 t/s 3.35.105.012 I slot print_timing: id 0 | task 21464 | prompt eval time = 115.81 ms / 336 tokens ( 0.34 ms per token, 2901.30 tokens per second) 3.35.105.017 I slot print_timing: id 0 | task 21464 | eval time = 5154.95 ms / 651 tokens ( 7.93 ms per token, 126.09 tokens per second) 3.35.105.018 I slot print_timing: id 0 | task 21464 | total time = 5270.76 ms / 987 tokens 3.35.105.019 I slot print_timing: id 0 | task 21464 | graphs reused = 21018 3.35.105.020 I slot print_timing: id 0 | task 21464 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.105.050 I slot release: id 0 | task 21464 | stop processing: n_tokens = 1018, truncated = 0 3.35.108.771 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1018, t_last = 215013430 3.35.108.831 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.671 MiB) 3.35.184.434 I slot launch_slot_: id 0 | task 22118 | processing task, is_child = 0 3.38.302.352 I slot print_timing: id 0 | task 22118 | n_gen = 380, tg = 126.19 t/s, tg_3s = 126.53 t/s 3.39.406.457 I slot print_timing: id 0 | task 22118 | prompt eval time = 114.60 ms / 349 tokens ( 0.33 ms per token, 3045.48 tokens per second) 3.39.406.462 I slot print_timing: id 0 | task 22118 | eval time = 4107.41 ms / 519 tokens ( 7.93 ms per token, 126.11 tokens per second) 3.39.406.463 I slot print_timing: id 0 | task 22118 | total time = 4222.00 ms / 868 tokens 3.39.406.464 I slot print_timing: id 0 | task 22118 | graphs reused = 21533 3.39.406.465 I slot print_timing: id 0 | task 22118 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.406.494 I slot release: id 0 | task 22118 | stop processing: n_tokens = 899, truncated = 0 3.39.426.329 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 219314873 3.39.426.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.654 MiB) 3.39.498.767 I slot launch_slot_: id 0 | task 22640 | processing task, is_child = 0 3.40.043.465 I slot print_timing: id 0 | task 22640 | prompt eval time = 114.28 ms / 349 tokens ( 0.33 ms per token, 3053.88 tokens per second) 3.40.043.470 I slot print_timing: id 0 | task 22640 | eval time = 430.40 ms / 55 tokens ( 7.97 ms per token, 125.47 tokens per second) 3.40.043.471 I slot print_timing: id 0 | task 22640 | total time = 544.68 ms / 404 tokens 3.40.043.472 I slot print_timing: id 0 | task 22640 | graphs reused = 21586 3.40.043.473 I slot print_timing: id 0 | task 22640 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.043.501 I slot release: id 0 | task 22640 | stop processing: n_tokens = 435, truncated = 0 3.40.067.414 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 435, t_last = 219951881 3.40.067.456 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.888 MiB) 3.40.132.343 I slot launch_slot_: id 0 | task 22698 | processing task, is_child = 0 3.40.405.622 I slot print_timing: id 0 | task 22698 | prompt eval time = 118.91 ms / 385 tokens ( 0.31 ms per token, 3237.72 tokens per second) 3.40.405.627 I slot print_timing: id 0 | task 22698 | eval time = 154.35 ms / 20 tokens ( 8.12 ms per token, 123.10 tokens per second) 3.40.405.628 I slot print_timing: id 0 | task 22698 | total time = 273.26 ms / 405 tokens 3.40.405.629 I slot print_timing: id 0 | task 22698 | graphs reused = 21604 3.40.405.630 I slot print_timing: id 0 | task 22698 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.405.660 I slot release: id 0 | task 22698 | stop processing: n_tokens = 436, truncated = 0 3.40.429.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 436, t_last = 220314040 3.40.429.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 3.40.502.350 I slot launch_slot_: id 0 | task 22721 | processing task, is_child = 0 3.41.065.722 I slot print_timing: id 0 | task 22721 | prompt eval time = 116.84 ms / 328 tokens ( 0.36 ms per token, 2807.26 tokens per second) 3.41.065.727 I slot print_timing: id 0 | task 22721 | eval time = 446.51 ms / 57 tokens ( 7.97 ms per token, 125.42 tokens per second) 3.41.065.728 I slot print_timing: id 0 | task 22721 | total time = 563.36 ms / 385 tokens 3.41.065.729 I slot print_timing: id 0 | task 22721 | graphs reused = 21659 3.41.065.730 I slot print_timing: id 0 | task 22721 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.065.756 I slot release: id 0 | task 22721 | stop processing: n_tokens = 416, truncated = 0