$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-9B-GGUF\snapshots\3885219b6810b007914f3a7950a8d1b469d598a5\Qwen3.5-9B-UD-Q2_K_XL.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.098.187 I srv llama_server: initializing ... 0.00.098.193 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.098.299 I srv init_listene: The UI is disabled 0.00.098.301 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.098.393 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) 0.00.106.833 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-9B-GGUF\snapshots\3885219b6810b007914f3a7950a8d1b469d598a5\Qwen3.5-9B-UD-Q2_K_XL.gguf' 0.02.223.741 I cmn init: llama threadpool init, n_threads = 8 0.02.305.812 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.310.594 I srv llama_server: model loaded 0.02.310.600 I srv llama_server: listening on http://127.0.0.1:8089 0.02.552.878 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.553.024 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.142.675 I slot print_timing: id 0 | task 0 | prompt eval time = 180.77 ms / 368 tokens ( 0.49 ms per token, 2035.71 tokens per second) 0.03.142.682 I slot print_timing: id 0 | task 0 | eval time = 408.86 ms / 53 tokens ( 7.86 ms per token, 127.18 tokens per second) 0.03.142.683 I slot print_timing: id 0 | task 0 | total time = 589.63 ms / 421 tokens 0.03.142.690 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.03.142.691 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.142.722 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.03.146.374 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 3046610 0.03.177.136 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.03.636.070 I slot print_timing: id 0 | task 56 | prompt eval time = 138.56 ms / 322 tokens ( 0.43 ms per token, 2323.90 tokens per second) 0.03.636.075 I slot print_timing: id 0 | task 56 | eval time = 320.35 ms / 42 tokens ( 7.81 ms per token, 127.98 tokens per second) 0.03.636.076 I slot print_timing: id 0 | task 56 | total time = 458.91 ms / 364 tokens 0.03.636.077 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.03.636.078 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.636.103 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.03.658.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 3539991 0.03.685.443 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.04.150.428 I slot print_timing: id 0 | task 101 | prompt eval time = 142.41 ms / 365 tokens ( 0.39 ms per token, 2563.02 tokens per second) 0.04.150.435 I slot print_timing: id 0 | task 101 | eval time = 322.55 ms / 42 tokens ( 7.87 ms per token, 127.11 tokens per second) 0.04.150.436 I slot print_timing: id 0 | task 101 | total time = 464.96 ms / 407 tokens 0.04.150.437 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.04.150.437 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.150.466 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.04.173.050 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 4054355 0.04.198.801 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.04.794.341 I slot print_timing: id 0 | task 146 | prompt eval time = 149.80 ms / 397 tokens ( 0.38 ms per token, 2650.15 tokens per second) 0.04.794.348 I slot print_timing: id 0 | task 146 | eval time = 445.71 ms / 58 tokens ( 7.82 ms per token, 127.88 tokens per second) 0.04.794.349 I slot print_timing: id 0 | task 146 | total time = 595.52 ms / 455 tokens 0.04.794.350 I slot print_timing: id 0 | task 146 | graphs reused = 188 0.04.794.351 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.794.385 I slot release: id 0 | task 146 | stop processing: n_tokens = 454, truncated = 0 0.04.811.515 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.099 0.04.837.689 I slot launch_slot_: id 0 | task 207 | processing task, is_child = 0 0.05.401.245 I slot print_timing: id 0 | task 207 | prompt eval time = 143.18 ms / 383 tokens ( 0.37 ms per token, 2674.99 tokens per second) 0.05.401.251 I slot print_timing: id 0 | task 207 | eval time = 420.36 ms / 55 tokens ( 7.78 ms per token, 128.46 tokens per second) 0.05.401.253 I slot print_timing: id 0 | task 207 | total time = 563.54 ms / 438 tokens 0.05.401.255 I slot print_timing: id 0 | task 207 | graphs reused = 241 0.05.401.255 I slot print_timing: id 0 | task 207 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.401.283 I slot release: id 0 | task 207 | stop processing: n_tokens = 437, truncated = 0 0.05.418.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 5305171 0.05.444.238 I slot launch_slot_: id 0 | task 265 | processing task, is_child = 0 0.06.041.121 I slot print_timing: id 0 | task 265 | prompt eval time = 147.87 ms / 372 tokens ( 0.40 ms per token, 2515.81 tokens per second) 0.06.041.127 I slot print_timing: id 0 | task 265 | eval time = 449.00 ms / 55 tokens ( 8.31 ms per token, 120.27 tokens per second) 0.06.041.128 I slot print_timing: id 0 | task 265 | total time = 596.86 ms / 427 tokens 0.06.041.129 I slot print_timing: id 0 | task 265 | graphs reused = 294 0.06.041.129 I slot print_timing: id 0 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.041.157 I slot release: id 0 | task 265 | stop processing: n_tokens = 426, truncated = 0 0.06.060.054 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 5945045 0.06.085.684 I slot launch_slot_: id 0 | task 323 | processing task, is_child = 0 0.06.670.987 I slot print_timing: id 0 | task 323 | prompt eval time = 165.52 ms / 422 tokens ( 0.39 ms per token, 2549.48 tokens per second) 0.06.670.993 I slot print_timing: id 0 | task 323 | eval time = 419.76 ms / 55 tokens ( 7.77 ms per token, 128.64 tokens per second) 0.06.670.994 I slot print_timing: id 0 | task 323 | total time = 585.28 ms / 477 tokens 0.06.670.995 I slot print_timing: id 0 | task 323 | graphs reused = 347 0.06.670.995 I slot print_timing: id 0 | task 323 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.671.024 I slot release: id 0 | task 323 | stop processing: n_tokens = 476, truncated = 0 0.06.699.802 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 6574913 0.06.726.231 I slot launch_slot_: id 0 | task 381 | processing task, is_child = 0 0.07.452.412 I slot print_timing: id 0 | task 381 | prompt eval time = 169.99 ms / 470 tokens ( 0.36 ms per token, 2764.93 tokens per second) 0.07.452.417 I slot print_timing: id 0 | task 381 | eval time = 556.17 ms / 72 tokens ( 7.83 ms per token, 127.66 tokens per second) 0.07.452.418 I slot print_timing: id 0 | task 381 | total time = 726.16 ms / 542 tokens 0.07.452.419 I slot print_timing: id 0 | task 381 | graphs reused = 416 0.07.452.420 I slot print_timing: id 0 | task 381 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.452.450 I slot release: id 0 | task 381 | stop processing: n_tokens = 541, truncated = 0 0.07.466.659 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 7356338 0.07.493.435 I slot launch_slot_: id 0 | task 456 | processing task, is_child = 0 0.07.992.896 I slot print_timing: id 0 | task 456 | prompt eval time = 139.22 ms / 345 tokens ( 0.40 ms per token, 2478.02 tokens per second) 0.07.992.902 I slot print_timing: id 0 | task 456 | eval time = 360.22 ms / 47 tokens ( 7.83 ms per token, 127.70 tokens per second) 0.07.992.903 I slot print_timing: id 0 | task 456 | total time = 499.44 ms / 392 tokens 0.07.992.904 I slot print_timing: id 0 | task 456 | graphs reused = 461 0.07.992.905 I slot print_timing: id 0 | task 456 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.992.931 I slot release: id 0 | task 456 | stop processing: n_tokens = 391, truncated = 0 0.08.011.553 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 7896819 0.08.036.998 I slot launch_slot_: id 0 | task 506 | processing task, is_child = 0 0.08.490.296 I slot print_timing: id 0 | task 506 | prompt eval time = 141.34 ms / 364 tokens ( 0.39 ms per token, 2575.30 tokens per second) 0.08.490.302 I slot print_timing: id 0 | task 506 | eval time = 311.94 ms / 41 tokens ( 7.80 ms per token, 128.23 tokens per second) 0.08.490.303 I slot print_timing: id 0 | task 506 | total time = 453.28 ms / 405 tokens 0.08.490.304 I slot print_timing: id 0 | task 506 | graphs reused = 500 0.08.490.305 I slot print_timing: id 0 | task 506 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.490.332 I slot release: id 0 | task 506 | stop processing: n_tokens = 404, truncated = 0 0.08.507.097 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 8394220 0.08.532.776 I slot launch_slot_: id 0 | task 550 | processing task, is_child = 0 0.09.182.590 I slot print_timing: id 0 | task 550 | prompt eval time = 146.00 ms / 376 tokens ( 0.39 ms per token, 2575.31 tokens per second) 0.09.182.596 I slot print_timing: id 0 | task 550 | eval time = 503.79 ms / 62 tokens ( 8.26 ms per token, 121.08 tokens per second) 0.09.182.597 I slot print_timing: id 0 | task 550 | total time = 649.80 ms / 438 tokens 0.09.182.597 I slot print_timing: id 0 | task 550 | graphs reused = 560 0.09.182.598 I slot print_timing: id 0 | task 550 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.182.626 I slot release: id 0 | task 550 | stop processing: n_tokens = 437, truncated = 0 0.09.196.867 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 9086514 0.09.222.806 I slot launch_slot_: id 0 | task 615 | processing task, is_child = 0 0.09.731.938 I slot print_timing: id 0 | task 615 | prompt eval time = 150.61 ms / 412 tokens ( 0.37 ms per token, 2735.60 tokens per second) 0.09.731.944 I slot print_timing: id 0 | task 615 | eval time = 358.50 ms / 47 tokens ( 7.79 ms per token, 128.31 tokens per second) 0.09.731.945 I slot print_timing: id 0 | task 615 | total time = 509.11 ms / 459 tokens 0.09.731.945 I slot print_timing: id 0 | task 615 | graphs reused = 605 0.09.731.946 I slot print_timing: id 0 | task 615 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.731.978 I slot release: id 0 | task 615 | stop processing: n_tokens = 458, truncated = 0 0.09.753.876 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 9635866 0.09.779.998 I slot launch_slot_: id 0 | task 665 | processing task, is_child = 0 0.10.397.194 I slot print_timing: id 0 | task 665 | prompt eval time = 143.59 ms / 376 tokens ( 0.38 ms per token, 2618.53 tokens per second) 0.10.397.201 I slot print_timing: id 0 | task 665 | eval time = 473.58 ms / 62 tokens ( 7.76 ms per token, 128.80 tokens per second) 0.10.397.202 I slot print_timing: id 0 | task 665 | total time = 617.18 ms / 438 tokens 0.10.397.204 I slot print_timing: id 0 | task 665 | graphs reused = 665 0.10.397.205 I slot print_timing: id 0 | task 665 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.397.232 I slot release: id 0 | task 665 | stop processing: n_tokens = 437, truncated = 0 0.10.423.461 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 10301121 0.10.449.387 I slot launch_slot_: id 0 | task 730 | processing task, is_child = 0 0.10.993.069 I slot print_timing: id 0 | task 730 | prompt eval time = 146.48 ms / 378 tokens ( 0.39 ms per token, 2580.50 tokens per second) 0.10.993.075 I slot print_timing: id 0 | task 730 | eval time = 397.18 ms / 52 tokens ( 7.79 ms per token, 128.41 tokens per second) 0.10.993.076 I slot print_timing: id 0 | task 730 | total time = 543.66 ms / 430 tokens 0.10.993.076 I slot print_timing: id 0 | task 730 | graphs reused = 715 0.10.993.077 I slot print_timing: id 0 | task 730 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.993.105 I slot release: id 0 | task 730 | stop processing: n_tokens = 429, truncated = 0 0.11.014.620 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 10896993 0.11.041.146 I slot launch_slot_: id 0 | task 785 | processing task, is_child = 0 0.11.663.287 I slot print_timing: id 0 | task 785 | prompt eval time = 146.22 ms / 367 tokens ( 0.40 ms per token, 2509.95 tokens per second) 0.11.663.293 I slot print_timing: id 0 | task 785 | eval time = 475.90 ms / 58 tokens ( 8.35 ms per token, 119.77 tokens per second) 0.11.663.294 I slot print_timing: id 0 | task 785 | total time = 622.12 ms / 425 tokens 0.11.663.294 I slot print_timing: id 0 | task 785 | graphs reused = 771 0.11.663.295 I slot print_timing: id 0 | task 785 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.663.325 I slot release: id 0 | task 785 | stop processing: n_tokens = 424, truncated = 0 0.11.682.986 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 11567213 0.11.709.035 I slot launch_slot_: id 0 | task 846 | processing task, is_child = 0 0.12.238.031 I slot print_timing: id 0 | task 846 | prompt eval time = 138.85 ms / 347 tokens ( 0.40 ms per token, 2499.05 tokens per second) 0.12.238.036 I slot print_timing: id 0 | task 846 | eval time = 390.12 ms / 51 tokens ( 7.80 ms per token, 128.16 tokens per second) 0.12.238.037 I slot print_timing: id 0 | task 846 | total time = 528.98 ms / 398 tokens 0.12.238.038 I slot print_timing: id 0 | task 846 | graphs reused = 820 0.12.238.039 I slot print_timing: id 0 | task 846 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.238.066 I slot release: id 0 | task 846 | stop processing: n_tokens = 397, truncated = 0 0.12.241.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 12141954 0.12.267.714 I slot launch_slot_: id 0 | task 900 | processing task, is_child = 0 0.12.951.639 I slot print_timing: id 0 | task 900 | prompt eval time = 139.82 ms / 369 tokens ( 0.38 ms per token, 2639.05 tokens per second) 0.12.951.644 I slot print_timing: id 0 | task 900 | eval time = 544.08 ms / 71 tokens ( 7.77 ms per token, 128.66 tokens per second) 0.12.951.645 I slot print_timing: id 0 | task 900 | total time = 683.91 ms / 440 tokens 0.12.951.646 I slot print_timing: id 0 | task 900 | graphs reused = 889 0.12.951.647 I slot print_timing: id 0 | task 900 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.951.674 I slot release: id 0 | task 900 | stop processing: n_tokens = 439, truncated = 0 0.12.980.342 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 12855563 0.13.006.207 I slot launch_slot_: id 0 | task 974 | processing task, is_child = 0 0.13.454.630 I slot print_timing: id 0 | task 974 | prompt eval time = 136.92 ms / 352 tokens ( 0.39 ms per token, 2570.92 tokens per second) 0.13.454.636 I slot print_timing: id 0 | task 974 | eval time = 311.49 ms / 41 tokens ( 7.79 ms per token, 128.42 tokens per second) 0.13.454.637 I slot print_timing: id 0 | task 974 | total time = 448.40 ms / 393 tokens 0.13.454.638 I slot print_timing: id 0 | task 974 | graphs reused = 928 0.13.454.639 I slot print_timing: id 0 | task 974 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.454.667 I slot release: id 0 | task 974 | stop processing: n_tokens = 392, truncated = 0 0.13.476.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 13358555 0.13.502.749 I slot launch_slot_: id 0 | task 1018 | processing task, is_child = 0 0.13.947.398 I slot print_timing: id 0 | task 1018 | prompt eval time = 137.50 ms / 349 tokens ( 0.39 ms per token, 2538.22 tokens per second) 0.13.947.404 I slot print_timing: id 0 | task 1018 | eval time = 307.13 ms / 40 tokens ( 7.88 ms per token, 126.98 tokens per second) 0.13.947.405 I slot print_timing: id 0 | task 1018 | total time = 444.63 ms / 389 tokens 0.13.947.407 I slot print_timing: id 0 | task 1018 | graphs reused = 966 0.13.947.407 I slot print_timing: id 0 | task 1018 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.947.433 I slot release: id 0 | task 1018 | stop processing: n_tokens = 388, truncated = 0 0.13.951.240 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 13851322 0.13.978.507 I slot launch_slot_: id 0 | task 1061 | processing task, is_child = 0 0.14.640.567 I slot print_timing: id 0 | task 1061 | prompt eval time = 150.38 ms / 384 tokens ( 0.39 ms per token, 2553.58 tokens per second) 0.14.640.572 I slot print_timing: id 0 | task 1061 | eval time = 511.66 ms / 63 tokens ( 8.25 ms per token, 121.17 tokens per second) 0.14.640.573 I slot print_timing: id 0 | task 1061 | total time = 662.04 ms / 447 tokens 0.14.640.575 I slot print_timing: id 0 | task 1061 | graphs reused = 1027 0.14.640.575 I slot print_timing: id 0 | task 1061 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.640.606 I slot release: id 0 | task 1061 | stop processing: n_tokens = 446, truncated = 0 0.14.664.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 14544494 0.14.690.259 I slot launch_slot_: id 0 | task 1127 | processing task, is_child = 0 0.15.241.911 I slot print_timing: id 0 | task 1127 | prompt eval time = 139.26 ms / 356 tokens ( 0.39 ms per token, 2556.30 tokens per second) 0.15.241.917 I slot print_timing: id 0 | task 1127 | eval time = 412.37 ms / 54 tokens ( 7.78 ms per token, 128.53 tokens per second) 0.15.241.918 I slot print_timing: id 0 | task 1127 | total time = 551.63 ms / 410 tokens 0.15.241.918 I slot print_timing: id 0 | task 1127 | graphs reused = 1079 0.15.241.919 I slot print_timing: id 0 | task 1127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.241.946 I slot release: id 0 | task 1127 | stop processing: n_tokens = 409, truncated = 0 0.15.257.739 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 15145834 0.15.283.155 I slot launch_slot_: id 0 | task 1184 | processing task, is_child = 0 0.15.970.135 I slot print_timing: id 0 | task 1184 | prompt eval time = 150.38 ms / 410 tokens ( 0.37 ms per token, 2726.52 tokens per second) 0.15.970.141 I slot print_timing: id 0 | task 1184 | eval time = 536.58 ms / 70 tokens ( 7.78 ms per token, 128.59 tokens per second) 0.15.970.142 I slot print_timing: id 0 | task 1184 | total time = 686.96 ms / 480 tokens 0.15.970.143 I slot print_timing: id 0 | task 1184 | graphs reused = 1147 0.15.970.143 I slot print_timing: id 0 | task 1184 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.970.172 I slot release: id 0 | task 1184 | stop processing: n_tokens = 479, truncated = 0 0.15.992.770 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 15874060 0.16.018.634 I slot launch_slot_: id 0 | task 1257 | processing task, is_child = 0 0.16.501.473 I slot print_timing: id 0 | task 1257 | prompt eval time = 147.90 ms / 385 tokens ( 0.38 ms per token, 2603.15 tokens per second) 0.16.501.479 I slot print_timing: id 0 | task 1257 | eval time = 334.92 ms / 44 tokens ( 7.79 ms per token, 128.39 tokens per second) 0.16.501.480 I slot print_timing: id 0 | task 1257 | total time = 482.82 ms / 429 tokens 0.16.501.481 I slot print_timing: id 0 | task 1257 | graphs reused = 1189 0.16.501.482 I slot print_timing: id 0 | task 1257 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.501.510 I slot release: id 0 | task 1257 | stop processing: n_tokens = 428, truncated = 0 0.16.528.336 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 16405398 0.16.554.046 I slot launch_slot_: id 0 | task 1304 | processing task, is_child = 0 0.17.249.338 I slot print_timing: id 0 | task 1304 | prompt eval time = 152.82 ms / 395 tokens ( 0.39 ms per token, 2584.69 tokens per second) 0.17.249.344 I slot print_timing: id 0 | task 1304 | eval time = 542.45 ms / 71 tokens ( 7.75 ms per token, 129.04 tokens per second) 0.17.249.345 I slot print_timing: id 0 | task 1304 | total time = 695.27 ms / 466 tokens 0.17.249.346 I slot print_timing: id 0 | task 1304 | graphs reused = 1258 0.17.249.347 I slot print_timing: id 0 | task 1304 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.249.377 I slot release: id 0 | task 1304 | stop processing: n_tokens = 465, truncated = 0 0.17.277.814 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 17153265 0.17.304.968 I slot launch_slot_: id 0 | task 1378 | processing task, is_child = 0 0.17.931.776 I slot print_timing: id 0 | task 1378 | prompt eval time = 152.40 ms / 430 tokens ( 0.35 ms per token, 2821.45 tokens per second) 0.17.931.783 I slot print_timing: id 0 | task 1378 | eval time = 474.39 ms / 62 tokens ( 7.78 ms per token, 128.59 tokens per second) 0.17.931.784 I slot print_timing: id 0 | task 1378 | total time = 626.79 ms / 492 tokens 0.17.931.785 I slot print_timing: id 0 | task 1378 | graphs reused = 1318 0.17.931.786 I slot print_timing: id 0 | task 1378 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.931.816 I slot release: id 0 | task 1378 | stop processing: n_tokens = 491, truncated = 0 0.17.951.579 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 17835704 0.17.980.806 I slot launch_slot_: id 0 | task 1443 | processing task, is_child = 0 0.18.611.465 I slot print_timing: id 0 | task 1443 | prompt eval time = 152.14 ms / 392 tokens ( 0.39 ms per token, 2576.56 tokens per second) 0.18.611.471 I slot print_timing: id 0 | task 1443 | eval time = 478.50 ms / 62 tokens ( 7.84 ms per token, 127.48 tokens per second) 0.18.611.472 I slot print_timing: id 0 | task 1443 | total time = 630.64 ms / 454 tokens 0.18.611.473 I slot print_timing: id 0 | task 1443 | graphs reused = 1378 0.18.611.474 I slot print_timing: id 0 | task 1443 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.611.501 I slot release: id 0 | task 1443 | stop processing: n_tokens = 453, truncated = 0 0.18.630.786 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 18515390 0.18.674.429 I slot launch_slot_: id 0 | task 1508 | processing task, is_child = 0 0.19.188.446 I slot print_timing: id 0 | task 1508 | prompt eval time = 139.46 ms / 350 tokens ( 0.40 ms per token, 2509.70 tokens per second) 0.19.188.452 I slot print_timing: id 0 | task 1508 | eval time = 374.54 ms / 49 tokens ( 7.80 ms per token, 128.16 tokens per second) 0.19.188.453 I slot print_timing: id 0 | task 1508 | total time = 514.00 ms / 399 tokens 0.19.188.453 I slot print_timing: id 0 | task 1508 | graphs reused = 1425 0.19.188.454 I slot print_timing: id 0 | task 1508 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.188.481 I slot release: id 0 | task 1508 | stop processing: n_tokens = 398, truncated = 0 0.19.206.667 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 19092369 0.19.242.260 I slot launch_slot_: id 0 | task 1560 | processing task, is_child = 0 0.19.860.982 I slot print_timing: id 0 | task 1560 | prompt eval time = 148.55 ms / 380 tokens ( 0.39 ms per token, 2558.11 tokens per second) 0.19.860.988 I slot print_timing: id 0 | task 1560 | eval time = 470.15 ms / 61 tokens ( 7.84 ms per token, 127.62 tokens per second) 0.19.860.989 I slot print_timing: id 0 | task 1560 | total time = 618.70 ms / 441 tokens 0.19.860.990 I slot print_timing: id 0 | task 1560 | graphs reused = 1484 0.19.860.991 I slot print_timing: id 0 | task 1560 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.861.020 I slot release: id 0 | task 1560 | stop processing: n_tokens = 440, truncated = 0 0.19.877.441 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 19764909 0.19.913.141 I slot launch_slot_: id 0 | task 1624 | processing task, is_child = 0 0.20.723.626 I slot print_timing: id 0 | task 1624 | prompt eval time = 161.57 ms / 410 tokens ( 0.39 ms per token, 2537.62 tokens per second) 0.20.723.632 I slot print_timing: id 0 | task 1624 | eval time = 648.90 ms / 80 tokens ( 8.21 ms per token, 121.75 tokens per second) 0.20.723.633 I slot print_timing: id 0 | task 1624 | total time = 810.47 ms / 490 tokens 0.20.723.634 I slot print_timing: id 0 | task 1624 | graphs reused = 1562 0.20.723.635 I slot print_timing: id 0 | task 1624 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.723.665 I slot release: id 0 | task 1624 | stop processing: n_tokens = 489, truncated = 0 0.20.747.347 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 20627553 0.20.784.675 I slot launch_slot_: id 0 | task 1707 | processing task, is_child = 0 0.21.455.830 I slot print_timing: id 0 | task 1707 | prompt eval time = 147.73 ms / 387 tokens ( 0.38 ms per token, 2619.71 tokens per second) 0.21.455.835 I slot print_timing: id 0 | task 1707 | eval time = 523.41 ms / 68 tokens ( 7.81 ms per token, 128.01 tokens per second) 0.21.455.836 I slot print_timing: id 0 | task 1707 | total time = 671.13 ms / 455 tokens 0.21.455.837 I slot print_timing: id 0 | task 1707 | graphs reused = 1628 0.21.455.838 I slot print_timing: id 0 | task 1707 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.455.866 I slot release: id 0 | task 1707 | stop processing: n_tokens = 454, truncated = 0 0.21.459.446 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 21359755 0.21.490.697 I slot launch_slot_: id 0 | task 1778 | processing task, is_child = 0 0.22.081.517 I slot print_timing: id 0 | task 1778 | prompt eval time = 137.48 ms / 358 tokens ( 0.38 ms per token, 2604.03 tokens per second) 0.22.081.522 I slot print_timing: id 0 | task 1778 | eval time = 453.32 ms / 59 tokens ( 7.82 ms per token, 127.94 tokens per second) 0.22.081.524 I slot print_timing: id 0 | task 1778 | total time = 590.80 ms / 417 tokens 0.22.081.525 I slot print_timing: id 0 | task 1778 | graphs reused = 1685 0.22.081.525 I slot print_timing: id 0 | task 1778 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.081.554 I slot release: id 0 | task 1778 | stop processing: n_tokens = 416, truncated = 0 0.22.108.351 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 21985443 0.22.146.726 I slot launch_slot_: id 0 | task 1840 | processing task, is_child = 0 0.22.742.617 I slot print_timing: id 0 | task 1840 | prompt eval time = 139.70 ms / 359 tokens ( 0.39 ms per token, 2569.87 tokens per second) 0.22.742.622 I slot print_timing: id 0 | task 1840 | eval time = 456.17 ms / 56 tokens ( 8.29 ms per token, 120.57 tokens per second) 0.22.742.624 I slot print_timing: id 0 | task 1840 | total time = 595.87 ms / 415 tokens 0.22.742.624 I slot print_timing: id 0 | task 1840 | graphs reused = 1739 0.22.742.625 I slot print_timing: id 0 | task 1840 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.742.651 I slot release: id 0 | task 1840 | stop processing: n_tokens = 414, truncated = 0 0.22.762.776 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 22646540 0.22.798.948 I slot launch_slot_: id 0 | task 1899 | processing task, is_child = 0 0.23.417.217 I slot print_timing: id 0 | task 1899 | prompt eval time = 146.33 ms / 387 tokens ( 0.38 ms per token, 2644.71 tokens per second) 0.23.417.223 I slot print_timing: id 0 | task 1899 | eval time = 471.92 ms / 61 tokens ( 7.87 ms per token, 127.14 tokens per second) 0.23.417.224 I slot print_timing: id 0 | task 1899 | total time = 618.25 ms / 448 tokens 0.23.417.226 I slot print_timing: id 0 | task 1899 | graphs reused = 1798 0.23.417.227 I slot print_timing: id 0 | task 1899 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.417.255 I slot release: id 0 | task 1899 | stop processing: n_tokens = 447, truncated = 0 0.23.440.229 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 23321144 0.23.473.377 I slot launch_slot_: id 0 | task 1963 | processing task, is_child = 0 0.24.112.699 I slot print_timing: id 0 | task 1963 | prompt eval time = 146.85 ms / 410 tokens ( 0.36 ms per token, 2791.98 tokens per second) 0.24.112.705 I slot print_timing: id 0 | task 1963 | eval time = 492.45 ms / 61 tokens ( 8.21 ms per token, 121.84 tokens per second) 0.24.112.706 I slot print_timing: id 0 | task 1963 | total time = 639.30 ms / 471 tokens 0.24.112.707 I slot print_timing: id 0 | task 1963 | graphs reused = 1857 0.24.112.707 I slot print_timing: id 0 | task 1963 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.112.736 I slot release: id 0 | task 1963 | stop processing: n_tokens = 470, truncated = 0 0.24.136.701 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 24016624 0.24.173.266 I slot launch_slot_: id 0 | task 2027 | processing task, is_child = 0 0.24.691.903 I slot print_timing: id 0 | task 2027 | prompt eval time = 134.06 ms / 351 tokens ( 0.38 ms per token, 2618.17 tokens per second) 0.24.691.909 I slot print_timing: id 0 | task 2027 | eval time = 384.55 ms / 50 tokens ( 7.85 ms per token, 127.42 tokens per second) 0.24.691.910 I slot print_timing: id 0 | task 2027 | total time = 518.62 ms / 401 tokens 0.24.691.911 I slot print_timing: id 0 | task 2027 | graphs reused = 1905 0.24.691.912 I slot print_timing: id 0 | task 2027 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.691.942 I slot release: id 0 | task 2027 | stop processing: n_tokens = 400, truncated = 0 0.24.695.901 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 24595830 0.24.732.985 I slot launch_slot_: id 0 | task 2080 | processing task, is_child = 0 0.26.610.268 I slot print_timing: id 0 | task 2080 | prompt eval time = 149.40 ms / 393 tokens ( 0.38 ms per token, 2630.56 tokens per second) 0.26.610.274 I slot print_timing: id 0 | task 2080 | eval time = 1727.86 ms / 224 tokens ( 7.75 ms per token, 129.06 tokens per second) 0.26.610.275 I slot print_timing: id 0 | task 2080 | total time = 1877.26 ms / 617 tokens 0.26.610.276 I slot print_timing: id 0 | task 2080 | graphs reused = 2126 0.26.610.277 I slot print_timing: id 0 | task 2080 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.610.307 I slot release: id 0 | task 2080 | stop processing: n_tokens = 616, truncated = 0 0.26.634.277 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 26514195 0.26.675.389 I slot launch_slot_: id 0 | task 2307 | processing task, is_child = 0 0.27.064.611 I slot print_timing: id 0 | task 2307 | prompt eval time = 134.76 ms / 321 tokens ( 0.42 ms per token, 2381.94 tokens per second) 0.27.064.617 I slot print_timing: id 0 | task 2307 | eval time = 254.44 ms / 30 tokens ( 8.77 ms per token, 113.98 tokens per second) 0.27.064.618 I slot print_timing: id 0 | task 2307 | total time = 389.20 ms / 351 tokens 0.27.064.619 I slot print_timing: id 0 | task 2307 | graphs reused = 2154 0.27.064.619 I slot print_timing: id 0 | task 2307 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.064.645 I slot release: id 0 | task 2307 | stop processing: n_tokens = 350, truncated = 0 0.27.083.740 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 26968533 0.27.119.068 I slot launch_slot_: id 0 | task 2340 | processing task, is_child = 0 0.27.850.760 I slot print_timing: id 0 | task 2340 | prompt eval time = 134.96 ms / 330 tokens ( 0.41 ms per token, 2445.22 tokens per second) 0.27.850.766 I slot print_timing: id 0 | task 2340 | eval time = 596.72 ms / 78 tokens ( 7.75 ms per token, 129.04 tokens per second) 0.27.850.767 I slot print_timing: id 0 | task 2340 | total time = 731.67 ms / 408 tokens 0.27.850.768 I slot print_timing: id 0 | task 2340 | graphs reused = 2230 0.27.850.769 I slot print_timing: id 0 | task 2340 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.850.797 I slot release: id 0 | task 2340 | stop processing: n_tokens = 407, truncated = 0 0.27.878.336 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 27754685 0.27.913.288 I slot launch_slot_: id 0 | task 2421 | processing task, is_child = 0 0.28.318.871 I slot print_timing: id 0 | task 2421 | prompt eval time = 134.23 ms / 341 tokens ( 0.39 ms per token, 2540.47 tokens per second) 0.28.318.877 I slot print_timing: id 0 | task 2421 | eval time = 271.34 ms / 32 tokens ( 8.75 ms per token, 114.25 tokens per second) 0.28.318.878 I slot print_timing: id 0 | task 2421 | total time = 405.57 ms / 373 tokens 0.28.318.879 I slot print_timing: id 0 | task 2421 | graphs reused = 2260 0.28.318.879 I slot print_timing: id 0 | task 2421 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.318.908 I slot release: id 0 | task 2421 | stop processing: n_tokens = 372, truncated = 0 0.28.322.546 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 28222796 0.28.360.592 I slot launch_slot_: id 0 | task 2456 | processing task, is_child = 0 0.28.860.795 I slot print_timing: id 0 | task 2456 | prompt eval time = 134.12 ms / 338 tokens ( 0.40 ms per token, 2520.07 tokens per second) 0.28.860.800 I slot print_timing: id 0 | task 2456 | eval time = 366.06 ms / 48 tokens ( 7.79 ms per token, 128.39 tokens per second) 0.28.860.802 I slot print_timing: id 0 | task 2456 | total time = 500.18 ms / 386 tokens 0.28.860.802 I slot print_timing: id 0 | task 2456 | graphs reused = 2306 0.28.860.803 I slot print_timing: id 0 | task 2456 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.860.830 I slot release: id 0 | task 2456 | stop processing: n_tokens = 385, truncated = 0 0.28.876.303 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 28764718 0.28.912.096 I slot launch_slot_: id 0 | task 2507 | processing task, is_child = 0 0.29.488.518 I slot print_timing: id 0 | task 2507 | prompt eval time = 147.99 ms / 395 tokens ( 0.37 ms per token, 2669.10 tokens per second) 0.29.488.525 I slot print_timing: id 0 | task 2507 | eval time = 428.41 ms / 56 tokens ( 7.79 ms per token, 128.38 tokens per second) 0.29.488.526 I slot print_timing: id 0 | task 2507 | total time = 576.40 ms / 451 tokens 0.29.488.527 I slot print_timing: id 0 | task 2507 | graphs reused = 2360 0.29.488.528 I slot print_timing: id 0 | task 2507 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.488.558 I slot release: id 0 | task 2507 | stop processing: n_tokens = 450, truncated = 0 0.29.514.551 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 29392446 0.29.550.013 I slot launch_slot_: id 0 | task 2566 | processing task, is_child = 0 0.30.392.227 I slot print_timing: id 0 | task 2566 | prompt eval time = 204.26 ms / 528 tokens ( 0.39 ms per token, 2584.99 tokens per second) 0.30.392.233 I slot print_timing: id 0 | task 2566 | eval time = 637.94 ms / 83 tokens ( 7.78 ms per token, 128.54 tokens per second) 0.30.392.234 I slot print_timing: id 0 | task 2566 | total time = 842.19 ms / 611 tokens 0.30.392.235 I slot print_timing: id 0 | task 2566 | graphs reused = 2441 0.30.392.237 I slot print_timing: id 0 | task 2566 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.392.272 I slot release: id 0 | task 2566 | stop processing: n_tokens = 610, truncated = 0 0.30.395.870 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 30296161 0.30.442.003 I slot launch_slot_: id 0 | task 2653 | processing task, is_child = 0 0.30.939.177 I slot print_timing: id 0 | task 2653 | prompt eval time = 154.73 ms / 331 tokens ( 0.47 ms per token, 2139.27 tokens per second) 0.30.939.184 I slot print_timing: id 0 | task 2653 | eval time = 342.43 ms / 45 tokens ( 7.78 ms per token, 128.49 tokens per second) 0.30.939.185 I slot print_timing: id 0 | task 2653 | total time = 497.16 ms / 376 tokens 0.30.939.187 I slot print_timing: id 0 | task 2653 | graphs reused = 2484 0.30.939.188 I slot print_timing: id 0 | task 2653 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.939.216 I slot release: id 0 | task 2653 | stop processing: n_tokens = 387, truncated = 0 0.30.955.601 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 30843104 0.30.999.828 I slot launch_slot_: id 0 | task 2701 | processing task, is_child = 0 0.31.684.375 I slot print_timing: id 0 | task 2701 | prompt eval time = 164.16 ms / 362 tokens ( 0.45 ms per token, 2205.10 tokens per second) 0.31.684.381 I slot print_timing: id 0 | task 2701 | eval time = 520.36 ms / 68 tokens ( 7.77 ms per token, 128.76 tokens per second) 0.31.684.382 I slot print_timing: id 0 | task 2701 | total time = 684.53 ms / 430 tokens 0.31.684.383 I slot print_timing: id 0 | task 2701 | graphs reused = 2550 0.31.684.384 I slot print_timing: id 0 | task 2701 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.684.414 I slot release: id 0 | task 2701 | stop processing: n_tokens = 441, truncated = 0 0.31.701.193 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 441, t_last = 31588302 0.31.746.001 I slot launch_slot_: id 0 | task 2772 | processing task, is_child = 0 0.32.444.229 I slot print_timing: id 0 | task 2772 | prompt eval time = 170.06 ms / 419 tokens ( 0.41 ms per token, 2463.88 tokens per second) 0.32.444.235 I slot print_timing: id 0 | task 2772 | eval time = 528.15 ms / 69 tokens ( 7.77 ms per token, 128.75 tokens per second) 0.32.444.236 I slot print_timing: id 0 | task 2772 | total time = 698.21 ms / 488 tokens 0.32.444.237 I slot print_timing: id 0 | task 2772 | graphs reused = 2617 0.32.444.241 I slot print_timing: id 0 | task 2772 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.444.273 I slot release: id 0 | task 2772 | stop processing: n_tokens = 499, truncated = 0 0.32.466.574 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 32348161 0.32.512.350 I slot launch_slot_: id 0 | task 2844 | processing task, is_child = 0 0.33.308.002 I slot print_timing: id 0 | task 2844 | prompt eval time = 183.83 ms / 423 tokens ( 0.43 ms per token, 2301.04 tokens per second) 0.33.308.008 I slot print_timing: id 0 | task 2844 | eval time = 611.80 ms / 72 tokens ( 8.62 ms per token, 116.05 tokens per second) 0.33.308.009 I slot print_timing: id 0 | task 2844 | total time = 795.63 ms / 495 tokens 0.33.308.009 I slot print_timing: id 0 | task 2844 | graphs reused = 2687 0.33.308.010 I slot print_timing: id 0 | task 2844 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.308.042 I slot release: id 0 | task 2844 | stop processing: n_tokens = 506, truncated = 0 0.33.326.671 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 33211930 0.33.377.753 I slot launch_slot_: id 0 | task 2919 | processing task, is_child = 0 0.33.861.101 I slot print_timing: id 0 | task 2919 | prompt eval time = 155.35 ms / 341 tokens ( 0.46 ms per token, 2195.06 tokens per second) 0.33.861.107 I slot print_timing: id 0 | task 2919 | eval time = 327.98 ms / 43 tokens ( 7.81 ms per token, 128.06 tokens per second) 0.33.861.108 I slot print_timing: id 0 | task 2919 | total time = 483.33 ms / 384 tokens 0.33.861.109 I slot print_timing: id 0 | task 2919 | graphs reused = 2728 0.33.861.110 I slot print_timing: id 0 | task 2919 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.861.138 I slot release: id 0 | task 2919 | stop processing: n_tokens = 395, truncated = 0 0.33.886.801 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 33765026 0.33.938.638 I slot launch_slot_: id 0 | task 2965 | processing task, is_child = 0 0.34.454.964 I slot print_timing: id 0 | task 2965 | prompt eval time = 157.46 ms / 356 tokens ( 0.44 ms per token, 2260.92 tokens per second) 0.34.454.970 I slot print_timing: id 0 | task 2965 | eval time = 358.85 ms / 47 tokens ( 7.80 ms per token, 128.19 tokens per second) 0.34.454.971 I slot print_timing: id 0 | task 2965 | total time = 516.31 ms / 403 tokens 0.34.454.972 I slot print_timing: id 0 | task 2965 | graphs reused = 2773 0.34.454.973 I slot print_timing: id 0 | task 2965 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.455.000 I slot release: id 0 | task 2965 | stop processing: n_tokens = 414, truncated = 0 0.34.478.155 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 34358888 0.34.478.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 0.34.537.859 I slot launch_slot_: id 0 | task 3015 | processing task, is_child = 0 0.35.051.938 I slot print_timing: id 0 | task 3015 | prompt eval time = 164.34 ms / 362 tokens ( 0.45 ms per token, 2202.82 tokens per second) 0.35.051.944 I slot print_timing: id 0 | task 3015 | eval time = 349.73 ms / 46 tokens ( 7.77 ms per token, 128.67 tokens per second) 0.35.051.944 I slot print_timing: id 0 | task 3015 | total time = 514.06 ms / 408 tokens 0.35.051.945 I slot print_timing: id 0 | task 3015 | graphs reused = 2817 0.35.051.946 I slot print_timing: id 0 | task 3015 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.051.975 I slot release: id 0 | task 3015 | stop processing: n_tokens = 419, truncated = 0 0.35.068.637 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 34955863 0.35.068.688 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.35.127.829 I slot launch_slot_: id 0 | task 3064 | processing task, is_child = 0 0.35.818.131 I slot print_timing: id 0 | task 3064 | prompt eval time = 167.80 ms / 391 tokens ( 0.43 ms per token, 2330.13 tokens per second) 0.35.818.137 I slot print_timing: id 0 | task 3064 | eval time = 522.48 ms / 68 tokens ( 7.80 ms per token, 128.23 tokens per second) 0.35.818.137 I slot print_timing: id 0 | task 3064 | total time = 690.28 ms / 459 tokens 0.35.818.138 I slot print_timing: id 0 | task 3064 | graphs reused = 2883 0.35.818.139 I slot print_timing: id 0 | task 3064 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.818.169 I slot release: id 0 | task 3064 | stop processing: n_tokens = 470, truncated = 0 0.35.832.821 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 35722057 0.35.832.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.35.892.263 I slot launch_slot_: id 0 | task 3135 | processing task, is_child = 0 0.36.460.722 I slot print_timing: id 0 | task 3135 | prompt eval time = 156.68 ms / 343 tokens ( 0.46 ms per token, 2189.12 tokens per second) 0.36.460.728 I slot print_timing: id 0 | task 3135 | eval time = 411.75 ms / 54 tokens ( 7.77 ms per token, 128.72 tokens per second) 0.36.460.729 I slot print_timing: id 0 | task 3135 | total time = 568.44 ms / 397 tokens 0.36.460.730 I slot print_timing: id 0 | task 3135 | graphs reused = 2935 0.36.460.730 I slot print_timing: id 0 | task 3135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.460.757 I slot release: id 0 | task 3135 | stop processing: n_tokens = 408, truncated = 0 0.36.488.883 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 36364646 0.36.488.935 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 0.36.499.082 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.36.563.936 I slot launch_slot_: id 0 | task 3192 | processing task, is_child = 0 0.37.175.559 I slot print_timing: id 0 | task 3192 | prompt eval time = 168.45 ms / 401 tokens ( 0.42 ms per token, 2380.51 tokens per second) 0.37.175.566 I slot print_timing: id 0 | task 3192 | eval time = 443.15 ms / 58 tokens ( 7.77 ms per token, 128.62 tokens per second) 0.37.175.567 I slot print_timing: id 0 | task 3192 | total time = 611.60 ms / 459 tokens 0.37.175.568 I slot print_timing: id 0 | task 3192 | graphs reused = 2991 0.37.175.569 I slot print_timing: id 0 | task 3192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.175.601 I slot release: id 0 | task 3192 | stop processing: n_tokens = 470, truncated = 0 0.37.190.548 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 37079489 0.37.190.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.37.243.683 I slot launch_slot_: id 0 | task 3253 | processing task, is_child = 0 0.37.923.455 I slot print_timing: id 0 | task 3253 | prompt eval time = 158.65 ms / 355 tokens ( 0.45 ms per token, 2237.62 tokens per second) 0.37.923.461 I slot print_timing: id 0 | task 3253 | eval time = 521.10 ms / 68 tokens ( 7.78 ms per token, 128.57 tokens per second) 0.37.923.462 I slot print_timing: id 0 | task 3253 | total time = 679.75 ms / 423 tokens 0.37.923.463 I slot print_timing: id 0 | task 3253 | graphs reused = 3057 0.37.923.463 I slot print_timing: id 0 | task 3253 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.923.491 I slot release: id 0 | task 3253 | stop processing: n_tokens = 434, truncated = 0 0.37.951.488 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 37827379 0.37.951.536 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.38.009.441 I slot launch_slot_: id 0 | task 3324 | processing task, is_child = 0 0.38.639.364 I slot print_timing: id 0 | task 3324 | prompt eval time = 158.26 ms / 351 tokens ( 0.45 ms per token, 2217.83 tokens per second) 0.38.639.370 I slot print_timing: id 0 | task 3324 | eval time = 471.64 ms / 57 tokens ( 8.42 ms per token, 118.73 tokens per second) 0.38.639.371 I slot print_timing: id 0 | task 3324 | total time = 629.90 ms / 408 tokens 0.38.639.372 I slot print_timing: id 0 | task 3324 | graphs reused = 3112 0.38.639.372 I slot print_timing: id 0 | task 3324 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.639.400 I slot release: id 0 | task 3324 | stop processing: n_tokens = 419, truncated = 0 0.38.652.943 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 38543289 0.38.652.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.38.663.277 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.38.722.475 I slot launch_slot_: id 0 | task 3384 | processing task, is_child = 0 0.39.640.781 I slot print_timing: id 0 | task 3384 | prompt eval time = 192.87 ms / 475 tokens ( 0.41 ms per token, 2462.76 tokens per second) 0.39.640.787 I slot print_timing: id 0 | task 3384 | eval time = 725.41 ms / 94 tokens ( 7.80 ms per token, 128.20 tokens per second) 0.39.640.789 I slot print_timing: id 0 | task 3384 | total time = 918.29 ms / 569 tokens 0.39.640.789 I slot print_timing: id 0 | task 3384 | graphs reused = 3203 0.39.640.790 I slot print_timing: id 0 | task 3384 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.640.823 I slot release: id 0 | task 3384 | stop processing: n_tokens = 580, truncated = 0 0.39.661.550 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 39544711 0.39.661.607 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.386 MiB) 0.39.713.696 I slot launch_slot_: id 0 | task 3481 | processing task, is_child = 0 0.40.612.487 I slot print_timing: id 0 | task 3481 | prompt eval time = 187.40 ms / 440 tokens ( 0.43 ms per token, 2347.97 tokens per second) 0.40.612.493 I slot print_timing: id 0 | task 3481 | eval time = 711.38 ms / 92 tokens ( 7.82 ms per token, 127.92 tokens per second) 0.40.612.494 I slot print_timing: id 0 | task 3481 | total time = 898.77 ms / 532 tokens 0.40.612.494 I slot print_timing: id 0 | task 3481 | graphs reused = 3292 0.40.612.495 I slot print_timing: id 0 | task 3481 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.612.525 I slot release: id 0 | task 3481 | stop processing: n_tokens = 543, truncated = 0 0.40.635.847 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 40516413 0.40.635.903 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.40.702.969 I slot launch_slot_: id 0 | task 3576 | processing task, is_child = 0 0.41.282.769 I slot print_timing: id 0 | task 3576 | prompt eval time = 159.13 ms / 345 tokens ( 0.46 ms per token, 2168.04 tokens per second) 0.41.282.775 I slot print_timing: id 0 | task 3576 | eval time = 420.65 ms / 55 tokens ( 7.79 ms per token, 128.37 tokens per second) 0.41.282.776 I slot print_timing: id 0 | task 3576 | total time = 579.78 ms / 400 tokens 0.41.282.776 I slot print_timing: id 0 | task 3576 | graphs reused = 3345 0.41.282.777 I slot print_timing: id 0 | task 3576 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.282.804 I slot release: id 0 | task 3576 | stop processing: n_tokens = 411, truncated = 0 0.41.304.839 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 41186692 0.41.304.888 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.41.314.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.41.378.284 I slot launch_slot_: id 0 | task 3634 | processing task, is_child = 0 0.41.967.746 I slot print_timing: id 0 | task 3634 | prompt eval time = 168.81 ms / 382 tokens ( 0.44 ms per token, 2262.83 tokens per second) 0.41.967.752 I slot print_timing: id 0 | task 3634 | eval time = 420.63 ms / 55 tokens ( 7.79 ms per token, 128.38 tokens per second) 0.41.967.753 I slot print_timing: id 0 | task 3634 | total time = 589.44 ms / 437 tokens 0.41.967.754 I slot print_timing: id 0 | task 3634 | graphs reused = 3398 0.41.967.755 I slot print_timing: id 0 | task 3634 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.967.785 I slot release: id 0 | task 3634 | stop processing: n_tokens = 448, truncated = 0 0.41.988.048 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 41871673 0.41.988.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.42.052.764 I slot launch_slot_: id 0 | task 3692 | processing task, is_child = 0 0.42.553.974 I slot print_timing: id 0 | task 3692 | prompt eval time = 157.80 ms / 337 tokens ( 0.47 ms per token, 2135.61 tokens per second) 0.42.553.980 I slot print_timing: id 0 | task 3692 | eval time = 343.39 ms / 45 tokens ( 7.80 ms per token, 128.13 tokens per second) 0.42.553.981 I slot print_timing: id 0 | task 3692 | total time = 501.19 ms / 382 tokens 0.42.553.981 I slot print_timing: id 0 | task 3692 | graphs reused = 3441 0.42.553.982 I slot print_timing: id 0 | task 3692 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.554.011 I slot release: id 0 | task 3692 | stop processing: n_tokens = 393, truncated = 0 0.42.580.506 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 42457899 0.42.580.558 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.42.638.063 I slot launch_slot_: id 0 | task 3740 | processing task, is_child = 0 0.43.379.827 I slot print_timing: id 0 | task 3740 | prompt eval time = 170.41 ms / 402 tokens ( 0.42 ms per token, 2358.96 tokens per second) 0.43.379.833 I slot print_timing: id 0 | task 3740 | eval time = 571.33 ms / 70 tokens ( 8.28 ms per token, 120.77 tokens per second) 0.43.379.834 I slot print_timing: id 0 | task 3740 | total time = 741.75 ms / 472 tokens 0.43.379.835 I slot print_timing: id 0 | task 3740 | graphs reused = 3509 0.43.379.836 I slot print_timing: id 0 | task 3740 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.379.867 I slot release: id 0 | task 3740 | stop processing: n_tokens = 483, truncated = 0 0.43.405.486 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 43283755 0.43.405.532 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.43.415.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.43.480.170 I slot launch_slot_: id 0 | task 3813 | processing task, is_child = 0 0.44.133.985 I slot print_timing: id 0 | task 3813 | prompt eval time = 215.91 ms / 549 tokens ( 0.39 ms per token, 2542.70 tokens per second) 0.44.133.991 I slot print_timing: id 0 | task 3813 | eval time = 437.88 ms / 57 tokens ( 7.82 ms per token, 127.89 tokens per second) 0.44.133.992 I slot print_timing: id 0 | task 3813 | total time = 653.79 ms / 606 tokens 0.44.133.993 I slot print_timing: id 0 | task 3813 | graphs reused = 3564 0.44.133.994 I slot print_timing: id 0 | task 3813 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.134.027 I slot release: id 0 | task 3813 | stop processing: n_tokens = 617, truncated = 0 0.44.163.446 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 44037915 0.44.163.515 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.44.228.162 I slot launch_slot_: id 0 | task 3874 | processing task, is_child = 0 0.44.908.384 I slot print_timing: id 0 | task 3874 | prompt eval time = 235.73 ms / 616 tokens ( 0.38 ms per token, 2613.19 tokens per second) 0.44.908.394 I slot print_timing: id 0 | task 3874 | eval time = 444.47 ms / 58 tokens ( 7.80 ms per token, 128.24 tokens per second) 0.44.908.395 I slot print_timing: id 0 | task 3874 | total time = 680.20 ms / 674 tokens 0.44.908.396 I slot print_timing: id 0 | task 3874 | graphs reused = 3620 0.44.908.397 I slot print_timing: id 0 | task 3874 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.908.437 I slot release: id 0 | task 3874 | stop processing: n_tokens = 685, truncated = 0 0.44.926.987 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 44812325 0.44.927.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.886 MiB) 0.44.939.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.45.018.857 I slot launch_slot_: id 0 | task 3936 | processing task, is_child = 0 0.45.738.524 I slot print_timing: id 0 | task 3936 | prompt eval time = 250.84 ms / 665 tokens ( 0.38 ms per token, 2651.13 tokens per second) 0.45.738.530 I slot print_timing: id 0 | task 3936 | eval time = 468.81 ms / 61 tokens ( 7.81 ms per token, 127.98 tokens per second) 0.45.738.531 I slot print_timing: id 0 | task 3936 | total time = 719.65 ms / 726 tokens 0.45.738.532 I slot print_timing: id 0 | task 3936 | graphs reused = 3679 0.45.738.532 I slot print_timing: id 0 | task 3936 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.738.570 I slot release: id 0 | task 3936 | stop processing: n_tokens = 737, truncated = 0 0.45.765.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 45642459 0.45.765.921 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.45.776.040 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.45.838.239 I slot launch_slot_: id 0 | task 4001 | processing task, is_child = 0 0.46.502.802 I slot print_timing: id 0 | task 4001 | prompt eval time = 244.14 ms / 645 tokens ( 0.38 ms per token, 2641.97 tokens per second) 0.46.502.807 I slot print_timing: id 0 | task 4001 | eval time = 420.41 ms / 55 tokens ( 7.79 ms per token, 128.45 tokens per second) 0.46.502.808 I slot print_timing: id 0 | task 4001 | total time = 664.54 ms / 700 tokens 0.46.502.810 I slot print_timing: id 0 | task 4001 | graphs reused = 3732 0.46.502.810 I slot print_timing: id 0 | task 4001 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.502.846 I slot release: id 0 | task 4001 | stop processing: n_tokens = 711, truncated = 0 0.46.530.272 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 46406734 0.46.530.339 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.137 MiB) 0.46.609.532 I slot launch_slot_: id 0 | task 4060 | processing task, is_child = 0 0.47.206.813 I slot print_timing: id 0 | task 4060 | prompt eval time = 193.11 ms / 474 tokens ( 0.41 ms per token, 2454.58 tokens per second) 0.47.206.819 I slot print_timing: id 0 | task 4060 | eval time = 404.15 ms / 52 tokens ( 7.92 ms per token, 126.19 tokens per second) 0.47.206.820 I slot print_timing: id 0 | task 4060 | total time = 597.26 ms / 526 tokens 0.47.206.821 I slot print_timing: id 0 | task 4060 | graphs reused = 3781 0.47.206.822 I slot print_timing: id 0 | task 4060 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.206.852 I slot release: id 0 | task 4060 | stop processing: n_tokens = 537, truncated = 0 0.47.233.989 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 47110740 0.47.234.043 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.47.244.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.107 MiB) 0.47.309.374 I slot launch_slot_: id 0 | task 4115 | processing task, is_child = 0 0.47.860.770 I slot print_timing: id 0 | task 4115 | prompt eval time = 230.73 ms / 617 tokens ( 0.37 ms per token, 2674.12 tokens per second) 0.47.860.776 I slot print_timing: id 0 | task 4115 | eval time = 320.65 ms / 42 tokens ( 7.82 ms per token, 127.87 tokens per second) 0.47.860.777 I slot print_timing: id 0 | task 4115 | total time = 551.38 ms / 659 tokens 0.47.860.778 I slot print_timing: id 0 | task 4115 | graphs reused = 3821 0.47.860.779 I slot print_timing: id 0 | task 4115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.860.813 I slot release: id 0 | task 4115 | stop processing: n_tokens = 670, truncated = 0 0.47.885.131 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 47764701 0.47.885.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 0.47.937.948 I slot launch_slot_: id 0 | task 4161 | processing task, is_child = 0 0.48.535.256 I slot print_timing: id 0 | task 4161 | prompt eval time = 230.63 ms / 601 tokens ( 0.38 ms per token, 2605.86 tokens per second) 0.48.535.262 I slot print_timing: id 0 | task 4161 | eval time = 366.65 ms / 48 tokens ( 7.80 ms per token, 128.19 tokens per second) 0.48.535.263 I slot print_timing: id 0 | task 4161 | total time = 597.29 ms / 649 tokens 0.48.535.264 I slot print_timing: id 0 | task 4161 | graphs reused = 3867 0.48.535.264 I slot print_timing: id 0 | task 4161 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.535.300 I slot release: id 0 | task 4161 | stop processing: n_tokens = 660, truncated = 0 0.48.539.469 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 48439188 0.48.539.530 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 0.48.549.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.48.622.619 I slot launch_slot_: id 0 | task 4213 | processing task, is_child = 0 0.49.198.805 I slot print_timing: id 0 | task 4213 | prompt eval time = 215.93 ms / 533 tokens ( 0.41 ms per token, 2468.40 tokens per second) 0.49.198.810 I slot print_timing: id 0 | task 4213 | eval time = 360.24 ms / 47 tokens ( 7.83 ms per token, 127.69 tokens per second) 0.49.198.811 I slot print_timing: id 0 | task 4213 | total time = 576.17 ms / 580 tokens 0.49.198.812 I slot print_timing: id 0 | task 4213 | graphs reused = 3912 0.49.198.813 I slot print_timing: id 0 | task 4213 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.198.846 I slot release: id 0 | task 4213 | stop processing: n_tokens = 591, truncated = 0 0.49.227.942 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 49102735 0.49.227.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 0.49.298.592 I slot launch_slot_: id 0 | task 4264 | processing task, is_child = 0 0.49.903.488 I slot print_timing: id 0 | task 4264 | prompt eval time = 201.48 ms / 480 tokens ( 0.42 ms per token, 2382.42 tokens per second) 0.49.903.494 I slot print_timing: id 0 | task 4264 | eval time = 403.40 ms / 52 tokens ( 7.91 ms per token, 126.43 tokens per second) 0.49.903.495 I slot print_timing: id 0 | task 4264 | total time = 604.88 ms / 532 tokens 0.49.903.496 I slot print_timing: id 0 | task 4264 | graphs reused = 3961 0.49.903.497 I slot print_timing: id 0 | task 4264 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.903.528 I slot release: id 0 | task 4264 | stop processing: n_tokens = 560, truncated = 0 0.49.908.089 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 49807416 0.49.908.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 0.49.917.749 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.49.970.285 I slot launch_slot_: id 0 | task 4319 | processing task, is_child = 0 0.50.508.172 I slot print_timing: id 0 | task 4319 | prompt eval time = 216.41 ms / 567 tokens ( 0.38 ms per token, 2620.09 tokens per second) 0.50.508.177 I slot print_timing: id 0 | task 4319 | eval time = 321.46 ms / 42 tokens ( 7.84 ms per token, 127.54 tokens per second) 0.50.508.179 I slot print_timing: id 0 | task 4319 | total time = 537.87 ms / 609 tokens 0.50.508.179 I slot print_timing: id 0 | task 4319 | graphs reused = 4001 0.50.508.180 I slot print_timing: id 0 | task 4319 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.508.215 I slot release: id 0 | task 4319 | stop processing: n_tokens = 637, truncated = 0 0.50.526.586 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 50412103 0.50.526.651 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 0.50.537.106 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 0.50.613.667 I slot launch_slot_: id 0 | task 4365 | processing task, is_child = 0 0.51.307.256 I slot print_timing: id 0 | task 4365 | prompt eval time = 211.39 ms / 506 tokens ( 0.42 ms per token, 2393.68 tokens per second) 0.51.307.264 I slot print_timing: id 0 | task 4365 | eval time = 482.18 ms / 63 tokens ( 7.78 ms per token, 128.58 tokens per second) 0.51.307.265 I slot print_timing: id 0 | task 4365 | total time = 693.57 ms / 569 tokens 0.51.307.266 I slot print_timing: id 0 | task 4365 | graphs reused = 4062 0.51.307.267 I slot print_timing: id 0 | task 4365 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.307.300 I slot release: id 0 | task 4365 | stop processing: n_tokens = 597, truncated = 0 0.51.322.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 51211189 0.51.322.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 0.51.333.063 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 0.51.393.075 I slot launch_slot_: id 0 | task 4431 | processing task, is_child = 0 0.51.884.389 I slot print_timing: id 0 | task 4431 | prompt eval time = 185.68 ms / 436 tokens ( 0.43 ms per token, 2348.11 tokens per second) 0.51.884.395 I slot print_timing: id 0 | task 4431 | eval time = 305.61 ms / 40 tokens ( 7.84 ms per token, 127.61 tokens per second) 0.51.884.396 I slot print_timing: id 0 | task 4431 | total time = 491.29 ms / 476 tokens 0.51.884.397 I slot print_timing: id 0 | task 4431 | graphs reused = 4100 0.51.884.398 I slot print_timing: id 0 | task 4431 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.884.431 I slot release: id 0 | task 4431 | stop processing: n_tokens = 504, truncated = 0 0.51.897.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 51788319 0.51.897.909 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 0.51.963.585 I slot launch_slot_: id 0 | task 4474 | processing task, is_child = 0 0.52.645.217 I slot print_timing: id 0 | task 4474 | prompt eval time = 205.28 ms / 519 tokens ( 0.40 ms per token, 2528.19 tokens per second) 0.52.645.223 I slot print_timing: id 0 | task 4474 | eval time = 476.33 ms / 62 tokens ( 7.81 ms per token, 128.06 tokens per second) 0.52.645.224 I slot print_timing: id 0 | task 4474 | total time = 681.61 ms / 581 tokens 0.52.645.225 I slot print_timing: id 0 | task 4474 | graphs reused = 4160 0.52.645.226 I slot print_timing: id 0 | task 4474 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.645.260 I slot release: id 0 | task 4474 | stop processing: n_tokens = 609, truncated = 0 0.52.661.872 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 52549148 0.52.661.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.697 MiB) 0.52.671.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.480 MiB) 0.52.753.437 I slot launch_slot_: id 0 | task 4540 | processing task, is_child = 0 0.53.297.359 I slot print_timing: id 0 | task 4540 | prompt eval time = 188.37 ms / 465 tokens ( 0.41 ms per token, 2468.55 tokens per second) 0.53.297.365 I slot print_timing: id 0 | task 4540 | eval time = 355.53 ms / 46 tokens ( 7.90 ms per token, 126.57 tokens per second) 0.53.297.366 I slot print_timing: id 0 | task 4540 | total time = 543.90 ms / 511 tokens 0.53.297.367 I slot print_timing: id 0 | task 4540 | graphs reused = 4203 0.53.297.367 I slot print_timing: id 0 | task 4540 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.297.400 I slot release: id 0 | task 4540 | stop processing: n_tokens = 542, truncated = 0 0.53.314.065 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 53201288 0.53.314.111 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 0.53.324.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 0.53.408.814 I slot launch_slot_: id 0 | task 4589 | processing task, is_child = 0 0.53.912.504 I slot print_timing: id 0 | task 4589 | prompt eval time = 190.00 ms / 431 tokens ( 0.44 ms per token, 2268.41 tokens per second) 0.53.912.510 I slot print_timing: id 0 | task 4589 | eval time = 313.67 ms / 41 tokens ( 7.84 ms per token, 127.52 tokens per second) 0.53.912.511 I slot print_timing: id 0 | task 4589 | total time = 503.67 ms / 472 tokens 0.53.912.512 I slot print_timing: id 0 | task 4589 | graphs reused = 4242 0.53.912.513 I slot print_timing: id 0 | task 4589 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.912.546 I slot release: id 0 | task 4589 | stop processing: n_tokens = 503, truncated = 0 0.53.916.648 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 53816434 0.53.916.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 0.53.927.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 0.54.013.682 I slot launch_slot_: id 0 | task 4633 | processing task, is_child = 0 0.54.545.072 I slot print_timing: id 0 | task 4633 | prompt eval time = 189.82 ms / 457 tokens ( 0.42 ms per token, 2407.51 tokens per second) 0.54.545.078 I slot print_timing: id 0 | task 4633 | eval time = 341.55 ms / 44 tokens ( 7.94 ms per token, 125.90 tokens per second) 0.54.545.079 I slot print_timing: id 0 | task 4633 | total time = 531.37 ms / 501 tokens 0.54.545.080 I slot print_timing: id 0 | task 4633 | graphs reused = 4283 0.54.545.080 I slot print_timing: id 0 | task 4633 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.545.113 I slot release: id 0 | task 4633 | stop processing: n_tokens = 532, truncated = 0 0.54.560.295 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 54449001 0.54.560.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 0.54.656.062 I slot launch_slot_: id 0 | task 4680 | processing task, is_child = 0 0.55.165.932 I slot print_timing: id 0 | task 4680 | prompt eval time = 189.33 ms / 439 tokens ( 0.43 ms per token, 2318.67 tokens per second) 0.55.165.938 I slot print_timing: id 0 | task 4680 | eval time = 320.52 ms / 42 tokens ( 7.82 ms per token, 127.92 tokens per second) 0.55.165.939 I slot print_timing: id 0 | task 4680 | total time = 509.85 ms / 481 tokens 0.55.165.940 I slot print_timing: id 0 | task 4680 | graphs reused = 4323 0.55.165.941 I slot print_timing: id 0 | task 4680 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.165.972 I slot release: id 0 | task 4680 | stop processing: n_tokens = 512, truncated = 0 0.55.183.673 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 55069861 0.55.183.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.794 MiB) 0.55.196.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 0.55.279.381 I slot launch_slot_: id 0 | task 4725 | processing task, is_child = 0 0.55.934.760 I slot print_timing: id 0 | task 4725 | prompt eval time = 226.78 ms / 606 tokens ( 0.37 ms per token, 2672.18 tokens per second) 0.55.934.766 I slot print_timing: id 0 | task 4725 | eval time = 428.58 ms / 56 tokens ( 7.79 ms per token, 128.33 tokens per second) 0.55.934.767 I slot print_timing: id 0 | task 4725 | total time = 655.36 ms / 662 tokens 0.55.934.768 I slot print_timing: id 0 | task 4725 | graphs reused = 4377 0.55.934.769 I slot print_timing: id 0 | task 4725 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.934.805 I slot release: id 0 | task 4725 | stop processing: n_tokens = 693, truncated = 0 0.55.955.035 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 55838693 0.55.955.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.827 MiB) 0.55.968.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 0.56.061.050 I slot launch_slot_: id 0 | task 4785 | processing task, is_child = 0 0.56.578.063 I slot print_timing: id 0 | task 4785 | prompt eval time = 196.07 ms / 477 tokens ( 0.41 ms per token, 2432.82 tokens per second) 0.56.578.070 I slot print_timing: id 0 | task 4785 | eval time = 320.92 ms / 41 tokens ( 8.02 ms per token, 124.64 tokens per second) 0.56.578.071 I slot print_timing: id 0 | task 4785 | total time = 516.99 ms / 518 tokens 0.56.578.072 I slot print_timing: id 0 | task 4785 | graphs reused = 4415 0.56.578.074 I slot print_timing: id 0 | task 4785 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.578.109 I slot release: id 0 | task 4785 | stop processing: n_tokens = 549, truncated = 0 0.56.593.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 56481997 0.56.593.703 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 0.56.678.937 I slot launch_slot_: id 0 | task 4829 | processing task, is_child = 0 0.57.425.326 I slot print_timing: id 0 | task 4829 | prompt eval time = 286.45 ms / 845 tokens ( 0.34 ms per token, 2949.89 tokens per second) 0.57.425.332 I slot print_timing: id 0 | task 4829 | eval time = 459.92 ms / 60 tokens ( 7.80 ms per token, 128.28 tokens per second) 0.57.425.333 I slot print_timing: id 0 | task 4829 | total time = 746.37 ms / 905 tokens 0.57.425.334 I slot print_timing: id 0 | task 4829 | graphs reused = 4473 0.57.425.335 I slot print_timing: id 0 | task 4829 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.425.380 I slot release: id 0 | task 4829 | stop processing: n_tokens = 936, truncated = 0 0.57.450.870 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 57329268 0.57.450.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 0.57.464.043 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 0.57.561.774 I slot launch_slot_: id 0 | task 4893 | processing task, is_child = 0 0.58.120.685 I slot print_timing: id 0 | task 4893 | prompt eval time = 199.37 ms / 459 tokens ( 0.43 ms per token, 2302.22 tokens per second) 0.58.120.691 I slot print_timing: id 0 | task 4893 | eval time = 359.52 ms / 43 tokens ( 8.56 ms per token, 116.82 tokens per second) 0.58.120.692 I slot print_timing: id 0 | task 4893 | total time = 558.89 ms / 502 tokens 0.58.120.693 I slot print_timing: id 0 | task 4893 | graphs reused = 4513 0.58.120.693 I slot print_timing: id 0 | task 4893 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.120.728 I slot release: id 0 | task 4893 | stop processing: n_tokens = 533, truncated = 0 0.58.149.845 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 58024616 0.58.149.899 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 0.58.231.639 I slot launch_slot_: id 0 | task 4939 | processing task, is_child = 0 0.58.834.855 I slot print_timing: id 0 | task 4939 | prompt eval time = 244.26 ms / 670 tokens ( 0.36 ms per token, 2743.00 tokens per second) 0.58.834.861 I slot print_timing: id 0 | task 4939 | eval time = 358.94 ms / 47 tokens ( 7.80 ms per token, 128.16 tokens per second) 0.58.834.862 I slot print_timing: id 0 | task 4939 | total time = 603.20 ms / 717 tokens 0.58.834.863 I slot print_timing: id 0 | task 4939 | graphs reused = 4558 0.58.834.864 I slot print_timing: id 0 | task 4939 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.834.903 I slot release: id 0 | task 4939 | stop processing: n_tokens = 748, truncated = 0 0.58.858.335 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 58738791 0.58.858.398 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 0.58.871.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 0.58.968.407 I slot launch_slot_: id 0 | task 4990 | processing task, is_child = 0 0.59.770.224 I slot print_timing: id 0 | task 4990 | prompt eval time = 280.77 ms / 775 tokens ( 0.36 ms per token, 2760.31 tokens per second) 0.59.770.230 I slot print_timing: id 0 | task 4990 | eval time = 521.03 ms / 63 tokens ( 8.40 ms per token, 119.00 tokens per second) 0.59.770.231 I slot print_timing: id 0 | task 4990 | total time = 801.80 ms / 838 tokens 0.59.770.233 I slot print_timing: id 0 | task 4990 | graphs reused = 4619 0.59.770.233 I slot print_timing: id 0 | task 4990 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.770.275 I slot release: id 0 | task 4990 | stop processing: n_tokens = 869, truncated = 0 0.59.790.170 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 59674163 0.59.790.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 0.59.803.282 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.141 MiB) 0.59.908.726 I slot launch_slot_: id 0 | task 5057 | processing task, is_child = 0 1.00.675.457 I slot print_timing: id 0 | task 5057 | prompt eval time = 222.76 ms / 573 tokens ( 0.39 ms per token, 2572.25 tokens per second) 1.00.675.463 I slot print_timing: id 0 | task 5057 | eval time = 543.95 ms / 71 tokens ( 7.77 ms per token, 128.69 tokens per second) 1.00.675.464 I slot print_timing: id 0 | task 5057 | total time = 766.71 ms / 644 tokens 1.00.675.464 I slot print_timing: id 0 | task 5057 | graphs reused = 4688 1.00.675.465 I slot print_timing: id 0 | task 5057 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.675.502 I slot release: id 0 | task 5057 | stop processing: n_tokens = 675, truncated = 0 1.00.690.602 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 60579390 1.00.690.666 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.984 MiB) 1.00.703.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 1.00.810.958 I slot launch_slot_: id 0 | task 5132 | processing task, is_child = 0 1.01.496.188 I slot print_timing: id 0 | task 5132 | prompt eval time = 191.21 ms / 461 tokens ( 0.41 ms per token, 2410.95 tokens per second) 1.01.496.194 I slot print_timing: id 0 | task 5132 | eval time = 494.00 ms / 64 tokens ( 7.84 ms per token, 127.53 tokens per second) 1.01.496.195 I slot print_timing: id 0 | task 5132 | total time = 685.21 ms / 525 tokens 1.01.496.196 I slot print_timing: id 0 | task 5132 | graphs reused = 4749 1.01.496.197 I slot print_timing: id 0 | task 5132 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.496.228 I slot release: id 0 | task 5132 | stop processing: n_tokens = 556, truncated = 0 1.01.516.641 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 61400117 1.01.516.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.01.603.090 I slot launch_slot_: id 0 | task 5199 | processing task, is_child = 0 1.02.189.062 I slot print_timing: id 0 | task 5199 | prompt eval time = 223.41 ms / 609 tokens ( 0.37 ms per token, 2725.99 tokens per second) 1.02.189.068 I slot print_timing: id 0 | task 5199 | eval time = 362.55 ms / 43 tokens ( 8.63 ms per token, 115.85 tokens per second) 1.02.189.069 I slot print_timing: id 0 | task 5199 | total time = 585.95 ms / 652 tokens 1.02.189.069 I slot print_timing: id 0 | task 5199 | graphs reused = 4790 1.02.189.070 I slot print_timing: id 0 | task 5199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.189.107 I slot release: id 0 | task 5199 | stop processing: n_tokens = 683, truncated = 0 1.02.210.326 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 62092995 1.02.210.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.02.223.423 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.02.320.099 I slot launch_slot_: id 0 | task 5246 | processing task, is_child = 0 1.02.985.469 I slot print_timing: id 0 | task 5246 | prompt eval time = 276.23 ms / 791 tokens ( 0.35 ms per token, 2863.51 tokens per second) 1.02.985.476 I slot print_timing: id 0 | task 5246 | eval time = 389.12 ms / 47 tokens ( 8.46 ms per token, 118.22 tokens per second) 1.02.985.477 I slot print_timing: id 0 | task 5246 | total time = 665.35 ms / 838 tokens 1.02.985.477 I slot print_timing: id 0 | task 5246 | graphs reused = 4835 1.02.985.478 I slot print_timing: id 0 | task 5246 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.985.525 I slot release: id 0 | task 5246 | stop processing: n_tokens = 869, truncated = 0 1.03.003.247 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 62889413 1.03.003.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 1.03.138.295 I slot launch_slot_: id 0 | task 5297 | processing task, is_child = 0 1.03.781.294 I slot print_timing: id 0 | task 5297 | prompt eval time = 212.28 ms / 533 tokens ( 0.40 ms per token, 2510.79 tokens per second) 1.03.781.299 I slot print_timing: id 0 | task 5297 | eval time = 430.69 ms / 56 tokens ( 7.83 ms per token, 127.70 tokens per second) 1.03.781.300 I slot print_timing: id 0 | task 5297 | total time = 642.98 ms / 589 tokens 1.03.781.301 I slot print_timing: id 0 | task 5297 | graphs reused = 4889 1.03.781.302 I slot print_timing: id 0 | task 5297 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.781.337 I slot release: id 0 | task 5297 | stop processing: n_tokens = 677, truncated = 0 1.03.810.167 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 63685225 1.03.810.232 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 1.03.900.073 I slot launch_slot_: id 0 | task 5357 | processing task, is_child = 0 1.04.512.500 I slot print_timing: id 0 | task 5357 | prompt eval time = 227.33 ms / 566 tokens ( 0.40 ms per token, 2489.78 tokens per second) 1.04.512.505 I slot print_timing: id 0 | task 5357 | eval time = 385.07 ms / 46 tokens ( 8.56 ms per token, 116.86 tokens per second) 1.04.512.506 I slot print_timing: id 0 | task 5357 | total time = 612.40 ms / 612 tokens 1.04.512.507 I slot print_timing: id 0 | task 5357 | graphs reused = 4933 1.04.512.508 I slot print_timing: id 0 | task 5357 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.512.543 I slot release: id 0 | task 5357 | stop processing: n_tokens = 643, truncated = 0 1.04.536.340 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 64416431 1.04.536.397 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.301 MiB) 1.04.630.711 I slot launch_slot_: id 0 | task 5407 | processing task, is_child = 0 1.05.152.978 I slot print_timing: id 0 | task 5407 | prompt eval time = 187.51 ms / 443 tokens ( 0.42 ms per token, 2362.58 tokens per second) 1.05.152.984 I slot print_timing: id 0 | task 5407 | eval time = 334.74 ms / 43 tokens ( 7.97 ms per token, 125.47 tokens per second) 1.05.152.985 I slot print_timing: id 0 | task 5407 | total time = 522.25 ms / 486 tokens 1.05.152.986 I slot print_timing: id 0 | task 5407 | graphs reused = 4973 1.05.152.987 I slot print_timing: id 0 | task 5407 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.153.023 I slot release: id 0 | task 5407 | stop processing: n_tokens = 517, truncated = 0 1.05.175.404 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 65056911 1.05.175.456 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.05.253.074 I slot launch_slot_: id 0 | task 5453 | processing task, is_child = 0 1.06.087.997 I slot print_timing: id 0 | task 5453 | prompt eval time = 190.67 ms / 487 tokens ( 0.39 ms per token, 2554.14 tokens per second) 1.06.088.002 I slot print_timing: id 0 | task 5453 | eval time = 644.23 ms / 74 tokens ( 8.83 ms per token, 113.31 tokens per second) 1.06.088.003 I slot print_timing: id 0 | task 5453 | total time = 834.90 ms / 561 tokens 1.06.088.005 I slot print_timing: id 0 | task 5453 | graphs reused = 5045 1.06.088.005 I slot print_timing: id 0 | task 5453 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.088.038 I slot release: id 0 | task 5453 | stop processing: n_tokens = 592, truncated = 0 1.06.112.190 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 592, t_last = 65991926 1.06.112.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 1.06.200.830 I slot launch_slot_: id 0 | task 5530 | processing task, is_child = 0 1.06.762.184 I slot print_timing: id 0 | task 5530 | prompt eval time = 201.38 ms / 507 tokens ( 0.40 ms per token, 2517.69 tokens per second) 1.06.762.190 I slot print_timing: id 0 | task 5530 | eval time = 359.96 ms / 47 tokens ( 7.83 ms per token, 127.79 tokens per second) 1.06.762.191 I slot print_timing: id 0 | task 5530 | total time = 561.33 ms / 554 tokens 1.06.762.192 I slot print_timing: id 0 | task 5530 | graphs reused = 5090 1.06.762.192 I slot print_timing: id 0 | task 5530 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.762.227 I slot release: id 0 | task 5530 | stop processing: n_tokens = 585, truncated = 0 1.06.766.790 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 66666115 1.06.766.843 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 1.06.784.574 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 1.06.854.413 I slot launch_slot_: id 0 | task 5580 | processing task, is_child = 0 1.07.590.473 I slot print_timing: id 0 | task 5580 | prompt eval time = 230.80 ms / 633 tokens ( 0.36 ms per token, 2742.59 tokens per second) 1.07.590.478 I slot print_timing: id 0 | task 5580 | eval time = 505.23 ms / 66 tokens ( 7.77 ms per token, 128.65 tokens per second) 1.07.590.480 I slot print_timing: id 0 | task 5580 | total time = 736.04 ms / 699 tokens 1.07.590.480 I slot print_timing: id 0 | task 5580 | graphs reused = 5154 1.07.590.481 I slot print_timing: id 0 | task 5580 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.590.520 I slot release: id 0 | task 5580 | stop processing: n_tokens = 730, truncated = 0 1.07.618.542 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 67494409 1.07.618.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.07.718.323 I slot launch_slot_: id 0 | task 5650 | processing task, is_child = 0 1.08.330.391 I slot print_timing: id 0 | task 5650 | prompt eval time = 222.53 ms / 571 tokens ( 0.39 ms per token, 2566.00 tokens per second) 1.08.330.397 I slot print_timing: id 0 | task 5650 | eval time = 389.52 ms / 47 tokens ( 8.47 ms per token, 118.09 tokens per second) 1.08.330.398 I slot print_timing: id 0 | task 5650 | total time = 612.05 ms / 618 tokens 1.08.330.399 I slot print_timing: id 0 | task 5650 | graphs reused = 5199 1.08.330.400 I slot print_timing: id 0 | task 5650 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.330.436 I slot release: id 0 | task 5650 | stop processing: n_tokens = 649, truncated = 0 1.08.348.584 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 68234325 1.08.348.637 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.08.419.075 I slot launch_slot_: id 0 | task 5701 | processing task, is_child = 0 1.09.030.543 I slot print_timing: id 0 | task 5701 | prompt eval time = 274.22 ms / 798 tokens ( 0.34 ms per token, 2910.05 tokens per second) 1.09.030.549 I slot print_timing: id 0 | task 5701 | eval time = 337.23 ms / 44 tokens ( 7.84 ms per token, 127.51 tokens per second) 1.09.030.550 I slot print_timing: id 0 | task 5701 | total time = 611.45 ms / 842 tokens 1.09.030.551 I slot print_timing: id 0 | task 5701 | graphs reused = 5241 1.09.030.552 I slot print_timing: id 0 | task 5701 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.030.595 I slot release: id 0 | task 5701 | stop processing: n_tokens = 873, truncated = 0 1.09.035.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 68934483 1.09.035.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.09.056.487 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 1.09.131.230 I slot launch_slot_: id 0 | task 5749 | processing task, is_child = 0 1.09.681.715 I slot print_timing: id 0 | task 5749 | prompt eval time = 222.37 ms / 572 tokens ( 0.39 ms per token, 2572.32 tokens per second) 1.09.681.720 I slot print_timing: id 0 | task 5749 | eval time = 328.10 ms / 43 tokens ( 7.81 ms per token, 128.01 tokens per second) 1.09.681.721 I slot print_timing: id 0 | task 5749 | total time = 550.46 ms / 615 tokens 1.09.681.722 I slot print_timing: id 0 | task 5749 | graphs reused = 5282 1.09.681.722 I slot print_timing: id 0 | task 5749 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.681.759 I slot release: id 0 | task 5749 | stop processing: n_tokens = 646, truncated = 0 1.09.709.667 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 69585647 1.09.709.725 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.09.807.385 I slot launch_slot_: id 0 | task 5796 | processing task, is_child = 0 1.10.413.441 I slot print_timing: id 0 | task 5796 | prompt eval time = 230.90 ms / 613 tokens ( 0.38 ms per token, 2654.86 tokens per second) 1.10.413.447 I slot print_timing: id 0 | task 5796 | eval time = 375.14 ms / 49 tokens ( 7.82 ms per token, 127.95 tokens per second) 1.10.413.447 I slot print_timing: id 0 | task 5796 | total time = 606.03 ms / 662 tokens 1.10.413.449 I slot print_timing: id 0 | task 5796 | graphs reused = 5329 1.10.413.449 I slot print_timing: id 0 | task 5796 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.413.486 I slot release: id 0 | task 5796 | stop processing: n_tokens = 693, truncated = 0 1.10.441.364 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 70317374 1.10.441.415 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.10.544.642 I slot launch_slot_: id 0 | task 5849 | processing task, is_child = 0 1.11.257.345 I slot print_timing: id 0 | task 5849 | prompt eval time = 221.40 ms / 580 tokens ( 0.38 ms per token, 2619.67 tokens per second) 1.11.257.351 I slot print_timing: id 0 | task 5849 | eval time = 491.28 ms / 64 tokens ( 7.80 ms per token, 128.24 tokens per second) 1.11.257.353 I slot print_timing: id 0 | task 5849 | total time = 712.68 ms / 644 tokens 1.11.257.354 I slot print_timing: id 0 | task 5849 | graphs reused = 5391 1.11.257.355 I slot print_timing: id 0 | task 5849 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.257.398 I slot release: id 0 | task 5849 | stop processing: n_tokens = 675, truncated = 0 1.11.284.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 71161287 1.11.284.124 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.11.394.695 I slot launch_slot_: id 0 | task 5917 | processing task, is_child = 0 1.12.038.514 I slot print_timing: id 0 | task 5917 | prompt eval time = 255.22 ms / 716 tokens ( 0.36 ms per token, 2805.37 tokens per second) 1.12.038.520 I slot print_timing: id 0 | task 5917 | eval time = 388.57 ms / 50 tokens ( 7.93 ms per token, 126.10 tokens per second) 1.12.038.521 I slot print_timing: id 0 | task 5917 | total time = 643.80 ms / 766 tokens 1.12.038.522 I slot print_timing: id 0 | task 5917 | graphs reused = 5438 1.12.038.523 I slot print_timing: id 0 | task 5917 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.038.564 I slot release: id 0 | task 5917 | stop processing: n_tokens = 797, truncated = 0 1.12.066.028 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 71942453 1.12.066.092 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.12.085.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.12.190.926 I slot launch_slot_: id 0 | task 5971 | processing task, is_child = 0 1.13.252.266 I slot print_timing: id 0 | task 5971 | prompt eval time = 275.37 ms / 799 tokens ( 0.34 ms per token, 2901.59 tokens per second) 1.13.252.272 I slot print_timing: id 0 | task 5971 | eval time = 785.95 ms / 102 tokens ( 7.78 ms per token, 128.51 tokens per second) 1.13.252.273 I slot print_timing: id 0 | task 5971 | total time = 1061.32 ms / 901 tokens 1.13.252.274 I slot print_timing: id 0 | task 5971 | graphs reused = 5538 1.13.252.275 I slot print_timing: id 0 | task 5971 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.252.317 I slot release: id 0 | task 5971 | stop processing: n_tokens = 932, truncated = 0 1.13.272.048 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 73156206 1.13.272.117 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 1.13.361.670 I slot launch_slot_: id 0 | task 6077 | processing task, is_child = 0 1.14.384.368 I slot print_timing: id 0 | task 6077 | prompt eval time = 163.37 ms / 361 tokens ( 0.45 ms per token, 2209.76 tokens per second) 1.14.384.374 I slot print_timing: id 0 | task 6077 | eval time = 859.31 ms / 112 tokens ( 7.74 ms per token, 129.17 tokens per second) 1.14.384.375 I slot print_timing: id 0 | task 6077 | total time = 1022.68 ms / 473 tokens 1.14.384.376 I slot print_timing: id 0 | task 6077 | graphs reused = 5648 1.14.384.377 I slot print_timing: id 0 | task 6077 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.384.410 I slot release: id 0 | task 6077 | stop processing: n_tokens = 504, truncated = 0 1.14.388.642 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 74288298 1.14.388.691 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.14.468.785 I slot launch_slot_: id 0 | task 6192 | processing task, is_child = 0 1.15.470.139 I slot print_timing: id 0 | task 6192 | prompt eval time = 167.28 ms / 381 tokens ( 0.44 ms per token, 2277.60 tokens per second) 1.15.470.144 I slot print_timing: id 0 | task 6192 | eval time = 834.05 ms / 108 tokens ( 7.79 ms per token, 128.29 tokens per second) 1.15.470.145 I slot print_timing: id 0 | task 6192 | total time = 1001.33 ms / 489 tokens 1.15.470.146 I slot print_timing: id 0 | task 6192 | graphs reused = 5753 1.15.470.147 I slot print_timing: id 0 | task 6192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.470.178 I slot release: id 0 | task 6192 | stop processing: n_tokens = 520, truncated = 0 1.15.495.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 75374066 1.15.496.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.15.574.440 I slot launch_slot_: id 0 | task 6303 | processing task, is_child = 0 1.16.694.847 I slot print_timing: id 0 | task 6303 | prompt eval time = 162.78 ms / 365 tokens ( 0.45 ms per token, 2242.36 tokens per second) 1.16.694.852 I slot print_timing: id 0 | task 6303 | eval time = 957.61 ms / 124 tokens ( 7.79 ms per token, 128.44 tokens per second) 1.16.694.854 I slot print_timing: id 0 | task 6303 | total time = 1120.39 ms / 489 tokens 1.16.694.855 I slot print_timing: id 0 | task 6303 | graphs reused = 5874 1.16.694.855 I slot print_timing: id 0 | task 6303 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.694.885 I slot release: id 0 | task 6303 | stop processing: n_tokens = 520, truncated = 0 1.16.721.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 76598773 1.16.721.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.16.804.900 I slot launch_slot_: id 0 | task 6430 | processing task, is_child = 0 1.17.789.662 I slot print_timing: id 0 | task 6430 | prompt eval time = 164.36 ms / 333 tokens ( 0.49 ms per token, 2026.05 tokens per second) 1.17.789.668 I slot print_timing: id 0 | task 6430 | eval time = 820.38 ms / 107 tokens ( 7.74 ms per token, 129.21 tokens per second) 1.17.789.669 I slot print_timing: id 0 | task 6430 | total time = 984.74 ms / 440 tokens 1.17.789.670 I slot print_timing: id 0 | task 6430 | graphs reused = 5979 1.17.789.671 I slot print_timing: id 0 | task 6430 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.789.701 I slot release: id 0 | task 6430 | stop processing: n_tokens = 471, truncated = 0 1.17.814.109 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 77693589 1.17.864.193 I slot launch_slot_: id 0 | task 6540 | processing task, is_child = 0 1.19.100.191 I slot print_timing: id 0 | task 6540 | prompt eval time = 169.35 ms / 403 tokens ( 0.42 ms per token, 2379.63 tokens per second) 1.19.100.197 I slot print_timing: id 0 | task 6540 | eval time = 1066.62 ms / 138 tokens ( 7.79 ms per token, 128.44 tokens per second) 1.19.100.198 I slot print_timing: id 0 | task 6540 | total time = 1235.98 ms / 541 tokens 1.19.100.199 I slot print_timing: id 0 | task 6540 | graphs reused = 6114 1.19.100.200 I slot print_timing: id 0 | task 6540 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.100.230 I slot release: id 0 | task 6540 | stop processing: n_tokens = 572, truncated = 0 1.19.114.314 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 79004119 1.19.114.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.19.204.605 I slot launch_slot_: id 0 | task 6681 | processing task, is_child = 0 1.20.809.387 I slot print_timing: id 0 | task 6681 | prompt eval time = 171.15 ms / 411 tokens ( 0.42 ms per token, 2401.44 tokens per second) 1.20.809.393 I slot print_timing: id 0 | task 6681 | eval time = 1433.62 ms / 185 tokens ( 7.79 ms per token, 128.35 tokens per second) 1.20.809.394 I slot print_timing: id 0 | task 6681 | total time = 1604.76 ms / 596 tokens 1.20.809.395 I slot print_timing: id 0 | task 6681 | graphs reused = 6296 1.20.809.396 I slot print_timing: id 0 | task 6681 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.809.426 I slot release: id 0 | task 6681 | stop processing: n_tokens = 627, truncated = 0 1.20.825.837 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 80713315 1.20.825.899 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.20.925.317 I slot launch_slot_: id 0 | task 6869 | processing task, is_child = 0 1.22.884.745 I slot print_timing: id 0 | task 6869 | prompt eval time = 204.10 ms / 490 tokens ( 0.42 ms per token, 2400.80 tokens per second) 1.22.884.751 I slot print_timing: id 0 | task 6869 | eval time = 1755.31 ms / 225 tokens ( 7.84 ms per token, 127.61 tokens per second) 1.22.884.752 I slot print_timing: id 0 | task 6869 | total time = 1959.41 ms / 715 tokens 1.22.884.753 I slot print_timing: id 0 | task 6869 | graphs reused = 6519 1.22.884.754 I slot print_timing: id 0 | task 6869 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.884.788 I slot release: id 0 | task 6869 | stop processing: n_tokens = 746, truncated = 0 1.22.905.640 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 82788676 1.22.905.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.23.003.674 I slot launch_slot_: id 0 | task 7097 | processing task, is_child = 0 1.26.010.846 I slot print_timing: id 0 | task 7097 | prompt eval time = 158.72 ms / 344 tokens ( 0.46 ms per token, 2167.38 tokens per second) 1.26.010.851 I slot print_timing: id 0 | task 7097 | eval time = 2848.43 ms / 368 tokens ( 7.76 ms per token, 128.84 tokens per second) 1.26.010.852 I slot print_timing: id 0 | task 7097 | total time = 3007.15 ms / 712 tokens 1.26.010.853 I slot print_timing: id 0 | task 7097 | graphs reused = 6884 1.26.010.854 I slot print_timing: id 0 | task 7097 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.010.882 I slot release: id 0 | task 7097 | stop processing: n_tokens = 743, truncated = 0 1.26.036.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 743, t_last = 85914770 1.26.036.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 1.26.131.283 I slot launch_slot_: id 0 | task 7468 | processing task, is_child = 0 1.29.291.339 I slot print_timing: id 0 | task 7468 | n_gen = 389, tg = 129.30 t/s, tg_3s = 129.63 t/s 1.30.316.919 I slot print_timing: id 0 | task 7468 | prompt eval time = 159.16 ms / 347 tokens ( 0.46 ms per token, 2180.17 tokens per second) 1.30.316.925 I slot print_timing: id 0 | task 7468 | eval time = 4026.45 ms / 521 tokens ( 7.74 ms per token, 129.15 tokens per second) 1.30.316.926 I slot print_timing: id 0 | task 7468 | total time = 4185.62 ms / 868 tokens 1.30.316.927 I slot print_timing: id 0 | task 7468 | graphs reused = 7401 1.30.316.928 I slot print_timing: id 0 | task 7468 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.316.957 I slot release: id 0 | task 7468 | stop processing: n_tokens = 899, truncated = 0 1.30.338.152 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 90220845 1.30.338.222 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.114 MiB) 1.30.435.216 I slot launch_slot_: id 0 | task 7992 | processing task, is_child = 0 1.33.236.890 I slot print_timing: id 0 | task 7992 | prompt eval time = 173.27 ms / 401 tokens ( 0.43 ms per token, 2314.29 tokens per second) 1.33.236.896 I slot print_timing: id 0 | task 7992 | eval time = 2628.38 ms / 339 tokens ( 7.78 ms per token, 128.60 tokens per second) 1.33.236.897 I slot print_timing: id 0 | task 7992 | total time = 2801.65 ms / 740 tokens 1.33.236.898 I slot print_timing: id 0 | task 7992 | graphs reused = 7736 1.33.236.899 I slot print_timing: id 0 | task 7992 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.236.928 I slot release: id 0 | task 7992 | stop processing: n_tokens = 771, truncated = 0 1.33.263.154 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 771, t_last = 93140816 1.33.263.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.33.359.246 I slot launch_slot_: id 0 | task 8334 | processing task, is_child = 0 1.34.465.819 I slot print_timing: id 0 | task 8334 | prompt eval time = 184.56 ms / 456 tokens ( 0.40 ms per token, 2470.79 tokens per second) 1.34.465.825 I slot print_timing: id 0 | task 8334 | eval time = 922.00 ms / 115 tokens ( 8.09 ms per token, 123.64 tokens per second) 1.34.465.826 I slot print_timing: id 0 | task 8334 | total time = 1106.55 ms / 571 tokens 1.34.465.827 I slot print_timing: id 0 | task 8334 | graphs reused = 7848 1.34.465.828 I slot print_timing: id 0 | task 8334 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.465.860 I slot release: id 0 | task 8334 | stop processing: n_tokens = 602, truncated = 0 1.34.493.681 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 1.34.493.735 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.34.594.262 I slot launch_slot_: id 0 | task 8452 | processing task, is_child = 0 1.35.749.603 I slot print_timing: id 0 | task 8452 | prompt eval time = 174.55 ms / 406 tokens ( 0.43 ms per token, 2325.94 tokens per second) 1.35.749.609 I slot print_timing: id 0 | task 8452 | eval time = 980.77 ms / 127 tokens ( 7.78 ms per token, 128.47 tokens per second) 1.35.749.610 I slot print_timing: id 0 | task 8452 | total time = 1155.32 ms / 533 tokens 1.35.749.610 I slot print_timing: id 0 | task 8452 | graphs reused = 7972 1.35.749.611 I slot print_timing: id 0 | task 8452 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.749.642 I slot release: id 0 | task 8452 | stop processing: n_tokens = 564, truncated = 0 1.35.775.836 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 564, t_last = 95653530 1.35.836.660 I slot launch_slot_: id 0 | task 8582 | processing task, is_child = 0 1.37.480.455 I slot print_timing: id 0 | task 8582 | prompt eval time = 176.19 ms / 406 tokens ( 0.43 ms per token, 2304.28 tokens per second) 1.37.480.461 I slot print_timing: id 0 | task 8582 | eval time = 1467.58 ms / 190 tokens ( 7.76 ms per token, 128.78 tokens per second) 1.37.480.462 I slot print_timing: id 0 | task 8582 | total time = 1643.77 ms / 596 tokens 1.37.480.463 I slot print_timing: id 0 | task 8582 | graphs reused = 8159 1.37.480.464 I slot print_timing: id 0 | task 8582 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.480.494 I slot release: id 0 | task 8582 | stop processing: n_tokens = 627, truncated = 0 1.37.506.139 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 97384382 1.37.506.196 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.37.607.656 I slot launch_slot_: id 0 | task 8775 | processing task, is_child = 0 1.38.902.571 I slot print_timing: id 0 | task 8775 | prompt eval time = 179.49 ms / 444 tokens ( 0.40 ms per token, 2473.68 tokens per second) 1.38.902.576 I slot print_timing: id 0 | task 8775 | eval time = 1115.40 ms / 144 tokens ( 7.80 ms per token, 128.20 tokens per second) 1.38.902.577 I slot print_timing: id 0 | task 8775 | total time = 1294.89 ms / 588 tokens 1.38.902.579 I slot print_timing: id 0 | task 8775 | graphs reused = 8300 1.38.902.581 I slot print_timing: id 0 | task 8775 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.902.612 I slot release: id 0 | task 8775 | stop processing: n_tokens = 619, truncated = 0 1.38.925.735 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 98806500 1.38.925.786 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.39.021.165 I slot launch_slot_: id 0 | task 8922 | processing task, is_child = 0 1.39.978.472 I slot print_timing: id 0 | task 8922 | prompt eval time = 166.16 ms / 372 tokens ( 0.45 ms per token, 2238.74 tokens per second) 1.39.978.478 I slot print_timing: id 0 | task 8922 | eval time = 791.12 ms / 103 tokens ( 7.76 ms per token, 128.93 tokens per second) 1.39.978.479 I slot print_timing: id 0 | task 8922 | total time = 957.29 ms / 475 tokens 1.39.978.480 I slot print_timing: id 0 | task 8922 | graphs reused = 8401 1.39.978.481 I slot print_timing: id 0 | task 8922 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.978.511 I slot release: id 0 | task 8922 | stop processing: n_tokens = 506, truncated = 0 1.40.001.720 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 99882399 1.40.001.770 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.017 MiB) 1.40.093.457 I slot launch_slot_: id 0 | task 9028 | processing task, is_child = 0 1.42.055.234 I slot print_timing: id 0 | task 9028 | prompt eval time = 180.98 ms / 454 tokens ( 0.40 ms per token, 2508.51 tokens per second) 1.42.055.240 I slot print_timing: id 0 | task 9028 | eval time = 1780.77 ms / 230 tokens ( 7.78 ms per token, 128.60 tokens per second) 1.42.055.241 I slot print_timing: id 0 | task 9028 | total time = 1961.76 ms / 684 tokens 1.42.055.242 I slot print_timing: id 0 | task 9028 | graphs reused = 8628 1.42.055.243 I slot print_timing: id 0 | task 9028 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.055.274 I slot release: id 0 | task 9028 | stop processing: n_tokens = 715, truncated = 0 1.42.084.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 101959162 1.42.084.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.42.153.731 I slot launch_slot_: id 0 | task 9261 | processing task, is_child = 0 1.44.064.951 I slot print_timing: id 0 | task 9261 | prompt eval time = 165.99 ms / 354 tokens ( 0.47 ms per token, 2132.67 tokens per second) 1.44.064.956 I slot print_timing: id 0 | task 9261 | eval time = 1745.21 ms / 226 tokens ( 7.76 ms per token, 128.92 tokens per second) 1.44.064.957 I slot print_timing: id 0 | task 9261 | total time = 1911.20 ms / 580 tokens 1.44.064.958 I slot print_timing: id 0 | task 9261 | graphs reused = 8851 1.44.064.959 I slot print_timing: id 0 | task 9261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.064.989 I slot release: id 0 | task 9261 | stop processing: n_tokens = 611, truncated = 0 1.44.080.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 103968877 1.44.080.315 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.44.174.894 I slot launch_slot_: id 0 | task 9490 | processing task, is_child = 0 1.45.412.384 I slot print_timing: id 0 | task 9490 | prompt eval time = 159.35 ms / 334 tokens ( 0.48 ms per token, 2096.05 tokens per second) 1.45.412.389 I slot print_timing: id 0 | task 9490 | eval time = 1078.12 ms / 140 tokens ( 7.76 ms per token, 128.93 tokens per second) 1.45.412.390 I slot print_timing: id 0 | task 9490 | total time = 1237.47 ms / 474 tokens 1.45.412.391 I slot print_timing: id 0 | task 9490 | graphs reused = 8989 1.45.412.392 I slot print_timing: id 0 | task 9490 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.412.421 I slot release: id 0 | task 9490 | stop processing: n_tokens = 505, truncated = 0 1.45.438.774 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 105316309 1.45.438.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.050 MiB) 1.45.509.232 I slot launch_slot_: id 0 | task 9633 | processing task, is_child = 0 1.47.037.927 I slot print_timing: id 0 | task 9633 | prompt eval time = 177.90 ms / 426 tokens ( 0.42 ms per token, 2394.55 tokens per second) 1.47.037.932 I slot print_timing: id 0 | task 9633 | eval time = 1350.77 ms / 175 tokens ( 7.76 ms per token, 128.82 tokens per second) 1.47.037.934 I slot print_timing: id 0 | task 9633 | total time = 1528.67 ms / 601 tokens 1.47.037.934 I slot print_timing: id 0 | task 9633 | graphs reused = 9161 1.47.037.935 I slot print_timing: id 0 | task 9633 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.037.966 I slot release: id 0 | task 9633 | stop processing: n_tokens = 632, truncated = 0 1.47.052.198 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 106941854 1.47.052.246 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 1.47.124.063 I slot launch_slot_: id 0 | task 9811 | processing task, is_child = 0 1.48.210.454 I slot print_timing: id 0 | task 9811 | prompt eval time = 163.93 ms / 366 tokens ( 0.45 ms per token, 2232.62 tokens per second) 1.48.210.462 I slot print_timing: id 0 | task 9811 | eval time = 922.44 ms / 117 tokens ( 7.95 ms per token, 125.75 tokens per second) 1.48.210.463 I slot print_timing: id 0 | task 9811 | total time = 1086.37 ms / 483 tokens 1.48.210.464 I slot print_timing: id 0 | task 9811 | graphs reused = 9275 1.48.210.465 I slot print_timing: id 0 | task 9811 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.210.502 I slot release: id 0 | task 9811 | stop processing: n_tokens = 514, truncated = 0 1.48.214.612 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 108114391 1.48.214.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 1.48.314.907 I slot launch_slot_: id 0 | task 9931 | processing task, is_child = 0 1.49.929.134 I slot print_timing: id 0 | task 9931 | prompt eval time = 188.91 ms / 462 tokens ( 0.41 ms per token, 2445.65 tokens per second) 1.49.929.140 I slot print_timing: id 0 | task 9931 | eval time = 1425.30 ms / 184 tokens ( 7.79 ms per token, 128.39 tokens per second) 1.49.929.141 I slot print_timing: id 0 | task 9931 | total time = 1614.21 ms / 646 tokens 1.49.929.142 I slot print_timing: id 0 | task 9931 | graphs reused = 9456 1.49.929.142 I slot print_timing: id 0 | task 9931 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.929.174 I slot release: id 0 | task 9931 | stop processing: n_tokens = 677, truncated = 0 1.49.948.871 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 109833062 1.49.948.929 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.50.041.802 I slot launch_slot_: id 0 | task 10118 | processing task, is_child = 0 1.53.217.700 I slot print_timing: id 0 | task 10118 | n_gen = 388, tg = 128.96 t/s, tg_3s = 129.29 t/s 1.53.358.217 I slot print_timing: id 0 | task 10118 | prompt eval time = 174.88 ms / 396 tokens ( 0.44 ms per token, 2264.40 tokens per second) 1.53.358.223 I slot print_timing: id 0 | task 10118 | eval time = 3141.51 ms / 406 tokens ( 7.76 ms per token, 128.92 tokens per second) 1.53.358.224 I slot print_timing: id 0 | task 10118 | total time = 3316.40 ms / 802 tokens 1.53.358.225 I slot print_timing: id 0 | task 10118 | graphs reused = 9858 1.53.358.226 I slot print_timing: id 0 | task 10118 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.358.256 I slot release: id 0 | task 10118 | stop processing: n_tokens = 833, truncated = 0 1.53.377.664 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 833, t_last = 113262144 1.53.377.720 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.863 MiB) 1.53.475.850 I slot launch_slot_: id 0 | task 10527 | processing task, is_child = 0 1.54.906.314 I slot print_timing: id 0 | task 10527 | prompt eval time = 185.61 ms / 458 tokens ( 0.41 ms per token, 2467.53 tokens per second) 1.54.906.320 I slot print_timing: id 0 | task 10527 | eval time = 1244.83 ms / 161 tokens ( 7.78 ms per token, 128.53 tokens per second) 1.54.906.321 I slot print_timing: id 0 | task 10527 | total time = 1430.44 ms / 619 tokens 1.54.906.322 I slot print_timing: id 0 | task 10527 | graphs reused = 10016 1.54.906.322 I slot print_timing: id 0 | task 10527 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.906.355 I slot release: id 0 | task 10527 | stop processing: n_tokens = 650, truncated = 0 1.54.926.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 114810243 1.54.994.749 I slot launch_slot_: id 0 | task 10691 | processing task, is_child = 0 1.56.575.165 I slot print_timing: id 0 | task 10691 | prompt eval time = 188.76 ms / 458 tokens ( 0.41 ms per token, 2426.40 tokens per second) 1.56.575.171 I slot print_timing: id 0 | task 10691 | eval time = 1391.64 ms / 176 tokens ( 7.95 ms per token, 125.75 tokens per second) 1.56.575.172 I slot print_timing: id 0 | task 10691 | total time = 1580.40 ms / 634 tokens 1.56.575.173 I slot print_timing: id 0 | task 10691 | graphs reused = 10189 1.56.575.173 I slot print_timing: id 0 | task 10691 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.575.205 I slot release: id 0 | task 10691 | stop processing: n_tokens = 665, truncated = 0 1.56.595.755 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 116479093 1.56.595.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 1.56.691.231 I slot launch_slot_: id 0 | task 10870 | processing task, is_child = 0 1.58.499.286 I slot print_timing: id 0 | task 10870 | prompt eval time = 185.76 ms / 452 tokens ( 0.41 ms per token, 2433.23 tokens per second) 1.58.499.292 I slot print_timing: id 0 | task 10870 | eval time = 1622.27 ms / 210 tokens ( 7.76 ms per token, 128.83 tokens per second) 1.58.499.293 I slot print_timing: id 0 | task 10870 | total time = 1808.03 ms / 662 tokens 1.58.499.293 I slot print_timing: id 0 | task 10870 | graphs reused = 10396 1.58.499.294 I slot print_timing: id 0 | task 10870 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.499.326 I slot release: id 0 | task 10870 | stop processing: n_tokens = 693, truncated = 0 1.58.518.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 118403214 1.58.518.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 1.58.616.700 I slot launch_slot_: id 0 | task 11083 | processing task, is_child = 0 1.59.721.645 I slot print_timing: id 0 | task 11083 | prompt eval time = 177.77 ms / 404 tokens ( 0.44 ms per token, 2272.56 tokens per second) 1.59.721.651 I slot print_timing: id 0 | task 11083 | eval time = 927.15 ms / 120 tokens ( 7.79 ms per token, 128.35 tokens per second) 1.59.721.652 I slot print_timing: id 0 | task 11083 | total time = 1104.93 ms / 524 tokens 1.59.721.653 I slot print_timing: id 0 | task 11083 | graphs reused = 10513 1.59.721.654 I slot print_timing: id 0 | task 11083 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.721.683 I slot release: id 0 | task 11083 | stop processing: n_tokens = 555, truncated = 0 1.59.748.693 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 119625572 1.59.748.745 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 1.59.832.652 I slot launch_slot_: id 0 | task 11206 | processing task, is_child = 0 2.00.806.206 I slot print_timing: id 0 | task 11206 | prompt eval time = 160.18 ms / 345 tokens ( 0.46 ms per token, 2153.85 tokens per second) 2.00.806.212 I slot print_timing: id 0 | task 11206 | eval time = 813.36 ms / 106 tokens ( 7.75 ms per token, 129.09 tokens per second) 2.00.806.213 I slot print_timing: id 0 | task 11206 | total time = 973.53 ms / 451 tokens 2.00.806.214 I slot print_timing: id 0 | task 11206 | graphs reused = 10617 2.00.806.215 I slot print_timing: id 0 | task 11206 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.806.245 I slot release: id 0 | task 11206 | stop processing: n_tokens = 482, truncated = 0 2.00.830.545 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 120710133 2.00.830.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.00.916.579 I slot launch_slot_: id 0 | task 11315 | processing task, is_child = 0 2.01.914.953 I slot print_timing: id 0 | task 11315 | prompt eval time = 187.21 ms / 430 tokens ( 0.44 ms per token, 2296.85 tokens per second) 2.01.914.959 I slot print_timing: id 0 | task 11315 | eval time = 811.14 ms / 105 tokens ( 7.80 ms per token, 128.21 tokens per second) 2.01.914.960 I slot print_timing: id 0 | task 11315 | total time = 998.36 ms / 535 tokens 2.01.914.961 I slot print_timing: id 0 | task 11315 | graphs reused = 10719 2.01.914.962 I slot print_timing: id 0 | task 11315 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.914.993 I slot release: id 0 | task 11315 | stop processing: n_tokens = 566, truncated = 0 2.01.940.717 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 121818881 2.01.940.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.02.030.332 I slot launch_slot_: id 0 | task 11423 | processing task, is_child = 0 2.02.864.938 I slot print_timing: id 0 | task 11423 | prompt eval time = 152.42 ms / 316 tokens ( 0.48 ms per token, 2073.16 tokens per second) 2.02.864.943 I slot print_timing: id 0 | task 11423 | eval time = 682.16 ms / 85 tokens ( 8.12 ms per token, 123.14 tokens per second) 2.02.864.944 I slot print_timing: id 0 | task 11423 | total time = 834.58 ms / 401 tokens 2.02.864.946 I slot print_timing: id 0 | task 11423 | graphs reused = 10802 2.02.864.947 I slot print_timing: id 0 | task 11423 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.864.977 I slot release: id 0 | task 11423 | stop processing: n_tokens = 432, truncated = 0 2.02.889.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 122768865 2.02.889.694 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 2.02.979.648 I slot launch_slot_: id 0 | task 11511 | processing task, is_child = 0 2.03.964.060 I slot print_timing: id 0 | task 11511 | prompt eval time = 163.18 ms / 354 tokens ( 0.46 ms per token, 2169.40 tokens per second) 2.03.964.066 I slot print_timing: id 0 | task 11511 | eval time = 821.21 ms / 107 tokens ( 7.75 ms per token, 129.08 tokens per second) 2.03.964.066 I slot print_timing: id 0 | task 11511 | total time = 984.39 ms / 461 tokens 2.03.964.067 I slot print_timing: id 0 | task 11511 | graphs reused = 10907 2.03.964.068 I slot print_timing: id 0 | task 11511 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.964.098 I slot release: id 0 | task 11511 | stop processing: n_tokens = 492, truncated = 0 2.03.980.791 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 123867986 2.03.980.839 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 2.04.075.871 I slot launch_slot_: id 0 | task 11621 | processing task, is_child = 0 2.05.019.227 I slot print_timing: id 0 | task 11621 | prompt eval time = 186.39 ms / 438 tokens ( 0.43 ms per token, 2349.87 tokens per second) 2.05.019.233 I slot print_timing: id 0 | task 11621 | eval time = 756.94 ms / 98 tokens ( 7.80 ms per token, 128.15 tokens per second) 2.05.019.234 I slot print_timing: id 0 | task 11621 | total time = 943.34 ms / 536 tokens 2.05.019.234 I slot print_timing: id 0 | task 11621 | graphs reused = 11002 2.05.019.235 I slot print_timing: id 0 | task 11621 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.019.267 I slot release: id 0 | task 11621 | stop processing: n_tokens = 567, truncated = 0 2.05.038.867 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 124923155 2.05.038.918 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 2.05.130.704 I slot launch_slot_: id 0 | task 11722 | processing task, is_child = 0 2.05.859.853 I slot print_timing: id 0 | task 11722 | prompt eval time = 188.13 ms / 457 tokens ( 0.41 ms per token, 2429.15 tokens per second) 2.05.859.859 I slot print_timing: id 0 | task 11722 | eval time = 541.00 ms / 70 tokens ( 7.84 ms per token, 127.54 tokens per second) 2.05.859.860 I slot print_timing: id 0 | task 11722 | total time = 729.13 ms / 527 tokens 2.05.859.861 I slot print_timing: id 0 | task 11722 | graphs reused = 11069 2.05.859.862 I slot print_timing: id 0 | task 11722 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.859.892 I slot release: id 0 | task 11722 | stop processing: n_tokens = 558, truncated = 0 2.05.863.907 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 125763780 2.05.863.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 2.05.962.398 I slot launch_slot_: id 0 | task 11795 | processing task, is_child = 0 2.07.059.807 I slot print_timing: id 0 | task 11795 | prompt eval time = 194.50 ms / 473 tokens ( 0.41 ms per token, 2431.94 tokens per second) 2.07.059.813 I slot print_timing: id 0 | task 11795 | eval time = 902.89 ms / 117 tokens ( 7.78 ms per token, 128.48 tokens per second) 2.07.059.814 I slot print_timing: id 0 | task 11795 | total time = 1097.39 ms / 590 tokens 2.07.059.815 I slot print_timing: id 0 | task 11795 | graphs reused = 11183 2.07.059.816 I slot print_timing: id 0 | task 11795 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.059.847 I slot release: id 0 | task 11795 | stop processing: n_tokens = 621, truncated = 0 2.07.064.136 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 126963736 2.07.064.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.739 MiB) 2.07.158.157 I slot launch_slot_: id 0 | task 11915 | processing task, is_child = 0 2.07.557.950 I slot print_timing: id 0 | task 11915 | prompt eval time = 189.48 ms / 476 tokens ( 0.40 ms per token, 2512.15 tokens per second) 2.07.557.956 I slot print_timing: id 0 | task 11915 | eval time = 210.29 ms / 27 tokens ( 8.09 ms per token, 123.64 tokens per second) 2.07.557.957 I slot print_timing: id 0 | task 11915 | total time = 399.77 ms / 503 tokens 2.07.557.958 I slot print_timing: id 0 | task 11915 | graphs reused = 11207 2.07.557.959 I slot print_timing: id 0 | task 11915 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.557.992 I slot release: id 0 | task 11915 | stop processing: n_tokens = 534, truncated = 0 2.07.578.700 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 127461880 2.07.578.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.618 MiB) 2.07.669.728 I slot launch_slot_: id 0 | task 11945 | processing task, is_child = 0 2.08.851.275 I slot print_timing: id 0 | task 11945 | prompt eval time = 194.11 ms / 466 tokens ( 0.42 ms per token, 2400.74 tokens per second) 2.08.851.280 I slot print_timing: id 0 | task 11945 | eval time = 987.42 ms / 128 tokens ( 7.77 ms per token, 128.62 tokens per second) 2.08.851.281 I slot print_timing: id 0 | task 11945 | total time = 1181.53 ms / 594 tokens 2.08.851.282 I slot print_timing: id 0 | task 11945 | graphs reused = 11332 2.08.851.283 I slot print_timing: id 0 | task 11945 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.851.315 I slot release: id 0 | task 11945 | stop processing: n_tokens = 625, truncated = 0 2.08.875.397 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 625, t_last = 128755203 2.08.875.452 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.615 MiB) 2.08.964.874 I slot launch_slot_: id 0 | task 12076 | processing task, is_child = 0 2.09.738.969 I slot print_timing: id 0 | task 12076 | prompt eval time = 170.70 ms / 415 tokens ( 0.41 ms per token, 2431.17 tokens per second) 2.09.738.975 I slot print_timing: id 0 | task 12076 | eval time = 603.37 ms / 78 tokens ( 7.84 ms per token, 127.62 tokens per second) 2.09.738.976 I slot print_timing: id 0 | task 12076 | total time = 774.07 ms / 493 tokens 2.09.738.977 I slot print_timing: id 0 | task 12076 | graphs reused = 11407 2.09.738.978 I slot print_timing: id 0 | task 12076 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.739.009 I slot release: id 0 | task 12076 | stop processing: n_tokens = 524, truncated = 0 2.09.762.406 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 129642897 2.09.762.455 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.09.841.920 I slot launch_slot_: id 0 | task 12157 | processing task, is_child = 0 2.10.498.370 I slot print_timing: id 0 | task 12157 | prompt eval time = 163.50 ms / 352 tokens ( 0.46 ms per token, 2152.85 tokens per second) 2.10.498.376 I slot print_timing: id 0 | task 12157 | eval time = 492.92 ms / 64 tokens ( 7.82 ms per token, 127.81 tokens per second) 2.10.498.377 I slot print_timing: id 0 | task 12157 | total time = 656.43 ms / 416 tokens 2.10.498.378 I slot print_timing: id 0 | task 12157 | graphs reused = 11469 2.10.498.379 I slot print_timing: id 0 | task 12157 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.498.411 I slot release: id 0 | task 12157 | stop processing: n_tokens = 447, truncated = 0 2.10.527.203 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 130402299 2.10.527.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.142 MiB) 2.10.617.751 I slot launch_slot_: id 0 | task 12224 | processing task, is_child = 0 2.11.857.804 I slot print_timing: id 0 | task 12224 | prompt eval time = 218.07 ms / 550 tokens ( 0.40 ms per token, 2522.10 tokens per second) 2.11.857.810 I slot print_timing: id 0 | task 12224 | eval time = 1021.96 ms / 133 tokens ( 7.74 ms per token, 129.16 tokens per second) 2.11.857.810 I slot print_timing: id 0 | task 12224 | total time = 1240.03 ms / 683 tokens 2.11.857.811 I slot print_timing: id 0 | task 12224 | graphs reused = 11600 2.11.857.812 I slot print_timing: id 0 | task 12224 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.857.848 I slot release: id 0 | task 12224 | stop processing: n_tokens = 714, truncated = 0 2.11.878.069 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 131761736 2.11.878.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 2.11.986.252 I slot launch_slot_: id 0 | task 12361 | processing task, is_child = 0 2.13.436.640 I slot print_timing: id 0 | task 12361 | prompt eval time = 262.58 ms / 772 tokens ( 0.34 ms per token, 2940.09 tokens per second) 2.13.436.646 I slot print_timing: id 0 | task 12361 | eval time = 1187.79 ms / 154 tokens ( 7.76 ms per token, 128.81 tokens per second) 2.13.436.647 I slot print_timing: id 0 | task 12361 | total time = 1450.37 ms / 926 tokens 2.13.436.648 I slot print_timing: id 0 | task 12361 | graphs reused = 11752 2.13.436.649 I slot print_timing: id 0 | task 12361 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.436.693 I slot release: id 0 | task 12361 | stop processing: n_tokens = 957, truncated = 0 2.13.465.333 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 957, t_last = 133340581 2.13.465.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 2.13.584.330 I slot launch_slot_: id 0 | task 12519 | processing task, is_child = 0 2.15.442.974 I slot print_timing: id 0 | task 12519 | prompt eval time = 253.78 ms / 683 tokens ( 0.37 ms per token, 2691.36 tokens per second) 2.15.442.980 I slot print_timing: id 0 | task 12519 | eval time = 1604.85 ms / 206 tokens ( 7.83 ms per token, 127.74 tokens per second) 2.15.442.982 I slot print_timing: id 0 | task 12519 | total time = 1858.62 ms / 889 tokens 2.15.442.982 I slot print_timing: id 0 | task 12519 | graphs reused = 11955 2.15.442.983 I slot print_timing: id 0 | task 12519 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.443.020 I slot release: id 0 | task 12519 | stop processing: n_tokens = 920, truncated = 0 2.15.467.372 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 920, t_last = 135346908 2.15.467.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 2.15.578.787 I slot launch_slot_: id 0 | task 12729 | processing task, is_child = 0 2.18.816.711 I slot print_timing: id 0 | task 12729 | n_gen = 389, tg = 129.07 t/s, tg_3s = 129.41 t/s 2.21.822.758 I slot print_timing: id 0 | task 12729 | n_gen = 776, tg = 128.91 t/s, tg_3s = 128.74 t/s 2.23.747.691 I slot print_timing: id 0 | task 12729 | prompt eval time = 231.88 ms / 579 tokens ( 0.40 ms per token, 2496.97 tokens per second) 2.23.747.696 I slot print_timing: id 0 | task 12729 | eval time = 7937.00 ms / 1024 tokens ( 7.76 ms per token, 128.89 tokens per second) 2.23.747.697 I slot print_timing: id 0 | task 12729 | total time = 8168.88 ms / 1603 tokens 2.23.747.698 I slot print_timing: id 0 | task 12729 | graphs reused = 12973 2.23.747.698 I slot print_timing: id 0 | task 12729 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.747.734 I slot release: id 0 | task 12729 | stop processing: n_tokens = 1634, truncated = 0 2.23.767.426 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1634, t_last = 143651622 2.23.767.517 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 2.23.789.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 2.23.879.993 I slot launch_slot_: id 0 | task 13757 | processing task, is_child = 0 2.24.901.670 I slot print_timing: id 0 | task 13757 | prompt eval time = 206.53 ms / 500 tokens ( 0.41 ms per token, 2420.99 tokens per second) 2.24.901.675 I slot print_timing: id 0 | task 13757 | eval time = 815.13 ms / 106 tokens ( 7.76 ms per token, 128.81 tokens per second) 2.24.901.677 I slot print_timing: id 0 | task 13757 | total time = 1021.66 ms / 606 tokens 2.24.901.678 I slot print_timing: id 0 | task 13757 | graphs reused = 13077 2.24.901.679 I slot print_timing: id 0 | task 13757 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.901.712 I slot release: id 0 | task 13757 | stop processing: n_tokens = 637, truncated = 0 2.24.931.924 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 144805600 2.24.931.982 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 2.25.001.045 I slot launch_slot_: id 0 | task 13866 | processing task, is_child = 0 2.26.186.547 I slot print_timing: id 0 | task 13866 | prompt eval time = 270.92 ms / 776 tokens ( 0.35 ms per token, 2864.32 tokens per second) 2.26.186.553 I slot print_timing: id 0 | task 13866 | eval time = 914.56 ms / 119 tokens ( 7.75 ms per token, 129.02 tokens per second) 2.26.186.554 I slot print_timing: id 0 | task 13866 | total time = 1185.48 ms / 895 tokens 2.26.186.555 I slot print_timing: id 0 | task 13866 | graphs reused = 13194 2.26.186.556 I slot print_timing: id 0 | task 13866 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.186.595 I slot release: id 0 | task 13866 | stop processing: n_tokens = 926, truncated = 0 2.26.215.785 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 926, t_last = 146090483 2.26.215.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 2.26.288.873 I slot launch_slot_: id 0 | task 13989 | processing task, is_child = 0 2.28.441.323 I slot print_timing: id 0 | task 13989 | prompt eval time = 200.86 ms / 504 tokens ( 0.40 ms per token, 2509.24 tokens per second) 2.28.441.328 I slot print_timing: id 0 | task 13989 | eval time = 1951.57 ms / 253 tokens ( 7.74 ms per token, 129.13 tokens per second) 2.28.441.329 I slot print_timing: id 0 | task 13989 | total time = 2152.43 ms / 757 tokens 2.28.441.330 I slot print_timing: id 0 | task 13989 | graphs reused = 13444 2.28.441.331 I slot print_timing: id 0 | task 13989 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.441.364 I slot release: id 0 | task 13989 | stop processing: n_tokens = 788, truncated = 0 2.28.446.030 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 788, t_last = 148345252 2.28.446.082 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 2.28.533.884 I slot launch_slot_: id 0 | task 14245 | processing task, is_child = 0 2.29.900.691 I slot print_timing: id 0 | task 14245 | prompt eval time = 237.32 ms / 633 tokens ( 0.37 ms per token, 2667.24 tokens per second) 2.29.900.697 I slot print_timing: id 0 | task 14245 | eval time = 1129.46 ms / 146 tokens ( 7.79 ms per token, 128.38 tokens per second) 2.29.900.698 I slot print_timing: id 0 | task 14245 | total time = 1366.79 ms / 779 tokens 2.29.900.699 I slot print_timing: id 0 | task 14245 | graphs reused = 13587 2.29.900.700 I slot print_timing: id 0 | task 14245 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.900.738 I slot release: id 0 | task 14245 | stop processing: n_tokens = 810, truncated = 0 2.29.926.485 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 149804626 2.29.926.551 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.675 MiB) 2.30.030.968 I slot launch_slot_: id 0 | task 14395 | processing task, is_child = 0 2.31.244.701 I slot print_timing: id 0 | task 14395 | prompt eval time = 179.01 ms / 395 tokens ( 0.45 ms per token, 2206.53 tokens per second) 2.31.244.708 I slot print_timing: id 0 | task 14395 | eval time = 1034.70 ms / 134 tokens ( 7.78 ms per token, 128.54 tokens per second) 2.31.244.709 I slot print_timing: id 0 | task 14395 | total time = 1213.71 ms / 529 tokens 2.31.244.710 I slot print_timing: id 0 | task 14395 | graphs reused = 13718 2.31.244.711 I slot print_timing: id 0 | task 14395 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.244.747 I slot release: id 0 | task 14395 | stop processing: n_tokens = 560, truncated = 0 2.31.249.165 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 151148635 2.31.249.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.554 MiB) 2.31.344.495 I slot launch_slot_: id 0 | task 14532 | processing task, is_child = 0 2.33.187.530 I slot print_timing: id 0 | task 14532 | prompt eval time = 224.56 ms / 584 tokens ( 0.38 ms per token, 2600.62 tokens per second) 2.33.187.536 I slot print_timing: id 0 | task 14532 | eval time = 1618.45 ms / 209 tokens ( 7.78 ms per token, 128.52 tokens per second) 2.33.187.537 I slot print_timing: id 0 | task 14532 | total time = 1843.01 ms / 793 tokens 2.33.187.537 I slot print_timing: id 0 | task 14532 | graphs reused = 13924 2.33.187.538 I slot print_timing: id 0 | task 14532 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.187.573 I slot release: id 0 | task 14532 | stop processing: n_tokens = 824, truncated = 0 2.33.215.352 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 153091462 2.33.215.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 2.33.327.038 I slot launch_slot_: id 0 | task 14745 | processing task, is_child = 0 2.35.371.688 I slot print_timing: id 0 | task 14745 | prompt eval time = 256.68 ms / 695 tokens ( 0.37 ms per token, 2707.64 tokens per second) 2.35.371.694 I slot print_timing: id 0 | task 14745 | eval time = 1787.95 ms / 230 tokens ( 7.81 ms per token, 128.08 tokens per second) 2.35.371.695 I slot print_timing: id 0 | task 14745 | total time = 2044.63 ms / 925 tokens 2.35.371.696 I slot print_timing: id 0 | task 14745 | graphs reused = 14151 2.35.371.697 I slot print_timing: id 0 | task 14745 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.371.737 I slot release: id 0 | task 14745 | stop processing: n_tokens = 956, truncated = 0 2.35.376.731 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 155275625 2.35.376.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.300 MiB) 2.35.487.493 I slot launch_slot_: id 0 | task 14979 | processing task, is_child = 0 2.37.414.614 I slot print_timing: id 0 | task 14979 | prompt eval time = 271.17 ms / 769 tokens ( 0.35 ms per token, 2835.83 tokens per second) 2.37.414.622 I slot print_timing: id 0 | task 14979 | eval time = 1655.93 ms / 215 tokens ( 7.74 ms per token, 129.23 tokens per second) 2.37.414.623 I slot print_timing: id 0 | task 14979 | total time = 1927.10 ms / 984 tokens 2.37.414.624 I slot print_timing: id 0 | task 14979 | graphs reused = 14364 2.37.414.625 I slot print_timing: id 0 | task 14979 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.414.669 I slot release: id 0 | task 14979 | stop processing: n_tokens = 1015, truncated = 0 2.37.430.388 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1015, t_last = 157318557 2.37.430.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 2.37.450.430 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.860 MiB) 2.37.565.129 I slot launch_slot_: id 0 | task 15198 | processing task, is_child = 0 2.38.745.600 I slot print_timing: id 0 | task 15198 | prompt eval time = 221.67 ms / 576 tokens ( 0.38 ms per token, 2598.43 tokens per second) 2.38.745.606 I slot print_timing: id 0 | task 15198 | eval time = 958.78 ms / 124 tokens ( 7.79 ms per token, 128.29 tokens per second) 2.38.745.607 I slot print_timing: id 0 | task 15198 | total time = 1180.45 ms / 700 tokens 2.38.745.608 I slot print_timing: id 0 | task 15198 | graphs reused = 14486 2.38.745.609 I slot print_timing: id 0 | task 15198 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.745.644 I slot release: id 0 | task 15198 | stop processing: n_tokens = 731, truncated = 0 2.38.767.667 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 158649533 2.38.767.719 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 2.38.850.087 I slot launch_slot_: id 0 | task 15326 | processing task, is_child = 0 2.40.199.078 I slot print_timing: id 0 | task 15326 | prompt eval time = 248.49 ms / 655 tokens ( 0.38 ms per token, 2635.96 tokens per second) 2.40.199.083 I slot print_timing: id 0 | task 15326 | eval time = 1100.49 ms / 142 tokens ( 7.80 ms per token, 128.13 tokens per second) 2.40.199.084 I slot print_timing: id 0 | task 15326 | total time = 1348.97 ms / 797 tokens 2.40.199.085 I slot print_timing: id 0 | task 15326 | graphs reused = 14625 2.40.199.086 I slot print_timing: id 0 | task 15326 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.199.124 I slot release: id 0 | task 15326 | stop processing: n_tokens = 828, truncated = 0 2.40.220.575 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 160103012 2.40.220.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.40.318.115 I slot launch_slot_: id 0 | task 15472 | processing task, is_child = 0 2.42.055.957 I slot print_timing: id 0 | task 15472 | prompt eval time = 236.22 ms / 621 tokens ( 0.38 ms per token, 2628.94 tokens per second) 2.42.055.963 I slot print_timing: id 0 | task 15472 | eval time = 1501.61 ms / 194 tokens ( 7.78 ms per token, 128.53 tokens per second) 2.42.055.964 I slot print_timing: id 0 | task 15472 | total time = 1737.82 ms / 815 tokens 2.42.055.965 I slot print_timing: id 0 | task 15472 | graphs reused = 14816 2.42.055.966 I slot print_timing: id 0 | task 15472 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.056.003 I slot release: id 0 | task 15472 | stop processing: n_tokens = 846, truncated = 0 2.42.078.399 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 846, t_last = 161959891 2.42.078.464 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 2.42.195.553 I slot launch_slot_: id 0 | task 15670 | processing task, is_child = 0 2.44.141.823 I slot print_timing: id 0 | task 15670 | prompt eval time = 266.52 ms / 767 tokens ( 0.35 ms per token, 2877.85 tokens per second) 2.44.141.828 I slot print_timing: id 0 | task 15670 | eval time = 1679.73 ms / 213 tokens ( 7.92 ms per token, 126.21 tokens per second) 2.44.141.830 I slot print_timing: id 0 | task 15670 | total time = 1946.25 ms / 980 tokens 2.44.141.830 I slot print_timing: id 0 | task 15670 | graphs reused = 15027 2.44.141.831 I slot print_timing: id 0 | task 15670 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.141.873 I slot release: id 0 | task 15670 | stop processing: n_tokens = 1011, truncated = 0 2.44.165.766 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1011, t_last = 164045762 2.44.165.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 2.44.273.343 I slot launch_slot_: id 0 | task 15887 | processing task, is_child = 0 2.47.578.680 I slot print_timing: id 0 | task 15887 | n_gen = 383, tg = 127.21 t/s, tg_3s = 127.54 t/s 2.50.579.897 I slot print_timing: id 0 | task 15887 | n_gen = 768, tg = 127.75 t/s, tg_3s = 128.28 t/s 2.52.578.694 I slot print_timing: id 0 | task 15887 | prompt eval time = 302.45 ms / 864 tokens ( 0.35 ms per token, 2856.66 tokens per second) 2.52.578.699 I slot print_timing: id 0 | task 15887 | eval time = 8002.88 ms / 1024 tokens ( 7.82 ms per token, 127.83 tokens per second) 2.52.578.700 I slot print_timing: id 0 | task 15887 | total time = 8305.33 ms / 1888 tokens 2.52.578.701 I slot print_timing: id 0 | task 15887 | graphs reused = 16045 2.52.578.702 I slot print_timing: id 0 | task 15887 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.578.748 I slot release: id 0 | task 15887 | stop processing: n_tokens = 1919, truncated = 0 2.52.608.426 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1919, t_last = 172482636 2.52.608.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 2.52.628.769 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.52.751.757 I slot launch_slot_: id 0 | task 16915 | processing task, is_child = 0 2.54.088.178 I slot print_timing: id 0 | task 16915 | prompt eval time = 250.81 ms / 646 tokens ( 0.39 ms per token, 2575.62 tokens per second) 2.54.088.184 I slot print_timing: id 0 | task 16915 | eval time = 1085.59 ms / 140 tokens ( 7.81 ms per token, 128.04 tokens per second) 2.54.088.185 I slot print_timing: id 0 | task 16915 | total time = 1336.40 ms / 786 tokens 2.54.088.186 I slot print_timing: id 0 | task 16915 | graphs reused = 16182 2.54.088.186 I slot print_timing: id 0 | task 16915 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.088.225 I slot release: id 0 | task 16915 | stop processing: n_tokens = 817, truncated = 0 2.54.115.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 817, t_last = 173992113 2.54.115.128 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.924 MiB) 2.54.204.629 I slot launch_slot_: id 0 | task 17059 | processing task, is_child = 0 2.56.517.198 I slot print_timing: id 0 | task 17059 | prompt eval time = 258.73 ms / 720 tokens ( 0.36 ms per token, 2782.88 tokens per second) 2.56.517.204 I slot print_timing: id 0 | task 17059 | eval time = 2053.82 ms / 257 tokens ( 8.02 ms per token, 124.65 tokens per second) 2.56.517.205 I slot print_timing: id 0 | task 17059 | total time = 2312.55 ms / 977 tokens 2.56.517.206 I slot print_timing: id 0 | task 17059 | graphs reused = 16436 2.56.517.207 I slot print_timing: id 0 | task 17059 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.517.247 I slot release: id 0 | task 17059 | stop processing: n_tokens = 1008, truncated = 0 2.56.534.222 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1008, t_last = 176421136 2.56.534.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.203 MiB) 2.56.639.805 I slot launch_slot_: id 0 | task 17320 | processing task, is_child = 0 2.58.496.697 I slot print_timing: id 0 | task 17320 | prompt eval time = 206.27 ms / 509 tokens ( 0.41 ms per token, 2467.68 tokens per second) 2.58.496.703 I slot print_timing: id 0 | task 17320 | eval time = 1650.61 ms / 214 tokens ( 7.75 ms per token, 129.04 tokens per second) 2.58.496.704 I slot print_timing: id 0 | task 17320 | total time = 1856.87 ms / 723 tokens 2.58.496.705 I slot print_timing: id 0 | task 17320 | graphs reused = 16648 2.58.496.705 I slot print_timing: id 0 | task 17320 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.496.739 I slot release: id 0 | task 17320 | stop processing: n_tokens = 754, truncated = 0 2.58.526.440 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 178400628 2.58.526.502 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.049 MiB) 2.58.621.952 I slot launch_slot_: id 0 | task 17537 | processing task, is_child = 0 3.00.725.908 I slot print_timing: id 0 | task 17537 | prompt eval time = 223.36 ms / 581 tokens ( 0.38 ms per token, 2601.19 tokens per second) 3.00.725.914 I slot print_timing: id 0 | task 17537 | eval time = 1880.58 ms / 242 tokens ( 7.80 ms per token, 128.15 tokens per second) 3.00.725.915 I slot print_timing: id 0 | task 17537 | total time = 2103.93 ms / 823 tokens 3.00.725.916 I slot print_timing: id 0 | task 17537 | graphs reused = 16887 3.00.725.917 I slot print_timing: id 0 | task 17537 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.725.958 I slot release: id 0 | task 17537 | stop processing: n_tokens = 854, truncated = 0 3.00.741.636 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 180629846 3.00.741.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 3.00.867.151 I slot launch_slot_: id 0 | task 17783 | processing task, is_child = 0 3.03.219.549 I slot print_timing: id 0 | task 17783 | prompt eval time = 307.46 ms / 925 tokens ( 0.33 ms per token, 3008.48 tokens per second) 3.03.219.554 I slot print_timing: id 0 | task 17783 | eval time = 2044.91 ms / 262 tokens ( 7.83 ms per token, 127.63 tokens per second) 3.03.219.555 I slot print_timing: id 0 | task 17783 | total time = 2352.38 ms / 1187 tokens 3.03.219.556 I slot print_timing: id 0 | task 17783 | graphs reused = 17146 3.03.219.557 I slot print_timing: id 0 | task 17783 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.219.603 I slot release: id 0 | task 17783 | stop processing: n_tokens = 1218, truncated = 0 3.03.245.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1218, t_last = 183123491 3.03.245.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 3.03.356.939 I slot launch_slot_: id 0 | task 18049 | processing task, is_child = 0 3.04.836.172 I slot print_timing: id 0 | task 18049 | prompt eval time = 293.66 ms / 885 tokens ( 0.33 ms per token, 3013.73 tokens per second) 3.04.836.177 I slot print_timing: id 0 | task 18049 | eval time = 1185.56 ms / 153 tokens ( 7.80 ms per token, 128.21 tokens per second) 3.04.836.178 I slot print_timing: id 0 | task 18049 | total time = 1479.21 ms / 1038 tokens 3.04.836.179 I slot print_timing: id 0 | task 18049 | graphs reused = 17296 3.04.836.180 I slot print_timing: id 0 | task 18049 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.836.225 I slot release: id 0 | task 18049 | stop processing: n_tokens = 1069, truncated = 0 3.04.860.369 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1069, t_last = 184740113 3.04.860.446 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 3.04.883.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.682 MiB) 3.05.003.047 I slot launch_slot_: id 0 | task 18206 | processing task, is_child = 0 3.06.937.487 I slot print_timing: id 0 | task 18206 | prompt eval time = 171.36 ms / 392 tokens ( 0.44 ms per token, 2287.64 tokens per second) 3.06.937.493 I slot print_timing: id 0 | task 18206 | eval time = 1763.07 ms / 228 tokens ( 7.77 ms per token, 128.75 tokens per second) 3.06.937.494 I slot print_timing: id 0 | task 18206 | total time = 1934.42 ms / 620 tokens 3.06.937.494 I slot print_timing: id 0 | task 18206 | graphs reused = 17521 3.06.937.495 I slot print_timing: id 0 | task 18206 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.937.526 I slot release: id 0 | task 18206 | stop processing: n_tokens = 651, truncated = 0 3.06.951.671 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 651, t_last = 186841414 3.06.997.025 I slot launch_slot_: id 0 | task 18437 | processing task, is_child = 0 3.08.038.053 I slot print_timing: id 0 | task 18437 | prompt eval time = 155.71 ms / 331 tokens ( 0.47 ms per token, 2125.71 tokens per second) 3.08.038.059 I slot print_timing: id 0 | task 18437 | eval time = 885.29 ms / 115 tokens ( 7.77 ms per token, 128.77 tokens per second) 3.08.038.060 I slot print_timing: id 0 | task 18437 | total time = 1041.01 ms / 446 tokens 3.08.038.062 I slot print_timing: id 0 | task 18437 | graphs reused = 17634 3.08.038.064 I slot print_timing: id 0 | task 18437 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.038.094 I slot release: id 0 | task 18437 | stop processing: n_tokens = 477, truncated = 0 3.08.062.944 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 477, t_last = 187941982 3.08.062.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.525 MiB) 3.08.164.603 I slot launch_slot_: id 0 | task 18555 | processing task, is_child = 0 3.10.199.992 I slot print_timing: id 0 | task 18555 | prompt eval time = 159.01 ms / 357 tokens ( 0.45 ms per token, 2245.16 tokens per second) 3.10.199.998 I slot print_timing: id 0 | task 18555 | eval time = 1876.36 ms / 243 tokens ( 7.75 ms per token, 128.97 tokens per second) 3.10.199.999 I slot print_timing: id 0 | task 18555 | total time = 2035.37 ms / 600 tokens 3.10.200.000 I slot print_timing: id 0 | task 18555 | graphs reused = 17874 3.10.200.000 I slot print_timing: id 0 | task 18555 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.200.029 I slot release: id 0 | task 18555 | stop processing: n_tokens = 631, truncated = 0 3.10.221.863 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 631, t_last = 190103917 3.10.221.918 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 402.854 MiB) 3.10.301.385 I slot launch_slot_: id 0 | task 18801 | processing task, is_child = 0 3.10.832.156 I slot print_timing: id 0 | task 18801 | prompt eval time = 154.87 ms / 315 tokens ( 0.49 ms per token, 2033.96 tokens per second) 3.10.832.162 I slot print_timing: id 0 | task 18801 | eval time = 375.88 ms / 49 tokens ( 7.83 ms per token, 127.70 tokens per second) 3.10.832.163 I slot print_timing: id 0 | task 18801 | total time = 530.75 ms / 364 tokens 3.10.832.164 I slot print_timing: id 0 | task 18801 | graphs reused = 17921 3.10.832.165 I slot print_timing: id 0 | task 18801 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.832.193 I slot release: id 0 | task 18801 | stop processing: n_tokens = 395, truncated = 0 3.10.835.975 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 190736081 3.10.836.018 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 3.10.898.239 I slot launch_slot_: id 0 | task 18853 | processing task, is_child = 0 3.14.063.521 I slot print_timing: id 0 | task 18853 | n_gen = 388, tg = 128.81 t/s, tg_3s = 129.15 t/s 3.14.983.553 I slot print_timing: id 0 | task 18853 | prompt eval time = 160.95 ms / 378 tokens ( 0.43 ms per token, 2348.54 tokens per second) 3.14.983.558 I slot print_timing: id 0 | task 18853 | eval time = 3924.34 ms / 507 tokens ( 7.76 ms per token, 128.94 tokens per second) 3.14.983.559 I slot print_timing: id 0 | task 18853 | total time = 4085.30 ms / 885 tokens 3.14.983.560 I slot print_timing: id 0 | task 18853 | graphs reused = 18424 3.14.983.561 I slot print_timing: id 0 | task 18853 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.983.591 I slot release: id 0 | task 18853 | stop processing: n_tokens = 916, truncated = 0 3.14.999.705 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 916, t_last = 194887479 3.14.999.770 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.713 MiB) 3.15.075.786 I slot launch_slot_: id 0 | task 19363 | processing task, is_child = 0 3.15.436.679 I slot print_timing: id 0 | task 19363 | prompt eval time = 147.90 ms / 295 tokens ( 0.50 ms per token, 1994.56 tokens per second) 3.15.436.685 I slot print_timing: id 0 | task 19363 | eval time = 212.97 ms / 28 tokens ( 7.89 ms per token, 126.78 tokens per second) 3.15.436.687 I slot print_timing: id 0 | task 19363 | total time = 360.87 ms / 323 tokens 3.15.436.687 I slot print_timing: id 0 | task 19363 | graphs reused = 18450 3.15.436.688 I slot print_timing: id 0 | task 19363 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.436.714 I slot release: id 0 | task 19363 | stop processing: n_tokens = 354, truncated = 0 3.15.454.335 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 195340603 3.15.454.371 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.147 MiB) 3.15.541.489 I slot launch_slot_: id 0 | task 19394 | processing task, is_child = 0 3.16.078.070 I slot print_timing: id 0 | task 19394 | prompt eval time = 155.05 ms / 337 tokens ( 0.46 ms per token, 2173.48 tokens per second) 3.16.078.076 I slot print_timing: id 0 | task 19394 | eval time = 381.51 ms / 46 tokens ( 8.48 ms per token, 117.95 tokens per second) 3.16.078.077 I slot print_timing: id 0 | task 19394 | total time = 536.56 ms / 383 tokens 3.16.078.077 I slot print_timing: id 0 | task 19394 | graphs reused = 18494 3.16.078.078 I slot print_timing: id 0 | task 19394 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.078.105 I slot release: id 0 | task 19394 | stop processing: n_tokens = 414, truncated = 0 3.16.105.375 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 195981994 3.16.105.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.085 MiB) 3.16.195.937 I slot launch_slot_: id 0 | task 19443 | processing task, is_child = 0 3.17.398.532 I slot print_timing: id 0 | task 19443 | prompt eval time = 158.93 ms / 325 tokens ( 0.49 ms per token, 2044.96 tokens per second) 3.17.398.538 I slot print_timing: id 0 | task 19443 | eval time = 1043.65 ms / 136 tokens ( 7.73 ms per token, 129.35 tokens per second) 3.17.398.539 I slot print_timing: id 0 | task 19443 | total time = 1202.58 ms / 461 tokens 3.17.398.540 I slot print_timing: id 0 | task 19443 | graphs reused = 18628 3.17.398.540 I slot print_timing: id 0 | task 19443 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.398.569 I slot release: id 0 | task 19443 | stop processing: n_tokens = 492, truncated = 0 3.17.419.260 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.065 3.17.477.194 I slot launch_slot_: id 0 | task 19582 | processing task, is_child = 0 3.18.053.788 I slot print_timing: id 0 | task 19582 | prompt eval time = 138.74 ms / 264 tokens ( 0.53 ms per token, 1902.91 tokens per second) 3.18.053.794 I slot print_timing: id 0 | task 19582 | eval time = 437.84 ms / 57 tokens ( 7.82 ms per token, 127.90 tokens per second) 3.18.053.795 I slot print_timing: id 0 | task 19582 | total time = 576.57 ms / 321 tokens 3.18.053.796 I slot print_timing: id 0 | task 19582 | graphs reused = 18683 3.18.053.797 I slot print_timing: id 0 | task 19582 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.053.823 I slot release: id 0 | task 19582 | stop processing: n_tokens = 352, truncated = 0 3.18.071.114 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 197957711 3.18.071.155 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 3.18.169.372 I slot launch_slot_: id 0 | task 19642 | processing task, is_child = 0 3.18.486.478 I slot print_timing: id 0 | task 19642 | prompt eval time = 156.39 ms / 331 tokens ( 0.47 ms per token, 2116.45 tokens per second) 3.18.486.484 I slot print_timing: id 0 | task 19642 | eval time = 160.69 ms / 21 tokens ( 8.03 ms per token, 124.46 tokens per second) 3.18.486.486 I slot print_timing: id 0 | task 19642 | total time = 317.09 ms / 352 tokens 3.18.486.486 I slot print_timing: id 0 | task 19642 | graphs reused = 18702 3.18.486.488 I slot print_timing: id 0 | task 19642 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.486.517 I slot release: id 0 | task 19642 | stop processing: n_tokens = 383, truncated = 0 3.18.508.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 198390406 3.18.508.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 3.18.608.792 I slot launch_slot_: id 0 | task 19666 | processing task, is_child = 0 3.19.435.590 I slot print_timing: id 0 | task 19666 | prompt eval time = 157.07 ms / 333 tokens ( 0.47 ms per token, 2120.03 tokens per second) 3.19.435.597 I slot print_timing: id 0 | task 19666 | eval time = 669.70 ms / 86 tokens ( 7.88 ms per token, 126.92 tokens per second) 3.19.435.599 I slot print_timing: id 0 | task 19666 | total time = 826.78 ms / 419 tokens 3.19.435.600 I slot print_timing: id 0 | task 19666 | graphs reused = 18786 3.19.435.601 I slot print_timing: id 0 | task 19666 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.435.636 I slot release: id 0 | task 19666 | stop processing: n_tokens = 450, truncated = 0 3.19.459.804 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 199339524 3.19.459.850 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 3.19.568.031 I slot launch_slot_: id 0 | task 19755 | processing task, is_child = 0 3.21.357.340 I slot print_timing: id 0 | task 19755 | prompt eval time = 159.48 ms / 346 tokens ( 0.46 ms per token, 2169.51 tokens per second) 3.21.357.347 I slot print_timing: id 0 | task 19755 | eval time = 1629.81 ms / 211 tokens ( 7.76 ms per token, 128.85 tokens per second) 3.21.357.349 I slot print_timing: id 0 | task 19755 | total time = 1789.29 ms / 557 tokens 3.21.357.350 I slot print_timing: id 0 | task 19755 | graphs reused = 18994 3.21.357.352 I slot print_timing: id 0 | task 19755 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.357.383 I slot release: id 0 | task 19755 | stop processing: n_tokens = 588, truncated = 0 3.21.385.051 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 201261272 3.21.385.104 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.496 MiB) 3.21.479.806 I slot launch_slot_: id 0 | task 19969 | processing task, is_child = 0 3.22.137.102 I slot print_timing: id 0 | task 19969 | prompt eval time = 159.57 ms / 325 tokens ( 0.49 ms per token, 2036.66 tokens per second) 3.22.137.107 I slot print_timing: id 0 | task 19969 | eval time = 497.70 ms / 65 tokens ( 7.78 ms per token, 128.59 tokens per second) 3.22.137.108 I slot print_timing: id 0 | task 19969 | total time = 657.28 ms / 390 tokens 3.22.137.109 I slot print_timing: id 0 | task 19969 | graphs reused = 19057 3.22.137.110 I slot print_timing: id 0 | task 19969 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.137.138 I slot release: id 0 | task 19969 | stop processing: n_tokens = 421, truncated = 0 3.22.162.512 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 202041026 3.22.162.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 3.22.253.732 I slot launch_slot_: id 0 | task 20037 | processing task, is_child = 0 3.25.099.021 I slot print_timing: id 0 | task 20037 | prompt eval time = 155.85 ms / 322 tokens ( 0.48 ms per token, 2066.02 tokens per second) 3.25.099.026 I slot print_timing: id 0 | task 20037 | eval time = 2689.41 ms / 349 tokens ( 7.73 ms per token, 129.40 tokens per second) 3.25.099.027 I slot print_timing: id 0 | task 20037 | total time = 2845.27 ms / 671 tokens 3.25.099.028 I slot print_timing: id 0 | task 20037 | graphs reused = 19403 3.25.099.028 I slot print_timing: id 0 | task 20037 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.099.056 I slot release: id 0 | task 20037 | stop processing: n_tokens = 702, truncated = 0 3.25.123.092 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 702, t_last = 205002944 3.25.123.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 3.25.213.575 I slot launch_slot_: id 0 | task 20389 | processing task, is_child = 0 3.28.372.682 I slot print_timing: id 0 | task 20389 | n_gen = 389, tg = 129.22 t/s, tg_3s = 129.55 t/s 3.31.380.044 I slot print_timing: id 0 | task 20389 | n_gen = 776, tg = 128.95 t/s, tg_3s = 128.68 t/s 3.33.305.135 I slot print_timing: id 0 | task 20389 | prompt eval time = 156.44 ms / 338 tokens ( 0.46 ms per token, 2160.52 tokens per second) 3.33.305.141 I slot print_timing: id 0 | task 20389 | eval time = 7935.10 ms / 1024 tokens ( 7.76 ms per token, 128.92 tokens per second) 3.33.305.142 I slot print_timing: id 0 | task 20389 | total time = 8091.54 ms / 1362 tokens 3.33.305.143 I slot print_timing: id 0 | task 20389 | graphs reused = 20421 3.33.305.143 I slot print_timing: id 0 | task 20389 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.305.171 I slot release: id 0 | task 20389 | stop processing: n_tokens = 1393, truncated = 0 3.33.308.939 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1393, t_last = 213209059 3.33.309.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.211 MiB) 3.33.412.070 I slot launch_slot_: id 0 | task 21416 | processing task, is_child = 0 3.36.570.823 I slot print_timing: id 0 | task 21416 | n_gen = 389, tg = 129.32 t/s, tg_3s = 129.65 t/s 3.39.574.221 I slot print_timing: id 0 | task 21416 | n_gen = 776, tg = 129.09 t/s, tg_3s = 128.85 t/s 3.41.498.206 I slot print_timing: id 0 | task 21416 | prompt eval time = 158.42 ms / 347 tokens ( 0.46 ms per token, 2190.39 tokens per second) 3.41.498.211 I slot print_timing: id 0 | task 21416 | eval time = 7927.70 ms / 1024 tokens ( 7.75 ms per token, 129.04 tokens per second) 3.41.498.212 I slot print_timing: id 0 | task 21416 | total time = 8086.12 ms / 1371 tokens 3.41.498.213 I slot print_timing: id 0 | task 21416 | graphs reused = 21439 3.41.498.213 I slot print_timing: id 0 | task 21416 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.498.245 I slot release: id 0 | task 21416 | stop processing: n_tokens = 1402, truncated = 0 3.41.514.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1402, t_last = 221402133 3.41.584.093 I slot launch_slot_: id 0 | task 22443 | processing task, is_child = 0 3.44.742.701 I slot print_timing: id 0 | task 22443 | n_gen = 389, tg = 129.29 t/s, tg_3s = 129.62 t/s 3.45.229.828 I slot print_timing: id 0 | task 22443 | prompt eval time = 157.49 ms / 331 tokens ( 0.48 ms per token, 2101.68 tokens per second) 3.45.229.834 I slot print_timing: id 0 | task 22443 | eval time = 3488.22 ms / 450 tokens ( 7.77 ms per token, 128.72 tokens per second) 3.45.229.835 I slot print_timing: id 0 | task 22443 | total time = 3645.72 ms / 781 tokens 3.45.229.836 I slot print_timing: id 0 | task 22443 | graphs reused = 21885 3.45.229.837 I slot print_timing: id 0 | task 22443 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.229.866 I slot release: id 0 | task 22443 | stop processing: n_tokens = 812, truncated = 0 3.45.258.423 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 812, t_last = 225133754 3.45.258.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.371 MiB) 3.45.367.057 I slot launch_slot_: id 0 | task 22896 | processing task, is_child = 0 3.46.196.747 I slot print_timing: id 0 | task 22896 | prompt eval time = 157.35 ms / 345 tokens ( 0.46 ms per token, 2192.58 tokens per second) 3.46.196.752 I slot print_timing: id 0 | task 22896 | eval time = 672.32 ms / 83 tokens ( 8.20 ms per token, 121.97 tokens per second) 3.46.196.753 I slot print_timing: id 0 | task 22896 | total time = 829.67 ms / 428 tokens 3.46.196.754 I slot print_timing: id 0 | task 22896 | graphs reused = 21966 3.46.196.755 I slot print_timing: id 0 | task 22896 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.196.783 I slot release: id 0 | task 22896 | stop processing: n_tokens = 459, truncated = 0 3.46.224.527 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 459, t_last = 226100671 3.46.224.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 411.767 MiB) 3.46.329.879 I slot launch_slot_: id 0 | task 22982 | processing task, is_child = 0 3.47.312.876 I slot print_timing: id 0 | task 22982 | prompt eval time = 155.71 ms / 320 tokens ( 0.49 ms per token, 2055.16 tokens per second) 3.47.312.881 I slot print_timing: id 0 | task 22982 | eval time = 827.27 ms / 108 tokens ( 7.73 ms per token, 129.34 tokens per second) 3.47.312.882 I slot print_timing: id 0 | task 22982 | total time = 982.98 ms / 428 tokens 3.47.312.883 I slot print_timing: id 0 | task 22982 | graphs reused = 22072 3.47.312.884 I slot print_timing: id 0 | task 22982 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.312.912 I slot release: id 0 | task 22982 | stop processing: n_tokens = 459, truncated = 0 3.47.336.083 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 459, t_last = 227216801 3.47.336.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.304 MiB) 3.47.423.688 I slot launch_slot_: id 0 | task 23093 | processing task, is_child = 0 3.47.957.563 I slot print_timing: id 0 | task 23093 | prompt eval time = 146.50 ms / 297 tokens ( 0.49 ms per token, 2027.23 tokens per second) 3.47.957.570 I slot print_timing: id 0 | task 23093 | eval time = 387.35 ms / 47 tokens ( 8.42 ms per token, 118.76 tokens per second) 3.47.957.571 I slot print_timing: id 0 | task 23093 | total time = 533.85 ms / 344 tokens 3.47.957.572 I slot print_timing: id 0 | task 23093 | graphs reused = 22117 3.47.957.573 I slot print_timing: id 0 | task 23093 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.957.602 I slot release: id 0 | task 23093 | stop processing: n_tokens = 375, truncated = 0 3.47.976.531 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 227861490 3.47.976.573 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.277 MiB) 3.48.063.252 I slot launch_slot_: id 0 | task 23143 | processing task, is_child = 0 3.49.352.593 I slot print_timing: id 0 | task 23143 | prompt eval time = 156.70 ms / 343 tokens ( 0.46 ms per token, 2188.84 tokens per second) 3.49.352.599 I slot print_timing: id 0 | task 23143 | eval time = 1132.62 ms / 147 tokens ( 7.76 ms per token, 128.91 tokens per second) 3.49.352.600 I slot print_timing: id 0 | task 23143 | total time = 1289.32 ms / 490 tokens 3.49.352.601 I slot print_timing: id 0 | task 23143 | graphs reused = 22261 3.49.352.602 I slot print_timing: id 0 | task 23143 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.352.634 I slot release: id 0 | task 23143 | stop processing: n_tokens = 521, truncated = 0 3.49.380.940 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 229256522 3.49.380.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 3.49.458.101 I slot launch_slot_: id 0 | task 23293 | processing task, is_child = 0 3.50.651.032 I slot print_timing: id 0 | task 23293 | prompt eval time = 165.28 ms / 371 tokens ( 0.45 ms per token, 2244.73 tokens per second) 3.50.651.037 I slot print_timing: id 0 | task 23293 | eval time = 1027.63 ms / 133 tokens ( 7.79 ms per token, 128.45 tokens per second) 3.50.651.038 I slot print_timing: id 0 | task 23293 | total time = 1192.91 ms / 504 tokens 3.50.651.039 I slot print_timing: id 0 | task 23293 | graphs reused = 22391 3.50.651.040 I slot print_timing: id 0 | task 23293 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.651.071 I slot release: id 0 | task 23293 | stop processing: n_tokens = 535, truncated = 0 3.50.669.649 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 230554959 3.50.669.704 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 3.50.761.276 I slot launch_slot_: id 0 | task 23429 | processing task, is_child = 0 3.51.835.902 I slot print_timing: id 0 | task 23429 | prompt eval time = 147.71 ms / 292 tokens ( 0.51 ms per token, 1976.91 tokens per second) 3.51.835.908 I slot print_timing: id 0 | task 23429 | eval time = 926.90 ms / 121 tokens ( 7.72 ms per token, 129.46 tokens per second) 3.51.835.909 I slot print_timing: id 0 | task 23429 | total time = 1074.61 ms / 413 tokens 3.51.835.910 I slot print_timing: id 0 | task 23429 | graphs reused = 22510 3.51.835.911 I slot print_timing: id 0 | task 23429 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.835.937 I slot release: id 0 | task 23429 | stop processing: n_tokens = 444, truncated = 0 3.51.860.864 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 231739826 3.51.913.041 I slot launch_slot_: id 0 | task 23553 | processing task, is_child = 0 3.52.202.591 I slot print_timing: id 0 | task 23553 | prompt eval time = 146.26 ms / 301 tokens ( 0.49 ms per token, 2057.98 tokens per second) 3.52.202.596 I slot print_timing: id 0 | task 23553 | eval time = 143.27 ms / 19 tokens ( 7.96 ms per token, 125.64 tokens per second) 3.52.202.597 I slot print_timing: id 0 | task 23553 | total time = 289.53 ms / 320 tokens 3.52.202.598 I slot print_timing: id 0 | task 23553 | graphs reused = 22527 3.52.202.599 I slot print_timing: id 0 | task 23553 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.202.625 I slot release: id 0 | task 23553 | stop processing: n_tokens = 351, truncated = 0 3.52.218.817 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 351, t_last = 232106513 3.52.218.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.845 MiB) 3.52.298.973 I slot launch_slot_: id 0 | task 23575 | processing task, is_child = 0 3.53.062.613 I slot print_timing: id 0 | task 23575 | prompt eval time = 151.66 ms / 303 tokens ( 0.50 ms per token, 1997.90 tokens per second) 3.53.062.619 I slot print_timing: id 0 | task 23575 | eval time = 611.96 ms / 80 tokens ( 7.75 ms per token, 129.09 tokens per second) 3.53.062.620 I slot print_timing: id 0 | task 23575 | total time = 763.62 ms / 383 tokens 3.53.062.621 I slot print_timing: id 0 | task 23575 | graphs reused = 22605 3.53.062.622 I slot print_timing: id 0 | task 23575 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.062.650 I slot release: id 0 | task 23575 | stop processing: n_tokens = 414, truncated = 0 3.53.066.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 232966538 3.53.066.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.185 MiB) 3.53.157.100 I slot launch_slot_: id 0 | task 23658 | processing task, is_child = 0 3.53.663.472 I slot print_timing: id 0 | task 23658 | prompt eval time = 155.43 ms / 321 tokens ( 0.48 ms per token, 2065.24 tokens per second) 3.53.663.477 I slot print_timing: id 0 | task 23658 | eval time = 350.92 ms / 46 tokens ( 7.80 ms per token, 128.23 tokens per second) 3.53.663.478 I slot print_timing: id 0 | task 23658 | total time = 506.35 ms / 367 tokens 3.53.663.479 I slot print_timing: id 0 | task 23658 | graphs reused = 22649 3.53.663.480 I slot print_timing: id 0 | task 23658 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.663.509 I slot release: id 0 | task 23658 | stop processing: n_tokens = 398, truncated = 0 3.53.684.402 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 233567397 3.53.684.446 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.862 MiB) 3.53.769.835 I slot launch_slot_: id 0 | task 23707 | processing task, is_child = 0 3.54.077.565 I slot print_timing: id 0 | task 23707 | prompt eval time = 156.48 ms / 322 tokens ( 0.49 ms per token, 2057.73 tokens per second) 3.54.077.570 I slot print_timing: id 0 | task 23707 | eval time = 151.23 ms / 20 tokens ( 7.96 ms per token, 125.64 tokens per second) 3.54.077.571 I slot print_timing: id 0 | task 23707 | total time = 307.71 ms / 342 tokens 3.54.077.572 I slot print_timing: id 0 | task 23707 | graphs reused = 22667 3.54.077.572 I slot print_timing: id 0 | task 23707 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.077.601 I slot release: id 0 | task 23707 | stop processing: n_tokens = 373, truncated = 0 3.54.100.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 373, t_last = 233981489 3.54.100.996 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.421 MiB) 3.54.190.300 I slot launch_slot_: id 0 | task 23730 | processing task, is_child = 0 3.54.981.877 I slot print_timing: id 0 | task 23730 | prompt eval time = 156.05 ms / 323 tokens ( 0.48 ms per token, 2069.88 tokens per second) 3.54.981.883 I slot print_timing: id 0 | task 23730 | eval time = 635.51 ms / 83 tokens ( 7.75 ms per token, 129.03 tokens per second) 3.54.981.884 I slot print_timing: id 0 | task 23730 | total time = 791.56 ms / 406 tokens 3.54.981.884 I slot print_timing: id 0 | task 23730 | graphs reused = 22748 3.54.981.885 I slot print_timing: id 0 | task 23730 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.981.914 I slot release: id 0 | task 23730 | stop processing: n_tokens = 437, truncated = 0 3.55.002.648 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 234885802 3.55.002.689 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.237 MiB) 3.55.069.018 I slot launch_slot_: id 0 | task 23816 | processing task, is_child = 0 3.57.315.846 I slot print_timing: id 0 | task 23816 | prompt eval time = 154.06 ms / 321 tokens ( 0.48 ms per token, 2083.56 tokens per second) 3.57.315.852 I slot print_timing: id 0 | task 23816 | eval time = 2092.75 ms / 272 tokens ( 7.72 ms per token, 129.49 tokens per second) 3.57.315.853 I slot print_timing: id 0 | task 23816 | total time = 2246.81 ms / 593 tokens 3.57.315.853 I slot print_timing: id 0 | task 23816 | graphs reused = 23017 3.57.315.855 I slot print_timing: id 0 | task 23816 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.315.883 I slot release: id 0 | task 23816 | stop processing: n_tokens = 624, truncated = 0 3.57.337.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 624, t_last = 237219771 3.57.337.534 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.856 MiB) 3.57.401.902 I slot launch_slot_: id 0 | task 24091 | processing task, is_child = 0 3.58.199.406 I slot print_timing: id 0 | task 24091 | prompt eval time = 154.73 ms / 322 tokens ( 0.48 ms per token, 2081.08 tokens per second) 3.58.199.411 I slot print_timing: id 0 | task 24091 | eval time = 642.76 ms / 84 tokens ( 7.74 ms per token, 129.13 tokens per second) 3.58.199.412 I slot print_timing: id 0 | task 24091 | total time = 797.48 ms / 406 tokens 3.58.199.413 I slot print_timing: id 0 | task 24091 | graphs reused = 23099 3.58.199.414 I slot print_timing: id 0 | task 24091 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.199.444 I slot release: id 0 | task 24091 | stop processing: n_tokens = 437, truncated = 0 3.58.227.759 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 238103332 3.58.227.800 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.150 MiB) 3.58.291.889 I slot launch_slot_: id 0 | task 24178 | processing task, is_child = 0 3.58.798.512 I slot print_timing: id 0 | task 24178 | prompt eval time = 156.14 ms / 337 tokens ( 0.46 ms per token, 2158.37 tokens per second) 3.58.798.518 I slot print_timing: id 0 | task 24178 | eval time = 350.47 ms / 46 tokens ( 7.79 ms per token, 128.40 tokens per second) 3.58.798.519 I slot print_timing: id 0 | task 24178 | total time = 506.60 ms / 383 tokens 3.58.798.520 I slot print_timing: id 0 | task 24178 | graphs reused = 23143 3.58.798.521 I slot print_timing: id 0 | task 24178 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.798.548 I slot release: id 0 | task 24178 | stop processing: n_tokens = 414, truncated = 0 3.58.822.907 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 238702436 3.58.822.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 3.58.910.303 I slot launch_slot_: id 0 | task 24227 | processing task, is_child = 0 3.59.563.372 I slot print_timing: id 0 | task 24227 | prompt eval time = 156.66 ms / 325 tokens ( 0.48 ms per token, 2074.49 tokens per second) 3.59.563.378 I slot print_timing: id 0 | task 24227 | eval time = 496.38 ms / 65 tokens ( 7.76 ms per token, 128.93 tokens per second) 3.59.563.379 I slot print_timing: id 0 | task 24227 | total time = 653.05 ms / 390 tokens 3.59.563.380 I slot print_timing: id 0 | task 24227 | graphs reused = 23206 3.59.563.380 I slot print_timing: id 0 | task 24227 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.563.409 I slot release: id 0 | task 24227 | stop processing: n_tokens = 421, truncated = 0 3.59.567.149 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 239467297 3.59.567.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.451 MiB) 3.59.671.617 I slot launch_slot_: id 0 | task 24295 | processing task, is_child = 0 4.00.723.117 I slot print_timing: id 0 | task 24295 | prompt eval time = 160.94 ms / 331 tokens ( 0.49 ms per token, 2056.62 tokens per second) 4.00.723.122 I slot print_timing: id 0 | task 24295 | eval time = 890.54 ms / 116 tokens ( 7.74 ms per token, 129.14 tokens per second) 4.00.723.123 I slot print_timing: id 0 | task 24295 | total time = 1051.48 ms / 447 tokens 4.00.723.124 I slot print_timing: id 0 | task 24295 | graphs reused = 23320 4.00.723.125 I slot print_timing: id 0 | task 24295 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.723.154 I slot release: id 0 | task 24295 | stop processing: n_tokens = 478, truncated = 0 4.00.751.566 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 240627042 4.00.751.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 4.00.839.738 I slot launch_slot_: id 0 | task 24414 | processing task, is_child = 0 4.01.541.748 I slot print_timing: id 0 | task 24414 | prompt eval time = 154.72 ms / 336 tokens ( 0.46 ms per token, 2171.72 tokens per second) 4.01.541.754 I slot print_timing: id 0 | task 24414 | eval time = 547.27 ms / 70 tokens ( 7.93 ms per token, 126.08 tokens per second) 4.01.541.755 I slot print_timing: id 0 | task 24414 | total time = 701.99 ms / 406 tokens 4.01.541.756 I slot print_timing: id 0 | task 24414 | graphs reused = 23388 4.01.541.757 I slot print_timing: id 0 | task 24414 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.541.789 I slot release: id 0 | task 24414 | stop processing: n_tokens = 437, truncated = 0 4.01.570.931 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 241445677 4.01.570.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.512 MiB) 4.01.661.986 I slot launch_slot_: id 0 | task 24487 | processing task, is_child = 0 4.01.974.048 I slot print_timing: id 0 | task 24487 | prompt eval time = 159.97 ms / 349 tokens ( 0.46 ms per token, 2181.59 tokens per second) 4.01.974.053 I slot print_timing: id 0 | task 24487 | eval time = 152.07 ms / 20 tokens ( 8.00 ms per token, 124.94 tokens per second) 4.01.974.054 I slot print_timing: id 0 | task 24487 | total time = 312.04 ms / 369 tokens 4.01.974.055 I slot print_timing: id 0 | task 24487 | graphs reused = 23406 4.01.974.056 I slot print_timing: id 0 | task 24487 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.974.084 I slot release: id 0 | task 24487 | stop processing: n_tokens = 400, truncated = 0 4.02.001.644 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 241877972 4.02.001.691 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.481 MiB) 4.02.088.090 I slot launch_slot_: id 0 | task 24510 | processing task, is_child = 0 4.05.244.621 I slot print_timing: id 0 | task 24510 | n_gen = 385, tg = 127.97 t/s, tg_3s = 128.30 t/s 4.08.246.662 I slot print_timing: id 0 | task 24510 | n_gen = 772, tg = 128.44 t/s, tg_3s = 128.91 t/s 4.09.529.402 I slot print_timing: id 0 | task 24510 | prompt eval time = 155.83 ms / 336 tokens ( 0.46 ms per token, 2156.20 tokens per second) 4.09.529.408 I slot print_timing: id 0 | task 24510 | eval time = 7285.46 ms / 937 tokens ( 7.78 ms per token, 128.48 tokens per second) 4.09.529.409 I slot print_timing: id 0 | task 24510 | total time = 7441.29 ms / 1273 tokens 4.09.529.410 I slot print_timing: id 0 | task 24510 | graphs reused = 24337 4.09.529.411 I slot print_timing: id 0 | task 24510 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.529.440 I slot release: id 0 | task 24510 | stop processing: n_tokens = 1304, truncated = 0 4.09.533.401 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1304, t_last = 249433328 4.09.533.475 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.576 MiB) 4.09.632.541 I slot launch_slot_: id 0 | task 25450 | processing task, is_child = 0 4.12.796.708 I slot print_timing: id 0 | task 25450 | n_gen = 389, tg = 129.07 t/s, tg_3s = 129.41 t/s 4.15.796.877 I slot print_timing: id 0 | task 25450 | n_gen = 776, tg = 129.03 t/s, tg_3s = 128.99 t/s 4.17.727.601 I slot print_timing: id 0 | task 25450 | prompt eval time = 158.09 ms / 349 tokens ( 0.45 ms per token, 2207.62 tokens per second) 4.17.727.607 I slot print_timing: id 0 | task 25450 | eval time = 7936.95 ms / 1024 tokens ( 7.76 ms per token, 128.89 tokens per second) 4.17.727.608 I slot print_timing: id 0 | task 25450 | total time = 8095.04 ms / 1373 tokens 4.17.727.609 I slot print_timing: id 0 | task 25450 | graphs reused = 25355 4.17.727.610 I slot print_timing: id 0 | task 25450 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.727.639 I slot release: id 0 | task 25450 | stop processing: n_tokens = 1404, truncated = 0 4.17.742.565 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1404, t_last = 257631527 4.17.742.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.892 MiB) 4.17.831.797 I slot launch_slot_: id 0 | task 26477 | processing task, is_child = 0 4.18.565.525 I slot print_timing: id 0 | task 26477 | prompt eval time = 156.44 ms / 349 tokens ( 0.45 ms per token, 2230.89 tokens per second) 4.18.565.530 I slot print_timing: id 0 | task 26477 | eval time = 577.27 ms / 75 tokens ( 7.80 ms per token, 128.19 tokens per second) 4.18.565.531 I slot print_timing: id 0 | task 26477 | total time = 733.71 ms / 424 tokens 4.18.565.532 I slot print_timing: id 0 | task 26477 | graphs reused = 25428 4.18.565.533 I slot print_timing: id 0 | task 26477 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.565.561 I slot release: id 0 | task 26477 | stop processing: n_tokens = 455, truncated = 0 4.18.584.169 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 455, t_last = 258469450 4.18.584.214 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.670 MiB) 4.18.673.961 I slot launch_slot_: id 0 | task 26555 | processing task, is_child = 0 4.19.590.829 I slot print_timing: id 0 | task 26555 | prompt eval time = 166.11 ms / 385 tokens ( 0.43 ms per token, 2317.78 tokens per second) 4.19.590.834 I slot print_timing: id 0 | task 26555 | eval time = 750.74 ms / 97 tokens ( 7.82 ms per token, 127.87 tokens per second) 4.19.590.835 I slot print_timing: id 0 | task 26555 | total time = 916.85 ms / 482 tokens 4.19.590.836 I slot print_timing: id 0 | task 26555 | graphs reused = 25522 4.19.590.837 I slot print_timing: id 0 | task 26555 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.590.866 I slot release: id 0 | task 26555 | stop processing: n_tokens = 513, truncated = 0 4.19.612.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 259494754 4.19.612.090 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.457 MiB) 4.19.702.151 I slot launch_slot_: id 0 | task 26655 | processing task, is_child = 0 4.20.301.973 I slot print_timing: id 0 | task 26655 | prompt eval time = 159.51 ms / 328 tokens ( 0.49 ms per token, 2056.35 tokens per second) 4.20.301.979 I slot print_timing: id 0 | task 26655 | eval time = 440.30 ms / 57 tokens ( 7.86 ms per token, 127.19 tokens per second) 4.20.301.980 I slot print_timing: id 0 | task 26655 | total time = 599.80 ms / 385 tokens 4.20.301.981 I slot print_timing: id 0 | task 26655 | graphs reused = 25577 4.20.301.982 I slot print_timing: id 0 | task 26655 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.302.010 I slot release: id 0 | task 26655 | stop processing: n_tokens = 416, truncated = 0