C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\dl\campaign\b6f76e74f862\Ornith-1.5-9B-Q6_K.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.097.034 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.097.206 I srv llama_server: initializing ... 0.00.097.210 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.097.333 I srv init_listene: The UI is disabled 0.00.097.336 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.097.436 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) 0.00.110.460 I srv load_model: loading model 'C:\quantdiff\dl\campaign\b6f76e74f862\Ornith-1.5-9B-Q6_K.gguf' 0.00.924.160 W model has unused tensor blk.32.attn_norm.weight (size = 16384 bytes) -- ignoring 0.00.924.174 W model has unused tensor blk.32.post_attention_norm.weight (size = 16384 bytes) -- ignoring 0.00.924.200 W model has unused tensor blk.32.attn_q.weight (size = 27525120 bytes) -- ignoring 0.00.924.209 W model has unused tensor blk.32.attn_k.weight (size = 3440640 bytes) -- ignoring 0.00.924.218 W model has unused tensor blk.32.attn_v.weight (size = 3440640 bytes) -- ignoring 0.00.924.251 W model has unused tensor blk.32.attn_output.weight (size = 13762560 bytes) -- ignoring 0.00.924.262 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.924.270 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.924.279 W model has unused tensor blk.32.ffn_gate.weight (size = 41287680 bytes) -- ignoring 0.00.924.288 W model has unused tensor blk.32.ffn_down.weight (size = 41287680 bytes) -- ignoring 0.00.924.297 W model has unused tensor blk.32.ffn_up.weight (size = 41287680 bytes) -- ignoring 0.00.924.307 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 27525120 bytes) -- ignoring 0.00.924.317 W model has unused tensor blk.32.nextn.enorm.weight (size = 16384 bytes) -- ignoring 0.00.924.326 W model has unused tensor blk.32.nextn.hnorm.weight (size = 16384 bytes) -- ignoring 0.00.924.354 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 16384 bytes) -- ignoring 0.03.256.288 I cmn init: llama threadpool init, n_threads = 8 0.03.338.602 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.03.343.931 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.03.343.949 I srv llama_server: model loaded 0.03.343.952 I srv llama_server: listening on http://127.0.0.1:8091 0.44.254.009 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.44.254.056 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.44.254.060 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.44.254.082 I slot launch_slot_: id 1 | task 2 | processing task, is_child = 0 0.44.254.084 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.44.254.101 I slot launch_slot_: id 2 | task 3 | processing task, is_child = 0 0.44.254.102 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.44.254.117 I slot launch_slot_: id 3 | task 1 | processing task, is_child = 0 0.44.679.505 I slot print_timing: id 0 | task 0 | prompt eval time = 404.96 ms / 115 tokens ( 3.52 ms per token, 283.98 tokens per second) 0.44.679.511 I slot print_timing: id 0 | task 0 | eval time = 20.41 ms / 2 tokens ( 20.41 ms per token, 48.99 tokens per second) 0.44.679.512 I slot print_timing: id 0 | task 0 | total time = 425.37 ms / 117 tokens 0.44.679.516 I slot print_timing: id 0 | task 0 | graphs reused = 1 0.44.679.518 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.679.553 I slot release: id 0 | task 0 | stop processing: n_tokens = 116, truncated = 0 0.44.679.853 I slot print_timing: id 1 | task 2 | prompt eval time = 405.54 ms / 122 tokens ( 3.32 ms per token, 300.83 tokens per second) 0.44.679.856 I slot print_timing: id 1 | task 2 | eval time = 20.17 ms / 2 tokens ( 20.17 ms per token, 49.58 tokens per second) 0.44.679.857 I slot print_timing: id 1 | task 2 | total time = 425.71 ms / 124 tokens 0.44.679.857 I slot print_timing: id 1 | task 2 | graphs reused = 1 0.44.679.858 I slot print_timing: id 1 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.679.872 I slot release: id 1 | task 2 | stop processing: n_tokens = 123, truncated = 0 0.44.680.162 I slot print_timing: id 2 | task 3 | prompt eval time = 406.10 ms / 130 tokens ( 3.12 ms per token, 320.12 tokens per second) 0.44.680.165 I slot print_timing: id 2 | task 3 | eval time = 19.92 ms / 2 tokens ( 19.92 ms per token, 50.21 tokens per second) 0.44.680.166 I slot print_timing: id 2 | task 3 | total time = 426.01 ms / 132 tokens 0.44.680.166 I slot print_timing: id 2 | task 3 | graphs reused = 1 0.44.680.167 I slot print_timing: id 2 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.680.181 I slot release: id 2 | task 3 | stop processing: n_tokens = 131, truncated = 0 0.44.680.469 I slot print_timing: id 3 | task 1 | prompt eval time = 406.64 ms / 115 tokens ( 3.54 ms per token, 282.81 tokens per second) 0.44.680.472 I slot print_timing: id 3 | task 1 | eval time = 19.67 ms / 2 tokens ( 19.67 ms per token, 50.83 tokens per second) 0.44.680.473 I slot print_timing: id 3 | task 1 | total time = 426.31 ms / 117 tokens 0.44.680.473 I slot print_timing: id 3 | task 1 | graphs reused = 1 0.44.680.474 I slot print_timing: id 3 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.680.482 I slot release: id 3 | task 1 | stop processing: n_tokens = 116, truncated = 0 0.44.690.654 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.250 0.44.707.678 I slot launch_slot_: id 0 | task 7 | processing task, is_child = 0 0.44.757.077 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.228 0.44.757.255 I slot launch_slot_: id 1 | task 8 | processing task, is_child = 0 0.44.757.295 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.221 0.44.757.400 I slot launch_slot_: id 2 | task 9 | processing task, is_child = 0 0.44.757.422 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.241 0.44.757.524 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 0.45.040.728 I slot print_timing: id 0 | task 7 | prompt eval time = 262.69 ms / 152 tokens ( 1.73 ms per token, 578.63 tokens per second) 0.45.040.734 I slot print_timing: id 0 | task 7 | eval time = 20.50 ms / 2 tokens ( 20.50 ms per token, 48.79 tokens per second) 0.45.040.735 I slot print_timing: id 0 | task 7 | total time = 283.19 ms / 154 tokens 0.45.040.736 I slot print_timing: id 0 | task 7 | graphs reused = 1 0.45.040.737 I slot print_timing: id 0 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.040.768 I slot release: id 0 | task 7 | stop processing: n_tokens = 153, truncated = 0 0.45.041.085 I slot print_timing: id 1 | task 8 | prompt eval time = 262.40 ms / 160 tokens ( 1.64 ms per token, 609.76 tokens per second) 0.45.041.088 I slot print_timing: id 1 | task 8 | eval time = 20.25 ms / 2 tokens ( 20.25 ms per token, 49.38 tokens per second) 0.45.041.089 I slot print_timing: id 1 | task 8 | total time = 282.65 ms / 162 tokens 0.45.041.089 I slot print_timing: id 1 | task 8 | graphs reused = 1 0.45.041.090 I slot print_timing: id 1 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.041.111 I slot release: id 1 | task 8 | stop processing: n_tokens = 161, truncated = 0 0.45.041.421 I slot print_timing: id 2 | task 9 | prompt eval time = 262.09 ms / 108 tokens ( 2.43 ms per token, 412.07 tokens per second) 0.45.041.424 I slot print_timing: id 2 | task 9 | eval time = 20.03 ms / 2 tokens ( 20.03 ms per token, 49.93 tokens per second) 0.45.041.425 I slot print_timing: id 2 | task 9 | total time = 282.12 ms / 110 tokens 0.45.041.425 I slot print_timing: id 2 | task 9 | graphs reused = 1 0.45.041.426 I slot print_timing: id 2 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.041.438 I slot release: id 2 | task 9 | stop processing: n_tokens = 109, truncated = 0 0.45.041.730 I slot print_timing: id 3 | task 10 | prompt eval time = 261.79 ms / 200 tokens ( 1.31 ms per token, 763.96 tokens per second) 0.45.041.733 I slot print_timing: id 3 | task 10 | eval time = 19.79 ms / 2 tokens ( 19.79 ms per token, 50.54 tokens per second) 0.45.041.733 I slot print_timing: id 3 | task 10 | total time = 281.58 ms / 202 tokens 0.45.041.734 I slot print_timing: id 3 | task 10 | graphs reused = 1 0.45.041.734 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.041.753 I slot release: id 3 | task 10 | stop processing: n_tokens = 201, truncated = 0 0.45.049.771 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.190 0.45.067.411 I slot launch_slot_: id 0 | task 14 | processing task, is_child = 0 0.45.117.107 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.174 0.45.117.284 I slot launch_slot_: id 1 | task 15 | processing task, is_child = 0 0.45.117.329 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.257 0.45.117.442 I slot launch_slot_: id 2 | task 16 | processing task, is_child = 0 0.45.117.468 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.139 0.45.117.572 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 0.45.386.985 I slot print_timing: id 0 | task 14 | prompt eval time = 248.53 ms / 118 tokens ( 2.11 ms per token, 474.79 tokens per second) 0.45.386.991 I slot print_timing: id 0 | task 14 | eval time = 20.86 ms / 2 tokens ( 20.86 ms per token, 47.93 tokens per second) 0.45.386.992 I slot print_timing: id 0 | task 14 | total time = 269.39 ms / 120 tokens 0.45.386.993 I slot print_timing: id 0 | task 14 | graphs reused = 1 0.45.386.994 I slot print_timing: id 0 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.387.023 I slot release: id 0 | task 14 | stop processing: n_tokens = 119, truncated = 0 0.45.387.369 I slot print_timing: id 1 | task 15 | prompt eval time = 248.36 ms / 125 tokens ( 1.99 ms per token, 503.31 tokens per second) 0.45.387.373 I slot print_timing: id 1 | task 15 | eval time = 20.54 ms / 2 tokens ( 20.54 ms per token, 48.69 tokens per second) 0.45.387.374 I slot print_timing: id 1 | task 15 | total time = 268.89 ms / 127 tokens 0.45.387.375 I slot print_timing: id 1 | task 15 | graphs reused = 1 0.45.387.375 I slot print_timing: id 1 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.387.392 I slot release: id 1 | task 15 | stop processing: n_tokens = 126, truncated = 0 0.45.387.739 I slot print_timing: id 2 | task 16 | prompt eval time = 248.18 ms / 150 tokens ( 1.65 ms per token, 604.40 tokens per second) 0.45.387.742 I slot print_timing: id 2 | task 16 | eval time = 20.22 ms / 2 tokens ( 20.22 ms per token, 49.46 tokens per second) 0.45.387.743 I slot print_timing: id 2 | task 16 | total time = 268.40 ms / 152 tokens 0.45.387.744 I slot print_timing: id 2 | task 16 | graphs reused = 1 0.45.387.744 I slot print_timing: id 2 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.387.762 I slot release: id 2 | task 16 | stop processing: n_tokens = 151, truncated = 0 0.45.388.082 I slot print_timing: id 3 | task 17 | prompt eval time = 248.01 ms / 117 tokens ( 2.12 ms per token, 471.75 tokens per second) 0.45.388.085 I slot print_timing: id 3 | task 17 | eval time = 19.89 ms / 2 tokens ( 19.89 ms per token, 50.28 tokens per second) 0.45.388.086 I slot print_timing: id 3 | task 17 | total time = 267.90 ms / 119 tokens 0.45.388.087 I slot print_timing: id 3 | task 17 | graphs reused = 1 0.45.388.087 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.388.096 I slot release: id 3 | task 17 | stop processing: n_tokens = 118, truncated = 0 0.45.396.000 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.235 0.45.417.615 I slot launch_slot_: id 0 | task 21 | processing task, is_child = 0 0.45.480.602 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.222 0.45.480.767 I slot launch_slot_: id 1 | task 22 | processing task, is_child = 0 0.45.480.809 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.185 0.45.480.919 I slot launch_slot_: id 2 | task 23 | processing task, is_child = 0 0.45.480.941 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.235 (> 0.100 thold), f_keep = 0.237 0.45.481.044 I slot launch_slot_: id 3 | task 24 | processing task, is_child = 0 0.45.767.470 I slot print_timing: id 0 | task 21 | prompt eval time = 265.60 ms / 181 tokens ( 1.47 ms per token, 681.48 tokens per second) 0.45.767.475 I slot print_timing: id 0 | task 21 | eval time = 20.81 ms / 2 tokens ( 20.81 ms per token, 48.06 tokens per second) 0.45.767.476 I slot print_timing: id 0 | task 21 | total time = 286.41 ms / 183 tokens 0.45.767.477 I slot print_timing: id 0 | task 21 | graphs reused = 1 0.45.767.478 I slot print_timing: id 0 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.767.505 I slot release: id 0 | task 21 | stop processing: n_tokens = 182, truncated = 0 0.45.767.851 I slot print_timing: id 1 | task 22 | prompt eval time = 265.55 ms / 143 tokens ( 1.86 ms per token, 538.51 tokens per second) 0.45.767.854 I slot print_timing: id 1 | task 22 | eval time = 20.39 ms / 2 tokens ( 20.39 ms per token, 49.04 tokens per second) 0.45.767.855 I slot print_timing: id 1 | task 22 | total time = 285.94 ms / 145 tokens 0.45.767.855 I slot print_timing: id 1 | task 22 | graphs reused = 1 0.45.767.856 I slot print_timing: id 1 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.767.871 I slot release: id 1 | task 22 | stop processing: n_tokens = 144, truncated = 0 0.45.768.268 I slot print_timing: id 2 | task 23 | prompt eval time = 265.51 ms / 136 tokens ( 1.95 ms per token, 512.23 tokens per second) 0.45.768.271 I slot print_timing: id 2 | task 23 | eval time = 19.97 ms / 2 tokens ( 19.97 ms per token, 50.07 tokens per second) 0.45.768.272 I slot print_timing: id 2 | task 23 | total time = 285.48 ms / 138 tokens 0.45.768.272 I slot print_timing: id 2 | task 23 | graphs reused = 1 0.45.768.273 I slot print_timing: id 2 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.768.285 I slot release: id 2 | task 23 | stop processing: n_tokens = 137, truncated = 0 0.45.768.591 I slot print_timing: id 3 | task 24 | prompt eval time = 265.30 ms / 119 tokens ( 2.23 ms per token, 448.55 tokens per second) 0.45.768.594 I slot print_timing: id 3 | task 24 | eval time = 19.69 ms / 2 tokens ( 19.69 ms per token, 50.79 tokens per second) 0.45.768.595 I slot print_timing: id 3 | task 24 | total time = 284.99 ms / 121 tokens 0.45.768.595 I slot print_timing: id 3 | task 24 | graphs reused = 1 0.45.768.596 I slot print_timing: id 3 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.768.607 I slot release: id 3 | task 24 | stop processing: n_tokens = 120, truncated = 0 0.45.776.125 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.154 0.45.801.665 I slot launch_slot_: id 0 | task 28 | processing task, is_child = 0 0.45.856.090 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.194 0.45.864.592 I slot launch_slot_: id 1 | task 29 | processing task, is_child = 0 0.45.864.641 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.204 0.45.864.754 I slot launch_slot_: id 2 | task 30 | processing task, is_child = 0 0.45.864.777 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.233 0.45.864.883 I slot launch_slot_: id 3 | task 31 | processing task, is_child = 0 0.46.149.562 I slot print_timing: id 0 | task 28 | prompt eval time = 263.85 ms / 131 tokens ( 2.01 ms per token, 496.49 tokens per second) 0.46.149.567 I slot print_timing: id 0 | task 28 | eval time = 20.81 ms / 2 tokens ( 20.81 ms per token, 48.05 tokens per second) 0.46.149.568 I slot print_timing: id 0 | task 28 | total time = 284.66 ms / 133 tokens 0.46.149.569 I slot print_timing: id 0 | task 28 | graphs reused = 1 0.46.149.569 I slot print_timing: id 0 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.149.594 I slot release: id 0 | task 28 | stop processing: n_tokens = 132, truncated = 0 0.46.149.897 I slot print_timing: id 1 | task 29 | prompt eval time = 263.69 ms / 122 tokens ( 2.16 ms per token, 462.66 tokens per second) 0.46.149.900 I slot print_timing: id 1 | task 29 | eval time = 20.43 ms / 2 tokens ( 20.43 ms per token, 48.95 tokens per second) 0.46.149.901 I slot print_timing: id 1 | task 29 | total time = 284.12 ms / 124 tokens 0.46.149.902 I slot print_timing: id 1 | task 29 | graphs reused = 1 0.46.149.902 I slot print_timing: id 1 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.149.916 I slot release: id 1 | task 29 | stop processing: n_tokens = 123, truncated = 0 0.46.150.198 I slot print_timing: id 2 | task 30 | prompt eval time = 263.51 ms / 178 tokens ( 1.48 ms per token, 675.50 tokens per second) 0.46.150.201 I slot print_timing: id 2 | task 30 | eval time = 20.03 ms / 2 tokens ( 20.03 ms per token, 49.92 tokens per second) 0.46.150.201 I slot print_timing: id 2 | task 30 | total time = 283.54 ms / 180 tokens 0.46.150.202 I slot print_timing: id 2 | task 30 | graphs reused = 1 0.46.150.202 I slot print_timing: id 2 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.150.217 I slot release: id 2 | task 30 | stop processing: n_tokens = 179, truncated = 0 0.46.150.508 I slot print_timing: id 3 | task 31 | prompt eval time = 263.33 ms / 144 tokens ( 1.83 ms per token, 546.83 tokens per second) 0.46.150.511 I slot print_timing: id 3 | task 31 | eval time = 19.66 ms / 2 tokens ( 19.66 ms per token, 50.87 tokens per second) 0.46.150.512 I slot print_timing: id 3 | task 31 | total time = 282.99 ms / 146 tokens 0.46.150.512 I slot print_timing: id 3 | task 31 | graphs reused = 1 0.46.150.513 I slot print_timing: id 3 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.150.524 I slot release: id 3 | task 31 | stop processing: n_tokens = 145, truncated = 0 0.46.158.262 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.212 0.46.180.540 I slot launch_slot_: id 0 | task 35 | processing task, is_child = 0 0.46.230.123 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.236 0.46.230.292 I slot launch_slot_: id 1 | task 36 | processing task, is_child = 0 0.46.230.339 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.162 0.46.230.450 I slot launch_slot_: id 2 | task 37 | processing task, is_child = 0 0.46.230.474 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.193 0.46.230.575 I slot launch_slot_: id 3 | task 38 | processing task, is_child = 0 0.46.494.448 I slot print_timing: id 0 | task 35 | prompt eval time = 244.03 ms / 113 tokens ( 2.16 ms per token, 463.06 tokens per second) 0.46.494.454 I slot print_timing: id 0 | task 35 | eval time = 19.83 ms / 2 tokens ( 19.83 ms per token, 50.43 tokens per second) 0.46.494.455 I slot print_timing: id 0 | task 35 | total time = 263.86 ms / 115 tokens 0.46.494.456 I slot print_timing: id 0 | task 35 | graphs reused = 1 0.46.494.457 I slot print_timing: id 0 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.494.481 I slot release: id 0 | task 35 | stop processing: n_tokens = 114, truncated = 0 0.46.494.780 I slot print_timing: id 1 | task 36 | prompt eval time = 243.76 ms / 120 tokens ( 2.03 ms per token, 492.30 tokens per second) 0.46.494.783 I slot print_timing: id 1 | task 36 | eval time = 19.57 ms / 2 tokens ( 19.57 ms per token, 51.10 tokens per second) 0.46.494.783 I slot print_timing: id 1 | task 36 | total time = 263.33 ms / 122 tokens 0.46.494.784 I slot print_timing: id 1 | task 36 | graphs reused = 1 0.46.494.785 I slot print_timing: id 1 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.494.796 I slot release: id 1 | task 36 | stop processing: n_tokens = 121, truncated = 0 0.46.495.172 I slot print_timing: id 2 | task 37 | prompt eval time = 243.48 ms / 144 tokens ( 1.69 ms per token, 591.41 tokens per second) 0.46.495.176 I slot print_timing: id 2 | task 37 | eval time = 19.35 ms / 2 tokens ( 19.35 ms per token, 51.67 tokens per second) 0.46.495.176 I slot print_timing: id 2 | task 37 | total time = 262.84 ms / 146 tokens 0.46.495.177 I slot print_timing: id 2 | task 37 | graphs reused = 1 0.46.495.177 I slot print_timing: id 2 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.495.191 I slot release: id 2 | task 37 | stop processing: n_tokens = 145, truncated = 0 0.46.495.493 I slot print_timing: id 3 | task 38 | prompt eval time = 243.17 ms / 142 tokens ( 1.71 ms per token, 583.96 tokens per second) 0.46.495.497 I slot print_timing: id 3 | task 38 | eval time = 19.11 ms / 2 tokens ( 19.11 ms per token, 52.34 tokens per second) 0.46.495.498 I slot print_timing: id 3 | task 38 | total time = 262.27 ms / 144 tokens 0.46.495.499 I slot print_timing: id 3 | task 38 | graphs reused = 1 0.46.495.499 I slot print_timing: id 3 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.495.513 I slot release: id 3 | task 38 | stop processing: n_tokens = 143, truncated = 0 0.46.504.700 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.246 0.46.521.436 I slot launch_slot_: id 0 | task 42 | processing task, is_child = 0 0.46.570.151 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.240 0.46.570.316 I slot launch_slot_: id 1 | task 43 | processing task, is_child = 0 0.46.570.360 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.193 0.46.570.477 I slot launch_slot_: id 2 | task 44 | processing task, is_child = 0 0.46.570.501 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.196 0.46.570.604 I slot launch_slot_: id 3 | task 45 | processing task, is_child = 0 0.46.828.541 I slot print_timing: id 0 | task 42 | prompt eval time = 237.84 ms / 143 tokens ( 1.66 ms per token, 601.25 tokens per second) 0.46.828.547 I slot print_timing: id 0 | task 42 | eval time = 20.08 ms / 2 tokens ( 20.08 ms per token, 49.79 tokens per second) 0.46.828.548 I slot print_timing: id 0 | task 42 | total time = 257.92 ms / 145 tokens 0.46.828.549 I slot print_timing: id 0 | task 42 | graphs reused = 1 0.46.828.549 I slot print_timing: id 0 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.828.573 I slot release: id 0 | task 42 | stop processing: n_tokens = 144, truncated = 0 0.46.828.891 I slot print_timing: id 1 | task 43 | prompt eval time = 237.75 ms / 112 tokens ( 2.12 ms per token, 471.09 tokens per second) 0.46.828.894 I slot print_timing: id 1 | task 43 | eval time = 19.70 ms / 2 tokens ( 19.70 ms per token, 50.76 tokens per second) 0.46.828.895 I slot print_timing: id 1 | task 43 | total time = 257.45 ms / 114 tokens 0.46.828.895 I slot print_timing: id 1 | task 43 | graphs reused = 1 0.46.828.896 I slot print_timing: id 1 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.828.909 I slot release: id 1 | task 43 | stop processing: n_tokens = 113, truncated = 0 0.46.829.199 I slot print_timing: id 2 | task 44 | prompt eval time = 237.51 ms / 123 tokens ( 1.93 ms per token, 517.86 tokens per second) 0.46.829.201 I slot print_timing: id 2 | task 44 | eval time = 19.39 ms / 2 tokens ( 19.39 ms per token, 51.57 tokens per second) 0.46.829.202 I slot print_timing: id 2 | task 44 | total time = 256.91 ms / 125 tokens 0.46.829.203 I slot print_timing: id 2 | task 44 | graphs reused = 1 0.46.829.204 I slot print_timing: id 2 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.829.216 I slot release: id 2 | task 44 | stop processing: n_tokens = 124, truncated = 0 0.46.829.480 I slot print_timing: id 3 | task 45 | prompt eval time = 237.25 ms / 109 tokens ( 2.18 ms per token, 459.44 tokens per second) 0.46.829.483 I slot print_timing: id 3 | task 45 | eval time = 19.10 ms / 2 tokens ( 19.10 ms per token, 52.37 tokens per second) 0.46.829.484 I slot print_timing: id 3 | task 45 | total time = 256.34 ms / 111 tokens 0.46.829.485 I slot print_timing: id 3 | task 45 | graphs reused = 1 0.46.829.485 I slot print_timing: id 3 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.829.496 I slot release: id 3 | task 45 | stop processing: n_tokens = 110, truncated = 0 0.46.837.406 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.283 0.46.854.374 I slot launch_slot_: id 1 | task 49 | processing task, is_child = 0 0.46.902.862 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.194 0.46.902.989 I slot launch_slot_: id 0 | task 51 | processing task, is_child = 0 0.46.903.030 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.226 0.46.911.214 I slot launch_slot_: id 2 | task 50 | processing task, is_child = 0 0.46.911.240 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.255 0.46.911.340 I slot launch_slot_: id 3 | task 52 | processing task, is_child = 0 0.47.169.826 I slot print_timing: id 0 | task 51 | prompt eval time = 238.32 ms / 102 tokens ( 2.34 ms per token, 427.99 tokens per second) 0.47.169.832 I slot print_timing: id 0 | task 51 | eval time = 20.15 ms / 2 tokens ( 20.15 ms per token, 49.64 tokens per second) 0.47.169.833 I slot print_timing: id 0 | task 51 | total time = 258.47 ms / 104 tokens 0.47.169.834 I slot print_timing: id 0 | task 51 | graphs reused = 1 0.47.169.834 I slot print_timing: id 0 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.169.857 I slot release: id 0 | task 51 | stop processing: n_tokens = 103, truncated = 0 0.47.170.137 I slot print_timing: id 1 | task 49 | prompt eval time = 238.18 ms / 129 tokens ( 1.85 ms per token, 541.61 tokens per second) 0.47.170.140 I slot print_timing: id 1 | task 49 | eval time = 19.74 ms / 2 tokens ( 19.74 ms per token, 50.66 tokens per second) 0.47.170.140 I slot print_timing: id 1 | task 49 | total time = 257.92 ms / 131 tokens 0.47.170.141 I slot print_timing: id 1 | task 49 | graphs reused = 1 0.47.170.141 I slot print_timing: id 1 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.170.155 I slot release: id 1 | task 49 | stop processing: n_tokens = 130, truncated = 0 0.47.170.419 I slot print_timing: id 2 | task 50 | prompt eval time = 238.01 ms / 112 tokens ( 2.13 ms per token, 470.57 tokens per second) 0.47.170.422 I slot print_timing: id 2 | task 50 | eval time = 19.33 ms / 2 tokens ( 19.33 ms per token, 51.73 tokens per second) 0.47.170.423 I slot print_timing: id 2 | task 50 | total time = 257.34 ms / 114 tokens 0.47.170.423 I slot print_timing: id 2 | task 50 | graphs reused = 1 0.47.170.424 I slot print_timing: id 2 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.170.436 I slot release: id 2 | task 50 | stop processing: n_tokens = 113, truncated = 0 0.47.170.701 I slot print_timing: id 3 | task 52 | prompt eval time = 237.97 ms / 136 tokens ( 1.75 ms per token, 571.51 tokens per second) 0.47.170.703 I slot print_timing: id 3 | task 52 | eval time = 18.91 ms / 2 tokens ( 18.91 ms per token, 52.88 tokens per second) 0.47.170.704 I slot print_timing: id 3 | task 52 | total time = 256.88 ms / 138 tokens 0.47.170.704 I slot print_timing: id 3 | task 52 | graphs reused = 1 0.47.170.705 I slot print_timing: id 3 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.170.716 I slot release: id 3 | task 52 | stop processing: n_tokens = 137, truncated = 0 0.47.178.894 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.272 0.47.197.966 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.47.247.076 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.215 0.47.247.250 I slot launch_slot_: id 1 | task 57 | processing task, is_child = 0 0.47.247.294 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.248 0.47.247.404 I slot launch_slot_: id 2 | task 58 | processing task, is_child = 0 0.47.247.428 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.204 0.47.247.537 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 0.47.532.559 I slot print_timing: id 0 | task 56 | prompt eval time = 265.12 ms / 182 tokens ( 1.46 ms per token, 686.47 tokens per second) 0.47.532.565 I slot print_timing: id 0 | task 56 | eval time = 19.88 ms / 2 tokens ( 19.88 ms per token, 50.30 tokens per second) 0.47.532.566 I slot print_timing: id 0 | task 56 | total time = 285.00 ms / 184 tokens 0.47.532.567 I slot print_timing: id 0 | task 56 | graphs reused = 1 0.47.532.568 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.532.598 I slot release: id 0 | task 56 | stop processing: n_tokens = 183, truncated = 0 0.47.532.938 I slot print_timing: id 1 | task 57 | prompt eval time = 264.86 ms / 177 tokens ( 1.50 ms per token, 668.29 tokens per second) 0.47.532.942 I slot print_timing: id 1 | task 57 | eval time = 19.68 ms / 2 tokens ( 19.68 ms per token, 50.81 tokens per second) 0.47.532.943 I slot print_timing: id 1 | task 57 | total time = 284.54 ms / 179 tokens 0.47.532.943 I slot print_timing: id 1 | task 57 | graphs reused = 1 0.47.532.944 I slot print_timing: id 1 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.532.966 I slot release: id 1 | task 57 | stop processing: n_tokens = 178, truncated = 0 0.47.533.433 I slot print_timing: id 2 | task 58 | prompt eval time = 264.62 ms / 132 tokens ( 2.00 ms per token, 498.82 tokens per second) 0.47.533.437 I slot print_timing: id 2 | task 58 | eval time = 19.58 ms / 2 tokens ( 19.58 ms per token, 51.06 tokens per second) 0.47.533.438 I slot print_timing: id 2 | task 58 | total time = 284.21 ms / 134 tokens 0.47.533.439 I slot print_timing: id 2 | task 58 | graphs reused = 1 0.47.533.439 I slot print_timing: id 2 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.533.457 I slot release: id 2 | task 58 | stop processing: n_tokens = 133, truncated = 0 0.47.533.819 I slot print_timing: id 3 | task 59 | prompt eval time = 264.33 ms / 166 tokens ( 1.59 ms per token, 627.99 tokens per second) 0.47.533.822 I slot print_timing: id 3 | task 59 | eval time = 19.41 ms / 2 tokens ( 19.41 ms per token, 51.52 tokens per second) 0.47.533.822 I slot print_timing: id 3 | task 59 | total time = 283.74 ms / 168 tokens 0.47.533.823 I slot print_timing: id 3 | task 59 | graphs reused = 1 0.47.533.824 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.533.838 I slot release: id 3 | task 59 | stop processing: n_tokens = 167, truncated = 0 0.47.541.055 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.153 0.47.558.278 I slot launch_slot_: id 0 | task 63 | processing task, is_child = 0 0.47.607.303 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.157 0.47.607.452 I slot launch_slot_: id 1 | task 64 | processing task, is_child = 0 0.47.607.498 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.211 0.47.615.704 I slot launch_slot_: id 2 | task 65 | processing task, is_child = 0 0.47.615.733 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.168 0.47.615.844 I slot launch_slot_: id 3 | task 66 | processing task, is_child = 0 0.47.900.242 I slot print_timing: id 0 | task 63 | prompt eval time = 263.57 ms / 169 tokens ( 1.56 ms per token, 641.20 tokens per second) 0.47.900.248 I slot print_timing: id 0 | task 63 | eval time = 20.81 ms / 2 tokens ( 20.81 ms per token, 48.05 tokens per second) 0.47.900.249 I slot print_timing: id 0 | task 63 | total time = 284.38 ms / 171 tokens 0.47.900.250 I slot print_timing: id 0 | task 63 | graphs reused = 1 0.47.900.251 I slot print_timing: id 0 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.900.280 I slot release: id 0 | task 63 | stop processing: n_tokens = 170, truncated = 0 0.47.900.616 I slot print_timing: id 1 | task 64 | prompt eval time = 263.46 ms / 149 tokens ( 1.77 ms per token, 565.56 tokens per second) 0.47.900.619 I slot print_timing: id 1 | task 64 | eval time = 20.44 ms / 2 tokens ( 20.44 ms per token, 48.92 tokens per second) 0.47.900.620 I slot print_timing: id 1 | task 64 | total time = 283.90 ms / 151 tokens 0.47.900.620 I slot print_timing: id 1 | task 64 | graphs reused = 1 0.47.900.621 I slot print_timing: id 1 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.900.635 I slot release: id 1 | task 64 | stop processing: n_tokens = 150, truncated = 0 0.47.900.976 I slot print_timing: id 2 | task 65 | prompt eval time = 263.36 ms / 140 tokens ( 1.88 ms per token, 531.59 tokens per second) 0.47.900.979 I slot print_timing: id 2 | task 65 | eval time = 20.04 ms / 2 tokens ( 20.04 ms per token, 49.89 tokens per second) 0.47.900.979 I slot print_timing: id 2 | task 65 | total time = 283.41 ms / 142 tokens 0.47.900.980 I slot print_timing: id 2 | task 65 | graphs reused = 1 0.47.900.980 I slot print_timing: id 2 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.900.992 I slot release: id 2 | task 65 | stop processing: n_tokens = 141, truncated = 0 0.47.901.405 I slot print_timing: id 3 | task 66 | prompt eval time = 263.36 ms / 123 tokens ( 2.14 ms per token, 467.05 tokens per second) 0.47.901.411 I slot print_timing: id 3 | task 66 | eval time = 19.73 ms / 2 tokens ( 19.73 ms per token, 50.70 tokens per second) 0.47.901.412 I slot print_timing: id 3 | task 66 | total time = 283.08 ms / 125 tokens 0.47.901.413 I slot print_timing: id 3 | task 66 | graphs reused = 1 0.47.901.414 I slot print_timing: id 3 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.901.431 I slot release: id 3 | task 66 | stop processing: n_tokens = 124, truncated = 0 0.47.908.703 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.165 0.47.927.947 I slot launch_slot_: id 0 | task 70 | processing task, is_child = 0 0.47.977.198 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.234 0.47.977.372 I slot launch_slot_: id 3 | task 71 | processing task, is_child = 0 0.47.977.419 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.187 0.47.977.539 I slot launch_slot_: id 1 | task 72 | processing task, is_child = 0 0.47.977.563 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.206 0.47.977.670 I slot launch_slot_: id 2 | task 73 | processing task, is_child = 0 0.48.252.484 I slot print_timing: id 0 | task 70 | prompt eval time = 254.83 ms / 128 tokens ( 1.99 ms per token, 502.29 tokens per second) 0.48.252.490 I slot print_timing: id 0 | task 70 | eval time = 19.97 ms / 2 tokens ( 19.97 ms per token, 50.09 tokens per second) 0.48.252.491 I slot print_timing: id 0 | task 70 | total time = 274.80 ms / 130 tokens 0.48.252.492 I slot print_timing: id 0 | task 70 | graphs reused = 1 0.48.252.493 I slot print_timing: id 0 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.252.517 I slot release: id 0 | task 70 | stop processing: n_tokens = 129, truncated = 0 0.48.252.794 I slot print_timing: id 1 | task 72 | prompt eval time = 254.62 ms / 161 tokens ( 1.58 ms per token, 632.31 tokens per second) 0.48.252.797 I slot print_timing: id 1 | task 72 | eval time = 19.64 ms / 2 tokens ( 19.64 ms per token, 50.92 tokens per second) 0.48.252.797 I slot print_timing: id 1 | task 72 | total time = 274.26 ms / 163 tokens 0.48.252.798 I slot print_timing: id 1 | task 72 | graphs reused = 1 0.48.252.799 I slot print_timing: id 1 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.252.815 I slot release: id 1 | task 72 | stop processing: n_tokens = 162, truncated = 0 0.48.253.059 I slot print_timing: id 2 | task 73 | prompt eval time = 254.36 ms / 111 tokens ( 2.29 ms per token, 436.40 tokens per second) 0.48.253.062 I slot print_timing: id 2 | task 73 | eval time = 19.34 ms / 2 tokens ( 19.34 ms per token, 51.69 tokens per second) 0.48.253.063 I slot print_timing: id 2 | task 73 | total time = 273.70 ms / 113 tokens 0.48.253.064 I slot print_timing: id 2 | task 73 | graphs reused = 1 0.48.253.064 I slot print_timing: id 2 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.253.077 I slot release: id 2 | task 73 | stop processing: n_tokens = 112, truncated = 0 0.48.253.324 I slot print_timing: id 3 | task 71 | prompt eval time = 254.06 ms / 163 tokens ( 1.56 ms per token, 641.57 tokens per second) 0.48.253.327 I slot print_timing: id 3 | task 71 | eval time = 19.06 ms / 2 tokens ( 19.06 ms per token, 52.47 tokens per second) 0.48.253.328 I slot print_timing: id 3 | task 71 | total time = 273.12 ms / 165 tokens 0.48.253.328 I slot print_timing: id 3 | task 71 | graphs reused = 1 0.48.253.329 I slot print_timing: id 3 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.253.340 I slot release: id 3 | task 71 | stop processing: n_tokens = 164, truncated = 0 0.48.261.413 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.217 0.48.278.220 I slot launch_slot_: id 0 | task 77 | processing task, is_child = 0 0.48.327.175 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.179 0.48.327.343 I slot launch_slot_: id 1 | task 78 | processing task, is_child = 0 0.48.327.387 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.250 0.48.327.489 I slot launch_slot_: id 2 | task 79 | processing task, is_child = 0 0.48.327.514 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.177 0.48.327.614 I slot launch_slot_: id 3 | task 80 | processing task, is_child = 0 0.48.594.206 I slot print_timing: id 0 | task 77 | prompt eval time = 246.15 ms / 167 tokens ( 1.47 ms per token, 678.44 tokens per second) 0.48.594.211 I slot print_timing: id 0 | task 77 | eval time = 20.42 ms / 2 tokens ( 20.42 ms per token, 48.97 tokens per second) 0.48.594.212 I slot print_timing: id 0 | task 77 | total time = 266.57 ms / 169 tokens 0.48.594.213 I slot print_timing: id 0 | task 77 | graphs reused = 1 0.48.594.214 I slot print_timing: id 0 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.594.240 I slot release: id 0 | task 77 | stop processing: n_tokens = 168, truncated = 0 0.48.594.620 I slot print_timing: id 1 | task 78 | prompt eval time = 245.99 ms / 109 tokens ( 2.26 ms per token, 443.10 tokens per second) 0.48.594.625 I slot print_timing: id 1 | task 78 | eval time = 20.12 ms / 2 tokens ( 20.12 ms per token, 49.70 tokens per second) 0.48.594.626 I slot print_timing: id 1 | task 78 | total time = 266.11 ms / 111 tokens 0.48.594.626 I slot print_timing: id 1 | task 78 | graphs reused = 1 0.48.594.627 I slot print_timing: id 1 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.594.647 I slot release: id 1 | task 78 | stop processing: n_tokens = 110, truncated = 0 0.48.595.042 I slot print_timing: id 2 | task 79 | prompt eval time = 245.78 ms / 112 tokens ( 2.19 ms per token, 455.69 tokens per second) 0.48.595.048 I slot print_timing: id 2 | task 79 | eval time = 19.89 ms / 2 tokens ( 19.89 ms per token, 50.27 tokens per second) 0.48.595.049 I slot print_timing: id 2 | task 79 | total time = 265.68 ms / 114 tokens 0.48.595.049 I slot print_timing: id 2 | task 79 | graphs reused = 1 0.48.595.050 I slot print_timing: id 2 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.595.063 I slot release: id 2 | task 79 | stop processing: n_tokens = 113, truncated = 0 0.48.595.356 I slot print_timing: id 3 | task 80 | prompt eval time = 245.51 ms / 164 tokens ( 1.50 ms per token, 667.99 tokens per second) 0.48.595.358 I slot print_timing: id 3 | task 80 | eval time = 19.66 ms / 2 tokens ( 19.66 ms per token, 50.88 tokens per second) 0.48.595.359 I slot print_timing: id 3 | task 80 | total time = 265.17 ms / 166 tokens 0.48.595.360 I slot print_timing: id 3 | task 80 | graphs reused = 1 0.48.595.360 I slot print_timing: id 3 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.595.372 I slot release: id 3 | task 80 | stop processing: n_tokens = 165, truncated = 0 0.48.602.925 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.167 0.48.619.931 I slot launch_slot_: id 0 | task 84 | processing task, is_child = 0 0.48.668.485 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.255 0.48.676.766 I slot launch_slot_: id 1 | task 85 | processing task, is_child = 0 0.48.676.815 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.248 0.48.676.918 I slot launch_slot_: id 2 | task 86 | processing task, is_child = 0 0.48.676.943 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.170 0.48.677.036 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 0.48.950.687 I slot print_timing: id 0 | task 84 | prompt eval time = 252.79 ms / 131 tokens ( 1.93 ms per token, 518.22 tokens per second) 0.48.950.692 I slot print_timing: id 0 | task 84 | eval time = 20.84 ms / 2 tokens ( 20.84 ms per token, 47.98 tokens per second) 0.48.950.693 I slot print_timing: id 0 | task 84 | total time = 273.63 ms / 133 tokens 0.48.950.694 I slot print_timing: id 0 | task 84 | graphs reused = 1 0.48.950.695 I slot print_timing: id 0 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.950.720 I slot release: id 0 | task 84 | stop processing: n_tokens = 132, truncated = 0 0.48.951.018 I slot print_timing: id 1 | task 85 | prompt eval time = 252.65 ms / 122 tokens ( 2.07 ms per token, 482.88 tokens per second) 0.48.951.021 I slot print_timing: id 1 | task 85 | eval time = 20.46 ms / 2 tokens ( 20.46 ms per token, 48.87 tokens per second) 0.48.951.022 I slot print_timing: id 1 | task 85 | total time = 273.12 ms / 124 tokens 0.48.951.023 I slot print_timing: id 1 | task 85 | graphs reused = 1 0.48.951.023 I slot print_timing: id 1 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.951.037 I slot release: id 1 | task 85 | stop processing: n_tokens = 123, truncated = 0 0.48.951.322 I slot print_timing: id 2 | task 86 | prompt eval time = 252.61 ms / 147 tokens ( 1.72 ms per token, 581.93 tokens per second) 0.48.951.325 I slot print_timing: id 2 | task 86 | eval time = 20.09 ms / 2 tokens ( 20.09 ms per token, 49.79 tokens per second) 0.48.951.325 I slot print_timing: id 2 | task 86 | total time = 272.69 ms / 149 tokens 0.48.951.326 I slot print_timing: id 2 | task 86 | graphs reused = 1 0.48.951.326 I slot print_timing: id 2 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.951.337 I slot release: id 2 | task 86 | stop processing: n_tokens = 148, truncated = 0 0.48.951.622 I slot print_timing: id 3 | task 87 | prompt eval time = 252.46 ms / 120 tokens ( 2.10 ms per token, 475.33 tokens per second) 0.48.951.625 I slot print_timing: id 3 | task 87 | eval time = 19.72 ms / 2 tokens ( 19.72 ms per token, 50.72 tokens per second) 0.48.951.626 I slot print_timing: id 3 | task 87 | total time = 272.17 ms / 122 tokens 0.48.951.626 I slot print_timing: id 3 | task 87 | graphs reused = 1 0.48.951.627 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.951.636 I slot release: id 3 | task 87 | stop processing: n_tokens = 121, truncated = 0 0.48.959.962 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.212 0.48.981.527 I slot launch_slot_: id 0 | task 91 | processing task, is_child = 0 0.49.030.810 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.236 0.49.030.968 I slot launch_slot_: id 1 | task 92 | processing task, is_child = 0 0.49.031.014 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.189 0.49.039.081 I slot launch_slot_: id 2 | task 93 | processing task, is_child = 0 0.49.039.109 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.231 0.49.039.215 I slot launch_slot_: id 3 | task 94 | processing task, is_child = 0 0.49.316.403 I slot print_timing: id 0 | task 91 | prompt eval time = 255.98 ms / 124 tokens ( 2.06 ms per token, 484.41 tokens per second) 0.49.316.409 I slot print_timing: id 0 | task 91 | eval time = 21.19 ms / 2 tokens ( 21.19 ms per token, 47.19 tokens per second) 0.49.316.410 I slot print_timing: id 0 | task 91 | total time = 277.17 ms / 126 tokens 0.49.316.411 I slot print_timing: id 0 | task 91 | graphs reused = 1 0.49.316.412 I slot print_timing: id 0 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.316.437 I slot release: id 0 | task 91 | stop processing: n_tokens = 125, truncated = 0 0.49.316.763 I slot print_timing: id 1 | task 92 | prompt eval time = 255.88 ms / 144 tokens ( 1.78 ms per token, 562.76 tokens per second) 0.49.316.766 I slot print_timing: id 1 | task 92 | eval time = 20.79 ms / 2 tokens ( 20.79 ms per token, 48.10 tokens per second) 0.49.316.767 I slot print_timing: id 1 | task 92 | total time = 276.67 ms / 146 tokens 0.49.316.767 I slot print_timing: id 1 | task 92 | graphs reused = 1 0.49.316.768 I slot print_timing: id 1 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.316.782 I slot release: id 1 | task 92 | stop processing: n_tokens = 145, truncated = 0 0.49.317.099 I slot print_timing: id 2 | task 93 | prompt eval time = 255.79 ms / 141 tokens ( 1.81 ms per token, 551.24 tokens per second) 0.49.317.103 I slot print_timing: id 2 | task 93 | eval time = 20.41 ms / 2 tokens ( 20.41 ms per token, 49.01 tokens per second) 0.49.317.103 I slot print_timing: id 2 | task 93 | total time = 276.19 ms / 143 tokens 0.49.317.104 I slot print_timing: id 2 | task 93 | graphs reused = 1 0.49.317.104 I slot print_timing: id 2 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.317.116 I slot release: id 2 | task 93 | stop processing: n_tokens = 142, truncated = 0 0.49.317.412 I slot print_timing: id 3 | task 94 | prompt eval time = 255.72 ms / 131 tokens ( 1.95 ms per token, 512.28 tokens per second) 0.49.317.415 I slot print_timing: id 3 | task 94 | eval time = 20.01 ms / 2 tokens ( 20.01 ms per token, 49.97 tokens per second) 0.49.317.416 I slot print_timing: id 3 | task 94 | total time = 275.73 ms / 133 tokens 0.49.317.416 I slot print_timing: id 3 | task 94 | graphs reused = 1 0.49.317.417 I slot print_timing: id 3 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.317.425 I slot release: id 3 | task 94 | stop processing: n_tokens = 132, truncated = 0 0.49.325.148 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.200 0.49.343.441 I slot launch_slot_: id 1 | task 98 | processing task, is_child = 0 0.49.393.659 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.224 0.49.393.843 I slot launch_slot_: id 0 | task 99 | processing task, is_child = 0 0.49.393.888 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.220 0.49.394.005 I slot launch_slot_: id 3 | task 100 | processing task, is_child = 0 0.49.394.029 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.204 0.49.394.135 I slot launch_slot_: id 2 | task 101 | processing task, is_child = 0 0.49.655.897 I slot print_timing: id 0 | task 99 | prompt eval time = 241.68 ms / 121 tokens ( 2.00 ms per token, 500.66 tokens per second) 0.49.655.902 I slot print_timing: id 0 | task 99 | eval time = 20.06 ms / 2 tokens ( 20.06 ms per token, 49.84 tokens per second) 0.49.655.903 I slot print_timing: id 0 | task 99 | total time = 261.74 ms / 123 tokens 0.49.655.904 I slot print_timing: id 0 | task 99 | graphs reused = 1 0.49.655.905 I slot print_timing: id 0 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.655.929 I slot release: id 0 | task 99 | stop processing: n_tokens = 122, truncated = 0 0.49.656.285 I slot print_timing: id 1 | task 98 | prompt eval time = 241.44 ms / 118 tokens ( 2.05 ms per token, 488.73 tokens per second) 0.49.656.288 I slot print_timing: id 1 | task 98 | eval time = 19.84 ms / 2 tokens ( 19.84 ms per token, 50.41 tokens per second) 0.49.656.289 I slot print_timing: id 1 | task 98 | total time = 261.28 ms / 120 tokens 0.49.656.289 I slot print_timing: id 1 | task 98 | graphs reused = 1 0.49.656.290 I slot print_timing: id 1 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.656.303 I slot release: id 1 | task 98 | stop processing: n_tokens = 119, truncated = 0 0.49.656.673 I slot print_timing: id 2 | task 101 | prompt eval time = 241.25 ms / 172 tokens ( 1.40 ms per token, 712.97 tokens per second) 0.49.656.676 I slot print_timing: id 2 | task 101 | eval time = 19.59 ms / 2 tokens ( 19.59 ms per token, 51.04 tokens per second) 0.49.656.677 I slot print_timing: id 2 | task 101 | total time = 260.84 ms / 174 tokens 0.49.656.678 I slot print_timing: id 2 | task 101 | graphs reused = 1 0.49.656.678 I slot print_timing: id 2 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.656.692 I slot release: id 2 | task 101 | stop processing: n_tokens = 173, truncated = 0 0.49.657.040 I slot print_timing: id 3 | task 100 | prompt eval time = 241.01 ms / 107 tokens ( 2.25 ms per token, 443.97 tokens per second) 0.49.657.043 I slot print_timing: id 3 | task 100 | eval time = 19.36 ms / 2 tokens ( 19.36 ms per token, 51.65 tokens per second) 0.49.657.044 I slot print_timing: id 3 | task 100 | total time = 260.37 ms / 109 tokens 0.49.657.044 I slot print_timing: id 3 | task 100 | graphs reused = 1 0.49.657.045 I slot print_timing: id 3 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.657.055 I slot release: id 3 | task 100 | stop processing: n_tokens = 108, truncated = 0 0.49.665.888 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.230 0.49.682.744 I slot launch_slot_: id 0 | task 105 | processing task, is_child = 0 0.49.732.001 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.235 0.49.732.175 I slot launch_slot_: id 1 | task 106 | processing task, is_child = 0 0.49.732.220 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.269 0.49.732.333 I slot launch_slot_: id 3 | task 108 | processing task, is_child = 0 0.49.732.359 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.162 0.49.740.568 I slot launch_slot_: id 2 | task 107 | processing task, is_child = 0 0.50.036.090 I slot print_timing: id 0 | task 105 | prompt eval time = 274.44 ms / 177 tokens ( 1.55 ms per token, 644.95 tokens per second) 0.50.036.095 I slot print_timing: id 0 | task 105 | eval time = 21.06 ms / 2 tokens ( 21.06 ms per token, 47.49 tokens per second) 0.50.036.097 I slot print_timing: id 0 | task 105 | total time = 295.50 ms / 179 tokens 0.50.036.098 I slot print_timing: id 0 | task 105 | graphs reused = 1 0.50.036.099 I slot print_timing: id 0 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.036.131 I slot release: id 0 | task 105 | stop processing: n_tokens = 178, truncated = 0 0.50.036.475 I slot print_timing: id 1 | task 106 | prompt eval time = 274.34 ms / 240 tokens ( 1.14 ms per token, 874.84 tokens per second) 0.50.036.478 I slot print_timing: id 1 | task 106 | eval time = 20.71 ms / 2 tokens ( 20.71 ms per token, 48.29 tokens per second) 0.50.036.479 I slot print_timing: id 1 | task 106 | total time = 295.05 ms / 242 tokens 0.50.036.479 I slot print_timing: id 1 | task 106 | graphs reused = 1 0.50.036.480 I slot print_timing: id 1 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.036.500 I slot release: id 1 | task 106 | stop processing: n_tokens = 241, truncated = 0 0.50.036.833 I slot print_timing: id 2 | task 107 | prompt eval time = 274.25 ms / 136 tokens ( 2.02 ms per token, 495.91 tokens per second) 0.50.036.836 I slot print_timing: id 2 | task 107 | eval time = 20.35 ms / 2 tokens ( 20.35 ms per token, 49.14 tokens per second) 0.50.036.837 I slot print_timing: id 2 | task 107 | total time = 294.60 ms / 138 tokens 0.50.036.837 I slot print_timing: id 2 | task 107 | graphs reused = 1 0.50.036.837 I slot print_timing: id 2 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.036.850 I slot release: id 2 | task 107 | stop processing: n_tokens = 137, truncated = 0 0.50.037.165 I slot print_timing: id 3 | task 108 | prompt eval time = 274.09 ms / 116 tokens ( 2.36 ms per token, 423.22 tokens per second) 0.50.037.168 I slot print_timing: id 3 | task 108 | eval time = 19.98 ms / 2 tokens ( 19.98 ms per token, 50.06 tokens per second) 0.50.037.169 I slot print_timing: id 3 | task 108 | total time = 294.06 ms / 118 tokens 0.50.037.169 I slot print_timing: id 3 | task 108 | graphs reused = 1 0.50.037.170 I slot print_timing: id 3 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.037.180 I slot release: id 3 | task 108 | stop processing: n_tokens = 117, truncated = 0 0.50.044.403 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.256 0.50.066.170 I slot launch_slot_: id 3 | task 112 | processing task, is_child = 0 0.50.115.882 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.157 0.50.116.053 I slot launch_slot_: id 0 | task 113 | processing task, is_child = 0 0.50.116.102 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.212 0.50.124.382 I slot launch_slot_: id 2 | task 114 | processing task, is_child = 0 0.50.124.417 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.116 0.50.124.543 I slot launch_slot_: id 1 | task 115 | processing task, is_child = 0 0.50.439.920 I slot print_timing: id 0 | task 113 | prompt eval time = 294.67 ms / 160 tokens ( 1.84 ms per token, 542.98 tokens per second) 0.50.439.925 I slot print_timing: id 0 | task 113 | eval time = 20.69 ms / 2 tokens ( 20.69 ms per token, 48.33 tokens per second) 0.50.439.927 I slot print_timing: id 0 | task 113 | total time = 315.36 ms / 162 tokens 0.50.439.927 I slot print_timing: id 0 | task 113 | graphs reused = 1 0.50.439.928 I slot print_timing: id 0 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.439.952 I slot release: id 0 | task 113 | stop processing: n_tokens = 161, truncated = 0 0.50.440.276 I slot print_timing: id 1 | task 115 | prompt eval time = 294.62 ms / 226 tokens ( 1.30 ms per token, 767.09 tokens per second) 0.50.440.280 I slot print_timing: id 1 | task 115 | eval time = 20.27 ms / 2 tokens ( 20.27 ms per token, 49.34 tokens per second) 0.50.440.281 I slot print_timing: id 1 | task 115 | total time = 314.89 ms / 228 tokens 0.50.440.281 I slot print_timing: id 1 | task 115 | graphs reused = 1 0.50.440.282 I slot print_timing: id 1 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.440.300 I slot release: id 1 | task 115 | stop processing: n_tokens = 227, truncated = 0 0.50.440.609 I slot print_timing: id 2 | task 114 | prompt eval time = 294.47 ms / 142 tokens ( 2.07 ms per token, 482.23 tokens per second) 0.50.440.612 I slot print_timing: id 2 | task 114 | eval time = 19.90 ms / 2 tokens ( 19.90 ms per token, 50.26 tokens per second) 0.50.440.613 I slot print_timing: id 2 | task 114 | total time = 314.37 ms / 144 tokens 0.50.440.613 I slot print_timing: id 2 | task 114 | graphs reused = 1 0.50.440.614 I slot print_timing: id 2 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.440.625 I slot release: id 2 | task 114 | stop processing: n_tokens = 143, truncated = 0 0.50.440.903 I slot print_timing: id 3 | task 112 | prompt eval time = 294.33 ms / 155 tokens ( 1.90 ms per token, 526.62 tokens per second) 0.50.440.906 I slot print_timing: id 3 | task 112 | eval time = 19.50 ms / 2 tokens ( 19.50 ms per token, 51.28 tokens per second) 0.50.440.906 I slot print_timing: id 3 | task 112 | total time = 313.83 ms / 157 tokens 0.50.440.907 I slot print_timing: id 3 | task 112 | graphs reused = 1 0.50.440.908 I slot print_timing: id 3 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.440.918 I slot release: id 3 | task 112 | stop processing: n_tokens = 156, truncated = 0 0.50.449.769 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.203 0.50.473.308 I slot launch_slot_: id 2 | task 120 | processing task, is_child = 0 0.50.522.942 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.174 0.50.523.099 I slot launch_slot_: id 0 | task 119 | processing task, is_child = 0 0.50.523.152 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.286 (> 0.100 thold), f_keep = 0.192 0.50.523.270 I slot launch_slot_: id 3 | task 121 | processing task, is_child = 0 0.50.523.299 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.123 0.50.531.418 I slot launch_slot_: id 1 | task 122 | processing task, is_child = 0 0.50.804.823 I slot print_timing: id 0 | task 119 | prompt eval time = 253.15 ms / 141 tokens ( 1.80 ms per token, 556.98 tokens per second) 0.50.804.829 I slot print_timing: id 0 | task 119 | eval time = 20.24 ms / 2 tokens ( 20.24 ms per token, 49.41 tokens per second) 0.50.804.830 I slot print_timing: id 0 | task 119 | total time = 273.39 ms / 143 tokens 0.50.804.831 I slot print_timing: id 0 | task 119 | graphs reused = 1 0.50.804.832 I slot print_timing: id 0 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.804.858 I slot release: id 0 | task 119 | stop processing: n_tokens = 142, truncated = 0 0.50.805.134 I slot print_timing: id 1 | task 122 | prompt eval time = 253.02 ms / 192 tokens ( 1.32 ms per token, 758.84 tokens per second) 0.50.805.137 I slot print_timing: id 1 | task 122 | eval time = 19.83 ms / 2 tokens ( 19.83 ms per token, 50.43 tokens per second) 0.50.805.138 I slot print_timing: id 1 | task 122 | total time = 272.85 ms / 194 tokens 0.50.805.138 I slot print_timing: id 1 | task 122 | graphs reused = 1 0.50.805.139 I slot print_timing: id 1 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.805.157 I slot release: id 1 | task 122 | stop processing: n_tokens = 193, truncated = 0 0.50.805.425 I slot print_timing: id 2 | task 120 | prompt eval time = 252.95 ms / 114 tokens ( 2.22 ms per token, 450.68 tokens per second) 0.50.805.428 I slot print_timing: id 2 | task 120 | eval time = 19.44 ms / 2 tokens ( 19.44 ms per token, 51.45 tokens per second) 0.50.805.429 I slot print_timing: id 2 | task 120 | total time = 272.39 ms / 116 tokens 0.50.805.429 I slot print_timing: id 2 | task 120 | graphs reused = 1 0.50.805.430 I slot print_timing: id 2 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.805.441 I slot release: id 2 | task 120 | stop processing: n_tokens = 115, truncated = 0 0.50.805.709 I slot print_timing: id 3 | task 121 | prompt eval time = 252.76 ms / 105 tokens ( 2.41 ms per token, 415.41 tokens per second) 0.50.805.711 I slot print_timing: id 3 | task 121 | eval time = 19.03 ms / 2 tokens ( 19.03 ms per token, 52.54 tokens per second) 0.50.805.712 I slot print_timing: id 3 | task 121 | total time = 271.79 ms / 107 tokens 0.50.805.712 I slot print_timing: id 3 | task 121 | graphs reused = 1 0.50.805.713 I slot print_timing: id 3 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.805.721 I slot release: id 3 | task 121 | stop processing: n_tokens = 106, truncated = 0 0.50.813.717 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.197 0.50.833.440 I slot launch_slot_: id 0 | task 126 | processing task, is_child = 0 0.50.882.183 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.252 0.50.882.353 I slot launch_slot_: id 2 | task 127 | processing task, is_child = 0 0.50.882.402 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.274 0.50.882.521 I slot launch_slot_: id 3 | task 128 | processing task, is_child = 0 0.50.882.548 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.145 0.50.882.665 I slot launch_slot_: id 1 | task 129 | processing task, is_child = 0 0.51.148.749 I slot print_timing: id 0 | task 126 | prompt eval time = 245.98 ms / 172 tokens ( 1.43 ms per token, 699.24 tokens per second) 0.51.148.754 I slot print_timing: id 0 | task 126 | eval time = 20.09 ms / 2 tokens ( 20.09 ms per token, 49.78 tokens per second) 0.51.148.755 I slot print_timing: id 0 | task 126 | total time = 266.07 ms / 174 tokens 0.51.148.756 I slot print_timing: id 0 | task 126 | graphs reused = 1 0.51.148.757 I slot print_timing: id 0 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.148.785 I slot release: id 0 | task 126 | stop processing: n_tokens = 173, truncated = 0 0.51.149.107 I slot print_timing: id 1 | task 129 | prompt eval time = 245.88 ms / 135 tokens ( 1.82 ms per token, 549.05 tokens per second) 0.51.149.110 I slot print_timing: id 1 | task 129 | eval time = 19.68 ms / 2 tokens ( 19.68 ms per token, 50.83 tokens per second) 0.51.149.111 I slot print_timing: id 1 | task 129 | total time = 265.55 ms / 137 tokens 0.51.149.111 I slot print_timing: id 1 | task 129 | graphs reused = 1 0.51.149.112 I slot print_timing: id 1 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.149.125 I slot release: id 1 | task 129 | stop processing: n_tokens = 136, truncated = 0 0.51.149.420 I slot print_timing: id 2 | task 127 | prompt eval time = 245.59 ms / 122 tokens ( 2.01 ms per token, 496.75 tokens per second) 0.51.149.423 I slot print_timing: id 2 | task 127 | eval time = 19.39 ms / 2 tokens ( 19.39 ms per token, 51.57 tokens per second) 0.51.149.424 I slot print_timing: id 2 | task 127 | total time = 264.99 ms / 124 tokens 0.51.149.424 I slot print_timing: id 2 | task 127 | graphs reused = 1 0.51.149.425 I slot print_timing: id 2 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.149.435 I slot release: id 2 | task 127 | stop processing: n_tokens = 123, truncated = 0 0.51.149.698 I slot print_timing: id 3 | task 128 | prompt eval time = 245.34 ms / 108 tokens ( 2.27 ms per token, 440.21 tokens per second) 0.51.149.701 I slot print_timing: id 3 | task 128 | eval time = 19.12 ms / 2 tokens ( 19.12 ms per token, 52.31 tokens per second) 0.51.149.702 I slot print_timing: id 3 | task 128 | total time = 264.46 ms / 110 tokens 0.51.149.702 I slot print_timing: id 3 | task 128 | graphs reused = 1 0.51.149.703 I slot print_timing: id 3 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.149.713 I slot release: id 3 | task 128 | stop processing: n_tokens = 109, truncated = 0 0.51.157.167 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.162 0.51.174.142 I slot launch_slot_: id 0 | task 133 | processing task, is_child = 0 0.51.222.791 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.206 0.51.222.931 I slot launch_slot_: id 1 | task 134 | processing task, is_child = 0 0.51.222.977 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.236 0.51.231.059 I slot launch_slot_: id 2 | task 135 | processing task, is_child = 0 0.51.231.086 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.257 0.51.231.179 I slot launch_slot_: id 3 | task 136 | processing task, is_child = 0 0.51.507.728 I slot print_timing: id 0 | task 133 | prompt eval time = 256.72 ms / 159 tokens ( 1.61 ms per token, 619.35 tokens per second) 0.51.507.734 I slot print_timing: id 0 | task 133 | eval time = 19.81 ms / 2 tokens ( 19.81 ms per token, 50.47 tokens per second) 0.51.507.735 I slot print_timing: id 0 | task 133 | total time = 276.53 ms / 161 tokens 0.51.507.736 I slot print_timing: id 0 | task 133 | graphs reused = 1 0.51.507.737 I slot print_timing: id 0 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.507.764 I slot release: id 0 | task 133 | stop processing: n_tokens = 160, truncated = 0 0.51.508.053 I slot print_timing: id 1 | task 134 | prompt eval time = 256.52 ms / 134 tokens ( 1.91 ms per token, 522.37 tokens per second) 0.51.508.056 I slot print_timing: id 1 | task 134 | eval time = 19.47 ms / 2 tokens ( 19.47 ms per token, 51.36 tokens per second) 0.51.508.057 I slot print_timing: id 1 | task 134 | total time = 275.99 ms / 136 tokens 0.51.508.058 I slot print_timing: id 1 | task 134 | graphs reused = 1 0.51.508.059 I slot print_timing: id 1 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.508.071 I slot release: id 1 | task 134 | stop processing: n_tokens = 135, truncated = 0 0.51.508.373 I slot print_timing: id 2 | task 135 | prompt eval time = 256.35 ms / 120 tokens ( 2.14 ms per token, 468.11 tokens per second) 0.51.508.376 I slot print_timing: id 2 | task 135 | eval time = 19.16 ms / 2 tokens ( 19.16 ms per token, 52.21 tokens per second) 0.51.508.377 I slot print_timing: id 2 | task 135 | total time = 275.50 ms / 122 tokens 0.51.508.377 I slot print_timing: id 2 | task 135 | graphs reused = 1 0.51.508.378 I slot print_timing: id 2 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.508.389 I slot release: id 2 | task 135 | stop processing: n_tokens = 121, truncated = 0 0.51.508.655 I slot print_timing: id 3 | task 136 | prompt eval time = 256.15 ms / 135 tokens ( 1.90 ms per token, 527.04 tokens per second) 0.51.508.658 I slot print_timing: id 3 | task 136 | eval time = 18.88 ms / 2 tokens ( 18.88 ms per token, 52.95 tokens per second) 0.51.508.658 I slot print_timing: id 3 | task 136 | total time = 275.03 ms / 137 tokens 0.51.508.659 I slot print_timing: id 3 | task 136 | graphs reused = 1 0.51.508.659 I slot print_timing: id 3 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.508.669 I slot release: id 3 | task 136 | stop processing: n_tokens = 136, truncated = 0 0.51.516.367 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.175 0.51.533.922 I slot launch_slot_: id 0 | task 140 | processing task, is_child = 0 0.51.583.545 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.207 0.51.583.715 I slot launch_slot_: id 1 | task 141 | processing task, is_child = 0 0.51.583.762 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.231 0.51.583.873 I slot launch_slot_: id 2 | task 142 | processing task, is_child = 0 0.51.583.898 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.206 0.51.583.999 I slot launch_slot_: id 3 | task 143 | processing task, is_child = 0 0.51.868.565 I slot print_timing: id 0 | task 140 | prompt eval time = 264.70 ms / 130 tokens ( 2.04 ms per token, 491.11 tokens per second) 0.51.868.573 I slot print_timing: id 0 | task 140 | eval time = 19.84 ms / 2 tokens ( 19.84 ms per token, 50.40 tokens per second) 0.51.868.574 I slot print_timing: id 0 | task 140 | total time = 284.55 ms / 132 tokens 0.51.868.575 I slot print_timing: id 0 | task 140 | graphs reused = 1 0.51.868.575 I slot print_timing: id 0 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.868.603 I slot release: id 0 | task 140 | stop processing: n_tokens = 131, truncated = 0 0.51.868.888 I slot print_timing: id 1 | task 141 | prompt eval time = 264.40 ms / 172 tokens ( 1.54 ms per token, 650.54 tokens per second) 0.51.868.891 I slot print_timing: id 1 | task 141 | eval time = 19.60 ms / 2 tokens ( 19.60 ms per token, 51.01 tokens per second) 0.51.868.892 I slot print_timing: id 1 | task 141 | total time = 284.00 ms / 174 tokens 0.51.868.892 I slot print_timing: id 1 | task 141 | graphs reused = 1 0.51.868.893 I slot print_timing: id 1 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.868.909 I slot release: id 1 | task 141 | stop processing: n_tokens = 173, truncated = 0 0.51.869.194 I slot print_timing: id 2 | task 142 | prompt eval time = 264.14 ms / 180 tokens ( 1.47 ms per token, 681.45 tokens per second) 0.51.869.197 I slot print_timing: id 2 | task 142 | eval time = 19.36 ms / 2 tokens ( 19.36 ms per token, 51.66 tokens per second) 0.51.869.198 I slot print_timing: id 2 | task 142 | total time = 283.50 ms / 182 tokens 0.51.869.198 I slot print_timing: id 2 | task 142 | graphs reused = 1 0.51.869.199 I slot print_timing: id 2 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.869.214 I slot release: id 2 | task 142 | stop processing: n_tokens = 181, truncated = 0 0.51.869.496 I slot print_timing: id 3 | task 143 | prompt eval time = 263.88 ms / 175 tokens ( 1.51 ms per token, 663.17 tokens per second) 0.51.869.499 I slot print_timing: id 3 | task 143 | eval time = 19.09 ms / 2 tokens ( 19.09 ms per token, 52.38 tokens per second) 0.51.869.500 I slot print_timing: id 3 | task 143 | total time = 282.98 ms / 177 tokens 0.51.869.501 I slot print_timing: id 3 | task 143 | graphs reused = 1 0.51.869.501 I slot print_timing: id 3 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.869.514 I slot release: id 3 | task 143 | stop processing: n_tokens = 176, truncated = 0 0.51.878.065 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.214 0.51.903.029 I slot launch_slot_: id 0 | task 147 | processing task, is_child = 0 0.51.958.073 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.162 0.51.958.250 I slot launch_slot_: id 1 | task 148 | processing task, is_child = 0 0.51.958.303 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.155 0.51.958.411 I slot launch_slot_: id 2 | task 149 | processing task, is_child = 0 0.51.958.438 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.159 0.51.966.662 I slot launch_slot_: id 3 | task 150 | processing task, is_child = 0 0.52.193.611 I slot print_timing: id 0 | task 147 | prompt eval time = 206.22 ms / 123 tokens ( 1.68 ms per token, 596.44 tokens per second) 0.52.193.617 I slot print_timing: id 0 | task 147 | eval time = 20.71 ms / 2 tokens ( 20.71 ms per token, 48.29 tokens per second) 0.52.193.618 I slot print_timing: id 0 | task 147 | total time = 226.93 ms / 125 tokens 0.52.193.619 I slot print_timing: id 0 | task 147 | graphs reused = 1 0.52.193.620 I slot print_timing: id 0 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.193.645 I slot release: id 0 | task 147 | stop processing: n_tokens = 124, truncated = 0 0.52.193.942 I slot print_timing: id 1 | task 148 | prompt eval time = 206.21 ms / 123 tokens ( 1.68 ms per token, 596.49 tokens per second) 0.52.193.945 I slot print_timing: id 1 | task 148 | eval time = 20.33 ms / 2 tokens ( 20.33 ms per token, 49.18 tokens per second) 0.52.193.946 I slot print_timing: id 1 | task 148 | total time = 226.54 ms / 125 tokens 0.52.193.946 I slot print_timing: id 1 | task 148 | graphs reused = 1 0.52.193.947 I slot print_timing: id 1 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.193.959 I slot release: id 1 | task 148 | stop processing: n_tokens = 124, truncated = 0 0.52.194.246 I slot print_timing: id 2 | task 149 | prompt eval time = 206.04 ms / 115 tokens ( 1.79 ms per token, 558.15 tokens per second) 0.52.194.249 I slot print_timing: id 2 | task 149 | eval time = 19.93 ms / 2 tokens ( 19.93 ms per token, 50.17 tokens per second) 0.52.194.250 I slot print_timing: id 2 | task 149 | total time = 225.97 ms / 117 tokens 0.52.194.251 I slot print_timing: id 2 | task 149 | graphs reused = 1 0.52.194.251 I slot print_timing: id 2 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.194.262 I slot release: id 2 | task 149 | stop processing: n_tokens = 116, truncated = 0 0.52.194.540 I slot print_timing: id 3 | task 150 | prompt eval time = 205.88 ms / 115 tokens ( 1.79 ms per token, 558.58 tokens per second) 0.52.194.543 I slot print_timing: id 3 | task 150 | eval time = 19.54 ms / 2 tokens ( 19.54 ms per token, 51.17 tokens per second) 0.52.194.543 I slot print_timing: id 3 | task 150 | total time = 225.42 ms / 117 tokens 0.52.194.544 I slot print_timing: id 3 | task 150 | graphs reused = 1 0.52.194.545 I slot print_timing: id 3 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.194.554 I slot release: id 3 | task 150 | stop processing: n_tokens = 116, truncated = 0 0.52.201.968 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.276 0.52.220.256 I slot launch_slot_: id 3 | task 154 | processing task, is_child = 0 0.52.269.018 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.226 0.52.269.191 I slot launch_slot_: id 0 | task 157 | processing task, is_child = 0 0.52.269.236 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.226 0.52.269.353 I slot launch_slot_: id 1 | task 155 | processing task, is_child = 0 0.52.269.377 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.241 0.52.277.735 I slot launch_slot_: id 2 | task 156 | processing task, is_child = 0 0.52.544.349 I slot print_timing: id 0 | task 157 | prompt eval time = 246.08 ms / 141 tokens ( 1.75 ms per token, 572.98 tokens per second) 0.52.544.355 I slot print_timing: id 0 | task 157 | eval time = 20.51 ms / 2 tokens ( 20.51 ms per token, 48.75 tokens per second) 0.52.544.357 I slot print_timing: id 0 | task 157 | total time = 266.59 ms / 143 tokens 0.52.544.358 I slot print_timing: id 0 | task 157 | graphs reused = 1 0.52.544.359 I slot print_timing: id 0 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.544.386 I slot release: id 0 | task 157 | stop processing: n_tokens = 142, truncated = 0 0.52.544.742 I slot print_timing: id 1 | task 155 | prompt eval time = 245.85 ms / 130 tokens ( 1.89 ms per token, 528.78 tokens per second) 0.52.544.746 I slot print_timing: id 1 | task 155 | eval time = 20.31 ms / 2 tokens ( 20.31 ms per token, 49.24 tokens per second) 0.52.544.747 I slot print_timing: id 1 | task 155 | total time = 266.16 ms / 132 tokens 0.52.544.747 I slot print_timing: id 1 | task 155 | graphs reused = 1 0.52.544.748 I slot print_timing: id 1 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.544.764 I slot release: id 1 | task 155 | stop processing: n_tokens = 131, truncated = 0 0.52.545.106 I slot print_timing: id 2 | task 156 | prompt eval time = 245.59 ms / 128 tokens ( 1.92 ms per token, 521.20 tokens per second) 0.52.545.109 I slot print_timing: id 2 | task 156 | eval time = 20.10 ms / 2 tokens ( 20.10 ms per token, 49.75 tokens per second) 0.52.545.110 I slot print_timing: id 2 | task 156 | total time = 265.69 ms / 130 tokens 0.52.545.110 I slot print_timing: id 2 | task 156 | graphs reused = 1 0.52.545.111 I slot print_timing: id 2 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.545.122 I slot release: id 2 | task 156 | stop processing: n_tokens = 129, truncated = 0 0.52.545.450 I slot print_timing: id 3 | task 154 | prompt eval time = 245.44 ms / 127 tokens ( 1.93 ms per token, 517.44 tokens per second) 0.52.545.453 I slot print_timing: id 3 | task 154 | eval time = 19.86 ms / 2 tokens ( 19.86 ms per token, 50.36 tokens per second) 0.52.545.454 I slot print_timing: id 3 | task 154 | total time = 265.30 ms / 129 tokens 0.52.545.454 I slot print_timing: id 3 | task 154 | graphs reused = 1 0.52.545.455 I slot print_timing: id 3 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.545.463 I slot release: id 3 | task 154 | stop processing: n_tokens = 128, truncated = 0 0.52.552.989 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.197 0.52.570.267 I slot launch_slot_: id 0 | task 161 | processing task, is_child = 0 0.52.586.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 0.52.610.071 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 0.52.633.077 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.214 0.52.633.243 I slot launch_slot_: id 1 | task 162 | processing task, is_child = 0 0.52.633.291 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.227 0.52.633.406 I slot launch_slot_: id 3 | task 163 | processing task, is_child = 0 0.52.633.432 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.217 0.52.633.544 I slot launch_slot_: id 2 | task 164 | processing task, is_child = 0 0.52.905.384 I slot print_timing: id 0 | task 161 | prompt eval time = 251.43 ms / 123 tokens ( 2.04 ms per token, 489.19 tokens per second) 0.52.905.389 I slot print_timing: id 0 | task 161 | eval time = 20.39 ms / 2 tokens ( 20.39 ms per token, 49.05 tokens per second) 0.52.905.390 I slot print_timing: id 0 | task 161 | total time = 271.82 ms / 125 tokens 0.52.905.391 I slot print_timing: id 0 | task 161 | graphs reused = 1 0.52.905.392 I slot print_timing: id 0 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.905.416 I slot release: id 0 | task 161 | stop processing: n_tokens = 124, truncated = 0 0.52.905.774 I slot print_timing: id 1 | task 162 | prompt eval time = 251.35 ms / 129 tokens ( 1.95 ms per token, 513.23 tokens per second) 0.52.905.777 I slot print_timing: id 1 | task 162 | eval time = 20.03 ms / 2 tokens ( 20.03 ms per token, 49.92 tokens per second) 0.52.905.778 I slot print_timing: id 1 | task 162 | total time = 271.38 ms / 131 tokens 0.52.905.779 I slot print_timing: id 1 | task 162 | graphs reused = 1 0.52.905.779 I slot print_timing: id 1 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.905.794 I slot release: id 1 | task 162 | stop processing: n_tokens = 130, truncated = 0 0.52.906.228 I slot print_timing: id 2 | task 164 | prompt eval time = 251.32 ms / 161 tokens ( 1.56 ms per token, 640.61 tokens per second) 0.52.906.231 I slot print_timing: id 2 | task 164 | eval time = 19.66 ms / 2 tokens ( 19.66 ms per token, 50.87 tokens per second) 0.52.906.232 I slot print_timing: id 2 | task 164 | total time = 270.98 ms / 163 tokens 0.52.906.233 I slot print_timing: id 2 | task 164 | graphs reused = 1 0.52.906.233 I slot print_timing: id 2 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.906.248 I slot release: id 2 | task 164 | stop processing: n_tokens = 162, truncated = 0 0.52.906.531 I slot print_timing: id 3 | task 163 | prompt eval time = 251.11 ms / 105 tokens ( 2.39 ms per token, 418.15 tokens per second) 0.52.906.534 I slot print_timing: id 3 | task 163 | eval time = 19.35 ms / 2 tokens ( 19.35 ms per token, 51.68 tokens per second) 0.52.906.535 I slot print_timing: id 3 | task 163 | total time = 270.46 ms / 107 tokens 0.52.906.535 I slot print_timing: id 3 | task 163 | graphs reused = 1 0.52.906.536 I slot print_timing: id 3 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.906.545 I slot release: id 3 | task 163 | stop processing: n_tokens = 106, truncated = 0 0.52.915.218 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.226 0.52.915.272 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.129 MiB) 0.52.938.680 I slot launch_slot_: id 0 | task 168 | processing task, is_child = 0 0.52.938.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.286 MiB) 0.52.962.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.536 MiB) 0.52.985.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.787 MiB) 0.53.008.034 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.215 0.53.008.217 I slot launch_slot_: id 1 | task 169 | processing task, is_child = 0 0.53.008.261 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.274 0.53.008.366 I slot launch_slot_: id 3 | task 170 | processing task, is_child = 0 0.53.008.391 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.173 0.53.008.495 I slot launch_slot_: id 2 | task 171 | processing task, is_child = 0 0.53.288.767 I slot print_timing: id 0 | task 168 | prompt eval time = 259.36 ms / 141 tokens ( 1.84 ms per token, 543.64 tokens per second) 0.53.288.775 I slot print_timing: id 0 | task 168 | eval time = 20.89 ms / 2 tokens ( 20.89 ms per token, 47.87 tokens per second) 0.53.288.776 I slot print_timing: id 0 | task 168 | total time = 280.25 ms / 143 tokens 0.53.288.778 I slot print_timing: id 0 | task 168 | graphs reused = 1 0.53.288.779 I slot print_timing: id 0 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.288.818 I slot release: id 0 | task 168 | stop processing: n_tokens = 142, truncated = 0 0.53.289.260 I slot print_timing: id 1 | task 169 | prompt eval time = 259.31 ms / 164 tokens ( 1.58 ms per token, 632.46 tokens per second) 0.53.289.264 I slot print_timing: id 1 | task 169 | eval time = 20.60 ms / 2 tokens ( 20.60 ms per token, 48.55 tokens per second) 0.53.289.265 I slot print_timing: id 1 | task 169 | total time = 279.90 ms / 166 tokens 0.53.289.266 I slot print_timing: id 1 | task 169 | graphs reused = 1 0.53.289.267 I slot print_timing: id 1 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.289.285 I slot release: id 1 | task 169 | stop processing: n_tokens = 165, truncated = 0 0.53.289.687 I slot print_timing: id 2 | task 171 | prompt eval time = 259.27 ms / 154 tokens ( 1.68 ms per token, 593.97 tokens per second) 0.53.289.690 I slot print_timing: id 2 | task 171 | eval time = 20.26 ms / 2 tokens ( 20.26 ms per token, 49.37 tokens per second) 0.53.289.691 I slot print_timing: id 2 | task 171 | total time = 279.53 ms / 156 tokens 0.53.289.691 I slot print_timing: id 2 | task 171 | graphs reused = 1 0.53.289.692 I slot print_timing: id 2 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.289.706 I slot release: id 2 | task 171 | stop processing: n_tokens = 155, truncated = 0 0.53.290.071 I slot print_timing: id 3 | task 170 | prompt eval time = 259.20 ms / 110 tokens ( 2.36 ms per token, 424.39 tokens per second) 0.53.290.074 I slot print_timing: id 3 | task 170 | eval time = 19.92 ms / 2 tokens ( 19.92 ms per token, 50.19 tokens per second) 0.53.290.075 I slot print_timing: id 3 | task 170 | total time = 279.12 ms / 112 tokens 0.53.290.075 I slot print_timing: id 3 | task 170 | graphs reused = 1 0.53.290.076 I slot print_timing: id 3 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.290.087 I slot release: id 3 | task 170 | stop processing: n_tokens = 111, truncated = 0 0.53.298.565 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.261 0.53.315.711 I slot launch_slot_: id 3 | task 175 | processing task, is_child = 0 0.53.315.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.442 MiB) 0.53.339.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.224 MiB) 0.53.362.918 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.192 MiB) 0.53.386.248 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.197 0.53.386.419 I slot launch_slot_: id 0 | task 176 | processing task, is_child = 0 0.53.386.466 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.170 0.53.386.585 I slot launch_slot_: id 1 | task 177 | processing task, is_child = 0 0.53.386.610 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.181 0.53.386.715 I slot launch_slot_: id 2 | task 178 | processing task, is_child = 0 0.53.629.790 I slot print_timing: id 0 | task 176 | prompt eval time = 222.43 ms / 137 tokens ( 1.62 ms per token, 615.92 tokens per second) 0.53.629.797 I slot print_timing: id 0 | task 176 | eval time = 20.62 ms / 2 tokens ( 20.62 ms per token, 48.48 tokens per second) 0.53.629.798 I slot print_timing: id 0 | task 176 | total time = 243.06 ms / 139 tokens 0.53.629.798 I slot print_timing: id 0 | task 176 | graphs reused = 1 0.53.629.799 I slot print_timing: id 0 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.629.824 I slot release: id 0 | task 176 | stop processing: n_tokens = 138, truncated = 0 0.53.630.119 I slot print_timing: id 1 | task 177 | prompt eval time = 222.27 ms / 148 tokens ( 1.50 ms per token, 665.87 tokens per second) 0.53.630.122 I slot print_timing: id 1 | task 177 | eval time = 20.24 ms / 2 tokens ( 20.24 ms per token, 49.41 tokens per second) 0.53.630.122 I slot print_timing: id 1 | task 177 | total time = 242.51 ms / 150 tokens 0.53.630.123 I slot print_timing: id 1 | task 177 | graphs reused = 1 0.53.630.123 I slot print_timing: id 1 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.630.137 I slot release: id 1 | task 177 | stop processing: n_tokens = 149, truncated = 0 0.53.630.428 I slot print_timing: id 2 | task 178 | prompt eval time = 222.15 ms / 110 tokens ( 2.02 ms per token, 495.17 tokens per second) 0.53.630.431 I slot print_timing: id 2 | task 178 | eval time = 19.85 ms / 2 tokens ( 19.85 ms per token, 50.37 tokens per second) 0.53.630.431 I slot print_timing: id 2 | task 178 | total time = 242.00 ms / 112 tokens 0.53.630.432 I slot print_timing: id 2 | task 178 | graphs reused = 1 0.53.630.433 I slot print_timing: id 2 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.630.444 I slot release: id 2 | task 178 | stop processing: n_tokens = 111, truncated = 0 0.53.630.724 I slot print_timing: id 3 | task 175 | prompt eval time = 221.97 ms / 110 tokens ( 2.02 ms per token, 495.56 tokens per second) 0.53.630.727 I slot print_timing: id 3 | task 175 | eval time = 19.51 ms / 2 tokens ( 19.51 ms per token, 51.25 tokens per second) 0.53.630.728 I slot print_timing: id 3 | task 175 | total time = 241.48 ms / 112 tokens 0.53.630.728 I slot print_timing: id 3 | task 175 | graphs reused = 1 0.53.630.729 I slot print_timing: id 3 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.630.737 I slot release: id 3 | task 175 | stop processing: n_tokens = 111, truncated = 0 0.53.639.483 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.203 0.53.639.537 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.193 MiB) 0.53.658.099 I slot launch_slot_: id 0 | task 182 | processing task, is_child = 0 0.53.658.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.005 MiB) 0.53.681.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.786 MiB) 0.53.701.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.254 MiB) 0.53.723.530 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.261 0.53.723.679 I slot launch_slot_: id 3 | task 183 | processing task, is_child = 0 0.53.723.727 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.188 0.53.723.845 I slot launch_slot_: id 1 | task 184 | processing task, is_child = 0 0.53.723.869 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.252 0.53.723.973 I slot launch_slot_: id 2 | task 185 | processing task, is_child = 0 0.53.991.403 I slot print_timing: id 0 | task 182 | prompt eval time = 246.54 ms / 152 tokens ( 1.62 ms per token, 616.54 tokens per second) 0.53.991.408 I slot print_timing: id 0 | task 182 | eval time = 20.87 ms / 2 tokens ( 20.87 ms per token, 47.91 tokens per second) 0.53.991.409 I slot print_timing: id 0 | task 182 | total time = 267.41 ms / 154 tokens 0.53.991.411 I slot print_timing: id 0 | task 182 | graphs reused = 1 0.53.991.412 I slot print_timing: id 0 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.991.437 I slot release: id 0 | task 182 | stop processing: n_tokens = 153, truncated = 0 0.53.991.789 I slot print_timing: id 1 | task 184 | prompt eval time = 246.49 ms / 123 tokens ( 2.00 ms per token, 499.01 tokens per second) 0.53.991.792 I slot print_timing: id 1 | task 184 | eval time = 20.44 ms / 2 tokens ( 20.44 ms per token, 48.92 tokens per second) 0.53.991.793 I slot print_timing: id 1 | task 184 | total time = 266.93 ms / 125 tokens 0.53.991.793 I slot print_timing: id 1 | task 184 | graphs reused = 1 0.53.991.794 I slot print_timing: id 1 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.991.807 I slot release: id 1 | task 184 | stop processing: n_tokens = 124, truncated = 0 0.53.992.212 I slot print_timing: id 2 | task 185 | prompt eval time = 246.48 ms / 130 tokens ( 1.90 ms per token, 527.43 tokens per second) 0.53.992.215 I slot print_timing: id 2 | task 185 | eval time = 20.06 ms / 2 tokens ( 20.06 ms per token, 49.86 tokens per second) 0.53.992.216 I slot print_timing: id 2 | task 185 | total time = 266.53 ms / 132 tokens 0.53.992.216 I slot print_timing: id 2 | task 185 | graphs reused = 1 0.53.992.217 I slot print_timing: id 2 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.992.230 I slot release: id 2 | task 185 | stop processing: n_tokens = 131, truncated = 0 0.53.992.535 I slot print_timing: id 3 | task 183 | prompt eval time = 246.23 ms / 112 tokens ( 2.20 ms per token, 454.86 tokens per second) 0.53.992.538 I slot print_timing: id 3 | task 183 | eval time = 19.71 ms / 2 tokens ( 19.71 ms per token, 50.74 tokens per second) 0.53.992.539 I slot print_timing: id 3 | task 183 | total time = 265.94 ms / 114 tokens 0.53.992.539 I slot print_timing: id 3 | task 183 | graphs reused = 1 0.53.992.540 I slot print_timing: id 3 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.992.550 I slot release: id 3 | task 183 | stop processing: n_tokens = 113, truncated = 0 0.54.001.468 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.221 0.54.001.517 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.629 MiB) 0.54.024.925 I slot launch_slot_: id 2 | task 189 | processing task, is_child = 0 0.54.024.956 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 0.54.047.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.099 MiB) 0.54.070.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 0.54.093.498 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.183 0.54.093.670 I slot launch_slot_: id 0 | task 190 | processing task, is_child = 0 0.54.093.717 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.226 0.54.093.839 I slot launch_slot_: id 1 | task 191 | processing task, is_child = 0 0.54.093.864 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.257 0.54.093.969 I slot launch_slot_: id 3 | task 192 | processing task, is_child = 0 0.54.373.109 I slot print_timing: id 0 | task 190 | prompt eval time = 258.50 ms / 157 tokens ( 1.65 ms per token, 607.36 tokens per second) 0.54.373.115 I slot print_timing: id 0 | task 190 | eval time = 20.63 ms / 2 tokens ( 20.63 ms per token, 48.48 tokens per second) 0.54.373.116 I slot print_timing: id 0 | task 190 | total time = 279.12 ms / 159 tokens 0.54.373.117 I slot print_timing: id 0 | task 190 | graphs reused = 1 0.54.373.118 I slot print_timing: id 0 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.373.145 I slot release: id 0 | task 190 | stop processing: n_tokens = 158, truncated = 0 0.54.373.472 I slot print_timing: id 1 | task 191 | prompt eval time = 258.35 ms / 166 tokens ( 1.56 ms per token, 642.55 tokens per second) 0.54.373.475 I slot print_timing: id 1 | task 191 | eval time = 20.26 ms / 2 tokens ( 20.26 ms per token, 49.35 tokens per second) 0.54.373.476 I slot print_timing: id 1 | task 191 | total time = 278.61 ms / 168 tokens 0.54.373.477 I slot print_timing: id 1 | task 191 | graphs reused = 1 0.54.373.477 I slot print_timing: id 1 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.373.495 I slot release: id 1 | task 191 | stop processing: n_tokens = 167, truncated = 0 0.54.373.886 I slot print_timing: id 2 | task 189 | prompt eval time = 258.26 ms / 128 tokens ( 2.02 ms per token, 495.62 tokens per second) 0.54.373.889 I slot print_timing: id 2 | task 189 | eval time = 19.93 ms / 2 tokens ( 19.93 ms per token, 50.18 tokens per second) 0.54.373.892 I slot print_timing: id 2 | task 189 | total time = 278.19 ms / 130 tokens 0.54.373.893 I slot print_timing: id 2 | task 189 | graphs reused = 1 0.54.373.893 I slot print_timing: id 2 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.373.905 I slot release: id 2 | task 189 | stop processing: n_tokens = 129, truncated = 0 0.54.374.232 I slot print_timing: id 3 | task 192 | prompt eval time = 258.13 ms / 114 tokens ( 2.26 ms per token, 441.64 tokens per second) 0.54.374.235 I slot print_timing: id 3 | task 192 | eval time = 19.58 ms / 2 tokens ( 19.58 ms per token, 51.07 tokens per second) 0.54.374.236 I slot print_timing: id 3 | task 192 | total time = 277.71 ms / 116 tokens 0.54.374.236 I slot print_timing: id 3 | task 192 | graphs reused = 1 0.54.374.237 I slot print_timing: id 3 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.374.246 I slot release: id 3 | task 192 | stop processing: n_tokens = 115, truncated = 0 0.54.381.838 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.177 0.54.381.891 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.066 MiB) 0.54.405.432 I slot launch_slot_: id 0 | task 196 | processing task, is_child = 0 0.54.405.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.285 MiB) 0.54.428.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 0.54.451.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.973 MiB) 0.54.477.986 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.168 0.54.478.168 I slot launch_slot_: id 1 | task 197 | processing task, is_child = 0 0.54.478.211 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.217 0.54.478.316 I slot launch_slot_: id 2 | task 198 | processing task, is_child = 0 0.54.478.341 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.243 0.54.486.701 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 0.54.764.996 I slot print_timing: id 0 | task 196 | prompt eval time = 258.13 ms / 108 tokens ( 2.39 ms per token, 418.39 tokens per second) 0.54.765.002 I slot print_timing: id 0 | task 196 | eval time = 20.14 ms / 2 tokens ( 20.14 ms per token, 49.65 tokens per second) 0.54.765.003 I slot print_timing: id 0 | task 196 | total time = 278.27 ms / 110 tokens 0.54.765.004 I slot print_timing: id 0 | task 196 | graphs reused = 1 0.54.765.005 I slot print_timing: id 0 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.765.031 I slot release: id 0 | task 196 | stop processing: n_tokens = 109, truncated = 0 0.54.765.366 I slot print_timing: id 1 | task 197 | prompt eval time = 257.97 ms / 153 tokens ( 1.69 ms per token, 593.09 tokens per second) 0.54.765.369 I slot print_timing: id 1 | task 197 | eval time = 19.81 ms / 2 tokens ( 19.81 ms per token, 50.48 tokens per second) 0.54.765.370 I slot print_timing: id 1 | task 197 | total time = 277.78 ms / 155 tokens 0.54.765.371 I slot print_timing: id 1 | task 197 | graphs reused = 1 0.54.765.371 I slot print_timing: id 1 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.765.386 I slot release: id 1 | task 197 | stop processing: n_tokens = 154, truncated = 0 0.54.765.713 I slot print_timing: id 2 | task 198 | prompt eval time = 257.84 ms / 179 tokens ( 1.44 ms per token, 694.23 tokens per second) 0.54.765.716 I slot print_timing: id 2 | task 198 | eval time = 19.46 ms / 2 tokens ( 19.46 ms per token, 51.38 tokens per second) 0.54.765.717 I slot print_timing: id 2 | task 198 | total time = 277.30 ms / 181 tokens 0.54.765.717 I slot print_timing: id 2 | task 198 | graphs reused = 1 0.54.765.718 I slot print_timing: id 2 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.765.735 I slot release: id 2 | task 198 | stop processing: n_tokens = 180, truncated = 0 0.54.766.062 I slot print_timing: id 3 | task 199 | prompt eval time = 257.71 ms / 141 tokens ( 1.83 ms per token, 547.12 tokens per second) 0.54.766.065 I slot print_timing: id 3 | task 199 | eval time = 19.13 ms / 2 tokens ( 19.13 ms per token, 52.28 tokens per second) 0.54.766.065 I slot print_timing: id 3 | task 199 | total time = 276.84 ms / 143 tokens 0.54.766.066 I slot print_timing: id 3 | task 199 | graphs reused = 1 0.54.766.066 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.766.076 I slot release: id 3 | task 199 | stop processing: n_tokens = 142, truncated = 0 0.54.773.518 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.257 0.54.801.565 I slot launch_slot_: id 0 | task 203 | processing task, is_child = 0 0.54.822.033 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.005 MiB) 0.54.842.208 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 0.54.864.980 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.182 0.54.865.160 I slot launch_slot_: id 1 | task 204 | processing task, is_child = 0 0.54.865.207 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.156 0.54.865.317 I slot launch_slot_: id 2 | task 205 | processing task, is_child = 0 0.54.865.342 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.197 0.54.865.446 I slot launch_slot_: id 3 | task 206 | processing task, is_child = 0 0.55.126.358 I slot print_timing: id 0 | task 203 | prompt eval time = 240.83 ms / 116 tokens ( 2.08 ms per token, 481.67 tokens per second) 0.55.126.364 I slot print_timing: id 0 | task 203 | eval time = 20.07 ms / 2 tokens ( 20.07 ms per token, 49.83 tokens per second) 0.55.126.365 I slot print_timing: id 0 | task 203 | total time = 260.90 ms / 118 tokens 0.55.126.365 I slot print_timing: id 0 | task 203 | graphs reused = 1 0.55.126.366 I slot print_timing: id 0 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.126.389 I slot release: id 0 | task 203 | stop processing: n_tokens = 117, truncated = 0 0.55.126.671 I slot print_timing: id 1 | task 204 | prompt eval time = 240.79 ms / 135 tokens ( 1.78 ms per token, 560.66 tokens per second) 0.55.126.674 I slot print_timing: id 1 | task 204 | eval time = 19.66 ms / 2 tokens ( 19.66 ms per token, 50.85 tokens per second) 0.55.126.675 I slot print_timing: id 1 | task 204 | total time = 260.45 ms / 137 tokens 0.55.126.676 I slot print_timing: id 1 | task 204 | graphs reused = 1 0.55.126.676 I slot print_timing: id 1 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.126.691 I slot release: id 1 | task 204 | stop processing: n_tokens = 136, truncated = 0 0.55.126.979 I slot print_timing: id 2 | task 205 | prompt eval time = 240.64 ms / 158 tokens ( 1.52 ms per token, 656.57 tokens per second) 0.55.126.982 I slot print_timing: id 2 | task 205 | eval time = 19.27 ms / 2 tokens ( 19.27 ms per token, 51.90 tokens per second) 0.55.126.983 I slot print_timing: id 2 | task 205 | total time = 259.91 ms / 160 tokens 0.55.126.983 I slot print_timing: id 2 | task 205 | graphs reused = 1 0.55.126.984 I slot print_timing: id 2 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.126.997 I slot release: id 2 | task 205 | stop processing: n_tokens = 159, truncated = 0 0.55.127.270 I slot print_timing: id 3 | task 206 | prompt eval time = 240.49 ms / 134 tokens ( 1.79 ms per token, 557.19 tokens per second) 0.55.127.273 I slot print_timing: id 3 | task 206 | eval time = 18.85 ms / 2 tokens ( 18.85 ms per token, 53.04 tokens per second) 0.55.127.274 I slot print_timing: id 3 | task 206 | total time = 259.35 ms / 136 tokens 0.55.127.274 I slot print_timing: id 3 | task 206 | graphs reused = 1 0.55.127.275 I slot print_timing: id 3 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.127.284 I slot release: id 3 | task 206 | stop processing: n_tokens = 135, truncated = 0 0.55.135.098 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.239 0.55.135.147 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.722 MiB) 0.55.136.996 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.567 MiB) 0.55.160.063 I slot launch_slot_: id 0 | task 210 | processing task, is_child = 0 0.55.160.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.786 MiB) 0.55.182.702 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.224 MiB) 0.55.227.117 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.206 0.55.235.438 I slot launch_slot_: id 1 | task 211 | processing task, is_child = 0 0.55.235.499 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.176 0.55.243.809 I slot launch_slot_: id 2 | task 212 | processing task, is_child = 0 0.55.243.850 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.207 0.55.243.956 I slot launch_slot_: id 3 | task 213 | processing task, is_child = 0 0.55.527.676 I slot print_timing: id 0 | task 210 | prompt eval time = 264.05 ms / 149 tokens ( 1.77 ms per token, 564.28 tokens per second) 0.55.527.681 I slot print_timing: id 0 | task 210 | eval time = 19.65 ms / 2 tokens ( 19.65 ms per token, 50.89 tokens per second) 0.55.527.682 I slot print_timing: id 0 | task 210 | total time = 283.70 ms / 151 tokens 0.55.527.683 I slot print_timing: id 0 | task 210 | graphs reused = 1 0.55.527.684 I slot print_timing: id 0 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.527.710 I slot release: id 0 | task 210 | stop processing: n_tokens = 150, truncated = 0 0.55.527.970 I slot print_timing: id 1 | task 211 | prompt eval time = 263.76 ms / 122 tokens ( 2.16 ms per token, 462.54 tokens per second) 0.55.527.973 I slot print_timing: id 1 | task 211 | eval time = 19.38 ms / 2 tokens ( 19.38 ms per token, 51.61 tokens per second) 0.55.527.974 I slot print_timing: id 1 | task 211 | total time = 283.13 ms / 124 tokens 0.55.527.974 I slot print_timing: id 1 | task 211 | graphs reused = 1 0.55.527.975 I slot print_timing: id 1 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.527.988 I slot release: id 1 | task 211 | stop processing: n_tokens = 123, truncated = 0 0.55.528.246 I slot print_timing: id 2 | task 212 | prompt eval time = 263.54 ms / 117 tokens ( 2.25 ms per token, 443.96 tokens per second) 0.55.528.249 I slot print_timing: id 2 | task 212 | eval time = 19.09 ms / 2 tokens ( 19.09 ms per token, 52.37 tokens per second) 0.55.528.250 I slot print_timing: id 2 | task 212 | total time = 282.63 ms / 119 tokens 0.55.528.250 I slot print_timing: id 2 | task 212 | graphs reused = 1 0.55.528.251 I slot print_timing: id 2 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.528.260 I slot release: id 2 | task 212 | stop processing: n_tokens = 118, truncated = 0 0.55.528.523 I slot print_timing: id 3 | task 213 | prompt eval time = 263.31 ms / 157 tokens ( 1.68 ms per token, 596.25 tokens per second) 0.55.528.526 I slot print_timing: id 3 | task 213 | eval time = 18.82 ms / 2 tokens ( 18.82 ms per token, 53.12 tokens per second) 0.55.528.527 I slot print_timing: id 3 | task 213 | total time = 282.14 ms / 159 tokens 0.55.528.527 I slot print_timing: id 3 | task 213 | graphs reused = 1 0.55.528.528 I slot print_timing: id 3 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.528.540 I slot release: id 3 | task 213 | stop processing: n_tokens = 158, truncated = 0 0.55.538.059 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.187 0.55.555.287 I slot launch_slot_: id 0 | task 217 | processing task, is_child = 0 0.55.555.316 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.068 MiB) 0.55.590.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.661 MiB) 0.55.611.320 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.228 0.55.611.480 I slot launch_slot_: id 1 | task 218 | processing task, is_child = 0 0.55.611.529 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.237 0.55.611.640 I slot launch_slot_: id 2 | task 219 | processing task, is_child = 0 0.55.611.666 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.177 0.55.611.773 I slot launch_slot_: id 3 | task 220 | processing task, is_child = 0 0.55.906.549 I slot print_timing: id 0 | task 217 | prompt eval time = 274.55 ms / 154 tokens ( 1.78 ms per token, 560.92 tokens per second) 0.55.906.555 I slot print_timing: id 0 | task 217 | eval time = 20.21 ms / 2 tokens ( 20.21 ms per token, 49.49 tokens per second) 0.55.906.556 I slot print_timing: id 0 | task 217 | total time = 294.76 ms / 156 tokens 0.55.906.557 I slot print_timing: id 0 | task 217 | graphs reused = 1 0.55.906.558 I slot print_timing: id 0 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.906.583 I slot release: id 0 | task 217 | stop processing: n_tokens = 155, truncated = 0 0.55.906.897 I slot print_timing: id 1 | task 218 | prompt eval time = 274.55 ms / 160 tokens ( 1.72 ms per token, 582.78 tokens per second) 0.55.906.900 I slot print_timing: id 1 | task 218 | eval time = 19.74 ms / 2 tokens ( 19.74 ms per token, 50.65 tokens per second) 0.55.906.901 I slot print_timing: id 1 | task 218 | total time = 294.29 ms / 162 tokens 0.55.906.901 I slot print_timing: id 1 | task 218 | graphs reused = 1 0.55.906.902 I slot print_timing: id 1 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.906.916 I slot release: id 1 | task 218 | stop processing: n_tokens = 161, truncated = 0 0.55.907.337 I slot print_timing: id 2 | task 219 | prompt eval time = 274.46 ms / 155 tokens ( 1.77 ms per token, 564.74 tokens per second) 0.55.907.340 I slot print_timing: id 2 | task 219 | eval time = 19.43 ms / 2 tokens ( 19.43 ms per token, 51.48 tokens per second) 0.55.907.341 I slot print_timing: id 2 | task 219 | total time = 293.89 ms / 157 tokens 0.55.907.341 I slot print_timing: id 2 | task 219 | graphs reused = 1 0.55.907.342 I slot print_timing: id 2 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.907.354 I slot release: id 2 | task 219 | stop processing: n_tokens = 156, truncated = 0 0.55.907.638 I slot print_timing: id 3 | task 220 | prompt eval time = 274.23 ms / 149 tokens ( 1.84 ms per token, 543.34 tokens per second) 0.55.907.641 I slot print_timing: id 3 | task 220 | eval time = 19.14 ms / 2 tokens ( 19.14 ms per token, 52.25 tokens per second) 0.55.907.642 I slot print_timing: id 3 | task 220 | total time = 293.37 ms / 151 tokens 0.55.907.642 I slot print_timing: id 3 | task 220 | graphs reused = 1 0.55.907.643 I slot print_timing: id 3 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.907.652 I slot release: id 3 | task 220 | stop processing: n_tokens = 150, truncated = 0 0.55.915.483 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.181 0.55.915.532 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.724 MiB) 0.55.939.073 I slot launch_slot_: id 0 | task 224 | processing task, is_child = 0 0.55.939.105 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.818 MiB) 0.55.960.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.192 MiB) 0.55.984.105 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.911 MiB) 0.56.007.045 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.174 0.56.007.224 I slot launch_slot_: id 1 | task 225 | processing task, is_child = 0 0.56.007.269 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.179 0.56.015.830 I slot launch_slot_: id 2 | task 226 | processing task, is_child = 0 0.56.015.875 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.187 0.56.016.003 I slot launch_slot_: id 3 | task 227 | processing task, is_child = 0 0.56.288.989 I slot print_timing: id 0 | task 224 | prompt eval time = 252.34 ms / 107 tokens ( 2.36 ms per token, 424.02 tokens per second) 0.56.288.995 I slot print_timing: id 0 | task 224 | eval time = 20.62 ms / 2 tokens ( 20.62 ms per token, 48.49 tokens per second) 0.56.288.996 I slot print_timing: id 0 | task 224 | total time = 272.97 ms / 109 tokens 0.56.288.997 I slot print_timing: id 0 | task 224 | graphs reused = 1 0.56.288.998 I slot print_timing: id 0 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.289.021 I slot release: id 0 | task 224 | stop processing: n_tokens = 108, truncated = 0 0.56.289.314 I slot print_timing: id 1 | task 225 | prompt eval time = 252.22 ms / 114 tokens ( 2.21 ms per token, 451.98 tokens per second) 0.56.289.317 I slot print_timing: id 1 | task 225 | eval time = 20.21 ms / 2 tokens ( 20.21 ms per token, 49.48 tokens per second) 0.56.289.317 I slot print_timing: id 1 | task 225 | total time = 272.44 ms / 116 tokens 0.56.289.318 I slot print_timing: id 1 | task 225 | graphs reused = 1 0.56.289.318 I slot print_timing: id 1 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.289.332 I slot release: id 1 | task 225 | stop processing: n_tokens = 115, truncated = 0 0.56.289.617 I slot print_timing: id 2 | task 226 | prompt eval time = 252.10 ms / 102 tokens ( 2.47 ms per token, 404.61 tokens per second) 0.56.289.620 I slot print_timing: id 2 | task 226 | eval time = 19.80 ms / 2 tokens ( 19.80 ms per token, 50.51 tokens per second) 0.56.289.621 I slot print_timing: id 2 | task 226 | total time = 271.89 ms / 104 tokens 0.56.289.621 I slot print_timing: id 2 | task 226 | graphs reused = 1 0.56.289.621 I slot print_timing: id 2 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.289.632 I slot release: id 2 | task 226 | stop processing: n_tokens = 103, truncated = 0 0.56.289.917 I slot print_timing: id 3 | task 227 | prompt eval time = 251.92 ms / 185 tokens ( 1.36 ms per token, 734.37 tokens per second) 0.56.289.920 I slot print_timing: id 3 | task 227 | eval time = 19.41 ms / 2 tokens ( 19.41 ms per token, 51.51 tokens per second) 0.56.289.920 I slot print_timing: id 3 | task 227 | total time = 271.33 ms / 187 tokens 0.56.289.921 I slot print_timing: id 3 | task 227 | graphs reused = 1 0.56.289.921 I slot print_timing: id 3 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.289.932 I slot release: id 3 | task 227 | stop processing: n_tokens = 186, truncated = 0 0.56.297.619 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.259 0.56.319.502 I slot launch_slot_: id 0 | task 231 | processing task, is_child = 0 0.56.319.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 0.56.342.176 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.536 MiB) 0.56.365.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.568 MiB) 0.56.389.380 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.282 0.56.389.555 I slot launch_slot_: id 2 | task 232 | processing task, is_child = 0 0.56.389.602 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.243 0.56.389.716 I slot launch_slot_: id 1 | task 233 | processing task, is_child = 0 0.56.389.744 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.151 0.56.389.849 I slot launch_slot_: id 3 | task 234 | processing task, is_child = 0 0.56.649.538 I slot print_timing: id 0 | task 231 | prompt eval time = 239.13 ms / 122 tokens ( 1.96 ms per token, 510.18 tokens per second) 0.56.649.544 I slot print_timing: id 0 | task 231 | eval time = 20.54 ms / 2 tokens ( 20.54 ms per token, 48.69 tokens per second) 0.56.649.546 I slot print_timing: id 0 | task 231 | total time = 259.67 ms / 124 tokens 0.56.649.546 I slot print_timing: id 0 | task 231 | graphs reused = 1 0.56.649.547 I slot print_timing: id 0 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.649.570 I slot release: id 0 | task 231 | stop processing: n_tokens = 123, truncated = 0 0.56.649.871 I slot print_timing: id 1 | task 233 | prompt eval time = 239.00 ms / 126 tokens ( 1.90 ms per token, 527.20 tokens per second) 0.56.649.875 I slot print_timing: id 1 | task 233 | eval time = 20.16 ms / 2 tokens ( 20.16 ms per token, 49.59 tokens per second) 0.56.649.875 I slot print_timing: id 1 | task 233 | total time = 259.16 ms / 128 tokens 0.56.649.876 I slot print_timing: id 1 | task 233 | graphs reused = 1 0.56.649.876 I slot print_timing: id 1 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.649.891 I slot release: id 1 | task 233 | stop processing: n_tokens = 127, truncated = 0 0.56.650.180 I slot print_timing: id 2 | task 232 | prompt eval time = 238.79 ms / 110 tokens ( 2.17 ms per token, 460.66 tokens per second) 0.56.650.183 I slot print_timing: id 2 | task 232 | eval time = 19.79 ms / 2 tokens ( 19.79 ms per token, 50.53 tokens per second) 0.56.650.184 I slot print_timing: id 2 | task 232 | total time = 258.58 ms / 112 tokens 0.56.650.184 I slot print_timing: id 2 | task 232 | graphs reused = 1 0.56.650.185 I slot print_timing: id 2 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.650.197 I slot release: id 2 | task 232 | stop processing: n_tokens = 111, truncated = 0 0.56.650.482 I slot print_timing: id 3 | task 234 | prompt eval time = 238.58 ms / 164 tokens ( 1.45 ms per token, 687.39 tokens per second) 0.56.650.485 I slot print_timing: id 3 | task 234 | eval time = 19.46 ms / 2 tokens ( 19.46 ms per token, 51.38 tokens per second) 0.56.650.486 I slot print_timing: id 3 | task 234 | total time = 258.05 ms / 166 tokens 0.56.650.486 I slot print_timing: id 3 | task 234 | graphs reused = 1 0.56.650.486 I slot print_timing: id 3 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.650.497 I slot release: id 3 | task 234 | stop processing: n_tokens = 165, truncated = 0 0.56.658.063 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.261 0.56.658.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.630 MiB) 0.56.677.223 I slot launch_slot_: id 2 | task 238 | processing task, is_child = 0 0.56.677.261 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.755 MiB) 0.56.696.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.661 MiB) 0.56.719.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.629 MiB) 0.56.742.148 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.228 0.56.742.298 I slot launch_slot_: id 0 | task 239 | processing task, is_child = 0 0.56.742.345 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.220 0.56.742.465 I slot launch_slot_: id 1 | task 240 | processing task, is_child = 0 0.56.742.492 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.170 0.56.750.680 I slot launch_slot_: id 3 | task 241 | processing task, is_child = 0 0.57.020.843 I slot print_timing: id 0 | task 239 | prompt eval time = 249.43 ms / 125 tokens ( 2.00 ms per token, 501.13 tokens per second) 0.57.020.848 I slot print_timing: id 0 | task 239 | eval time = 20.71 ms / 2 tokens ( 20.71 ms per token, 48.28 tokens per second) 0.57.020.850 I slot print_timing: id 0 | task 239 | total time = 270.14 ms / 127 tokens 0.57.020.851 I slot print_timing: id 0 | task 239 | graphs reused = 1 0.57.020.852 I slot print_timing: id 0 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.020.874 I slot release: id 0 | task 239 | stop processing: n_tokens = 126, truncated = 0 0.57.021.201 I slot print_timing: id 1 | task 240 | prompt eval time = 249.38 ms / 122 tokens ( 2.04 ms per token, 489.21 tokens per second) 0.57.021.205 I slot print_timing: id 1 | task 240 | eval time = 20.29 ms / 2 tokens ( 20.29 ms per token, 49.30 tokens per second) 0.57.021.205 I slot print_timing: id 1 | task 240 | total time = 269.67 ms / 124 tokens 0.57.021.206 I slot print_timing: id 1 | task 240 | graphs reused = 1 0.57.021.206 I slot print_timing: id 1 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.021.219 I slot release: id 1 | task 240 | stop processing: n_tokens = 123, truncated = 0 0.57.021.555 I slot print_timing: id 2 | task 238 | prompt eval time = 249.30 ms / 138 tokens ( 1.81 ms per token, 553.55 tokens per second) 0.57.021.558 I slot print_timing: id 2 | task 238 | eval time = 19.86 ms / 2 tokens ( 19.86 ms per token, 50.35 tokens per second) 0.57.021.559 I slot print_timing: id 2 | task 238 | total time = 269.16 ms / 140 tokens 0.57.021.559 I slot print_timing: id 2 | task 238 | graphs reused = 1 0.57.021.560 I slot print_timing: id 2 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.021.572 I slot release: id 2 | task 238 | stop processing: n_tokens = 139, truncated = 0 0.57.021.873 I slot print_timing: id 3 | task 241 | prompt eval time = 249.15 ms / 137 tokens ( 1.82 ms per token, 549.87 tokens per second) 0.57.021.876 I slot print_timing: id 3 | task 241 | eval time = 19.48 ms / 2 tokens ( 19.48 ms per token, 51.33 tokens per second) 0.57.021.877 I slot print_timing: id 3 | task 241 | total time = 268.63 ms / 139 tokens 0.57.021.877 I slot print_timing: id 3 | task 241 | graphs reused = 1 0.57.021.878 I slot print_timing: id 3 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.021.888 I slot release: id 3 | task 241 | stop processing: n_tokens = 138, truncated = 0 0.57.029.323 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.222 0.57.059.767 I slot launch_slot_: id 0 | task 245 | processing task, is_child = 0 0.57.081.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 0.57.104.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.130 MiB) 0.57.126.938 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.228 0.57.127.107 I slot launch_slot_: id 1 | task 246 | processing task, is_child = 0 0.57.127.158 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.201 0.57.127.298 I slot launch_slot_: id 2 | task 247 | processing task, is_child = 0 0.57.127.326 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.203 0.57.127.441 I slot launch_slot_: id 3 | task 248 | processing task, is_child = 0 0.57.413.807 I slot print_timing: id 0 | task 245 | prompt eval time = 265.20 ms / 158 tokens ( 1.68 ms per token, 595.77 tokens per second) 0.57.413.813 I slot print_timing: id 0 | task 245 | eval time = 21.14 ms / 2 tokens ( 21.14 ms per token, 47.30 tokens per second) 0.57.413.814 I slot print_timing: id 0 | task 245 | total time = 286.35 ms / 160 tokens 0.57.413.815 I slot print_timing: id 0 | task 245 | graphs reused = 1 0.57.413.816 I slot print_timing: id 0 | task 245 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.413.845 I slot release: id 0 | task 245 | stop processing: n_tokens = 159, truncated = 0 0.57.414.212 I slot print_timing: id 1 | task 246 | prompt eval time = 265.13 ms / 140 tokens ( 1.89 ms per token, 528.05 tokens per second) 0.57.414.216 I slot print_timing: id 1 | task 246 | eval time = 20.75 ms / 2 tokens ( 20.75 ms per token, 48.19 tokens per second) 0.57.414.216 I slot print_timing: id 1 | task 246 | total time = 285.88 ms / 142 tokens 0.57.414.217 I slot print_timing: id 1 | task 246 | graphs reused = 1 0.57.414.217 I slot print_timing: id 1 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.414.231 I slot release: id 1 | task 246 | stop processing: n_tokens = 141, truncated = 0 0.57.414.679 I slot print_timing: id 2 | task 247 | prompt eval time = 265.05 ms / 168 tokens ( 1.58 ms per token, 633.84 tokens per second) 0.57.414.683 I slot print_timing: id 2 | task 247 | eval time = 20.41 ms / 2 tokens ( 20.41 ms per token, 49.01 tokens per second) 0.57.414.684 I slot print_timing: id 2 | task 247 | total time = 285.46 ms / 170 tokens 0.57.414.684 I slot print_timing: id 2 | task 247 | graphs reused = 1 0.57.414.685 I slot print_timing: id 2 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.414.701 I slot release: id 2 | task 247 | stop processing: n_tokens = 169, truncated = 0 0.57.415.053 I slot print_timing: id 3 | task 248 | prompt eval time = 264.91 ms / 120 tokens ( 2.21 ms per token, 452.99 tokens per second) 0.57.415.056 I slot print_timing: id 3 | task 248 | eval time = 20.07 ms / 2 tokens ( 20.07 ms per token, 49.83 tokens per second) 0.57.415.056 I slot print_timing: id 3 | task 248 | total time = 284.98 ms / 122 tokens 0.57.415.057 I slot print_timing: id 3 | task 248 | graphs reused = 1 0.57.415.058 I slot print_timing: id 3 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.415.068 I slot release: id 3 | task 248 | stop processing: n_tokens = 121, truncated = 0 0.57.422.815 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.248 0.57.422.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.285 MiB) 0.57.446.512 I slot launch_slot_: id 3 | task 252 | processing task, is_child = 0 0.57.446.545 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 0.57.475.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.410 MiB) 0.57.495.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 0.57.514.942 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.176 0.57.515.124 I slot launch_slot_: id 0 | task 253 | processing task, is_child = 0 0.57.515.172 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.199 0.57.515.289 I slot launch_slot_: id 1 | task 254 | processing task, is_child = 0 0.57.515.315 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.166 0.57.523.684 I slot launch_slot_: id 2 | task 255 | processing task, is_child = 0 0.57.806.205 I slot print_timing: id 0 | task 253 | prompt eval time = 261.73 ms / 155 tokens ( 1.69 ms per token, 592.22 tokens per second) 0.57.806.210 I slot print_timing: id 0 | task 253 | eval time = 20.77 ms / 2 tokens ( 20.77 ms per token, 48.15 tokens per second) 0.57.806.211 I slot print_timing: id 0 | task 253 | total time = 282.50 ms / 157 tokens 0.57.806.212 I slot print_timing: id 0 | task 253 | graphs reused = 1 0.57.806.213 I slot print_timing: id 0 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.806.239 I slot release: id 0 | task 253 | stop processing: n_tokens = 156, truncated = 0 0.57.806.542 I slot print_timing: id 1 | task 254 | prompt eval time = 261.58 ms / 103 tokens ( 2.54 ms per token, 393.75 tokens per second) 0.57.806.546 I slot print_timing: id 1 | task 254 | eval time = 20.39 ms / 2 tokens ( 20.39 ms per token, 49.05 tokens per second) 0.57.806.546 I slot print_timing: id 1 | task 254 | total time = 281.97 ms / 105 tokens 0.57.806.547 I slot print_timing: id 1 | task 254 | graphs reused = 1 0.57.806.547 I slot print_timing: id 1 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.806.560 I slot release: id 1 | task 254 | stop processing: n_tokens = 104, truncated = 0 0.57.806.851 I slot print_timing: id 2 | task 255 | prompt eval time = 261.46 ms / 133 tokens ( 1.97 ms per token, 508.67 tokens per second) 0.57.806.854 I slot print_timing: id 2 | task 255 | eval time = 20.00 ms / 2 tokens ( 20.00 ms per token, 50.01 tokens per second) 0.57.806.855 I slot print_timing: id 2 | task 255 | total time = 281.46 ms / 135 tokens 0.57.806.856 I slot print_timing: id 2 | task 255 | graphs reused = 1 0.57.806.856 I slot print_timing: id 2 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.806.867 I slot release: id 2 | task 255 | stop processing: n_tokens = 134, truncated = 0 0.57.807.156 I slot print_timing: id 3 | task 252 | prompt eval time = 261.36 ms / 182 tokens ( 1.44 ms per token, 696.36 tokens per second) 0.57.807.159 I slot print_timing: id 3 | task 252 | eval time = 19.61 ms / 2 tokens ( 19.61 ms per token, 51.01 tokens per second) 0.57.807.159 I slot print_timing: id 3 | task 252 | total time = 280.96 ms / 184 tokens 0.57.807.160 I slot print_timing: id 3 | task 252 | graphs reused = 1 0.57.807.160 I slot print_timing: id 3 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.807.172 I slot release: id 3 | task 252 | stop processing: n_tokens = 183, truncated = 0 0.57.814.508 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.179 0.57.814.558 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.629 MiB) 0.57.837.963 I slot launch_slot_: id 0 | task 259 | processing task, is_child = 0 0.57.857.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.317 MiB) 0.57.880.392 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.223 MiB) 0.57.881.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.912 MiB) 0.57.904.953 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.269 0.57.905.131 I slot launch_slot_: id 1 | task 260 | processing task, is_child = 0 0.58.052.582 I slot print_timing: id 0 | task 259 | prompt eval time = 129.98 ms / 124 tokens ( 1.05 ms per token, 953.99 tokens per second) 0.58.052.587 I slot print_timing: id 0 | task 259 | eval time = 17.41 ms / 2 tokens ( 17.41 ms per token, 57.44 tokens per second) 0.58.052.588 I slot print_timing: id 0 | task 259 | total time = 147.39 ms / 126 tokens 0.58.052.589 I slot print_timing: id 0 | task 259 | graphs reused = 1 0.58.052.590 I slot print_timing: id 0 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.052.611 I slot release: id 0 | task 259 | stop processing: n_tokens = 125, truncated = 0 0.58.052.939 I slot print_timing: id 1 | task 260 | prompt eval time = 129.98 ms / 144 tokens ( 0.90 ms per token, 1107.89 tokens per second) 0.58.052.942 I slot print_timing: id 1 | task 260 | eval time = 16.90 ms / 2 tokens ( 16.90 ms per token, 59.18 tokens per second) 0.58.052.944 I slot print_timing: id 1 | task 260 | total time = 146.88 ms / 146 tokens 0.58.052.944 I slot print_timing: id 1 | task 260 | graphs reused = 1 0.58.052.945 I slot print_timing: id 1 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.052.956 I slot release: id 1 | task 260 | stop processing: n_tokens = 145, truncated = 0 0.58.076.669 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 134, t_last = 57711772 0.58.076.847 I slot launch_slot_: id 2 | task 264 | processing task, is_child = 0 0.58.076.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.068 MiB) 0.58.122.316 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 183, t_last = 57712077 0.58.122.475 I slot launch_slot_: id 3 | task 265 | processing task, is_child = 0 0.58.122.519 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 125, t_last = 57957516 0.58.122.628 I slot launch_slot_: id 0 | task 266 | processing task, is_child = 0 0.58.122.652 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 145, t_last = 57957861 0.58.122.758 I slot launch_slot_: id 1 | task 267 | processing task, is_child = 0 1.00.212.137 I slot print_timing: id 3 | task 265 | prompt eval time = 1591.55 ms / 1243 tokens ( 1.28 ms per token, 781.00 tokens per second) 1.00.212.143 I slot print_timing: id 3 | task 265 | eval time = 495.26 ms / 32 tokens ( 15.98 ms per token, 62.59 tokens per second) 1.00.212.144 I slot print_timing: id 3 | task 265 | total time = 2086.80 ms / 1275 tokens 1.00.212.145 I slot print_timing: id 3 | task 265 | graphs reused = 33 1.00.212.146 I slot print_timing: id 3 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.212.198 I slot release: id 3 | task 265 | stop processing: n_tokens = 1274, truncated = 0 1.00.249.933 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.900 1.00.250.038 I slot launch_slot_: id 3 | task 307 | processing task, is_child = 0 1.00.826.249 I slot print_timing: id 1 | task 267 | prompt eval time = 1592.11 ms / 1215 tokens ( 1.31 ms per token, 763.14 tokens per second) 1.00.826.255 I slot print_timing: id 1 | task 267 | eval time = 1110.51 ms / 63 tokens ( 17.91 ms per token, 55.83 tokens per second) 1.00.826.256 I slot print_timing: id 1 | task 267 | total time = 2702.61 ms / 1278 tokens 1.00.826.257 I slot print_timing: id 1 | task 267 | graphs reused = 59 1.00.826.257 I slot print_timing: id 1 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.826.310 I slot release: id 1 | task 267 | stop processing: n_tokens = 1277, truncated = 0 1.00.859.686 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.897 1.00.859.792 I slot launch_slot_: id 1 | task 338 | processing task, is_child = 0 1.01.076.518 I slot print_timing: id 2 | task 264 | prompt eval time = 1591.84 ms / 1230 tokens ( 1.29 ms per token, 772.69 tokens per second) 1.01.076.523 I slot print_timing: id 2 | task 264 | eval time = 1360.19 ms / 69 tokens ( 20.00 ms per token, 49.99 tokens per second) 1.01.076.524 I slot print_timing: id 2 | task 264 | total time = 2952.04 ms / 1299 tokens 1.01.076.525 I slot print_timing: id 2 | task 264 | graphs reused = 61 1.01.076.526 I slot print_timing: id 2 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.076.579 I slot release: id 2 | task 264 | stop processing: n_tokens = 1298, truncated = 0 1.01.109.747 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.883 1.01.109.860 I slot launch_slot_: id 2 | task 345 | processing task, is_child = 0 1.01.964.338 I slot print_timing: id 3 | task 307 | prompt eval time = 124.04 ms / 132 tokens ( 0.94 ms per token, 1064.20 tokens per second) 1.01.964.344 I slot print_timing: id 3 | task 307 | eval time = 1590.24 ms / 79 tokens ( 20.39 ms per token, 49.05 tokens per second) 1.01.964.345 I slot print_timing: id 3 | task 307 | total time = 1714.28 ms / 211 tokens 1.01.964.345 I slot print_timing: id 3 | task 307 | graphs reused = 102 1.01.964.346 I slot print_timing: id 3 | task 307 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.964.400 I slot release: id 3 | task 307 | stop processing: n_tokens = 1335, truncated = 0 1.02.001.359 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.858 1.02.001.463 I slot launch_slot_: id 3 | task 392 | processing task, is_child = 0 1.02.178.072 I slot print_timing: id 0 | task 266 | prompt eval time = 1592.40 ms / 1234 tokens ( 1.29 ms per token, 774.93 tokens per second) 1.02.178.077 I slot print_timing: id 0 | task 266 | eval time = 2462.89 ms / 121 tokens ( 20.52 ms per token, 48.72 tokens per second) 1.02.178.079 I slot print_timing: id 0 | task 266 | total time = 4055.30 ms / 1355 tokens 1.02.178.080 I slot print_timing: id 0 | task 266 | graphs reused = 105 1.02.178.080 I slot print_timing: id 0 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.178.130 I slot release: id 0 | task 266 | stop processing: n_tokens = 1354, truncated = 0 1.02.215.504 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.846 1.02.215.609 I slot launch_slot_: id 0 | task 400 | processing task, is_child = 0 1.02.756.129 I slot print_timing: id 2 | task 345 | prompt eval time = 161.40 ms / 139 tokens ( 1.16 ms per token, 861.21 tokens per second) 1.02.756.134 I slot print_timing: id 2 | task 345 | eval time = 1484.85 ms / 79 tokens ( 19.04 ms per token, 52.53 tokens per second) 1.02.756.135 I slot print_timing: id 2 | task 345 | total time = 1646.25 ms / 218 tokens 1.02.756.136 I slot print_timing: id 2 | task 345 | graphs reused = 131 1.02.756.137 I slot print_timing: id 2 | task 345 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.756.190 I slot release: id 2 | task 345 | stop processing: n_tokens = 1342, truncated = 0 1.02.819.502 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.854 1.02.819.627 I slot launch_slot_: id 2 | task 430 | processing task, is_child = 0 1.03.380.273 I slot print_timing: id 1 | task 338 | prompt eval time = 161.71 ms / 139 tokens ( 1.16 ms per token, 859.58 tokens per second) 1.03.380.278 I slot print_timing: id 1 | task 338 | eval time = 2358.76 ms / 114 tokens ( 20.87 ms per token, 47.91 tokens per second) 1.03.380.280 I slot print_timing: id 1 | task 338 | total time = 2520.46 ms / 253 tokens 1.03.380.280 I slot print_timing: id 1 | task 338 | graphs reused = 155 1.03.380.281 I slot print_timing: id 1 | task 338 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.380.331 I slot release: id 1 | task 338 | stop processing: n_tokens = 1377, truncated = 0 1.03.443.730 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.832 1.03.443.841 I slot launch_slot_: id 1 | task 460 | processing task, is_child = 0 1.04.282.377 I slot print_timing: id 3 | task 392 | prompt eval time = 122.47 ms / 114 tokens ( 1.07 ms per token, 930.84 tokens per second) 1.04.282.383 I slot print_timing: id 3 | task 392 | eval time = 2158.43 ms / 109 tokens ( 19.99 ms per token, 50.04 tokens per second) 1.04.282.384 I slot print_timing: id 3 | task 392 | total time = 2280.90 ms / 223 tokens 1.04.282.385 I slot print_timing: id 3 | task 392 | graphs reused = 197 1.04.282.386 I slot print_timing: id 3 | task 392 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.282.441 I slot release: id 3 | task 392 | stop processing: n_tokens = 1347, truncated = 0 1.04.318.774 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.851 1.04.318.894 I slot launch_slot_: id 3 | task 508 | processing task, is_child = 0 1.04.456.136 I slot print_timing: id 0 | task 400 | prompt eval time = 127.68 ms / 141 tokens ( 0.91 ms per token, 1104.32 tokens per second) 1.04.456.142 I slot print_timing: id 0 | task 400 | eval time = 2112.83 ms / 107 tokens ( 19.93 ms per token, 50.17 tokens per second) 1.04.456.143 I slot print_timing: id 0 | task 400 | total time = 2240.51 ms / 248 tokens 1.04.456.145 I slot print_timing: id 0 | task 400 | graphs reused = 198 1.04.456.145 I slot print_timing: id 0 | task 400 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.456.199 I slot release: id 0 | task 400 | stop processing: n_tokens = 1372, truncated = 0 1.04.494.392 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.835 1.04.494.498 I slot launch_slot_: id 0 | task 514 | processing task, is_child = 0 1.05.352.518 I slot print_timing: id 1 | task 460 | prompt eval time = 152.28 ms / 125 tokens ( 1.22 ms per token, 820.83 tokens per second) 1.05.352.524 I slot print_timing: id 1 | task 460 | eval time = 1756.37 ms / 98 tokens ( 18.11 ms per token, 55.23 tokens per second) 1.05.352.525 I slot print_timing: id 1 | task 460 | total time = 1908.66 ms / 223 tokens 1.05.352.526 I slot print_timing: id 1 | task 460 | graphs reused = 244 1.05.352.527 I slot print_timing: id 1 | task 460 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.352.600 I slot release: id 1 | task 460 | stop processing: n_tokens = 1347, truncated = 0 1.05.386.167 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.851 1.05.386.274 I slot launch_slot_: id 1 | task 563 | processing task, is_child = 0 1.05.532.532 I slot print_timing: id 2 | task 430 | prompt eval time = 164.54 ms / 169 tokens ( 0.97 ms per token, 1027.09 tokens per second) 1.05.532.538 I slot print_timing: id 2 | task 430 | eval time = 2548.34 ms / 130 tokens ( 19.75 ms per token, 50.62 tokens per second) 1.05.532.539 I slot print_timing: id 2 | task 430 | total time = 2712.88 ms / 299 tokens 1.05.532.540 I slot print_timing: id 2 | task 430 | graphs reused = 244 1.05.532.541 I slot print_timing: id 2 | task 430 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.532.596 I slot release: id 2 | task 430 | stop processing: n_tokens = 1423, truncated = 0 1.05.566.117 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.805 1.05.566.227 I slot launch_slot_: id 2 | task 567 | processing task, is_child = 0 1.05.658.603 I slot print_timing: id 0 | task 514 | prompt eval time = 114.35 ms / 101 tokens ( 1.13 ms per token, 883.27 tokens per second) 1.05.658.609 I slot print_timing: id 0 | task 514 | eval time = 1049.74 ms / 51 tokens ( 20.99 ms per token, 47.63 tokens per second) 1.05.658.610 I slot print_timing: id 0 | task 514 | total time = 1164.09 ms / 152 tokens 1.05.658.611 I slot print_timing: id 0 | task 514 | graphs reused = 244 1.05.658.612 I slot print_timing: id 0 | task 514 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.658.668 I slot release: id 0 | task 514 | stop processing: n_tokens = 1276, truncated = 0 1.05.718.442 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.898 1.05.718.560 I slot launch_slot_: id 0 | task 570 | processing task, is_child = 0 1.06.219.882 I slot print_timing: id 3 | task 508 | prompt eval time = 118.52 ms / 101 tokens ( 1.17 ms per token, 852.18 tokens per second) 1.06.219.888 I slot print_timing: id 3 | task 508 | eval time = 1782.45 ms / 81 tokens ( 22.28 ms per token, 44.88 tokens per second) 1.06.219.889 I slot print_timing: id 3 | task 508 | total time = 1900.97 ms / 182 tokens 1.06.219.890 I slot print_timing: id 3 | task 508 | graphs reused = 265 1.06.219.890 I slot print_timing: id 3 | task 508 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.219.942 I slot release: id 3 | task 508 | stop processing: n_tokens = 1306, truncated = 0 1.06.257.431 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.877 1.06.257.552 I slot launch_slot_: id 3 | task 597 | processing task, is_child = 0 1.07.091.600 I slot print_timing: id 2 | task 567 | prompt eval time = 151.91 ms / 120 tokens ( 1.27 ms per token, 789.92 tokens per second) 1.07.091.605 I slot print_timing: id 2 | task 567 | eval time = 1373.44 ms / 73 tokens ( 19.08 ms per token, 52.42 tokens per second) 1.07.091.607 I slot print_timing: id 2 | task 567 | total time = 1525.36 ms / 193 tokens 1.07.091.607 I slot print_timing: id 2 | task 567 | graphs reused = 309 1.07.091.608 I slot print_timing: id 2 | task 567 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.091.657 I slot release: id 2 | task 567 | stop processing: n_tokens = 1317, truncated = 0 1.07.123.393 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.870 1.07.123.493 I slot launch_slot_: id 2 | task 645 | processing task, is_child = 0 1.07.795.714 I slot print_timing: id 1 | task 563 | prompt eval time = 145.96 ms / 95 tokens ( 1.54 ms per token, 650.88 tokens per second) 1.07.795.720 I slot print_timing: id 1 | task 563 | eval time = 2263.47 ms / 112 tokens ( 20.39 ms per token, 49.04 tokens per second) 1.07.795.721 I slot print_timing: id 1 | task 563 | total time = 2409.42 ms / 207 tokens 1.07.795.722 I slot print_timing: id 1 | task 563 | graphs reused = 341 1.07.795.722 I slot print_timing: id 1 | task 563 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.795.771 I slot release: id 1 | task 563 | stop processing: n_tokens = 1331, truncated = 0 1.07.827.730 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.861 1.07.827.832 I slot launch_slot_: id 1 | task 682 | processing task, is_child = 0 1.08.039.357 I slot print_timing: id 3 | task 597 | prompt eval time = 118.93 ms / 86 tokens ( 1.38 ms per token, 723.13 tokens per second) 1.08.039.363 I slot print_timing: id 3 | task 597 | eval time = 1662.86 ms / 88 tokens ( 19.11 ms per token, 52.32 tokens per second) 1.08.039.364 I slot print_timing: id 3 | task 597 | total time = 1781.79 ms / 174 tokens 1.08.039.365 I slot print_timing: id 3 | task 597 | graphs reused = 344 1.08.039.366 I slot print_timing: id 3 | task 597 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.039.415 I slot release: id 3 | task 597 | stop processing: n_tokens = 1298, truncated = 0 1.08.075.585 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.948 (> 0.100 thold), f_keep = 0.883 1.08.075.684 I slot launch_slot_: id 3 | task 691 | processing task, is_child = 0 1.08.602.254 I slot print_timing: id 0 | task 570 | prompt eval time = 133.66 ms / 148 tokens ( 0.90 ms per token, 1107.31 tokens per second) 1.08.602.260 I slot print_timing: id 0 | task 570 | eval time = 2750.02 ms / 143 tokens ( 19.37 ms per token, 51.64 tokens per second) 1.08.602.261 I slot print_timing: id 0 | task 570 | total time = 2883.68 ms / 291 tokens 1.08.602.262 I slot print_timing: id 0 | task 570 | graphs reused = 369 1.08.602.262 I slot print_timing: id 0 | task 570 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.602.313 I slot release: id 0 | task 570 | stop processing: n_tokens = 1415, truncated = 0 1.08.621.030 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.810 1.08.621.149 I slot launch_slot_: id 0 | task 720 | processing task, is_child = 0 1.09.170.513 I slot print_timing: id 1 | task 682 | prompt eval time = 142.83 ms / 97 tokens ( 1.47 ms per token, 679.13 tokens per second) 1.09.170.519 I slot print_timing: id 1 | task 682 | eval time = 1199.84 ms / 63 tokens ( 19.35 ms per token, 51.67 tokens per second) 1.09.170.520 I slot print_timing: id 1 | task 682 | total time = 1342.67 ms / 160 tokens 1.09.170.521 I slot print_timing: id 1 | task 682 | graphs reused = 395 1.09.170.521 I slot print_timing: id 1 | task 682 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.170.571 I slot release: id 1 | task 682 | stop processing: n_tokens = 1284, truncated = 0 1.09.203.696 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.893 1.09.203.805 I slot launch_slot_: id 1 | task 750 | processing task, is_child = 0 1.09.456.019 I slot print_timing: id 3 | task 691 | prompt eval time = 114.02 ms / 84 tokens ( 1.36 ms per token, 736.73 tokens per second) 1.09.456.025 I slot print_timing: id 3 | task 691 | eval time = 1266.29 ms / 64 tokens ( 20.10 ms per token, 49.75 tokens per second) 1.09.456.026 I slot print_timing: id 3 | task 691 | total time = 1380.31 ms / 148 tokens 1.09.456.027 I slot print_timing: id 3 | task 691 | graphs reused = 400 1.09.456.028 I slot print_timing: id 3 | task 691 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.456.082 I slot release: id 3 | task 691 | stop processing: n_tokens = 1272, truncated = 0 1.09.493.364 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.901 1.09.493.470 I slot launch_slot_: id 3 | task 761 | processing task, is_child = 0 1.09.937.418 I slot print_timing: id 0 | task 720 | prompt eval time = 117.59 ms / 101 tokens ( 1.16 ms per token, 858.91 tokens per second) 1.09.937.424 I slot print_timing: id 0 | task 720 | eval time = 1198.66 ms / 59 tokens ( 20.67 ms per token, 48.39 tokens per second) 1.09.937.425 I slot print_timing: id 0 | task 720 | total time = 1316.25 ms / 160 tokens 1.09.937.425 I slot print_timing: id 0 | task 720 | graphs reused = 419 1.09.937.426 I slot print_timing: id 0 | task 720 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.937.478 I slot release: id 0 | task 720 | stop processing: n_tokens = 1284, truncated = 0 1.09.975.511 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.893 1.09.975.618 I slot launch_slot_: id 0 | task 785 | processing task, is_child = 0 1.10.274.463 I slot print_timing: id 2 | task 645 | n_gen = 146, tg = 48.29 t/s, tg_3s = 48.63 t/s 1.10.471.430 I slot print_timing: id 1 | task 750 | prompt eval time = 146.70 ms / 95 tokens ( 1.54 ms per token, 647.58 tokens per second) 1.10.471.435 I slot print_timing: id 1 | task 750 | eval time = 1120.91 ms / 57 tokens ( 20.02 ms per token, 49.96 tokens per second) 1.10.471.437 I slot print_timing: id 1 | task 750 | total time = 1267.61 ms / 152 tokens 1.10.471.437 I slot print_timing: id 1 | task 750 | graphs reused = 443 1.10.471.438 I slot print_timing: id 1 | task 750 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.471.488 I slot release: id 1 | task 750 | stop processing: n_tokens = 1276, truncated = 0 1.10.504.405 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.898 1.10.504.518 I slot launch_slot_: id 1 | task 812 | processing task, is_child = 0 1.10.994.570 I slot print_timing: id 2 | task 645 | prompt eval time = 148.43 ms / 133 tokens ( 1.12 ms per token, 896.06 tokens per second) 1.10.994.575 I slot print_timing: id 2 | task 645 | eval time = 3722.63 ms / 182 tokens ( 20.57 ms per token, 48.62 tokens per second) 1.10.994.577 I slot print_timing: id 2 | task 645 | total time = 3871.06 ms / 315 tokens 1.10.994.577 I slot print_timing: id 2 | task 645 | graphs reused = 463 1.10.994.578 I slot print_timing: id 2 | task 645 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.994.627 I slot release: id 2 | task 645 | stop processing: n_tokens = 1439, truncated = 0 1.11.058.838 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.796 1.11.058.963 I slot launch_slot_: id 2 | task 838 | processing task, is_child = 0 1.11.928.164 I slot print_timing: id 0 | task 785 | prompt eval time = 111.39 ms / 90 tokens ( 1.24 ms per token, 807.96 tokens per second) 1.11.928.170 I slot print_timing: id 0 | task 785 | eval time = 1841.14 ms / 98 tokens ( 18.98 ms per token, 52.68 tokens per second) 1.11.928.171 I slot print_timing: id 0 | task 785 | total time = 1952.53 ms / 188 tokens 1.11.928.171 I slot print_timing: id 0 | task 785 | graphs reused = 508 1.11.928.172 I slot print_timing: id 0 | task 785 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.928.221 I slot release: id 0 | task 785 | stop processing: n_tokens = 1312, truncated = 0 1.11.964.919 I slot print_timing: id 3 | task 761 | prompt eval time = 126.08 ms / 130 tokens ( 0.97 ms per token, 1031.13 tokens per second) 1.11.964.924 I slot print_timing: id 3 | task 761 | eval time = 2345.36 ms / 123 tokens ( 19.22 ms per token, 52.02 tokens per second) 1.11.964.925 I slot print_timing: id 3 | task 761 | total time = 2471.43 ms / 253 tokens 1.11.964.926 I slot print_timing: id 3 | task 761 | graphs reused = 509 1.11.964.927 I slot print_timing: id 3 | task 761 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.964.978 I slot release: id 3 | task 761 | stop processing: n_tokens = 1377, truncated = 0 1.11.964.994 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.874 1.11.965.102 I slot launch_slot_: id 0 | task 889 | processing task, is_child = 0 1.11.965.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 108.038 MiB) 1.11.966.923 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.786 MiB) 1.11.968.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.973 MiB) 1.12.020.400 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.832 1.12.020.528 I slot launch_slot_: id 3 | task 890 | processing task, is_child = 0 1.12.500.969 I slot print_timing: id 1 | task 812 | prompt eval time = 145.72 ms / 96 tokens ( 1.52 ms per token, 658.78 tokens per second) 1.12.500.974 I slot print_timing: id 1 | task 812 | eval time = 1850.71 ms / 92 tokens ( 20.34 ms per token, 49.17 tokens per second) 1.12.500.975 I slot print_timing: id 1 | task 812 | total time = 1996.43 ms / 188 tokens 1.12.500.976 I slot print_timing: id 1 | task 812 | graphs reused = 524 1.12.500.977 I slot print_timing: id 1 | task 812 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.501.025 I slot release: id 1 | task 812 | stop processing: n_tokens = 1312, truncated = 0 1.12.566.272 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.873 1.12.566.389 I slot launch_slot_: id 1 | task 911 | processing task, is_child = 0 1.13.178.017 I slot print_timing: id 2 | task 838 | prompt eval time = 142.25 ms / 87 tokens ( 1.64 ms per token, 611.59 tokens per second) 1.13.178.023 I slot print_timing: id 2 | task 838 | eval time = 1976.78 ms / 98 tokens ( 20.38 ms per token, 49.07 tokens per second) 1.13.178.024 I slot print_timing: id 2 | task 838 | total time = 2119.04 ms / 185 tokens 1.13.178.025 I slot print_timing: id 2 | task 838 | graphs reused = 550 1.13.178.026 I slot print_timing: id 2 | task 838 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.178.076 I slot release: id 2 | task 838 | stop processing: n_tokens = 1309, truncated = 0 1.13.211.104 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.875 1.13.211.218 I slot launch_slot_: id 2 | task 942 | processing task, is_child = 0 1.14.135.994 I slot print_timing: id 3 | task 890 | prompt eval time = 193.88 ms / 137 tokens ( 1.42 ms per token, 706.63 tokens per second) 1.14.136.000 I slot print_timing: id 3 | task 890 | eval time = 1902.15 ms / 98 tokens ( 19.61 ms per token, 50.99 tokens per second) 1.14.136.001 I slot print_timing: id 3 | task 890 | total time = 2096.03 ms / 235 tokens 1.14.136.002 I slot print_timing: id 3 | task 890 | graphs reused = 596 1.14.136.003 I slot print_timing: id 3 | task 890 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.136.067 I slot release: id 3 | task 890 | stop processing: n_tokens = 1359, truncated = 0 1.14.154.934 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.843 1.14.155.058 I slot launch_slot_: id 3 | task 993 | processing task, is_child = 0 1.14.546.882 I slot print_timing: id 2 | task 942 | prompt eval time = 145.18 ms / 93 tokens ( 1.56 ms per token, 640.60 tokens per second) 1.14.546.888 I slot print_timing: id 2 | task 942 | eval time = 1190.47 ms / 67 tokens ( 18.04 ms per token, 55.44 tokens per second) 1.14.546.889 I slot print_timing: id 2 | task 942 | total time = 1335.65 ms / 160 tokens 1.14.546.890 I slot print_timing: id 2 | task 942 | graphs reused = 611 1.14.546.891 I slot print_timing: id 2 | task 942 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.546.941 I slot release: id 2 | task 942 | stop processing: n_tokens = 1284, truncated = 0 1.14.612.228 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.893 1.14.612.357 I slot launch_slot_: id 2 | task 1014 | processing task, is_child = 0 1.15.242.842 I slot print_timing: id 0 | task 889 | n_gen = 151, tg = 49.83 t/s, tg_3s = 50.16 t/s 1.15.369.900 I slot print_timing: id 3 | task 993 | prompt eval time = 121.73 ms / 87 tokens ( 1.40 ms per token, 714.67 tokens per second) 1.15.369.905 I slot print_timing: id 3 | task 993 | eval time = 1093.09 ms / 59 tokens ( 18.85 ms per token, 53.06 tokens per second) 1.15.369.906 I slot print_timing: id 3 | task 993 | total time = 1214.82 ms / 146 tokens 1.15.369.907 I slot print_timing: id 3 | task 993 | graphs reused = 648 1.15.369.908 I slot print_timing: id 3 | task 993 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.369.958 I slot release: id 3 | task 993 | stop processing: n_tokens = 1270, truncated = 0 1.15.405.836 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.902 1.15.405.950 I slot launch_slot_: id 3 | task 1057 | processing task, is_child = 0 1.15.624.126 I slot print_timing: id 2 | task 1014 | prompt eval time = 145.05 ms / 98 tokens ( 1.48 ms per token, 675.64 tokens per second) 1.15.624.132 I slot print_timing: id 2 | task 1014 | eval time = 866.70 ms / 49 tokens ( 18.06 ms per token, 55.38 tokens per second) 1.15.624.133 I slot print_timing: id 2 | task 1014 | total time = 1011.75 ms / 147 tokens 1.15.624.133 I slot print_timing: id 2 | task 1014 | graphs reused = 654 1.15.624.134 I slot print_timing: id 2 | task 1014 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.624.186 I slot release: id 2 | task 1014 | stop processing: n_tokens = 1271, truncated = 0 1.15.686.736 I slot print_timing: id 0 | task 889 | prompt eval time = 212.15 ms / 131 tokens ( 1.62 ms per token, 617.48 tokens per second) 1.15.686.742 I slot print_timing: id 0 | task 889 | eval time = 3454.04 ms / 171 tokens ( 20.32 ms per token, 49.22 tokens per second) 1.15.686.743 I slot print_timing: id 0 | task 889 | total time = 3666.19 ms / 302 tokens 1.15.686.743 I slot print_timing: id 0 | task 889 | graphs reused = 654 1.15.686.745 I slot print_timing: id 0 | task 889 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.686.793 I slot release: id 0 | task 889 | stop processing: n_tokens = 1426, truncated = 0 1.15.687.275 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.804 1.15.687.394 I slot launch_slot_: id 0 | task 1068 | processing task, is_child = 0 1.15.687.483 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.536 MiB) 1.15.689.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.600 MiB) 1.15.690.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.380 MiB) 1.15.734.857 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.902 1.15.734.974 I slot launch_slot_: id 2 | task 1069 | processing task, is_child = 0 1.15.877.376 I slot print_timing: id 1 | task 911 | n_gen = 152, tg = 47.98 t/s, tg_3s = 48.30 t/s 1.16.297.198 I slot print_timing: id 1 | task 911 | prompt eval time = 163.91 ms / 153 tokens ( 1.07 ms per token, 933.46 tokens per second) 1.16.297.204 I slot print_timing: id 1 | task 911 | eval time = 3566.88 ms / 174 tokens ( 20.62 ms per token, 48.50 tokens per second) 1.16.297.205 I slot print_timing: id 1 | task 911 | total time = 3730.79 ms / 327 tokens 1.16.297.205 I slot print_timing: id 1 | task 911 | graphs reused = 674 1.16.297.206 I slot print_timing: id 1 | task 911 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.297.258 I slot release: id 1 | task 911 | stop processing: n_tokens = 1451, truncated = 0 1.16.329.264 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.790 1.16.329.370 I slot launch_slot_: id 1 | task 1094 | processing task, is_child = 0 1.17.384.479 I slot print_timing: id 2 | task 1069 | prompt eval time = 207.84 ms / 122 tokens ( 1.70 ms per token, 586.98 tokens per second) 1.17.384.485 I slot print_timing: id 2 | task 1069 | eval time = 1422.19 ms / 80 tokens ( 18.00 ms per token, 55.55 tokens per second) 1.17.384.486 I slot print_timing: id 2 | task 1069 | total time = 1630.04 ms / 202 tokens 1.17.384.488 I slot print_timing: id 2 | task 1069 | graphs reused = 727 1.17.384.489 I slot print_timing: id 2 | task 1069 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.384.541 I slot release: id 2 | task 1069 | stop processing: n_tokens = 1326, truncated = 0 1.17.450.274 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.864 1.17.450.404 I slot launch_slot_: id 2 | task 1154 | processing task, is_child = 0 1.17.785.988 I slot print_timing: id 3 | task 1057 | prompt eval time = 118.50 ms / 105 tokens ( 1.13 ms per token, 886.10 tokens per second) 1.17.785.994 I slot print_timing: id 3 | task 1057 | eval time = 2261.53 ms / 105 tokens ( 21.75 ms per token, 45.99 tokens per second) 1.17.785.995 I slot print_timing: id 3 | task 1057 | total time = 2380.02 ms / 210 tokens 1.17.785.995 I slot print_timing: id 3 | task 1057 | graphs reused = 737 1.17.785.996 I slot print_timing: id 3 | task 1057 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.786.047 I slot release: id 3 | task 1057 | stop processing: n_tokens = 1334, truncated = 0 1.17.804.189 I slot print_timing: id 0 | task 1068 | prompt eval time = 226.47 ms / 113 tokens ( 2.00 ms per token, 498.97 tokens per second) 1.17.804.196 I slot print_timing: id 0 | task 1068 | eval time = 1842.73 ms / 96 tokens ( 19.40 ms per token, 51.55 tokens per second) 1.17.804.197 I slot print_timing: id 0 | task 1068 | total time = 2069.20 ms / 209 tokens 1.17.804.198 I slot print_timing: id 0 | task 1068 | graphs reused = 737 1.17.804.199 I slot print_timing: id 0 | task 1068 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.804.253 I slot release: id 0 | task 1068 | stop processing: n_tokens = 1333, truncated = 0 1.17.840.249 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.860 1.17.840.360 I slot launch_slot_: id 0 | task 1171 | processing task, is_child = 0 1.17.840.454 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 1.17.842.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.537 MiB) 1.17.843.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.912 MiB) 1.17.892.768 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.859 1.17.892.890 I slot launch_slot_: id 3 | task 1172 | processing task, is_child = 0 1.18.448.215 I slot print_timing: id 1 | task 1094 | prompt eval time = 145.01 ms / 96 tokens ( 1.51 ms per token, 662.03 tokens per second) 1.18.448.220 I slot print_timing: id 1 | task 1094 | eval time = 1973.82 ms / 96 tokens ( 20.78 ms per token, 48.13 tokens per second) 1.18.448.221 I slot print_timing: id 1 | task 1094 | total time = 2118.83 ms / 192 tokens 1.18.448.222 I slot print_timing: id 1 | task 1094 | graphs reused = 757 1.18.448.223 I slot print_timing: id 1 | task 1094 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.448.271 I slot release: id 1 | task 1094 | stop processing: n_tokens = 1316, truncated = 0 1.18.481.931 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.871 1.18.482.057 I slot launch_slot_: id 1 | task 1196 | processing task, is_child = 0 1.19.676.502 I slot print_timing: id 2 | task 1154 | prompt eval time = 149.23 ms / 113 tokens ( 1.32 ms per token, 757.24 tokens per second) 1.19.676.508 I slot print_timing: id 2 | task 1154 | eval time = 2076.86 ms / 105 tokens ( 19.97 ms per token, 50.08 tokens per second) 1.19.676.510 I slot print_timing: id 2 | task 1154 | total time = 2226.08 ms / 218 tokens 1.19.676.510 I slot print_timing: id 2 | task 1154 | graphs reused = 821 1.19.676.511 I slot print_timing: id 2 | task 1154 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.676.561 I slot release: id 2 | task 1154 | stop processing: n_tokens = 1342, truncated = 0 1.19.739.702 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.854 1.19.739.814 I slot launch_slot_: id 2 | task 1266 | processing task, is_child = 0 1.20.490.360 I slot print_timing: id 1 | task 1196 | prompt eval time = 150.43 ms / 117 tokens ( 1.29 ms per token, 777.77 tokens per second) 1.20.490.365 I slot print_timing: id 1 | task 1196 | eval time = 1857.86 ms / 108 tokens ( 17.36 ms per token, 57.59 tokens per second) 1.20.490.366 I slot print_timing: id 1 | task 1196 | total time = 2008.29 ms / 225 tokens 1.20.490.367 I slot print_timing: id 1 | task 1196 | graphs reused = 858 1.20.490.368 I slot print_timing: id 1 | task 1196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.490.416 I slot release: id 1 | task 1196 | stop processing: n_tokens = 1349, truncated = 0 1.20.522.933 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.850 1.20.523.049 I slot launch_slot_: id 1 | task 1308 | processing task, is_child = 0 1.20.841.170 I slot print_timing: id 3 | task 1172 | prompt eval time = 202.28 ms / 131 tokens ( 1.54 ms per token, 647.62 tokens per second) 1.20.841.177 I slot print_timing: id 3 | task 1172 | eval time = 2726.19 ms / 143 tokens ( 19.20 ms per token, 52.09 tokens per second) 1.20.841.177 I slot print_timing: id 3 | task 1172 | total time = 2928.47 ms / 274 tokens 1.20.841.179 I slot print_timing: id 3 | task 1172 | graphs reused = 866 1.20.841.180 I slot print_timing: id 3 | task 1172 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.841.233 I slot release: id 3 | task 1172 | stop processing: n_tokens = 1398, truncated = 0 1.20.859.865 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.820 1.20.859.977 I slot launch_slot_: id 3 | task 1321 | processing task, is_child = 0 1.21.098.269 I slot print_timing: id 0 | task 1171 | prompt eval time = 220.93 ms / 149 tokens ( 1.48 ms per token, 674.43 tokens per second) 1.21.098.275 I slot print_timing: id 0 | task 1171 | eval time = 2984.43 ms / 153 tokens ( 19.63 ms per token, 50.93 tokens per second) 1.21.098.276 I slot print_timing: id 0 | task 1171 | total time = 3205.36 ms / 302 tokens 1.21.098.277 I slot print_timing: id 0 | task 1171 | graphs reused = 872 1.21.098.277 I slot print_timing: id 0 | task 1171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.098.332 I slot release: id 0 | task 1171 | stop processing: n_tokens = 1426, truncated = 0 1.21.136.583 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.804 1.21.136.688 I slot launch_slot_: id 0 | task 1333 | processing task, is_child = 0 1.22.262.613 I slot print_timing: id 2 | task 1266 | prompt eval time = 148.73 ms / 127 tokens ( 1.17 ms per token, 853.90 tokens per second) 1.22.262.619 I slot print_timing: id 2 | task 1266 | eval time = 2374.05 ms / 126 tokens ( 18.99 ms per token, 52.65 tokens per second) 1.22.262.620 I slot print_timing: id 2 | task 1266 | total time = 2522.78 ms / 253 tokens 1.22.262.621 I slot print_timing: id 2 | task 1266 | graphs reused = 934 1.22.262.622 I slot print_timing: id 2 | task 1266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.262.675 I slot release: id 2 | task 1266 | stop processing: n_tokens = 1377, truncated = 0 1.22.328.347 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.832 1.22.328.466 I slot launch_slot_: id 2 | task 1399 | processing task, is_child = 0 1.22.627.260 I slot print_timing: id 0 | task 1333 | prompt eval time = 116.51 ms / 104 tokens ( 1.12 ms per token, 892.63 tokens per second) 1.22.627.266 I slot print_timing: id 0 | task 1333 | eval time = 1374.05 ms / 75 tokens ( 18.57 ms per token, 53.86 tokens per second) 1.22.627.267 I slot print_timing: id 0 | task 1333 | total time = 1490.56 ms / 179 tokens 1.22.627.268 I slot print_timing: id 0 | task 1333 | graphs reused = 942 1.22.627.268 I slot print_timing: id 0 | task 1333 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.627.321 I slot release: id 0 | task 1333 | stop processing: n_tokens = 1303, truncated = 0 1.22.646.367 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.880 1.22.646.478 I slot launch_slot_: id 0 | task 1412 | processing task, is_child = 0 1.22.787.072 I slot print_timing: id 3 | task 1321 | prompt eval time = 119.55 ms / 96 tokens ( 1.25 ms per token, 803.00 tokens per second) 1.22.787.078 I slot print_timing: id 3 | task 1321 | eval time = 1807.53 ms / 90 tokens ( 20.31 ms per token, 49.24 tokens per second) 1.22.787.079 I slot print_timing: id 3 | task 1321 | total time = 1927.08 ms / 186 tokens 1.22.787.079 I slot print_timing: id 3 | task 1321 | graphs reused = 943 1.22.787.080 I slot print_timing: id 3 | task 1321 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.787.132 I slot release: id 3 | task 1321 | stop processing: n_tokens = 1310, truncated = 0 1.22.823.483 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.875 1.22.823.598 I slot launch_slot_: id 3 | task 1418 | processing task, is_child = 0 1.23.634.401 I slot print_timing: id 2 | task 1399 | prompt eval time = 146.44 ms / 98 tokens ( 1.49 ms per token, 669.23 tokens per second) 1.23.634.407 I slot print_timing: id 2 | task 1399 | eval time = 1159.48 ms / 61 tokens ( 19.32 ms per token, 51.75 tokens per second) 1.23.634.409 I slot print_timing: id 2 | task 1399 | total time = 1305.92 ms / 159 tokens 1.23.634.411 I slot print_timing: id 2 | task 1399 | graphs reused = 986 1.23.634.411 I slot print_timing: id 2 | task 1399 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.634.461 I slot release: id 2 | task 1399 | stop processing: n_tokens = 1283, truncated = 0 1.23.666.274 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.893 1.23.666.382 I slot launch_slot_: id 2 | task 1465 | processing task, is_child = 0 1.23.756.065 I slot print_timing: id 1 | task 1308 | n_gen = 151, tg = 48.88 t/s, tg_3s = 49.20 t/s 1.23.851.567 I slot print_timing: id 1 | task 1308 | prompt eval time = 163.99 ms / 137 tokens ( 1.20 ms per token, 835.43 tokens per second) 1.23.851.573 I slot print_timing: id 1 | task 1308 | eval time = 3164.51 ms / 154 tokens ( 20.68 ms per token, 48.35 tokens per second) 1.23.851.574 I slot print_timing: id 1 | task 1308 | total time = 3328.50 ms / 291 tokens 1.23.851.575 I slot print_timing: id 1 | task 1308 | graphs reused = 987 1.23.851.576 I slot print_timing: id 1 | task 1308 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.851.627 I slot release: id 1 | task 1308 | stop processing: n_tokens = 1415, truncated = 0 1.23.883.682 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.810 1.23.883.796 I slot launch_slot_: id 1 | task 1471 | processing task, is_child = 0 1.24.165.107 I slot print_timing: id 0 | task 1412 | prompt eval time = 120.10 ms / 102 tokens ( 1.18 ms per token, 849.29 tokens per second) 1.24.165.112 I slot print_timing: id 0 | task 1412 | eval time = 1398.51 ms / 65 tokens ( 21.85 ms per token, 45.76 tokens per second) 1.24.165.113 I slot print_timing: id 0 | task 1412 | total time = 1518.61 ms / 167 tokens 1.24.165.113 I slot print_timing: id 0 | task 1412 | graphs reused = 994 1.24.165.114 I slot print_timing: id 0 | task 1412 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.165.164 I slot release: id 0 | task 1412 | stop processing: n_tokens = 1291, truncated = 0 1.24.202.027 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.888 1.24.202.136 I slot launch_slot_: id 0 | task 1484 | processing task, is_child = 0 1.24.952.857 I slot print_timing: id 3 | task 1418 | prompt eval time = 121.62 ms / 108 tokens ( 1.13 ms per token, 888.00 tokens per second) 1.24.952.863 I slot print_timing: id 3 | task 1418 | eval time = 2007.62 ms / 103 tokens ( 19.68 ms per token, 50.81 tokens per second) 1.24.952.864 I slot print_timing: id 3 | task 1418 | total time = 2129.24 ms / 211 tokens 1.24.952.866 I slot print_timing: id 3 | task 1418 | graphs reused = 1034 1.24.952.867 I slot print_timing: id 3 | task 1418 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.952.922 I slot release: id 3 | task 1418 | stop processing: n_tokens = 1335, truncated = 0 1.24.971.189 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.858 1.24.971.330 I slot launch_slot_: id 3 | task 1527 | processing task, is_child = 0 1.25.721.704 I slot print_timing: id 2 | task 1465 | prompt eval time = 148.72 ms / 122 tokens ( 1.22 ms per token, 820.31 tokens per second) 1.25.721.709 I slot print_timing: id 2 | task 1465 | eval time = 1906.58 ms / 98 tokens ( 19.66 ms per token, 50.88 tokens per second) 1.25.721.711 I slot print_timing: id 2 | task 1465 | total time = 2055.30 ms / 220 tokens 1.25.721.712 I slot print_timing: id 2 | task 1465 | graphs reused = 1071 1.25.721.712 I slot print_timing: id 2 | task 1465 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.721.769 I slot release: id 2 | task 1465 | stop processing: n_tokens = 1344, truncated = 0 1.25.754.528 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.853 1.25.754.634 I slot launch_slot_: id 2 | task 1569 | processing task, is_child = 0 1.26.089.786 I slot print_timing: id 3 | task 1527 | prompt eval time = 119.22 ms / 86 tokens ( 1.39 ms per token, 721.37 tokens per second) 1.26.089.792 I slot print_timing: id 3 | task 1527 | eval time = 999.22 ms / 53 tokens ( 19.22 ms per token, 52.04 tokens per second) 1.26.089.793 I slot print_timing: id 3 | task 1527 | total time = 1118.44 ms / 139 tokens 1.26.089.794 I slot print_timing: id 3 | task 1527 | graphs reused = 1081 1.26.089.794 I slot print_timing: id 3 | task 1527 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.089.846 I slot release: id 3 | task 1527 | stop processing: n_tokens = 1263, truncated = 0 1.26.127.273 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.907 1.26.127.386 I slot launch_slot_: id 3 | task 1585 | processing task, is_child = 0 1.26.679.629 I slot print_timing: id 0 | task 1484 | prompt eval time = 114.21 ms / 111 tokens ( 1.03 ms per token, 971.89 tokens per second) 1.26.679.635 I slot print_timing: id 0 | task 1484 | eval time = 2363.26 ms / 125 tokens ( 19.06 ms per token, 52.47 tokens per second) 1.26.679.636 I slot print_timing: id 0 | task 1484 | total time = 2477.48 ms / 236 tokens 1.26.679.637 I slot print_timing: id 0 | task 1484 | graphs reused = 1107 1.26.679.638 I slot print_timing: id 0 | task 1484 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.679.688 I slot release: id 0 | task 1484 | stop processing: n_tokens = 1360, truncated = 0 1.26.717.649 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.843 1.26.717.763 I slot launch_slot_: id 0 | task 1616 | processing task, is_child = 0 1.27.037.448 I slot print_timing: id 1 | task 1471 | n_gen = 153, tg = 50.61 t/s, tg_3s = 50.94 t/s 1.27.152.353 I slot print_timing: id 1 | task 1471 | prompt eval time = 150.33 ms / 124 tokens ( 1.21 ms per token, 824.85 tokens per second) 1.27.152.358 I slot print_timing: id 1 | task 1471 | eval time = 3118.21 ms / 160 tokens ( 19.61 ms per token, 50.99 tokens per second) 1.27.152.359 I slot print_timing: id 1 | task 1471 | total time = 3268.54 ms / 284 tokens 1.27.152.360 I slot print_timing: id 1 | task 1471 | graphs reused = 1127 1.27.152.361 I slot print_timing: id 1 | task 1471 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.152.412 I slot release: id 1 | task 1471 | stop processing: n_tokens = 1408, truncated = 0 1.27.184.685 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.814 1.27.184.798 I slot launch_slot_: id 1 | task 1639 | processing task, is_child = 0 1.27.924.362 I slot print_timing: id 2 | task 1569 | prompt eval time = 148.54 ms / 106 tokens ( 1.40 ms per token, 713.61 tokens per second) 1.27.924.368 I slot print_timing: id 2 | task 1569 | eval time = 2021.17 ms / 105 tokens ( 19.43 ms per token, 51.46 tokens per second) 1.27.924.369 I slot print_timing: id 2 | task 1569 | total time = 2169.71 ms / 211 tokens 1.27.924.370 I slot print_timing: id 2 | task 1569 | graphs reused = 1163 1.27.924.371 I slot print_timing: id 2 | task 1569 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.924.422 I slot release: id 2 | task 1569 | stop processing: n_tokens = 1335, truncated = 0 1.27.956.311 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.858 1.27.956.424 I slot launch_slot_: id 2 | task 1680 | processing task, is_child = 0 1.28.391.522 I slot print_timing: id 1 | task 1639 | prompt eval time = 150.14 ms / 121 tokens ( 1.24 ms per token, 805.93 tokens per second) 1.28.391.528 I slot print_timing: id 1 | task 1639 | eval time = 1056.57 ms / 59 tokens ( 18.22 ms per token, 54.89 tokens per second) 1.28.391.529 I slot print_timing: id 1 | task 1639 | total time = 1206.71 ms / 180 tokens 1.28.391.529 I slot print_timing: id 1 | task 1639 | graphs reused = 1180 1.28.391.530 I slot print_timing: id 1 | task 1639 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.391.580 I slot release: id 1 | task 1639 | stop processing: n_tokens = 1304, truncated = 0 1.28.455.397 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.879 1.28.455.499 I slot launch_slot_: id 1 | task 1703 | processing task, is_child = 0 1.28.734.885 I slot print_timing: id 3 | task 1585 | prompt eval time = 119.92 ms / 98 tokens ( 1.22 ms per token, 817.20 tokens per second) 1.28.734.891 I slot print_timing: id 3 | task 1585 | eval time = 2487.56 ms / 123 tokens ( 20.39 ms per token, 49.04 tokens per second) 1.28.734.892 I slot print_timing: id 3 | task 1585 | total time = 2607.48 ms / 221 tokens 1.28.734.893 I slot print_timing: id 3 | task 1585 | graphs reused = 1187 1.28.734.894 I slot print_timing: id 3 | task 1585 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.734.944 I slot release: id 3 | task 1585 | stop processing: n_tokens = 1345, truncated = 0 1.28.772.333 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.852 1.28.772.447 I slot launch_slot_: id 3 | task 1716 | processing task, is_child = 0 1.28.860.953 I slot print_timing: id 0 | task 1616 | prompt eval time = 114.54 ms / 91 tokens ( 1.26 ms per token, 794.50 tokens per second) 1.28.860.959 I slot print_timing: id 0 | task 1616 | eval time = 2028.63 ms / 96 tokens ( 21.35 ms per token, 46.83 tokens per second) 1.28.860.960 I slot print_timing: id 0 | task 1616 | total time = 2143.17 ms / 187 tokens 1.28.860.961 I slot print_timing: id 0 | task 1616 | graphs reused = 1188 1.28.860.962 I slot print_timing: id 0 | task 1616 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.861.015 I slot release: id 0 | task 1616 | stop processing: n_tokens = 1311, truncated = 0 1.28.906.934 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.874 1.28.907.046 I slot launch_slot_: id 0 | task 1719 | processing task, is_child = 0 1.29.662.745 I slot print_timing: id 2 | task 1680 | prompt eval time = 146.14 ms / 105 tokens ( 1.39 ms per token, 718.48 tokens per second) 1.29.662.751 I slot print_timing: id 2 | task 1680 | eval time = 1560.16 ms / 75 tokens ( 21.08 ms per token, 47.43 tokens per second) 1.29.662.753 I slot print_timing: id 2 | task 1680 | total time = 1706.31 ms / 180 tokens 1.29.662.754 I slot print_timing: id 2 | task 1680 | graphs reused = 1224 1.29.662.754 I slot print_timing: id 2 | task 1680 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.662.807 I slot release: id 2 | task 1680 | stop processing: n_tokens = 1304, truncated = 0 1.29.695.079 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.879 1.29.695.201 I slot launch_slot_: id 2 | task 1761 | processing task, is_child = 0 1.30.272.246 I slot print_timing: id 1 | task 1703 | prompt eval time = 143.53 ms / 95 tokens ( 1.51 ms per token, 661.89 tokens per second) 1.30.272.251 I slot print_timing: id 1 | task 1703 | eval time = 1673.20 ms / 82 tokens ( 20.66 ms per token, 48.41 tokens per second) 1.30.272.252 I slot print_timing: id 1 | task 1703 | total time = 1816.73 ms / 177 tokens 1.30.272.253 I slot print_timing: id 1 | task 1703 | graphs reused = 1249 1.30.272.254 I slot print_timing: id 1 | task 1703 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.272.303 I slot release: id 1 | task 1703 | stop processing: n_tokens = 1301, truncated = 0 1.30.304.276 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.881 1.30.304.383 I slot launch_slot_: id 1 | task 1791 | processing task, is_child = 0 1.30.504.689 I slot print_timing: id 0 | task 1719 | prompt eval time = 121.14 ms / 110 tokens ( 1.10 ms per token, 908.01 tokens per second) 1.30.504.695 I slot print_timing: id 0 | task 1719 | eval time = 1476.48 ms / 74 tokens ( 20.23 ms per token, 49.44 tokens per second) 1.30.504.696 I slot print_timing: id 0 | task 1719 | total time = 1597.63 ms / 184 tokens 1.30.504.696 I slot print_timing: id 0 | task 1719 | graphs reused = 1251 1.30.504.697 I slot print_timing: id 0 | task 1719 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.504.745 I slot release: id 0 | task 1719 | stop processing: n_tokens = 1308, truncated = 0 1.30.541.390 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.876 1.30.541.496 I slot launch_slot_: id 0 | task 1799 | processing task, is_child = 0 1.31.921.032 I slot print_timing: id 1 | task 1791 | prompt eval time = 146.40 ms / 115 tokens ( 1.27 ms per token, 785.52 tokens per second) 1.31.921.037 I slot print_timing: id 1 | task 1791 | eval time = 1470.23 ms / 88 tokens ( 16.90 ms per token, 59.17 tokens per second) 1.31.921.038 I slot print_timing: id 1 | task 1791 | total time = 1616.63 ms / 203 tokens 1.31.921.039 I slot print_timing: id 1 | task 1791 | graphs reused = 1332 1.31.921.040 I slot print_timing: id 1 | task 1791 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.921.089 I slot release: id 1 | task 1791 | stop processing: n_tokens = 1327, truncated = 0 1.31.921.563 I slot print_timing: id 3 | task 1716 | n_gen = 160, tg = 52.74 t/s, tg_3s = 53.07 t/s 1.31.953.265 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.864 1.31.953.374 I slot launch_slot_: id 1 | task 1883 | processing task, is_child = 0 1.32.242.321 I slot print_timing: id 3 | task 1716 | prompt eval time = 134.47 ms / 144 tokens ( 0.93 ms per token, 1070.89 tokens per second) 1.32.242.326 I slot print_timing: id 3 | task 1716 | eval time = 3335.39 ms / 172 tokens ( 19.51 ms per token, 51.27 tokens per second) 1.32.242.327 I slot print_timing: id 3 | task 1716 | total time = 3469.86 ms / 316 tokens 1.32.242.329 I slot print_timing: id 3 | task 1716 | graphs reused = 1340 1.32.242.330 I slot print_timing: id 3 | task 1716 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.242.383 I slot release: id 3 | task 1716 | stop processing: n_tokens = 1440, truncated = 0 1.32.278.403 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.796 1.32.278.507 I slot launch_slot_: id 3 | task 1897 | processing task, is_child = 0 1.32.858.359 I slot print_timing: id 2 | task 1761 | n_gen = 162, tg = 53.63 t/s, tg_3s = 53.96 t/s 1.32.984.084 I slot print_timing: id 2 | task 1761 | prompt eval time = 160.83 ms / 158 tokens ( 1.02 ms per token, 982.40 tokens per second) 1.32.984.089 I slot print_timing: id 2 | task 1761 | eval time = 3128.04 ms / 170 tokens ( 18.51 ms per token, 54.03 tokens per second) 1.32.984.090 I slot print_timing: id 2 | task 1761 | total time = 3288.87 ms / 328 tokens 1.32.984.091 I slot print_timing: id 2 | task 1761 | graphs reused = 1377 1.32.984.092 I slot print_timing: id 2 | task 1761 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.984.142 I slot release: id 2 | task 1761 | stop processing: n_tokens = 1452, truncated = 0 1.33.016.199 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.789 1.33.016.313 I slot launch_slot_: id 2 | task 1938 | processing task, is_child = 0 1.33.233.652 I slot print_timing: id 1 | task 1883 | prompt eval time = 141.08 ms / 81 tokens ( 1.74 ms per token, 574.15 tokens per second) 1.33.233.657 I slot print_timing: id 1 | task 1883 | eval time = 1139.19 ms / 58 tokens ( 19.99 ms per token, 50.04 tokens per second) 1.33.233.658 I slot print_timing: id 1 | task 1883 | total time = 1280.26 ms / 139 tokens 1.33.233.659 I slot print_timing: id 1 | task 1883 | graphs reused = 1380 1.33.233.660 I slot print_timing: id 1 | task 1883 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.233.708 I slot release: id 1 | task 1883 | stop processing: n_tokens = 1263, truncated = 0 1.33.265.689 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.907 1.33.265.798 I slot launch_slot_: id 1 | task 1946 | processing task, is_child = 0 1.33.668.690 I slot print_timing: id 0 | task 1799 | n_gen = 160, tg = 52.82 t/s, tg_3s = 53.16 t/s 1.33.999.488 I slot print_timing: id 3 | task 1897 | prompt eval time = 119.45 ms / 104 tokens ( 1.15 ms per token, 870.62 tokens per second) 1.33.999.494 I slot print_timing: id 3 | task 1897 | eval time = 1601.51 ms / 85 tokens ( 19.07 ms per token, 52.45 tokens per second) 1.33.999.494 I slot print_timing: id 3 | task 1897 | total time = 1720.96 ms / 189 tokens 1.33.999.495 I slot print_timing: id 3 | task 1897 | graphs reused = 1416 1.33.999.496 I slot print_timing: id 3 | task 1897 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.999.546 I slot release: id 3 | task 1897 | stop processing: n_tokens = 1313, truncated = 0 1.34.035.414 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.873 1.34.035.520 I slot launch_slot_: id 3 | task 1988 | processing task, is_child = 0 1.34.619.838 I slot print_timing: id 2 | task 1938 | prompt eval time = 148.75 ms / 125 tokens ( 1.19 ms per token, 840.31 tokens per second) 1.34.619.843 I slot print_timing: id 2 | task 1938 | eval time = 1454.76 ms / 78 tokens ( 18.89 ms per token, 52.93 tokens per second) 1.34.619.844 I slot print_timing: id 2 | task 1938 | total time = 1603.51 ms / 203 tokens 1.34.619.845 I slot print_timing: id 2 | task 1938 | graphs reused = 1445 1.34.619.845 I slot print_timing: id 2 | task 1938 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.619.894 I slot release: id 2 | task 1938 | stop processing: n_tokens = 1327, truncated = 0 1.34.683.008 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.864 1.34.683.110 I slot launch_slot_: id 2 | task 2022 | processing task, is_child = 0 1.35.576.615 I slot print_timing: id 3 | task 1988 | prompt eval time = 123.09 ms / 126 tokens ( 0.98 ms per token, 1023.66 tokens per second) 1.35.576.621 I slot print_timing: id 3 | task 1988 | eval time = 1417.99 ms / 81 tokens ( 17.72 ms per token, 56.42 tokens per second) 1.35.576.622 I slot print_timing: id 3 | task 1988 | total time = 1541.08 ms / 207 tokens 1.35.576.623 I slot print_timing: id 3 | task 1988 | graphs reused = 1491 1.35.576.624 I slot print_timing: id 3 | task 1988 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.576.674 I slot release: id 3 | task 1988 | stop processing: n_tokens = 1331, truncated = 0 1.35.594.747 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.861 1.35.594.848 I slot launch_slot_: id 3 | task 2073 | processing task, is_child = 0 1.36.406.536 I slot print_timing: id 1 | task 1946 | prompt eval time = 146.94 ms / 103 tokens ( 1.43 ms per token, 700.98 tokens per second) 1.36.406.541 I slot print_timing: id 1 | task 1946 | eval time = 2993.78 ms / 168 tokens ( 17.93 ms per token, 55.78 tokens per second) 1.36.406.542 I slot print_timing: id 1 | task 1946 | total time = 3140.72 ms / 271 tokens 1.36.406.543 I slot print_timing: id 1 | task 1946 | graphs reused = 1532 1.36.406.544 I slot print_timing: id 1 | task 1946 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.406.596 I slot release: id 1 | task 1946 | stop processing: n_tokens = 1395, truncated = 0 1.36.439.271 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.822 1.36.439.387 I slot launch_slot_: id 1 | task 2120 | processing task, is_child = 0 1.36.527.108 I slot print_timing: id 0 | task 1799 | prompt eval time = 117.15 ms / 128 tokens ( 0.92 ms per token, 1092.64 tokens per second) 1.36.527.115 I slot print_timing: id 0 | task 1799 | eval time = 5868.44 ms / 313 tokens ( 18.81 ms per token, 53.17 tokens per second) 1.36.527.116 I slot print_timing: id 0 | task 1799 | total time = 5985.59 ms / 441 tokens 1.36.527.118 I slot print_timing: id 0 | task 1799 | graphs reused = 1532 1.36.527.119 I slot print_timing: id 0 | task 1799 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.527.176 I slot release: id 0 | task 1799 | stop processing: n_tokens = 1565, truncated = 0 1.36.572.202 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.732 1.36.572.335 I slot launch_slot_: id 0 | task 2123 | processing task, is_child = 0 1.37.315.932 I slot print_timing: id 3 | task 2073 | prompt eval time = 119.21 ms / 108 tokens ( 1.10 ms per token, 905.96 tokens per second) 1.37.315.938 I slot print_timing: id 3 | task 2073 | eval time = 1601.86 ms / 87 tokens ( 18.63 ms per token, 53.69 tokens per second) 1.37.315.939 I slot print_timing: id 3 | task 2073 | total time = 1721.07 ms / 195 tokens 1.37.315.940 I slot print_timing: id 3 | task 2073 | graphs reused = 1569 1.37.315.940 I slot print_timing: id 3 | task 2073 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.315.989 I slot release: id 3 | task 2073 | stop processing: n_tokens = 1319, truncated = 0 1.37.352.219 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.869 1.37.352.329 I slot launch_slot_: id 3 | task 2166 | processing task, is_child = 0 1.37.568.361 I slot print_timing: id 1 | task 2120 | prompt eval time = 132.19 ms / 100 tokens ( 1.32 ms per token, 756.47 tokens per second) 1.37.568.366 I slot print_timing: id 1 | task 2120 | eval time = 996.76 ms / 51 tokens ( 19.94 ms per token, 50.16 tokens per second) 1.37.568.367 I slot print_timing: id 1 | task 2120 | total time = 1128.96 ms / 151 tokens 1.37.568.369 I slot print_timing: id 1 | task 2120 | graphs reused = 1575 1.37.568.370 I slot print_timing: id 1 | task 2120 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.568.419 I slot release: id 1 | task 2120 | stop processing: n_tokens = 1275, truncated = 0 1.37.631.654 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.949 (> 0.100 thold), f_keep = 0.899 1.37.631.758 I slot launch_slot_: id 1 | task 2177 | processing task, is_child = 0 1.37.713.076 I slot print_timing: id 2 | task 2022 | prompt eval time = 149.05 ms / 125 tokens ( 1.19 ms per token, 838.67 tokens per second) 1.37.713.081 I slot print_timing: id 2 | task 2022 | eval time = 2880.91 ms / 150 tokens ( 19.33 ms per token, 51.72 tokens per second) 1.37.713.082 I slot print_timing: id 2 | task 2022 | total time = 3029.95 ms / 275 tokens 1.37.713.083 I slot print_timing: id 2 | task 2022 | graphs reused = 1575 1.37.713.084 I slot print_timing: id 2 | task 2022 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.713.135 I slot release: id 2 | task 2022 | stop processing: n_tokens = 1399, truncated = 0 1.37.772.950 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.819 1.37.773.056 I slot launch_slot_: id 2 | task 2180 | processing task, is_child = 0 1.38.112.348 I slot print_timing: id 0 | task 2123 | prompt eval time = 139.17 ms / 171 tokens ( 0.81 ms per token, 1228.73 tokens per second) 1.38.112.353 I slot print_timing: id 0 | task 2123 | eval time = 1400.83 ms / 67 tokens ( 21.22 ms per token, 47.12 tokens per second) 1.38.112.354 I slot print_timing: id 0 | task 2123 | total time = 1539.99 ms / 238 tokens 1.38.112.355 I slot print_timing: id 0 | task 2123 | graphs reused = 1586 1.38.112.356 I slot print_timing: id 0 | task 2123 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.112.406 I slot release: id 0 | task 2123 | stop processing: n_tokens = 1362, truncated = 0 1.38.130.889 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.841 1.38.131.002 I slot launch_slot_: id 0 | task 2196 | processing task, is_child = 0 1.38.883.838 I slot print_timing: id 1 | task 2177 | prompt eval time = 140.90 ms / 82 tokens ( 1.72 ms per token, 581.97 tokens per second) 1.38.883.844 I slot print_timing: id 1 | task 2177 | eval time = 1111.16 ms / 58 tokens ( 19.49 ms per token, 51.30 tokens per second) 1.38.883.845 I slot print_timing: id 1 | task 2177 | total time = 1252.06 ms / 140 tokens 1.38.883.845 I slot print_timing: id 1 | task 2177 | graphs reused = 1625 1.38.883.846 I slot print_timing: id 1 | task 2177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.883.894 I slot release: id 1 | task 2177 | stop processing: n_tokens = 1264, truncated = 0 1.38.916.236 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.907 1.38.916.340 I slot launch_slot_: id 1 | task 2240 | processing task, is_child = 0 1.39.164.184 I slot print_timing: id 3 | task 2166 | prompt eval time = 116.85 ms / 89 tokens ( 1.31 ms per token, 761.67 tokens per second) 1.39.164.190 I slot print_timing: id 3 | task 2166 | eval time = 1694.99 ms / 77 tokens ( 22.30 ms per token, 44.84 tokens per second) 1.39.164.191 I slot print_timing: id 3 | task 2166 | total time = 1811.84 ms / 166 tokens 1.39.164.191 I slot print_timing: id 3 | task 2166 | graphs reused = 1630 1.39.164.192 I slot print_timing: id 3 | task 2166 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.164.240 I slot release: id 3 | task 2166 | stop processing: n_tokens = 1290, truncated = 0 1.39.182.275 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.888 1.39.182.392 I slot launch_slot_: id 3 | task 2250 | processing task, is_child = 0 1.39.446.157 I slot print_timing: id 2 | task 2180 | prompt eval time = 145.92 ms / 114 tokens ( 1.28 ms per token, 781.26 tokens per second) 1.39.446.163 I slot print_timing: id 2 | task 2180 | eval time = 1527.16 ms / 77 tokens ( 20.09 ms per token, 49.77 tokens per second) 1.39.446.164 I slot print_timing: id 2 | task 2180 | total time = 1673.08 ms / 191 tokens 1.39.446.165 I slot print_timing: id 2 | task 2180 | graphs reused = 1638 1.39.446.166 I slot print_timing: id 2 | task 2180 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.446.214 I slot release: id 2 | task 2180 | stop processing: n_tokens = 1315, truncated = 0 1.39.478.180 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.871 1.39.478.278 I slot launch_slot_: id 2 | task 2263 | processing task, is_child = 0 1.39.707.259 I slot print_timing: id 0 | task 2196 | prompt eval time = 114.75 ms / 98 tokens ( 1.17 ms per token, 854.01 tokens per second) 1.39.707.264 I slot print_timing: id 0 | task 2196 | eval time = 1461.49 ms / 70 tokens ( 21.18 ms per token, 47.21 tokens per second) 1.39.707.265 I slot print_timing: id 0 | task 2196 | total time = 1576.24 ms / 168 tokens 1.39.707.266 I slot print_timing: id 0 | task 2196 | graphs reused = 1642 1.39.707.267 I slot print_timing: id 0 | task 2196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.707.315 I slot release: id 0 | task 2196 | stop processing: n_tokens = 1292, truncated = 0 1.39.743.694 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.887 1.39.743.808 I slot launch_slot_: id 0 | task 2273 | processing task, is_child = 0 1.41.363.242 I slot print_timing: id 2 | task 2263 | prompt eval time = 145.97 ms / 113 tokens ( 1.29 ms per token, 774.13 tokens per second) 1.41.363.248 I slot print_timing: id 2 | task 2263 | eval time = 1738.98 ms / 105 tokens ( 16.72 ms per token, 59.81 tokens per second) 1.41.363.249 I slot print_timing: id 2 | task 2263 | total time = 1884.95 ms / 218 tokens 1.41.363.250 I slot print_timing: id 2 | task 2263 | graphs reused = 1737 1.41.363.251 I slot print_timing: id 2 | task 2263 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.363.302 I slot release: id 2 | task 2263 | stop processing: n_tokens = 1342, truncated = 0 1.41.395.125 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.854 1.41.395.228 I slot launch_slot_: id 2 | task 2372 | processing task, is_child = 0 1.41.553.637 I slot print_timing: id 3 | task 2250 | prompt eval time = 117.89 ms / 97 tokens ( 1.22 ms per token, 822.80 tokens per second) 1.41.553.643 I slot print_timing: id 3 | task 2250 | eval time = 2253.34 ms / 120 tokens ( 18.94 ms per token, 52.81 tokens per second) 1.41.553.645 I slot print_timing: id 3 | task 2250 | total time = 2371.23 ms / 217 tokens 1.41.553.645 I slot print_timing: id 3 | task 2250 | graphs reused = 1737 1.41.553.646 I slot print_timing: id 3 | task 2250 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.553.697 I slot release: id 3 | task 2250 | stop processing: n_tokens = 1341, truncated = 0 1.41.589.587 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.855 1.41.589.694 I slot launch_slot_: id 3 | task 2377 | processing task, is_child = 0 1.41.903.257 I slot print_timing: id 0 | task 2273 | prompt eval time = 117.53 ms / 119 tokens ( 0.99 ms per token, 1012.54 tokens per second) 1.41.903.263 I slot print_timing: id 0 | task 2273 | eval time = 2041.91 ms / 115 tokens ( 17.91 ms per token, 55.83 tokens per second) 1.41.903.264 I slot print_timing: id 0 | task 2273 | total time = 2159.43 ms / 234 tokens 1.41.903.264 I slot print_timing: id 0 | task 2273 | graphs reused = 1749 1.41.903.265 I slot print_timing: id 0 | task 2273 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.903.315 I slot release: id 0 | task 2273 | stop processing: n_tokens = 1358, truncated = 0 1.41.939.636 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.845 1.41.939.747 I slot launch_slot_: id 0 | task 2394 | processing task, is_child = 0 1.42.073.049 I slot print_timing: id 1 | task 2240 | n_gen = 150, tg = 49.53 t/s, tg_3s = 49.86 t/s 1.42.264.847 I slot print_timing: id 1 | task 2240 | prompt eval time = 148.27 ms / 109 tokens ( 1.36 ms per token, 735.16 tokens per second) 1.42.264.854 I slot print_timing: id 1 | task 2240 | eval time = 3200.22 ms / 162 tokens ( 19.88 ms per token, 50.31 tokens per second) 1.42.264.855 I slot print_timing: id 1 | task 2240 | total time = 3348.49 ms / 271 tokens 1.42.264.855 I slot print_timing: id 1 | task 2240 | graphs reused = 1763 1.42.264.856 I slot print_timing: id 1 | task 2240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.264.905 I slot release: id 1 | task 2240 | stop processing: n_tokens = 1395, truncated = 0 1.42.328.654 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.822 1.42.328.764 I slot launch_slot_: id 1 | task 2412 | processing task, is_child = 0 1.43.014.558 I slot print_timing: id 0 | task 2394 | prompt eval time = 114.14 ms / 109 tokens ( 1.05 ms per token, 954.93 tokens per second) 1.43.014.563 I slot print_timing: id 0 | task 2394 | eval time = 960.65 ms / 52 tokens ( 18.84 ms per token, 53.09 tokens per second) 1.43.014.564 I slot print_timing: id 0 | task 2394 | total time = 1074.79 ms / 161 tokens 1.43.014.565 I slot print_timing: id 0 | task 2394 | graphs reused = 1796 1.43.014.566 I slot print_timing: id 0 | task 2394 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.014.614 I slot release: id 0 | task 2394 | stop processing: n_tokens = 1285, truncated = 0 1.43.051.366 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.892 1.43.051.493 I slot launch_slot_: id 0 | task 2451 | processing task, is_child = 0 1.43.719.694 I slot print_timing: id 1 | task 2412 | prompt eval time = 145.55 ms / 95 tokens ( 1.53 ms per token, 652.69 tokens per second) 1.43.719.700 I slot print_timing: id 1 | task 2412 | eval time = 1245.36 ms / 74 tokens ( 17.06 ms per token, 58.62 tokens per second) 1.43.719.701 I slot print_timing: id 1 | task 2412 | total time = 1390.91 ms / 169 tokens 1.43.719.702 I slot print_timing: id 1 | task 2412 | graphs reused = 1832 1.43.719.702 I slot print_timing: id 1 | task 2412 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.719.750 I slot release: id 1 | task 2412 | stop processing: n_tokens = 1293, truncated = 0 1.43.751.728 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.886 1.43.751.834 I slot launch_slot_: id 1 | task 2490 | processing task, is_child = 0 1.43.958.050 I slot print_timing: id 3 | task 2377 | prompt eval time = 120.00 ms / 112 tokens ( 1.07 ms per token, 933.34 tokens per second) 1.43.958.056 I slot print_timing: id 3 | task 2377 | eval time = 2248.34 ms / 113 tokens ( 20.07 ms per token, 49.81 tokens per second) 1.43.958.057 I slot print_timing: id 3 | task 2377 | total time = 2368.34 ms / 225 tokens 1.43.958.058 I slot print_timing: id 3 | task 2377 | graphs reused = 1834 1.43.958.058 I slot print_timing: id 3 | task 2377 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.958.109 I slot release: id 3 | task 2377 | stop processing: n_tokens = 1349, truncated = 0 1.43.994.374 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.850 1.43.994.479 I slot launch_slot_: id 3 | task 2498 | processing task, is_child = 0 1.44.423.216 I slot print_timing: id 2 | task 2372 | prompt eval time = 158.14 ms / 134 tokens ( 1.18 ms per token, 847.37 tokens per second) 1.44.423.222 I slot print_timing: id 2 | task 2372 | eval time = 2869.83 ms / 139 tokens ( 20.80 ms per token, 48.09 tokens per second) 1.44.423.223 I slot print_timing: id 2 | task 2372 | total time = 3027.97 ms / 273 tokens 1.44.423.224 I slot print_timing: id 2 | task 2372 | graphs reused = 1852 1.44.423.225 I slot print_timing: id 2 | task 2372 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.423.278 I slot release: id 2 | task 2372 | stop processing: n_tokens = 1397, truncated = 0 1.44.455.234 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.820 1.44.455.335 I slot launch_slot_: id 2 | task 2520 | processing task, is_child = 0 1.45.143.553 I slot print_timing: id 0 | task 2451 | prompt eval time = 111.75 ms / 96 tokens ( 1.16 ms per token, 859.10 tokens per second) 1.45.143.559 I slot print_timing: id 0 | task 2451 | eval time = 1980.30 ms / 101 tokens ( 19.80 ms per token, 50.50 tokens per second) 1.45.143.560 I slot print_timing: id 0 | task 2451 | total time = 2092.04 ms / 197 tokens 1.45.143.562 I slot print_timing: id 0 | task 2451 | graphs reused = 1885 1.45.143.562 I slot print_timing: id 0 | task 2451 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.143.611 I slot release: id 0 | task 2451 | stop processing: n_tokens = 1321, truncated = 0 1.45.179.965 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.868 1.45.180.089 I slot launch_slot_: id 0 | task 2559 | processing task, is_child = 0 1.45.914.594 I slot print_timing: id 3 | task 2498 | prompt eval time = 139.74 ms / 166 tokens ( 0.84 ms per token, 1187.93 tokens per second) 1.45.914.600 I slot print_timing: id 3 | task 2498 | eval time = 1780.36 ms / 99 tokens ( 18.17 ms per token, 55.05 tokens per second) 1.45.914.601 I slot print_timing: id 3 | task 2498 | total time = 1920.10 ms / 265 tokens 1.45.914.603 I slot print_timing: id 3 | task 2498 | graphs reused = 1925 1.45.914.604 I slot print_timing: id 3 | task 2498 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.914.658 I slot release: id 3 | task 2498 | stop processing: n_tokens = 1389, truncated = 0 1.45.950.514 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.825 1.45.950.615 I slot launch_slot_: id 3 | task 2603 | processing task, is_child = 0 1.46.616.435 I slot print_timing: id 1 | task 2490 | prompt eval time = 153.24 ms / 122 tokens ( 1.26 ms per token, 796.14 tokens per second) 1.46.616.441 I slot print_timing: id 1 | task 2490 | eval time = 2711.35 ms / 144 tokens ( 18.96 ms per token, 52.74 tokens per second) 1.46.616.442 I slot print_timing: id 1 | task 2490 | total time = 2864.59 ms / 266 tokens 1.46.616.442 I slot print_timing: id 1 | task 2490 | graphs reused = 1959 1.46.616.443 I slot print_timing: id 1 | task 2490 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.616.493 I slot release: id 1 | task 2490 | stop processing: n_tokens = 1390, truncated = 0 1.46.648.542 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.824 1.46.648.648 I slot launch_slot_: id 1 | task 2641 | processing task, is_child = 0 1.47.072.276 I slot print_timing: id 2 | task 2520 | prompt eval time = 148.76 ms / 117 tokens ( 1.27 ms per token, 786.52 tokens per second) 1.47.072.281 I slot print_timing: id 2 | task 2520 | eval time = 2468.17 ms / 136 tokens ( 18.28 ms per token, 54.70 tokens per second) 1.47.072.282 I slot print_timing: id 2 | task 2520 | total time = 2616.93 ms / 253 tokens 1.47.072.283 I slot print_timing: id 2 | task 2520 | graphs reused = 1975 1.47.072.284 I slot print_timing: id 2 | task 2520 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.072.334 I slot release: id 2 | task 2520 | stop processing: n_tokens = 1377, truncated = 0 1.47.103.857 I slot print_timing: id 0 | task 2559 | prompt eval time = 113.74 ms / 104 tokens ( 1.09 ms per token, 914.35 tokens per second) 1.47.103.865 I slot print_timing: id 0 | task 2559 | eval time = 1810.01 ms / 99 tokens ( 18.47 ms per token, 54.14 tokens per second) 1.47.103.866 I slot print_timing: id 0 | task 2559 | total time = 1923.75 ms / 203 tokens 1.47.103.867 I slot print_timing: id 0 | task 2559 | graphs reused = 1975 1.47.103.868 I slot print_timing: id 0 | task 2559 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.103.922 I slot release: id 0 | task 2559 | stop processing: n_tokens = 1327, truncated = 0 1.47.104.646 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.864 1.47.104.771 I slot launch_slot_: id 0 | task 2662 | processing task, is_child = 0 1.47.104.892 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.754 MiB) 1.47.106.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 1.47.108.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.505 MiB) 1.47.157.512 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.832 1.47.157.617 I slot launch_slot_: id 2 | task 2663 | processing task, is_child = 0 1.48.747.187 I slot print_timing: id 3 | task 2603 | prompt eval time = 121.25 ms / 108 tokens ( 1.12 ms per token, 890.76 tokens per second) 1.48.747.192 I slot print_timing: id 3 | task 2603 | eval time = 2675.31 ms / 144 tokens ( 18.71 ms per token, 53.45 tokens per second) 1.48.747.193 I slot print_timing: id 3 | task 2603 | total time = 2796.56 ms / 252 tokens 1.48.747.194 I slot print_timing: id 3 | task 2603 | graphs reused = 2060 1.48.747.195 I slot print_timing: id 3 | task 2603 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.747.244 I slot release: id 3 | task 2603 | stop processing: n_tokens = 1376, truncated = 0 1.48.783.223 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.833 1.48.783.325 I slot launch_slot_: id 3 | task 2754 | processing task, is_child = 0 1.48.989.763 I slot print_timing: id 2 | task 2663 | prompt eval time = 206.73 ms / 116 tokens ( 1.78 ms per token, 561.11 tokens per second) 1.48.989.769 I slot print_timing: id 2 | task 2663 | eval time = 1605.83 ms / 96 tokens ( 16.90 ms per token, 59.16 tokens per second) 1.48.989.770 I slot print_timing: id 2 | task 2663 | total time = 1812.56 ms / 212 tokens 1.48.989.771 I slot print_timing: id 2 | task 2663 | graphs reused = 2065 1.48.989.771 I slot print_timing: id 2 | task 2663 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.989.820 I slot release: id 2 | task 2663 | stop processing: n_tokens = 1336, truncated = 0 1.49.021.074 I slot print_timing: id 0 | task 2662 | prompt eval time = 225.46 ms / 112 tokens ( 2.01 ms per token, 496.77 tokens per second) 1.49.021.080 I slot print_timing: id 0 | task 2662 | eval time = 1637.98 ms / 97 tokens ( 17.06 ms per token, 58.61 tokens per second) 1.49.021.081 I slot print_timing: id 0 | task 2662 | total time = 1863.44 ms / 209 tokens 1.49.021.082 I slot print_timing: id 0 | task 2662 | graphs reused = 2065 1.49.021.083 I slot print_timing: id 0 | task 2662 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.021.136 I slot release: id 0 | task 2662 | stop processing: n_tokens = 1333, truncated = 0 1.49.051.587 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.860 1.49.051.690 I slot launch_slot_: id 0 | task 2764 | processing task, is_child = 0 1.49.051.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.723 MiB) 1.49.053.398 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.754 MiB) 1.49.115.787 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.858 1.49.115.915 I slot launch_slot_: id 2 | task 2765 | processing task, is_child = 0 1.49.569.514 I slot print_timing: id 1 | task 2641 | prompt eval time = 150.81 ms / 133 tokens ( 1.13 ms per token, 881.88 tokens per second) 1.49.569.520 I slot print_timing: id 1 | task 2641 | eval time = 2770.04 ms / 134 tokens ( 20.83 ms per token, 48.01 tokens per second) 1.49.569.521 I slot print_timing: id 1 | task 2641 | total time = 2920.85 ms / 267 tokens 1.49.569.522 I slot print_timing: id 1 | task 2641 | graphs reused = 2078 1.49.569.522 I slot print_timing: id 1 | task 2641 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.569.575 I slot release: id 1 | task 2641 | stop processing: n_tokens = 1391, truncated = 0 1.49.601.501 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.824 1.49.601.613 I slot launch_slot_: id 1 | task 2783 | processing task, is_child = 0 1.50.686.206 I slot print_timing: id 1 | task 2783 | prompt eval time = 150.09 ms / 120 tokens ( 1.25 ms per token, 799.50 tokens per second) 1.50.686.211 I slot print_timing: id 1 | task 2783 | eval time = 934.48 ms / 60 tokens ( 15.84 ms per token, 63.14 tokens per second) 1.50.686.213 I slot print_timing: id 1 | task 2783 | total time = 1084.58 ms / 180 tokens 1.50.686.213 I slot print_timing: id 1 | task 2783 | graphs reused = 2135 1.50.686.214 I slot print_timing: id 1 | task 2783 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.686.266 I slot release: id 1 | task 2783 | stop processing: n_tokens = 1304, truncated = 0 1.50.718.164 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.879 1.50.718.266 I slot launch_slot_: id 1 | task 2846 | processing task, is_child = 0 1.50.965.482 I slot print_timing: id 2 | task 2765 | prompt eval time = 209.49 ms / 103 tokens ( 2.03 ms per token, 491.67 tokens per second) 1.50.965.487 I slot print_timing: id 2 | task 2765 | eval time = 1620.37 ms / 86 tokens ( 19.06 ms per token, 52.46 tokens per second) 1.50.965.489 I slot print_timing: id 2 | task 2765 | total time = 1829.86 ms / 189 tokens 1.50.965.489 I slot print_timing: id 2 | task 2765 | graphs reused = 2140 1.50.965.490 I slot print_timing: id 2 | task 2765 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.965.538 I slot release: id 2 | task 2765 | stop processing: n_tokens = 1313, truncated = 0 1.50.997.247 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.873 1.50.997.350 I slot launch_slot_: id 2 | task 2856 | processing task, is_child = 0 1.51.350.395 I slot print_timing: id 3 | task 2754 | prompt eval time = 123.00 ms / 119 tokens ( 1.03 ms per token, 967.46 tokens per second) 1.51.350.400 I slot print_timing: id 3 | task 2754 | eval time = 2444.05 ms / 111 tokens ( 22.22 ms per token, 45.01 tokens per second) 1.51.350.401 I slot print_timing: id 3 | task 2754 | total time = 2567.05 ms / 230 tokens 1.51.350.401 I slot print_timing: id 3 | task 2754 | graphs reused = 2152 1.51.350.402 I slot print_timing: id 3 | task 2754 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.350.452 I slot release: id 3 | task 2754 | stop processing: n_tokens = 1354, truncated = 0 1.51.386.208 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.846 1.51.386.315 I slot launch_slot_: id 3 | task 2874 | processing task, is_child = 0 1.51.538.301 I slot print_timing: id 0 | task 2764 | prompt eval time = 228.36 ms / 119 tokens ( 1.92 ms per token, 521.11 tokens per second) 1.51.538.307 I slot print_timing: id 0 | task 2764 | eval time = 2194.01 ms / 108 tokens ( 20.50 ms per token, 48.77 tokens per second) 1.51.538.308 I slot print_timing: id 0 | task 2764 | total time = 2422.37 ms / 227 tokens 1.51.538.308 I slot print_timing: id 0 | task 2764 | graphs reused = 2154 1.51.538.310 I slot print_timing: id 0 | task 2764 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.538.361 I slot release: id 0 | task 2764 | stop processing: n_tokens = 1351, truncated = 0 1.51.575.119 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.848 1.51.575.234 I slot launch_slot_: id 0 | task 2881 | processing task, is_child = 0 1.52.454.663 I slot print_timing: id 2 | task 2856 | prompt eval time = 144.62 ms / 97 tokens ( 1.49 ms per token, 670.73 tokens per second) 1.52.454.669 I slot print_timing: id 2 | task 2856 | eval time = 1312.68 ms / 71 tokens ( 18.75 ms per token, 53.33 tokens per second) 1.52.454.670 I slot print_timing: id 2 | task 2856 | total time = 1457.30 ms / 168 tokens 1.52.454.671 I slot print_timing: id 2 | task 2856 | graphs reused = 2202 1.52.454.671 I slot print_timing: id 2 | task 2856 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.454.721 I slot release: id 2 | task 2856 | stop processing: n_tokens = 1292, truncated = 0 1.52.486.477 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.887 1.52.486.584 I slot launch_slot_: id 2 | task 2932 | processing task, is_child = 0 1.52.798.808 I slot print_timing: id 1 | task 2846 | prompt eval time = 147.55 ms / 108 tokens ( 1.37 ms per token, 731.95 tokens per second) 1.52.798.813 I slot print_timing: id 1 | task 2846 | eval time = 1932.98 ms / 93 tokens ( 21.01 ms per token, 47.60 tokens per second) 1.52.798.814 I slot print_timing: id 1 | task 2846 | total time = 2080.53 ms / 201 tokens 1.52.798.815 I slot print_timing: id 1 | task 2846 | graphs reused = 2211 1.52.798.815 I slot print_timing: id 1 | task 2846 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.798.864 I slot release: id 1 | task 2846 | stop processing: n_tokens = 1325, truncated = 0 1.52.830.887 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.865 1.52.830.999 I slot launch_slot_: id 1 | task 2946 | processing task, is_child = 0 1.53.047.383 I slot print_timing: id 3 | task 2874 | prompt eval time = 116.14 ms / 100 tokens ( 1.16 ms per token, 861.03 tokens per second) 1.53.047.388 I slot print_timing: id 3 | task 2874 | eval time = 1544.91 ms / 74 tokens ( 21.16 ms per token, 47.25 tokens per second) 1.53.047.389 I slot print_timing: id 3 | task 2874 | total time = 1661.05 ms / 174 tokens 1.53.047.390 I slot print_timing: id 3 | task 2874 | graphs reused = 2214 1.53.047.391 I slot print_timing: id 3 | task 2874 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.047.440 I slot release: id 3 | task 2874 | stop processing: n_tokens = 1298, truncated = 0 1.53.083.355 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.883 1.53.083.462 I slot launch_slot_: id 3 | task 2955 | processing task, is_child = 0 1.54.186.319 I slot print_timing: id 3 | task 2955 | prompt eval time = 121.23 ms / 104 tokens ( 1.17 ms per token, 857.84 tokens per second) 1.54.186.324 I slot print_timing: id 3 | task 2955 | eval time = 981.61 ms / 63 tokens ( 15.83 ms per token, 63.16 tokens per second) 1.54.186.325 I slot print_timing: id 3 | task 2955 | total time = 1102.84 ms / 167 tokens 1.54.186.327 I slot print_timing: id 3 | task 2955 | graphs reused = 2276 1.54.186.328 I slot print_timing: id 3 | task 2955 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.186.376 I slot release: id 3 | task 2955 | stop processing: n_tokens = 1291, truncated = 0 1.54.222.602 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.888 1.54.222.711 I slot launch_slot_: id 3 | task 3022 | processing task, is_child = 0 1.54.616.463 I slot print_timing: id 1 | task 2946 | prompt eval time = 147.69 ms / 114 tokens ( 1.30 ms per token, 771.88 tokens per second) 1.54.616.468 I slot print_timing: id 1 | task 2946 | eval time = 1637.76 ms / 92 tokens ( 18.00 ms per token, 55.56 tokens per second) 1.54.616.470 I slot print_timing: id 1 | task 2946 | total time = 1785.45 ms / 206 tokens 1.54.616.470 I slot print_timing: id 1 | task 2946 | graphs reused = 2293 1.54.616.471 I slot print_timing: id 1 | task 2946 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.616.526 I slot release: id 1 | task 2946 | stop processing: n_tokens = 1330, truncated = 0 1.54.649.152 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.862 1.54.649.273 I slot launch_slot_: id 1 | task 3043 | processing task, is_child = 0 1.54.732.832 I slot print_timing: id 0 | task 2881 | n_gen = 157, tg = 51.59 t/s, tg_3s = 51.92 t/s 1.54.861.956 I slot print_timing: id 0 | task 2881 | prompt eval time = 133.98 ms / 172 tokens ( 0.78 ms per token, 1283.79 tokens per second) 1.54.861.961 I slot print_timing: id 0 | task 2881 | eval time = 3152.73 ms / 162 tokens ( 19.58 ms per token, 51.07 tokens per second) 1.54.861.962 I slot print_timing: id 0 | task 2881 | total time = 3286.70 ms / 334 tokens 1.54.861.963 I slot print_timing: id 0 | task 2881 | graphs reused = 2296 1.54.861.964 I slot print_timing: id 0 | task 2881 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.862.018 I slot release: id 0 | task 2881 | stop processing: n_tokens = 1458, truncated = 0 1.54.898.728 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.786 1.54.898.840 I slot launch_slot_: id 0 | task 3052 | processing task, is_child = 0 1.55.642.958 I slot print_timing: id 2 | task 2932 | n_gen = 155, tg = 51.23 t/s, tg_3s = 51.56 t/s 1.55.865.973 I slot print_timing: id 2 | task 2932 | prompt eval time = 150.39 ms / 119 tokens ( 1.26 ms per token, 791.27 tokens per second) 1.55.865.978 I slot print_timing: id 2 | task 2932 | eval time = 3228.98 ms / 169 tokens ( 19.22 ms per token, 52.03 tokens per second) 1.55.865.979 I slot print_timing: id 2 | task 2932 | total time = 3379.37 ms / 288 tokens 1.55.865.980 I slot print_timing: id 2 | task 2932 | graphs reused = 2350 1.55.865.981 I slot print_timing: id 2 | task 2932 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.866.031 I slot release: id 2 | task 2932 | stop processing: n_tokens = 1412, truncated = 0 1.55.929.464 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.812 1.55.929.573 I slot launch_slot_: id 2 | task 3110 | processing task, is_child = 0 1.56.237.475 I slot print_timing: id 3 | task 3022 | prompt eval time = 121.38 ms / 117 tokens ( 1.04 ms per token, 963.88 tokens per second) 1.56.237.481 I slot print_timing: id 3 | task 3022 | eval time = 1893.37 ms / 96 tokens ( 19.93 ms per token, 50.18 tokens per second) 1.56.237.482 I slot print_timing: id 3 | task 3022 | total time = 2014.75 ms / 213 tokens 1.56.237.483 I slot print_timing: id 3 | task 3022 | graphs reused = 2359 1.56.237.484 I slot print_timing: id 3 | task 3022 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.237.535 I slot release: id 3 | task 3022 | stop processing: n_tokens = 1337, truncated = 0 1.56.273.566 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.857 1.56.273.674 I slot launch_slot_: id 3 | task 3125 | processing task, is_child = 0 1.56.407.618 I slot print_timing: id 1 | task 3043 | prompt eval time = 144.52 ms / 88 tokens ( 1.64 ms per token, 608.90 tokens per second) 1.56.407.625 I slot print_timing: id 1 | task 3043 | eval time = 1613.81 ms / 80 tokens ( 20.43 ms per token, 48.95 tokens per second) 1.56.407.626 I slot print_timing: id 1 | task 3043 | total time = 1758.33 ms / 168 tokens 1.56.407.627 I slot print_timing: id 1 | task 3043 | graphs reused = 2360 1.56.407.628 I slot print_timing: id 1 | task 3043 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.407.678 I slot release: id 1 | task 3043 | stop processing: n_tokens = 1292, truncated = 0 1.56.440.513 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.887 1.56.440.626 I slot launch_slot_: id 1 | task 3129 | processing task, is_child = 0 1.56.661.328 I slot print_timing: id 0 | task 3052 | prompt eval time = 117.68 ms / 129 tokens ( 0.91 ms per token, 1096.23 tokens per second) 1.56.661.335 I slot print_timing: id 0 | task 3052 | eval time = 1644.79 ms / 79 tokens ( 21.09 ms per token, 47.42 tokens per second) 1.56.661.336 I slot print_timing: id 0 | task 3052 | total time = 1762.47 ms / 208 tokens 1.56.661.336 I slot print_timing: id 0 | task 3052 | graphs reused = 2363 1.56.661.338 I slot print_timing: id 0 | task 3052 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.661.392 I slot release: id 0 | task 3052 | stop processing: n_tokens = 1332, truncated = 0 1.56.698.265 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.860 1.56.698.376 I slot launch_slot_: id 0 | task 3138 | processing task, is_child = 0 1.57.545.425 I slot print_timing: id 2 | task 3110 | prompt eval time = 143.64 ms / 87 tokens ( 1.65 ms per token, 605.68 tokens per second) 1.57.545.431 I slot print_timing: id 2 | task 3110 | eval time = 1472.20 ms / 72 tokens ( 20.74 ms per token, 48.23 tokens per second) 1.57.545.432 I slot print_timing: id 2 | task 3110 | total time = 1615.84 ms / 159 tokens 1.57.545.433 I slot print_timing: id 2 | task 3110 | graphs reused = 2410 1.57.545.434 I slot print_timing: id 2 | task 3110 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.545.481 I slot release: id 2 | task 3110 | stop processing: n_tokens = 1283, truncated = 0 1.57.577.381 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.893 1.57.577.491 I slot launch_slot_: id 2 | task 3188 | processing task, is_child = 0 1.58.626.563 I slot print_timing: id 1 | task 3129 | prompt eval time = 151.06 ms / 118 tokens ( 1.28 ms per token, 781.15 tokens per second) 1.58.626.569 I slot print_timing: id 1 | task 3129 | eval time = 2034.86 ms / 114 tokens ( 18.01 ms per token, 55.53 tokens per second) 1.58.626.570 I slot print_timing: id 1 | task 3129 | total time = 2185.92 ms / 232 tokens 1.58.626.571 I slot print_timing: id 1 | task 3129 | graphs reused = 2465 1.58.626.571 I slot print_timing: id 1 | task 3129 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.626.621 I slot release: id 1 | task 3129 | stop processing: n_tokens = 1356, truncated = 0 1.58.658.663 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.845 1.58.658.845 I slot launch_slot_: id 1 | task 3248 | processing task, is_child = 0 1.58.875.499 I slot print_timing: id 3 | task 3125 | prompt eval time = 134.94 ms / 152 tokens ( 0.89 ms per token, 1126.43 tokens per second) 1.58.875.505 I slot print_timing: id 3 | task 3125 | eval time = 2466.87 ms / 124 tokens ( 20.06 ms per token, 49.86 tokens per second) 1.58.875.506 I slot print_timing: id 3 | task 3125 | total time = 2601.81 ms / 276 tokens 1.58.875.507 I slot print_timing: id 3 | task 3125 | graphs reused = 2468 1.58.875.508 I slot print_timing: id 3 | task 3125 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.875.559 I slot release: id 3 | task 3125 | stop processing: n_tokens = 1400, truncated = 0 1.58.911.537 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.819 1.58.911.652 I slot launch_slot_: id 3 | task 3257 | processing task, is_child = 0 1.59.119.740 I slot print_timing: id 2 | task 3188 | prompt eval time = 159.78 ms / 135 tokens ( 1.18 ms per token, 844.89 tokens per second) 1.59.119.746 I slot print_timing: id 2 | task 3188 | eval time = 1382.45 ms / 73 tokens ( 19.20 ms per token, 52.08 tokens per second) 1.59.119.748 I slot print_timing: id 2 | task 3188 | total time = 1542.24 ms / 208 tokens 1.59.119.748 I slot print_timing: id 2 | task 3188 | graphs reused = 2473 1.59.119.749 I slot print_timing: id 2 | task 3188 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.119.799 I slot release: id 2 | task 3188 | stop processing: n_tokens = 1332, truncated = 0 1.59.151.801 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.860 1.59.151.916 I slot launch_slot_: id 2 | task 3266 | processing task, is_child = 0 1.59.782.158 I slot print_timing: id 0 | task 3138 | prompt eval time = 114.45 ms / 110 tokens ( 1.04 ms per token, 961.08 tokens per second) 1.59.782.165 I slot print_timing: id 0 | task 3138 | eval time = 2969.31 ms / 155 tokens ( 19.28 ms per token, 51.86 tokens per second) 1.59.782.166 I slot print_timing: id 0 | task 3138 | total time = 3083.76 ms / 265 tokens 1.59.782.167 I slot print_timing: id 0 | task 3138 | graphs reused = 2502 1.59.782.168 I slot print_timing: id 0 | task 3138 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.782.218 I slot release: id 0 | task 3138 | stop processing: n_tokens = 1389, truncated = 0 1.59.818.732 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.825 1.59.818.846 I slot launch_slot_: id 0 | task 3301 | processing task, is_child = 0 2.00.378.614 I slot print_timing: id 1 | task 3248 | prompt eval time = 147.80 ms / 92 tokens ( 1.61 ms per token, 622.48 tokens per second) 2.00.378.620 I slot print_timing: id 1 | task 3248 | eval time = 1571.96 ms / 79 tokens ( 20.15 ms per token, 49.62 tokens per second) 2.00.378.621 I slot print_timing: id 1 | task 3248 | total time = 1719.75 ms / 171 tokens 2.00.378.621 I slot print_timing: id 1 | task 3248 | graphs reused = 2531 2.00.378.622 I slot print_timing: id 1 | task 3248 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.378.669 I slot release: id 1 | task 3248 | stop processing: n_tokens = 1295, truncated = 0 2.00.442.270 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.885 2.00.442.397 I slot launch_slot_: id 1 | task 3334 | processing task, is_child = 0 2.01.177.669 I slot print_timing: id 3 | task 3257 | prompt eval time = 124.02 ms / 120 tokens ( 1.03 ms per token, 967.61 tokens per second) 2.01.177.674 I slot print_timing: id 3 | task 3257 | eval time = 2141.98 ms / 112 tokens ( 19.30 ms per token, 51.82 tokens per second) 2.01.177.676 I slot print_timing: id 3 | task 3257 | total time = 2266.00 ms / 232 tokens 2.01.177.676 I slot print_timing: id 3 | task 3257 | graphs reused = 2567 2.01.177.677 I slot print_timing: id 3 | task 3257 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.177.728 I slot release: id 3 | task 3257 | stop processing: n_tokens = 1356, truncated = 0 2.01.213.934 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.845 2.01.214.037 I slot launch_slot_: id 3 | task 3376 | processing task, is_child = 0 2.01.925.165 I slot print_timing: id 1 | task 3334 | prompt eval time = 143.91 ms / 98 tokens ( 1.47 ms per token, 680.96 tokens per second) 2.01.925.172 I slot print_timing: id 1 | task 3334 | eval time = 1338.84 ms / 79 tokens ( 17.16 ms per token, 58.26 tokens per second) 2.01.925.173 I slot print_timing: id 1 | task 3334 | total time = 1482.75 ms / 177 tokens 2.01.925.174 I slot print_timing: id 1 | task 3334 | graphs reused = 2604 2.01.925.175 I slot print_timing: id 1 | task 3334 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.925.225 I slot release: id 1 | task 3334 | stop processing: n_tokens = 1301, truncated = 0 2.01.988.717 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.881 2.01.988.834 I slot launch_slot_: id 1 | task 3418 | processing task, is_child = 0 2.02.303.719 I slot print_timing: id 2 | task 3266 | n_gen = 159, tg = 52.67 t/s, tg_3s = 53.00 t/s 2.02.871.256 I slot print_timing: id 2 | task 3266 | prompt eval time = 151.69 ms / 131 tokens ( 1.16 ms per token, 863.58 tokens per second) 2.02.871.261 I slot print_timing: id 2 | task 3266 | eval time = 3567.63 ms / 195 tokens ( 18.39 ms per token, 54.38 tokens per second) 2.02.871.263 I slot print_timing: id 2 | task 3266 | total time = 3719.32 ms / 326 tokens 2.02.871.263 I slot print_timing: id 2 | task 3266 | graphs reused = 2649 2.02.871.264 I slot print_timing: id 2 | task 3266 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.871.312 I slot release: id 2 | task 3266 | stop processing: n_tokens = 1450, truncated = 0 2.02.903.189 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.790 2.02.903.290 I slot launch_slot_: id 2 | task 3468 | processing task, is_child = 0 2.02.989.293 I slot print_timing: id 0 | task 3301 | n_gen = 163, tg = 52.96 t/s, tg_3s = 53.29 t/s 2.03.386.680 I slot print_timing: id 3 | task 3376 | prompt eval time = 121.20 ms / 116 tokens ( 1.04 ms per token, 957.09 tokens per second) 2.03.386.687 I slot print_timing: id 3 | task 3376 | eval time = 2051.43 ms / 112 tokens ( 18.48 ms per token, 54.11 tokens per second) 2.03.386.688 I slot print_timing: id 3 | task 3376 | total time = 2172.63 ms / 228 tokens 2.03.386.689 I slot print_timing: id 3 | task 3376 | graphs reused = 2669 2.03.386.689 I slot print_timing: id 3 | task 3376 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.386.739 I slot release: id 3 | task 3376 | stop processing: n_tokens = 1352, truncated = 0 2.03.423.039 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.848 2.03.423.147 I slot launch_slot_: id 3 | task 3494 | processing task, is_child = 0 2.03.628.587 I slot print_timing: id 0 | task 3301 | prompt eval time = 111.52 ms / 95 tokens ( 1.17 ms per token, 851.88 tokens per second) 2.03.628.592 I slot print_timing: id 0 | task 3301 | eval time = 3698.21 ms / 194 tokens ( 19.16 ms per token, 52.19 tokens per second) 2.03.628.593 I slot print_timing: id 0 | task 3301 | total time = 3809.72 ms / 289 tokens 2.03.628.594 I slot print_timing: id 0 | task 3301 | graphs reused = 2674 2.03.628.594 I slot print_timing: id 0 | task 3301 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.628.641 I slot release: id 0 | task 3301 | stop processing: n_tokens = 1413, truncated = 0 2.03.647.238 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.811 2.03.647.341 I slot launch_slot_: id 0 | task 3503 | processing task, is_child = 0 2.04.669.147 I slot print_timing: id 1 | task 3418 | prompt eval time = 151.27 ms / 130 tokens ( 1.16 ms per token, 859.41 tokens per second) 2.04.669.153 I slot print_timing: id 1 | task 3418 | eval time = 2529.03 ms / 139 tokens ( 18.33 ms per token, 54.57 tokens per second) 2.04.669.154 I slot print_timing: id 1 | task 3418 | total time = 2680.30 ms / 269 tokens 2.04.669.155 I slot print_timing: id 1 | task 3418 | graphs reused = 2730 2.04.669.156 I slot print_timing: id 1 | task 3418 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.669.207 I slot release: id 1 | task 3418 | stop processing: n_tokens = 1393, truncated = 0 2.04.733.590 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.823 2.04.733.796 I slot launch_slot_: id 1 | task 3564 | processing task, is_child = 0 2.05.360.110 I slot print_timing: id 2 | task 3468 | prompt eval time = 146.59 ms / 103 tokens ( 1.42 ms per token, 702.66 tokens per second) 2.05.360.116 I slot print_timing: id 2 | task 3468 | eval time = 2310.22 ms / 122 tokens ( 19.09 ms per token, 52.38 tokens per second) 2.05.360.117 I slot print_timing: id 2 | task 3468 | total time = 2456.80 ms / 225 tokens 2.05.360.118 I slot print_timing: id 2 | task 3468 | graphs reused = 2757 2.05.360.119 I slot print_timing: id 2 | task 3468 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.360.171 I slot release: id 2 | task 3468 | stop processing: n_tokens = 1349, truncated = 0 2.05.393.222 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.850 2.05.393.333 I slot launch_slot_: id 2 | task 3596 | processing task, is_child = 0 2.06.554.708 I slot print_timing: id 3 | task 3494 | n_gen = 161, tg = 53.16 t/s, tg_3s = 53.50 t/s 2.06.585.516 I slot print_timing: id 0 | task 3503 | prompt eval time = 130.00 ms / 133 tokens ( 0.98 ms per token, 1023.04 tokens per second) 2.06.585.521 I slot print_timing: id 0 | task 3503 | eval time = 2808.16 ms / 155 tokens ( 18.23 ms per token, 54.84 tokens per second) 2.06.585.522 I slot print_timing: id 0 | task 3503 | total time = 2938.16 ms / 288 tokens 2.06.585.522 I slot print_timing: id 0 | task 3503 | graphs reused = 2819 2.06.585.523 I slot print_timing: id 0 | task 3503 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.585.573 I slot release: id 0 | task 3503 | stop processing: n_tokens = 1412, truncated = 0 2.06.622.492 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.812 2.06.622.605 I slot launch_slot_: id 0 | task 3664 | processing task, is_child = 0 2.06.755.774 I slot print_timing: id 1 | task 3564 | prompt eval time = 157.10 ms / 123 tokens ( 1.28 ms per token, 782.92 tokens per second) 2.06.755.780 I slot print_timing: id 1 | task 3564 | eval time = 1864.86 ms / 100 tokens ( 18.84 ms per token, 53.09 tokens per second) 2.06.755.781 I slot print_timing: id 1 | task 3564 | total time = 2021.96 ms / 223 tokens 2.06.755.782 I slot print_timing: id 1 | task 3564 | graphs reused = 2821 2.06.755.783 I slot print_timing: id 1 | task 3564 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.755.835 I slot release: id 1 | task 3564 | stop processing: n_tokens = 1347, truncated = 0 2.06.787.778 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.851 2.06.787.890 I slot launch_slot_: id 1 | task 3669 | processing task, is_child = 0 2.07.742.704 I slot print_timing: id 3 | task 3494 | prompt eval time = 121.96 ms / 122 tokens ( 1.00 ms per token, 1000.30 tokens per second) 2.07.742.710 I slot print_timing: id 3 | task 3494 | eval time = 4197.58 ms / 222 tokens ( 18.99 ms per token, 52.65 tokens per second) 2.07.742.711 I slot print_timing: id 3 | task 3494 | total time = 4319.54 ms / 344 tokens 2.07.742.712 I slot print_timing: id 3 | task 3494 | graphs reused = 2871 2.07.742.712 I slot print_timing: id 3 | task 3494 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.742.762 I slot release: id 3 | task 3494 | stop processing: n_tokens = 1468, truncated = 0 2.07.778.826 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.781 2.07.778.950 I slot launch_slot_: id 3 | task 3725 | processing task, is_child = 0 2.08.264.746 I slot print_timing: id 0 | task 3664 | prompt eval time = 113.66 ms / 101 tokens ( 1.13 ms per token, 888.64 tokens per second) 2.08.264.751 I slot print_timing: id 0 | task 3664 | eval time = 1528.46 ms / 81 tokens ( 19.11 ms per token, 52.34 tokens per second) 2.08.264.753 I slot print_timing: id 0 | task 3664 | total time = 1642.12 ms / 182 tokens 2.08.264.754 I slot print_timing: id 0 | task 3664 | graphs reused = 2892 2.08.264.754 I slot print_timing: id 0 | task 3664 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.264.805 I slot release: id 0 | task 3664 | stop processing: n_tokens = 1306, truncated = 0 2.08.302.884 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.877 2.08.303.001 I slot launch_slot_: id 0 | task 3751 | processing task, is_child = 0 2.08.370.977 I slot print_timing: id 2 | task 3596 | prompt eval time = 151.94 ms / 118 tokens ( 1.29 ms per token, 776.63 tokens per second) 2.08.370.983 I slot print_timing: id 2 | task 3596 | eval time = 2825.69 ms / 151 tokens ( 18.84 ms per token, 53.08 tokens per second) 2.08.370.984 I slot print_timing: id 2 | task 3596 | total time = 2977.63 ms / 269 tokens 2.08.370.985 I slot print_timing: id 2 | task 3596 | graphs reused = 2894 2.08.370.985 I slot print_timing: id 2 | task 3596 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.371.040 I slot release: id 2 | task 3596 | stop processing: n_tokens = 1393, truncated = 0 2.08.431.697 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.823 2.08.431.817 I slot launch_slot_: id 2 | task 3754 | processing task, is_child = 0 2.08.735.198 I slot print_timing: id 1 | task 3669 | prompt eval time = 146.10 ms / 95 tokens ( 1.54 ms per token, 650.23 tokens per second) 2.08.735.204 I slot print_timing: id 1 | task 3669 | eval time = 1801.19 ms / 92 tokens ( 19.79 ms per token, 50.52 tokens per second) 2.08.735.205 I slot print_timing: id 1 | task 3669 | total time = 1947.29 ms / 187 tokens 2.08.735.206 I slot print_timing: id 1 | task 3669 | graphs reused = 2902 2.08.735.207 I slot print_timing: id 1 | task 3669 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.735.259 I slot release: id 1 | task 3669 | stop processing: n_tokens = 1311, truncated = 0 2.08.800.797 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.874 2.08.800.923 I slot launch_slot_: id 1 | task 3768 | processing task, is_child = 0 2.09.735.984 I slot print_timing: id 0 | task 3751 | prompt eval time = 128.06 ms / 89 tokens ( 1.44 ms per token, 695.01 tokens per second) 2.09.735.990 I slot print_timing: id 0 | task 3751 | eval time = 1304.91 ms / 63 tokens ( 21.05 ms per token, 47.51 tokens per second) 2.09.735.991 I slot print_timing: id 0 | task 3751 | total time = 1432.97 ms / 152 tokens 2.09.735.992 I slot print_timing: id 0 | task 3751 | graphs reused = 2948 2.09.735.993 I slot print_timing: id 0 | task 3751 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.736.044 I slot release: id 0 | task 3751 | stop processing: n_tokens = 1276, truncated = 0 2.09.774.354 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.898 2.09.774.472 I slot launch_slot_: id 0 | task 3820 | processing task, is_child = 0 2.10.149.555 I slot print_timing: id 1 | task 3768 | prompt eval time = 149.64 ms / 92 tokens ( 1.63 ms per token, 614.82 tokens per second) 2.10.149.560 I slot print_timing: id 1 | task 3768 | eval time = 1198.98 ms / 67 tokens ( 18.17 ms per token, 55.05 tokens per second) 2.10.149.561 I slot print_timing: id 1 | task 3768 | total time = 1348.61 ms / 159 tokens 2.10.149.562 I slot print_timing: id 1 | task 3768 | graphs reused = 2964 2.10.149.563 I slot print_timing: id 1 | task 3768 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.149.613 I slot release: id 1 | task 3768 | stop processing: n_tokens = 1283, truncated = 0 2.10.214.853 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.893 2.10.214.979 I slot launch_slot_: id 1 | task 3840 | processing task, is_child = 0 2.10.906.202 I slot print_timing: id 2 | task 3754 | prompt eval time = 147.35 ms / 99 tokens ( 1.49 ms per token, 671.87 tokens per second) 2.10.906.208 I slot print_timing: id 2 | task 3754 | eval time = 2327.02 ms / 117 tokens ( 20.06 ms per token, 49.85 tokens per second) 2.10.906.209 I slot print_timing: id 2 | task 3754 | total time = 2474.37 ms / 216 tokens 2.10.906.210 I slot print_timing: id 2 | task 3754 | graphs reused = 2996 2.10.906.211 I slot print_timing: id 2 | task 3754 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.906.263 I slot release: id 2 | task 3754 | stop processing: n_tokens = 1340, truncated = 0 2.10.938.393 I slot print_timing: id 3 | task 3725 | n_gen = 145, tg = 47.62 t/s, tg_3s = 47.95 t/s 2.10.938.403 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.855 2.10.938.513 I slot launch_slot_: id 2 | task 3877 | processing task, is_child = 0 2.11.247.552 I slot print_timing: id 3 | task 3725 | prompt eval time = 135.50 ms / 152 tokens ( 0.89 ms per token, 1121.81 tokens per second) 2.11.247.558 I slot print_timing: id 3 | task 3725 | eval time = 3333.09 ms / 157 tokens ( 21.37 ms per token, 46.80 tokens per second) 2.11.247.559 I slot print_timing: id 3 | task 3725 | total time = 3468.59 ms / 309 tokens 2.11.247.560 I slot print_timing: id 3 | task 3725 | graphs reused = 3005 2.11.247.561 I slot print_timing: id 3 | task 3725 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.247.614 I slot release: id 3 | task 3725 | stop processing: n_tokens = 1433, truncated = 0 2.11.283.797 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.800 2.11.283.917 I slot launch_slot_: id 3 | task 3892 | processing task, is_child = 0 2.11.588.362 I slot print_timing: id 0 | task 3820 | prompt eval time = 117.16 ms / 113 tokens ( 1.04 ms per token, 964.51 tokens per second) 2.11.588.368 I slot print_timing: id 0 | task 3820 | eval time = 1696.72 ms / 80 tokens ( 21.48 ms per token, 46.56 tokens per second) 2.11.588.369 I slot print_timing: id 0 | task 3820 | total time = 1813.87 ms / 193 tokens 2.11.588.370 I slot print_timing: id 0 | task 3820 | graphs reused = 3015 2.11.588.371 I slot print_timing: id 0 | task 3820 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.588.421 I slot release: id 0 | task 3820 | stop processing: n_tokens = 1317, truncated = 0 2.11.625.123 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.870 2.11.625.235 I slot launch_slot_: id 0 | task 3907 | processing task, is_child = 0 2.12.408.574 I slot print_timing: id 2 | task 3877 | prompt eval time = 144.24 ms / 90 tokens ( 1.60 ms per token, 623.97 tokens per second) 2.12.408.580 I slot print_timing: id 2 | task 3877 | eval time = 1325.81 ms / 70 tokens ( 19.21 ms per token, 52.04 tokens per second) 2.12.408.581 I slot print_timing: id 2 | task 3877 | total time = 1470.04 ms / 160 tokens 2.12.408.583 I slot print_timing: id 2 | task 3877 | graphs reused = 3057 2.12.408.584 I slot print_timing: id 2 | task 3877 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.408.635 I slot release: id 2 | task 3877 | stop processing: n_tokens = 1284, truncated = 0 2.12.441.656 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.893 2.12.441.780 I slot launch_slot_: id 2 | task 3952 | processing task, is_child = 0 2.13.204.539 I slot print_timing: id 0 | task 3907 | prompt eval time = 114.31 ms / 107 tokens ( 1.07 ms per token, 936.03 tokens per second) 2.13.204.545 I slot print_timing: id 0 | task 3907 | eval time = 1464.97 ms / 81 tokens ( 18.31 ms per token, 54.61 tokens per second) 2.13.204.546 I slot print_timing: id 0 | task 3907 | total time = 1579.29 ms / 188 tokens 2.13.204.546 I slot print_timing: id 0 | task 3907 | graphs reused = 3092 2.13.204.547 I slot print_timing: id 0 | task 3907 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.204.600 I slot release: id 0 | task 3907 | stop processing: n_tokens = 1312, truncated = 0 2.13.242.877 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.873 2.13.243.007 I slot launch_slot_: id 0 | task 3993 | processing task, is_child = 0 2.13.361.206 I slot print_timing: id 1 | task 3840 | prompt eval time = 154.67 ms / 118 tokens ( 1.31 ms per token, 762.90 tokens per second) 2.13.361.212 I slot print_timing: id 1 | task 3840 | eval time = 2991.53 ms / 149 tokens ( 20.21 ms per token, 49.47 tokens per second) 2.13.361.213 I slot print_timing: id 1 | task 3840 | total time = 3146.21 ms / 267 tokens 2.13.361.214 I slot print_timing: id 1 | task 3840 | graphs reused = 3094 2.13.361.214 I slot print_timing: id 1 | task 3840 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.361.266 I slot release: id 1 | task 3840 | stop processing: n_tokens = 1391, truncated = 0 2.13.394.855 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.824 2.13.394.975 I slot launch_slot_: id 1 | task 3997 | processing task, is_child = 0 2.13.929.834 I slot print_timing: id 3 | task 3892 | prompt eval time = 141.76 ms / 170 tokens ( 0.83 ms per token, 1199.22 tokens per second) 2.13.929.839 I slot print_timing: id 3 | task 3892 | eval time = 2504.14 ms / 124 tokens ( 20.36 ms per token, 49.12 tokens per second) 2.13.929.840 I slot print_timing: id 3 | task 3892 | total time = 2645.90 ms / 294 tokens 2.13.929.841 I slot print_timing: id 3 | task 3892 | graphs reused = 3115 2.13.929.842 I slot print_timing: id 3 | task 3892 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.929.898 I slot release: id 3 | task 3892 | stop processing: n_tokens = 1418, truncated = 0 2.13.967.328 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.808 2.13.967.472 I slot launch_slot_: id 3 | task 4024 | processing task, is_child = 0 2.14.799.616 I slot print_timing: id 0 | task 3993 | prompt eval time = 117.88 ms / 109 tokens ( 1.08 ms per token, 924.65 tokens per second) 2.14.799.621 I slot print_timing: id 0 | task 3993 | eval time = 1438.71 ms / 73 tokens ( 19.98 ms per token, 50.04 tokens per second) 2.14.799.622 I slot print_timing: id 0 | task 3993 | total time = 1556.59 ms / 182 tokens 2.14.799.623 I slot print_timing: id 0 | task 3993 | graphs reused = 3158 2.14.799.624 I slot print_timing: id 0 | task 3993 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.799.674 I slot release: id 0 | task 3993 | stop processing: n_tokens = 1306, truncated = 0 2.14.836.555 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.877 2.14.836.678 I slot launch_slot_: id 0 | task 4072 | processing task, is_child = 0 2.15.416.565 I slot print_timing: id 2 | task 3952 | prompt eval time = 163.78 ms / 147 tokens ( 1.11 ms per token, 897.56 tokens per second) 2.15.416.571 I slot print_timing: id 2 | task 3952 | eval time = 2810.99 ms / 145 tokens ( 19.52 ms per token, 51.23 tokens per second) 2.15.416.572 I slot print_timing: id 2 | task 3952 | total time = 2974.77 ms / 292 tokens 2.15.416.573 I slot print_timing: id 2 | task 3952 | graphs reused = 3187 2.15.416.574 I slot print_timing: id 2 | task 3952 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.416.625 I slot release: id 2 | task 3952 | stop processing: n_tokens = 1416, truncated = 0 2.15.448.600 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.809 2.15.448.711 I slot launch_slot_: id 2 | task 4104 | processing task, is_child = 0 2.15.998.761 I slot print_timing: id 3 | task 4024 | prompt eval time = 125.18 ms / 110 tokens ( 1.14 ms per token, 878.74 tokens per second) 2.15.998.767 I slot print_timing: id 3 | task 4024 | eval time = 1906.09 ms / 104 tokens ( 18.51 ms per token, 54.04 tokens per second) 2.15.998.768 I slot print_timing: id 3 | task 4024 | total time = 2031.27 ms / 214 tokens 2.15.998.768 I slot print_timing: id 3 | task 4024 | graphs reused = 3211 2.15.998.769 I slot print_timing: id 3 | task 4024 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.998.822 I slot release: id 3 | task 4024 | stop processing: n_tokens = 1338, truncated = 0 2.16.016.943 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.857 2.16.017.056 I slot launch_slot_: id 3 | task 4133 | processing task, is_child = 0 2.16.570.915 I slot print_timing: id 1 | task 3997 | n_gen = 159, tg = 52.44 t/s, tg_3s = 52.77 t/s 2.16.982.513 I slot print_timing: id 1 | task 3997 | prompt eval time = 163.05 ms / 139 tokens ( 1.17 ms per token, 852.51 tokens per second) 2.16.982.518 I slot print_timing: id 1 | task 3997 | eval time = 3424.47 ms / 184 tokens ( 18.71 ms per token, 53.44 tokens per second) 2.16.982.519 I slot print_timing: id 1 | task 3997 | total time = 3587.52 ms / 323 tokens 2.16.982.520 I slot print_timing: id 1 | task 3997 | graphs reused = 3261 2.16.982.521 I slot print_timing: id 1 | task 3997 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.982.574 I slot release: id 1 | task 3997 | stop processing: n_tokens = 1447, truncated = 0 2.17.015.648 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.792 2.17.015.767 I slot launch_slot_: id 1 | task 4188 | processing task, is_child = 0 2.17.438.612 I slot print_timing: id 0 | task 4072 | prompt eval time = 128.10 ms / 134 tokens ( 0.96 ms per token, 1046.03 tokens per second) 2.17.438.618 I slot print_timing: id 0 | task 4072 | eval time = 2473.81 ms / 130 tokens ( 19.18 ms per token, 52.15 tokens per second) 2.17.438.619 I slot print_timing: id 0 | task 4072 | total time = 2601.92 ms / 264 tokens 2.17.438.620 I slot print_timing: id 0 | task 4072 | graphs reused = 3276 2.17.438.620 I slot print_timing: id 0 | task 4072 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.438.672 I slot release: id 0 | task 4072 | stop processing: n_tokens = 1388, truncated = 0 2.17.477.116 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.826 2.17.477.230 I slot launch_slot_: id 0 | task 4209 | processing task, is_child = 0 2.17.864.997 I slot print_timing: id 3 | task 4133 | prompt eval time = 120.33 ms / 96 tokens ( 1.25 ms per token, 797.83 tokens per second) 2.17.865.003 I slot print_timing: id 3 | task 4133 | eval time = 1727.60 ms / 91 tokens ( 19.20 ms per token, 52.10 tokens per second) 2.17.865.004 I slot print_timing: id 3 | task 4133 | total time = 1847.92 ms / 187 tokens 2.17.865.005 I slot print_timing: id 3 | task 4133 | graphs reused = 3293 2.17.865.006 I slot print_timing: id 3 | task 4133 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.865.056 I slot release: id 3 | task 4133 | stop processing: n_tokens = 1311, truncated = 0 2.17.883.878 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.874 2.17.883.990 I slot launch_slot_: id 3 | task 4229 | processing task, is_child = 0 2.18.146.392 I slot print_timing: id 2 | task 4104 | prompt eval time = 150.53 ms / 122 tokens ( 1.23 ms per token, 810.46 tokens per second) 2.18.146.398 I slot print_timing: id 2 | task 4104 | eval time = 2547.13 ms / 130 tokens ( 19.75 ms per token, 50.65 tokens per second) 2.18.146.399 I slot print_timing: id 2 | task 4104 | total time = 2697.66 ms / 252 tokens 2.18.146.400 I slot print_timing: id 2 | task 4104 | graphs reused = 3300 2.18.146.400 I slot print_timing: id 2 | task 4104 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.146.453 I slot release: id 2 | task 4104 | stop processing: n_tokens = 1376, truncated = 0 2.18.179.400 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.833 2.18.179.520 I slot launch_slot_: id 2 | task 4241 | processing task, is_child = 0 2.19.129.482 I slot print_timing: id 1 | task 4188 | prompt eval time = 152.34 ms / 111 tokens ( 1.37 ms per token, 728.66 tokens per second) 2.19.129.488 I slot print_timing: id 1 | task 4188 | eval time = 1961.36 ms / 99 tokens ( 20.01 ms per token, 49.97 tokens per second) 2.19.129.489 I slot print_timing: id 1 | task 4188 | total time = 2113.70 ms / 210 tokens 2.19.129.491 I slot print_timing: id 1 | task 4188 | graphs reused = 3347 2.19.129.491 I slot print_timing: id 1 | task 4188 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.129.542 I slot release: id 1 | task 4188 | stop processing: n_tokens = 1334, truncated = 0 2.19.162.036 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.859 2.19.162.145 I slot launch_slot_: id 1 | task 4293 | processing task, is_child = 0 2.19.632.809 I slot print_timing: id 0 | task 4209 | prompt eval time = 116.50 ms / 101 tokens ( 1.15 ms per token, 866.99 tokens per second) 2.19.632.815 I slot print_timing: id 0 | task 4209 | eval time = 2039.07 ms / 102 tokens ( 20.19 ms per token, 49.53 tokens per second) 2.19.632.816 I slot print_timing: id 0 | task 4209 | total time = 2155.56 ms / 203 tokens 2.19.632.817 I slot print_timing: id 0 | task 4209 | graphs reused = 3366 2.19.632.818 I slot print_timing: id 0 | task 4209 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.632.869 I slot release: id 0 | task 4209 | stop processing: n_tokens = 1327, truncated = 0 2.19.669.920 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.864 2.19.670.036 I slot launch_slot_: id 0 | task 4318 | processing task, is_child = 0 2.20.554.189 I slot print_timing: id 3 | task 4229 | prompt eval time = 124.14 ms / 108 tokens ( 1.15 ms per token, 869.95 tokens per second) 2.20.554.195 I slot print_timing: id 3 | task 4229 | eval time = 2546.04 ms / 134 tokens ( 19.14 ms per token, 52.24 tokens per second) 2.20.554.196 I slot print_timing: id 3 | task 4229 | total time = 2670.18 ms / 242 tokens 2.20.554.197 I slot print_timing: id 3 | task 4229 | graphs reused = 3414 2.20.554.197 I slot print_timing: id 3 | task 4229 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.554.250 I slot release: id 3 | task 4229 | stop processing: n_tokens = 1366, truncated = 0 2.20.591.971 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.839 2.20.592.090 I slot launch_slot_: id 3 | task 4370 | processing task, is_child = 0 2.20.833.284 I slot print_timing: id 0 | task 4318 | prompt eval time = 117.45 ms / 128 tokens ( 0.92 ms per token, 1089.79 tokens per second) 2.20.833.290 I slot print_timing: id 0 | task 4318 | eval time = 1045.78 ms / 59 tokens ( 18.03 ms per token, 55.46 tokens per second) 2.20.833.291 I slot print_timing: id 0 | task 4318 | total time = 1163.23 ms / 187 tokens 2.20.833.292 I slot print_timing: id 0 | task 4318 | graphs reused = 3421 2.20.833.292 I slot print_timing: id 0 | task 4318 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.833.347 I slot release: id 0 | task 4318 | stop processing: n_tokens = 1311, truncated = 0 2.20.853.159 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.874 2.20.853.291 I slot launch_slot_: id 0 | task 4381 | processing task, is_child = 0 2.21.158.968 I slot print_timing: id 1 | task 4293 | prompt eval time = 149.58 ms / 110 tokens ( 1.36 ms per token, 735.41 tokens per second) 2.21.158.974 I slot print_timing: id 1 | task 4293 | eval time = 1847.23 ms / 96 tokens ( 19.44 ms per token, 51.43 tokens per second) 2.21.158.975 I slot print_timing: id 1 | task 4293 | total time = 1996.81 ms / 206 tokens 2.21.158.977 I slot print_timing: id 1 | task 4293 | graphs reused = 3431 2.21.158.977 I slot print_timing: id 1 | task 4293 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.159.031 I slot release: id 1 | task 4293 | stop processing: n_tokens = 1330, truncated = 0 2.21.191.923 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.862 2.21.192.047 I slot launch_slot_: id 1 | task 4395 | processing task, is_child = 0 2.21.342.273 I slot print_timing: id 2 | task 4241 | prompt eval time = 171.20 ms / 166 tokens ( 1.03 ms per token, 969.64 tokens per second) 2.21.342.278 I slot print_timing: id 2 | task 4241 | eval time = 2991.53 ms / 150 tokens ( 20.08 ms per token, 49.81 tokens per second) 2.21.342.279 I slot print_timing: id 2 | task 4241 | total time = 3162.73 ms / 316 tokens 2.21.342.280 I slot print_timing: id 2 | task 4241 | graphs reused = 3431 2.21.342.281 I slot print_timing: id 2 | task 4241 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.342.337 I slot release: id 2 | task 4241 | stop processing: n_tokens = 1440, truncated = 0 2.22.897.908 I slot print_timing: id 3 | task 4370 | prompt eval time = 121.38 ms / 95 tokens ( 1.28 ms per token, 782.69 tokens per second) 2.22.897.914 I slot print_timing: id 3 | task 4370 | eval time = 2184.42 ms / 72 tokens ( 30.77 ms per token, 32.50 tokens per second) 2.22.897.915 I slot print_timing: id 3 | task 4370 | total time = 2305.80 ms / 167 tokens 2.22.897.916 I slot print_timing: id 3 | task 4370 | graphs reused = 3431 2.22.897.917 I slot print_timing: id 3 | task 4370 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.897.965 I slot release: id 3 | task 4370 | stop processing: n_tokens = 1291, truncated = 0 2.23.215.070 I slot print_timing: id 1 | task 4395 | prompt eval time = 149.90 ms / 96 tokens ( 1.56 ms per token, 640.42 tokens per second) 2.23.215.075 I slot print_timing: id 1 | task 4395 | eval time = 1873.11 ms / 72 tokens ( 26.38 ms per token, 37.90 tokens per second) 2.23.215.076 I slot print_timing: id 1 | task 4395 | total time = 2023.01 ms / 168 tokens 2.23.215.077 I slot print_timing: id 1 | task 4395 | graphs reused = 3453 2.23.215.078 I slot print_timing: id 1 | task 4395 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.215.124 I slot release: id 1 | task 4395 | stop processing: n_tokens = 1292, truncated = 0 2.23.993.628 I slot print_timing: id 0 | task 4381 | n_gen = 148, tg = 48.88 t/s, tg_3s = 49.21 t/s 2.24.067.247 I slot print_timing: id 0 | task 4381 | prompt eval time = 133.06 ms / 142 tokens ( 0.94 ms per token, 1067.20 tokens per second) 2.24.067.253 I slot print_timing: id 0 | task 4381 | eval time = 3080.88 ms / 154 tokens ( 20.14 ms per token, 49.66 tokens per second) 2.24.067.254 I slot print_timing: id 0 | task 4381 | total time = 3213.94 ms / 296 tokens 2.24.067.255 I slot print_timing: id 0 | task 4381 | graphs reused = 3521 2.24.067.256 I slot print_timing: id 0 | task 4381 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.067.305 I slot release: id 0 | task 4381 | stop processing: n_tokens = 1420, truncated = 0 2.24.089.157 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1440, t_last = 141247242 2.24.089.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 2.24.091.022 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.912 MiB) 2.24.092.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.162 MiB) 2.24.141.625 I slot launch_slot_: id 2 | task 4538 | processing task, is_child = 0 2.24.141.714 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.005 MiB) 2.24.143.283 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 2.24.144.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 2.24.192.706 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 2.24.194.415 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 2.24.196.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.536 MiB) 2.24.245.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.504 MiB) 2.24.247.796 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 2.24.249.537 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.567 MiB) 2.24.304.707 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 142802870 2.24.304.952 I slot launch_slot_: id 3 | task 4539 | processing task, is_child = 0 2.24.305.114 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1292, t_last = 143120029 2.24.305.300 I slot launch_slot_: id 1 | task 4540 | processing task, is_child = 0 2.24.305.382 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1420, t_last = 143972211 2.24.305.553 I slot launch_slot_: id 0 | task 4541 | processing task, is_child = 0 2.25.629.755 I slot print_timing: id 1 | task 4540 | prompt eval time = 1238.79 ms / 779 tokens ( 1.59 ms per token, 628.84 tokens per second) 2.25.629.761 I slot print_timing: id 1 | task 4540 | eval time = 81.73 ms / 2 tokens ( 81.73 ms per token, 12.23 tokens per second) 2.25.629.762 I slot print_timing: id 1 | task 4540 | total time = 1320.52 ms / 781 tokens 2.25.629.763 I slot print_timing: id 1 | task 4540 | graphs reused = 3521 2.25.629.764 I slot print_timing: id 1 | task 4540 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.629.805 I slot release: id 1 | task 4540 | stop processing: n_tokens = 780, truncated = 0 2.25.663.695 I slot print_timing: id 0 | task 4541 | prompt eval time = 1323.90 ms / 952 tokens ( 1.39 ms per token, 719.08 tokens per second) 2.25.663.702 I slot print_timing: id 0 | task 4541 | eval time = 34.22 ms / 2 tokens ( 34.22 ms per token, 29.23 tokens per second) 2.25.663.703 I slot print_timing: id 0 | task 4541 | total time = 1358.12 ms / 954 tokens 2.25.663.704 I slot print_timing: id 0 | task 4541 | graphs reused = 3521 2.25.663.705 I slot print_timing: id 0 | task 4541 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.663.758 I slot release: id 0 | task 4541 | stop processing: n_tokens = 953, truncated = 0 2.25.664.091 I slot print_timing: id 2 | task 4538 | prompt eval time = 1317.55 ms / 806 tokens ( 1.63 ms per token, 611.74 tokens per second) 2.25.664.094 I slot print_timing: id 2 | task 4538 | eval time = 33.68 ms / 2 tokens ( 33.68 ms per token, 29.69 tokens per second) 2.25.664.095 I slot print_timing: id 2 | task 4538 | total time = 1351.24 ms / 808 tokens 2.25.664.096 I slot print_timing: id 2 | task 4538 | graphs reused = 3521 2.25.664.097 I slot print_timing: id 2 | task 4538 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.664.127 I slot release: id 2 | task 4538 | stop processing: n_tokens = 807, truncated = 0 2.25.664.448 I slot print_timing: id 3 | task 4539 | prompt eval time = 1314.59 ms / 987 tokens ( 1.33 ms per token, 750.81 tokens per second) 2.25.664.451 I slot print_timing: id 3 | task 4539 | eval time = 33.47 ms / 2 tokens ( 33.47 ms per token, 29.88 tokens per second) 2.25.664.452 I slot print_timing: id 3 | task 4539 | total time = 1348.06 ms / 989 tokens 2.25.664.452 I slot print_timing: id 3 | task 4539 | graphs reused = 3521 2.25.664.453 I slot print_timing: id 3 | task 4539 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.664.489 I slot release: id 3 | task 4539 | stop processing: n_tokens = 988, truncated = 0 2.25.664.499 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 145534710 2.25.664.572 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.568 MiB) 2.25.666.445 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 2.25.714.808 I slot launch_slot_: id 1 | task 4549 | processing task, is_child = 0 2.25.714.881 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.661 MiB) 2.25.716.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.349 MiB) 2.25.718.662 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.817 MiB) 2.25.767.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.161 MiB) 2.25.768.917 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.973 MiB) 2.25.770.585 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 2.25.819.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.286 MiB) 2.25.821.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 2.25.864.064 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 145568663 2.25.864.357 I slot launch_slot_: id 0 | task 4550 | processing task, is_child = 0 2.25.864.469 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 145569032 2.25.864.673 I slot launch_slot_: id 2 | task 4551 | processing task, is_child = 0 2.25.864.733 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 145569394 2.25.864.940 I slot launch_slot_: id 3 | task 4552 | processing task, is_child = 0 2.27.098.668 I slot print_timing: id 0 | task 4550 | prompt eval time = 1213.82 ms / 846 tokens ( 1.43 ms per token, 696.97 tokens per second) 2.27.098.673 I slot print_timing: id 0 | task 4550 | eval time = 19.89 ms / 2 tokens ( 19.89 ms per token, 50.27 tokens per second) 2.27.098.674 I slot print_timing: id 0 | task 4550 | total time = 1233.71 ms / 848 tokens 2.27.098.675 I slot print_timing: id 0 | task 4550 | graphs reused = 3521 2.27.098.676 I slot print_timing: id 0 | task 4550 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.098.721 I slot release: id 0 | task 4550 | stop processing: n_tokens = 847, truncated = 0 2.27.098.992 I slot print_timing: id 1 | task 4549 | prompt eval time = 1210.19 ms / 801 tokens ( 1.51 ms per token, 661.88 tokens per second) 2.27.098.995 I slot print_timing: id 1 | task 4549 | eval time = 19.61 ms / 2 tokens ( 19.61 ms per token, 50.98 tokens per second) 2.27.098.996 I slot print_timing: id 1 | task 4549 | total time = 1229.81 ms / 803 tokens 2.27.098.996 I slot print_timing: id 1 | task 4549 | graphs reused = 3521 2.27.098.997 I slot print_timing: id 1 | task 4549 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.099.021 I slot release: id 1 | task 4549 | stop processing: n_tokens = 802, truncated = 0 2.27.099.290 I slot print_timing: id 2 | task 4551 | prompt eval time = 1207.38 ms / 855 tokens ( 1.41 ms per token, 708.15 tokens per second) 2.27.099.293 I slot print_timing: id 2 | task 4551 | eval time = 19.32 ms / 2 tokens ( 19.32 ms per token, 51.75 tokens per second) 2.27.099.294 I slot print_timing: id 2 | task 4551 | total time = 1226.70 ms / 857 tokens 2.27.099.294 I slot print_timing: id 2 | task 4551 | graphs reused = 3521 2.27.099.295 I slot print_timing: id 2 | task 4551 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.099.319 I slot release: id 2 | task 4551 | stop processing: n_tokens = 856, truncated = 0 2.27.099.587 I slot print_timing: id 3 | task 4552 | prompt eval time = 1204.63 ms / 804 tokens ( 1.50 ms per token, 667.42 tokens per second) 2.27.099.590 I slot print_timing: id 3 | task 4552 | eval time = 19.04 ms / 2 tokens ( 19.04 ms per token, 52.53 tokens per second) 2.27.099.591 I slot print_timing: id 3 | task 4552 | total time = 1223.67 ms / 806 tokens 2.27.099.591 I slot print_timing: id 3 | task 4552 | graphs reused = 3521 2.27.099.592 I slot print_timing: id 3 | task 4552 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.099.610 I slot release: id 3 | task 4552 | stop processing: n_tokens = 805, truncated = 0 2.27.113.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 147003626 2.27.113.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.035 MiB) 2.27.115.063 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.442 MiB) 2.27.116.721 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.724 MiB) 2.27.158.439 I slot launch_slot_: id 0 | task 4560 | processing task, is_child = 0 2.27.158.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.536 MiB) 2.27.160.143 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.098 MiB) 2.27.200.849 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.910 MiB) 2.27.202.578 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.317 MiB) 2.27.205.311 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.130 MiB) 2.27.248.443 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 2.27.250.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.160 MiB) 2.27.255.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.754 MiB) 2.27.307.808 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 802, t_last = 147003926 2.27.308.012 I slot launch_slot_: id 1 | task 4561 | processing task, is_child = 0 2.27.308.122 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.846 2.27.308.217 I slot launch_slot_: id 2 | task 4562 | processing task, is_child = 0 2.27.308.270 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 805, t_last = 147004516 2.27.308.406 I slot launch_slot_: id 3 | task 4563 | processing task, is_child = 0 2.27.820.812 I slot print_timing: id 2 | task 4562 | prompt eval time = 413.75 ms / 129 tokens ( 3.21 ms per token, 311.79 tokens per second) 2.27.820.818 I slot print_timing: id 2 | task 4562 | eval time = 91.75 ms / 2 tokens ( 91.75 ms per token, 10.90 tokens per second) 2.27.820.819 I slot print_timing: id 2 | task 4562 | total time = 505.50 ms / 131 tokens 2.27.820.820 I slot print_timing: id 2 | task 4562 | graphs reused = 3521 2.27.820.821 I slot print_timing: id 2 | task 4562 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.820.865 I slot release: id 2 | task 4562 | stop processing: n_tokens = 826, truncated = 0 2.28.069.869 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 147725770 2.28.069.947 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.474 MiB) 2.28.071.636 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.723 MiB) 2.28.169.551 I slot launch_slot_: id 2 | task 4568 | processing task, is_child = 0 2.28.589.010 I slot print_timing: id 0 | task 4560 | prompt eval time = 1217.76 ms / 880 tokens ( 1.38 ms per token, 722.64 tokens per second) 2.28.589.016 I slot print_timing: id 0 | task 4560 | eval time = 62.83 ms / 2 tokens ( 62.83 ms per token, 15.92 tokens per second) 2.28.589.017 I slot print_timing: id 0 | task 4560 | total time = 1280.59 ms / 882 tokens 2.28.589.018 I slot print_timing: id 0 | task 4560 | graphs reused = 3521 2.28.589.019 I slot print_timing: id 0 | task 4560 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.589.071 I slot release: id 0 | task 4560 | stop processing: n_tokens = 881, truncated = 0 2.28.589.401 I slot print_timing: id 1 | task 4561 | prompt eval time = 1214.89 ms / 896 tokens ( 1.36 ms per token, 737.52 tokens per second) 2.28.589.404 I slot print_timing: id 1 | task 4561 | eval time = 62.63 ms / 2 tokens ( 62.63 ms per token, 15.97 tokens per second) 2.28.589.405 I slot print_timing: id 1 | task 4561 | total time = 1277.52 ms / 898 tokens 2.28.589.406 I slot print_timing: id 1 | task 4561 | graphs reused = 3521 2.28.589.406 I slot print_timing: id 1 | task 4561 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.589.438 I slot release: id 1 | task 4561 | stop processing: n_tokens = 897, truncated = 0 2.28.589.766 I slot print_timing: id 3 | task 4563 | prompt eval time = 1191.90 ms / 963 tokens ( 1.24 ms per token, 807.95 tokens per second) 2.28.589.769 I slot print_timing: id 3 | task 4563 | eval time = 62.45 ms / 2 tokens ( 62.45 ms per token, 16.01 tokens per second) 2.28.589.770 I slot print_timing: id 3 | task 4563 | total time = 1254.35 ms / 965 tokens 2.28.589.770 I slot print_timing: id 3 | task 4563 | graphs reused = 3521 2.28.589.771 I slot print_timing: id 3 | task 4563 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.589.803 I slot release: id 3 | task 4563 | stop processing: n_tokens = 964, truncated = 0 2.28.606.607 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 148493976 2.28.606.682 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.192 MiB) 2.28.608.454 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 2.28.610.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.192 MiB) 2.28.724.728 I slot launch_slot_: id 0 | task 4573 | processing task, is_child = 0 2.28.724.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.442 MiB) 2.28.726.454 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.349 MiB) 2.28.728.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.536 MiB) 2.28.776.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.380 MiB) 2.28.778.545 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.192 MiB) 2.28.818.827 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 148494343 2.28.819.046 I slot launch_slot_: id 1 | task 4574 | processing task, is_child = 0 2.28.819.111 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 964, t_last = 148494708 2.28.819.261 I slot launch_slot_: id 3 | task 4575 | processing task, is_child = 0 2.29.489.906 I slot print_timing: id 2 | task 4568 | prompt eval time = 1071.62 ms / 987 tokens ( 1.09 ms per token, 921.03 tokens per second) 2.29.489.912 I slot print_timing: id 2 | task 4568 | eval time = 228.76 ms / 2 tokens ( 228.76 ms per token, 4.37 tokens per second) 2.29.489.913 I slot print_timing: id 2 | task 4568 | total time = 1300.38 ms / 989 tokens 2.29.489.914 I slot print_timing: id 2 | task 4568 | graphs reused = 3521 2.29.489.915 I slot print_timing: id 2 | task 4568 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.489.972 I slot release: id 2 | task 4568 | stop processing: n_tokens = 988, truncated = 0 2.29.735.862 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 149394877 2.29.735.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.098 MiB) 2.29.737.555 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.722 MiB) 2.29.739.134 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.318 MiB) 2.29.872.089 I slot launch_slot_: id 2 | task 4580 | processing task, is_child = 0 2.30.393.799 I slot print_timing: id 0 | task 4573 | prompt eval time = 1492.03 ms / 1022 tokens ( 1.46 ms per token, 684.98 tokens per second) 2.30.393.806 I slot print_timing: id 0 | task 4573 | eval time = 82.49 ms / 2 tokens ( 82.49 ms per token, 12.12 tokens per second) 2.30.393.807 I slot print_timing: id 0 | task 4573 | total time = 1574.52 ms / 1024 tokens 2.30.393.808 I slot print_timing: id 0 | task 4573 | graphs reused = 3521 2.30.393.810 I slot print_timing: id 0 | task 4573 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.393.863 I slot release: id 0 | task 4573 | stop processing: n_tokens = 1023, truncated = 0 2.30.394.213 I slot print_timing: id 1 | task 4574 | prompt eval time = 1489.09 ms / 924 tokens ( 1.61 ms per token, 620.51 tokens per second) 2.30.394.216 I slot print_timing: id 1 | task 4574 | eval time = 82.34 ms / 2 tokens ( 82.34 ms per token, 12.15 tokens per second) 2.30.394.217 I slot print_timing: id 1 | task 4574 | total time = 1571.43 ms / 926 tokens 2.30.394.218 I slot print_timing: id 1 | task 4574 | graphs reused = 3521 2.30.394.219 I slot print_timing: id 1 | task 4574 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.394.257 I slot release: id 1 | task 4574 | stop processing: n_tokens = 925, truncated = 0 2.30.394.581 I slot print_timing: id 3 | task 4575 | prompt eval time = 1473.86 ms / 1780 tokens ( 0.83 ms per token, 1207.72 tokens per second) 2.30.394.584 I slot print_timing: id 3 | task 4575 | eval time = 82.17 ms / 2 tokens ( 82.17 ms per token, 12.17 tokens per second) 2.30.394.584 I slot print_timing: id 3 | task 4575 | total time = 1556.02 ms / 1782 tokens 2.30.394.585 I slot print_timing: id 3 | task 4575 | graphs reused = 3521 2.30.394.585 I slot print_timing: id 3 | task 4575 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.394.646 I slot release: id 3 | task 4575 | stop processing: n_tokens = 1781, truncated = 0 2.30.411.048 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1023, t_last = 150298768 2.30.411.151 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.973 MiB) 2.30.413.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 2.30.415.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.473 MiB) 2.30.504.532 I slot launch_slot_: id 0 | task 4585 | processing task, is_child = 0 2.30.504.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.661 MiB) 2.30.506.525 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.442 MiB) 2.30.550.438 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 2.30.552.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.848 MiB) 2.30.553.892 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.817 MiB) 2.30.607.211 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 150299162 2.30.607.423 I slot launch_slot_: id 1 | task 4586 | processing task, is_child = 0 2.30.607.521 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1781, t_last = 150299552 2.30.607.703 I slot launch_slot_: id 3 | task 4587 | processing task, is_child = 0 2.31.268.270 I slot print_timing: id 2 | task 4580 | prompt eval time = 1089.60 ms / 937 tokens ( 1.16 ms per token, 859.95 tokens per second) 2.31.268.276 I slot print_timing: id 2 | task 4580 | eval time = 286.11 ms / 2 tokens ( 286.11 ms per token, 3.50 tokens per second) 2.31.268.277 I slot print_timing: id 2 | task 4580 | total time = 1375.71 ms / 939 tokens 2.31.268.278 I slot print_timing: id 2 | task 4580 | graphs reused = 3521 2.31.268.280 I slot print_timing: id 2 | task 4580 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.268.332 I slot release: id 2 | task 4580 | stop processing: n_tokens = 938, truncated = 0 2.31.468.269 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 151173238 2.31.468.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.285 MiB) 2.31.469.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.474 MiB) 2.31.471.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.911 MiB) 2.31.518.624 I slot launch_slot_: id 2 | task 4592 | processing task, is_child = 0 2.31.755.655 I slot print_timing: id 0 | task 4585 | prompt eval time = 1047.54 ms / 741 tokens ( 1.41 ms per token, 707.37 tokens per second) 2.31.755.661 I slot print_timing: id 0 | task 4585 | eval time = 100.39 ms / 2 tokens ( 100.39 ms per token, 9.96 tokens per second) 2.31.755.662 I slot print_timing: id 0 | task 4585 | total time = 1147.93 ms / 743 tokens 2.31.755.663 I slot print_timing: id 0 | task 4585 | graphs reused = 3521 2.31.755.663 I slot print_timing: id 0 | task 4585 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.755.709 I slot release: id 0 | task 4585 | stop processing: n_tokens = 742, truncated = 0 2.31.756.712 I slot print_timing: id 3 | task 4587 | prompt eval time = 1028.66 ms / 713 tokens ( 1.44 ms per token, 693.13 tokens per second) 2.31.756.716 I slot print_timing: id 3 | task 4587 | eval time = 100.73 ms / 2 tokens ( 100.73 ms per token, 9.93 tokens per second) 2.31.756.717 I slot print_timing: id 3 | task 4587 | total time = 1129.39 ms / 715 tokens 2.31.756.717 I slot print_timing: id 3 | task 4587 | graphs reused = 3521 2.31.756.718 I slot print_timing: id 3 | task 4587 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.756.748 I slot release: id 3 | task 4587 | stop processing: n_tokens = 714, truncated = 0 2.31.894.965 I slot print_timing: id 1 | task 4586 | prompt eval time = 1145.18 ms / 880 tokens ( 1.30 ms per token, 768.44 tokens per second) 2.31.894.971 I slot print_timing: id 1 | task 4586 | eval time = 138.56 ms / 2 tokens ( 138.56 ms per token, 7.22 tokens per second) 2.31.894.972 I slot print_timing: id 1 | task 4586 | total time = 1283.73 ms / 882 tokens 2.31.894.974 I slot print_timing: id 1 | task 4586 | graphs reused = 3521 2.31.894.975 I slot print_timing: id 1 | task 4586 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.895.020 I slot release: id 1 | task 4586 | stop processing: n_tokens = 881, truncated = 0 2.31.895.036 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.850 2.31.895.190 I slot launch_slot_: id 0 | task 4597 | processing task, is_child = 0 2.31.895.261 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.786 MiB) 2.31.897.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.380 MiB) 2.31.898.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.754 MiB) 2.31.943.663 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.692 MiB) 2.31.945.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.224 MiB) 2.31.986.763 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.884 2.31.986.920 I slot launch_slot_: id 3 | task 4596 | processing task, is_child = 0 2.31.986.988 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 151799925 2.31.987.130 I slot launch_slot_: id 1 | task 4598 | processing task, is_child = 0 2.32.382.270 I slot print_timing: id 0 | task 4597 | prompt eval time = 330.23 ms / 122 tokens ( 2.71 ms per token, 369.44 tokens per second) 2.32.382.276 I slot print_timing: id 0 | task 4597 | eval time = 64.89 ms / 2 tokens ( 64.89 ms per token, 15.41 tokens per second) 2.32.382.277 I slot print_timing: id 0 | task 4597 | total time = 395.12 ms / 124 tokens 2.32.382.278 I slot print_timing: id 0 | task 4597 | graphs reused = 3521 2.32.382.279 I slot print_timing: id 0 | task 4597 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.382.321 I slot release: id 0 | task 4597 | stop processing: n_tokens = 726, truncated = 0 2.32.382.654 I slot print_timing: id 2 | task 4592 | prompt eval time = 779.42 ms / 716 tokens ( 1.09 ms per token, 918.63 tokens per second) 2.32.382.657 I slot print_timing: id 2 | task 4592 | eval time = 64.60 ms / 2 tokens ( 64.60 ms per token, 15.48 tokens per second) 2.32.382.658 I slot print_timing: id 2 | task 4592 | total time = 844.03 ms / 718 tokens 2.32.382.659 I slot print_timing: id 2 | task 4592 | graphs reused = 3521 2.32.382.659 I slot print_timing: id 2 | task 4592 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.382.683 I slot release: id 2 | task 4592 | stop processing: n_tokens = 717, truncated = 0 2.32.383.011 I slot print_timing: id 3 | task 4596 | prompt eval time = 295.69 ms / 116 tokens ( 2.55 ms per token, 392.30 tokens per second) 2.32.383.014 I slot print_timing: id 3 | task 4596 | eval time = 64.38 ms / 2 tokens ( 64.38 ms per token, 15.53 tokens per second) 2.32.383.015 I slot print_timing: id 3 | task 4596 | total time = 360.06 ms / 118 tokens 2.32.383.015 I slot print_timing: id 3 | task 4596 | graphs reused = 3521 2.32.383.016 I slot print_timing: id 3 | task 4596 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.383.036 I slot release: id 3 | task 4596 | stop processing: n_tokens = 720, truncated = 0 2.32.400.308 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 152287226 2.32.400.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.410 MiB) 2.32.402.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 2.32.403.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 294.316 MiB) 2.32.518.858 I slot launch_slot_: id 0 | task 4603 | processing task, is_child = 0 2.32.518.915 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.001 MiB) 2.32.562.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.971 MiB) 2.32.610.583 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 152287588 2.32.610.786 I slot launch_slot_: id 2 | task 4604 | processing task, is_child = 0 2.32.610.839 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 152287941 2.32.610.981 I slot launch_slot_: id 3 | task 4605 | processing task, is_child = 0 2.33.213.966 I slot print_timing: id 1 | task 4598 | prompt eval time = 1038.31 ms / 876 tokens ( 1.19 ms per token, 843.68 tokens per second) 2.33.213.972 I slot print_timing: id 1 | task 4598 | eval time = 168.49 ms / 2 tokens ( 168.49 ms per token, 5.94 tokens per second) 2.33.213.973 I slot print_timing: id 1 | task 4598 | total time = 1206.80 ms / 878 tokens 2.33.213.974 I slot print_timing: id 1 | task 4598 | graphs reused = 3521 2.33.213.975 I slot print_timing: id 1 | task 4598 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.214.020 I slot release: id 1 | task 4598 | stop processing: n_tokens = 877, truncated = 0 2.33.561.684 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 153118925 2.33.598.590 I slot launch_slot_: id 1 | task 4610 | processing task, is_child = 0 2.34.033.193 I slot print_timing: id 0 | task 4603 | prompt eval time = 1338.01 ms / 992 tokens ( 1.35 ms per token, 741.40 tokens per second) 2.34.033.200 I slot print_timing: id 0 | task 4603 | eval time = 84.18 ms / 2 tokens ( 84.18 ms per token, 11.88 tokens per second) 2.34.033.202 I slot print_timing: id 0 | task 4603 | total time = 1422.19 ms / 994 tokens 2.34.033.204 I slot print_timing: id 0 | task 4603 | graphs reused = 3521 2.34.033.205 I slot print_timing: id 0 | task 4603 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.033.258 I slot release: id 0 | task 4603 | stop processing: n_tokens = 993, truncated = 0 2.34.033.601 I slot print_timing: id 2 | task 4604 | prompt eval time = 1322.74 ms / 1034 tokens ( 1.28 ms per token, 781.71 tokens per second) 2.34.033.606 I slot print_timing: id 2 | task 4604 | eval time = 84.03 ms / 2 tokens ( 84.03 ms per token, 11.90 tokens per second) 2.34.033.607 I slot print_timing: id 2 | task 4604 | total time = 1406.76 ms / 1036 tokens 2.34.033.607 I slot print_timing: id 2 | task 4604 | graphs reused = 3521 2.34.033.608 I slot print_timing: id 2 | task 4604 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.033.643 I slot release: id 2 | task 4604 | stop processing: n_tokens = 1035, truncated = 0 2.34.033.991 I slot print_timing: id 3 | task 4605 | prompt eval time = 1319.94 ms / 1006 tokens ( 1.31 ms per token, 762.16 tokens per second) 2.34.033.995 I slot print_timing: id 3 | task 4605 | eval time = 83.86 ms / 2 tokens ( 83.86 ms per token, 11.92 tokens per second) 2.34.033.996 I slot print_timing: id 3 | task 4605 | total time = 1403.80 ms / 1008 tokens 2.34.033.996 I slot print_timing: id 3 | task 4605 | graphs reused = 3521 2.34.033.997 I slot print_timing: id 3 | task 4605 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.034.025 I slot release: id 3 | task 4605 | stop processing: n_tokens = 1007, truncated = 0 2.34.050.865 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.895 2.34.050.980 I slot launch_slot_: id 0 | task 4615 | processing task, is_child = 0 2.34.051.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 294.316 MiB) 2.34.154.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.034 MiB) 2.34.199.121 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 153938548 2.34.199.339 I slot launch_slot_: id 2 | task 4616 | processing task, is_child = 0 2.34.199.400 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1007, t_last = 153938930 2.34.199.542 I slot launch_slot_: id 3 | task 4617 | processing task, is_child = 0 2.34.729.742 I slot print_timing: id 0 | task 4615 | prompt eval time = 424.76 ms / 132 tokens ( 3.22 ms per token, 310.77 tokens per second) 2.34.729.747 I slot print_timing: id 0 | task 4615 | eval time = 105.42 ms / 2 tokens ( 105.42 ms per token, 9.49 tokens per second) 2.34.729.749 I slot print_timing: id 0 | task 4615 | total time = 530.18 ms / 134 tokens 2.34.729.750 I slot print_timing: id 0 | task 4615 | graphs reused = 3521 2.34.729.751 I slot print_timing: id 0 | task 4615 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.729.797 I slot release: id 0 | task 4615 | stop processing: n_tokens = 994, truncated = 0 2.34.730.111 I slot print_timing: id 1 | task 4610 | prompt eval time = 1016.20 ms / 999 tokens ( 1.02 ms per token, 983.07 tokens per second) 2.34.730.115 I slot print_timing: id 1 | task 4610 | eval time = 105.22 ms / 2 tokens ( 105.22 ms per token, 9.50 tokens per second) 2.34.730.116 I slot print_timing: id 1 | task 4610 | total time = 1121.42 ms / 1001 tokens 2.34.730.116 I slot print_timing: id 1 | task 4610 | graphs reused = 3521 2.34.730.117 I slot print_timing: id 1 | task 4610 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.730.145 I slot release: id 1 | task 4610 | stop processing: n_tokens = 1000, truncated = 0 2.34.908.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 154634702 2.34.908.658 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 296.286 MiB) 2.34.957.984 I slot launch_slot_: id 0 | task 4622 | processing task, is_child = 0 2.34.958.053 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 295.661 MiB) 2.35.006.201 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 154635050 2.35.006.427 I slot launch_slot_: id 1 | task 4623 | processing task, is_child = 0 2.35.489.931 I slot print_timing: id 2 | task 4616 | prompt eval time = 1150.20 ms / 879 tokens ( 1.31 ms per token, 764.21 tokens per second) 2.35.489.936 I slot print_timing: id 2 | task 4616 | eval time = 109.77 ms / 2 tokens ( 109.77 ms per token, 9.11 tokens per second) 2.35.489.937 I slot print_timing: id 2 | task 4616 | total time = 1259.97 ms / 881 tokens 2.35.489.938 I slot print_timing: id 2 | task 4616 | graphs reused = 3521 2.35.489.939 I slot print_timing: id 2 | task 4616 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.489.980 I slot release: id 2 | task 4616 | stop processing: n_tokens = 880, truncated = 0 2.35.490.307 I slot print_timing: id 3 | task 4617 | prompt eval time = 1147.25 ms / 1018 tokens ( 1.13 ms per token, 887.34 tokens per second) 2.35.490.310 I slot print_timing: id 3 | task 4617 | eval time = 109.56 ms / 2 tokens ( 109.56 ms per token, 9.13 tokens per second) 2.35.490.311 I slot print_timing: id 3 | task 4617 | total time = 1256.81 ms / 1020 tokens 2.35.490.312 I slot print_timing: id 3 | task 4617 | graphs reused = 3521 2.35.490.312 I slot print_timing: id 3 | task 4617 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.490.353 I slot release: id 3 | task 4617 | stop processing: n_tokens = 1019, truncated = 0 2.35.667.531 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.786 2.35.667.678 I slot launch_slot_: id 3 | task 4628 | processing task, is_child = 0 2.35.667.748 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.658 MiB) 2.35.717.827 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 155394885 2.35.718.024 I slot launch_slot_: id 2 | task 4629 | processing task, is_child = 0 2.36.167.430 I slot print_timing: id 0 | task 4622 | prompt eval time = 1073.79 ms / 896 tokens ( 1.20 ms per token, 834.43 tokens per second) 2.36.167.435 I slot print_timing: id 0 | task 4622 | eval time = 87.19 ms / 2 tokens ( 87.19 ms per token, 11.47 tokens per second) 2.36.167.436 I slot print_timing: id 0 | task 4622 | total time = 1160.98 ms / 898 tokens 2.36.167.437 I slot print_timing: id 0 | task 4622 | graphs reused = 3521 2.36.167.438 I slot print_timing: id 0 | task 4622 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.167.488 I slot release: id 0 | task 4622 | stop processing: n_tokens = 897, truncated = 0 2.36.167.845 I slot print_timing: id 1 | task 4623 | prompt eval time = 1071.01 ms / 1009 tokens ( 1.06 ms per token, 942.10 tokens per second) 2.36.167.849 I slot print_timing: id 1 | task 4623 | eval time = 86.88 ms / 2 tokens ( 86.88 ms per token, 11.51 tokens per second) 2.36.167.850 I slot print_timing: id 1 | task 4623 | total time = 1157.89 ms / 1011 tokens 2.36.167.850 I slot print_timing: id 1 | task 4623 | graphs reused = 3521 2.36.167.851 I slot print_timing: id 1 | task 4623 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.167.885 I slot release: id 1 | task 4623 | stop processing: n_tokens = 1010, truncated = 0 2.36.168.236 I slot print_timing: id 3 | task 4628 | prompt eval time = 339.95 ms / 129 tokens ( 2.64 ms per token, 379.47 tokens per second) 2.36.168.239 I slot print_timing: id 3 | task 4628 | eval time = 86.56 ms / 2 tokens ( 86.56 ms per token, 11.55 tokens per second) 2.36.168.240 I slot print_timing: id 3 | task 4628 | total time = 426.51 ms / 131 tokens 2.36.168.240 I slot print_timing: id 3 | task 4628 | graphs reused = 3521 2.36.168.241 I slot print_timing: id 3 | task 4628 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.168.265 I slot release: id 3 | task 4628 | stop processing: n_tokens = 903, truncated = 0 2.36.184.550 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.893 2.36.184.671 I slot launch_slot_: id 0 | task 4634 | processing task, is_child = 0 2.36.184.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.626 MiB) 2.36.273.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.646 MiB) 2.36.325.361 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1010, t_last = 156072791 2.36.325.588 I slot launch_slot_: id 1 | task 4635 | processing task, is_child = 0 2.36.325.647 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 156073170 2.36.325.791 I slot launch_slot_: id 3 | task 4636 | processing task, is_child = 0 2.36.811.157 I slot print_timing: id 0 | task 4634 | prompt eval time = 339.93 ms / 108 tokens ( 3.15 ms per token, 317.71 tokens per second) 2.36.811.162 I slot print_timing: id 0 | task 4634 | eval time = 145.41 ms / 2 tokens ( 145.41 ms per token, 6.88 tokens per second) 2.36.811.163 I slot print_timing: id 0 | task 4634 | total time = 485.34 ms / 110 tokens 2.36.811.164 I slot print_timing: id 0 | task 4634 | graphs reused = 3521 2.36.811.165 I slot print_timing: id 0 | task 4634 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.811.215 I slot release: id 0 | task 4634 | stop processing: n_tokens = 882, truncated = 0 2.36.811.554 I slot print_timing: id 2 | task 4629 | prompt eval time = 928.10 ms / 985 tokens ( 0.94 ms per token, 1061.31 tokens per second) 2.36.811.557 I slot print_timing: id 2 | task 4629 | eval time = 145.23 ms / 2 tokens ( 145.23 ms per token, 6.89 tokens per second) 2.36.811.558 I slot print_timing: id 2 | task 4629 | total time = 1073.33 ms / 987 tokens 2.36.811.559 I slot print_timing: id 2 | task 4629 | graphs reused = 3521 2.36.811.559 I slot print_timing: id 2 | task 4629 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.811.592 I slot release: id 2 | task 4629 | stop processing: n_tokens = 986, truncated = 0 2.36.935.811 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 156716120 2.36.935.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.056 MiB) 2.37.036.897 I slot launch_slot_: id 0 | task 4641 | processing task, is_child = 0 2.37.036.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.490 MiB) 2.37.089.662 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 156716497 2.37.089.887 I slot launch_slot_: id 2 | task 4642 | processing task, is_child = 0 2.37.700.422 I slot print_timing: id 1 | task 4635 | prompt eval time = 1150.09 ms / 906 tokens ( 1.27 ms per token, 787.77 tokens per second) 2.37.700.428 I slot print_timing: id 1 | task 4635 | eval time = 204.62 ms / 2 tokens ( 204.62 ms per token, 4.89 tokens per second) 2.37.700.429 I slot print_timing: id 1 | task 4635 | total time = 1354.70 ms / 908 tokens 2.37.700.430 I slot print_timing: id 1 | task 4635 | graphs reused = 3521 2.37.700.431 I slot print_timing: id 1 | task 4635 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.700.480 I slot release: id 1 | task 4635 | stop processing: n_tokens = 907, truncated = 0 2.37.700.834 I slot print_timing: id 3 | task 4636 | prompt eval time = 1134.90 ms / 952 tokens ( 1.19 ms per token, 838.84 tokens per second) 2.37.700.839 I slot print_timing: id 3 | task 4636 | eval time = 204.36 ms / 2 tokens ( 204.36 ms per token, 4.89 tokens per second) 2.37.700.840 I slot print_timing: id 3 | task 4636 | total time = 1339.26 ms / 954 tokens 2.37.700.841 I slot print_timing: id 3 | task 4636 | graphs reused = 3521 2.37.700.841 I slot print_timing: id 3 | task 4636 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.700.873 I slot release: id 3 | task 4636 | stop processing: n_tokens = 953, truncated = 0 2.37.824.196 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 157605385 2.37.824.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.151 MiB) 2.37.916.644 I slot launch_slot_: id 1 | task 4647 | processing task, is_child = 0 2.37.916.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.741 MiB) 2.37.961.170 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 157605778 2.37.961.383 I slot launch_slot_: id 3 | task 4648 | processing task, is_child = 0 2.38.664.698 I slot print_timing: id 0 | task 4641 | prompt eval time = 1336.61 ms / 940 tokens ( 1.42 ms per token, 703.27 tokens per second) 2.38.664.703 I slot print_timing: id 0 | task 4641 | eval time = 238.18 ms / 2 tokens ( 238.18 ms per token, 4.20 tokens per second) 2.38.664.704 I slot print_timing: id 0 | task 4641 | total time = 1574.78 ms / 942 tokens 2.38.664.705 I slot print_timing: id 0 | task 4641 | graphs reused = 3521 2.38.664.706 I slot print_timing: id 0 | task 4641 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.664.755 I slot release: id 0 | task 4641 | stop processing: n_tokens = 941, truncated = 0 2.38.665.066 I slot print_timing: id 2 | task 4642 | prompt eval time = 1321.64 ms / 1356 tokens ( 0.97 ms per token, 1025.99 tokens per second) 2.38.665.069 I slot print_timing: id 2 | task 4642 | eval time = 237.76 ms / 2 tokens ( 237.76 ms per token, 4.21 tokens per second) 2.38.665.070 I slot print_timing: id 2 | task 4642 | total time = 1559.41 ms / 1358 tokens 2.38.665.071 I slot print_timing: id 2 | task 4642 | graphs reused = 3521 2.38.665.071 I slot print_timing: id 2 | task 4642 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.665.130 I slot release: id 2 | task 4642 | stop processing: n_tokens = 1357, truncated = 0 2.38.808.055 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 158569660 2.38.808.138 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.334 MiB) 2.38.901.720 I slot launch_slot_: id 0 | task 4653 | processing task, is_child = 0 2.38.901.812 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.023 MiB) 2.38.951.583 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.870 2.38.951.734 I slot launch_slot_: id 2 | task 4654 | processing task, is_child = 0 2.39.439.152 I slot print_timing: id 1 | task 4647 | prompt eval time = 1327.32 ms / 1259 tokens ( 1.05 ms per token, 948.53 tokens per second) 2.39.439.159 I slot print_timing: id 1 | task 4647 | eval time = 140.35 ms / 2 tokens ( 140.35 ms per token, 7.12 tokens per second) 2.39.439.160 I slot print_timing: id 1 | task 4647 | total time = 1467.67 ms / 1261 tokens 2.39.439.161 I slot print_timing: id 1 | task 4647 | graphs reused = 3521 2.39.439.162 I slot print_timing: id 1 | task 4647 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.439.224 I slot release: id 1 | task 4647 | stop processing: n_tokens = 1260, truncated = 0 2.39.439.568 I slot print_timing: id 2 | task 4654 | prompt eval time = 331.91 ms / 148 tokens ( 2.24 ms per token, 445.90 tokens per second) 2.39.439.571 I slot print_timing: id 2 | task 4654 | eval time = 140.17 ms / 2 tokens ( 140.17 ms per token, 7.13 tokens per second) 2.39.439.572 I slot print_timing: id 2 | task 4654 | total time = 472.08 ms / 150 tokens 2.39.439.572 I slot print_timing: id 2 | task 4654 | graphs reused = 3521 2.39.439.573 I slot print_timing: id 2 | task 4654 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.439.615 I slot release: id 2 | task 4654 | stop processing: n_tokens = 1301, truncated = 0 2.39.439.965 I slot print_timing: id 3 | task 4648 | prompt eval time = 1312.84 ms / 1342 tokens ( 0.98 ms per token, 1022.22 tokens per second) 2.39.439.969 I slot print_timing: id 3 | task 4648 | eval time = 140.02 ms / 2 tokens ( 140.02 ms per token, 7.14 tokens per second) 2.39.439.969 I slot print_timing: id 3 | task 4648 | total time = 1452.85 ms / 1344 tokens 2.39.439.970 I slot print_timing: id 3 | task 4648 | graphs reused = 3521 2.39.439.971 I slot print_timing: id 3 | task 4648 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.440.009 I slot release: id 3 | task 4648 | stop processing: n_tokens = 1343, truncated = 0 2.39.458.806 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1260, t_last = 159344131 2.39.458.977 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.428 MiB) 2.39.522.181 I slot launch_slot_: id 1 | task 4659 | processing task, is_child = 0 2.39.522.260 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.085 MiB) 2.39.573.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.805 MiB) 2.39.621.355 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1301, t_last = 159344520 2.39.621.586 I slot launch_slot_: id 2 | task 4660 | processing task, is_child = 0 2.39.621.668 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1343, t_last = 159344914 2.39.621.834 I slot launch_slot_: id 3 | task 4661 | processing task, is_child = 0 2.39.981.260 I slot print_timing: id 0 | task 4653 | prompt eval time = 845.26 ms / 792 tokens ( 1.07 ms per token, 936.99 tokens per second) 2.39.981.266 I slot print_timing: id 0 | task 4653 | eval time = 184.24 ms / 2 tokens ( 184.24 ms per token, 5.43 tokens per second) 2.39.981.268 I slot print_timing: id 0 | task 4653 | total time = 1029.50 ms / 794 tokens 2.39.981.269 I slot print_timing: id 0 | task 4653 | graphs reused = 3521 2.39.981.270 I slot print_timing: id 0 | task 4653 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.981.317 I slot release: id 0 | task 4653 | stop processing: n_tokens = 793, truncated = 0 2.40.040.189 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 159886223 2.40.040.258 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.305 MiB) 2.40.093.606 I slot launch_slot_: id 0 | task 4665 | processing task, is_child = 0 2.40.965.434 I slot print_timing: id 1 | task 4659 | prompt eval time = 1255.00 ms / 859 tokens ( 1.46 ms per token, 684.46 tokens per second) 2.40.965.439 I slot print_timing: id 1 | task 4659 | eval time = 78.13 ms / 2 tokens ( 78.13 ms per token, 12.80 tokens per second) 2.40.965.440 I slot print_timing: id 1 | task 4659 | total time = 1333.13 ms / 861 tokens 2.40.965.441 I slot print_timing: id 1 | task 4659 | graphs reused = 3521 2.40.965.442 I slot print_timing: id 1 | task 4659 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.965.489 I slot release: id 1 | task 4659 | stop processing: n_tokens = 860, truncated = 0 2.40.965.820 I slot print_timing: id 2 | task 4660 | prompt eval time = 1251.95 ms / 891 tokens ( 1.41 ms per token, 711.69 tokens per second) 2.40.965.823 I slot print_timing: id 2 | task 4660 | eval time = 77.95 ms / 2 tokens ( 77.95 ms per token, 12.83 tokens per second) 2.40.965.823 I slot print_timing: id 2 | task 4660 | total time = 1329.91 ms / 893 tokens 2.40.965.824 I slot print_timing: id 2 | task 4660 | graphs reused = 3521 2.40.965.824 I slot print_timing: id 2 | task 4660 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.965.854 I slot release: id 2 | task 4660 | stop processing: n_tokens = 892, truncated = 0 2.40.966.178 I slot print_timing: id 3 | task 4661 | prompt eval time = 1248.95 ms / 808 tokens ( 1.55 ms per token, 646.94 tokens per second) 2.40.966.181 I slot print_timing: id 3 | task 4661 | eval time = 77.76 ms / 2 tokens ( 77.76 ms per token, 12.86 tokens per second) 2.40.966.181 I slot print_timing: id 3 | task 4661 | total time = 1326.71 ms / 810 tokens 2.40.966.182 I slot print_timing: id 3 | task 4661 | graphs reused = 3521 2.40.966.183 I slot print_timing: id 3 | task 4661 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.966.210 I slot release: id 3 | task 4661 | stop processing: n_tokens = 809, truncated = 0 2.40.994.425 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 160870394 2.40.994.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.400 MiB) 2.41.037.521 I slot launch_slot_: id 1 | task 4671 | processing task, is_child = 0 2.41.037.592 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.151 MiB) 2.41.091.470 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.245 MiB) 2.41.137.328 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 892, t_last = 160870759 2.41.137.534 I slot launch_slot_: id 2 | task 4672 | processing task, is_child = 0 2.41.137.590 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 809, t_last = 160871115 2.41.137.728 I slot launch_slot_: id 3 | task 4673 | processing task, is_child = 0 2.41.296.660 I slot print_timing: id 0 | task 4665 | prompt eval time = 900.80 ms / 790 tokens ( 1.14 ms per token, 877.00 tokens per second) 2.41.296.667 I slot print_timing: id 0 | task 4665 | eval time = 302.23 ms / 2 tokens ( 302.23 ms per token, 3.31 tokens per second) 2.41.296.668 I slot print_timing: id 0 | task 4665 | total time = 1203.03 ms / 792 tokens 2.41.296.669 I slot print_timing: id 0 | task 4665 | graphs reused = 3521 2.41.296.670 I slot print_timing: id 0 | task 4665 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.296.721 I slot release: id 0 | task 4665 | stop processing: n_tokens = 791, truncated = 0 2.41.436.112 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.852 (> 0.100 thold), f_keep = 0.863 2.41.436.290 I slot launch_slot_: id 0 | task 4676 | processing task, is_child = 0 2.42.176.777 I slot print_timing: id 0 | task 4676 | prompt eval time = 613.55 ms / 147 tokens ( 4.17 ms per token, 239.59 tokens per second) 2.42.176.782 I slot print_timing: id 0 | task 4676 | eval time = 126.91 ms / 2 tokens ( 126.91 ms per token, 7.88 tokens per second) 2.42.176.783 I slot print_timing: id 0 | task 4676 | total time = 740.46 ms / 149 tokens 2.42.176.784 I slot print_timing: id 0 | task 4676 | graphs reused = 3521 2.42.176.785 I slot print_timing: id 0 | task 4676 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.176.829 I slot release: id 0 | task 4676 | stop processing: n_tokens = 803, truncated = 0 2.42.222.110 I slot print_timing: id 2 | task 4672 | prompt eval time = 1036.24 ms / 778 tokens ( 1.33 ms per token, 750.79 tokens per second) 2.42.222.115 I slot print_timing: id 2 | task 4672 | eval time = 44.61 ms / 2 tokens ( 44.61 ms per token, 22.42 tokens per second) 2.42.222.116 I slot print_timing: id 2 | task 4672 | total time = 1080.85 ms / 780 tokens 2.42.222.117 I slot print_timing: id 2 | task 4672 | graphs reused = 3521 2.42.222.118 I slot print_timing: id 2 | task 4672 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.222.160 I slot release: id 2 | task 4672 | stop processing: n_tokens = 779, truncated = 0 2.42.222.453 I slot print_timing: id 3 | task 4673 | prompt eval time = 1033.41 ms / 774 tokens ( 1.34 ms per token, 748.98 tokens per second) 2.42.222.456 I slot print_timing: id 3 | task 4673 | eval time = 44.37 ms / 2 tokens ( 44.37 ms per token, 22.54 tokens per second) 2.42.222.457 I slot print_timing: id 3 | task 4673 | total time = 1077.78 ms / 776 tokens 2.42.222.458 I slot print_timing: id 3 | task 4673 | graphs reused = 3521 2.42.222.459 I slot print_timing: id 3 | task 4673 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.222.484 I slot release: id 3 | task 4673 | stop processing: n_tokens = 775, truncated = 0 2.42.222.495 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 162081734 2.42.222.565 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.181 MiB) 2.42.270.180 I slot launch_slot_: id 0 | task 4681 | processing task, is_child = 0 2.42.270.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.950 MiB) 2.42.321.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.587 MiB) 2.42.369.925 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 162127065 2.42.370.226 I slot launch_slot_: id 2 | task 4682 | processing task, is_child = 0 2.42.370.313 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 775, t_last = 162127389 2.42.370.559 I slot launch_slot_: id 3 | task 4683 | processing task, is_child = 0 2.42.555.666 I slot print_timing: id 1 | task 4671 | prompt eval time = 1084.08 ms / 855 tokens ( 1.27 ms per token, 788.69 tokens per second) 2.42.555.671 I slot print_timing: id 1 | task 4671 | eval time = 333.84 ms / 2 tokens ( 333.84 ms per token, 3.00 tokens per second) 2.42.555.672 I slot print_timing: id 1 | task 4671 | total time = 1417.91 ms / 857 tokens 2.42.555.673 I slot print_timing: id 1 | task 4671 | graphs reused = 3521 2.42.555.674 I slot print_timing: id 1 | task 4671 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.555.719 I slot release: id 1 | task 4671 | stop processing: n_tokens = 856, truncated = 0 2.42.641.179 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 162460625 2.42.641.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.805 MiB) 2.42.733.634 I slot launch_slot_: id 1 | task 4686 | processing task, is_child = 0 2.43.772.847 I slot print_timing: id 0 | task 4681 | prompt eval time = 1324.06 ms / 971 tokens ( 1.36 ms per token, 733.35 tokens per second) 2.43.772.852 I slot print_timing: id 0 | task 4681 | eval time = 78.20 ms / 2 tokens ( 78.20 ms per token, 12.79 tokens per second) 2.43.772.853 I slot print_timing: id 0 | task 4681 | total time = 1402.26 ms / 973 tokens 2.43.772.854 I slot print_timing: id 0 | task 4681 | graphs reused = 3521 2.43.772.855 I slot print_timing: id 0 | task 4681 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.772.904 I slot release: id 0 | task 4681 | stop processing: n_tokens = 972, truncated = 0 2.43.773.233 I slot print_timing: id 2 | task 4682 | prompt eval time = 1320.78 ms / 944 tokens ( 1.40 ms per token, 714.73 tokens per second) 2.43.773.236 I slot print_timing: id 2 | task 4682 | eval time = 78.01 ms / 2 tokens ( 78.01 ms per token, 12.82 tokens per second) 2.43.773.237 I slot print_timing: id 2 | task 4682 | total time = 1398.79 ms / 946 tokens 2.43.773.237 I slot print_timing: id 2 | task 4682 | graphs reused = 3521 2.43.773.238 I slot print_timing: id 2 | task 4682 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.773.263 I slot release: id 2 | task 4682 | stop processing: n_tokens = 945, truncated = 0 2.43.773.602 I slot print_timing: id 3 | task 4683 | prompt eval time = 1317.81 ms / 964 tokens ( 1.37 ms per token, 731.52 tokens per second) 2.43.773.604 I slot print_timing: id 3 | task 4683 | eval time = 77.81 ms / 2 tokens ( 77.81 ms per token, 12.85 tokens per second) 2.43.773.605 I slot print_timing: id 3 | task 4683 | total time = 1395.62 ms / 966 tokens 2.43.773.606 I slot print_timing: id 3 | task 4683 | graphs reused = 3521 2.43.773.606 I slot print_timing: id 3 | task 4683 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.773.630 I slot release: id 3 | task 4683 | stop processing: n_tokens = 965, truncated = 0 2.43.801.327 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.889 2.43.801.452 I slot launch_slot_: id 0 | task 4693 | processing task, is_child = 0 2.43.801.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.582 MiB) 2.43.847.907 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.957 MiB) 2.43.900.354 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 163678168 2.43.900.562 I slot launch_slot_: id 2 | task 4694 | processing task, is_child = 0 2.43.900.626 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 163678535 2.43.900.777 I slot launch_slot_: id 3 | task 4695 | processing task, is_child = 0 2.44.077.019 I slot print_timing: id 1 | task 4686 | prompt eval time = 1067.66 ms / 947 tokens ( 1.13 ms per token, 886.99 tokens per second) 2.44.077.025 I slot print_timing: id 1 | task 4686 | eval time = 275.69 ms / 2 tokens ( 275.69 ms per token, 3.63 tokens per second) 2.44.077.026 I slot print_timing: id 1 | task 4686 | total time = 1343.35 ms / 949 tokens 2.44.077.027 I slot print_timing: id 1 | task 4686 | graphs reused = 3521 2.44.077.029 I slot print_timing: id 1 | task 4686 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.077.080 I slot release: id 1 | task 4686 | stop processing: n_tokens = 948, truncated = 0 2.44.210.953 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 163981985 2.44.211.031 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.676 MiB) 2.44.256.722 I slot launch_slot_: id 1 | task 4698 | processing task, is_child = 0 2.44.568.610 I slot print_timing: id 0 | task 4693 | prompt eval time = 310.16 ms / 133 tokens ( 2.33 ms per token, 428.82 tokens per second) 2.44.568.615 I slot print_timing: id 0 | task 4693 | eval time = 357.66 ms / 2 tokens ( 357.66 ms per token, 2.80 tokens per second) 2.44.568.616 I slot print_timing: id 0 | task 4693 | total time = 667.81 ms / 135 tokens 2.44.568.617 I slot print_timing: id 0 | task 4693 | graphs reused = 3521 2.44.568.618 I slot print_timing: id 0 | task 4693 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.568.664 I slot release: id 0 | task 4693 | stop processing: n_tokens = 970, truncated = 0 2.44.714.340 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 164473569 2.44.714.426 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.770 MiB) 2.44.764.692 I slot launch_slot_: id 0 | task 4701 | processing task, is_child = 0 2.45.115.303 I slot print_timing: id 2 | task 4694 | prompt eval time = 985.25 ms / 799 tokens ( 1.23 ms per token, 810.97 tokens per second) 2.45.115.308 I slot print_timing: id 2 | task 4694 | eval time = 211.57 ms / 2 tokens ( 211.57 ms per token, 4.73 tokens per second) 2.45.115.310 I slot print_timing: id 2 | task 4694 | total time = 1196.82 ms / 801 tokens 2.45.115.311 I slot print_timing: id 2 | task 4694 | graphs reused = 3521 2.45.115.312 I slot print_timing: id 2 | task 4694 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.115.355 I slot release: id 2 | task 4694 | stop processing: n_tokens = 800, truncated = 0 2.45.115.683 I slot print_timing: id 3 | task 4695 | prompt eval time = 982.55 ms / 798 tokens ( 1.23 ms per token, 812.17 tokens per second) 2.45.115.686 I slot print_timing: id 3 | task 4695 | eval time = 211.21 ms / 2 tokens ( 211.21 ms per token, 4.73 tokens per second) 2.45.115.687 I slot print_timing: id 3 | task 4695 | total time = 1193.76 ms / 800 tokens 2.45.115.687 I slot print_timing: id 3 | task 4695 | graphs reused = 3521 2.45.115.688 I slot print_timing: id 3 | task 4695 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.115.713 I slot release: id 3 | task 4695 | stop processing: n_tokens = 799, truncated = 0 2.45.193.910 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 165020260 2.45.193.980 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.679 MiB) 2.45.236.407 I slot launch_slot_: id 2 | task 4705 | processing task, is_child = 0 2.45.236.465 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.621 MiB) 2.45.285.019 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 165020618 2.45.285.230 I slot launch_slot_: id 3 | task 4706 | processing task, is_child = 0 2.45.743.256 I slot print_timing: id 1 | task 4698 | prompt eval time = 1288.89 ms / 975 tokens ( 1.32 ms per token, 756.47 tokens per second) 2.45.743.261 I slot print_timing: id 1 | task 4698 | eval time = 197.62 ms / 2 tokens ( 197.62 ms per token, 5.06 tokens per second) 2.45.743.262 I slot print_timing: id 1 | task 4698 | total time = 1486.50 ms / 977 tokens 2.45.743.263 I slot print_timing: id 1 | task 4698 | graphs reused = 3521 2.45.743.264 I slot print_timing: id 1 | task 4698 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.743.313 I slot release: id 1 | task 4698 | stop processing: n_tokens = 976, truncated = 0 2.45.833.894 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 165648218 2.45.833.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.745 MiB) 2.45.879.551 I slot launch_slot_: id 1 | task 4710 | processing task, is_child = 0 2.46.185.964 I slot print_timing: id 0 | task 4701 | prompt eval time = 1069.18 ms / 953 tokens ( 1.12 ms per token, 891.34 tokens per second) 2.46.185.969 I slot print_timing: id 0 | task 4701 | eval time = 352.07 ms / 2 tokens ( 352.07 ms per token, 2.84 tokens per second) 2.46.185.970 I slot print_timing: id 0 | task 4701 | total time = 1421.24 ms / 955 tokens 2.46.185.972 I slot print_timing: id 0 | task 4701 | graphs reused = 3521 2.46.185.973 I slot print_timing: id 0 | task 4701 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.186.019 I slot release: id 0 | task 4701 | stop processing: n_tokens = 954, truncated = 0 2.46.358.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 166090924 2.46.358.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.338 MiB) 2.46.408.310 I slot launch_slot_: id 0 | task 4713 | processing task, is_child = 0 2.46.734.814 I slot print_timing: id 2 | task 4705 | prompt eval time = 1231.71 ms / 961 tokens ( 1.28 ms per token, 780.21 tokens per second) 2.46.734.819 I slot print_timing: id 2 | task 4705 | eval time = 197.50 ms / 2 tokens ( 197.50 ms per token, 5.06 tokens per second) 2.46.734.820 I slot print_timing: id 2 | task 4705 | total time = 1429.21 ms / 963 tokens 2.46.734.823 I slot print_timing: id 2 | task 4705 | graphs reused = 3521 2.46.734.824 I slot print_timing: id 2 | task 4705 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.734.871 I slot release: id 2 | task 4705 | stop processing: n_tokens = 962, truncated = 0 2.46.735.198 I slot print_timing: id 3 | task 4706 | prompt eval time = 1228.73 ms / 930 tokens ( 1.32 ms per token, 756.88 tokens per second) 2.46.735.201 I slot print_timing: id 3 | task 4706 | eval time = 197.32 ms / 2 tokens ( 197.32 ms per token, 5.07 tokens per second) 2.46.735.201 I slot print_timing: id 3 | task 4706 | total time = 1426.05 ms / 932 tokens 2.46.735.202 I slot print_timing: id 3 | task 4706 | graphs reused = 3521 2.46.735.203 I slot print_timing: id 3 | task 4706 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.735.243 I slot release: id 3 | task 4706 | stop processing: n_tokens = 931, truncated = 0 2.46.807.184 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.867 2.46.807.355 I slot launch_slot_: id 3 | task 4717 | processing task, is_child = 0 2.46.807.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.526 MiB) 2.46.855.919 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 166639777 2.46.856.142 I slot launch_slot_: id 2 | task 4718 | processing task, is_child = 0 2.47.283.059 I slot print_timing: id 1 | task 4710 | prompt eval time = 1239.96 ms / 898 tokens ( 1.38 ms per token, 724.22 tokens per second) 2.47.283.065 I slot print_timing: id 1 | task 4710 | eval time = 163.52 ms / 2 tokens ( 163.52 ms per token, 6.12 tokens per second) 2.47.283.066 I slot print_timing: id 1 | task 4710 | total time = 1403.48 ms / 900 tokens 2.47.283.067 I slot print_timing: id 1 | task 4710 | graphs reused = 3521 2.47.283.067 I slot print_timing: id 1 | task 4710 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.283.117 I slot release: id 1 | task 4710 | stop processing: n_tokens = 899, truncated = 0 2.47.353.695 I slot print_timing: id 3 | task 4717 | prompt eval time = 403.55 ms / 120 tokens ( 3.36 ms per token, 297.36 tokens per second) 2.47.353.700 I slot print_timing: id 3 | task 4717 | eval time = 69.93 ms / 2 tokens ( 69.93 ms per token, 14.30 tokens per second) 2.47.353.702 I slot print_timing: id 3 | task 4717 | total time = 473.48 ms / 122 tokens 2.47.353.703 I slot print_timing: id 3 | task 4717 | graphs reused = 3521 2.47.353.703 I slot print_timing: id 3 | task 4717 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.353.749 I slot release: id 3 | task 4717 | stop processing: n_tokens = 900, truncated = 0 2.47.353.759 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 167188022 2.47.353.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.773 MiB) 2.47.404.172 I slot launch_slot_: id 1 | task 4722 | processing task, is_child = 0 2.47.404.243 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.839 MiB) 2.47.466.130 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 900, t_last = 167258654 2.47.466.549 I slot launch_slot_: id 3 | task 4723 | processing task, is_child = 0 2.47.724.352 I slot print_timing: id 0 | task 4713 | prompt eval time = 945.07 ms / 902 tokens ( 1.05 ms per token, 954.43 tokens per second) 2.47.724.357 I slot print_timing: id 0 | task 4713 | eval time = 370.95 ms / 2 tokens ( 370.95 ms per token, 2.70 tokens per second) 2.47.724.358 I slot print_timing: id 0 | task 4713 | total time = 1316.02 ms / 904 tokens 2.47.724.359 I slot print_timing: id 0 | task 4713 | graphs reused = 3521 2.47.724.360 I slot print_timing: id 0 | task 4713 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.724.409 I slot release: id 0 | task 4713 | stop processing: n_tokens = 903, truncated = 0 2.47.884.592 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 167629314 2.47.884.683 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.493 MiB) 2.47.936.978 I slot launch_slot_: id 0 | task 4726 | processing task, is_child = 0 2.48.499.311 I slot print_timing: id 2 | task 4718 | prompt eval time = 1317.30 ms / 890 tokens ( 1.48 ms per token, 675.63 tokens per second) 2.48.499.317 I slot print_timing: id 2 | task 4718 | eval time = 305.28 ms / 2 tokens ( 305.28 ms per token, 3.28 tokens per second) 2.48.499.318 I slot print_timing: id 2 | task 4718 | total time = 1622.58 ms / 892 tokens 2.48.499.319 I slot print_timing: id 2 | task 4718 | graphs reused = 3521 2.48.499.320 I slot print_timing: id 2 | task 4718 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.499.374 I slot release: id 2 | task 4718 | stop processing: n_tokens = 891, truncated = 0 2.48.672.159 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 168404279 2.48.672.233 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.836 MiB) 2.48.732.571 I slot launch_slot_: id 2 | task 4730 | processing task, is_child = 0 2.49.268.435 I slot print_timing: id 1 | task 4722 | prompt eval time = 1521.41 ms / 1225 tokens ( 1.24 ms per token, 805.17 tokens per second) 2.49.268.442 I slot print_timing: id 1 | task 4722 | eval time = 280.44 ms / 2 tokens ( 280.44 ms per token, 3.57 tokens per second) 2.49.268.444 I slot print_timing: id 1 | task 4722 | total time = 1801.85 ms / 1227 tokens 2.49.268.445 I slot print_timing: id 1 | task 4722 | graphs reused = 3521 2.49.268.446 I slot print_timing: id 1 | task 4722 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.268.510 I slot release: id 1 | task 4722 | stop processing: n_tokens = 1226, truncated = 0 2.49.268.864 I slot print_timing: id 3 | task 4723 | prompt eval time = 1499.97 ms / 1236 tokens ( 1.21 ms per token, 824.01 tokens per second) 2.49.268.868 I slot print_timing: id 3 | task 4723 | eval time = 280.17 ms / 2 tokens ( 280.17 ms per token, 3.57 tokens per second) 2.49.268.868 I slot print_timing: id 3 | task 4723 | total time = 1780.15 ms / 1238 tokens 2.49.268.869 I slot print_timing: id 3 | task 4723 | graphs reused = 3521 2.49.268.870 I slot print_timing: id 3 | task 4723 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.268.909 I slot release: id 3 | task 4723 | stop processing: n_tokens = 1237, truncated = 0 2.49.596.287 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1226, t_last = 169173416 2.49.596.380 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.088 MiB) 2.49.651.244 I slot launch_slot_: id 1 | task 4734 | processing task, is_child = 0 2.49.651.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.618 MiB) 2.49.699.279 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1237, t_last = 169173814 2.49.699.509 I slot launch_slot_: id 3 | task 4735 | processing task, is_child = 0 2.50.034.849 I slot print_timing: id 0 | task 4726 | prompt eval time = 1659.28 ms / 1290 tokens ( 1.29 ms per token, 777.45 tokens per second) 2.50.034.855 I slot print_timing: id 0 | task 4726 | eval time = 438.57 ms / 2 tokens ( 438.57 ms per token, 2.28 tokens per second) 2.50.034.857 I slot print_timing: id 0 | task 4726 | total time = 2097.84 ms / 1292 tokens 2.50.034.858 I slot print_timing: id 0 | task 4726 | graphs reused = 3521 2.50.034.859 I slot print_timing: id 0 | task 4726 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.034.922 I slot release: id 0 | task 4726 | stop processing: n_tokens = 1291, truncated = 0 2.50.389.040 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 169939831 2.50.389.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.056 MiB) 2.50.485.304 I slot launch_slot_: id 0 | task 4738 | processing task, is_child = 0 2.51.534.181 I slot print_timing: id 2 | task 4730 | prompt eval time = 2327.93 ms / 2587 tokens ( 0.90 ms per token, 1111.29 tokens per second) 2.51.534.187 I slot print_timing: id 2 | task 4730 | eval time = 453.07 ms / 2 tokens ( 453.07 ms per token, 2.21 tokens per second) 2.51.534.188 I slot print_timing: id 2 | task 4730 | total time = 2780.99 ms / 2589 tokens 2.51.534.190 I slot print_timing: id 2 | task 4730 | graphs reused = 3521 2.51.534.191 I slot print_timing: id 2 | task 4730 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.534.311 I slot release: id 2 | task 4730 | stop processing: n_tokens = 2588, truncated = 0 2.51.929.650 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2588, t_last = 171439218 2.51.929.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.681 MiB) 2.51.934.443 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.690 MiB) 2.51.995.741 I slot launch_slot_: id 2 | task 4742 | processing task, is_child = 0 2.52.538.731 I slot print_timing: id 1 | task 4734 | prompt eval time = 2586.05 ms / 2500 tokens ( 1.03 ms per token, 966.73 tokens per second) 2.52.538.736 I slot print_timing: id 1 | task 4734 | eval time = 253.15 ms / 2 tokens ( 253.15 ms per token, 3.95 tokens per second) 2.52.538.737 I slot print_timing: id 1 | task 4734 | total time = 2839.19 ms / 2502 tokens 2.52.538.738 I slot print_timing: id 1 | task 4734 | graphs reused = 3521 2.52.538.739 I slot print_timing: id 1 | task 4734 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.538.844 I slot release: id 1 | task 4734 | stop processing: n_tokens = 2501, truncated = 0 2.52.777.023 I slot print_timing: id 3 | task 4735 | prompt eval time = 2824.16 ms / 2742 tokens ( 1.03 ms per token, 970.91 tokens per second) 2.52.777.028 I slot print_timing: id 3 | task 4735 | eval time = 237.55 ms / 2 tokens ( 237.55 ms per token, 4.21 tokens per second) 2.52.777.029 I slot print_timing: id 3 | task 4735 | total time = 3061.71 ms / 2744 tokens 2.52.777.030 I slot print_timing: id 3 | task 4735 | graphs reused = 3521 2.52.777.030 I slot print_timing: id 3 | task 4735 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.777.148 I slot release: id 3 | task 4735 | stop processing: n_tokens = 2743, truncated = 0 2.52.777.164 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2501, t_last = 172443751 2.52.777.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 290.657 MiB) 2.52.839.775 I slot launch_slot_: id 1 | task 4746 | processing task, is_child = 0 2.52.839.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.939 MiB) 2.52.900.567 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2743, t_last = 172682055 2.52.900.862 I slot launch_slot_: id 3 | task 4747 | processing task, is_child = 0 2.53.132.675 I slot print_timing: id 0 | task 4738 | prompt eval time = 2291.37 ms / 2655 tokens ( 0.86 ms per token, 1158.70 tokens per second) 2.53.132.681 I slot print_timing: id 0 | task 4738 | eval time = 355.94 ms / 2 tokens ( 355.94 ms per token, 2.81 tokens per second) 2.53.132.683 I slot print_timing: id 0 | task 4738 | total time = 2647.31 ms / 2657 tokens 2.53.132.684 I slot print_timing: id 0 | task 4738 | graphs reused = 3521 2.53.132.685 I slot print_timing: id 0 | task 4738 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.132.802 I slot release: id 0 | task 4738 | stop processing: n_tokens = 2656, truncated = 0 2.53.423.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2656, t_last = 173037708 2.53.423.931 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.253 MiB) 2.53.502.613 I slot launch_slot_: id 0 | task 4750 | processing task, is_child = 0 2.54.283.890 I slot print_timing: id 2 | task 4742 | prompt eval time = 2057.63 ms / 1779 tokens ( 1.16 ms per token, 864.59 tokens per second) 2.54.283.896 I slot print_timing: id 2 | task 4742 | eval time = 210.40 ms / 2 tokens ( 210.40 ms per token, 4.75 tokens per second) 2.54.283.897 I slot print_timing: id 2 | task 4742 | total time = 2268.03 ms / 1781 tokens 2.54.283.899 I slot print_timing: id 2 | task 4742 | graphs reused = 3521 2.54.283.900 I slot print_timing: id 2 | task 4742 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.283.985 I slot release: id 2 | task 4742 | stop processing: n_tokens = 1780, truncated = 0 2.54.643.965 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.756 (> 0.100 thold), f_keep = 0.834 2.54.644.127 I slot launch_slot_: id 2 | task 4754 | processing task, is_child = 0 2.55.199.762 I slot print_timing: id 1 | task 4746 | prompt eval time = 2113.41 ms / 1841 tokens ( 1.15 ms per token, 871.10 tokens per second) 2.55.199.767 I slot print_timing: id 1 | task 4746 | eval time = 185.47 ms / 2 tokens ( 185.47 ms per token, 5.39 tokens per second) 2.55.199.769 I slot print_timing: id 1 | task 4746 | total time = 2298.88 ms / 1843 tokens 2.55.199.770 I slot print_timing: id 1 | task 4746 | graphs reused = 3521 2.55.199.770 I slot print_timing: id 1 | task 4746 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.199.853 I slot release: id 1 | task 4746 | stop processing: n_tokens = 1842, truncated = 0 2.55.200.794 I slot print_timing: id 3 | task 4747 | prompt eval time = 2097.91 ms / 2048 tokens ( 1.02 ms per token, 976.21 tokens per second) 2.55.200.797 I slot print_timing: id 3 | task 4747 | eval time = 185.94 ms / 2 tokens ( 185.94 ms per token, 5.38 tokens per second) 2.55.200.798 I slot print_timing: id 3 | task 4747 | total time = 2283.85 ms / 2050 tokens 2.55.200.798 I slot print_timing: id 3 | task 4747 | graphs reused = 3521 2.55.200.799 I slot print_timing: id 3 | task 4747 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.200.877 I slot release: id 3 | task 4747 | stop processing: n_tokens = 2049, truncated = 0 2.55.243.757 I slot print_timing: id 2 | task 4754 | prompt eval time = 411.46 ms / 515 tokens ( 0.80 ms per token, 1251.63 tokens per second) 2.55.243.763 I slot print_timing: id 2 | task 4754 | eval time = 43.27 ms / 2 tokens ( 43.27 ms per token, 23.11 tokens per second) 2.55.243.764 I slot print_timing: id 2 | task 4754 | total time = 454.74 ms / 517 tokens 2.55.243.765 I slot print_timing: id 2 | task 4754 | graphs reused = 3521 2.55.243.766 I slot print_timing: id 2 | task 4754 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.243.847 I slot release: id 2 | task 4754 | stop processing: n_tokens = 1963, truncated = 0 2.55.243.863 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.833 (> 0.100 thold), f_keep = 0.806 2.55.243.985 I slot launch_slot_: id 1 | task 4758 | processing task, is_child = 0 2.55.244.106 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.052 MiB) 2.55.304.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.148 MiB) 2.55.354.454 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2049, t_last = 175105783 2.55.354.715 I slot launch_slot_: id 3 | task 4759 | processing task, is_child = 0 2.55.354.822 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1963, t_last = 175148754 2.55.355.009 I slot launch_slot_: id 2 | task 4760 | processing task, is_child = 0 2.55.570.941 I slot print_timing: id 0 | task 4750 | prompt eval time = 1740.83 ms / 1852 tokens ( 0.94 ms per token, 1063.86 tokens per second) 2.55.570.946 I slot print_timing: id 0 | task 4750 | eval time = 327.47 ms / 2 tokens ( 327.47 ms per token, 3.05 tokens per second) 2.55.570.947 I slot print_timing: id 0 | task 4750 | total time = 2068.30 ms / 1854 tokens 2.55.570.948 I slot print_timing: id 0 | task 4750 | graphs reused = 3521 2.55.570.949 I slot print_timing: id 0 | task 4750 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.571.032 I slot release: id 0 | task 4750 | stop processing: n_tokens = 1853, truncated = 0 2.55.690.876 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1853, t_last = 175475938 2.55.690.989 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.149 MiB) 2.55.749.611 I slot launch_slot_: id 0 | task 4763 | processing task, is_child = 0 2.56.055.861 I slot print_timing: id 1 | task 4758 | prompt eval time = 335.85 ms / 334 tokens ( 1.01 ms per token, 994.50 tokens per second) 2.56.055.867 I slot print_timing: id 1 | task 4758 | eval time = 364.98 ms / 2 tokens ( 364.98 ms per token, 2.74 tokens per second) 2.56.055.868 I slot print_timing: id 1 | task 4758 | total time = 700.83 ms / 336 tokens 2.56.055.869 I slot print_timing: id 1 | task 4758 | graphs reused = 3521 2.56.055.869 I slot print_timing: id 1 | task 4758 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.055.949 I slot release: id 1 | task 4758 | stop processing: n_tokens = 1782, truncated = 0 2.56.188.397 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1782, t_last = 175960856 2.56.188.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.553 MiB) 2.56.193.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.365 MiB) 2.56.251.484 I slot launch_slot_: id 1 | task 4766 | processing task, is_child = 0 2.56.575.811 I slot print_timing: id 2 | task 4760 | prompt eval time = 1073.63 ms / 748 tokens ( 1.44 ms per token, 696.70 tokens per second) 2.56.575.817 I slot print_timing: id 2 | task 4760 | eval time = 129.36 ms / 2 tokens ( 129.36 ms per token, 7.73 tokens per second) 2.56.575.818 I slot print_timing: id 2 | task 4760 | total time = 1202.99 ms / 750 tokens 2.56.575.819 I slot print_timing: id 2 | task 4760 | graphs reused = 3521 2.56.575.820 I slot print_timing: id 2 | task 4760 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.575.862 I slot release: id 2 | task 4760 | stop processing: n_tokens = 749, truncated = 0 2.56.576.184 I slot print_timing: id 3 | task 4759 | prompt eval time = 1070.74 ms / 726 tokens ( 1.47 ms per token, 678.04 tokens per second) 2.56.576.187 I slot print_timing: id 3 | task 4759 | eval time = 129.03 ms / 2 tokens ( 129.03 ms per token, 7.75 tokens per second) 2.56.576.187 I slot print_timing: id 3 | task 4759 | total time = 1199.77 ms / 728 tokens 2.56.576.188 I slot print_timing: id 3 | task 4759 | graphs reused = 3521 2.56.576.188 I slot print_timing: id 3 | task 4759 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.576.213 I slot release: id 3 | task 4759 | stop processing: n_tokens = 727, truncated = 0 2.56.728.426 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.858 2.56.728.555 I slot launch_slot_: id 2 | task 4770 | processing task, is_child = 0 2.56.764.141 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 176481118 2.56.764.355 I slot launch_slot_: id 3 | task 4771 | processing task, is_child = 0 2.56.937.454 I slot print_timing: id 0 | task 4763 | prompt eval time = 978.79 ms / 761 tokens ( 1.29 ms per token, 777.49 tokens per second) 2.56.937.461 I slot print_timing: id 0 | task 4763 | eval time = 209.03 ms / 2 tokens ( 209.03 ms per token, 4.78 tokens per second) 2.56.937.462 I slot print_timing: id 0 | task 4763 | total time = 1187.82 ms / 763 tokens 2.56.937.463 I slot print_timing: id 0 | task 4763 | graphs reused = 3521 2.56.937.464 I slot print_timing: id 0 | task 4763 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.937.513 I slot release: id 0 | task 4763 | stop processing: n_tokens = 762, truncated = 0 2.57.047.652 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 176842418 2.57.047.727 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.615 MiB) 2.57.098.877 I slot launch_slot_: id 0 | task 4774 | processing task, is_child = 0 2.57.194.365 I slot print_timing: id 1 | task 4766 | prompt eval time = 785.44 ms / 725 tokens ( 1.08 ms per token, 923.05 tokens per second) 2.57.194.371 I slot print_timing: id 1 | task 4766 | eval time = 147.37 ms / 2 tokens ( 147.37 ms per token, 6.79 tokens per second) 2.57.194.372 I slot print_timing: id 1 | task 4766 | total time = 932.82 ms / 727 tokens 2.57.194.372 I slot print_timing: id 1 | task 4766 | graphs reused = 3521 2.57.194.374 I slot print_timing: id 1 | task 4766 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.194.420 I slot release: id 1 | task 4766 | stop processing: n_tokens = 726, truncated = 0 2.57.194.750 I slot print_timing: id 2 | task 4770 | prompt eval time = 273.05 ms / 124 tokens ( 2.20 ms per token, 454.14 tokens per second) 2.57.194.752 I slot print_timing: id 2 | task 4770 | eval time = 147.11 ms / 2 tokens ( 147.11 ms per token, 6.80 tokens per second) 2.57.194.753 I slot print_timing: id 2 | task 4770 | total time = 420.15 ms / 126 tokens 2.57.194.754 I slot print_timing: id 2 | task 4770 | graphs reused = 3521 2.57.194.755 I slot print_timing: id 2 | task 4770 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.194.780 I slot release: id 2 | task 4770 | stop processing: n_tokens = 740, truncated = 0 2.57.278.280 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 177099326 2.57.278.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.490 MiB) 2.57.379.298 I slot launch_slot_: id 1 | task 4777 | processing task, is_child = 0 2.57.379.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.023 MiB) 2.57.432.082 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 177099686 2.57.432.279 I slot launch_slot_: id 2 | task 4778 | processing task, is_child = 0 2.58.004.038 I slot print_timing: id 3 | task 4771 | prompt eval time = 1093.64 ms / 798 tokens ( 1.37 ms per token, 729.67 tokens per second) 2.58.004.044 I slot print_timing: id 3 | task 4771 | eval time = 116.11 ms / 2 tokens ( 116.11 ms per token, 8.61 tokens per second) 2.58.004.045 I slot print_timing: id 3 | task 4771 | total time = 1209.75 ms / 800 tokens 2.58.004.046 I slot print_timing: id 3 | task 4771 | graphs reused = 3521 2.58.004.047 I slot print_timing: id 3 | task 4771 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.004.094 I slot release: id 3 | task 4771 | stop processing: n_tokens = 799, truncated = 0 2.58.277.521 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 177908999 2.58.277.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.806 MiB) 2.58.323.058 I slot launch_slot_: id 3 | task 4783 | processing task, is_child = 0 2.58.499.957 I slot print_timing: id 0 | task 4774 | prompt eval time = 1178.62 ms / 1042 tokens ( 1.13 ms per token, 884.09 tokens per second) 2.58.499.962 I slot print_timing: id 0 | task 4774 | eval time = 222.44 ms / 2 tokens ( 222.44 ms per token, 4.50 tokens per second) 2.58.499.963 I slot print_timing: id 0 | task 4774 | total time = 1401.05 ms / 1044 tokens 2.58.499.965 I slot print_timing: id 0 | task 4774 | graphs reused = 3521 2.58.499.966 I slot print_timing: id 0 | task 4774 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.500.015 I slot release: id 0 | task 4774 | stop processing: n_tokens = 1043, truncated = 0 2.58.609.753 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1043, t_last = 178404920 2.58.609.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.431 MiB) 2.58.664.296 I slot launch_slot_: id 0 | task 4786 | processing task, is_child = 0 2.58.752.771 I slot print_timing: id 1 | task 4777 | prompt eval time = 1176.88 ms / 809 tokens ( 1.45 ms per token, 687.41 tokens per second) 2.58.752.777 I slot print_timing: id 1 | task 4777 | eval time = 143.58 ms / 2 tokens ( 143.58 ms per token, 6.96 tokens per second) 2.58.752.778 I slot print_timing: id 1 | task 4777 | total time = 1320.46 ms / 811 tokens 2.58.752.779 I slot print_timing: id 1 | task 4777 | graphs reused = 3521 2.58.752.780 I slot print_timing: id 1 | task 4777 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.752.830 I slot release: id 1 | task 4777 | stop processing: n_tokens = 810, truncated = 0 2.58.753.193 I slot print_timing: id 2 | task 4778 | prompt eval time = 1174.08 ms / 799 tokens ( 1.47 ms per token, 680.53 tokens per second) 2.58.753.197 I slot print_timing: id 2 | task 4778 | eval time = 143.45 ms / 2 tokens ( 143.45 ms per token, 6.97 tokens per second) 2.58.753.198 I slot print_timing: id 2 | task 4778 | total time = 1317.53 ms / 801 tokens 2.58.753.198 I slot print_timing: id 2 | task 4778 | graphs reused = 3521 2.58.753.199 I slot print_timing: id 2 | task 4778 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.753.232 I slot release: id 2 | task 4778 | stop processing: n_tokens = 800, truncated = 0 2.58.839.958 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 178657735 2.58.840.032 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.900 MiB) 2.58.959.020 I slot launch_slot_: id 1 | task 4789 | processing task, is_child = 0 2.58.959.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.588 MiB) 2.59.008.678 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 178658137 2.59.008.883 I slot launch_slot_: id 2 | task 4790 | processing task, is_child = 0 2.59.585.948 I slot print_timing: id 3 | task 4783 | prompt eval time = 1103.80 ms / 845 tokens ( 1.31 ms per token, 765.54 tokens per second) 2.59.585.954 I slot print_timing: id 3 | task 4783 | eval time = 138.62 ms / 2 tokens ( 138.62 ms per token, 7.21 tokens per second) 2.59.585.955 I slot print_timing: id 3 | task 4783 | total time = 1242.41 ms / 847 tokens 2.59.585.956 I slot print_timing: id 3 | task 4783 | graphs reused = 3521 2.59.585.956 I slot print_timing: id 3 | task 4783 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.586.010 I slot release: id 3 | task 4783 | stop processing: n_tokens = 846, truncated = 0 2.59.832.815 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.888 2.59.832.944 I slot launch_slot_: id 3 | task 4795 | processing task, is_child = 0 3.00.050.859 I slot print_timing: id 0 | task 4786 | prompt eval time = 1168.49 ms / 839 tokens ( 1.39 ms per token, 718.02 tokens per second) 3.00.050.864 I slot print_timing: id 0 | task 4786 | eval time = 218.05 ms / 2 tokens ( 218.05 ms per token, 4.59 tokens per second) 3.00.050.865 I slot print_timing: id 0 | task 4786 | total time = 1386.54 ms / 841 tokens 3.00.050.867 I slot print_timing: id 0 | task 4786 | graphs reused = 3521 3.00.050.869 I slot print_timing: id 0 | task 4786 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.050.915 I slot release: id 0 | task 4786 | stop processing: n_tokens = 840, truncated = 0 3.00.105.264 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 840, t_last = 179955820 3.00.105.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.271 MiB) 3.00.147.693 I slot launch_slot_: id 0 | task 4798 | processing task, is_child = 0 3.00.206.143 I slot print_timing: id 1 | task 4789 | prompt eval time = 1095.21 ms / 910 tokens ( 1.20 ms per token, 830.89 tokens per second) 3.00.206.147 I slot print_timing: id 1 | task 4789 | eval time = 102.03 ms / 2 tokens ( 102.03 ms per token, 9.80 tokens per second) 3.00.206.149 I slot print_timing: id 1 | task 4789 | total time = 1197.23 ms / 912 tokens 3.00.206.149 I slot print_timing: id 1 | task 4789 | graphs reused = 3521 3.00.206.150 I slot print_timing: id 1 | task 4789 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.206.197 I slot release: id 1 | task 4789 | stop processing: n_tokens = 911, truncated = 0 3.00.206.499 I slot print_timing: id 2 | task 4790 | prompt eval time = 1092.28 ms / 901 tokens ( 1.21 ms per token, 824.88 tokens per second) 3.00.206.502 I slot print_timing: id 2 | task 4790 | eval time = 101.83 ms / 2 tokens ( 101.83 ms per token, 9.82 tokens per second) 3.00.206.503 I slot print_timing: id 2 | task 4790 | total time = 1194.11 ms / 903 tokens 3.00.206.503 I slot print_timing: id 2 | task 4790 | graphs reused = 3521 3.00.206.504 I slot print_timing: id 2 | task 4790 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.206.532 I slot release: id 2 | task 4790 | stop processing: n_tokens = 902, truncated = 0 3.00.206.861 I slot print_timing: id 3 | task 4795 | prompt eval time = 252.05 ms / 139 tokens ( 1.81 ms per token, 551.47 tokens per second) 3.00.206.864 I slot print_timing: id 3 | task 4795 | eval time = 101.60 ms / 2 tokens ( 101.60 ms per token, 9.84 tokens per second) 3.00.206.864 I slot print_timing: id 3 | task 4795 | total time = 353.65 ms / 141 tokens 3.00.206.865 I slot print_timing: id 3 | task 4795 | graphs reused = 3521 3.00.206.866 I slot print_timing: id 3 | task 4795 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.206.889 I slot release: id 3 | task 4795 | stop processing: n_tokens = 863, truncated = 0 3.00.223.976 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 180111102 3.00.224.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.240 MiB) 3.00.277.174 I slot launch_slot_: id 1 | task 4801 | processing task, is_child = 0 3.00.277.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.775 MiB) 3.00.324.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.087 MiB) 3.00.375.250 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 902, t_last = 180111438 3.00.375.443 I slot launch_slot_: id 2 | task 4802 | processing task, is_child = 0 3.00.375.503 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 180111795 3.00.375.664 I slot launch_slot_: id 3 | task 4803 | processing task, is_child = 0 3.01.324.613 I slot print_timing: id 0 | task 4798 | prompt eval time = 872.03 ms / 688 tokens ( 1.27 ms per token, 788.97 tokens per second) 3.01.324.619 I slot print_timing: id 0 | task 4798 | eval time = 304.87 ms / 2 tokens ( 304.87 ms per token, 3.28 tokens per second) 3.01.324.620 I slot print_timing: id 0 | task 4798 | total time = 1176.89 ms / 690 tokens 3.01.324.621 I slot print_timing: id 0 | task 4798 | graphs reused = 3521 3.01.324.622 I slot print_timing: id 0 | task 4798 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.324.660 I slot release: id 0 | task 4798 | stop processing: n_tokens = 689, truncated = 0 3.01.459.796 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 689, t_last = 181229565 3.01.459.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.338 MiB) 3.01.506.476 I slot launch_slot_: id 0 | task 4809 | processing task, is_child = 0 3.01.627.199 I slot print_timing: id 2 | task 4802 | prompt eval time = 1068.08 ms / 769 tokens ( 1.39 ms per token, 719.98 tokens per second) 3.01.627.205 I slot print_timing: id 2 | task 4802 | eval time = 167.40 ms / 2 tokens ( 167.40 ms per token, 5.97 tokens per second) 3.01.627.207 I slot print_timing: id 2 | task 4802 | total time = 1235.48 ms / 771 tokens 3.01.627.208 I slot print_timing: id 2 | task 4802 | graphs reused = 3521 3.01.627.208 I slot print_timing: id 2 | task 4802 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.627.258 I slot release: id 2 | task 4802 | stop processing: n_tokens = 770, truncated = 0 3.01.707.341 I slot print_timing: id 1 | task 4801 | prompt eval time = 1238.62 ms / 825 tokens ( 1.50 ms per token, 666.06 tokens per second) 3.01.707.348 I slot print_timing: id 1 | task 4801 | eval time = 80.47 ms / 2 tokens ( 80.47 ms per token, 12.43 tokens per second) 3.01.707.349 I slot print_timing: id 1 | task 4801 | total time = 1319.09 ms / 827 tokens 3.01.707.350 I slot print_timing: id 1 | task 4801 | graphs reused = 3521 3.01.707.351 I slot print_timing: id 1 | task 4801 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.707.398 I slot release: id 1 | task 4801 | stop processing: n_tokens = 826, truncated = 0 3.01.707.744 I slot print_timing: id 3 | task 4803 | prompt eval time = 1232.87 ms / 851 tokens ( 1.45 ms per token, 690.26 tokens per second) 3.01.707.747 I slot print_timing: id 3 | task 4803 | eval time = 79.72 ms / 2 tokens ( 79.72 ms per token, 12.54 tokens per second) 3.01.707.748 I slot print_timing: id 3 | task 4803 | total time = 1312.59 ms / 853 tokens 3.01.707.749 I slot print_timing: id 3 | task 4803 | graphs reused = 3521 3.01.707.750 I slot print_timing: id 3 | task 4803 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.707.782 I slot release: id 3 | task 4803 | stop processing: n_tokens = 852, truncated = 0 3.01.707.794 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 181532163 3.01.707.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.367 MiB) 3.01.757.957 I slot launch_slot_: id 2 | task 4812 | processing task, is_child = 0 3.01.758.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.399 MiB) 3.01.811.699 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.493 MiB) 3.01.863.397 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 181612303 3.01.863.593 I slot launch_slot_: id 1 | task 4813 | processing task, is_child = 0 3.01.863.653 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 852, t_last = 181612687 3.01.863.795 I slot launch_slot_: id 3 | task 4814 | processing task, is_child = 0 3.02.831.004 I slot print_timing: id 0 | task 4809 | prompt eval time = 1158.90 ms / 752 tokens ( 1.54 ms per token, 648.89 tokens per second) 3.02.831.011 I slot print_timing: id 0 | task 4809 | eval time = 165.60 ms / 2 tokens ( 165.60 ms per token, 6.04 tokens per second) 3.02.831.012 I slot print_timing: id 0 | task 4809 | total time = 1324.50 ms / 754 tokens 3.02.831.013 I slot print_timing: id 0 | task 4809 | graphs reused = 3521 3.02.831.014 I slot print_timing: id 0 | task 4809 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.831.060 I slot release: id 0 | task 4809 | stop processing: n_tokens = 753, truncated = 0 3.02.884.723 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 182735965 3.02.884.795 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.117 MiB) 3.02.935.992 I slot launch_slot_: id 0 | task 4820 | processing task, is_child = 0 3.02.991.352 I slot print_timing: id 1 | task 4813 | prompt eval time = 1009.40 ms / 719 tokens ( 1.40 ms per token, 712.31 tokens per second) 3.02.991.357 I slot print_timing: id 1 | task 4813 | eval time = 107.77 ms / 2 tokens ( 107.77 ms per token, 9.28 tokens per second) 3.02.991.358 I slot print_timing: id 1 | task 4813 | total time = 1117.17 ms / 721 tokens 3.02.991.359 I slot print_timing: id 1 | task 4813 | graphs reused = 3521 3.02.991.360 I slot print_timing: id 1 | task 4813 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.991.400 I slot release: id 1 | task 4813 | stop processing: n_tokens = 720, truncated = 0 3.02.991.699 I slot print_timing: id 2 | task 4812 | prompt eval time = 1006.53 ms / 713 tokens ( 1.41 ms per token, 708.38 tokens per second) 3.02.991.701 I slot print_timing: id 2 | task 4812 | eval time = 107.56 ms / 2 tokens ( 107.56 ms per token, 9.30 tokens per second) 3.02.991.702 I slot print_timing: id 2 | task 4812 | total time = 1114.09 ms / 715 tokens 3.02.991.702 I slot print_timing: id 2 | task 4812 | graphs reused = 3521 3.02.991.703 I slot print_timing: id 2 | task 4812 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.991.729 I slot release: id 2 | task 4812 | stop processing: n_tokens = 714, truncated = 0 3.02.992.043 I slot print_timing: id 3 | task 4814 | prompt eval time = 1003.74 ms / 736 tokens ( 1.36 ms per token, 733.26 tokens per second) 3.02.992.046 I slot print_timing: id 3 | task 4814 | eval time = 107.33 ms / 2 tokens ( 107.33 ms per token, 9.32 tokens per second) 3.02.992.047 I slot print_timing: id 3 | task 4814 | total time = 1111.07 ms / 738 tokens 3.02.992.047 I slot print_timing: id 3 | task 4814 | graphs reused = 3521 3.02.992.048 I slot print_timing: id 3 | task 4814 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.992.069 I slot release: id 3 | task 4814 | stop processing: n_tokens = 737, truncated = 0 3.03.009.345 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.876 3.03.009.464 I slot launch_slot_: id 1 | task 4823 | processing task, is_child = 0 3.03.009.525 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.594 MiB) 3.03.063.216 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.938 MiB) 3.03.112.512 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.884 3.03.112.649 I slot launch_slot_: id 2 | task 4824 | processing task, is_child = 0 3.03.112.706 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.856 3.03.112.802 I slot launch_slot_: id 3 | task 4825 | processing task, is_child = 0 3.03.546.178 I slot print_timing: id 1 | task 4823 | prompt eval time = 378.58 ms / 112 tokens ( 3.38 ms per token, 295.84 tokens per second) 3.03.546.183 I slot print_timing: id 1 | task 4823 | eval time = 44.41 ms / 2 tokens ( 44.41 ms per token, 22.52 tokens per second) 3.03.546.184 I slot print_timing: id 1 | task 4823 | total time = 423.00 ms / 114 tokens 3.03.546.184 I slot print_timing: id 1 | task 4823 | graphs reused = 3521 3.03.546.185 I slot print_timing: id 1 | task 4823 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.546.230 I slot release: id 1 | task 4823 | stop processing: n_tokens = 716, truncated = 0 3.03.546.489 I slot print_timing: id 2 | task 4824 | prompt eval time = 361.29 ms / 106 tokens ( 3.41 ms per token, 293.40 tokens per second) 3.03.546.492 I slot print_timing: id 2 | task 4824 | eval time = 44.10 ms / 2 tokens ( 44.10 ms per token, 22.68 tokens per second) 3.03.546.493 I slot print_timing: id 2 | task 4824 | total time = 405.38 ms / 108 tokens 3.03.546.494 I slot print_timing: id 2 | task 4824 | graphs reused = 3521 3.03.546.494 I slot print_timing: id 2 | task 4824 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.546.516 I slot release: id 2 | task 4824 | stop processing: n_tokens = 710, truncated = 0 3.03.546.775 I slot print_timing: id 3 | task 4825 | prompt eval time = 344.17 ms / 104 tokens ( 3.31 ms per token, 302.18 tokens per second) 3.03.546.778 I slot print_timing: id 3 | task 4825 | eval time = 43.82 ms / 2 tokens ( 43.82 ms per token, 22.82 tokens per second) 3.03.546.778 I slot print_timing: id 3 | task 4825 | total time = 387.99 ms / 106 tokens 3.03.546.779 I slot print_timing: id 3 | task 4825 | graphs reused = 3521 3.03.546.779 I slot print_timing: id 3 | task 4825 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.546.798 I slot release: id 3 | task 4825 | stop processing: n_tokens = 708, truncated = 0 3.03.562.244 I slot print_timing: id 0 | task 4820 | prompt eval time = 609.91 ms / 710 tokens ( 0.86 ms per token, 1164.10 tokens per second) 3.03.562.250 I slot print_timing: id 0 | task 4820 | eval time = 16.32 ms / 2 tokens ( 16.32 ms per token, 61.29 tokens per second) 3.03.562.251 I slot print_timing: id 0 | task 4820 | total time = 626.23 ms / 712 tokens 3.03.562.252 I slot print_timing: id 0 | task 4820 | graphs reused = 3521 3.03.562.253 I slot print_timing: id 0 | task 4820 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.562.287 I slot release: id 0 | task 4820 | stop processing: n_tokens = 711, truncated = 0 3.03.562.300 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.893 3.03.562.424 I slot launch_slot_: id 2 | task 4830 | processing task, is_child = 0 3.03.562.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.626 MiB) 3.03.607.121 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.187 MiB) 3.03.657.204 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.467 MiB) 3.03.708.444 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.893 3.03.708.584 I slot launch_slot_: id 3 | task 4831 | processing task, is_child = 0 3.03.708.691 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.887 3.03.708.788 I slot launch_slot_: id 0 | task 4832 | processing task, is_child = 0 3.03.708.838 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.881 3.03.708.927 I slot launch_slot_: id 1 | task 4833 | processing task, is_child = 0 3.04.027.864 I slot print_timing: id 0 | task 4832 | prompt eval time = 298.78 ms / 148 tokens ( 2.02 ms per token, 495.34 tokens per second) 3.04.027.870 I slot print_timing: id 0 | task 4832 | eval time = 20.14 ms / 2 tokens ( 20.14 ms per token, 49.66 tokens per second) 3.04.027.871 I slot print_timing: id 0 | task 4832 | total time = 318.92 ms / 150 tokens 3.04.027.871 I slot print_timing: id 0 | task 4832 | graphs reused = 3521 3.04.027.872 I slot print_timing: id 0 | task 4832 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.027.913 I slot release: id 0 | task 4832 | stop processing: n_tokens = 752, truncated = 0 3.04.028.146 I slot print_timing: id 1 | task 4833 | prompt eval time = 281.47 ms / 106 tokens ( 2.66 ms per token, 376.59 tokens per second) 3.04.028.149 I slot print_timing: id 1 | task 4833 | eval time = 19.70 ms / 2 tokens ( 19.70 ms per token, 50.75 tokens per second) 3.04.028.150 I slot print_timing: id 1 | task 4833 | total time = 301.18 ms / 108 tokens 3.04.028.150 I slot print_timing: id 1 | task 4833 | graphs reused = 3521 3.04.028.151 I slot print_timing: id 1 | task 4833 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.028.172 I slot release: id 1 | task 4833 | stop processing: n_tokens = 710, truncated = 0 3.04.028.400 I slot print_timing: id 2 | task 4830 | prompt eval time = 264.39 ms / 114 tokens ( 2.32 ms per token, 431.19 tokens per second) 3.04.028.403 I slot print_timing: id 2 | task 4830 | eval time = 19.25 ms / 2 tokens ( 19.25 ms per token, 51.94 tokens per second) 3.04.028.403 I slot print_timing: id 2 | task 4830 | total time = 283.64 ms / 116 tokens 3.04.028.404 I slot print_timing: id 2 | task 4830 | graphs reused = 3521 3.04.028.404 I slot print_timing: id 2 | task 4830 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.028.424 I slot release: id 2 | task 4830 | stop processing: n_tokens = 718, truncated = 0 3.04.028.666 I slot print_timing: id 3 | task 4831 | prompt eval time = 246.54 ms / 113 tokens ( 2.18 ms per token, 458.33 tokens per second) 3.04.028.669 I slot print_timing: id 3 | task 4831 | eval time = 18.79 ms / 2 tokens ( 18.79 ms per token, 53.21 tokens per second) 3.04.028.669 I slot print_timing: id 3 | task 4831 | total time = 265.34 ms / 115 tokens 3.04.028.670 I slot print_timing: id 3 | task 4831 | graphs reused = 3521 3.04.028.670 I slot print_timing: id 3 | task 4831 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.028.688 I slot release: id 3 | task 4831 | stop processing: n_tokens = 717, truncated = 0 3.04.041.782 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 752, t_last = 183932818 3.04.041.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 337.035 MiB) 3.04.101.339 I slot launch_slot_: id 0 | task 4837 | processing task, is_child = 0 3.04.101.397 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.314 MiB) 3.04.205.791 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.642 MiB) 3.04.259.124 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 183933077 3.04.259.326 I slot launch_slot_: id 1 | task 4838 | processing task, is_child = 0 3.04.259.422 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 718, t_last = 183933329 3.04.259.555 I slot launch_slot_: id 2 | task 4839 | processing task, is_child = 0 3.04.259.604 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 183933593 3.04.259.734 I slot launch_slot_: id 3 | task 4840 | processing task, is_child = 0 3.05.676.822 I slot print_timing: id 0 | task 4837 | prompt eval time = 1397.26 ms / 896 tokens ( 1.56 ms per token, 641.25 tokens per second) 3.05.676.827 I slot print_timing: id 0 | task 4837 | eval time = 19.81 ms / 2 tokens ( 19.81 ms per token, 50.48 tokens per second) 3.05.676.828 I slot print_timing: id 0 | task 4837 | total time = 1417.07 ms / 898 tokens 3.05.676.828 I slot print_timing: id 0 | task 4837 | graphs reused = 3521 3.05.676.829 I slot print_timing: id 0 | task 4837 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.676.876 I slot release: id 0 | task 4837 | stop processing: n_tokens = 897, truncated = 0 3.05.677.118 I slot print_timing: id 1 | task 4838 | prompt eval time = 1394.46 ms / 1091 tokens ( 1.28 ms per token, 782.38 tokens per second) 3.05.677.121 I slot print_timing: id 1 | task 4838 | eval time = 19.54 ms / 2 tokens ( 19.54 ms per token, 51.17 tokens per second) 3.05.677.122 I slot print_timing: id 1 | task 4838 | total time = 1414.00 ms / 1093 tokens 3.05.677.122 I slot print_timing: id 1 | task 4838 | graphs reused = 3521 3.05.677.123 I slot print_timing: id 1 | task 4838 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.677.155 I slot release: id 1 | task 4838 | stop processing: n_tokens = 1092, truncated = 0 3.05.677.393 I slot print_timing: id 2 | task 4839 | prompt eval time = 1391.50 ms / 880 tokens ( 1.58 ms per token, 632.41 tokens per second) 3.05.677.395 I slot print_timing: id 2 | task 4839 | eval time = 19.27 ms / 2 tokens ( 19.27 ms per token, 51.89 tokens per second) 3.05.677.396 I slot print_timing: id 2 | task 4839 | total time = 1410.77 ms / 882 tokens 3.05.677.396 I slot print_timing: id 2 | task 4839 | graphs reused = 3521 3.05.677.397 I slot print_timing: id 2 | task 4839 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.677.424 I slot release: id 2 | task 4839 | stop processing: n_tokens = 881, truncated = 0 3.05.677.667 I slot print_timing: id 3 | task 4840 | prompt eval time = 1388.67 ms / 1082 tokens ( 1.28 ms per token, 779.16 tokens per second) 3.05.677.670 I slot print_timing: id 3 | task 4840 | eval time = 19.00 ms / 2 tokens ( 19.00 ms per token, 52.63 tokens per second) 3.05.677.671 I slot print_timing: id 3 | task 4840 | total time = 1407.67 ms / 1084 tokens 3.05.677.672 I slot print_timing: id 3 | task 4840 | graphs reused = 3521 3.05.677.672 I slot print_timing: id 3 | task 4840 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.677.699 I slot release: id 3 | task 4840 | stop processing: n_tokens = 1083, truncated = 0 3.05.691.328 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.895 3.05.691.477 I slot launch_slot_: id 1 | task 4848 | processing task, is_child = 0 3.05.691.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.331 MiB) 3.05.736.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.202 MiB) 3.05.789.597 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.981 MiB) 3.05.844.995 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.901 3.05.845.140 I slot launch_slot_: id 3 | task 4849 | processing task, is_child = 0 3.05.845.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 185581781 3.05.859.516 I slot launch_slot_: id 0 | task 4850 | processing task, is_child = 0 3.05.859.582 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 185582329 3.05.859.725 I slot launch_slot_: id 2 | task 4851 | processing task, is_child = 0 3.06.367.311 I slot print_timing: id 0 | task 4850 | prompt eval time = 415.35 ms / 175 tokens ( 2.37 ms per token, 421.33 tokens per second) 3.06.367.317 I slot print_timing: id 0 | task 4850 | eval time = 92.22 ms / 2 tokens ( 92.22 ms per token, 10.84 tokens per second) 3.06.367.318 I slot print_timing: id 0 | task 4850 | total time = 507.57 ms / 177 tokens 3.06.367.318 I slot print_timing: id 0 | task 4850 | graphs reused = 3521 3.06.367.319 I slot print_timing: id 0 | task 4850 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.367.366 I slot release: id 0 | task 4850 | stop processing: n_tokens = 1081, truncated = 0 3.06.367.715 I slot print_timing: id 1 | task 4848 | prompt eval time = 396.47 ms / 180 tokens ( 2.20 ms per token, 454.00 tokens per second) 3.06.367.718 I slot print_timing: id 1 | task 4848 | eval time = 92.04 ms / 2 tokens ( 92.04 ms per token, 10.86 tokens per second) 3.06.367.718 I slot print_timing: id 1 | task 4848 | total time = 488.51 ms / 182 tokens 3.06.367.719 I slot print_timing: id 1 | task 4848 | graphs reused = 3521 3.06.367.720 I slot print_timing: id 1 | task 4848 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.367.749 I slot release: id 1 | task 4848 | stop processing: n_tokens = 1086, truncated = 0 3.06.368.090 I slot print_timing: id 3 | task 4849 | prompt eval time = 374.16 ms / 166 tokens ( 2.25 ms per token, 443.66 tokens per second) 3.06.368.093 I slot print_timing: id 3 | task 4849 | eval time = 91.86 ms / 2 tokens ( 91.86 ms per token, 10.89 tokens per second) 3.06.368.094 I slot print_timing: id 3 | task 4849 | total time = 466.02 ms / 168 tokens 3.06.368.095 I slot print_timing: id 3 | task 4849 | graphs reused = 3521 3.06.368.095 I slot print_timing: id 3 | task 4849 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.368.120 I slot release: id 3 | task 4849 | stop processing: n_tokens = 1072, truncated = 0 3.06.384.400 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.904 3.06.384.506 I slot launch_slot_: id 0 | task 4856 | processing task, is_child = 0 3.06.489.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.988 MiB) 3.06.532.184 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.900 3.06.532.334 I slot launch_slot_: id 1 | task 4857 | processing task, is_child = 0 3.06.532.413 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.911 3.06.532.507 I slot launch_slot_: id 3 | task 4858 | processing task, is_child = 0 3.06.914.787 I slot print_timing: id 0 | task 4856 | prompt eval time = 362.37 ms / 168 tokens ( 2.16 ms per token, 463.61 tokens per second) 3.06.914.793 I slot print_timing: id 0 | task 4856 | eval time = 19.89 ms / 2 tokens ( 19.89 ms per token, 50.28 tokens per second) 3.06.914.794 I slot print_timing: id 0 | task 4856 | total time = 382.26 ms / 170 tokens 3.06.914.795 I slot print_timing: id 0 | task 4856 | graphs reused = 3521 3.06.914.796 I slot print_timing: id 0 | task 4856 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.914.843 I slot release: id 0 | task 4856 | stop processing: n_tokens = 1074, truncated = 0 3.06.915.156 I slot print_timing: id 1 | task 4857 | prompt eval time = 343.32 ms / 177 tokens ( 1.94 ms per token, 515.56 tokens per second) 3.06.915.159 I slot print_timing: id 1 | task 4857 | eval time = 19.67 ms / 2 tokens ( 19.67 ms per token, 50.85 tokens per second) 3.06.915.160 I slot print_timing: id 1 | task 4857 | total time = 362.99 ms / 179 tokens 3.06.915.160 I slot print_timing: id 1 | task 4857 | graphs reused = 3521 3.06.915.161 I slot print_timing: id 1 | task 4857 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.915.189 I slot release: id 1 | task 4857 | stop processing: n_tokens = 1083, truncated = 0 3.06.915.512 I slot print_timing: id 2 | task 4851 | prompt eval time = 997.35 ms / 1079 tokens ( 0.92 ms per token, 1081.87 tokens per second) 3.06.915.515 I slot print_timing: id 2 | task 4851 | eval time = 19.46 ms / 2 tokens ( 19.46 ms per token, 51.38 tokens per second) 3.06.915.515 I slot print_timing: id 2 | task 4851 | total time = 1016.82 ms / 1081 tokens 3.06.915.516 I slot print_timing: id 2 | task 4851 | graphs reused = 3521 3.06.915.516 I slot print_timing: id 2 | task 4851 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.915.542 I slot release: id 2 | task 4851 | stop processing: n_tokens = 1080, truncated = 0 3.06.915.853 I slot print_timing: id 3 | task 4858 | prompt eval time = 312.43 ms / 183 tokens ( 1.71 ms per token, 585.73 tokens per second) 3.06.915.856 I slot print_timing: id 3 | task 4858 | eval time = 19.23 ms / 2 tokens ( 19.23 ms per token, 52.00 tokens per second) 3.06.915.857 I slot print_timing: id 3 | task 4858 | total time = 331.66 ms / 185 tokens 3.06.915.857 I slot print_timing: id 3 | task 4858 | graphs reused = 3521 3.06.915.858 I slot print_timing: id 3 | task 4858 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.915.882 I slot release: id 3 | task 4858 | stop processing: n_tokens = 1089, truncated = 0 3.06.928.927 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.910 3.06.929.054 I slot launch_slot_: id 0 | task 4862 | processing task, is_child = 0 3.06.929.138 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.083 MiB) 3.06.982.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.957 MiB) 3.07.033.021 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.395 MiB) 3.07.088.281 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.902 3.07.088.424 I slot launch_slot_: id 1 | task 4863 | processing task, is_child = 0 3.07.088.565 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.905 3.07.088.658 I slot launch_slot_: id 2 | task 4864 | processing task, is_child = 0 3.07.088.728 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.897 3.07.088.819 I slot launch_slot_: id 3 | task 4865 | processing task, is_child = 0 3.07.480.275 I slot print_timing: id 0 | task 4862 | prompt eval time = 364.91 ms / 178 tokens ( 2.05 ms per token, 487.79 tokens per second) 3.07.480.280 I slot print_timing: id 0 | task 4862 | eval time = 26.52 ms / 2 tokens ( 26.52 ms per token, 37.70 tokens per second) 3.07.480.282 I slot print_timing: id 0 | task 4862 | total time = 391.44 ms / 180 tokens 3.07.480.283 I slot print_timing: id 0 | task 4862 | graphs reused = 3521 3.07.480.284 I slot print_timing: id 0 | task 4862 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.480.332 I slot release: id 0 | task 4862 | stop processing: n_tokens = 1084, truncated = 0 3.07.480.590 I slot print_timing: id 1 | task 4863 | prompt eval time = 347.00 ms / 171 tokens ( 2.03 ms per token, 492.80 tokens per second) 3.07.480.593 I slot print_timing: id 1 | task 4863 | eval time = 25.05 ms / 2 tokens ( 25.05 ms per token, 39.92 tokens per second) 3.07.480.594 I slot print_timing: id 1 | task 4863 | total time = 372.05 ms / 173 tokens 3.07.480.594 I slot print_timing: id 1 | task 4863 | graphs reused = 3521 3.07.480.595 I slot print_timing: id 1 | task 4863 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.480.622 I slot release: id 1 | task 4863 | stop processing: n_tokens = 1077, truncated = 0 3.07.480.874 I slot print_timing: id 2 | task 4864 | prompt eval time = 329.15 ms / 170 tokens ( 1.94 ms per token, 516.48 tokens per second) 3.07.480.877 I slot print_timing: id 2 | task 4864 | eval time = 23.47 ms / 2 tokens ( 23.47 ms per token, 42.61 tokens per second) 3.07.480.877 I slot print_timing: id 2 | task 4864 | total time = 352.62 ms / 172 tokens 3.07.480.878 I slot print_timing: id 2 | task 4864 | graphs reused = 3521 3.07.480.878 I slot print_timing: id 2 | task 4864 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.480.903 I slot release: id 2 | task 4864 | stop processing: n_tokens = 1076, truncated = 0 3.07.481.171 I slot print_timing: id 3 | task 4865 | prompt eval time = 311.05 ms / 175 tokens ( 1.78 ms per token, 562.61 tokens per second) 3.07.481.174 I slot print_timing: id 3 | task 4865 | eval time = 21.86 ms / 2 tokens ( 21.86 ms per token, 45.74 tokens per second) 3.07.481.175 I slot print_timing: id 3 | task 4865 | total time = 332.91 ms / 177 tokens 3.07.481.175 I slot print_timing: id 3 | task 4865 | graphs reused = 3521 3.07.481.176 I slot print_timing: id 3 | task 4865 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.481.199 I slot release: id 3 | task 4865 | stop processing: n_tokens = 1081, truncated = 0 3.07.494.037 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.901 3.07.494.156 I slot launch_slot_: id 0 | task 4870 | processing task, is_child = 0 3.07.494.240 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.240 MiB) 3.07.541.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.871 MiB) 3.07.596.176 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.584 MiB) 3.07.642.838 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.907 3.07.642.979 I slot launch_slot_: id 1 | task 4869 | processing task, is_child = 0 3.07.643.126 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1076, t_last = 187385808 3.07.643.285 I slot launch_slot_: id 2 | task 4871 | processing task, is_child = 0 3.07.643.353 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1081, t_last = 187386104 3.07.643.507 I slot launch_slot_: id 3 | task 4872 | processing task, is_child = 0 3.08.178.656 I slot print_timing: id 0 | task 4870 | prompt eval time = 437.66 ms / 174 tokens ( 2.52 ms per token, 397.57 tokens per second) 3.08.178.661 I slot print_timing: id 0 | task 4870 | eval time = 97.47 ms / 2 tokens ( 97.47 ms per token, 10.26 tokens per second) 3.08.178.662 I slot print_timing: id 0 | task 4870 | total time = 535.13 ms / 176 tokens 3.08.178.663 I slot print_timing: id 0 | task 4870 | graphs reused = 3521 3.08.178.664 I slot print_timing: id 0 | task 4870 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.178.711 I slot release: id 0 | task 4870 | stop processing: n_tokens = 1080, truncated = 0 3.08.179.028 I slot print_timing: id 1 | task 4869 | prompt eval time = 418.79 ms / 173 tokens ( 2.42 ms per token, 413.10 tokens per second) 3.08.179.032 I slot print_timing: id 1 | task 4869 | eval time = 97.06 ms / 2 tokens ( 97.06 ms per token, 10.30 tokens per second) 3.08.179.033 I slot print_timing: id 1 | task 4869 | total time = 515.84 ms / 175 tokens 3.08.179.033 I slot print_timing: id 1 | task 4869 | graphs reused = 3521 3.08.179.034 I slot print_timing: id 1 | task 4869 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.179.062 I slot release: id 1 | task 4869 | stop processing: n_tokens = 1079, truncated = 0 3.08.398.227 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1080, t_last = 188083616 3.08.398.316 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.271 MiB) 3.08.449.632 I slot launch_slot_: id 0 | task 4877 | processing task, is_child = 0 3.08.449.720 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.522 MiB) 3.08.522.596 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1079, t_last = 188083967 3.08.522.826 I slot launch_slot_: id 1 | task 4878 | processing task, is_child = 0 3.09.053.313 I slot print_timing: id 2 | task 4871 | prompt eval time = 1245.48 ms / 1031 tokens ( 1.21 ms per token, 827.80 tokens per second) 3.09.053.318 I slot print_timing: id 2 | task 4871 | eval time = 124.77 ms / 2 tokens ( 124.77 ms per token, 8.01 tokens per second) 3.09.053.319 I slot print_timing: id 2 | task 4871 | total time = 1370.25 ms / 1033 tokens 3.09.053.320 I slot print_timing: id 2 | task 4871 | graphs reused = 3521 3.09.053.321 I slot print_timing: id 2 | task 4871 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.053.371 I slot release: id 2 | task 4871 | stop processing: n_tokens = 1032, truncated = 0 3.09.053.675 I slot print_timing: id 3 | task 4872 | prompt eval time = 1242.69 ms / 1017 tokens ( 1.22 ms per token, 818.39 tokens per second) 3.09.053.678 I slot print_timing: id 3 | task 4872 | eval time = 124.44 ms / 2 tokens ( 124.44 ms per token, 8.04 tokens per second) 3.09.053.679 I slot print_timing: id 3 | task 4872 | total time = 1367.13 ms / 1019 tokens 3.09.053.680 I slot print_timing: id 3 | task 4872 | graphs reused = 3521 3.09.053.680 I slot print_timing: id 3 | task 4872 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.053.710 I slot release: id 3 | task 4872 | stop processing: n_tokens = 1018, truncated = 0 3.09.235.632 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.878 3.09.235.767 I slot launch_slot_: id 2 | task 4883 | processing task, is_child = 0 3.09.235.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.743 MiB) 3.09.289.671 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.890 3.09.289.821 I slot launch_slot_: id 3 | task 4884 | processing task, is_child = 0 3.09.659.870 I slot print_timing: id 0 | task 4877 | prompt eval time = 1116.97 ms / 1071 tokens ( 1.04 ms per token, 958.84 tokens per second) 3.09.659.875 I slot print_timing: id 0 | task 4877 | eval time = 20.05 ms / 2 tokens ( 20.05 ms per token, 49.88 tokens per second) 3.09.659.876 I slot print_timing: id 0 | task 4877 | total time = 1137.02 ms / 1073 tokens 3.09.659.877 I slot print_timing: id 0 | task 4877 | graphs reused = 3521 3.09.659.878 I slot print_timing: id 0 | task 4877 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.659.928 I slot release: id 0 | task 4877 | stop processing: n_tokens = 1072, truncated = 0 3.09.660.238 I slot print_timing: id 1 | task 4878 | prompt eval time = 1114.07 ms / 1106 tokens ( 1.01 ms per token, 992.76 tokens per second) 3.09.660.241 I slot print_timing: id 1 | task 4878 | eval time = 19.83 ms / 2 tokens ( 19.83 ms per token, 50.43 tokens per second) 3.09.660.242 I slot print_timing: id 1 | task 4878 | total time = 1133.90 ms / 1108 tokens 3.09.660.242 I slot print_timing: id 1 | task 4878 | graphs reused = 3521 3.09.660.243 I slot print_timing: id 1 | task 4878 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.660.277 I slot release: id 1 | task 4878 | stop processing: n_tokens = 1107, truncated = 0 3.09.660.587 I slot print_timing: id 2 | task 4883 | prompt eval time = 330.92 ms / 152 tokens ( 2.18 ms per token, 459.33 tokens per second) 3.09.660.590 I slot print_timing: id 2 | task 4883 | eval time = 19.60 ms / 2 tokens ( 19.60 ms per token, 51.01 tokens per second) 3.09.660.591 I slot print_timing: id 2 | task 4883 | total time = 350.52 ms / 154 tokens 3.09.660.591 I slot print_timing: id 2 | task 4883 | graphs reused = 3521 3.09.660.592 I slot print_timing: id 2 | task 4883 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.660.618 I slot release: id 2 | task 4883 | stop processing: n_tokens = 1031, truncated = 0 3.09.660.914 I slot print_timing: id 3 | task 4884 | prompt eval time = 311.84 ms / 167 tokens ( 1.87 ms per token, 535.53 tokens per second) 3.09.660.917 I slot print_timing: id 3 | task 4884 | eval time = 19.35 ms / 2 tokens ( 19.35 ms per token, 51.67 tokens per second) 3.09.660.917 I slot print_timing: id 3 | task 4884 | total time = 331.20 ms / 169 tokens 3.09.660.918 I slot print_timing: id 3 | task 4884 | graphs reused = 3521 3.09.660.919 I slot print_timing: id 3 | task 4884 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.660.944 I slot release: id 3 | task 4884 | stop processing: n_tokens = 1046, truncated = 0 3.09.674.222 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1072, t_last = 189564833 3.09.674.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.461 MiB) 3.09.722.709 I slot launch_slot_: id 0 | task 4888 | processing task, is_child = 0 3.09.722.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.242 MiB) 3.09.772.315 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.800 MiB) 3.09.821.236 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.333 MiB) 3.09.872.212 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1107, t_last = 189565182 3.09.872.423 I slot launch_slot_: id 1 | task 4889 | processing task, is_child = 0 3.09.872.547 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 189565523 3.09.872.696 I slot launch_slot_: id 2 | task 4890 | processing task, is_child = 0 3.09.872.758 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1046, t_last = 189565849 3.09.872.901 I slot launch_slot_: id 3 | task 4891 | processing task, is_child = 0 3.11.018.889 I slot print_timing: id 1 | task 4889 | prompt eval time = 1097.44 ms / 753 tokens ( 1.46 ms per token, 686.14 tokens per second) 3.11.018.894 I slot print_timing: id 1 | task 4889 | eval time = 44.99 ms / 2 tokens ( 44.99 ms per token, 22.23 tokens per second) 3.11.018.895 I slot print_timing: id 1 | task 4889 | total time = 1142.44 ms / 755 tokens 3.11.018.895 I slot print_timing: id 1 | task 4889 | graphs reused = 3521 3.11.018.896 I slot print_timing: id 1 | task 4889 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.018.938 I slot release: id 1 | task 4889 | stop processing: n_tokens = 754, truncated = 0 3.11.019.206 I slot print_timing: id 2 | task 4890 | prompt eval time = 1094.67 ms / 729 tokens ( 1.50 ms per token, 665.95 tokens per second) 3.11.019.209 I slot print_timing: id 2 | task 4890 | eval time = 44.68 ms / 2 tokens ( 44.68 ms per token, 22.38 tokens per second) 3.11.019.210 I slot print_timing: id 2 | task 4890 | total time = 1139.35 ms / 731 tokens 3.11.019.210 I slot print_timing: id 2 | task 4890 | graphs reused = 3521 3.11.019.211 I slot print_timing: id 2 | task 4890 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.019.233 I slot release: id 2 | task 4890 | stop processing: n_tokens = 730, truncated = 0 3.11.019.502 I slot print_timing: id 3 | task 4891 | prompt eval time = 1091.80 ms / 740 tokens ( 1.48 ms per token, 677.78 tokens per second) 3.11.019.505 I slot print_timing: id 3 | task 4891 | eval time = 44.43 ms / 2 tokens ( 44.43 ms per token, 22.51 tokens per second) 3.11.019.505 I slot print_timing: id 3 | task 4891 | total time = 1136.22 ms / 742 tokens 3.11.019.506 I slot print_timing: id 3 | task 4891 | graphs reused = 3521 3.11.019.506 I slot print_timing: id 3 | task 4891 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.019.527 I slot release: id 3 | task 4891 | stop processing: n_tokens = 741, truncated = 0 3.11.034.815 I slot print_timing: id 0 | task 4888 | prompt eval time = 1145.70 ms / 797 tokens ( 1.44 ms per token, 695.64 tokens per second) 3.11.034.820 I slot print_timing: id 0 | task 4888 | eval time = 16.20 ms / 2 tokens ( 16.20 ms per token, 61.74 tokens per second) 3.11.034.821 I slot print_timing: id 0 | task 4888 | total time = 1161.90 ms / 799 tokens 3.11.034.821 I slot print_timing: id 0 | task 4888 | graphs reused = 3521 3.11.034.822 I slot print_timing: id 0 | task 4888 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.034.857 I slot release: id 0 | task 4888 | stop processing: n_tokens = 798, truncated = 0 3.11.034.869 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.816 3.11.035.003 I slot launch_slot_: id 0 | task 4899 | processing task, is_child = 0 3.11.035.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.085 MiB) 3.11.088.752 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.898 MiB) 3.11.140.128 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.802 MiB) 3.11.190.588 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.866 3.11.190.729 I slot launch_slot_: id 1 | task 4900 | processing task, is_child = 0 3.11.190.836 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.892 3.11.190.929 I slot launch_slot_: id 2 | task 4901 | processing task, is_child = 0 3.11.190.982 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.862 (> 0.100 thold), f_keep = 0.879 3.11.191.064 I slot launch_slot_: id 3 | task 4902 | processing task, is_child = 0 3.11.522.485 I slot print_timing: id 0 | task 4899 | prompt eval time = 311.77 ms / 123 tokens ( 2.53 ms per token, 394.52 tokens per second) 3.11.522.491 I slot print_timing: id 0 | task 4899 | eval time = 19.63 ms / 2 tokens ( 19.63 ms per token, 50.95 tokens per second) 3.11.522.492 I slot print_timing: id 0 | task 4899 | total time = 331.40 ms / 125 tokens 3.11.522.493 I slot print_timing: id 0 | task 4899 | graphs reused = 3521 3.11.522.494 I slot print_timing: id 0 | task 4899 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.522.540 I slot release: id 0 | task 4899 | stop processing: n_tokens = 747, truncated = 0 3.11.522.833 I slot print_timing: id 1 | task 4900 | prompt eval time = 294.90 ms / 116 tokens ( 2.54 ms per token, 393.35 tokens per second) 3.11.522.836 I slot print_timing: id 1 | task 4900 | eval time = 19.40 ms / 2 tokens ( 19.40 ms per token, 51.54 tokens per second) 3.11.522.837 I slot print_timing: id 1 | task 4900 | total time = 314.31 ms / 118 tokens 3.11.522.838 I slot print_timing: id 1 | task 4900 | graphs reused = 3521 3.11.522.839 I slot print_timing: id 1 | task 4900 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.522.869 I slot release: id 1 | task 4900 | stop processing: n_tokens = 740, truncated = 0 3.11.523.149 I slot print_timing: id 2 | task 4901 | prompt eval time = 275.99 ms / 110 tokens ( 2.51 ms per token, 398.56 tokens per second) 3.11.523.153 I slot print_timing: id 2 | task 4901 | eval time = 19.16 ms / 2 tokens ( 19.16 ms per token, 52.18 tokens per second) 3.11.523.154 I slot print_timing: id 2 | task 4901 | total time = 295.16 ms / 112 tokens 3.11.523.155 I slot print_timing: id 2 | task 4901 | graphs reused = 3521 3.11.523.156 I slot print_timing: id 2 | task 4901 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.523.183 I slot release: id 2 | task 4901 | stop processing: n_tokens = 734, truncated = 0 3.11.523.475 I slot print_timing: id 3 | task 4902 | prompt eval time = 257.10 ms / 132 tokens ( 1.95 ms per token, 513.41 tokens per second) 3.11.523.480 I slot print_timing: id 3 | task 4902 | eval time = 18.91 ms / 2 tokens ( 18.91 ms per token, 52.89 tokens per second) 3.11.523.481 I slot print_timing: id 3 | task 4902 | total time = 276.01 ms / 134 tokens 3.11.523.482 I slot print_timing: id 3 | task 4902 | graphs reused = 3521 3.11.523.483 I slot print_timing: id 3 | task 4902 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.523.509 I slot release: id 3 | task 4902 | stop processing: n_tokens = 756, truncated = 0 3.11.536.248 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.871 3.11.536.401 I slot launch_slot_: id 0 | task 4906 | processing task, is_child = 0 3.11.536.481 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.582 MiB) 3.11.589.540 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.301 MiB) 3.11.638.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 3.11.682.616 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 191427774 3.11.682.816 I slot launch_slot_: id 1 | task 4907 | processing task, is_child = 0 3.11.682.915 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 734, t_last = 191428088 3.11.683.053 I slot launch_slot_: id 2 | task 4908 | processing task, is_child = 0 3.11.683.104 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 191428414 3.11.683.244 I slot launch_slot_: id 3 | task 4909 | processing task, is_child = 0 3.12.227.942 I slot print_timing: id 0 | task 4906 | prompt eval time = 410.29 ms / 124 tokens ( 3.31 ms per token, 302.23 tokens per second) 3.12.227.948 I slot print_timing: id 0 | task 4906 | eval time = 134.39 ms / 2 tokens ( 134.39 ms per token, 7.44 tokens per second) 3.12.227.949 I slot print_timing: id 0 | task 4906 | total time = 544.68 ms / 126 tokens 3.12.227.950 I slot print_timing: id 0 | task 4906 | graphs reused = 3521 3.12.227.950 I slot print_timing: id 0 | task 4906 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.227.991 I slot release: id 0 | task 4906 | stop processing: n_tokens = 748, truncated = 0 3.12.566.944 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 192132896 3.12.567.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.644 MiB) 3.12.615.470 I slot launch_slot_: id 0 | task 4914 | processing task, is_child = 0 3.13.048.506 I slot print_timing: id 1 | task 4907 | prompt eval time = 1274.72 ms / 955 tokens ( 1.33 ms per token, 749.18 tokens per second) 3.13.048.511 I slot print_timing: id 1 | task 4907 | eval time = 72.84 ms / 2 tokens ( 72.84 ms per token, 13.73 tokens per second) 3.13.048.512 I slot print_timing: id 1 | task 4907 | total time = 1347.56 ms / 957 tokens 3.13.048.513 I slot print_timing: id 1 | task 4907 | graphs reused = 3521 3.13.048.515 I slot print_timing: id 1 | task 4907 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.048.565 I slot release: id 1 | task 4907 | stop processing: n_tokens = 956, truncated = 0 3.13.048.850 I slot print_timing: id 2 | task 4908 | prompt eval time = 1271.83 ms / 990 tokens ( 1.28 ms per token, 778.41 tokens per second) 3.13.048.853 I slot print_timing: id 2 | task 4908 | eval time = 72.63 ms / 2 tokens ( 72.63 ms per token, 13.77 tokens per second) 3.13.048.854 I slot print_timing: id 2 | task 4908 | total time = 1344.46 ms / 992 tokens 3.13.048.854 I slot print_timing: id 2 | task 4908 | graphs reused = 3521 3.13.048.855 I slot print_timing: id 2 | task 4908 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.048.885 I slot release: id 2 | task 4908 | stop processing: n_tokens = 991, truncated = 0 3.13.049.159 I slot print_timing: id 3 | task 4909 | prompt eval time = 1268.93 ms / 973 tokens ( 1.30 ms per token, 766.78 tokens per second) 3.13.049.162 I slot print_timing: id 3 | task 4909 | eval time = 72.39 ms / 2 tokens ( 72.39 ms per token, 13.81 tokens per second) 3.13.049.163 I slot print_timing: id 3 | task 4909 | total time = 1341.32 ms / 975 tokens 3.13.049.163 I slot print_timing: id 3 | task 4909 | graphs reused = 3521 3.13.049.164 I slot print_timing: id 3 | task 4909 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.049.190 I slot release: id 3 | task 4909 | stop processing: n_tokens = 974, truncated = 0 3.13.065.021 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 192953470 3.13.065.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.394 MiB) 3.13.153.365 I slot launch_slot_: id 1 | task 4920 | processing task, is_child = 0 3.13.153.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.770 MiB) 3.13.202.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.457 MiB) 3.13.249.253 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 192953790 3.13.249.454 I slot launch_slot_: id 2 | task 4919 | processing task, is_child = 0 3.13.249.517 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 974, t_last = 192954095 3.13.249.662 I slot launch_slot_: id 3 | task 4921 | processing task, is_child = 0 3.14.186.541 I slot print_timing: id 0 | task 4914 | prompt eval time = 1150.52 ms / 1044 tokens ( 1.10 ms per token, 907.42 tokens per second) 3.14.186.546 I slot print_timing: id 0 | task 4914 | eval time = 420.53 ms / 2 tokens ( 420.53 ms per token, 2.38 tokens per second) 3.14.186.547 I slot print_timing: id 0 | task 4914 | total time = 1571.04 ms / 1046 tokens 3.14.186.548 I slot print_timing: id 0 | task 4914 | graphs reused = 3521 3.14.186.550 I slot print_timing: id 0 | task 4914 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.186.606 I slot release: id 0 | task 4914 | stop processing: n_tokens = 1045, truncated = 0 3.14.463.054 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1045, t_last = 194091511 3.14.463.143 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.707 MiB) 3.14.506.190 I slot launch_slot_: id 0 | task 4926 | processing task, is_child = 0 3.15.244.354 I slot print_timing: id 1 | task 4920 | prompt eval time = 1724.20 ms / 1124 tokens ( 1.53 ms per token, 651.90 tokens per second) 3.15.244.360 I slot print_timing: id 1 | task 4920 | eval time = 260.25 ms / 2 tokens ( 260.25 ms per token, 3.84 tokens per second) 3.15.244.362 I slot print_timing: id 1 | task 4920 | total time = 1984.45 ms / 1126 tokens 3.15.244.362 I slot print_timing: id 1 | task 4920 | graphs reused = 3521 3.15.244.364 I slot print_timing: id 1 | task 4920 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.244.419 I slot release: id 1 | task 4920 | stop processing: n_tokens = 1125, truncated = 0 3.15.244.773 I slot print_timing: id 2 | task 4919 | prompt eval time = 1721.33 ms / 1161 tokens ( 1.48 ms per token, 674.48 tokens per second) 3.15.244.777 I slot print_timing: id 2 | task 4919 | eval time = 260.06 ms / 2 tokens ( 260.06 ms per token, 3.85 tokens per second) 3.15.244.777 I slot print_timing: id 2 | task 4919 | total time = 1981.39 ms / 1163 tokens 3.15.244.778 I slot print_timing: id 2 | task 4919 | graphs reused = 3521 3.15.244.779 I slot print_timing: id 2 | task 4919 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.244.812 I slot release: id 2 | task 4919 | stop processing: n_tokens = 1162, truncated = 0 3.15.245.143 I slot print_timing: id 3 | task 4921 | prompt eval time = 1718.44 ms / 2091 tokens ( 0.82 ms per token, 1216.80 tokens per second) 3.15.245.146 I slot print_timing: id 3 | task 4921 | eval time = 259.87 ms / 2 tokens ( 259.87 ms per token, 3.85 tokens per second) 3.15.245.147 I slot print_timing: id 3 | task 4921 | total time = 1978.30 ms / 2093 tokens 3.15.245.147 I slot print_timing: id 3 | task 4921 | graphs reused = 3521 3.15.245.148 I slot print_timing: id 3 | task 4921 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.245.219 I slot release: id 3 | task 4921 | stop processing: n_tokens = 2092, truncated = 0 3.15.262.198 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.856 3.15.262.323 I slot launch_slot_: id 3 | task 4931 | processing task, is_child = 0 3.15.262.409 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.676 MiB) 3.15.321.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.305 MiB) 3.15.368.491 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1125, t_last = 195149324 3.15.368.751 I slot launch_slot_: id 1 | task 4932 | processing task, is_child = 0 3.15.368.832 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1162, t_last = 195149718 3.15.369.021 I slot launch_slot_: id 2 | task 4933 | processing task, is_child = 0 3.16.528.427 I slot print_timing: id 0 | task 4926 | prompt eval time = 1495.29 ms / 2094 tokens ( 0.71 ms per token, 1400.39 tokens per second) 3.16.528.433 I slot print_timing: id 0 | task 4926 | eval time = 526.91 ms / 2 tokens ( 526.91 ms per token, 1.90 tokens per second) 3.16.528.434 I slot print_timing: id 0 | task 4926 | total time = 2022.20 ms / 2096 tokens 3.16.528.435 I slot print_timing: id 0 | task 4926 | graphs reused = 3521 3.16.528.436 I slot print_timing: id 0 | task 4926 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.528.528 I slot release: id 0 | task 4926 | stop processing: n_tokens = 2095, truncated = 0 3.16.528.953 I slot print_timing: id 3 | task 4931 | prompt eval time = 614.70 ms / 296 tokens ( 2.08 ms per token, 481.53 tokens per second) 3.16.528.957 I slot print_timing: id 3 | task 4931 | eval time = 526.87 ms / 2 tokens ( 526.87 ms per token, 1.90 tokens per second) 3.16.528.957 I slot print_timing: id 3 | task 4931 | total time = 1141.58 ms / 298 tokens 3.16.528.958 I slot print_timing: id 3 | task 4931 | graphs reused = 3521 3.16.528.959 I slot print_timing: id 3 | task 4931 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.529.033 I slot release: id 3 | task 4931 | stop processing: n_tokens = 2058, truncated = 0 3.16.654.821 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.854 3.16.654.972 I slot launch_slot_: id 0 | task 4938 | processing task, is_child = 0 3.16.655.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.805 MiB) 3.16.659.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.215 MiB) 3.16.721.327 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.869 3.16.721.479 I slot launch_slot_: id 3 | task 4939 | processing task, is_child = 0 3.17.247.886 I slot print_timing: id 0 | task 4938 | prompt eval time = 505.99 ms / 369 tokens ( 1.37 ms per token, 729.27 tokens per second) 3.17.247.892 I slot print_timing: id 0 | task 4938 | eval time = 20.40 ms / 2 tokens ( 20.40 ms per token, 49.02 tokens per second) 3.17.247.893 I slot print_timing: id 0 | task 4938 | total time = 526.38 ms / 371 tokens 3.17.247.894 I slot print_timing: id 0 | task 4938 | graphs reused = 3522 3.17.247.895 I slot print_timing: id 0 | task 4938 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.247.989 I slot release: id 0 | task 4938 | stop processing: n_tokens = 2131, truncated = 0 3.17.248.346 I slot print_timing: id 1 | task 4932 | prompt eval time = 1848.45 ms / 2105 tokens ( 0.88 ms per token, 1138.79 tokens per second) 3.17.248.349 I slot print_timing: id 1 | task 4932 | eval time = 20.23 ms / 2 tokens ( 20.23 ms per token, 49.44 tokens per second) 3.17.248.350 I slot print_timing: id 1 | task 4932 | total time = 1868.68 ms / 2107 tokens 3.17.248.350 I slot print_timing: id 1 | task 4932 | graphs reused = 3522 3.17.248.351 I slot print_timing: id 1 | task 4932 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.248.415 I slot release: id 1 | task 4932 | stop processing: n_tokens = 2106, truncated = 0 3.17.248.745 I slot print_timing: id 2 | task 4933 | prompt eval time = 1845.45 ms / 2041 tokens ( 0.90 ms per token, 1105.97 tokens per second) 3.17.248.748 I slot print_timing: id 2 | task 4933 | eval time = 20.04 ms / 2 tokens ( 20.04 ms per token, 49.91 tokens per second) 3.17.248.749 I slot print_timing: id 2 | task 4933 | total time = 1865.48 ms / 2043 tokens 3.17.248.749 I slot print_timing: id 2 | task 4933 | graphs reused = 3522 3.17.248.750 I slot print_timing: id 2 | task 4933 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.248.800 I slot release: id 2 | task 4933 | stop processing: n_tokens = 2042, truncated = 0 3.17.249.108 I slot print_timing: id 3 | task 4939 | prompt eval time = 462.11 ms / 300 tokens ( 1.54 ms per token, 649.20 tokens per second) 3.17.249.110 I slot print_timing: id 3 | task 4939 | eval time = 19.84 ms / 2 tokens ( 19.84 ms per token, 50.41 tokens per second) 3.17.249.111 I slot print_timing: id 3 | task 4939 | total time = 481.94 ms / 302 tokens 3.17.249.112 I slot print_timing: id 3 | task 4939 | graphs reused = 3522 3.17.249.112 I slot print_timing: id 3 | task 4939 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.249.158 I slot release: id 3 | task 4939 | stop processing: n_tokens = 2062, truncated = 0 3.17.263.381 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.840 3.17.263.499 I slot launch_slot_: id 0 | task 4943 | processing task, is_child = 0 3.17.263.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.778 MiB) 3.17.314.075 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.122 MiB) 3.17.374.224 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.028 MiB) 3.17.433.994 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.850 3.17.434.135 I slot launch_slot_: id 1 | task 4944 | processing task, is_child = 0 3.17.434.362 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.877 3.17.434.454 I slot launch_slot_: id 2 | task 4945 | processing task, is_child = 0 3.17.434.565 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.803 (> 0.100 thold), f_keep = 0.868 3.17.434.651 I slot launch_slot_: id 3 | task 4946 | processing task, is_child = 0 3.17.997.276 I slot print_timing: id 0 | task 4943 | prompt eval time = 542.20 ms / 380 tokens ( 1.43 ms per token, 700.84 tokens per second) 3.17.997.282 I slot print_timing: id 0 | task 4943 | eval time = 20.40 ms / 2 tokens ( 20.40 ms per token, 49.01 tokens per second) 3.17.997.283 I slot print_timing: id 0 | task 4943 | total time = 562.61 ms / 382 tokens 3.17.997.284 I slot print_timing: id 0 | task 4943 | graphs reused = 3522 3.17.997.285 I slot print_timing: id 0 | task 4943 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.997.375 I slot release: id 0 | task 4943 | stop processing: n_tokens = 2142, truncated = 0 3.17.997.692 I slot print_timing: id 1 | task 4944 | prompt eval time = 516.34 ms / 210 tokens ( 2.46 ms per token, 406.71 tokens per second) 3.17.997.695 I slot print_timing: id 1 | task 4944 | eval time = 20.22 ms / 2 tokens ( 20.22 ms per token, 49.46 tokens per second) 3.17.997.696 I slot print_timing: id 1 | task 4944 | total time = 536.56 ms / 212 tokens 3.17.997.697 I slot print_timing: id 1 | task 4944 | graphs reused = 3522 3.17.997.697 I slot print_timing: id 1 | task 4944 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.997.751 I slot release: id 1 | task 4944 | stop processing: n_tokens = 1972, truncated = 0 3.17.998.072 I slot print_timing: id 2 | task 4945 | prompt eval time = 478.18 ms / 258 tokens ( 1.85 ms per token, 539.54 tokens per second) 3.17.998.075 I slot print_timing: id 2 | task 4945 | eval time = 20.04 ms / 2 tokens ( 20.04 ms per token, 49.90 tokens per second) 3.17.998.076 I slot print_timing: id 2 | task 4945 | total time = 498.22 ms / 260 tokens 3.17.998.076 I slot print_timing: id 2 | task 4945 | graphs reused = 3522 3.17.998.077 I slot print_timing: id 2 | task 4945 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.998.122 I slot release: id 2 | task 4945 | stop processing: n_tokens = 2020, truncated = 0 3.17.998.432 I slot print_timing: id 3 | task 4946 | prompt eval time = 459.94 ms / 467 tokens ( 0.98 ms per token, 1015.34 tokens per second) 3.17.998.435 I slot print_timing: id 3 | task 4946 | eval time = 19.83 ms / 2 tokens ( 19.83 ms per token, 50.44 tokens per second) 3.17.998.436 I slot print_timing: id 3 | task 4946 | total time = 479.77 ms / 469 tokens 3.17.998.437 I slot print_timing: id 3 | task 4946 | graphs reused = 3522 3.17.998.437 I slot print_timing: id 3 | task 4946 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.998.487 I slot release: id 3 | task 4946 | stop processing: n_tokens = 2229, truncated = 0 3.18.013.420 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.835 3.18.013.544 I slot launch_slot_: id 0 | task 4950 | processing task, is_child = 0 3.18.013.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.309 MiB) 3.18.077.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.934 MiB) 3.18.132.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.903 MiB) 3.18.193.305 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.908 3.18.193.458 I slot launch_slot_: id 1 | task 4951 | processing task, is_child = 0 3.18.193.690 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.850 (> 0.100 thold), f_keep = 0.886 3.18.193.790 I slot launch_slot_: id 2 | task 4952 | processing task, is_child = 0 3.18.193.915 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.803 3.18.194.005 I slot launch_slot_: id 3 | task 4953 | processing task, is_child = 0 3.18.668.149 I slot print_timing: id 0 | task 4950 | prompt eval time = 453.92 ms / 253 tokens ( 1.79 ms per token, 557.37 tokens per second) 3.18.668.154 I slot print_timing: id 0 | task 4950 | eval time = 20.21 ms / 2 tokens ( 20.21 ms per token, 49.48 tokens per second) 3.18.668.156 I slot print_timing: id 0 | task 4950 | total time = 474.13 ms / 255 tokens 3.18.668.157 I slot print_timing: id 0 | task 4950 | graphs reused = 3522 3.18.668.157 I slot print_timing: id 0 | task 4950 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.668.240 I slot release: id 0 | task 4950 | stop processing: n_tokens = 2015, truncated = 0 3.18.668.523 I slot print_timing: id 1 | task 4951 | prompt eval time = 434.85 ms / 304 tokens ( 1.43 ms per token, 699.09 tokens per second) 3.18.668.527 I slot print_timing: id 1 | task 4951 | eval time = 19.91 ms / 2 tokens ( 19.91 ms per token, 50.24 tokens per second) 3.18.668.527 I slot print_timing: id 1 | task 4951 | total time = 454.76 ms / 306 tokens 3.18.668.528 I slot print_timing: id 1 | task 4951 | graphs reused = 3522 3.18.668.528 I slot print_timing: id 1 | task 4951 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.668.581 I slot release: id 1 | task 4951 | stop processing: n_tokens = 2066, truncated = 0 3.18.668.885 I slot print_timing: id 2 | task 4952 | prompt eval time = 415.62 ms / 345 tokens ( 1.20 ms per token, 830.09 tokens per second) 3.18.668.888 I slot print_timing: id 2 | task 4952 | eval time = 19.64 ms / 2 tokens ( 19.64 ms per token, 50.93 tokens per second) 3.18.668.888 I slot print_timing: id 2 | task 4952 | total time = 435.25 ms / 347 tokens 3.18.668.889 I slot print_timing: id 2 | task 4952 | graphs reused = 3522 3.18.668.889 I slot print_timing: id 2 | task 4952 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.668.938 I slot release: id 2 | task 4952 | stop processing: n_tokens = 2107, truncated = 0 3.18.669.248 I slot print_timing: id 3 | task 4953 | prompt eval time = 396.41 ms / 212 tokens ( 1.87 ms per token, 534.80 tokens per second) 3.18.669.252 I slot print_timing: id 3 | task 4953 | eval time = 19.36 ms / 2 tokens ( 19.36 ms per token, 51.65 tokens per second) 3.18.669.252 I slot print_timing: id 3 | task 4953 | total time = 415.77 ms / 214 tokens 3.18.669.253 I slot print_timing: id 3 | task 4953 | graphs reused = 3522 3.18.669.253 I slot print_timing: id 3 | task 4953 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.669.294 I slot release: id 3 | task 4953 | stop processing: n_tokens = 1974, truncated = 0 3.18.684.392 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.866 3.18.684.543 I slot launch_slot_: id 1 | task 4957 | processing task, is_child = 0 3.18.684.676 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.059 MiB) 3.18.737.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.028 MiB) 3.18.794.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.997 MiB) 3.18.799.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.089 MiB) 3.18.859.848 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.847 (> 0.100 thold), f_keep = 0.850 3.18.859.995 I slot launch_slot_: id 2 | task 4958 | processing task, is_child = 0 3.18.860.217 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.888 3.18.860.309 I slot launch_slot_: id 0 | task 4959 | processing task, is_child = 0 3.18.860.420 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.906 3.18.860.517 I slot launch_slot_: id 3 | task 4960 | processing task, is_child = 0 3.19.370.967 I slot print_timing: id 0 | task 4959 | prompt eval time = 490.38 ms / 304 tokens ( 1.61 ms per token, 619.93 tokens per second) 3.19.370.972 I slot print_timing: id 0 | task 4959 | eval time = 20.05 ms / 2 tokens ( 20.05 ms per token, 49.87 tokens per second) 3.19.370.973 I slot print_timing: id 0 | task 4959 | total time = 510.43 ms / 306 tokens 3.19.370.974 I slot print_timing: id 0 | task 4959 | graphs reused = 3522 3.19.370.974 I slot print_timing: id 0 | task 4959 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.371.059 I slot release: id 0 | task 4959 | stop processing: n_tokens = 2066, truncated = 0 3.19.371.323 I slot print_timing: id 1 | task 4957 | prompt eval time = 470.99 ms / 210 tokens ( 2.24 ms per token, 445.87 tokens per second) 3.19.371.326 I slot print_timing: id 1 | task 4957 | eval time = 19.81 ms / 2 tokens ( 19.81 ms per token, 50.47 tokens per second) 3.19.371.327 I slot print_timing: id 1 | task 4957 | total time = 490.81 ms / 212 tokens 3.19.371.328 I slot print_timing: id 1 | task 4957 | graphs reused = 3522 3.19.371.329 I slot print_timing: id 1 | task 4957 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.371.384 I slot release: id 1 | task 4957 | stop processing: n_tokens = 1972, truncated = 0 3.19.371.648 I slot print_timing: id 2 | task 4958 | prompt eval time = 452.02 ms / 353 tokens ( 1.28 ms per token, 780.94 tokens per second) 3.19.371.651 I slot print_timing: id 2 | task 4958 | eval time = 19.57 ms / 2 tokens ( 19.57 ms per token, 51.09 tokens per second) 3.19.371.652 I slot print_timing: id 2 | task 4958 | total time = 471.59 ms / 355 tokens 3.19.371.652 I slot print_timing: id 2 | task 4958 | graphs reused = 3522 3.19.371.653 I slot print_timing: id 2 | task 4958 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.371.703 I slot release: id 2 | task 4958 | stop processing: n_tokens = 2115, truncated = 0 3.19.371.968 I slot print_timing: id 3 | task 4960 | prompt eval time = 432.94 ms / 405 tokens ( 1.07 ms per token, 935.46 tokens per second) 3.19.371.971 I slot print_timing: id 3 | task 4960 | eval time = 19.32 ms / 2 tokens ( 19.32 ms per token, 51.75 tokens per second) 3.19.371.972 I slot print_timing: id 3 | task 4960 | total time = 452.27 ms / 407 tokens 3.19.371.972 I slot print_timing: id 3 | task 4960 | graphs reused = 3522 3.19.371.973 I slot print_timing: id 3 | task 4960 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.372.021 I slot release: id 3 | task 4960 | stop processing: n_tokens = 2167, truncated = 0 3.19.386.906 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.866 3.19.387.033 I slot launch_slot_: id 0 | task 4964 | processing task, is_child = 0 3.19.387.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.778 MiB) 3.19.449.204 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.872 MiB) 3.19.533.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.495 MiB) 3.19.589.975 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.908 3.19.590.118 I slot launch_slot_: id 1 | task 4965 | processing task, is_child = 0 3.19.590.360 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.846 3.19.590.457 I slot launch_slot_: id 2 | task 4966 | processing task, is_child = 0 3.19.590.572 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.826 3.19.590.670 I slot launch_slot_: id 3 | task 4967 | processing task, is_child = 0 3.20.100.528 I slot print_timing: id 0 | task 4964 | prompt eval time = 489.53 ms / 272 tokens ( 1.80 ms per token, 555.63 tokens per second) 3.20.100.534 I slot print_timing: id 0 | task 4964 | eval time = 20.31 ms / 2 tokens ( 20.31 ms per token, 49.24 tokens per second) 3.20.100.535 I slot print_timing: id 0 | task 4964 | total time = 509.84 ms / 274 tokens 3.20.100.537 I slot print_timing: id 0 | task 4964 | graphs reused = 3522 3.20.100.538 I slot print_timing: id 0 | task 4964 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.100.622 I slot release: id 0 | task 4964 | stop processing: n_tokens = 2034, truncated = 0 3.20.100.873 I slot print_timing: id 1 | task 4965 | prompt eval time = 470.58 ms / 264 tokens ( 1.78 ms per token, 561.01 tokens per second) 3.20.100.876 I slot print_timing: id 1 | task 4965 | eval time = 20.07 ms / 2 tokens ( 20.07 ms per token, 49.83 tokens per second) 3.20.100.877 I slot print_timing: id 1 | task 4965 | total time = 490.65 ms / 266 tokens 3.20.100.878 I slot print_timing: id 1 | task 4965 | graphs reused = 3522 3.20.100.878 I slot print_timing: id 1 | task 4965 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.100.926 I slot release: id 1 | task 4965 | stop processing: n_tokens = 2026, truncated = 0 3.20.101.175 I slot print_timing: id 2 | task 4966 | prompt eval time = 451.45 ms / 413 tokens ( 1.09 ms per token, 914.83 tokens per second) 3.20.101.178 I slot print_timing: id 2 | task 4966 | eval time = 19.80 ms / 2 tokens ( 19.80 ms per token, 50.49 tokens per second) 3.20.101.178 I slot print_timing: id 2 | task 4966 | total time = 471.25 ms / 415 tokens 3.20.101.179 I slot print_timing: id 2 | task 4966 | graphs reused = 3522 3.20.101.179 I slot print_timing: id 2 | task 4966 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.101.230 I slot release: id 2 | task 4966 | stop processing: n_tokens = 2175, truncated = 0 3.20.101.481 I slot print_timing: id 3 | task 4967 | prompt eval time = 432.52 ms / 236 tokens ( 1.83 ms per token, 545.63 tokens per second) 3.20.101.484 I slot print_timing: id 3 | task 4967 | eval time = 19.54 ms / 2 tokens ( 19.54 ms per token, 51.18 tokens per second) 3.20.101.484 I slot print_timing: id 3 | task 4967 | total time = 452.06 ms / 238 tokens 3.20.101.485 I slot print_timing: id 3 | task 4967 | graphs reused = 3522 3.20.101.485 I slot print_timing: id 3 | task 4967 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.101.526 I slot release: id 3 | task 4967 | stop processing: n_tokens = 1998, truncated = 0 3.20.115.706 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.880 3.20.115.842 I slot launch_slot_: id 0 | task 4971 | processing task, is_child = 0 3.20.116.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.965 MiB) 3.20.173.882 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.833 MiB) 3.20.235.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.082 MiB) 3.20.294.517 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2026, t_last = 200005832 3.20.294.778 I slot launch_slot_: id 1 | task 4972 | processing task, is_child = 0 3.20.295.015 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.823 3.20.295.108 I slot launch_slot_: id 2 | task 4973 | processing task, is_child = 0 3.20.295.226 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.895 3.20.295.321 I slot launch_slot_: id 3 | task 4974 | processing task, is_child = 0 3.20.907.131 I slot print_timing: id 0 | task 4971 | prompt eval time = 478.67 ms / 149 tokens ( 3.21 ms per token, 311.28 tokens per second) 3.20.907.137 I slot print_timing: id 0 | task 4971 | eval time = 133.12 ms / 2 tokens ( 133.12 ms per token, 7.51 tokens per second) 3.20.907.139 I slot print_timing: id 0 | task 4971 | total time = 611.79 ms / 151 tokens 3.20.907.140 I slot print_timing: id 0 | task 4971 | graphs reused = 3522 3.20.907.141 I slot print_timing: id 0 | task 4971 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.907.235 I slot release: id 0 | task 4971 | stop processing: n_tokens = 1911, truncated = 0 3.20.907.573 I slot print_timing: id 2 | task 4973 | prompt eval time = 455.83 ms / 196 tokens ( 2.33 ms per token, 429.98 tokens per second) 3.20.907.576 I slot print_timing: id 2 | task 4973 | eval time = 132.99 ms / 2 tokens ( 132.99 ms per token, 7.52 tokens per second) 3.20.907.577 I slot print_timing: id 2 | task 4973 | total time = 588.83 ms / 198 tokens 3.20.907.578 I slot print_timing: id 2 | task 4973 | graphs reused = 3522 3.20.907.578 I slot print_timing: id 2 | task 4973 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.907.634 I slot release: id 2 | task 4973 | stop processing: n_tokens = 1958, truncated = 0 3.20.907.947 I slot print_timing: id 3 | task 4974 | prompt eval time = 436.69 ms / 230 tokens ( 1.90 ms per token, 526.68 tokens per second) 3.20.907.950 I slot print_timing: id 3 | task 4974 | eval time = 132.81 ms / 2 tokens ( 132.81 ms per token, 7.53 tokens per second) 3.20.907.950 I slot print_timing: id 3 | task 4974 | total time = 569.50 ms / 232 tokens 3.20.907.951 I slot print_timing: id 3 | task 4974 | graphs reused = 3522 3.20.907.952 I slot print_timing: id 3 | task 4974 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.907.997 I slot release: id 3 | task 4974 | stop processing: n_tokens = 1992, truncated = 0 3.20.924.295 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1911, t_last = 200812141 3.20.924.428 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.426 MiB) 3.21.020.156 I slot launch_slot_: id 0 | task 4979 | processing task, is_child = 0 3.21.020.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.395 MiB) 3.21.024.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.207 MiB) 3.21.087.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.895 MiB) 3.21.145.573 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1958, t_last = 200812540 3.21.145.831 I slot launch_slot_: id 2 | task 4980 | processing task, is_child = 0 3.21.145.940 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1992, t_last = 200812904 3.21.146.132 I slot launch_slot_: id 3 | task 4981 | processing task, is_child = 0 3.22.100.036 I slot print_timing: id 1 | task 4972 | prompt eval time = 1438.56 ms / 1475 tokens ( 0.98 ms per token, 1025.33 tokens per second) 3.22.100.041 I slot print_timing: id 1 | task 4972 | eval time = 346.33 ms / 2 tokens ( 346.33 ms per token, 2.89 tokens per second) 3.22.100.043 I slot print_timing: id 1 | task 4972 | total time = 1784.88 ms / 1477 tokens 3.22.100.044 I slot print_timing: id 1 | task 4972 | graphs reused = 3522 3.22.100.044 I slot print_timing: id 1 | task 4972 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.100.117 I slot release: id 1 | task 4972 | stop processing: n_tokens = 1476, truncated = 0 3.22.303.234 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 202005023 3.22.303.338 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.645 MiB) 3.22.360.933 I slot launch_slot_: id 1 | task 4986 | processing task, is_child = 0 3.22.882.818 I slot print_timing: id 0 | task 4979 | prompt eval time = 1677.88 ms / 1677 tokens ( 1.00 ms per token, 999.47 tokens per second) 3.22.882.825 I slot print_timing: id 0 | task 4979 | eval time = 58.78 ms / 2 tokens ( 58.78 ms per token, 17.01 tokens per second) 3.22.882.826 I slot print_timing: id 0 | task 4979 | total time = 1736.66 ms / 1679 tokens 3.22.882.827 I slot print_timing: id 0 | task 4979 | graphs reused = 3522 3.22.882.828 I slot print_timing: id 0 | task 4979 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.882.910 I slot release: id 0 | task 4979 | stop processing: n_tokens = 1678, truncated = 0 3.22.883.252 I slot print_timing: id 2 | task 4980 | prompt eval time = 1662.83 ms / 1555 tokens ( 1.07 ms per token, 935.15 tokens per second) 3.22.883.256 I slot print_timing: id 2 | task 4980 | eval time = 58.65 ms / 2 tokens ( 58.65 ms per token, 17.05 tokens per second) 3.22.883.257 I slot print_timing: id 2 | task 4980 | total time = 1721.48 ms / 1557 tokens 3.22.883.258 I slot print_timing: id 2 | task 4980 | graphs reused = 3522 3.22.883.258 I slot print_timing: id 2 | task 4980 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.883.312 I slot release: id 2 | task 4980 | stop processing: n_tokens = 1556, truncated = 0 3.22.883.664 I slot print_timing: id 3 | task 4981 | prompt eval time = 1659.84 ms / 999 tokens ( 1.66 ms per token, 601.86 tokens per second) 3.22.883.666 I slot print_timing: id 3 | task 4981 | eval time = 58.50 ms / 2 tokens ( 58.50 ms per token, 17.09 tokens per second) 3.22.883.667 I slot print_timing: id 3 | task 4981 | total time = 1718.34 ms / 1001 tokens 3.22.883.668 I slot print_timing: id 3 | task 4981 | graphs reused = 3522 3.22.883.668 I slot print_timing: id 3 | task 4981 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.883.703 I slot release: id 3 | task 4981 | stop processing: n_tokens = 1000, truncated = 0 3.22.900.208 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.882 3.22.900.325 I slot launch_slot_: id 3 | task 4991 | processing task, is_child = 0 3.22.900.427 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.150 MiB) 3.23.001.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.245 MiB) 3.23.054.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1678, t_last = 202787817 3.23.055.162 I slot launch_slot_: id 0 | task 4992 | processing task, is_child = 0 3.23.055.252 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1556, t_last = 202788217 3.23.055.501 I slot launch_slot_: id 2 | task 4993 | processing task, is_child = 0 3.23.581.457 I slot print_timing: id 1 | task 4986 | prompt eval time = 1133.09 ms / 989 tokens ( 1.15 ms per token, 872.84 tokens per second) 3.23.581.463 I slot print_timing: id 1 | task 4986 | eval time = 76.37 ms / 2 tokens ( 76.37 ms per token, 13.09 tokens per second) 3.23.581.464 I slot print_timing: id 1 | task 4986 | total time = 1209.45 ms / 991 tokens 3.23.581.465 I slot print_timing: id 1 | task 4986 | graphs reused = 3522 3.23.581.466 I slot print_timing: id 1 | task 4986 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.581.514 I slot release: id 1 | task 4986 | stop processing: n_tokens = 990, truncated = 0 3.23.581.825 I slot print_timing: id 3 | task 4991 | prompt eval time = 428.13 ms / 124 tokens ( 3.45 ms per token, 289.63 tokens per second) 3.23.581.828 I slot print_timing: id 3 | task 4991 | eval time = 76.17 ms / 2 tokens ( 76.17 ms per token, 13.13 tokens per second) 3.23.581.829 I slot print_timing: id 3 | task 4991 | total time = 504.29 ms / 126 tokens 3.23.581.829 I slot print_timing: id 3 | task 4991 | graphs reused = 3522 3.23.581.830 I slot print_timing: id 3 | task 4991 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.581.861 I slot release: id 3 | task 4991 | stop processing: n_tokens = 978, truncated = 0 3.23.719.890 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.890 3.23.720.020 I slot launch_slot_: id 1 | task 4998 | processing task, is_child = 0 3.23.720.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.713 MiB) 3.23.837.478 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.901 3.23.837.633 I slot launch_slot_: id 3 | task 4999 | processing task, is_child = 0 3.24.153.602 I slot print_timing: id 0 | task 4992 | prompt eval time = 1077.45 ms / 983 tokens ( 1.10 ms per token, 912.34 tokens per second) 3.24.153.608 I slot print_timing: id 0 | task 4992 | eval time = 20.64 ms / 2 tokens ( 20.64 ms per token, 48.46 tokens per second) 3.24.153.609 I slot print_timing: id 0 | task 4992 | total time = 1098.08 ms / 985 tokens 3.24.153.610 I slot print_timing: id 0 | task 4992 | graphs reused = 3522 3.24.153.610 I slot print_timing: id 0 | task 4992 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.153.659 I slot release: id 0 | task 4992 | stop processing: n_tokens = 984, truncated = 0 3.24.153.971 I slot print_timing: id 1 | task 4998 | prompt eval time = 285.76 ms / 119 tokens ( 2.40 ms per token, 416.43 tokens per second) 3.24.153.974 I slot print_timing: id 1 | task 4998 | eval time = 20.35 ms / 2 tokens ( 20.35 ms per token, 49.14 tokens per second) 3.24.153.975 I slot print_timing: id 1 | task 4998 | total time = 306.11 ms / 121 tokens 3.24.153.975 I slot print_timing: id 1 | task 4998 | graphs reused = 3522 3.24.153.977 I slot print_timing: id 1 | task 4998 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.154.006 I slot release: id 1 | task 4998 | stop processing: n_tokens = 973, truncated = 0 3.24.154.328 I slot print_timing: id 2 | task 4993 | prompt eval time = 1060.30 ms / 960 tokens ( 1.10 ms per token, 905.40 tokens per second) 3.24.154.331 I slot print_timing: id 2 | task 4993 | eval time = 20.05 ms / 2 tokens ( 20.05 ms per token, 49.88 tokens per second) 3.24.154.332 I slot print_timing: id 2 | task 4993 | total time = 1080.35 ms / 962 tokens 3.24.154.332 I slot print_timing: id 2 | task 4993 | graphs reused = 3522 3.24.154.333 I slot print_timing: id 2 | task 4993 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.154.357 I slot release: id 2 | task 4993 | stop processing: n_tokens = 961, truncated = 0 3.24.154.654 I slot print_timing: id 3 | task 4999 | prompt eval time = 254.81 ms / 123 tokens ( 2.07 ms per token, 482.72 tokens per second) 3.24.154.658 I slot print_timing: id 3 | task 4999 | eval time = 19.80 ms / 2 tokens ( 19.80 ms per token, 50.51 tokens per second) 3.24.154.658 I slot print_timing: id 3 | task 4999 | total time = 274.61 ms / 125 tokens 3.24.154.659 I slot print_timing: id 3 | task 4999 | graphs reused = 3522 3.24.154.660 I slot print_timing: id 3 | task 4999 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.154.684 I slot release: id 3 | task 4999 | stop processing: n_tokens = 977, truncated = 0 3.24.167.882 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 984, t_last = 204058564 3.24.167.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.933 MiB) 3.24.215.025 I slot launch_slot_: id 0 | task 5003 | processing task, is_child = 0 3.24.215.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 286.435 MiB) 3.24.269.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 287.592 MiB) 3.24.313.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.613 MiB) 3.24.368.934 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 204058911 3.24.369.153 I slot launch_slot_: id 1 | task 5004 | processing task, is_child = 0 3.24.369.277 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 204059262 3.24.369.431 I slot launch_slot_: id 2 | task 5005 | processing task, is_child = 0 3.24.369.495 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 204059589 3.24.369.645 I slot launch_slot_: id 3 | task 5006 | processing task, is_child = 0 3.26.235.433 I slot print_timing: id 0 | task 5003 | prompt eval time = 1726.62 ms / 825 tokens ( 2.09 ms per token, 477.81 tokens per second) 3.26.235.438 I slot print_timing: id 0 | task 5003 | eval time = 139.15 ms / 2 tokens ( 139.15 ms per token, 7.19 tokens per second) 3.26.235.439 I slot print_timing: id 0 | task 5003 | total time = 1865.77 ms / 827 tokens 3.26.235.440 I slot print_timing: id 0 | task 5003 | graphs reused = 3523 3.26.235.440 I slot print_timing: id 0 | task 5003 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.235.485 I slot release: id 0 | task 5003 | stop processing: n_tokens = 826, truncated = 0 3.26.280.754 I slot print_timing: id 1 | task 5004 | prompt eval time = 1862.92 ms / 1587 tokens ( 1.17 ms per token, 851.89 tokens per second) 3.26.280.760 I slot print_timing: id 1 | task 5004 | eval time = 44.62 ms / 2 tokens ( 44.62 ms per token, 22.41 tokens per second) 3.26.280.761 I slot print_timing: id 1 | task 5004 | total time = 1907.54 ms / 1589 tokens 3.26.280.762 I slot print_timing: id 1 | task 5004 | graphs reused = 3523 3.26.280.763 I slot print_timing: id 1 | task 5004 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.280.837 I slot release: id 1 | task 5004 | stop processing: n_tokens = 1588, truncated = 0 3.26.281.158 I slot print_timing: id 2 | task 5005 | prompt eval time = 1860.05 ms / 1629 tokens ( 1.14 ms per token, 875.78 tokens per second) 3.26.281.161 I slot print_timing: id 2 | task 5005 | eval time = 44.45 ms / 2 tokens ( 44.45 ms per token, 22.50 tokens per second) 3.26.281.162 I slot print_timing: id 2 | task 5005 | total time = 1904.51 ms / 1631 tokens 3.26.281.162 I slot print_timing: id 2 | task 5005 | graphs reused = 3523 3.26.281.163 I slot print_timing: id 2 | task 5005 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.281.211 I slot release: id 2 | task 5005 | stop processing: n_tokens = 1630, truncated = 0 3.26.281.844 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.861 (> 0.100 thold), f_keep = 0.883 3.26.281.976 I slot launch_slot_: id 1 | task 5014 | processing task, is_child = 0 3.26.282.050 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.114 MiB) 3.26.325.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.112 MiB) 3.26.384.247 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 206140390 3.26.384.456 I slot launch_slot_: id 0 | task 5015 | processing task, is_child = 0 3.26.384.555 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.816 (> 0.100 thold), f_keep = 0.860 3.26.384.649 I slot launch_slot_: id 2 | task 5016 | processing task, is_child = 0 3.26.637.874 I slot print_timing: id 3 | task 5006 | prompt eval time = 1901.75 ms / 1615 tokens ( 1.18 ms per token, 849.22 tokens per second) 3.26.637.881 I slot print_timing: id 3 | task 5006 | eval time = 356.02 ms / 2 tokens ( 356.02 ms per token, 2.81 tokens per second) 3.26.637.882 I slot print_timing: id 3 | task 5006 | total time = 2257.77 ms / 1617 tokens 3.26.637.883 I slot print_timing: id 3 | task 5006 | graphs reused = 3523 3.26.637.884 I slot print_timing: id 3 | task 5006 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.637.967 I slot release: id 3 | task 5006 | stop processing: n_tokens = 1616, truncated = 0 3.26.729.376 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1616, t_last = 206542873 3.26.729.485 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.738 MiB) 3.26.783.944 I slot launch_slot_: id 3 | task 5019 | processing task, is_child = 0 3.26.871.640 I slot print_timing: id 1 | task 5014 | prompt eval time = 340.56 ms / 255 tokens ( 1.34 ms per token, 748.77 tokens per second) 3.26.871.645 I slot print_timing: id 1 | task 5014 | eval time = 142.83 ms / 2 tokens ( 142.83 ms per token, 7.00 tokens per second) 3.26.871.646 I slot print_timing: id 1 | task 5014 | total time = 483.39 ms / 257 tokens 3.26.871.647 I slot print_timing: id 1 | task 5014 | graphs reused = 3523 3.26.871.648 I slot print_timing: id 1 | task 5014 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.871.722 I slot release: id 1 | task 5014 | stop processing: n_tokens = 1630, truncated = 0 3.26.872.062 I slot print_timing: id 2 | task 5016 | prompt eval time = 321.48 ms / 344 tokens ( 0.93 ms per token, 1070.06 tokens per second) 3.26.872.065 I slot print_timing: id 2 | task 5016 | eval time = 142.69 ms / 2 tokens ( 142.69 ms per token, 7.01 tokens per second) 3.26.872.066 I slot print_timing: id 2 | task 5016 | total time = 464.17 ms / 346 tokens 3.26.872.066 I slot print_timing: id 2 | task 5016 | graphs reused = 3523 3.26.872.067 I slot print_timing: id 2 | task 5016 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.872.118 I slot release: id 2 | task 5016 | stop processing: n_tokens = 1719, truncated = 0 3.27.012.265 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 206776628 3.27.012.371 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.923 MiB) 3.27.071.769 I slot launch_slot_: id 1 | task 5022 | processing task, is_child = 0 3.27.071.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.424 MiB) 3.27.123.471 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1719, t_last = 206777025 3.27.123.708 I slot launch_slot_: id 2 | task 5023 | processing task, is_child = 0 3.27.659.562 I slot print_timing: id 0 | task 5015 | prompt eval time = 1147.78 ms / 838 tokens ( 1.37 ms per token, 730.10 tokens per second) 3.27.659.568 I slot print_timing: id 0 | task 5015 | eval time = 127.11 ms / 2 tokens ( 127.11 ms per token, 7.87 tokens per second) 3.27.659.569 I slot print_timing: id 0 | task 5015 | total time = 1274.89 ms / 840 tokens 3.27.659.570 I slot print_timing: id 0 | task 5015 | graphs reused = 3523 3.27.659.571 I slot print_timing: id 0 | task 5015 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.659.618 I slot release: id 0 | task 5015 | stop processing: n_tokens = 839, truncated = 0 3.27.927.074 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 839, t_last = 207564523 3.27.964.318 I slot launch_slot_: id 0 | task 5028 | processing task, is_child = 0 3.28.145.039 I slot print_timing: id 3 | task 5019 | prompt eval time = 1143.09 ms / 865 tokens ( 1.32 ms per token, 756.72 tokens per second) 3.28.145.045 I slot print_timing: id 3 | task 5019 | eval time = 217.97 ms / 2 tokens ( 217.97 ms per token, 4.59 tokens per second) 3.28.145.046 I slot print_timing: id 3 | task 5019 | total time = 1361.06 ms / 867 tokens 3.28.145.047 I slot print_timing: id 3 | task 5019 | graphs reused = 3523 3.28.145.048 I slot print_timing: id 3 | task 5019 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.145.098 I slot release: id 3 | task 5019 | stop processing: n_tokens = 866, truncated = 0 3.28.239.428 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 866, t_last = 208050003 3.28.239.504 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.960 MiB) 3.28.293.726 I slot launch_slot_: id 3 | task 5031 | processing task, is_child = 0 3.28.386.534 I slot print_timing: id 1 | task 5022 | prompt eval time = 1103.39 ms / 859 tokens ( 1.28 ms per token, 778.51 tokens per second) 3.28.386.539 I slot print_timing: id 1 | task 5022 | eval time = 147.68 ms / 2 tokens ( 147.68 ms per token, 6.77 tokens per second) 3.28.386.540 I slot print_timing: id 1 | task 5022 | total time = 1251.07 ms / 861 tokens 3.28.386.541 I slot print_timing: id 1 | task 5022 | graphs reused = 3523 3.28.386.543 I slot print_timing: id 1 | task 5022 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.386.591 I slot release: id 1 | task 5022 | stop processing: n_tokens = 860, truncated = 0 3.28.386.912 I slot print_timing: id 2 | task 5023 | prompt eval time = 1100.33 ms / 842 tokens ( 1.31 ms per token, 765.22 tokens per second) 3.28.386.915 I slot print_timing: id 2 | task 5023 | eval time = 147.49 ms / 2 tokens ( 147.49 ms per token, 6.78 tokens per second) 3.28.386.916 I slot print_timing: id 2 | task 5023 | total time = 1247.82 ms / 844 tokens 3.28.386.916 I slot print_timing: id 2 | task 5023 | graphs reused = 3523 3.28.386.917 I slot print_timing: id 2 | task 5023 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.386.945 I slot release: id 2 | task 5023 | stop processing: n_tokens = 843, truncated = 0 3.28.514.237 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 208291497 3.28.514.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.268 MiB) 3.28.568.100 I slot launch_slot_: id 1 | task 5034 | processing task, is_child = 0 3.28.568.167 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.145 MiB) 3.28.618.461 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 208291850 3.28.618.668 I slot launch_slot_: id 2 | task 5035 | processing task, is_child = 0 3.29.336.755 I slot print_timing: id 0 | task 5028 | prompt eval time = 1055.27 ms / 886 tokens ( 1.19 ms per token, 839.59 tokens per second) 3.29.336.761 I slot print_timing: id 0 | task 5028 | eval time = 317.13 ms / 2 tokens ( 317.13 ms per token, 3.15 tokens per second) 3.29.336.762 I slot print_timing: id 0 | task 5028 | total time = 1372.41 ms / 888 tokens 3.29.336.763 I slot print_timing: id 0 | task 5028 | graphs reused = 3523 3.29.336.764 I slot print_timing: id 0 | task 5028 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.336.813 I slot release: id 0 | task 5028 | stop processing: n_tokens = 887, truncated = 0 3.29.470.910 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 209241718 3.29.471.035 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.986 MiB) 3.29.525.889 I slot launch_slot_: id 0 | task 5040 | processing task, is_child = 0 3.29.629.178 I slot print_timing: id 3 | task 5031 | prompt eval time = 1177.11 ms / 780 tokens ( 1.51 ms per token, 662.64 tokens per second) 3.29.629.184 I slot print_timing: id 3 | task 5031 | eval time = 158.31 ms / 2 tokens ( 158.31 ms per token, 6.32 tokens per second) 3.29.629.185 I slot print_timing: id 3 | task 5031 | total time = 1335.42 ms / 782 tokens 3.29.629.186 I slot print_timing: id 3 | task 5031 | graphs reused = 3523 3.29.629.186 I slot print_timing: id 3 | task 5031 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.629.237 I slot release: id 3 | task 5031 | stop processing: n_tokens = 781, truncated = 0 3.29.691.842 I slot print_timing: id 1 | task 5034 | prompt eval time = 998.96 ms / 691 tokens ( 1.45 ms per token, 691.72 tokens per second) 3.29.691.847 I slot print_timing: id 1 | task 5034 | eval time = 63.92 ms / 2 tokens ( 63.92 ms per token, 15.64 tokens per second) 3.29.691.848 I slot print_timing: id 1 | task 5034 | total time = 1062.89 ms / 693 tokens 3.29.691.851 I slot print_timing: id 1 | task 5034 | graphs reused = 3523 3.29.691.852 I slot print_timing: id 1 | task 5034 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.691.893 I slot release: id 1 | task 5034 | stop processing: n_tokens = 692, truncated = 0 3.29.692.213 I slot print_timing: id 2 | task 5035 | prompt eval time = 996.30 ms / 749 tokens ( 1.33 ms per token, 751.78 tokens per second) 3.29.692.216 I slot print_timing: id 2 | task 5035 | eval time = 63.43 ms / 2 tokens ( 63.43 ms per token, 15.76 tokens per second) 3.29.692.217 I slot print_timing: id 2 | task 5035 | total time = 1059.73 ms / 751 tokens 3.29.692.218 I slot print_timing: id 2 | task 5035 | graphs reused = 3523 3.29.692.219 I slot print_timing: id 2 | task 5035 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.692.249 I slot release: id 2 | task 5035 | stop processing: n_tokens = 750, truncated = 0 3.29.692.260 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.866 3.29.692.415 I slot launch_slot_: id 1 | task 5043 | processing task, is_child = 0 3.29.692.485 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.923 MiB) 3.29.741.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.395 MiB) 3.30.094.444 I slot print_timing: id 1 | task 5043 | prompt eval time = 249.68 ms / 107 tokens ( 2.33 ms per token, 428.55 tokens per second) 3.30.094.450 I slot print_timing: id 1 | task 5043 | eval time = 42.59 ms / 2 tokens ( 42.59 ms per token, 23.48 tokens per second) 3.30.094.451 I slot print_timing: id 1 | task 5043 | total time = 292.27 ms / 109 tokens 3.30.094.451 I slot print_timing: id 1 | task 5043 | graphs reused = 3523 3.30.094.452 I slot print_timing: id 1 | task 5043 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.094.489 I slot release: id 1 | task 5043 | stop processing: n_tokens = 679, truncated = 0 3.30.109.702 I slot print_timing: id 0 | task 5040 | prompt eval time = 568.25 ms / 712 tokens ( 0.80 ms per token, 1252.96 tokens per second) 3.30.109.708 I slot print_timing: id 0 | task 5040 | eval time = 15.54 ms / 2 tokens ( 15.54 ms per token, 64.36 tokens per second) 3.30.109.708 I slot print_timing: id 0 | task 5040 | total time = 583.79 ms / 714 tokens 3.30.109.709 I slot print_timing: id 0 | task 5040 | graphs reused = 3523 3.30.109.710 I slot print_timing: id 0 | task 5040 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.109.740 I slot release: id 0 | task 5040 | stop processing: n_tokens = 713, truncated = 0