C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\dl\campaign\70c112196e0b\Ornith-1.5-9B-Q4_K_M.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 0.00.093.602 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.093.749 I srv llama_server: initializing ... 0.00.093.754 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.093.863 I srv init_listene: The UI is disabled 0.00.093.865 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.093.945 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.107.902 I srv load_model: loading model 'C:\quantdiff\dl\campaign\70c112196e0b\Ornith-1.5-9B-Q4_K_M.gguf' 0.00.925.996 W model has unused tensor blk.32.attn_norm.weight (size = 16384 bytes) -- ignoring 0.00.926.011 W model has unused tensor blk.32.post_attention_norm.weight (size = 16384 bytes) -- ignoring 0.00.926.036 W model has unused tensor blk.32.attn_q.weight (size = 18874368 bytes) -- ignoring 0.00.926.045 W model has unused tensor blk.32.attn_k.weight (size = 2359296 bytes) -- ignoring 0.00.926.054 W model has unused tensor blk.32.attn_v.weight (size = 3440640 bytes) -- ignoring 0.00.926.087 W model has unused tensor blk.32.attn_output.weight (size = 9437184 bytes) -- ignoring 0.00.926.098 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.926.107 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.926.116 W model has unused tensor blk.32.ffn_gate.weight (size = 28311552 bytes) -- ignoring 0.00.926.125 W model has unused tensor blk.32.ffn_down.weight (size = 41287680 bytes) -- ignoring 0.00.926.134 W model has unused tensor blk.32.ffn_up.weight (size = 28311552 bytes) -- ignoring 0.00.926.143 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 18874368 bytes) -- ignoring 0.00.926.154 W model has unused tensor blk.32.nextn.enorm.weight (size = 16384 bytes) -- ignoring 0.00.926.163 W model has unused tensor blk.32.nextn.hnorm.weight (size = 16384 bytes) -- ignoring 0.00.926.191 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 16384 bytes) -- ignoring 0.02.721.593 I cmn init: llama threadpool init, n_threads = 8 0.02.800.237 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.02.805.267 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.02.805.285 I srv llama_server: model loaded 0.02.805.288 I srv llama_server: listening on http://127.0.0.1:8091 0.44.877.224 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.44.877.274 I slot launch_slot_: id 0 | task 2 | processing task, is_child = 0 0.44.877.280 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.44.877.310 I slot launch_slot_: id 1 | task 0 | processing task, is_child = 0 0.44.877.314 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.44.877.342 I slot launch_slot_: id 2 | task 1 | processing task, is_child = 0 0.45.064.727 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.45.064.807 I slot launch_slot_: id 3 | task 4 | processing task, is_child = 0 0.45.192.282 I slot print_timing: id 0 | task 2 | prompt eval time = 274.17 ms / 130 tokens ( 2.11 ms per token, 474.16 tokens per second) 0.45.192.288 I slot print_timing: id 0 | task 2 | eval time = 40.76 ms / 2 tokens ( 40.76 ms per token, 24.54 tokens per second) 0.45.192.289 I slot print_timing: id 0 | task 2 | total time = 314.92 ms / 132 tokens 0.45.192.293 I slot print_timing: id 0 | task 2 | graphs reused = 1 0.45.192.294 I slot print_timing: id 0 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.192.326 I slot release: id 0 | task 2 | stop processing: n_tokens = 131, truncated = 0 0.45.192.632 I slot print_timing: id 1 | task 0 | prompt eval time = 274.83 ms / 115 tokens ( 2.39 ms per token, 418.44 tokens per second) 0.45.192.635 I slot print_timing: id 1 | task 0 | eval time = 40.43 ms / 2 tokens ( 40.43 ms per token, 24.73 tokens per second) 0.45.192.636 I slot print_timing: id 1 | task 0 | total time = 315.26 ms / 117 tokens 0.45.192.636 I slot print_timing: id 1 | task 0 | graphs reused = 1 0.45.192.637 I slot print_timing: id 1 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.192.649 I slot release: id 1 | task 0 | stop processing: n_tokens = 116, truncated = 0 0.45.192.953 I slot print_timing: id 2 | task 1 | prompt eval time = 275.49 ms / 122 tokens ( 2.26 ms per token, 442.85 tokens per second) 0.45.192.955 I slot print_timing: id 2 | task 1 | eval time = 40.09 ms / 2 tokens ( 40.09 ms per token, 24.95 tokens per second) 0.45.192.956 I slot print_timing: id 2 | task 1 | total time = 315.58 ms / 124 tokens 0.45.192.957 I slot print_timing: id 2 | task 1 | graphs reused = 1 0.45.192.958 I slot print_timing: id 2 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.192.971 I slot release: id 2 | task 1 | stop processing: n_tokens = 123, truncated = 0 0.45.207.549 I slot print_timing: id 3 | task 4 | prompt eval time = 94.52 ms / 115 tokens ( 0.82 ms per token, 1216.70 tokens per second) 0.45.207.554 I slot print_timing: id 3 | task 4 | eval time = 13.93 ms / 2 tokens ( 13.93 ms per token, 71.77 tokens per second) 0.45.207.555 I slot print_timing: id 3 | task 4 | total time = 108.45 ms / 117 tokens 0.45.207.557 I slot print_timing: id 3 | task 4 | graphs reused = 1 0.45.207.558 I slot print_timing: id 3 | task 4 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.207.576 I slot release: id 3 | task 4 | stop processing: n_tokens = 116, truncated = 0 0.45.251.396 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.214 0.45.268.499 I slot launch_slot_: id 0 | task 8 | processing task, is_child = 0 0.45.317.781 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.236 0.45.317.929 I slot launch_slot_: id 2 | task 9 | processing task, is_child = 0 0.45.317.970 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.241 0.45.318.085 I slot launch_slot_: id 1 | task 10 | processing task, is_child = 0 0.45.318.107 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.250 0.45.318.210 I slot launch_slot_: id 3 | task 11 | processing task, is_child = 0 0.45.568.219 I slot print_timing: id 0 | task 8 | prompt eval time = 231.92 ms / 200 tokens ( 1.16 ms per token, 862.37 tokens per second) 0.45.568.225 I slot print_timing: id 0 | task 8 | eval time = 18.07 ms / 2 tokens ( 18.07 ms per token, 55.33 tokens per second) 0.45.568.226 I slot print_timing: id 0 | task 8 | total time = 249.99 ms / 202 tokens 0.45.568.227 I slot print_timing: id 0 | task 8 | graphs reused = 1 0.45.568.228 I slot print_timing: id 0 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.568.261 I slot release: id 0 | task 8 | stop processing: n_tokens = 201, truncated = 0 0.45.568.570 I slot print_timing: id 1 | task 10 | prompt eval time = 231.69 ms / 160 tokens ( 1.45 ms per token, 690.59 tokens per second) 0.45.568.573 I slot print_timing: id 1 | task 10 | eval time = 17.76 ms / 2 tokens ( 17.76 ms per token, 56.30 tokens per second) 0.45.568.574 I slot print_timing: id 1 | task 10 | total time = 249.45 ms / 162 tokens 0.45.568.574 I slot print_timing: id 1 | task 10 | graphs reused = 1 0.45.568.575 I slot print_timing: id 1 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.568.593 I slot release: id 1 | task 10 | stop processing: n_tokens = 161, truncated = 0 0.45.568.867 I slot print_timing: id 2 | task 9 | prompt eval time = 231.39 ms / 152 tokens ( 1.52 ms per token, 656.89 tokens per second) 0.45.568.870 I slot print_timing: id 2 | task 9 | eval time = 17.48 ms / 2 tokens ( 17.48 ms per token, 57.22 tokens per second) 0.45.568.870 I slot print_timing: id 2 | task 9 | total time = 248.87 ms / 154 tokens 0.45.568.871 I slot print_timing: id 2 | task 9 | graphs reused = 1 0.45.568.871 I slot print_timing: id 2 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.568.885 I slot release: id 2 | task 9 | stop processing: n_tokens = 153, truncated = 0 0.45.569.142 I slot print_timing: id 3 | task 11 | prompt eval time = 231.08 ms / 108 tokens ( 2.14 ms per token, 467.37 tokens per second) 0.45.569.145 I slot print_timing: id 3 | task 11 | eval time = 17.18 ms / 2 tokens ( 17.18 ms per token, 58.20 tokens per second) 0.45.569.146 I slot print_timing: id 3 | task 11 | total time = 248.26 ms / 110 tokens 0.45.569.146 I slot print_timing: id 3 | task 11 | graphs reused = 1 0.45.569.147 I slot print_timing: id 3 | task 11 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.569.158 I slot release: id 3 | task 11 | stop processing: n_tokens = 109, truncated = 0 0.45.576.653 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.190 0.45.593.906 I slot launch_slot_: id 2 | task 15 | processing task, is_child = 0 0.45.643.353 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.139 0.45.643.514 I slot launch_slot_: id 0 | task 16 | processing task, is_child = 0 0.45.643.555 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 0.45.643.666 I slot launch_slot_: id 1 | task 17 | processing task, is_child = 0 0.45.643.688 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.257 0.45.643.786 I slot launch_slot_: id 3 | task 18 | processing task, is_child = 0 0.45.871.657 I slot print_timing: id 0 | task 16 | prompt eval time = 209.88 ms / 150 tokens ( 1.40 ms per token, 714.69 tokens per second) 0.45.871.662 I slot print_timing: id 0 | task 16 | eval time = 17.97 ms / 2 tokens ( 17.97 ms per token, 55.64 tokens per second) 0.45.871.663 I slot print_timing: id 0 | task 16 | total time = 227.85 ms / 152 tokens 0.45.871.664 I slot print_timing: id 0 | task 16 | graphs reused = 1 0.45.871.665 I slot print_timing: id 0 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.871.693 I slot release: id 0 | task 16 | stop processing: n_tokens = 151, truncated = 0 0.45.872.004 I slot print_timing: id 1 | task 17 | prompt eval time = 209.66 ms / 125 tokens ( 1.68 ms per token, 596.21 tokens per second) 0.45.872.007 I slot print_timing: id 1 | task 17 | eval time = 17.66 ms / 2 tokens ( 17.66 ms per token, 56.63 tokens per second) 0.45.872.008 I slot print_timing: id 1 | task 17 | total time = 227.31 ms / 127 tokens 0.45.872.009 I slot print_timing: id 1 | task 17 | graphs reused = 1 0.45.872.010 I slot print_timing: id 1 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.872.023 I slot release: id 1 | task 17 | stop processing: n_tokens = 126, truncated = 0 0.45.872.278 I slot print_timing: id 2 | task 15 | prompt eval time = 209.38 ms / 118 tokens ( 1.77 ms per token, 563.58 tokens per second) 0.45.872.281 I slot print_timing: id 2 | task 15 | eval time = 17.36 ms / 2 tokens ( 17.36 ms per token, 57.60 tokens per second) 0.45.872.282 I slot print_timing: id 2 | task 15 | total time = 226.74 ms / 120 tokens 0.45.872.283 I slot print_timing: id 2 | task 15 | graphs reused = 1 0.45.872.283 I slot print_timing: id 2 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.872.296 I slot release: id 2 | task 15 | stop processing: n_tokens = 119, truncated = 0 0.45.872.550 I slot print_timing: id 3 | task 18 | prompt eval time = 209.11 ms / 117 tokens ( 1.79 ms per token, 559.52 tokens per second) 0.45.872.553 I slot print_timing: id 3 | task 18 | eval time = 17.07 ms / 2 tokens ( 17.07 ms per token, 58.57 tokens per second) 0.45.872.553 I slot print_timing: id 3 | task 18 | total time = 226.18 ms / 119 tokens 0.45.872.554 I slot print_timing: id 3 | task 18 | graphs reused = 1 0.45.872.554 I slot print_timing: id 3 | task 18 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.872.564 I slot release: id 3 | task 18 | stop processing: n_tokens = 118, truncated = 0 0.45.880.525 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.185 0.45.897.631 I slot launch_slot_: id 0 | task 22 | processing task, is_child = 0 0.45.964.488 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.222 0.45.964.650 I slot launch_slot_: id 1 | task 23 | processing task, is_child = 0 0.45.964.691 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.235 (> 0.100 thold), f_keep = 0.235 0.45.964.799 I slot launch_slot_: id 2 | task 24 | processing task, is_child = 0 0.45.964.821 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.237 0.45.964.917 I slot launch_slot_: id 3 | task 25 | processing task, is_child = 0 0.46.206.011 I slot print_timing: id 0 | task 22 | prompt eval time = 222.78 ms / 181 tokens ( 1.23 ms per token, 812.48 tokens per second) 0.46.206.016 I slot print_timing: id 0 | task 22 | eval time = 18.30 ms / 2 tokens ( 18.30 ms per token, 54.64 tokens per second) 0.46.206.017 I slot print_timing: id 0 | task 22 | total time = 241.08 ms / 183 tokens 0.46.206.018 I slot print_timing: id 0 | task 22 | graphs reused = 1 0.46.206.019 I slot print_timing: id 0 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.206.046 I slot release: id 0 | task 22 | stop processing: n_tokens = 182, truncated = 0 0.46.206.293 I slot print_timing: id 1 | task 23 | prompt eval time = 222.62 ms / 136 tokens ( 1.64 ms per token, 610.92 tokens per second) 0.46.206.296 I slot print_timing: id 1 | task 23 | eval time = 17.88 ms / 2 tokens ( 17.88 ms per token, 55.93 tokens per second) 0.46.206.296 I slot print_timing: id 1 | task 23 | total time = 240.50 ms / 138 tokens 0.46.206.297 I slot print_timing: id 1 | task 23 | graphs reused = 1 0.46.206.297 I slot print_timing: id 1 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.206.311 I slot release: id 1 | task 23 | stop processing: n_tokens = 137, truncated = 0 0.46.206.550 I slot print_timing: id 2 | task 24 | prompt eval time = 222.48 ms / 119 tokens ( 1.87 ms per token, 534.87 tokens per second) 0.46.206.553 I slot print_timing: id 2 | task 24 | eval time = 17.44 ms / 2 tokens ( 17.44 ms per token, 57.33 tokens per second) 0.46.206.554 I slot print_timing: id 2 | task 24 | total time = 239.93 ms / 121 tokens 0.46.206.555 I slot print_timing: id 2 | task 24 | graphs reused = 1 0.46.206.555 I slot print_timing: id 2 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.206.566 I slot release: id 2 | task 24 | stop processing: n_tokens = 120, truncated = 0 0.46.206.817 I slot print_timing: id 3 | task 25 | prompt eval time = 222.37 ms / 143 tokens ( 1.56 ms per token, 643.09 tokens per second) 0.46.206.820 I slot print_timing: id 3 | task 25 | eval time = 17.01 ms / 2 tokens ( 17.01 ms per token, 58.78 tokens per second) 0.46.206.820 I slot print_timing: id 3 | task 25 | total time = 239.38 ms / 145 tokens 0.46.206.821 I slot print_timing: id 3 | task 25 | graphs reused = 1 0.46.206.821 I slot print_timing: id 3 | task 25 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.206.833 I slot release: id 3 | task 25 | stop processing: n_tokens = 144, truncated = 0 0.46.215.638 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 0.46.245.822 I slot launch_slot_: id 0 | task 29 | processing task, is_child = 0 0.46.300.811 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.204 0.46.300.953 I slot launch_slot_: id 1 | task 30 | processing task, is_child = 0 0.46.300.996 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.233 0.46.301.099 I slot launch_slot_: id 2 | task 31 | processing task, is_child = 0 0.46.301.122 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.194 0.46.311.004 I slot launch_slot_: id 3 | task 32 | processing task, is_child = 0 0.46.558.609 I slot print_timing: id 0 | task 29 | prompt eval time = 228.47 ms / 131 tokens ( 1.74 ms per token, 573.37 tokens per second) 0.46.558.614 I slot print_timing: id 0 | task 29 | eval time = 19.11 ms / 2 tokens ( 19.11 ms per token, 52.33 tokens per second) 0.46.558.615 I slot print_timing: id 0 | task 29 | total time = 247.58 ms / 133 tokens 0.46.558.616 I slot print_timing: id 0 | task 29 | graphs reused = 1 0.46.558.618 I slot print_timing: id 0 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.558.645 I slot release: id 0 | task 29 | stop processing: n_tokens = 132, truncated = 0 0.46.558.990 I slot print_timing: id 1 | task 30 | prompt eval time = 228.37 ms / 178 tokens ( 1.28 ms per token, 779.44 tokens per second) 0.46.558.993 I slot print_timing: id 1 | task 30 | eval time = 18.72 ms / 2 tokens ( 18.72 ms per token, 53.42 tokens per second) 0.46.558.994 I slot print_timing: id 1 | task 30 | total time = 247.09 ms / 180 tokens 0.46.558.995 I slot print_timing: id 1 | task 30 | graphs reused = 1 0.46.558.995 I slot print_timing: id 1 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.559.013 I slot release: id 1 | task 30 | stop processing: n_tokens = 179, truncated = 0 0.46.559.359 I slot print_timing: id 2 | task 31 | prompt eval time = 228.27 ms / 144 tokens ( 1.59 ms per token, 630.82 tokens per second) 0.46.559.362 I slot print_timing: id 2 | task 31 | eval time = 18.32 ms / 2 tokens ( 18.32 ms per token, 54.59 tokens per second) 0.46.559.363 I slot print_timing: id 2 | task 31 | total time = 246.59 ms / 146 tokens 0.46.559.363 I slot print_timing: id 2 | task 31 | graphs reused = 1 0.46.559.364 I slot print_timing: id 2 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.559.375 I slot release: id 2 | task 31 | stop processing: n_tokens = 145, truncated = 0 0.46.559.676 I slot print_timing: id 3 | task 32 | prompt eval time = 228.18 ms / 122 tokens ( 1.87 ms per token, 534.68 tokens per second) 0.46.559.680 I slot print_timing: id 3 | task 32 | eval time = 17.87 ms / 2 tokens ( 17.87 ms per token, 55.96 tokens per second) 0.46.559.680 I slot print_timing: id 3 | task 32 | total time = 246.05 ms / 124 tokens 0.46.559.681 I slot print_timing: id 3 | task 32 | graphs reused = 1 0.46.559.682 I slot print_timing: id 3 | task 32 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.559.693 I slot release: id 3 | task 32 | stop processing: n_tokens = 123, truncated = 0 0.46.566.995 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 0.46.588.445 I slot launch_slot_: id 0 | task 36 | processing task, is_child = 0 0.46.639.014 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.156 0.46.639.180 I slot launch_slot_: id 1 | task 37 | processing task, is_child = 0 0.46.639.225 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.193 0.46.639.339 I slot launch_slot_: id 2 | task 38 | processing task, is_child = 0 0.46.639.361 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.236 0.46.639.462 I slot launch_slot_: id 3 | task 39 | processing task, is_child = 0 0.46.874.867 I slot print_timing: id 0 | task 36 | prompt eval time = 216.36 ms / 113 tokens ( 1.91 ms per token, 522.28 tokens per second) 0.46.874.872 I slot print_timing: id 0 | task 36 | eval time = 19.03 ms / 2 tokens ( 19.03 ms per token, 52.56 tokens per second) 0.46.874.873 I slot print_timing: id 0 | task 36 | total time = 235.39 ms / 115 tokens 0.46.874.874 I slot print_timing: id 0 | task 36 | graphs reused = 1 0.46.874.875 I slot print_timing: id 0 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.874.899 I slot release: id 0 | task 36 | stop processing: n_tokens = 114, truncated = 0 0.46.875.259 I slot print_timing: id 1 | task 37 | prompt eval time = 216.31 ms / 142 tokens ( 1.52 ms per token, 656.47 tokens per second) 0.46.875.263 I slot print_timing: id 1 | task 37 | eval time = 18.61 ms / 2 tokens ( 18.61 ms per token, 53.75 tokens per second) 0.46.875.263 I slot print_timing: id 1 | task 37 | total time = 234.91 ms / 144 tokens 0.46.875.264 I slot print_timing: id 1 | task 37 | graphs reused = 1 0.46.875.264 I slot print_timing: id 1 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.875.280 I slot release: id 1 | task 37 | stop processing: n_tokens = 143, truncated = 0 0.46.875.662 I slot print_timing: id 2 | task 38 | prompt eval time = 216.26 ms / 144 tokens ( 1.50 ms per token, 665.86 tokens per second) 0.46.875.665 I slot print_timing: id 2 | task 38 | eval time = 18.20 ms / 2 tokens ( 18.20 ms per token, 54.95 tokens per second) 0.46.875.666 I slot print_timing: id 2 | task 38 | total time = 234.46 ms / 146 tokens 0.46.875.666 I slot print_timing: id 2 | task 38 | graphs reused = 1 0.46.875.667 I slot print_timing: id 2 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.875.680 I slot release: id 2 | task 38 | stop processing: n_tokens = 145, truncated = 0 0.46.876.033 I slot print_timing: id 3 | task 39 | prompt eval time = 216.10 ms / 120 tokens ( 1.80 ms per token, 555.30 tokens per second) 0.46.876.036 I slot print_timing: id 3 | task 39 | eval time = 17.88 ms / 2 tokens ( 17.88 ms per token, 55.93 tokens per second) 0.46.876.036 I slot print_timing: id 3 | task 39 | total time = 233.98 ms / 122 tokens 0.46.876.037 I slot print_timing: id 3 | task 39 | graphs reused = 1 0.46.876.038 I slot print_timing: id 3 | task 39 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.876.046 I slot release: id 3 | task 39 | stop processing: n_tokens = 121, truncated = 0 0.46.883.388 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.240 0.46.900.633 I slot launch_slot_: id 3 | task 43 | processing task, is_child = 0 0.46.950.516 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.246 0.46.950.808 I slot launch_slot_: id 0 | task 44 | processing task, is_child = 0 0.46.950.855 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.196 0.46.951.095 I slot launch_slot_: id 1 | task 45 | processing task, is_child = 0 0.46.951.120 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.193 0.46.951.348 I slot launch_slot_: id 2 | task 46 | processing task, is_child = 0 0.47.187.959 I slot print_timing: id 0 | task 44 | prompt eval time = 217.79 ms / 123 tokens ( 1.77 ms per token, 564.76 tokens per second) 0.47.187.964 I slot print_timing: id 0 | task 44 | eval time = 18.80 ms / 2 tokens ( 18.80 ms per token, 53.18 tokens per second) 0.47.187.965 I slot print_timing: id 0 | task 44 | total time = 236.59 ms / 125 tokens 0.47.187.967 I slot print_timing: id 0 | task 44 | graphs reused = 1 0.47.187.967 I slot print_timing: id 0 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.187.993 I slot release: id 0 | task 44 | stop processing: n_tokens = 124, truncated = 0 0.47.188.339 I slot print_timing: id 1 | task 45 | prompt eval time = 215.71 ms / 109 tokens ( 1.98 ms per token, 505.31 tokens per second) 0.47.188.342 I slot print_timing: id 1 | task 45 | eval time = 18.38 ms / 2 tokens ( 18.38 ms per token, 54.40 tokens per second) 0.47.188.343 I slot print_timing: id 1 | task 45 | total time = 234.09 ms / 111 tokens 0.47.188.343 I slot print_timing: id 1 | task 45 | graphs reused = 1 0.47.188.344 I slot print_timing: id 1 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.188.357 I slot release: id 1 | task 45 | stop processing: n_tokens = 110, truncated = 0 0.47.188.738 I slot print_timing: id 2 | task 46 | prompt eval time = 213.62 ms / 143 tokens ( 1.49 ms per token, 669.43 tokens per second) 0.47.188.741 I slot print_timing: id 2 | task 46 | eval time = 17.98 ms / 2 tokens ( 17.98 ms per token, 55.61 tokens per second) 0.47.188.741 I slot print_timing: id 2 | task 46 | total time = 231.60 ms / 145 tokens 0.47.188.742 I slot print_timing: id 2 | task 46 | graphs reused = 1 0.47.188.743 I slot print_timing: id 2 | task 46 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.188.755 I slot release: id 2 | task 46 | stop processing: n_tokens = 144, truncated = 0 0.47.189.051 I slot print_timing: id 3 | task 43 | prompt eval time = 213.25 ms / 112 tokens ( 1.90 ms per token, 525.21 tokens per second) 0.47.189.054 I slot print_timing: id 3 | task 43 | eval time = 17.72 ms / 2 tokens ( 17.72 ms per token, 56.43 tokens per second) 0.47.189.054 I slot print_timing: id 3 | task 43 | total time = 230.97 ms / 114 tokens 0.47.189.055 I slot print_timing: id 3 | task 43 | graphs reused = 1 0.47.189.055 I slot print_timing: id 3 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.189.066 I slot release: id 3 | task 43 | stop processing: n_tokens = 113, truncated = 0 0.47.197.508 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.226 0.47.214.380 I slot launch_slot_: id 0 | task 50 | processing task, is_child = 0 0.47.263.112 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.257 0.47.263.257 I slot launch_slot_: id 3 | task 52 | processing task, is_child = 0 0.47.263.299 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.255 0.47.263.410 I slot launch_slot_: id 1 | task 51 | processing task, is_child = 0 0.47.263.433 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.194 0.47.271.560 I slot launch_slot_: id 2 | task 53 | processing task, is_child = 0 0.47.508.883 I slot print_timing: id 0 | task 50 | prompt eval time = 218.31 ms / 136 tokens ( 1.61 ms per token, 622.98 tokens per second) 0.47.508.888 I slot print_timing: id 0 | task 50 | eval time = 19.00 ms / 2 tokens ( 19.00 ms per token, 52.64 tokens per second) 0.47.508.889 I slot print_timing: id 0 | task 50 | total time = 237.30 ms / 138 tokens 0.47.508.890 I slot print_timing: id 0 | task 50 | graphs reused = 1 0.47.508.891 I slot print_timing: id 0 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.508.917 I slot release: id 0 | task 50 | stop processing: n_tokens = 137, truncated = 0 0.47.509.255 I slot print_timing: id 1 | task 51 | prompt eval time = 218.19 ms / 102 tokens ( 2.14 ms per token, 467.47 tokens per second) 0.47.509.258 I slot print_timing: id 1 | task 51 | eval time = 18.59 ms / 2 tokens ( 18.59 ms per token, 53.80 tokens per second) 0.47.509.258 I slot print_timing: id 1 | task 51 | total time = 236.78 ms / 104 tokens 0.47.509.259 I slot print_timing: id 1 | task 51 | graphs reused = 1 0.47.509.259 I slot print_timing: id 1 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.509.273 I slot release: id 1 | task 51 | stop processing: n_tokens = 103, truncated = 0 0.47.509.615 I slot print_timing: id 2 | task 53 | prompt eval time = 218.05 ms / 129 tokens ( 1.69 ms per token, 591.60 tokens per second) 0.47.509.618 I slot print_timing: id 2 | task 53 | eval time = 18.22 ms / 2 tokens ( 18.22 ms per token, 54.88 tokens per second) 0.47.509.619 I slot print_timing: id 2 | task 53 | total time = 236.27 ms / 131 tokens 0.47.509.619 I slot print_timing: id 2 | task 53 | graphs reused = 1 0.47.509.620 I slot print_timing: id 2 | task 53 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.509.632 I slot release: id 2 | task 53 | stop processing: n_tokens = 130, truncated = 0 0.47.509.990 I slot print_timing: id 3 | task 52 | prompt eval time = 217.92 ms / 112 tokens ( 1.95 ms per token, 513.96 tokens per second) 0.47.509.993 I slot print_timing: id 3 | task 52 | eval time = 17.93 ms / 2 tokens ( 17.93 ms per token, 55.76 tokens per second) 0.47.509.993 I slot print_timing: id 3 | task 52 | total time = 235.85 ms / 114 tokens 0.47.509.994 I slot print_timing: id 3 | task 52 | graphs reused = 1 0.47.509.995 I slot print_timing: id 3 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.510.005 I slot release: id 3 | task 52 | stop processing: n_tokens = 113, truncated = 0 0.47.518.888 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.204 0.47.536.119 I slot launch_slot_: id 0 | task 57 | processing task, is_child = 0 0.47.585.644 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.272 0.47.585.811 I slot launch_slot_: id 1 | task 58 | processing task, is_child = 0 0.47.585.855 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.215 0.47.585.970 I slot launch_slot_: id 2 | task 60 | processing task, is_child = 0 0.47.585.993 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.248 0.47.586.094 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 0.47.847.392 I slot print_timing: id 0 | task 57 | prompt eval time = 242.38 ms / 166 tokens ( 1.46 ms per token, 684.88 tokens per second) 0.47.847.398 I slot print_timing: id 0 | task 57 | eval time = 18.90 ms / 2 tokens ( 18.90 ms per token, 52.90 tokens per second) 0.47.847.399 I slot print_timing: id 0 | task 57 | total time = 261.28 ms / 168 tokens 0.47.847.400 I slot print_timing: id 0 | task 57 | graphs reused = 1 0.47.847.401 I slot print_timing: id 0 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.847.428 I slot release: id 0 | task 57 | stop processing: n_tokens = 167, truncated = 0 0.47.847.800 I slot print_timing: id 1 | task 58 | prompt eval time = 242.31 ms / 177 tokens ( 1.37 ms per token, 730.46 tokens per second) 0.47.847.803 I slot print_timing: id 1 | task 58 | eval time = 18.48 ms / 2 tokens ( 18.48 ms per token, 54.10 tokens per second) 0.47.847.804 I slot print_timing: id 1 | task 58 | total time = 260.80 ms / 179 tokens 0.47.847.805 I slot print_timing: id 1 | task 58 | graphs reused = 1 0.47.847.805 I slot print_timing: id 1 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.847.825 I slot release: id 1 | task 58 | stop processing: n_tokens = 178, truncated = 0 0.47.848.201 I slot print_timing: id 2 | task 60 | prompt eval time = 242.20 ms / 182 tokens ( 1.33 ms per token, 751.44 tokens per second) 0.47.848.204 I slot print_timing: id 2 | task 60 | eval time = 18.14 ms / 2 tokens ( 18.14 ms per token, 55.14 tokens per second) 0.47.848.205 I slot print_timing: id 2 | task 60 | total time = 260.34 ms / 184 tokens 0.47.848.205 I slot print_timing: id 2 | task 60 | graphs reused = 1 0.47.848.206 I slot print_timing: id 2 | task 60 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.848.222 I slot release: id 2 | task 60 | stop processing: n_tokens = 183, truncated = 0 0.47.848.511 I slot print_timing: id 3 | task 59 | prompt eval time = 241.89 ms / 132 tokens ( 1.83 ms per token, 545.70 tokens per second) 0.47.848.514 I slot print_timing: id 3 | task 59 | eval time = 17.90 ms / 2 tokens ( 17.90 ms per token, 55.87 tokens per second) 0.47.848.515 I slot print_timing: id 3 | task 59 | total time = 259.79 ms / 134 tokens 0.47.848.516 I slot print_timing: id 3 | task 59 | graphs reused = 1 0.47.848.516 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.848.527 I slot release: id 3 | task 59 | stop processing: n_tokens = 133, truncated = 0 0.47.857.248 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.168 0.47.874.419 I slot launch_slot_: id 0 | task 64 | processing task, is_child = 0 0.47.923.874 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 0.47.924.012 I slot launch_slot_: id 1 | task 65 | processing task, is_child = 0 0.47.924.057 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.153 0.47.924.166 I slot launch_slot_: id 2 | task 66 | processing task, is_child = 0 0.47.924.189 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.211 0.47.932.415 I slot launch_slot_: id 3 | task 67 | processing task, is_child = 0 0.48.176.669 I slot print_timing: id 0 | task 64 | prompt eval time = 225.74 ms / 123 tokens ( 1.84 ms per token, 544.87 tokens per second) 0.48.176.675 I slot print_timing: id 0 | task 64 | eval time = 18.49 ms / 2 tokens ( 18.49 ms per token, 54.07 tokens per second) 0.48.176.676 I slot print_timing: id 0 | task 64 | total time = 244.24 ms / 125 tokens 0.48.176.677 I slot print_timing: id 0 | task 64 | graphs reused = 1 0.48.176.678 I slot print_timing: id 0 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.176.706 I slot release: id 0 | task 64 | stop processing: n_tokens = 124, truncated = 0 0.48.177.049 I slot print_timing: id 1 | task 65 | prompt eval time = 225.56 ms / 149 tokens ( 1.51 ms per token, 660.57 tokens per second) 0.48.177.052 I slot print_timing: id 1 | task 65 | eval time = 18.19 ms / 2 tokens ( 18.19 ms per token, 54.96 tokens per second) 0.48.177.053 I slot print_timing: id 1 | task 65 | total time = 243.76 ms / 151 tokens 0.48.177.053 I slot print_timing: id 1 | task 65 | graphs reused = 1 0.48.177.054 I slot print_timing: id 1 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.177.068 I slot release: id 1 | task 65 | stop processing: n_tokens = 150, truncated = 0 0.48.177.391 I slot print_timing: id 2 | task 66 | prompt eval time = 225.42 ms / 169 tokens ( 1.33 ms per token, 749.70 tokens per second) 0.48.177.394 I slot print_timing: id 2 | task 66 | eval time = 17.82 ms / 2 tokens ( 17.82 ms per token, 56.11 tokens per second) 0.48.177.395 I slot print_timing: id 2 | task 66 | total time = 243.25 ms / 171 tokens 0.48.177.396 I slot print_timing: id 2 | task 66 | graphs reused = 1 0.48.177.396 I slot print_timing: id 2 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.177.409 I slot release: id 2 | task 66 | stop processing: n_tokens = 170, truncated = 0 0.48.177.734 I slot print_timing: id 3 | task 67 | prompt eval time = 225.23 ms / 140 tokens ( 1.61 ms per token, 621.60 tokens per second) 0.48.177.737 I slot print_timing: id 3 | task 67 | eval time = 17.51 ms / 2 tokens ( 17.51 ms per token, 57.12 tokens per second) 0.48.177.737 I slot print_timing: id 3 | task 67 | total time = 242.73 ms / 142 tokens 0.48.177.738 I slot print_timing: id 3 | task 67 | graphs reused = 1 0.48.177.738 I slot print_timing: id 3 | task 67 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.177.749 I slot release: id 3 | task 67 | stop processing: n_tokens = 141, truncated = 0 0.48.185.256 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.226 0.48.202.294 I slot launch_slot_: id 0 | task 71 | processing task, is_child = 0 0.48.251.618 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.206 0.48.251.765 I slot launch_slot_: id 3 | task 72 | processing task, is_child = 0 0.48.251.811 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.187 0.48.251.937 I slot launch_slot_: id 1 | task 73 | processing task, is_child = 0 0.48.251.964 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.165 0.48.252.071 I slot launch_slot_: id 2 | task 74 | processing task, is_child = 0 0.48.497.669 I slot print_timing: id 0 | task 71 | prompt eval time = 227.12 ms / 128 tokens ( 1.77 ms per token, 563.57 tokens per second) 0.48.497.675 I slot print_timing: id 0 | task 71 | eval time = 18.46 ms / 2 tokens ( 18.46 ms per token, 54.17 tokens per second) 0.48.497.676 I slot print_timing: id 0 | task 71 | total time = 245.58 ms / 130 tokens 0.48.497.677 I slot print_timing: id 0 | task 71 | graphs reused = 1 0.48.497.678 I slot print_timing: id 0 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.497.702 I slot release: id 0 | task 71 | stop processing: n_tokens = 129, truncated = 0 0.48.498.084 I slot print_timing: id 1 | task 73 | prompt eval time = 227.06 ms / 163 tokens ( 1.39 ms per token, 717.88 tokens per second) 0.48.498.087 I slot print_timing: id 1 | task 73 | eval time = 18.08 ms / 2 tokens ( 18.08 ms per token, 55.32 tokens per second) 0.48.498.087 I slot print_timing: id 1 | task 73 | total time = 245.13 ms / 165 tokens 0.48.498.088 I slot print_timing: id 1 | task 73 | graphs reused = 1 0.48.498.089 I slot print_timing: id 1 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.498.105 I slot release: id 1 | task 73 | stop processing: n_tokens = 164, truncated = 0 0.48.498.488 I slot print_timing: id 2 | task 74 | prompt eval time = 226.89 ms / 161 tokens ( 1.41 ms per token, 709.59 tokens per second) 0.48.498.491 I slot print_timing: id 2 | task 74 | eval time = 17.77 ms / 2 tokens ( 17.77 ms per token, 56.27 tokens per second) 0.48.498.492 I slot print_timing: id 2 | task 74 | total time = 244.66 ms / 163 tokens 0.48.498.493 I slot print_timing: id 2 | task 74 | graphs reused = 1 0.48.498.494 I slot print_timing: id 2 | task 74 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.498.512 I slot release: id 2 | task 74 | stop processing: n_tokens = 162, truncated = 0 0.48.498.913 I slot print_timing: id 3 | task 72 | prompt eval time = 226.61 ms / 111 tokens ( 2.04 ms per token, 489.84 tokens per second) 0.48.498.918 I slot print_timing: id 3 | task 72 | eval time = 17.61 ms / 2 tokens ( 17.61 ms per token, 56.80 tokens per second) 0.48.498.919 I slot print_timing: id 3 | task 72 | total time = 244.21 ms / 113 tokens 0.48.498.919 I slot print_timing: id 3 | task 72 | graphs reused = 1 0.48.498.920 I slot print_timing: id 3 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.498.937 I slot release: id 3 | task 72 | stop processing: n_tokens = 112, truncated = 0 0.48.506.765 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 0.48.523.322 I slot launch_slot_: id 0 | task 78 | processing task, is_child = 0 0.48.572.456 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.177 0.48.572.608 I slot launch_slot_: id 1 | task 79 | processing task, is_child = 0 0.48.572.652 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.173 0.48.572.766 I slot launch_slot_: id 2 | task 80 | processing task, is_child = 0 0.48.572.789 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.250 0.48.572.884 I slot launch_slot_: id 3 | task 81 | processing task, is_child = 0 0.48.816.475 I slot print_timing: id 0 | task 78 | prompt eval time = 224.84 ms / 167 tokens ( 1.35 ms per token, 742.76 tokens per second) 0.48.816.481 I slot print_timing: id 0 | task 78 | eval time = 18.74 ms / 2 tokens ( 18.74 ms per token, 53.37 tokens per second) 0.48.816.483 I slot print_timing: id 0 | task 78 | total time = 243.57 ms / 169 tokens 0.48.816.484 I slot print_timing: id 0 | task 78 | graphs reused = 1 0.48.816.485 I slot print_timing: id 0 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.816.514 I slot release: id 0 | task 78 | stop processing: n_tokens = 168, truncated = 0 0.48.816.974 I slot print_timing: id 1 | task 79 | prompt eval time = 224.74 ms / 109 tokens ( 2.06 ms per token, 485.01 tokens per second) 0.48.816.979 I slot print_timing: id 1 | task 79 | eval time = 18.41 ms / 2 tokens ( 18.41 ms per token, 54.33 tokens per second) 0.48.816.979 I slot print_timing: id 1 | task 79 | total time = 243.14 ms / 111 tokens 0.48.816.980 I slot print_timing: id 1 | task 79 | graphs reused = 1 0.48.816.981 I slot print_timing: id 1 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.816.998 I slot release: id 1 | task 79 | stop processing: n_tokens = 110, truncated = 0 0.48.817.481 I slot print_timing: id 2 | task 80 | prompt eval time = 224.69 ms / 112 tokens ( 2.01 ms per token, 498.46 tokens per second) 0.48.817.484 I slot print_timing: id 2 | task 80 | eval time = 18.09 ms / 2 tokens ( 18.09 ms per token, 55.29 tokens per second) 0.48.817.485 I slot print_timing: id 2 | task 80 | total time = 242.78 ms / 114 tokens 0.48.817.485 I slot print_timing: id 2 | task 80 | graphs reused = 1 0.48.817.486 I slot print_timing: id 2 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.817.498 I slot release: id 2 | task 80 | stop processing: n_tokens = 113, truncated = 0 0.48.817.824 I slot print_timing: id 3 | task 81 | prompt eval time = 224.46 ms / 164 tokens ( 1.37 ms per token, 730.64 tokens per second) 0.48.817.827 I slot print_timing: id 3 | task 81 | eval time = 17.80 ms / 2 tokens ( 17.80 ms per token, 56.17 tokens per second) 0.48.817.829 I slot print_timing: id 3 | task 81 | total time = 242.26 ms / 166 tokens 0.48.817.829 I slot print_timing: id 3 | task 81 | graphs reused = 1 0.48.817.830 I slot print_timing: id 3 | task 81 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.817.843 I slot release: id 3 | task 81 | stop processing: n_tokens = 165, truncated = 0 0.48.826.194 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.167 0.48.843.041 I slot launch_slot_: id 0 | task 86 | processing task, is_child = 0 0.48.891.883 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 0.48.899.975 I slot launch_slot_: id 1 | task 85 | processing task, is_child = 0 0.48.900.023 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.248 0.48.900.131 I slot launch_slot_: id 2 | task 88 | processing task, is_child = 0 0.48.900.157 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.170 0.48.900.252 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 0.49.130.944 I slot print_timing: id 0 | task 86 | prompt eval time = 212.76 ms / 147 tokens ( 1.45 ms per token, 690.93 tokens per second) 0.49.130.950 I slot print_timing: id 0 | task 86 | eval time = 17.92 ms / 2 tokens ( 17.92 ms per token, 55.81 tokens per second) 0.49.130.951 I slot print_timing: id 0 | task 86 | total time = 230.68 ms / 149 tokens 0.49.130.952 I slot print_timing: id 0 | task 86 | graphs reused = 1 0.49.130.953 I slot print_timing: id 0 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.130.975 I slot release: id 0 | task 86 | stop processing: n_tokens = 148, truncated = 0 0.49.131.240 I slot print_timing: id 1 | task 85 | prompt eval time = 212.51 ms / 122 tokens ( 1.74 ms per token, 574.08 tokens per second) 0.49.131.243 I slot print_timing: id 1 | task 85 | eval time = 17.62 ms / 2 tokens ( 17.62 ms per token, 56.75 tokens per second) 0.49.131.244 I slot print_timing: id 1 | task 85 | total time = 230.13 ms / 124 tokens 0.49.131.244 I slot print_timing: id 1 | task 85 | graphs reused = 1 0.49.131.245 I slot print_timing: id 1 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.131.260 I slot release: id 1 | task 85 | stop processing: n_tokens = 123, truncated = 0 0.49.131.510 I slot print_timing: id 2 | task 88 | prompt eval time = 212.36 ms / 120 tokens ( 1.77 ms per token, 565.07 tokens per second) 0.49.131.513 I slot print_timing: id 2 | task 88 | eval time = 17.32 ms / 2 tokens ( 17.32 ms per token, 57.72 tokens per second) 0.49.131.513 I slot print_timing: id 2 | task 88 | total time = 229.69 ms / 122 tokens 0.49.131.514 I slot print_timing: id 2 | task 88 | graphs reused = 1 0.49.131.514 I slot print_timing: id 2 | task 88 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.131.525 I slot release: id 2 | task 88 | stop processing: n_tokens = 121, truncated = 0 0.49.131.765 I slot print_timing: id 3 | task 87 | prompt eval time = 212.06 ms / 131 tokens ( 1.62 ms per token, 617.74 tokens per second) 0.49.131.768 I slot print_timing: id 3 | task 87 | eval time = 17.02 ms / 2 tokens ( 17.02 ms per token, 58.76 tokens per second) 0.49.131.769 I slot print_timing: id 3 | task 87 | total time = 229.08 ms / 133 tokens 0.49.131.769 I slot print_timing: id 3 | task 87 | graphs reused = 1 0.49.131.770 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.131.780 I slot release: id 3 | task 87 | stop processing: n_tokens = 132, truncated = 0 0.49.140.906 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.236 0.49.158.293 I slot launch_slot_: id 1 | task 92 | processing task, is_child = 0 0.49.206.682 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.189 0.49.206.841 I slot launch_slot_: id 0 | task 93 | processing task, is_child = 0 0.49.206.885 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.231 0.49.215.004 I slot launch_slot_: id 2 | task 94 | processing task, is_child = 0 0.49.215.032 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.212 0.49.215.142 I slot launch_slot_: id 3 | task 95 | processing task, is_child = 0 0.49.453.085 I slot print_timing: id 0 | task 93 | prompt eval time = 219.49 ms / 124 tokens ( 1.77 ms per token, 564.95 tokens per second) 0.49.453.090 I slot print_timing: id 0 | task 93 | eval time = 18.44 ms / 2 tokens ( 18.44 ms per token, 54.24 tokens per second) 0.49.453.091 I slot print_timing: id 0 | task 93 | total time = 237.93 ms / 126 tokens 0.49.453.092 I slot print_timing: id 0 | task 93 | graphs reused = 1 0.49.453.093 I slot print_timing: id 0 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.453.116 I slot release: id 0 | task 93 | stop processing: n_tokens = 125, truncated = 0 0.49.453.425 I slot print_timing: id 1 | task 92 | prompt eval time = 219.49 ms / 131 tokens ( 1.68 ms per token, 596.85 tokens per second) 0.49.453.428 I slot print_timing: id 1 | task 92 | eval time = 18.00 ms / 2 tokens ( 18.00 ms per token, 55.56 tokens per second) 0.49.453.429 I slot print_timing: id 1 | task 92 | total time = 237.48 ms / 133 tokens 0.49.453.429 I slot print_timing: id 1 | task 92 | graphs reused = 1 0.49.453.430 I slot print_timing: id 1 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.453.443 I slot release: id 1 | task 92 | stop processing: n_tokens = 132, truncated = 0 0.49.453.727 I slot print_timing: id 2 | task 94 | prompt eval time = 219.36 ms / 141 tokens ( 1.56 ms per token, 642.78 tokens per second) 0.49.453.730 I slot print_timing: id 2 | task 94 | eval time = 17.57 ms / 2 tokens ( 17.57 ms per token, 56.92 tokens per second) 0.49.453.730 I slot print_timing: id 2 | task 94 | total time = 236.93 ms / 143 tokens 0.49.453.731 I slot print_timing: id 2 | task 94 | graphs reused = 1 0.49.453.731 I slot print_timing: id 2 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.453.742 I slot release: id 2 | task 94 | stop processing: n_tokens = 142, truncated = 0 0.49.454.012 I slot print_timing: id 3 | task 95 | prompt eval time = 219.27 ms / 144 tokens ( 1.52 ms per token, 656.72 tokens per second) 0.49.454.015 I slot print_timing: id 3 | task 95 | eval time = 17.18 ms / 2 tokens ( 17.18 ms per token, 58.22 tokens per second) 0.49.454.015 I slot print_timing: id 3 | task 95 | total time = 236.45 ms / 146 tokens 0.49.454.016 I slot print_timing: id 3 | task 95 | graphs reused = 1 0.49.454.016 I slot print_timing: id 3 | task 95 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.454.026 I slot release: id 3 | task 95 | stop processing: n_tokens = 145, truncated = 0 0.49.462.679 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.220 0.49.480.739 I slot launch_slot_: id 1 | task 99 | processing task, is_child = 0 0.49.529.687 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 0.49.529.857 I slot launch_slot_: id 2 | task 100 | processing task, is_child = 0 0.49.529.902 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.200 0.49.530.016 I slot launch_slot_: id 3 | task 101 | processing task, is_child = 0 0.49.530.041 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 0.49.530.147 I slot launch_slot_: id 0 | task 102 | processing task, is_child = 0 0.49.762.346 I slot print_timing: id 0 | task 102 | prompt eval time = 213.91 ms / 121 tokens ( 1.77 ms per token, 565.65 tokens per second) 0.49.762.352 I slot print_timing: id 0 | task 102 | eval time = 18.27 ms / 2 tokens ( 18.27 ms per token, 54.74 tokens per second) 0.49.762.353 I slot print_timing: id 0 | task 102 | total time = 232.18 ms / 123 tokens 0.49.762.354 I slot print_timing: id 0 | task 102 | graphs reused = 1 0.49.762.354 I slot print_timing: id 0 | task 102 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.762.378 I slot release: id 0 | task 102 | stop processing: n_tokens = 122, truncated = 0 0.49.762.711 I slot print_timing: id 1 | task 99 | prompt eval time = 213.85 ms / 107 tokens ( 2.00 ms per token, 500.36 tokens per second) 0.49.762.714 I slot print_timing: id 1 | task 99 | eval time = 17.91 ms / 2 tokens ( 17.91 ms per token, 55.82 tokens per second) 0.49.762.715 I slot print_timing: id 1 | task 99 | total time = 231.76 ms / 109 tokens 0.49.762.716 I slot print_timing: id 1 | task 99 | graphs reused = 1 0.49.762.717 I slot print_timing: id 1 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.762.730 I slot release: id 1 | task 99 | stop processing: n_tokens = 108, truncated = 0 0.49.763.094 I slot print_timing: id 2 | task 100 | prompt eval time = 213.70 ms / 172 tokens ( 1.24 ms per token, 804.87 tokens per second) 0.49.763.097 I slot print_timing: id 2 | task 100 | eval time = 17.60 ms / 2 tokens ( 17.60 ms per token, 56.81 tokens per second) 0.49.763.097 I slot print_timing: id 2 | task 100 | total time = 231.30 ms / 174 tokens 0.49.763.098 I slot print_timing: id 2 | task 100 | graphs reused = 1 0.49.763.098 I slot print_timing: id 2 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.763.112 I slot release: id 2 | task 100 | stop processing: n_tokens = 173, truncated = 0 0.49.763.389 I slot print_timing: id 3 | task 101 | prompt eval time = 213.51 ms / 118 tokens ( 1.81 ms per token, 552.67 tokens per second) 0.49.763.392 I slot print_timing: id 3 | task 101 | eval time = 17.28 ms / 2 tokens ( 17.28 ms per token, 57.86 tokens per second) 0.49.763.393 I slot print_timing: id 3 | task 101 | total time = 230.79 ms / 120 tokens 0.49.763.393 I slot print_timing: id 3 | task 101 | graphs reused = 1 0.49.763.394 I slot print_timing: id 3 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.763.403 I slot release: id 3 | task 101 | stop processing: n_tokens = 119, truncated = 0 0.49.772.107 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.269 0.49.788.766 I slot launch_slot_: id 1 | task 106 | processing task, is_child = 0 0.49.837.262 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 0.49.837.437 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.49.837.483 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.162 0.49.837.597 I slot launch_slot_: id 2 | task 108 | processing task, is_child = 0 0.49.837.620 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.244 0.49.837.712 I slot launch_slot_: id 3 | task 109 | processing task, is_child = 0 0.50.083.330 I slot print_timing: id 0 | task 107 | prompt eval time = 227.60 ms / 177 tokens ( 1.29 ms per token, 777.68 tokens per second) 0.50.083.335 I slot print_timing: id 0 | task 107 | eval time = 18.00 ms / 2 tokens ( 18.00 ms per token, 55.55 tokens per second) 0.50.083.336 I slot print_timing: id 0 | task 107 | total time = 245.60 ms / 179 tokens 0.50.083.337 I slot print_timing: id 0 | task 107 | graphs reused = 1 0.50.083.338 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.083.364 I slot release: id 0 | task 107 | stop processing: n_tokens = 178, truncated = 0 0.50.083.694 I slot print_timing: id 1 | task 106 | prompt eval time = 227.43 ms / 136 tokens ( 1.67 ms per token, 597.98 tokens per second) 0.50.083.698 I slot print_timing: id 1 | task 106 | eval time = 17.70 ms / 2 tokens ( 17.70 ms per token, 56.51 tokens per second) 0.50.083.698 I slot print_timing: id 1 | task 106 | total time = 245.13 ms / 138 tokens 0.50.083.699 I slot print_timing: id 1 | task 106 | graphs reused = 1 0.50.083.699 I slot print_timing: id 1 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.083.713 I slot release: id 1 | task 106 | stop processing: n_tokens = 137, truncated = 0 0.50.084.072 I slot print_timing: id 2 | task 108 | prompt eval time = 227.22 ms / 240 tokens ( 0.95 ms per token, 1056.22 tokens per second) 0.50.084.075 I slot print_timing: id 2 | task 108 | eval time = 17.48 ms / 2 tokens ( 17.48 ms per token, 57.19 tokens per second) 0.50.084.075 I slot print_timing: id 2 | task 108 | total time = 244.71 ms / 242 tokens 0.50.084.076 I slot print_timing: id 2 | task 108 | graphs reused = 1 0.50.084.076 I slot print_timing: id 2 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.084.093 I slot release: id 2 | task 108 | stop processing: n_tokens = 241, truncated = 0 0.50.084.382 I slot print_timing: id 3 | task 109 | prompt eval time = 226.93 ms / 116 tokens ( 1.96 ms per token, 511.17 tokens per second) 0.50.084.385 I slot print_timing: id 3 | task 109 | eval time = 17.24 ms / 2 tokens ( 17.24 ms per token, 58.01 tokens per second) 0.50.084.386 I slot print_timing: id 3 | task 109 | total time = 244.17 ms / 118 tokens 0.50.084.386 I slot print_timing: id 3 | task 109 | graphs reused = 1 0.50.084.387 I slot print_timing: id 3 | task 109 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.084.397 I slot release: id 3 | task 109 | stop processing: n_tokens = 117, truncated = 0 0.50.092.722 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.265 0.50.109.691 I slot launch_slot_: id 3 | task 113 | processing task, is_child = 0 0.50.159.566 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.212 0.50.167.647 I slot launch_slot_: id 1 | task 114 | processing task, is_child = 0 0.50.167.701 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 0.50.167.806 I slot launch_slot_: id 0 | task 115 | processing task, is_child = 0 0.50.167.835 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.116 0.50.167.938 I slot launch_slot_: id 2 | task 116 | processing task, is_child = 0 0.50.438.756 I slot print_timing: id 0 | task 115 | prompt eval time = 252.00 ms / 160 tokens ( 1.57 ms per token, 634.93 tokens per second) 0.50.438.762 I slot print_timing: id 0 | task 115 | eval time = 18.80 ms / 2 tokens ( 18.80 ms per token, 53.19 tokens per second) 0.50.438.763 I slot print_timing: id 0 | task 115 | total time = 270.80 ms / 162 tokens 0.50.438.763 I slot print_timing: id 0 | task 115 | graphs reused = 1 0.50.438.764 I slot print_timing: id 0 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.438.791 I slot release: id 0 | task 115 | stop processing: n_tokens = 161, truncated = 0 0.50.439.116 I slot print_timing: id 1 | task 114 | prompt eval time = 251.97 ms / 155 tokens ( 1.63 ms per token, 615.14 tokens per second) 0.50.439.119 I slot print_timing: id 1 | task 114 | eval time = 18.33 ms / 2 tokens ( 18.33 ms per token, 54.55 tokens per second) 0.50.439.120 I slot print_timing: id 1 | task 114 | total time = 270.31 ms / 157 tokens 0.50.439.120 I slot print_timing: id 1 | task 114 | graphs reused = 1 0.50.439.121 I slot print_timing: id 1 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.439.135 I slot release: id 1 | task 114 | stop processing: n_tokens = 156, truncated = 0 0.50.439.463 I slot print_timing: id 2 | task 116 | prompt eval time = 252.04 ms / 226 tokens ( 1.12 ms per token, 896.68 tokens per second) 0.50.439.466 I slot print_timing: id 2 | task 116 | eval time = 17.85 ms / 2 tokens ( 17.85 ms per token, 56.02 tokens per second) 0.50.439.467 I slot print_timing: id 2 | task 116 | total time = 269.89 ms / 228 tokens 0.50.439.467 I slot print_timing: id 2 | task 116 | graphs reused = 1 0.50.439.468 I slot print_timing: id 2 | task 116 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.439.484 I slot release: id 2 | task 116 | stop processing: n_tokens = 227, truncated = 0 0.50.439.809 I slot print_timing: id 3 | task 113 | prompt eval time = 251.95 ms / 142 tokens ( 1.77 ms per token, 563.60 tokens per second) 0.50.439.812 I slot print_timing: id 3 | task 113 | eval time = 17.41 ms / 2 tokens ( 17.41 ms per token, 57.44 tokens per second) 0.50.439.812 I slot print_timing: id 3 | task 113 | total time = 269.36 ms / 144 tokens 0.50.439.813 I slot print_timing: id 3 | task 113 | graphs reused = 1 0.50.439.814 I slot print_timing: id 3 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.439.825 I slot release: id 3 | task 113 | stop processing: n_tokens = 143, truncated = 0 0.50.448.199 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.186 0.50.466.601 I slot launch_slot_: id 1 | task 120 | processing task, is_child = 0 0.50.515.853 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.174 0.50.523.897 I slot launch_slot_: id 0 | task 121 | processing task, is_child = 0 0.50.523.948 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.295 (> 0.100 thold), f_keep = 0.217 0.50.524.059 I slot launch_slot_: id 3 | task 122 | processing task, is_child = 0 0.50.524.086 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.123 0.50.524.192 I slot launch_slot_: id 2 | task 123 | processing task, is_child = 0 0.50.770.386 I slot print_timing: id 0 | task 121 | prompt eval time = 227.14 ms / 192 tokens ( 1.18 ms per token, 845.29 tokens per second) 0.50.770.392 I slot print_timing: id 0 | task 121 | eval time = 19.03 ms / 2 tokens ( 19.03 ms per token, 52.54 tokens per second) 0.50.770.393 I slot print_timing: id 0 | task 121 | total time = 246.18 ms / 194 tokens 0.50.770.394 I slot print_timing: id 0 | task 121 | graphs reused = 1 0.50.770.395 I slot print_timing: id 0 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.770.425 I slot release: id 0 | task 121 | stop processing: n_tokens = 193, truncated = 0 0.50.770.748 I slot print_timing: id 1 | task 120 | prompt eval time = 227.17 ms / 114 tokens ( 1.99 ms per token, 501.82 tokens per second) 0.50.770.751 I slot print_timing: id 1 | task 120 | eval time = 18.61 ms / 2 tokens ( 18.61 ms per token, 53.73 tokens per second) 0.50.770.752 I slot print_timing: id 1 | task 120 | total time = 245.78 ms / 116 tokens 0.50.770.752 I slot print_timing: id 1 | task 120 | graphs reused = 1 0.50.770.753 I slot print_timing: id 1 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.770.766 I slot release: id 1 | task 120 | stop processing: n_tokens = 115, truncated = 0 0.50.771.093 I slot print_timing: id 2 | task 123 | prompt eval time = 227.06 ms / 141 tokens ( 1.61 ms per token, 620.97 tokens per second) 0.50.771.097 I slot print_timing: id 2 | task 123 | eval time = 18.20 ms / 2 tokens ( 18.20 ms per token, 54.96 tokens per second) 0.50.771.098 I slot print_timing: id 2 | task 123 | total time = 245.26 ms / 143 tokens 0.50.771.098 I slot print_timing: id 2 | task 123 | graphs reused = 1 0.50.771.099 I slot print_timing: id 2 | task 123 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.771.112 I slot release: id 2 | task 123 | stop processing: n_tokens = 142, truncated = 0 0.50.771.389 I slot print_timing: id 3 | task 122 | prompt eval time = 226.93 ms / 105 tokens ( 2.16 ms per token, 462.69 tokens per second) 0.50.771.392 I slot print_timing: id 3 | task 122 | eval time = 17.80 ms / 2 tokens ( 17.80 ms per token, 56.19 tokens per second) 0.50.771.392 I slot print_timing: id 3 | task 122 | total time = 244.73 ms / 107 tokens 0.50.771.393 I slot print_timing: id 3 | task 122 | graphs reused = 1 0.50.771.393 I slot print_timing: id 3 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.771.402 I slot release: id 3 | task 122 | stop processing: n_tokens = 106, truncated = 0 0.50.778.902 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.145 0.50.797.724 I slot launch_slot_: id 0 | task 127 | processing task, is_child = 0 0.50.846.735 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.252 0.50.846.913 I slot launch_slot_: id 1 | task 128 | processing task, is_child = 0 0.50.846.959 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.197 0.50.847.075 I slot launch_slot_: id 2 | task 129 | processing task, is_child = 0 0.50.847.099 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 0.50.847.203 I slot launch_slot_: id 3 | task 130 | processing task, is_child = 0 0.51.081.955 I slot print_timing: id 0 | task 127 | prompt eval time = 215.90 ms / 172 tokens ( 1.26 ms per token, 796.66 tokens per second) 0.51.081.961 I slot print_timing: id 0 | task 127 | eval time = 18.83 ms / 2 tokens ( 18.83 ms per token, 53.10 tokens per second) 0.51.081.962 I slot print_timing: id 0 | task 127 | total time = 234.74 ms / 174 tokens 0.51.081.963 I slot print_timing: id 0 | task 127 | graphs reused = 1 0.51.081.964 I slot print_timing: id 0 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.081.992 I slot release: id 0 | task 127 | stop processing: n_tokens = 173, truncated = 0 0.51.082.351 I slot print_timing: id 1 | task 128 | prompt eval time = 215.70 ms / 122 tokens ( 1.77 ms per token, 565.61 tokens per second) 0.51.082.354 I slot print_timing: id 1 | task 128 | eval time = 18.56 ms / 2 tokens ( 18.56 ms per token, 53.87 tokens per second) 0.51.082.355 I slot print_timing: id 1 | task 128 | total time = 234.26 ms / 124 tokens 0.51.082.355 I slot print_timing: id 1 | task 128 | graphs reused = 1 0.51.082.356 I slot print_timing: id 1 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.082.370 I slot release: id 1 | task 128 | stop processing: n_tokens = 123, truncated = 0 0.51.082.738 I slot print_timing: id 2 | task 129 | prompt eval time = 215.57 ms / 135 tokens ( 1.60 ms per token, 626.26 tokens per second) 0.51.082.741 I slot print_timing: id 2 | task 129 | eval time = 18.27 ms / 2 tokens ( 18.27 ms per token, 54.74 tokens per second) 0.51.082.742 I slot print_timing: id 2 | task 129 | total time = 233.84 ms / 137 tokens 0.51.082.742 I slot print_timing: id 2 | task 129 | graphs reused = 1 0.51.082.743 I slot print_timing: id 2 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.082.757 I slot release: id 2 | task 129 | stop processing: n_tokens = 136, truncated = 0 0.51.083.080 I slot print_timing: id 3 | task 130 | prompt eval time = 215.28 ms / 108 tokens ( 1.99 ms per token, 501.67 tokens per second) 0.51.083.083 I slot print_timing: id 3 | task 130 | eval time = 18.06 ms / 2 tokens ( 18.06 ms per token, 55.38 tokens per second) 0.51.083.084 I slot print_timing: id 3 | task 130 | total time = 233.34 ms / 110 tokens 0.51.083.085 I slot print_timing: id 3 | task 130 | graphs reused = 1 0.51.083.085 I slot print_timing: id 3 | task 130 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.083.096 I slot release: id 3 | task 130 | stop processing: n_tokens = 109, truncated = 0 0.51.090.529 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 0.51.107.573 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 0.51.156.496 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.228 0.51.156.666 I slot launch_slot_: id 1 | task 135 | processing task, is_child = 0 0.51.156.710 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.206 0.51.156.818 I slot launch_slot_: id 2 | task 136 | processing task, is_child = 0 0.51.156.841 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.266 0.51.164.842 I slot launch_slot_: id 3 | task 137 | processing task, is_child = 0 0.51.409.028 I slot print_timing: id 0 | task 134 | prompt eval time = 225.11 ms / 159 tokens ( 1.42 ms per token, 706.33 tokens per second) 0.51.409.034 I slot print_timing: id 0 | task 134 | eval time = 19.06 ms / 2 tokens ( 19.06 ms per token, 52.48 tokens per second) 0.51.409.036 I slot print_timing: id 0 | task 134 | total time = 244.16 ms / 161 tokens 0.51.409.036 I slot print_timing: id 0 | task 134 | graphs reused = 1 0.51.409.037 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.409.067 I slot release: id 0 | task 134 | stop processing: n_tokens = 160, truncated = 0 0.51.409.417 I slot print_timing: id 1 | task 135 | prompt eval time = 225.07 ms / 135 tokens ( 1.67 ms per token, 599.80 tokens per second) 0.51.409.420 I slot print_timing: id 1 | task 135 | eval time = 18.63 ms / 2 tokens ( 18.63 ms per token, 53.67 tokens per second) 0.51.409.421 I slot print_timing: id 1 | task 135 | total time = 243.71 ms / 137 tokens 0.51.409.421 I slot print_timing: id 1 | task 135 | graphs reused = 1 0.51.409.422 I slot print_timing: id 1 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.409.437 I slot release: id 1 | task 135 | stop processing: n_tokens = 136, truncated = 0 0.51.409.783 I slot print_timing: id 2 | task 136 | prompt eval time = 224.96 ms / 134 tokens ( 1.68 ms per token, 595.67 tokens per second) 0.51.409.786 I slot print_timing: id 2 | task 136 | eval time = 18.29 ms / 2 tokens ( 18.29 ms per token, 54.67 tokens per second) 0.51.409.787 I slot print_timing: id 2 | task 136 | total time = 243.25 ms / 136 tokens 0.51.409.787 I slot print_timing: id 2 | task 136 | graphs reused = 1 0.51.409.788 I slot print_timing: id 2 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.409.801 I slot release: id 2 | task 136 | stop processing: n_tokens = 135, truncated = 0 0.51.410.151 I slot print_timing: id 3 | task 137 | prompt eval time = 224.82 ms / 120 tokens ( 1.87 ms per token, 533.75 tokens per second) 0.51.410.154 I slot print_timing: id 3 | task 137 | eval time = 17.97 ms / 2 tokens ( 17.97 ms per token, 55.66 tokens per second) 0.51.410.155 I slot print_timing: id 3 | task 137 | total time = 242.79 ms / 122 tokens 0.51.410.155 I slot print_timing: id 3 | task 137 | graphs reused = 1 0.51.410.156 I slot print_timing: id 3 | task 137 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.410.165 I slot release: id 3 | task 137 | stop processing: n_tokens = 121, truncated = 0 0.51.417.413 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 0.51.437.256 I slot launch_slot_: id 0 | task 141 | processing task, is_child = 0 0.51.486.751 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.206 0.51.486.934 I slot launch_slot_: id 1 | task 142 | processing task, is_child = 0 0.51.486.981 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.207 0.51.487.098 I slot launch_slot_: id 2 | task 143 | processing task, is_child = 0 0.51.487.123 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.231 0.51.487.229 I slot launch_slot_: id 3 | task 144 | processing task, is_child = 0 0.51.746.794 I slot print_timing: id 0 | task 141 | prompt eval time = 240.78 ms / 130 tokens ( 1.85 ms per token, 539.91 tokens per second) 0.51.746.799 I slot print_timing: id 0 | task 141 | eval time = 18.77 ms / 2 tokens ( 18.77 ms per token, 53.29 tokens per second) 0.51.746.800 I slot print_timing: id 0 | task 141 | total time = 259.55 ms / 132 tokens 0.51.746.801 I slot print_timing: id 0 | task 141 | graphs reused = 1 0.51.746.801 I slot print_timing: id 0 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.746.826 I slot release: id 0 | task 141 | stop processing: n_tokens = 131, truncated = 0 0.51.747.166 I slot print_timing: id 1 | task 142 | prompt eval time = 240.76 ms / 180 tokens ( 1.34 ms per token, 747.64 tokens per second) 0.51.747.169 I slot print_timing: id 1 | task 142 | eval time = 18.34 ms / 2 tokens ( 18.34 ms per token, 54.52 tokens per second) 0.51.747.170 I slot print_timing: id 1 | task 142 | total time = 259.10 ms / 182 tokens 0.51.747.171 I slot print_timing: id 1 | task 142 | graphs reused = 1 0.51.747.172 I slot print_timing: id 1 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.747.191 I slot release: id 1 | task 142 | stop processing: n_tokens = 181, truncated = 0 0.51.747.555 I slot print_timing: id 2 | task 143 | prompt eval time = 240.73 ms / 172 tokens ( 1.40 ms per token, 714.51 tokens per second) 0.51.747.559 I slot print_timing: id 2 | task 143 | eval time = 17.93 ms / 2 tokens ( 17.93 ms per token, 55.78 tokens per second) 0.51.747.559 I slot print_timing: id 2 | task 143 | total time = 258.65 ms / 174 tokens 0.51.747.560 I slot print_timing: id 2 | task 143 | graphs reused = 1 0.51.747.560 I slot print_timing: id 2 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.747.576 I slot release: id 2 | task 143 | stop processing: n_tokens = 173, truncated = 0 0.51.747.866 I slot print_timing: id 3 | task 144 | prompt eval time = 240.44 ms / 175 tokens ( 1.37 ms per token, 727.83 tokens per second) 0.51.747.869 I slot print_timing: id 3 | task 144 | eval time = 17.68 ms / 2 tokens ( 17.68 ms per token, 56.56 tokens per second) 0.51.747.870 I slot print_timing: id 3 | task 144 | total time = 258.12 ms / 177 tokens 0.51.747.870 I slot print_timing: id 3 | task 144 | graphs reused = 1 0.51.747.871 I slot print_timing: id 3 | task 144 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.747.882 I slot release: id 3 | task 144 | stop processing: n_tokens = 176, truncated = 0 0.51.757.011 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.214 0.51.782.405 I slot launch_slot_: id 0 | task 149 | processing task, is_child = 0 0.51.836.059 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.155 0.51.844.178 I slot launch_slot_: id 1 | task 148 | processing task, is_child = 0 0.51.844.235 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.162 0.51.844.350 I slot launch_slot_: id 2 | task 150 | processing task, is_child = 0 0.51.844.378 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 0.51.844.476 I slot launch_slot_: id 3 | task 151 | processing task, is_child = 0 0.52.043.362 I slot print_timing: id 0 | task 149 | prompt eval time = 180.71 ms / 115 tokens ( 1.57 ms per token, 636.39 tokens per second) 0.52.043.368 I slot print_timing: id 0 | task 149 | eval time = 18.16 ms / 2 tokens ( 18.16 ms per token, 55.05 tokens per second) 0.52.043.369 I slot print_timing: id 0 | task 149 | total time = 198.87 ms / 117 tokens 0.52.043.370 I slot print_timing: id 0 | task 149 | graphs reused = 1 0.52.043.371 I slot print_timing: id 0 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.043.394 I slot release: id 0 | task 149 | stop processing: n_tokens = 116, truncated = 0 0.52.043.711 I slot print_timing: id 1 | task 148 | prompt eval time = 180.61 ms / 123 tokens ( 1.47 ms per token, 681.03 tokens per second) 0.52.043.714 I slot print_timing: id 1 | task 148 | eval time = 17.86 ms / 2 tokens ( 17.86 ms per token, 55.98 tokens per second) 0.52.043.715 I slot print_timing: id 1 | task 148 | total time = 198.47 ms / 125 tokens 0.52.043.716 I slot print_timing: id 1 | task 148 | graphs reused = 1 0.52.043.716 I slot print_timing: id 1 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.043.729 I slot release: id 1 | task 148 | stop processing: n_tokens = 124, truncated = 0 0.52.044.033 I slot print_timing: id 2 | task 150 | prompt eval time = 180.40 ms / 123 tokens ( 1.47 ms per token, 681.81 tokens per second) 0.52.044.036 I slot print_timing: id 2 | task 150 | eval time = 17.61 ms / 2 tokens ( 17.61 ms per token, 56.80 tokens per second) 0.52.044.037 I slot print_timing: id 2 | task 150 | total time = 198.01 ms / 125 tokens 0.52.044.037 I slot print_timing: id 2 | task 150 | graphs reused = 1 0.52.044.038 I slot print_timing: id 2 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.044.048 I slot release: id 2 | task 150 | stop processing: n_tokens = 124, truncated = 0 0.52.044.345 I slot print_timing: id 3 | task 151 | prompt eval time = 180.11 ms / 115 tokens ( 1.57 ms per token, 638.51 tokens per second) 0.52.044.348 I slot print_timing: id 3 | task 151 | eval time = 17.36 ms / 2 tokens ( 17.36 ms per token, 57.59 tokens per second) 0.52.044.349 I slot print_timing: id 3 | task 151 | total time = 197.47 ms / 117 tokens 0.52.044.350 I slot print_timing: id 3 | task 151 | graphs reused = 1 0.52.044.350 I slot print_timing: id 3 | task 151 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.044.359 I slot release: id 3 | task 151 | stop processing: n_tokens = 116, truncated = 0 0.52.052.072 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.276 0.52.068.906 I slot launch_slot_: id 0 | task 155 | processing task, is_child = 0 0.52.117.336 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 0.52.117.487 I slot launch_slot_: id 1 | task 156 | processing task, is_child = 0 0.52.117.530 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.226 0.52.117.642 I slot launch_slot_: id 2 | task 157 | processing task, is_child = 0 0.52.117.666 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.241 0.52.126.095 I slot launch_slot_: id 3 | task 158 | processing task, is_child = 0 0.52.363.822 I slot print_timing: id 0 | task 155 | prompt eval time = 218.64 ms / 127 tokens ( 1.72 ms per token, 580.86 tokens per second) 0.52.363.829 I slot print_timing: id 0 | task 155 | eval time = 19.07 ms / 2 tokens ( 19.07 ms per token, 52.45 tokens per second) 0.52.363.830 I slot print_timing: id 0 | task 155 | total time = 237.71 ms / 129 tokens 0.52.363.831 I slot print_timing: id 0 | task 155 | graphs reused = 1 0.52.363.832 I slot print_timing: id 0 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.363.857 I slot release: id 0 | task 155 | stop processing: n_tokens = 128, truncated = 0 0.52.364.200 I slot print_timing: id 1 | task 156 | prompt eval time = 218.58 ms / 130 tokens ( 1.68 ms per token, 594.76 tokens per second) 0.52.364.204 I slot print_timing: id 1 | task 156 | eval time = 18.68 ms / 2 tokens ( 18.68 ms per token, 53.53 tokens per second) 0.52.364.205 I slot print_timing: id 1 | task 156 | total time = 237.26 ms / 132 tokens 0.52.364.205 I slot print_timing: id 1 | task 156 | graphs reused = 1 0.52.364.206 I slot print_timing: id 1 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.364.221 I slot release: id 1 | task 156 | stop processing: n_tokens = 131, truncated = 0 0.52.364.628 I slot print_timing: id 2 | task 157 | prompt eval time = 218.50 ms / 141 tokens ( 1.55 ms per token, 645.30 tokens per second) 0.52.364.633 I slot print_timing: id 2 | task 157 | eval time = 18.34 ms / 2 tokens ( 18.34 ms per token, 54.51 tokens per second) 0.52.364.634 I slot print_timing: id 2 | task 157 | total time = 236.85 ms / 143 tokens 0.52.364.634 I slot print_timing: id 2 | task 157 | graphs reused = 1 0.52.364.635 I slot print_timing: id 2 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.364.649 I slot release: id 2 | task 157 | stop processing: n_tokens = 142, truncated = 0 0.52.365.006 I slot print_timing: id 3 | task 158 | prompt eval time = 218.41 ms / 128 tokens ( 1.71 ms per token, 586.05 tokens per second) 0.52.365.009 I slot print_timing: id 3 | task 158 | eval time = 18.02 ms / 2 tokens ( 18.02 ms per token, 55.48 tokens per second) 0.52.365.010 I slot print_timing: id 3 | task 158 | total time = 236.44 ms / 130 tokens 0.52.365.010 I slot print_timing: id 3 | task 158 | graphs reused = 1 0.52.365.011 I slot print_timing: id 3 | task 158 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.365.020 I slot release: id 3 | task 158 | stop processing: n_tokens = 129, truncated = 0 0.52.372.147 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.219 0.52.390.642 I slot launch_slot_: id 0 | task 162 | processing task, is_child = 0 0.52.390.676 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 0.52.413.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.129 MiB) 0.52.436.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 0.52.459.634 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.267 (> 0.100 thold), f_keep = 0.214 0.52.468.049 I slot launch_slot_: id 1 | task 163 | processing task, is_child = 0 0.52.468.108 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.197 0.52.468.228 I slot launch_slot_: id 2 | task 164 | processing task, is_child = 0 0.52.468.255 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.217 0.52.468.364 I slot launch_slot_: id 3 | task 165 | processing task, is_child = 0 0.52.706.781 I slot print_timing: id 0 | task 162 | prompt eval time = 219.66 ms / 123 tokens ( 1.79 ms per token, 559.96 tokens per second) 0.52.706.787 I slot print_timing: id 0 | task 162 | eval time = 18.74 ms / 2 tokens ( 18.74 ms per token, 53.36 tokens per second) 0.52.706.788 I slot print_timing: id 0 | task 162 | total time = 238.40 ms / 125 tokens 0.52.706.788 I slot print_timing: id 0 | task 162 | graphs reused = 1 0.52.706.790 I slot print_timing: id 0 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.706.815 I slot release: id 0 | task 162 | stop processing: n_tokens = 124, truncated = 0 0.52.707.147 I slot print_timing: id 1 | task 163 | prompt eval time = 219.64 ms / 105 tokens ( 2.09 ms per token, 478.05 tokens per second) 0.52.707.150 I slot print_timing: id 1 | task 163 | eval time = 18.30 ms / 2 tokens ( 18.30 ms per token, 54.63 tokens per second) 0.52.707.151 I slot print_timing: id 1 | task 163 | total time = 237.95 ms / 107 tokens 0.52.707.152 I slot print_timing: id 1 | task 163 | graphs reused = 1 0.52.707.152 I slot print_timing: id 1 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.707.166 I slot release: id 1 | task 163 | stop processing: n_tokens = 106, truncated = 0 0.52.707.482 I slot print_timing: id 2 | task 164 | prompt eval time = 219.61 ms / 129 tokens ( 1.70 ms per token, 587.40 tokens per second) 0.52.707.485 I slot print_timing: id 2 | task 164 | eval time = 17.90 ms / 2 tokens ( 17.90 ms per token, 55.86 tokens per second) 0.52.707.485 I slot print_timing: id 2 | task 164 | total time = 237.51 ms / 131 tokens 0.52.707.486 I slot print_timing: id 2 | task 164 | graphs reused = 1 0.52.707.487 I slot print_timing: id 2 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.707.498 I slot release: id 2 | task 164 | stop processing: n_tokens = 130, truncated = 0 0.52.707.854 I slot print_timing: id 3 | task 165 | prompt eval time = 219.50 ms / 161 tokens ( 1.36 ms per token, 733.47 tokens per second) 0.52.707.856 I slot print_timing: id 3 | task 165 | eval time = 17.52 ms / 2 tokens ( 17.52 ms per token, 57.06 tokens per second) 0.52.707.857 I slot print_timing: id 3 | task 165 | total time = 237.03 ms / 163 tokens 0.52.707.857 I slot print_timing: id 3 | task 165 | graphs reused = 1 0.52.707.858 I slot print_timing: id 3 | task 165 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.707.871 I slot release: id 3 | task 165 | stop processing: n_tokens = 162, truncated = 0 0.52.716.929 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.226 0.52.737.813 I slot launch_slot_: id 0 | task 169 | processing task, is_child = 0 0.52.737.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.286 MiB) 0.52.760.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.787 MiB) 0.52.804.746 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.264 0.52.804.919 I slot launch_slot_: id 1 | task 170 | processing task, is_child = 0 0.52.804.967 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.215 0.52.813.022 I slot launch_slot_: id 2 | task 171 | processing task, is_child = 0 0.52.813.053 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.173 0.52.813.167 I slot launch_slot_: id 3 | task 172 | processing task, is_child = 0 0.53.050.320 I slot print_timing: id 0 | task 169 | prompt eval time = 218.92 ms / 164 tokens ( 1.33 ms per token, 749.15 tokens per second) 0.53.050.326 I slot print_timing: id 0 | task 169 | eval time = 18.22 ms / 2 tokens ( 18.22 ms per token, 54.89 tokens per second) 0.53.050.327 I slot print_timing: id 0 | task 169 | total time = 237.13 ms / 166 tokens 0.53.050.328 I slot print_timing: id 0 | task 169 | graphs reused = 1 0.53.050.329 I slot print_timing: id 0 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.050.355 I slot release: id 0 | task 169 | stop processing: n_tokens = 165, truncated = 0 0.53.050.714 I slot print_timing: id 1 | task 170 | prompt eval time = 218.77 ms / 141 tokens ( 1.55 ms per token, 644.51 tokens per second) 0.53.050.717 I slot print_timing: id 1 | task 170 | eval time = 17.93 ms / 2 tokens ( 17.93 ms per token, 55.76 tokens per second) 0.53.050.718 I slot print_timing: id 1 | task 170 | total time = 236.71 ms / 143 tokens 0.53.050.719 I slot print_timing: id 1 | task 170 | graphs reused = 1 0.53.050.719 I slot print_timing: id 1 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.050.733 I slot release: id 1 | task 170 | stop processing: n_tokens = 142, truncated = 0 0.53.051.081 I slot print_timing: id 2 | task 171 | prompt eval time = 218.59 ms / 110 tokens ( 1.99 ms per token, 503.24 tokens per second) 0.53.051.084 I slot print_timing: id 2 | task 171 | eval time = 17.67 ms / 2 tokens ( 17.67 ms per token, 56.59 tokens per second) 0.53.051.086 I slot print_timing: id 2 | task 171 | total time = 236.26 ms / 112 tokens 0.53.051.086 I slot print_timing: id 2 | task 171 | graphs reused = 1 0.53.051.087 I slot print_timing: id 2 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.051.098 I slot release: id 2 | task 171 | stop processing: n_tokens = 111, truncated = 0 0.53.051.381 I slot print_timing: id 3 | task 172 | prompt eval time = 218.37 ms / 154 tokens ( 1.42 ms per token, 705.22 tokens per second) 0.53.051.384 I slot print_timing: id 3 | task 172 | eval time = 17.42 ms / 2 tokens ( 17.42 ms per token, 57.41 tokens per second) 0.53.051.385 I slot print_timing: id 3 | task 172 | total time = 235.79 ms / 156 tokens 0.53.051.386 I slot print_timing: id 3 | task 172 | graphs reused = 1 0.53.051.386 I slot print_timing: id 3 | task 172 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.051.399 I slot release: id 3 | task 172 | stop processing: n_tokens = 155, truncated = 0 0.53.059.053 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.170 0.53.059.110 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.536 MiB) 0.53.080.835 I slot launch_slot_: id 0 | task 176 | processing task, is_child = 0 0.53.080.870 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.224 MiB) 0.53.122.282 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.442 MiB) 0.53.123.986 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.223 MiB) 0.53.147.106 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.197 0.53.147.268 I slot launch_slot_: id 1 | task 177 | processing task, is_child = 0 0.53.147.314 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.261 0.53.147.427 I slot launch_slot_: id 2 | task 178 | processing task, is_child = 0 0.53.147.452 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.181 0.53.147.556 I slot launch_slot_: id 3 | task 179 | processing task, is_child = 0 0.53.362.874 I slot print_timing: id 0 | task 176 | prompt eval time = 196.97 ms / 110 tokens ( 1.79 ms per token, 558.47 tokens per second) 0.53.362.880 I slot print_timing: id 0 | task 176 | eval time = 18.34 ms / 2 tokens ( 18.34 ms per token, 54.53 tokens per second) 0.53.362.881 I slot print_timing: id 0 | task 176 | total time = 215.30 ms / 112 tokens 0.53.362.881 I slot print_timing: id 0 | task 176 | graphs reused = 1 0.53.362.883 I slot print_timing: id 0 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.362.905 I slot release: id 0 | task 176 | stop processing: n_tokens = 111, truncated = 0 0.53.363.158 I slot print_timing: id 1 | task 177 | prompt eval time = 196.82 ms / 137 tokens ( 1.44 ms per token, 696.07 tokens per second) 0.53.363.161 I slot print_timing: id 1 | task 177 | eval time = 17.92 ms / 2 tokens ( 17.92 ms per token, 55.81 tokens per second) 0.53.363.161 I slot print_timing: id 1 | task 177 | total time = 214.74 ms / 139 tokens 0.53.363.162 I slot print_timing: id 1 | task 177 | graphs reused = 1 0.53.363.162 I slot print_timing: id 1 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.363.175 I slot release: id 1 | task 177 | stop processing: n_tokens = 138, truncated = 0 0.53.363.422 I slot print_timing: id 2 | task 178 | prompt eval time = 196.68 ms / 110 tokens ( 1.79 ms per token, 559.28 tokens per second) 0.53.363.425 I slot print_timing: id 2 | task 178 | eval time = 17.48 ms / 2 tokens ( 17.48 ms per token, 57.20 tokens per second) 0.53.363.425 I slot print_timing: id 2 | task 178 | total time = 214.16 ms / 112 tokens 0.53.363.426 I slot print_timing: id 2 | task 178 | graphs reused = 1 0.53.363.426 I slot print_timing: id 2 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.363.436 I slot release: id 2 | task 178 | stop processing: n_tokens = 111, truncated = 0 0.53.363.687 I slot print_timing: id 3 | task 179 | prompt eval time = 196.57 ms / 148 tokens ( 1.33 ms per token, 752.92 tokens per second) 0.53.363.690 I slot print_timing: id 3 | task 179 | eval time = 17.05 ms / 2 tokens ( 17.05 ms per token, 58.66 tokens per second) 0.53.363.691 I slot print_timing: id 3 | task 179 | total time = 213.61 ms / 150 tokens 0.53.363.691 I slot print_timing: id 3 | task 179 | graphs reused = 1 0.53.363.692 I slot print_timing: id 3 | task 179 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.363.703 I slot release: id 3 | task 179 | stop processing: n_tokens = 149, truncated = 0 0.53.372.866 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.252 0.53.394.580 I slot launch_slot_: id 0 | task 185 | processing task, is_child = 0 0.53.394.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.192 MiB) 0.53.396.302 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.193 MiB) 0.53.441.331 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.786 MiB) 0.53.464.574 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.203 0.53.464.745 I slot launch_slot_: id 1 | task 183 | processing task, is_child = 0 0.53.464.790 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.252 0.53.464.901 I slot launch_slot_: id 2 | task 184 | processing task, is_child = 0 0.53.464.927 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.188 0.53.473.024 I slot launch_slot_: id 3 | task 186 | processing task, is_child = 0 0.53.704.113 I slot print_timing: id 0 | task 185 | prompt eval time = 212.70 ms / 130 tokens ( 1.64 ms per token, 611.19 tokens per second) 0.53.704.119 I slot print_timing: id 0 | task 185 | eval time = 18.37 ms / 2 tokens ( 18.37 ms per token, 54.43 tokens per second) 0.53.704.120 I slot print_timing: id 0 | task 185 | total time = 231.07 ms / 132 tokens 0.53.704.120 I slot print_timing: id 0 | task 185 | graphs reused = 1 0.53.704.121 I slot print_timing: id 0 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.704.146 I slot release: id 0 | task 185 | stop processing: n_tokens = 131, truncated = 0 0.53.704.437 I slot print_timing: id 1 | task 183 | prompt eval time = 212.63 ms / 123 tokens ( 1.73 ms per token, 578.48 tokens per second) 0.53.704.440 I slot print_timing: id 1 | task 183 | eval time = 17.93 ms / 2 tokens ( 17.93 ms per token, 55.78 tokens per second) 0.53.704.441 I slot print_timing: id 1 | task 183 | total time = 230.56 ms / 125 tokens 0.53.704.442 I slot print_timing: id 1 | task 183 | graphs reused = 1 0.53.704.442 I slot print_timing: id 1 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.704.455 I slot release: id 1 | task 183 | stop processing: n_tokens = 124, truncated = 0 0.53.704.761 I slot print_timing: id 2 | task 184 | prompt eval time = 212.54 ms / 152 tokens ( 1.40 ms per token, 715.16 tokens per second) 0.53.704.764 I slot print_timing: id 2 | task 184 | eval time = 17.49 ms / 2 tokens ( 17.49 ms per token, 57.18 tokens per second) 0.53.704.765 I slot print_timing: id 2 | task 184 | total time = 230.03 ms / 154 tokens 0.53.704.765 I slot print_timing: id 2 | task 184 | graphs reused = 1 0.53.704.766 I slot print_timing: id 2 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.704.777 I slot release: id 2 | task 184 | stop processing: n_tokens = 153, truncated = 0 0.53.705.032 I slot print_timing: id 3 | task 186 | prompt eval time = 212.45 ms / 112 tokens ( 1.90 ms per token, 527.19 tokens per second) 0.53.705.035 I slot print_timing: id 3 | task 186 | eval time = 17.06 ms / 2 tokens ( 17.06 ms per token, 58.63 tokens per second) 0.53.705.035 I slot print_timing: id 3 | task 186 | total time = 229.50 ms / 114 tokens 0.53.705.036 I slot print_timing: id 3 | task 186 | graphs reused = 1 0.53.705.036 I slot print_timing: id 3 | task 186 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.705.046 I slot release: id 3 | task 186 | stop processing: n_tokens = 113, truncated = 0 0.53.713.700 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.221 0.53.735.601 I slot launch_slot_: id 0 | task 191 | processing task, is_child = 0 0.53.735.635 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.254 MiB) 0.53.756.214 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.005 MiB) 0.53.776.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.629 MiB) 0.53.798.456 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 0.53.798.598 I slot launch_slot_: id 3 | task 190 | processing task, is_child = 0 0.53.798.645 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.226 0.53.798.752 I slot launch_slot_: id 1 | task 192 | processing task, is_child = 0 0.53.798.778 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.183 0.53.798.880 I slot launch_slot_: id 2 | task 193 | processing task, is_child = 0 0.54.036.429 I slot print_timing: id 0 | task 191 | prompt eval time = 219.47 ms / 128 tokens ( 1.71 ms per token, 583.22 tokens per second) 0.54.036.434 I slot print_timing: id 0 | task 191 | eval time = 18.06 ms / 2 tokens ( 18.06 ms per token, 55.36 tokens per second) 0.54.036.435 I slot print_timing: id 0 | task 191 | total time = 237.53 ms / 130 tokens 0.54.036.437 I slot print_timing: id 0 | task 191 | graphs reused = 1 0.54.036.438 I slot print_timing: id 0 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.036.461 I slot release: id 0 | task 191 | stop processing: n_tokens = 129, truncated = 0 0.54.036.829 I slot print_timing: id 1 | task 192 | prompt eval time = 219.29 ms / 157 tokens ( 1.40 ms per token, 715.95 tokens per second) 0.54.036.832 I slot print_timing: id 1 | task 192 | eval time = 17.78 ms / 2 tokens ( 17.78 ms per token, 56.24 tokens per second) 0.54.036.833 I slot print_timing: id 1 | task 192 | total time = 237.07 ms / 159 tokens 0.54.036.833 I slot print_timing: id 1 | task 192 | graphs reused = 1 0.54.036.834 I slot print_timing: id 1 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.036.849 I slot release: id 1 | task 192 | stop processing: n_tokens = 158, truncated = 0 0.54.037.185 I slot print_timing: id 2 | task 193 | prompt eval time = 219.02 ms / 166 tokens ( 1.32 ms per token, 757.94 tokens per second) 0.54.037.189 I slot print_timing: id 2 | task 193 | eval time = 17.55 ms / 2 tokens ( 17.55 ms per token, 56.97 tokens per second) 0.54.037.189 I slot print_timing: id 2 | task 193 | total time = 236.57 ms / 168 tokens 0.54.037.190 I slot print_timing: id 2 | task 193 | graphs reused = 1 0.54.037.190 I slot print_timing: id 2 | task 193 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.037.205 I slot release: id 2 | task 193 | stop processing: n_tokens = 167, truncated = 0 0.54.037.463 I slot print_timing: id 3 | task 190 | prompt eval time = 218.75 ms / 114 tokens ( 1.92 ms per token, 521.15 tokens per second) 0.54.037.466 I slot print_timing: id 3 | task 190 | eval time = 17.26 ms / 2 tokens ( 17.26 ms per token, 57.95 tokens per second) 0.54.037.467 I slot print_timing: id 3 | task 190 | total time = 236.01 ms / 116 tokens 0.54.037.468 I slot print_timing: id 3 | task 190 | graphs reused = 1 0.54.037.468 I slot print_timing: id 3 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.037.478 I slot release: id 3 | task 190 | stop processing: n_tokens = 115, truncated = 0 0.54.044.770 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.217 0.54.044.818 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.099 MiB) 0.54.066.740 I slot launch_slot_: id 0 | task 197 | processing task, is_child = 0 0.54.066.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 0.54.085.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 0.54.105.082 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.285 MiB) 0.54.123.536 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.177 0.54.131.632 I slot launch_slot_: id 1 | task 198 | processing task, is_child = 0 0.54.131.681 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.168 0.54.131.792 I slot launch_slot_: id 2 | task 199 | processing task, is_child = 0 0.54.131.817 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.243 0.54.131.919 I slot launch_slot_: id 3 | task 200 | processing task, is_child = 0 0.54.376.484 I slot print_timing: id 0 | task 197 | prompt eval time = 226.10 ms / 108 tokens ( 2.09 ms per token, 477.66 tokens per second) 0.54.376.489 I slot print_timing: id 0 | task 197 | eval time = 18.45 ms / 2 tokens ( 18.45 ms per token, 54.21 tokens per second) 0.54.376.491 I slot print_timing: id 0 | task 197 | total time = 244.55 ms / 110 tokens 0.54.376.492 I slot print_timing: id 0 | task 197 | graphs reused = 1 0.54.376.493 I slot print_timing: id 0 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.376.516 I slot release: id 0 | task 197 | stop processing: n_tokens = 109, truncated = 0 0.54.376.833 I slot print_timing: id 1 | task 198 | prompt eval time = 226.19 ms / 141 tokens ( 1.60 ms per token, 623.36 tokens per second) 0.54.376.836 I slot print_timing: id 1 | task 198 | eval time = 17.99 ms / 2 tokens ( 17.99 ms per token, 55.59 tokens per second) 0.54.376.837 I slot print_timing: id 1 | task 198 | total time = 244.18 ms / 143 tokens 0.54.376.837 I slot print_timing: id 1 | task 198 | graphs reused = 1 0.54.376.838 I slot print_timing: id 1 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.376.852 I slot release: id 1 | task 198 | stop processing: n_tokens = 142, truncated = 0 0.54.377.167 I slot print_timing: id 2 | task 199 | prompt eval time = 226.16 ms / 179 tokens ( 1.26 ms per token, 791.47 tokens per second) 0.54.377.170 I slot print_timing: id 2 | task 199 | eval time = 17.59 ms / 2 tokens ( 17.59 ms per token, 56.86 tokens per second) 0.54.377.171 I slot print_timing: id 2 | task 199 | total time = 243.75 ms / 181 tokens 0.54.377.171 I slot print_timing: id 2 | task 199 | graphs reused = 1 0.54.377.173 I slot print_timing: id 2 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.377.188 I slot release: id 2 | task 199 | stop processing: n_tokens = 180, truncated = 0 0.54.377.485 I slot print_timing: id 3 | task 200 | prompt eval time = 226.03 ms / 153 tokens ( 1.48 ms per token, 676.91 tokens per second) 0.54.377.488 I slot print_timing: id 3 | task 200 | eval time = 17.20 ms / 2 tokens ( 17.20 ms per token, 58.14 tokens per second) 0.54.377.488 I slot print_timing: id 3 | task 200 | total time = 243.23 ms / 155 tokens 0.54.377.489 I slot print_timing: id 3 | task 200 | graphs reused = 1 0.54.377.490 I slot print_timing: id 3 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.377.500 I slot release: id 3 | task 200 | stop processing: n_tokens = 154, truncated = 0 0.54.385.026 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 0.54.412.424 I slot launch_slot_: id 0 | task 204 | processing task, is_child = 0 0.54.412.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.066 MiB) 0.54.435.184 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.973 MiB) 0.54.456.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 0.54.475.043 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.197 0.54.475.206 I slot launch_slot_: id 1 | task 205 | processing task, is_child = 0 0.54.475.255 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.156 0.54.475.367 I slot launch_slot_: id 2 | task 206 | processing task, is_child = 0 0.54.475.393 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.182 0.54.475.499 I slot launch_slot_: id 3 | task 207 | processing task, is_child = 0 0.54.707.610 I slot print_timing: id 0 | task 204 | prompt eval time = 213.66 ms / 116 tokens ( 1.84 ms per token, 542.91 tokens per second) 0.54.707.616 I slot print_timing: id 0 | task 204 | eval time = 18.43 ms / 2 tokens ( 18.43 ms per token, 54.26 tokens per second) 0.54.707.617 I slot print_timing: id 0 | task 204 | total time = 232.09 ms / 118 tokens 0.54.707.618 I slot print_timing: id 0 | task 204 | graphs reused = 1 0.54.707.619 I slot print_timing: id 0 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.707.641 I slot release: id 0 | task 204 | stop processing: n_tokens = 117, truncated = 0 0.54.707.962 I slot print_timing: id 1 | task 205 | prompt eval time = 213.54 ms / 134 tokens ( 1.59 ms per token, 627.51 tokens per second) 0.54.707.965 I slot print_timing: id 1 | task 205 | eval time = 18.12 ms / 2 tokens ( 18.12 ms per token, 55.19 tokens per second) 0.54.707.965 I slot print_timing: id 1 | task 205 | total time = 231.66 ms / 136 tokens 0.54.707.966 I slot print_timing: id 1 | task 205 | graphs reused = 1 0.54.707.967 I slot print_timing: id 1 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.707.981 I slot release: id 1 | task 205 | stop processing: n_tokens = 135, truncated = 0 0.54.708.264 I slot print_timing: id 2 | task 206 | prompt eval time = 213.25 ms / 135 tokens ( 1.58 ms per token, 633.06 tokens per second) 0.54.708.268 I slot print_timing: id 2 | task 206 | eval time = 17.85 ms / 2 tokens ( 17.85 ms per token, 56.01 tokens per second) 0.54.708.269 I slot print_timing: id 2 | task 206 | total time = 231.10 ms / 137 tokens 0.54.708.270 I slot print_timing: id 2 | task 206 | graphs reused = 1 0.54.708.271 I slot print_timing: id 2 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.708.288 I slot release: id 2 | task 206 | stop processing: n_tokens = 136, truncated = 0 0.54.708.600 I slot print_timing: id 3 | task 207 | prompt eval time = 212.95 ms / 158 tokens ( 1.35 ms per token, 741.97 tokens per second) 0.54.708.603 I slot print_timing: id 3 | task 207 | eval time = 17.64 ms / 2 tokens ( 17.64 ms per token, 56.69 tokens per second) 0.54.708.604 I slot print_timing: id 3 | task 207 | total time = 230.59 ms / 160 tokens 0.54.708.604 I slot print_timing: id 3 | task 207 | graphs reused = 1 0.54.708.605 I slot print_timing: id 3 | task 207 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.708.616 I slot release: id 3 | task 207 | stop processing: n_tokens = 159, truncated = 0 0.54.717.312 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.248 0.54.717.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 0.54.747.017 I slot launch_slot_: id 0 | task 211 | processing task, is_child = 0 0.54.768.122 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.005 MiB) 0.54.787.326 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.786 MiB) 0.54.805.603 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.207 0.54.805.767 I slot launch_slot_: id 1 | task 212 | processing task, is_child = 0 0.54.805.813 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.206 0.54.805.916 I slot launch_slot_: id 2 | task 213 | processing task, is_child = 0 0.54.805.942 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.176 0.54.814.197 I slot launch_slot_: id 3 | task 214 | processing task, is_child = 0 0.55.079.604 I slot print_timing: id 0 | task 211 | prompt eval time = 246.87 ms / 122 tokens ( 2.02 ms per token, 494.19 tokens per second) 0.55.079.609 I slot print_timing: id 0 | task 211 | eval time = 18.52 ms / 2 tokens ( 18.52 ms per token, 54.00 tokens per second) 0.55.079.610 I slot print_timing: id 0 | task 211 | total time = 265.39 ms / 124 tokens 0.55.079.611 I slot print_timing: id 0 | task 211 | graphs reused = 1 0.55.079.611 I slot print_timing: id 0 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.079.635 I slot release: id 0 | task 211 | stop processing: n_tokens = 123, truncated = 0 0.55.079.956 I slot print_timing: id 1 | task 212 | prompt eval time = 246.80 ms / 149 tokens ( 1.66 ms per token, 603.73 tokens per second) 0.55.079.959 I slot print_timing: id 1 | task 212 | eval time = 18.20 ms / 2 tokens ( 18.20 ms per token, 54.94 tokens per second) 0.55.079.960 I slot print_timing: id 1 | task 212 | total time = 265.00 ms / 151 tokens 0.55.079.961 I slot print_timing: id 1 | task 212 | graphs reused = 1 0.55.079.961 I slot print_timing: id 1 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.079.976 I slot release: id 1 | task 212 | stop processing: n_tokens = 150, truncated = 0 0.55.080.282 I slot print_timing: id 2 | task 213 | prompt eval time = 246.48 ms / 157 tokens ( 1.57 ms per token, 636.98 tokens per second) 0.55.080.286 I slot print_timing: id 2 | task 213 | eval time = 17.96 ms / 2 tokens ( 17.96 ms per token, 55.66 tokens per second) 0.55.080.287 I slot print_timing: id 2 | task 213 | total time = 264.44 ms / 159 tokens 0.55.080.288 I slot print_timing: id 2 | task 213 | graphs reused = 1 0.55.080.289 I slot print_timing: id 2 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.080.303 I slot release: id 2 | task 213 | stop processing: n_tokens = 158, truncated = 0 0.55.080.604 I slot print_timing: id 3 | task 214 | prompt eval time = 246.12 ms / 117 tokens ( 2.10 ms per token, 475.38 tokens per second) 0.55.080.607 I slot print_timing: id 3 | task 214 | eval time = 17.74 ms / 2 tokens ( 17.74 ms per token, 56.37 tokens per second) 0.55.080.608 I slot print_timing: id 3 | task 214 | total time = 263.86 ms / 119 tokens 0.55.080.609 I slot print_timing: id 3 | task 214 | graphs reused = 1 0.55.080.609 I slot print_timing: id 3 | task 214 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.080.618 I slot release: id 3 | task 214 | stop processing: n_tokens = 118, truncated = 0 0.55.089.481 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.228 0.55.106.225 I slot launch_slot_: id 0 | task 218 | processing task, is_child = 0 0.55.106.259 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.722 MiB) 0.55.124.501 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.567 MiB) 0.55.143.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.724 MiB) 0.55.162.529 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.187 0.55.162.683 I slot launch_slot_: id 1 | task 219 | processing task, is_child = 0 0.55.162.733 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.177 0.55.162.845 I slot launch_slot_: id 2 | task 220 | processing task, is_child = 0 0.55.162.870 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.237 0.55.162.973 I slot launch_slot_: id 3 | task 221 | processing task, is_child = 0 0.55.429.353 I slot print_timing: id 0 | task 218 | prompt eval time = 247.24 ms / 149 tokens ( 1.66 ms per token, 602.66 tokens per second) 0.55.429.359 I slot print_timing: id 0 | task 218 | eval time = 19.12 ms / 2 tokens ( 19.12 ms per token, 52.29 tokens per second) 0.55.429.361 I slot print_timing: id 0 | task 218 | total time = 266.36 ms / 151 tokens 0.55.429.362 I slot print_timing: id 0 | task 218 | graphs reused = 1 0.55.429.363 I slot print_timing: id 0 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.429.393 I slot release: id 0 | task 218 | stop processing: n_tokens = 150, truncated = 0 0.55.429.840 I slot print_timing: id 1 | task 219 | prompt eval time = 247.07 ms / 155 tokens ( 1.59 ms per token, 627.34 tokens per second) 0.55.429.844 I slot print_timing: id 1 | task 219 | eval time = 18.88 ms / 2 tokens ( 18.88 ms per token, 52.95 tokens per second) 0.55.429.845 I slot print_timing: id 1 | task 219 | total time = 265.96 ms / 157 tokens 0.55.429.847 I slot print_timing: id 1 | task 219 | graphs reused = 1 0.55.429.847 I slot print_timing: id 1 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.429.871 I slot release: id 1 | task 219 | stop processing: n_tokens = 156, truncated = 0 0.55.430.341 I slot print_timing: id 2 | task 220 | prompt eval time = 246.93 ms / 154 tokens ( 1.60 ms per token, 623.65 tokens per second) 0.55.430.344 I slot print_timing: id 2 | task 220 | eval time = 18.67 ms / 2 tokens ( 18.67 ms per token, 53.57 tokens per second) 0.55.430.345 I slot print_timing: id 2 | task 220 | total time = 265.60 ms / 156 tokens 0.55.430.346 I slot print_timing: id 2 | task 220 | graphs reused = 1 0.55.430.347 I slot print_timing: id 2 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.430.364 I slot release: id 2 | task 220 | stop processing: n_tokens = 155, truncated = 0 0.55.430.795 I slot print_timing: id 3 | task 221 | prompt eval time = 246.72 ms / 160 tokens ( 1.54 ms per token, 648.50 tokens per second) 0.55.430.798 I slot print_timing: id 3 | task 221 | eval time = 18.45 ms / 2 tokens ( 18.45 ms per token, 54.19 tokens per second) 0.55.430.799 I slot print_timing: id 3 | task 221 | total time = 265.18 ms / 162 tokens 0.55.430.800 I slot print_timing: id 3 | task 221 | graphs reused = 1 0.55.430.800 I slot print_timing: id 3 | task 221 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.430.814 I slot release: id 3 | task 221 | stop processing: n_tokens = 161, truncated = 0 0.55.438.925 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.187 0.55.438.976 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.068 MiB) 0.55.468.278 I slot launch_slot_: id 0 | task 225 | processing task, is_child = 0 0.55.488.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.224 MiB) 0.55.511.009 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.661 MiB) 0.55.532.820 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.179 0.55.532.999 I slot launch_slot_: id 1 | task 226 | processing task, is_child = 0 0.55.533.049 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.181 0.55.533.161 I slot launch_slot_: id 2 | task 227 | processing task, is_child = 0 0.55.533.188 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.174 0.55.533.292 I slot launch_slot_: id 3 | task 228 | processing task, is_child = 0 0.55.773.034 I slot print_timing: id 0 | task 225 | prompt eval time = 221.04 ms / 102 tokens ( 2.17 ms per token, 461.45 tokens per second) 0.55.773.039 I slot print_timing: id 0 | task 225 | eval time = 18.68 ms / 2 tokens ( 18.68 ms per token, 53.52 tokens per second) 0.55.773.040 I slot print_timing: id 0 | task 225 | total time = 239.72 ms / 104 tokens 0.55.773.041 I slot print_timing: id 0 | task 225 | graphs reused = 1 0.55.773.041 I slot print_timing: id 0 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.773.064 I slot release: id 0 | task 225 | stop processing: n_tokens = 103, truncated = 0 0.55.773.368 I slot print_timing: id 1 | task 226 | prompt eval time = 220.83 ms / 107 tokens ( 2.06 ms per token, 484.54 tokens per second) 0.55.773.371 I slot print_timing: id 1 | task 226 | eval time = 18.38 ms / 2 tokens ( 18.38 ms per token, 54.42 tokens per second) 0.55.773.372 I slot print_timing: id 1 | task 226 | total time = 239.21 ms / 109 tokens 0.55.773.372 I slot print_timing: id 1 | task 226 | graphs reused = 1 0.55.773.373 I slot print_timing: id 1 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.773.386 I slot release: id 1 | task 226 | stop processing: n_tokens = 108, truncated = 0 0.55.773.702 I slot print_timing: id 2 | task 227 | prompt eval time = 220.57 ms / 114 tokens ( 1.93 ms per token, 516.84 tokens per second) 0.55.773.705 I slot print_timing: id 2 | task 227 | eval time = 18.08 ms / 2 tokens ( 18.08 ms per token, 55.31 tokens per second) 0.55.773.706 I slot print_timing: id 2 | task 227 | total time = 238.65 ms / 116 tokens 0.55.773.706 I slot print_timing: id 2 | task 227 | graphs reused = 1 0.55.773.707 I slot print_timing: id 2 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.773.718 I slot release: id 2 | task 227 | stop processing: n_tokens = 115, truncated = 0 0.55.774.029 I slot print_timing: id 3 | task 228 | prompt eval time = 220.32 ms / 185 tokens ( 1.19 ms per token, 839.68 tokens per second) 0.55.774.032 I slot print_timing: id 3 | task 228 | eval time = 17.77 ms / 2 tokens ( 17.77 ms per token, 56.27 tokens per second) 0.55.774.033 I slot print_timing: id 3 | task 228 | total time = 238.09 ms / 187 tokens 0.55.774.033 I slot print_timing: id 3 | task 228 | graphs reused = 1 0.55.774.034 I slot print_timing: id 3 | task 228 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.774.045 I slot release: id 3 | task 228 | stop processing: n_tokens = 186, truncated = 0 0.55.781.413 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.272 0.55.781.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 0.55.803.417 I slot launch_slot_: id 0 | task 232 | processing task, is_child = 0 0.55.803.450 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.192 MiB) 0.55.822.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.818 MiB) 0.55.842.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.911 MiB) 0.55.862.688 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.259 0.55.862.847 I slot launch_slot_: id 1 | task 233 | processing task, is_child = 0 0.55.862.893 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.243 0.55.871.196 I slot launch_slot_: id 2 | task 234 | processing task, is_child = 0 0.55.871.227 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 0.55.871.334 I slot launch_slot_: id 3 | task 235 | processing task, is_child = 0 0.56.100.336 I slot print_timing: id 0 | task 232 | prompt eval time = 210.85 ms / 122 tokens ( 1.73 ms per token, 578.62 tokens per second) 0.56.100.341 I slot print_timing: id 0 | task 232 | eval time = 18.14 ms / 2 tokens ( 18.14 ms per token, 55.13 tokens per second) 0.56.100.343 I slot print_timing: id 0 | task 232 | total time = 228.99 ms / 124 tokens 0.56.100.344 I slot print_timing: id 0 | task 232 | graphs reused = 1 0.56.100.345 I slot print_timing: id 0 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.100.369 I slot release: id 0 | task 232 | stop processing: n_tokens = 123, truncated = 0 0.56.100.692 I slot print_timing: id 1 | task 233 | prompt eval time = 210.58 ms / 126 tokens ( 1.67 ms per token, 598.34 tokens per second) 0.56.100.696 I slot print_timing: id 1 | task 233 | eval time = 17.88 ms / 2 tokens ( 17.88 ms per token, 55.92 tokens per second) 0.56.100.696 I slot print_timing: id 1 | task 233 | total time = 228.46 ms / 128 tokens 0.56.100.697 I slot print_timing: id 1 | task 233 | graphs reused = 1 0.56.100.697 I slot print_timing: id 1 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.100.712 I slot release: id 1 | task 233 | stop processing: n_tokens = 127, truncated = 0 0.56.101.065 I slot print_timing: id 2 | task 234 | prompt eval time = 210.30 ms / 110 tokens ( 1.91 ms per token, 523.07 tokens per second) 0.56.101.070 I slot print_timing: id 2 | task 234 | eval time = 17.68 ms / 2 tokens ( 17.68 ms per token, 56.55 tokens per second) 0.56.101.071 I slot print_timing: id 2 | task 234 | total time = 227.98 ms / 112 tokens 0.56.101.072 I slot print_timing: id 2 | task 234 | graphs reused = 1 0.56.101.072 I slot print_timing: id 2 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.101.086 I slot release: id 2 | task 234 | stop processing: n_tokens = 111, truncated = 0 0.56.101.407 I slot print_timing: id 3 | task 235 | prompt eval time = 210.05 ms / 164 tokens ( 1.28 ms per token, 780.77 tokens per second) 0.56.101.410 I slot print_timing: id 3 | task 235 | eval time = 17.44 ms / 2 tokens ( 17.44 ms per token, 57.34 tokens per second) 0.56.101.411 I slot print_timing: id 3 | task 235 | total time = 227.49 ms / 166 tokens 0.56.101.411 I slot print_timing: id 3 | task 235 | graphs reused = 1 0.56.101.412 I slot print_timing: id 3 | task 235 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.101.423 I slot release: id 3 | task 235 | stop processing: n_tokens = 165, truncated = 0 0.56.109.069 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 0.56.125.694 I slot launch_slot_: id 2 | task 239 | processing task, is_child = 0 0.56.125.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.536 MiB) 0.56.145.032 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.630 MiB) 0.56.166.968 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.568 MiB) 0.56.188.562 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 0.56.188.710 I slot launch_slot_: id 0 | task 240 | processing task, is_child = 0 0.56.188.759 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 0.56.188.873 I slot launch_slot_: id 1 | task 241 | processing task, is_child = 0 0.56.188.901 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 0.56.198.045 I slot launch_slot_: id 3 | task 242 | processing task, is_child = 0 0.56.434.684 I slot print_timing: id 0 | task 240 | prompt eval time = 217.41 ms / 125 tokens ( 1.74 ms per token, 574.96 tokens per second) 0.56.434.689 I slot print_timing: id 0 | task 240 | eval time = 19.22 ms / 2 tokens ( 19.22 ms per token, 52.04 tokens per second) 0.56.434.690 I slot print_timing: id 0 | task 240 | total time = 236.62 ms / 127 tokens 0.56.434.691 I slot print_timing: id 0 | task 240 | graphs reused = 1 0.56.434.692 I slot print_timing: id 0 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.434.715 I slot release: id 0 | task 240 | stop processing: n_tokens = 126, truncated = 0 0.56.435.040 I slot print_timing: id 1 | task 241 | prompt eval time = 217.36 ms / 122 tokens ( 1.78 ms per token, 561.29 tokens per second) 0.56.435.043 I slot print_timing: id 1 | task 241 | eval time = 18.75 ms / 2 tokens ( 18.75 ms per token, 53.34 tokens per second) 0.56.435.043 I slot print_timing: id 1 | task 241 | total time = 236.10 ms / 124 tokens 0.56.435.044 I slot print_timing: id 1 | task 241 | graphs reused = 1 0.56.435.045 I slot print_timing: id 1 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.435.058 I slot release: id 1 | task 241 | stop processing: n_tokens = 123, truncated = 0 0.56.435.378 I slot print_timing: id 2 | task 239 | prompt eval time = 217.36 ms / 138 tokens ( 1.58 ms per token, 634.88 tokens per second) 0.56.435.381 I slot print_timing: id 2 | task 239 | eval time = 18.20 ms / 2 tokens ( 18.20 ms per token, 54.93 tokens per second) 0.56.435.382 I slot print_timing: id 2 | task 239 | total time = 235.57 ms / 140 tokens 0.56.435.382 I slot print_timing: id 2 | task 239 | graphs reused = 1 0.56.435.383 I slot print_timing: id 2 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.435.395 I slot release: id 2 | task 239 | stop processing: n_tokens = 139, truncated = 0 0.56.435.710 I slot print_timing: id 3 | task 242 | prompt eval time = 217.21 ms / 137 tokens ( 1.59 ms per token, 630.71 tokens per second) 0.56.435.713 I slot print_timing: id 3 | task 242 | eval time = 17.83 ms / 2 tokens ( 17.83 ms per token, 56.10 tokens per second) 0.56.435.713 I slot print_timing: id 3 | task 242 | total time = 235.04 ms / 139 tokens 0.56.435.714 I slot print_timing: id 3 | task 242 | graphs reused = 1 0.56.435.714 I slot print_timing: id 3 | task 242 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.435.724 I slot release: id 3 | task 242 | stop processing: n_tokens = 138, truncated = 0 0.56.443.429 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 0.56.469.402 I slot launch_slot_: id 0 | task 246 | processing task, is_child = 0 0.56.489.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.755 MiB) 0.56.510.931 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.661 MiB) 0.56.533.082 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 0.56.533.243 I slot launch_slot_: id 1 | task 247 | processing task, is_child = 0 0.56.533.289 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.201 0.56.533.398 I slot launch_slot_: id 2 | task 248 | processing task, is_child = 0 0.56.533.424 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.203 0.56.533.524 I slot launch_slot_: id 3 | task 249 | processing task, is_child = 0 0.56.781.169 I slot print_timing: id 0 | task 246 | prompt eval time = 229.58 ms / 158 tokens ( 1.45 ms per token, 688.21 tokens per second) 0.56.781.174 I slot print_timing: id 0 | task 246 | eval time = 18.05 ms / 2 tokens ( 18.05 ms per token, 55.41 tokens per second) 0.56.781.176 I slot print_timing: id 0 | task 246 | total time = 247.63 ms / 160 tokens 0.56.781.176 I slot print_timing: id 0 | task 246 | graphs reused = 1 0.56.781.177 I slot print_timing: id 0 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.781.204 I slot release: id 0 | task 246 | stop processing: n_tokens = 159, truncated = 0 0.56.781.549 I slot print_timing: id 1 | task 247 | prompt eval time = 229.43 ms / 140 tokens ( 1.64 ms per token, 610.20 tokens per second) 0.56.781.554 I slot print_timing: id 1 | task 247 | eval time = 17.79 ms / 2 tokens ( 17.79 ms per token, 56.22 tokens per second) 0.56.781.554 I slot print_timing: id 1 | task 247 | total time = 247.22 ms / 142 tokens 0.56.781.555 I slot print_timing: id 1 | task 247 | graphs reused = 1 0.56.781.556 I slot print_timing: id 1 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.781.570 I slot release: id 1 | task 247 | stop processing: n_tokens = 141, truncated = 0 0.56.781.947 I slot print_timing: id 2 | task 248 | prompt eval time = 229.22 ms / 120 tokens ( 1.91 ms per token, 523.51 tokens per second) 0.56.781.950 I slot print_timing: id 2 | task 248 | eval time = 17.52 ms / 2 tokens ( 17.52 ms per token, 57.06 tokens per second) 0.56.781.951 I slot print_timing: id 2 | task 248 | total time = 246.75 ms / 122 tokens 0.56.781.952 I slot print_timing: id 2 | task 248 | graphs reused = 1 0.56.781.952 I slot print_timing: id 2 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.781.965 I slot release: id 2 | task 248 | stop processing: n_tokens = 121, truncated = 0 0.56.782.270 I slot print_timing: id 3 | task 249 | prompt eval time = 228.92 ms / 168 tokens ( 1.36 ms per token, 733.88 tokens per second) 0.56.782.273 I slot print_timing: id 3 | task 249 | eval time = 17.29 ms / 2 tokens ( 17.29 ms per token, 57.83 tokens per second) 0.56.782.274 I slot print_timing: id 3 | task 249 | total time = 246.21 ms / 170 tokens 0.56.782.274 I slot print_timing: id 3 | task 249 | graphs reused = 1 0.56.782.275 I slot print_timing: id 3 | task 249 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.782.292 I slot release: id 3 | task 249 | stop processing: n_tokens = 169, truncated = 0 0.56.790.824 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.176 0.56.790.880 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 0.56.814.448 I slot launch_slot_: id 0 | task 253 | processing task, is_child = 0 0.56.814.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.130 MiB) 0.56.833.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.285 MiB) 0.56.853.679 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.629 MiB) 0.56.873.063 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.199 0.56.881.154 I slot launch_slot_: id 1 | task 254 | processing task, is_child = 0 0.56.881.210 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.231 0.56.881.319 I slot launch_slot_: id 2 | task 255 | processing task, is_child = 0 0.56.881.346 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.166 0.56.881.451 I slot launch_slot_: id 3 | task 256 | processing task, is_child = 0 0.57.124.906 I slot print_timing: id 0 | task 253 | prompt eval time = 225.01 ms / 103 tokens ( 2.18 ms per token, 457.76 tokens per second) 0.57.124.912 I slot print_timing: id 0 | task 253 | eval time = 18.43 ms / 2 tokens ( 18.43 ms per token, 54.26 tokens per second) 0.57.124.913 I slot print_timing: id 0 | task 253 | total time = 243.44 ms / 105 tokens 0.57.124.914 I slot print_timing: id 0 | task 253 | graphs reused = 1 0.57.124.915 I slot print_timing: id 0 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.124.936 I slot release: id 0 | task 253 | stop processing: n_tokens = 104, truncated = 0 0.57.125.271 I slot print_timing: id 1 | task 254 | prompt eval time = 224.79 ms / 133 tokens ( 1.69 ms per token, 591.66 tokens per second) 0.57.125.274 I slot print_timing: id 1 | task 254 | eval time = 18.14 ms / 2 tokens ( 18.14 ms per token, 55.13 tokens per second) 0.57.125.275 I slot print_timing: id 1 | task 254 | total time = 242.93 ms / 135 tokens 0.57.125.276 I slot print_timing: id 1 | task 254 | graphs reused = 1 0.57.125.276 I slot print_timing: id 1 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.125.291 I slot release: id 1 | task 254 | stop processing: n_tokens = 134, truncated = 0 0.57.125.607 I slot print_timing: id 2 | task 255 | prompt eval time = 224.58 ms / 155 tokens ( 1.45 ms per token, 690.17 tokens per second) 0.57.125.611 I slot print_timing: id 2 | task 255 | eval time = 17.84 ms / 2 tokens ( 17.84 ms per token, 56.04 tokens per second) 0.57.125.611 I slot print_timing: id 2 | task 255 | total time = 242.43 ms / 157 tokens 0.57.125.612 I slot print_timing: id 2 | task 255 | graphs reused = 1 0.57.125.612 I slot print_timing: id 2 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.125.628 I slot release: id 2 | task 255 | stop processing: n_tokens = 156, truncated = 0 0.57.125.909 I slot print_timing: id 3 | task 256 | prompt eval time = 224.26 ms / 182 tokens ( 1.23 ms per token, 811.54 tokens per second) 0.57.125.912 I slot print_timing: id 3 | task 256 | eval time = 17.59 ms / 2 tokens ( 17.59 ms per token, 56.84 tokens per second) 0.57.125.913 I slot print_timing: id 3 | task 256 | total time = 241.86 ms / 184 tokens 0.57.125.913 I slot print_timing: id 3 | task 256 | graphs reused = 1 0.57.125.914 I slot print_timing: id 3 | task 256 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.125.926 I slot release: id 3 | task 256 | stop processing: n_tokens = 183, truncated = 0 0.57.151.817 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.269 0.57.168.670 I slot launch_slot_: id 0 | task 260 | processing task, is_child = 0 0.57.168.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.629 MiB) 0.57.189.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.410 MiB) 0.57.207.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 0.57.227.964 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.209 0.57.228.121 I slot launch_slot_: id 1 | task 261 | processing task, is_child = 0 0.57.353.650 I slot print_timing: id 0 | task 260 | prompt eval time = 110.65 ms / 144 tokens ( 0.77 ms per token, 1301.37 tokens per second) 0.57.353.655 I slot print_timing: id 0 | task 260 | eval time = 14.82 ms / 2 tokens ( 14.82 ms per token, 67.49 tokens per second) 0.57.353.656 I slot print_timing: id 0 | task 260 | total time = 125.47 ms / 146 tokens 0.57.353.657 I slot print_timing: id 0 | task 260 | graphs reused = 1 0.57.353.658 I slot print_timing: id 0 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.353.676 I slot release: id 0 | task 260 | stop processing: n_tokens = 145, truncated = 0 0.57.353.968 I slot print_timing: id 1 | task 261 | prompt eval time = 110.57 ms / 124 tokens ( 0.89 ms per token, 1121.49 tokens per second) 0.57.353.971 I slot print_timing: id 1 | task 261 | eval time = 14.41 ms / 2 tokens ( 14.41 ms per token, 69.40 tokens per second) 0.57.353.971 I slot print_timing: id 1 | task 261 | total time = 124.98 ms / 126 tokens 0.57.353.972 I slot print_timing: id 1 | task 261 | graphs reused = 1 0.57.353.973 I slot print_timing: id 1 | task 261 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.353.982 I slot release: id 1 | task 261 | stop processing: n_tokens = 125, truncated = 0 0.57.375.893 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 156, t_last = 57033897 0.57.376.104 I slot launch_slot_: id 2 | task 265 | processing task, is_child = 0 0.57.376.138 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 0.57.399.362 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.317 MiB) 0.57.419.658 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 183, t_last = 57034195 0.57.419.805 I slot launch_slot_: id 3 | task 266 | processing task, is_child = 0 0.57.419.849 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 145, t_last = 57261945 0.57.419.960 I slot launch_slot_: id 0 | task 267 | processing task, is_child = 0 0.57.419.983 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 125, t_last = 57262252 0.57.420.082 I slot launch_slot_: id 1 | task 268 | processing task, is_child = 0 0.59.623.516 I slot print_timing: id 2 | task 265 | prompt eval time = 1363.49 ms / 1215 tokens ( 1.12 ms per token, 891.10 tokens per second) 0.59.623.522 I slot print_timing: id 2 | task 265 | eval time = 838.23 ms / 59 tokens ( 14.45 ms per token, 69.19 tokens per second) 0.59.623.523 I slot print_timing: id 2 | task 265 | total time = 2201.72 ms / 1274 tokens 0.59.623.524 I slot print_timing: id 2 | task 265 | graphs reused = 59 0.59.623.525 I slot print_timing: id 2 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.623.579 I slot release: id 2 | task 265 | stop processing: n_tokens = 1273, truncated = 0 0.59.679.728 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.900 0.59.679.851 I slot launch_slot_: id 2 | task 335 | processing task, is_child = 0 0.59.905.987 I slot print_timing: id 3 | task 266 | prompt eval time = 1363.16 ms / 1230 tokens ( 1.11 ms per token, 902.32 tokens per second) 0.59.905.993 I slot print_timing: id 3 | task 266 | eval time = 1120.16 ms / 69 tokens ( 16.47 ms per token, 60.71 tokens per second) 0.59.905.994 I slot print_timing: id 3 | task 266 | total time = 2483.32 ms / 1299 tokens 0.59.905.995 I slot print_timing: id 3 | task 266 | graphs reused = 64 0.59.905.996 I slot print_timing: id 3 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.906.050 I slot release: id 3 | task 266 | stop processing: n_tokens = 1298, truncated = 0 0.59.921.744 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.883 0.59.921.842 I slot launch_slot_: id 3 | task 345 | processing task, is_child = 0 1.00.277.237 I slot print_timing: id 0 | task 267 | prompt eval time = 1364.06 ms / 1234 tokens ( 1.11 ms per token, 904.65 tokens per second) 1.00.277.242 I slot print_timing: id 0 | task 267 | eval time = 1493.08 ms / 88 tokens ( 17.16 ms per token, 58.27 tokens per second) 1.00.277.244 I slot print_timing: id 0 | task 267 | total time = 2857.14 ms / 1322 tokens 1.00.277.244 I slot print_timing: id 0 | task 267 | graphs reused = 79 1.00.277.245 I slot print_timing: id 0 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.277.295 I slot release: id 0 | task 267 | stop processing: n_tokens = 1321, truncated = 0 1.00.323.453 I slot print_timing: id 1 | task 268 | prompt eval time = 1363.74 ms / 1243 tokens ( 1.10 ms per token, 911.46 tokens per second) 1.00.323.459 I slot print_timing: id 1 | task 268 | eval time = 1538.73 ms / 91 tokens ( 17.10 ms per token, 58.49 tokens per second) 1.00.323.460 I slot print_timing: id 1 | task 268 | total time = 2902.47 ms / 1334 tokens 1.00.323.460 I slot print_timing: id 1 | task 268 | graphs reused = 81 1.00.323.461 I slot print_timing: id 1 | task 268 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.323.508 I slot release: id 1 | task 268 | stop processing: n_tokens = 1333, truncated = 0 1.00.323.968 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.868 1.00.324.088 I slot launch_slot_: id 0 | task 367 | processing task, is_child = 0 1.00.324.180 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.912 MiB) 1.00.325.755 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.223 MiB) 1.00.374.317 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.860 1.00.374.426 I slot launch_slot_: id 1 | task 368 | processing task, is_child = 0 1.01.254.442 I slot print_timing: id 2 | task 335 | prompt eval time = 134.68 ms / 132 tokens ( 1.02 ms per token, 980.09 tokens per second) 1.01.254.447 I slot print_timing: id 2 | task 335 | eval time = 1439.89 ms / 79 tokens ( 18.46 ms per token, 54.17 tokens per second) 1.01.254.448 I slot print_timing: id 2 | task 335 | total time = 1574.57 ms / 211 tokens 1.01.254.449 I slot print_timing: id 2 | task 335 | graphs reused = 128 1.01.254.450 I slot print_timing: id 2 | task 335 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.254.502 I slot release: id 2 | task 335 | stop processing: n_tokens = 1335, truncated = 0 1.01.309.517 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.858 1.01.309.629 I slot launch_slot_: id 2 | task 421 | processing task, is_child = 0 1.02.077.519 I slot print_timing: id 3 | task 345 | prompt eval time = 121.82 ms / 139 tokens ( 0.88 ms per token, 1140.99 tokens per second) 1.02.077.525 I slot print_timing: id 3 | task 345 | eval time = 2033.84 ms / 119 tokens ( 17.24 ms per token, 58.02 tokens per second) 1.02.077.526 I slot print_timing: id 3 | task 345 | total time = 2155.66 ms / 258 tokens 1.02.077.526 I slot print_timing: id 3 | task 345 | graphs reused = 172 1.02.077.527 I slot print_timing: id 3 | task 345 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.077.578 I slot release: id 3 | task 345 | stop processing: n_tokens = 1382, truncated = 0 1.02.108.823 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.829 1.02.108.931 I slot launch_slot_: id 3 | task 471 | processing task, is_child = 0 1.02.363.246 I slot print_timing: id 1 | task 368 | prompt eval time = 159.50 ms / 114 tokens ( 1.40 ms per token, 714.75 tokens per second) 1.02.363.251 I slot print_timing: id 1 | task 368 | eval time = 1810.31 ms / 111 tokens ( 16.46 ms per token, 60.76 tokens per second) 1.02.363.252 I slot print_timing: id 1 | task 368 | total time = 1969.81 ms / 225 tokens 1.02.363.253 I slot print_timing: id 1 | task 368 | graphs reused = 181 1.02.363.253 I slot print_timing: id 1 | task 368 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.363.304 I slot release: id 1 | task 368 | stop processing: n_tokens = 1349, truncated = 0 1.02.417.678 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.850 1.02.417.819 I slot launch_slot_: id 1 | task 485 | processing task, is_child = 0 1.03.555.709 I slot print_timing: id 0 | task 367 | n_gen = 185, tg = 61.26 t/s, tg_3s = 61.59 t/s 1.03.571.097 I slot print_timing: id 2 | task 421 | prompt eval time = 139.75 ms / 141 tokens ( 0.99 ms per token, 1008.94 tokens per second) 1.03.571.103 I slot print_timing: id 2 | task 421 | eval time = 2121.70 ms / 134 tokens ( 15.95 ms per token, 62.69 tokens per second) 1.03.571.104 I slot print_timing: id 2 | task 421 | total time = 2261.45 ms / 275 tokens 1.03.571.105 I slot print_timing: id 2 | task 421 | graphs reused = 251 1.03.571.106 I slot print_timing: id 2 | task 421 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.571.163 I slot release: id 2 | task 421 | stop processing: n_tokens = 1399, truncated = 0 1.03.599.392 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.819 1.03.599.514 I slot launch_slot_: id 2 | task 560 | processing task, is_child = 0 1.03.747.298 I slot print_timing: id 0 | task 367 | prompt eval time = 177.54 ms / 139 tokens ( 1.28 ms per token, 782.90 tokens per second) 1.03.747.303 I slot print_timing: id 0 | task 367 | eval time = 3195.31 ms / 190 tokens ( 16.91 ms per token, 59.15 tokens per second) 1.03.747.304 I slot print_timing: id 0 | task 367 | total time = 3372.85 ms / 329 tokens 1.03.747.305 I slot print_timing: id 0 | task 367 | graphs reused = 251 1.03.747.306 I slot print_timing: id 0 | task 367 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.747.361 I slot release: id 0 | task 367 | stop processing: n_tokens = 1453, truncated = 0 1.03.792.903 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.789 1.03.793.029 I slot launch_slot_: id 0 | task 567 | processing task, is_child = 0 1.04.208.765 I slot print_timing: id 1 | task 485 | prompt eval time = 131.62 ms / 125 tokens ( 1.05 ms per token, 949.72 tokens per second) 1.04.208.770 I slot print_timing: id 1 | task 485 | eval time = 1659.31 ms / 102 tokens ( 16.43 ms per token, 60.87 tokens per second) 1.04.208.771 I slot print_timing: id 1 | task 485 | total time = 1790.93 ms / 227 tokens 1.04.208.772 I slot print_timing: id 1 | task 485 | graphs reused = 274 1.04.208.772 I slot print_timing: id 1 | task 485 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.208.822 I slot release: id 1 | task 485 | stop processing: n_tokens = 1351, truncated = 0 1.04.236.937 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.848 1.04.237.045 I slot launch_slot_: id 1 | task 592 | processing task, is_child = 0 1.04.775.556 I slot print_timing: id 0 | task 567 | prompt eval time = 103.07 ms / 101 tokens ( 1.02 ms per token, 979.92 tokens per second) 1.04.775.562 I slot print_timing: id 0 | task 567 | eval time = 879.44 ms / 53 tokens ( 16.91 ms per token, 59.13 tokens per second) 1.04.775.563 I slot print_timing: id 0 | task 567 | total time = 982.51 ms / 154 tokens 1.04.775.564 I slot print_timing: id 0 | task 567 | graphs reused = 301 1.04.775.565 I slot print_timing: id 0 | task 567 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.775.615 I slot release: id 0 | task 567 | stop processing: n_tokens = 1278, truncated = 0 1.04.792.647 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.897 1.04.792.756 I slot launch_slot_: id 0 | task 624 | processing task, is_child = 0 1.05.154.837 I slot print_timing: id 2 | task 560 | prompt eval time = 130.47 ms / 101 tokens ( 1.29 ms per token, 774.15 tokens per second) 1.05.154.843 I slot print_timing: id 2 | task 560 | eval time = 1424.84 ms / 79 tokens ( 18.27 ms per token, 54.74 tokens per second) 1.05.154.844 I slot print_timing: id 2 | task 560 | total time = 1555.30 ms / 180 tokens 1.05.154.844 I slot print_timing: id 2 | task 560 | graphs reused = 318 1.05.154.845 I slot print_timing: id 2 | task 560 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.154.894 I slot release: id 2 | task 560 | stop processing: n_tokens = 1304, truncated = 0 1.05.182.888 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.879 1.05.183.061 I slot launch_slot_: id 2 | task 645 | processing task, is_child = 0 1.05.275.715 I slot print_timing: id 3 | task 471 | n_gen = 168, tg = 54.91 t/s, tg_3s = 55.23 t/s 1.05.902.907 I slot print_timing: id 3 | task 471 | prompt eval time = 125.17 ms / 169 tokens ( 0.74 ms per token, 1350.16 tokens per second) 1.05.902.912 I slot print_timing: id 3 | task 471 | eval time = 3668.79 ms / 210 tokens ( 17.55 ms per token, 56.97 tokens per second) 1.05.902.913 I slot print_timing: id 3 | task 471 | total time = 3793.96 ms / 379 tokens 1.05.902.914 I slot print_timing: id 3 | task 471 | graphs reused = 358 1.05.902.915 I slot print_timing: id 3 | task 471 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.902.968 I slot release: id 3 | task 471 | stop processing: n_tokens = 1503, truncated = 0 1.05.934.502 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.762 1.05.934.613 I slot launch_slot_: id 3 | task 691 | processing task, is_child = 0 1.06.143.954 I slot print_timing: id 0 | task 624 | prompt eval time = 110.78 ms / 120 tokens ( 0.92 ms per token, 1083.22 tokens per second) 1.06.143.960 I slot print_timing: id 0 | task 624 | eval time = 1240.40 ms / 73 tokens ( 17.23 ms per token, 58.05 tokens per second) 1.06.143.961 I slot print_timing: id 0 | task 624 | total time = 1351.18 ms / 193 tokens 1.06.143.962 I slot print_timing: id 0 | task 624 | graphs reused = 365 1.06.143.963 I slot print_timing: id 0 | task 624 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.144.015 I slot release: id 0 | task 624 | stop processing: n_tokens = 1317, truncated = 0 1.06.188.133 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.870 1.06.188.232 I slot launch_slot_: id 0 | task 704 | processing task, is_child = 0 1.06.582.746 I slot print_timing: id 1 | task 592 | prompt eval time = 129.38 ms / 95 tokens ( 1.36 ms per token, 734.29 tokens per second) 1.06.582.752 I slot print_timing: id 1 | task 592 | eval time = 2216.31 ms / 129 tokens ( 17.31 ms per token, 57.75 tokens per second) 1.06.582.753 I slot print_timing: id 1 | task 592 | total time = 2345.69 ms / 224 tokens 1.06.582.753 I slot print_timing: id 1 | task 592 | graphs reused = 387 1.06.582.754 I slot print_timing: id 1 | task 592 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.582.804 I slot release: id 1 | task 592 | stop processing: n_tokens = 1348, truncated = 0 1.06.637.153 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.850 1.06.637.263 I slot launch_slot_: id 1 | task 729 | processing task, is_child = 0 1.07.530.546 I slot print_timing: id 3 | task 691 | prompt eval time = 107.67 ms / 86 tokens ( 1.25 ms per token, 798.76 tokens per second) 1.07.530.552 I slot print_timing: id 3 | task 691 | eval time = 1488.25 ms / 90 tokens ( 16.72 ms per token, 59.80 tokens per second) 1.07.530.553 I slot print_timing: id 3 | task 691 | total time = 1595.91 ms / 176 tokens 1.07.530.554 I slot print_timing: id 3 | task 691 | graphs reused = 439 1.07.530.555 I slot print_timing: id 3 | task 691 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.530.613 I slot release: id 3 | task 691 | stop processing: n_tokens = 1300, truncated = 0 1.07.575.233 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.948 (> 0.100 thold), f_keep = 0.882 1.07.575.344 I slot launch_slot_: id 3 | task 788 | processing task, is_child = 0 1.07.773.879 I slot print_timing: id 0 | task 704 | prompt eval time = 111.70 ms / 133 tokens ( 0.84 ms per token, 1190.64 tokens per second) 1.07.773.885 I slot print_timing: id 0 | task 704 | eval time = 1473.93 ms / 89 tokens ( 16.75 ms per token, 59.70 tokens per second) 1.07.773.886 I slot print_timing: id 0 | task 704 | total time = 1585.63 ms / 222 tokens 1.07.773.887 I slot print_timing: id 0 | task 704 | graphs reused = 446 1.07.773.888 I slot print_timing: id 0 | task 704 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.773.941 I slot release: id 0 | task 704 | stop processing: n_tokens = 1346, truncated = 0 1.07.820.290 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.851 1.07.820.408 I slot launch_slot_: id 0 | task 800 | processing task, is_child = 0 1.08.247.766 I slot print_timing: id 1 | task 729 | prompt eval time = 126.64 ms / 97 tokens ( 1.31 ms per token, 765.94 tokens per second) 1.08.247.771 I slot print_timing: id 1 | task 729 | eval time = 1483.85 ms / 92 tokens ( 16.31 ms per token, 61.33 tokens per second) 1.08.247.773 I slot print_timing: id 1 | task 729 | total time = 1610.49 ms / 189 tokens 1.08.247.773 I slot print_timing: id 1 | task 729 | graphs reused = 470 1.08.247.774 I slot print_timing: id 1 | task 729 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.247.824 I slot release: id 1 | task 729 | stop processing: n_tokens = 1313, truncated = 0 1.08.275.881 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.873 1.08.275.995 I slot launch_slot_: id 1 | task 826 | processing task, is_child = 0 1.08.352.005 I slot print_timing: id 2 | task 645 | n_gen = 175, tg = 57.55 t/s, tg_3s = 57.89 t/s 1.08.685.262 I slot print_timing: id 2 | task 645 | prompt eval time = 145.71 ms / 148 tokens ( 0.98 ms per token, 1015.72 tokens per second) 1.08.685.267 I slot print_timing: id 2 | task 645 | eval time = 3356.47 ms / 195 tokens ( 17.30 ms per token, 57.80 tokens per second) 1.08.685.269 I slot print_timing: id 2 | task 645 | total time = 3502.18 ms / 343 tokens 1.08.685.269 I slot print_timing: id 2 | task 645 | graphs reused = 488 1.08.685.270 I slot print_timing: id 2 | task 645 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.685.324 I slot release: id 2 | task 645 | stop processing: n_tokens = 1467, truncated = 0 1.08.741.003 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.781 1.08.741.137 I slot launch_slot_: id 2 | task 850 | processing task, is_child = 0 1.09.045.210 I slot print_timing: id 3 | task 788 | prompt eval time = 106.55 ms / 84 tokens ( 1.27 ms per token, 788.35 tokens per second) 1.09.045.216 I slot print_timing: id 3 | task 788 | eval time = 1363.30 ms / 71 tokens ( 19.48 ms per token, 51.35 tokens per second) 1.09.045.217 I slot print_timing: id 3 | task 788 | total time = 1469.85 ms / 155 tokens 1.09.045.217 I slot print_timing: id 3 | task 788 | graphs reused = 497 1.09.045.218 I slot print_timing: id 3 | task 788 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.045.270 I slot release: id 3 | task 788 | stop processing: n_tokens = 1279, truncated = 0 1.09.077.842 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.896 1.09.077.946 I slot launch_slot_: id 3 | task 866 | processing task, is_child = 0 1.09.448.518 I slot print_timing: id 0 | task 800 | prompt eval time = 102.08 ms / 101 tokens ( 1.01 ms per token, 989.44 tokens per second) 1.09.448.523 I slot print_timing: id 0 | task 800 | eval time = 1526.02 ms / 82 tokens ( 18.84 ms per token, 53.08 tokens per second) 1.09.448.524 I slot print_timing: id 0 | task 800 | total time = 1628.09 ms / 183 tokens 1.09.448.525 I slot print_timing: id 0 | task 800 | graphs reused = 515 1.09.448.526 I slot print_timing: id 0 | task 800 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.448.578 I slot release: id 0 | task 800 | stop processing: n_tokens = 1307, truncated = 0 1.09.448.803 I slot print_timing: id 1 | task 826 | prompt eval time = 129.39 ms / 95 tokens ( 1.36 ms per token, 734.21 tokens per second) 1.09.448.806 I slot print_timing: id 1 | task 826 | eval time = 1043.41 ms / 57 tokens ( 18.63 ms per token, 53.67 tokens per second) 1.09.448.807 I slot print_timing: id 1 | task 826 | total time = 1172.80 ms / 152 tokens 1.09.448.807 I slot print_timing: id 1 | task 826 | graphs reused = 515 1.09.448.808 I slot print_timing: id 1 | task 826 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.448.838 I slot release: id 1 | task 826 | stop processing: n_tokens = 1276, truncated = 0 1.09.463.994 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.877 1.09.464.094 I slot launch_slot_: id 0 | task 888 | processing task, is_child = 0 1.09.464.180 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.068 MiB) 1.09.465.794 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.786 MiB) 1.09.467.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 108.038 MiB) 1.09.514.757 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.898 1.09.514.878 I slot launch_slot_: id 1 | task 889 | processing task, is_child = 0 1.10.753.260 I slot print_timing: id 3 | task 866 | prompt eval time = 109.61 ms / 90 tokens ( 1.22 ms per token, 821.08 tokens per second) 1.10.753.266 I slot print_timing: id 3 | task 866 | eval time = 1565.69 ms / 99 tokens ( 15.98 ms per token, 62.59 tokens per second) 1.10.753.267 I slot print_timing: id 3 | task 866 | total time = 1675.30 ms / 189 tokens 1.10.753.267 I slot print_timing: id 3 | task 866 | graphs reused = 592 1.10.753.268 I slot print_timing: id 3 | task 866 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.753.317 I slot release: id 3 | task 866 | stop processing: n_tokens = 1313, truncated = 0 1.10.784.545 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.874 1.10.784.646 I slot launch_slot_: id 3 | task 971 | processing task, is_child = 0 1.10.854.012 I slot print_timing: id 0 | task 888 | prompt eval time = 164.45 ms / 96 tokens ( 1.71 ms per token, 583.76 tokens per second) 1.10.854.017 I slot print_timing: id 0 | task 888 | eval time = 1174.66 ms / 81 tokens ( 14.68 ms per token, 68.10 tokens per second) 1.10.854.018 I slot print_timing: id 0 | task 888 | total time = 1339.11 ms / 177 tokens 1.10.854.019 I slot print_timing: id 0 | task 888 | graphs reused = 593 1.10.854.020 I slot print_timing: id 0 | task 888 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.854.072 I slot release: id 0 | task 888 | stop processing: n_tokens = 1301, truncated = 0 1.10.895.989 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.881 1.10.896.092 I slot launch_slot_: id 0 | task 974 | processing task, is_child = 0 1.11.180.372 I slot print_timing: id 1 | task 889 | prompt eval time = 145.34 ms / 87 tokens ( 1.67 ms per token, 598.61 tokens per second) 1.11.180.377 I slot print_timing: id 1 | task 889 | eval time = 1500.41 ms / 95 tokens ( 15.96 ms per token, 62.65 tokens per second) 1.11.180.378 I slot print_timing: id 1 | task 889 | total time = 1645.74 ms / 182 tokens 1.11.180.379 I slot print_timing: id 1 | task 889 | graphs reused = 603 1.11.180.379 I slot print_timing: id 1 | task 889 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.180.428 I slot release: id 1 | task 889 | stop processing: n_tokens = 1306, truncated = 0 1.11.208.623 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.877 1.11.208.738 I slot launch_slot_: id 1 | task 989 | processing task, is_child = 0 1.11.400.964 I slot print_timing: id 2 | task 850 | prompt eval time = 135.31 ms / 130 tokens ( 1.04 ms per token, 960.76 tokens per second) 1.11.400.970 I slot print_timing: id 2 | task 850 | eval time = 2524.50 ms / 137 tokens ( 18.56 ms per token, 53.87 tokens per second) 1.11.400.971 I slot print_timing: id 2 | task 850 | total time = 2659.81 ms / 267 tokens 1.11.400.972 I slot print_timing: id 2 | task 850 | graphs reused = 605 1.11.400.972 I slot print_timing: id 2 | task 850 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.401.022 I slot release: id 2 | task 850 | stop processing: n_tokens = 1391, truncated = 0 1.11.456.794 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.824 1.11.456.911 I slot launch_slot_: id 2 | task 997 | processing task, is_child = 0 1.12.518.350 I slot print_timing: id 2 | task 997 | prompt eval time = 130.59 ms / 93 tokens ( 1.40 ms per token, 712.13 tokens per second) 1.12.518.356 I slot print_timing: id 2 | task 997 | eval time = 930.83 ms / 65 tokens ( 14.54 ms per token, 68.76 tokens per second) 1.12.518.357 I slot print_timing: id 2 | task 997 | total time = 1061.42 ms / 158 tokens 1.12.518.358 I slot print_timing: id 2 | task 997 | graphs reused = 668 1.12.518.358 I slot print_timing: id 2 | task 997 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.518.411 I slot release: id 2 | task 997 | stop processing: n_tokens = 1282, truncated = 0 1.12.545.781 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.894 1.12.545.893 I slot launch_slot_: id 2 | task 1065 | processing task, is_child = 0 1.12.897.639 I slot print_timing: id 3 | task 971 | prompt eval time = 111.32 ms / 131 tokens ( 0.85 ms per token, 1176.79 tokens per second) 1.12.897.645 I slot print_timing: id 3 | task 971 | eval time = 2001.66 ms / 106 tokens ( 19.06 ms per token, 52.46 tokens per second) 1.12.897.646 I slot print_timing: id 3 | task 971 | total time = 2112.98 ms / 237 tokens 1.12.897.647 I slot print_timing: id 3 | task 971 | graphs reused = 682 1.12.897.648 I slot print_timing: id 3 | task 971 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.897.699 I slot release: id 3 | task 971 | stop processing: n_tokens = 1361, truncated = 0 1.12.942.712 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.842 1.12.942.817 I slot launch_slot_: id 3 | task 1086 | processing task, is_child = 0 1.13.600.701 I slot print_timing: id 2 | task 1065 | prompt eval time = 129.66 ms / 87 tokens ( 1.49 ms per token, 670.97 tokens per second) 1.13.600.707 I slot print_timing: id 2 | task 1065 | eval time = 925.13 ms / 59 tokens ( 15.95 ms per token, 62.69 tokens per second) 1.13.600.708 I slot print_timing: id 2 | task 1065 | total time = 1054.79 ms / 146 tokens 1.13.600.710 I slot print_timing: id 2 | task 1065 | graphs reused = 721 1.13.600.711 I slot print_timing: id 2 | task 1065 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.600.760 I slot release: id 2 | task 1065 | stop processing: n_tokens = 1270, truncated = 0 1.13.628.166 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.902 1.13.628.290 I slot launch_slot_: id 2 | task 1128 | processing task, is_child = 0 1.14.027.000 I slot print_timing: id 0 | task 974 | n_gen = 169, tg = 55.78 t/s, tg_3s = 56.11 t/s 1.14.027.207 I slot print_timing: id 1 | task 989 | prompt eval time = 144.03 ms / 153 tokens ( 0.94 ms per token, 1062.29 tokens per second) 1.14.027.210 I slot print_timing: id 1 | task 989 | eval time = 2674.43 ms / 155 tokens ( 17.37 ms per token, 57.58 tokens per second) 1.14.027.211 I slot print_timing: id 1 | task 989 | total time = 2818.46 ms / 308 tokens 1.14.027.213 I slot print_timing: id 1 | task 989 | graphs reused = 739 1.14.027.213 I slot print_timing: id 1 | task 989 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.027.267 I slot release: id 1 | task 989 | stop processing: n_tokens = 1432, truncated = 0 1.14.054.651 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.800 1.14.054.757 I slot launch_slot_: id 1 | task 1151 | processing task, is_child = 0 1.14.218.149 I slot print_timing: id 3 | task 1086 | prompt eval time = 110.52 ms / 98 tokens ( 1.13 ms per token, 886.73 tokens per second) 1.14.218.154 I slot print_timing: id 3 | task 1086 | eval time = 1164.80 ms / 66 tokens ( 17.92 ms per token, 55.80 tokens per second) 1.14.218.156 I slot print_timing: id 3 | task 1086 | total time = 1275.32 ms / 164 tokens 1.14.218.157 I slot print_timing: id 3 | task 1086 | graphs reused = 740 1.14.218.157 I slot print_timing: id 3 | task 1086 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.218.209 I slot release: id 3 | task 1086 | stop processing: n_tokens = 1288, truncated = 0 1.14.261.580 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.890 1.14.261.686 I slot launch_slot_: id 3 | task 1159 | processing task, is_child = 0 1.14.751.205 I slot print_timing: id 0 | task 974 | prompt eval time = 119.14 ms / 137 tokens ( 0.87 ms per token, 1149.94 tokens per second) 1.14.751.210 I slot print_timing: id 0 | task 974 | eval time = 3735.96 ms / 206 tokens ( 18.22 ms per token, 54.87 tokens per second) 1.14.751.212 I slot print_timing: id 0 | task 974 | total time = 3855.10 ms / 343 tokens 1.14.751.212 I slot print_timing: id 0 | task 974 | graphs reused = 768 1.14.751.213 I slot print_timing: id 0 | task 974 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.751.264 I slot release: id 0 | task 974 | stop processing: n_tokens = 1467, truncated = 0 1.14.795.387 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.781 1.14.795.492 I slot launch_slot_: id 0 | task 1192 | processing task, is_child = 0 1.15.392.499 I slot print_timing: id 2 | task 1128 | prompt eval time = 130.06 ms / 105 tokens ( 1.24 ms per token, 807.33 tokens per second) 1.15.392.504 I slot print_timing: id 2 | task 1128 | eval time = 1634.13 ms / 96 tokens ( 17.20 ms per token, 58.13 tokens per second) 1.15.392.505 I slot print_timing: id 2 | task 1128 | total time = 1764.19 ms / 201 tokens 1.15.392.506 I slot print_timing: id 2 | task 1128 | graphs reused = 804 1.15.392.507 I slot print_timing: id 2 | task 1128 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.392.559 I slot release: id 2 | task 1128 | stop processing: n_tokens = 1325, truncated = 0 1.15.448.234 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.865 1.15.448.351 I slot launch_slot_: id 2 | task 1231 | processing task, is_child = 0 1.16.020.131 I slot print_timing: id 1 | task 1151 | prompt eval time = 130.00 ms / 113 tokens ( 1.15 ms per token, 869.25 tokens per second) 1.16.020.136 I slot print_timing: id 1 | task 1151 | eval time = 1835.36 ms / 108 tokens ( 17.15 ms per token, 58.30 tokens per second) 1.16.020.137 I slot print_timing: id 1 | task 1151 | total time = 1965.36 ms / 221 tokens 1.16.020.139 I slot print_timing: id 1 | task 1151 | graphs reused = 833 1.16.020.139 I slot print_timing: id 1 | task 1151 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.020.193 I slot release: id 1 | task 1151 | stop processing: n_tokens = 1345, truncated = 0 1.16.020.770 I slot print_timing: id 3 | task 1159 | prompt eval time = 112.35 ms / 122 tokens ( 0.92 ms per token, 1085.89 tokens per second) 1.16.020.773 I slot print_timing: id 3 | task 1159 | eval time = 1646.72 ms / 101 tokens ( 16.47 ms per token, 60.73 tokens per second) 1.16.020.774 I slot print_timing: id 3 | task 1159 | total time = 1759.07 ms / 223 tokens 1.16.020.775 I slot print_timing: id 3 | task 1159 | graphs reused = 833 1.16.020.775 I slot print_timing: id 3 | task 1159 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.020.813 I slot release: id 3 | task 1159 | stop processing: n_tokens = 1347, truncated = 0 1.16.047.289 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.852 1.16.047.429 I slot launch_slot_: id 1 | task 1265 | processing task, is_child = 0 1.16.047.543 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.380 MiB) 1.16.049.514 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.536 MiB) 1.16.051.398 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.600 MiB) 1.16.097.861 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.851 1.16.097.977 I slot launch_slot_: id 3 | task 1266 | processing task, is_child = 0 1.16.742.064 I slot print_timing: id 0 | task 1192 | prompt eval time = 100.00 ms / 96 tokens ( 1.04 ms per token, 960.01 tokens per second) 1.16.742.070 I slot print_timing: id 0 | task 1192 | eval time = 1846.56 ms / 101 tokens ( 18.47 ms per token, 54.15 tokens per second) 1.16.742.071 I slot print_timing: id 0 | task 1192 | total time = 1946.56 ms / 197 tokens 1.16.742.071 I slot print_timing: id 0 | task 1192 | graphs reused = 861 1.16.742.072 I slot print_timing: id 0 | task 1192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.742.121 I slot release: id 0 | task 1192 | stop processing: n_tokens = 1321, truncated = 0 1.16.775.312 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.868 1.16.775.421 I slot launch_slot_: id 0 | task 1300 | processing task, is_child = 0 1.17.038.259 I slot print_timing: id 2 | task 1231 | prompt eval time = 134.26 ms / 113 tokens ( 1.19 ms per token, 841.65 tokens per second) 1.17.038.265 I slot print_timing: id 2 | task 1231 | eval time = 1455.63 ms / 77 tokens ( 19.15 ms per token, 52.21 tokens per second) 1.17.038.267 I slot print_timing: id 2 | task 1231 | total time = 1589.89 ms / 190 tokens 1.17.038.267 I slot print_timing: id 2 | task 1231 | graphs reused = 872 1.17.038.269 I slot print_timing: id 2 | task 1231 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.038.329 I slot release: id 2 | task 1231 | stop processing: n_tokens = 1314, truncated = 0 1.17.094.265 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.872 1.17.094.384 I slot launch_slot_: id 2 | task 1315 | processing task, is_child = 0 1.17.980.875 I slot print_timing: id 3 | task 1266 | prompt eval time = 203.14 ms / 131 tokens ( 1.55 ms per token, 644.87 tokens per second) 1.17.980.880 I slot print_timing: id 3 | task 1266 | eval time = 1659.97 ms / 101 tokens ( 16.60 ms per token, 60.24 tokens per second) 1.17.980.882 I slot print_timing: id 3 | task 1266 | total time = 1863.11 ms / 232 tokens 1.17.980.883 I slot print_timing: id 3 | task 1266 | graphs reused = 924 1.17.980.883 I slot print_timing: id 3 | task 1266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.980.933 I slot release: id 3 | task 1266 | stop processing: n_tokens = 1356, truncated = 0 1.18.012.252 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.845 1.18.012.356 I slot launch_slot_: id 3 | task 1373 | processing task, is_child = 0 1.18.089.776 I slot print_timing: id 0 | task 1300 | prompt eval time = 107.23 ms / 117 tokens ( 0.92 ms per token, 1091.14 tokens per second) 1.18.089.783 I slot print_timing: id 0 | task 1300 | eval time = 1207.11 ms / 71 tokens ( 17.24 ms per token, 57.99 tokens per second) 1.18.089.784 I slot print_timing: id 0 | task 1300 | total time = 1314.34 ms / 188 tokens 1.18.089.785 I slot print_timing: id 0 | task 1300 | graphs reused = 925 1.18.089.786 I slot print_timing: id 0 | task 1300 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.089.846 I slot release: id 0 | task 1300 | stop processing: n_tokens = 1312, truncated = 0 1.18.129.919 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.873 1.18.130.026 I slot launch_slot_: id 0 | task 1376 | processing task, is_child = 0 1.18.874.087 I slot print_timing: id 1 | task 1265 | prompt eval time = 221.96 ms / 149 tokens ( 1.49 ms per token, 671.29 tokens per second) 1.18.874.092 I slot print_timing: id 1 | task 1265 | eval time = 2554.13 ms / 153 tokens ( 16.80 ms per token, 59.51 tokens per second) 1.18.874.094 I slot print_timing: id 1 | task 1265 | total time = 2776.09 ms / 302 tokens 1.18.874.094 I slot print_timing: id 1 | task 1265 | graphs reused = 970 1.18.874.095 I slot print_timing: id 1 | task 1265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.874.145 I slot release: id 1 | task 1265 | stop processing: n_tokens = 1426, truncated = 0 1.18.928.265 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.804 1.18.928.375 I slot launch_slot_: id 1 | task 1427 | processing task, is_child = 0 1.19.271.178 I slot print_timing: id 2 | task 1315 | prompt eval time = 137.20 ms / 127 tokens ( 1.08 ms per token, 925.67 tokens per second) 1.19.271.184 I slot print_timing: id 2 | task 1315 | eval time = 2039.58 ms / 124 tokens ( 16.58 ms per token, 60.31 tokens per second) 1.19.271.185 I slot print_timing: id 2 | task 1315 | total time = 2176.78 ms / 251 tokens 1.19.271.187 I slot print_timing: id 2 | task 1315 | graphs reused = 983 1.19.271.188 I slot print_timing: id 2 | task 1315 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.271.238 I slot release: id 2 | task 1315 | stop processing: n_tokens = 1375, truncated = 0 1.19.299.313 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.833 1.19.299.424 I slot launch_slot_: id 2 | task 1445 | processing task, is_child = 0 1.19.752.218 I slot print_timing: id 0 | task 1376 | prompt eval time = 103.28 ms / 96 tokens ( 1.08 ms per token, 929.47 tokens per second) 1.19.752.224 I slot print_timing: id 0 | task 1376 | eval time = 1518.89 ms / 90 tokens ( 17.07 ms per token, 58.60 tokens per second) 1.19.752.225 I slot print_timing: id 0 | task 1376 | total time = 1622.17 ms / 186 tokens 1.19.752.226 I slot print_timing: id 0 | task 1376 | graphs reused = 1004 1.19.752.227 I slot print_timing: id 0 | task 1376 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.752.279 I slot release: id 0 | task 1376 | stop processing: n_tokens = 1310, truncated = 0 1.19.785.622 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.875 1.19.785.734 I slot launch_slot_: id 0 | task 1472 | processing task, is_child = 0 1.20.286.983 I slot print_timing: id 1 | task 1427 | prompt eval time = 134.81 ms / 104 tokens ( 1.30 ms per token, 771.46 tokens per second) 1.20.286.988 I slot print_timing: id 1 | task 1427 | eval time = 1223.78 ms / 71 tokens ( 17.48 ms per token, 57.20 tokens per second) 1.20.286.989 I slot print_timing: id 1 | task 1427 | total time = 1358.59 ms / 175 tokens 1.20.286.990 I slot print_timing: id 1 | task 1427 | graphs reused = 1032 1.20.286.991 I slot print_timing: id 1 | task 1427 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.287.040 I slot release: id 1 | task 1427 | stop processing: n_tokens = 1299, truncated = 0 1.20.315.461 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.882 1.20.315.571 I slot launch_slot_: id 1 | task 1503 | processing task, is_child = 0 1.20.514.495 I slot print_timing: id 2 | task 1445 | prompt eval time = 129.70 ms / 98 tokens ( 1.32 ms per token, 755.61 tokens per second) 1.20.514.500 I slot print_timing: id 2 | task 1445 | eval time = 1085.36 ms / 61 tokens ( 18.09 ms per token, 55.28 tokens per second) 1.20.514.502 I slot print_timing: id 2 | task 1445 | total time = 1215.05 ms / 159 tokens 1.20.514.502 I slot print_timing: id 2 | task 1445 | graphs reused = 1035 1.20.514.503 I slot print_timing: id 2 | task 1445 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.514.553 I slot release: id 2 | task 1445 | stop processing: n_tokens = 1283, truncated = 0 1.20.570.452 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 1.20.570.567 I slot launch_slot_: id 2 | task 1512 | processing task, is_child = 0 1.21.085.685 I slot print_timing: id 3 | task 1373 | prompt eval time = 117.55 ms / 137 tokens ( 0.86 ms per token, 1165.50 tokens per second) 1.21.085.691 I slot print_timing: id 3 | task 1373 | eval time = 2955.77 ms / 160 tokens ( 18.59 ms per token, 53.79 tokens per second) 1.21.085.692 I slot print_timing: id 3 | task 1373 | total time = 3073.31 ms / 297 tokens 1.21.085.693 I slot print_timing: id 3 | task 1373 | graphs reused = 1060 1.21.085.693 I slot print_timing: id 3 | task 1373 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.085.744 I slot release: id 3 | task 1373 | stop processing: n_tokens = 1421, truncated = 0 1.21.129.541 I slot print_timing: id 0 | task 1472 | prompt eval time = 104.46 ms / 102 tokens ( 1.02 ms per token, 976.46 tokens per second) 1.21.129.547 I slot print_timing: id 0 | task 1472 | eval time = 1239.33 ms / 68 tokens ( 18.50 ms per token, 54.06 tokens per second) 1.21.129.548 I slot print_timing: id 0 | task 1472 | total time = 1343.79 ms / 170 tokens 1.21.129.549 I slot print_timing: id 0 | task 1472 | graphs reused = 1062 1.21.129.550 I slot print_timing: id 0 | task 1472 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.129.598 I slot release: id 0 | task 1472 | stop processing: n_tokens = 1294, truncated = 0 1.21.130.178 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.886 1.21.130.291 I slot launch_slot_: id 0 | task 1544 | processing task, is_child = 0 1.21.130.394 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.973 MiB) 1.21.131.947 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.537 MiB) 1.21.133.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 1.21.180.545 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.806 1.21.180.673 I slot launch_slot_: id 3 | task 1545 | processing task, is_child = 0 1.22.205.326 I slot print_timing: id 1 | task 1503 | prompt eval time = 134.77 ms / 108 tokens ( 1.25 ms per token, 801.37 tokens per second) 1.22.205.331 I slot print_timing: id 1 | task 1503 | eval time = 1754.97 ms / 100 tokens ( 17.73 ms per token, 56.41 tokens per second) 1.22.205.332 I slot print_timing: id 1 | task 1503 | total time = 1889.74 ms / 208 tokens 1.22.205.333 I slot print_timing: id 1 | task 1503 | graphs reused = 1120 1.22.205.334 I slot print_timing: id 1 | task 1503 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.205.383 I slot release: id 1 | task 1503 | stop processing: n_tokens = 1332, truncated = 0 1.22.232.774 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.860 1.22.232.876 I slot launch_slot_: id 1 | task 1609 | processing task, is_child = 0 1.22.361.042 I slot print_timing: id 2 | task 1512 | prompt eval time = 135.74 ms / 122 tokens ( 1.11 ms per token, 898.76 tokens per second) 1.22.361.047 I slot print_timing: id 2 | task 1512 | eval time = 1654.71 ms / 95 tokens ( 17.60 ms per token, 56.81 tokens per second) 1.22.361.048 I slot print_timing: id 2 | task 1512 | total time = 1790.46 ms / 217 tokens 1.22.361.049 I slot print_timing: id 2 | task 1512 | graphs reused = 1120 1.22.361.049 I slot print_timing: id 2 | task 1512 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.361.100 I slot release: id 2 | task 1512 | stop processing: n_tokens = 1341, truncated = 0 1.22.387.950 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.855 1.22.388.054 I slot launch_slot_: id 2 | task 1613 | processing task, is_child = 0 1.23.226.210 I slot print_timing: id 1 | task 1609 | prompt eval time = 127.90 ms / 86 tokens ( 1.49 ms per token, 672.38 tokens per second) 1.23.226.215 I slot print_timing: id 1 | task 1609 | eval time = 865.41 ms / 55 tokens ( 16.03 ms per token, 62.40 tokens per second) 1.23.226.217 I slot print_timing: id 1 | task 1609 | total time = 993.32 ms / 141 tokens 1.23.226.217 I slot print_timing: id 1 | task 1609 | graphs reused = 1170 1.23.226.218 I slot print_timing: id 1 | task 1609 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.226.265 I slot release: id 1 | task 1609 | stop processing: n_tokens = 1265, truncated = 0 1.23.226.675 I slot print_timing: id 3 | task 1545 | prompt eval time = 163.10 ms / 111 tokens ( 1.47 ms per token, 680.54 tokens per second) 1.23.226.678 I slot print_timing: id 3 | task 1545 | eval time = 1862.99 ms / 118 tokens ( 15.92 ms per token, 62.80 tokens per second) 1.23.226.679 I slot print_timing: id 3 | task 1545 | total time = 2026.09 ms / 229 tokens 1.23.226.680 I slot print_timing: id 3 | task 1545 | graphs reused = 1170 1.23.226.680 I slot print_timing: id 3 | task 1545 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.226.712 I slot release: id 3 | task 1545 | stop processing: n_tokens = 1353, truncated = 0 1.23.252.749 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.906 1.23.252.861 I slot launch_slot_: id 1 | task 1668 | processing task, is_child = 0 1.23.252.953 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.912 MiB) 1.23.254.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 1.23.298.971 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.847 1.23.299.100 I slot launch_slot_: id 3 | task 1669 | processing task, is_child = 0 1.24.192.743 I slot print_timing: id 2 | task 1613 | prompt eval time = 130.11 ms / 106 tokens ( 1.23 ms per token, 814.69 tokens per second) 1.24.192.749 I slot print_timing: id 2 | task 1613 | eval time = 1674.56 ms / 105 tokens ( 16.10 ms per token, 62.11 tokens per second) 1.24.192.750 I slot print_timing: id 2 | task 1613 | total time = 1804.67 ms / 211 tokens 1.24.192.751 I slot print_timing: id 2 | task 1613 | graphs reused = 1219 1.24.192.752 I slot print_timing: id 2 | task 1613 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.192.802 I slot release: id 2 | task 1613 | stop processing: n_tokens = 1335, truncated = 0 1.24.220.169 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.858 1.24.220.275 I slot launch_slot_: id 2 | task 1723 | processing task, is_child = 0 1.24.369.934 I slot print_timing: id 0 | task 1544 | n_gen = 175, tg = 57.86 t/s, tg_3s = 58.19 t/s 1.24.867.957 I slot print_timing: id 0 | task 1544 | prompt eval time = 181.85 ms / 124 tokens ( 1.47 ms per token, 681.89 tokens per second) 1.24.867.962 I slot print_timing: id 0 | task 1544 | eval time = 3505.42 ms / 211 tokens ( 16.69 ms per token, 59.91 tokens per second) 1.24.867.963 I slot print_timing: id 0 | task 1544 | total time = 3687.27 ms / 335 tokens 1.24.867.964 I slot print_timing: id 0 | task 1544 | graphs reused = 1255 1.24.867.965 I slot print_timing: id 0 | task 1544 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.868.014 I slot release: id 0 | task 1544 | stop processing: n_tokens = 1459, truncated = 0 1.24.899.793 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.785 1.24.899.895 I slot launch_slot_: id 0 | task 1765 | processing task, is_child = 0 1.25.188.226 I slot print_timing: id 3 | task 1669 | prompt eval time = 179.26 ms / 91 tokens ( 1.97 ms per token, 507.64 tokens per second) 1.25.188.232 I slot print_timing: id 3 | task 1669 | eval time = 1690.51 ms / 108 tokens ( 15.80 ms per token, 63.29 tokens per second) 1.25.188.233 I slot print_timing: id 3 | task 1669 | total time = 1869.77 ms / 199 tokens 1.25.188.233 I slot print_timing: id 3 | task 1669 | graphs reused = 1269 1.25.188.234 I slot print_timing: id 3 | task 1669 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.188.285 I slot release: id 3 | task 1669 | stop processing: n_tokens = 1323, truncated = 0 1.25.203.849 I slot print_timing: id 2 | task 1723 | prompt eval time = 133.02 ms / 121 tokens ( 1.10 ms per token, 909.64 tokens per second) 1.25.203.854 I slot print_timing: id 2 | task 1723 | eval time = 850.54 ms / 56 tokens ( 15.46 ms per token, 64.66 tokens per second) 1.25.203.855 I slot print_timing: id 2 | task 1723 | total time = 983.56 ms / 177 tokens 1.25.203.856 I slot print_timing: id 2 | task 1723 | graphs reused = 1269 1.25.203.857 I slot print_timing: id 2 | task 1723 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.203.903 I slot release: id 2 | task 1723 | stop processing: n_tokens = 1301, truncated = 0 1.25.218.491 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.881 1.25.218.595 I slot launch_slot_: id 2 | task 1783 | processing task, is_child = 0 1.25.218.691 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.754 MiB) 1.25.220.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.505 MiB) 1.25.221.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.754 MiB) 1.25.273.501 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.866 1.25.273.627 I slot launch_slot_: id 3 | task 1784 | processing task, is_child = 0 1.25.451.141 I slot print_timing: id 1 | task 1668 | prompt eval time = 197.78 ms / 98 tokens ( 2.02 ms per token, 495.50 tokens per second) 1.25.451.147 I slot print_timing: id 1 | task 1668 | eval time = 1954.24 ms / 112 tokens ( 17.61 ms per token, 56.80 tokens per second) 1.25.451.148 I slot print_timing: id 1 | task 1668 | total time = 2152.02 ms / 210 tokens 1.25.451.148 I slot print_timing: id 1 | task 1668 | graphs reused = 1269 1.25.451.149 I slot print_timing: id 1 | task 1668 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.451.198 I slot release: id 1 | task 1668 | stop processing: n_tokens = 1334, truncated = 0 1.25.505.455 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 1.25.505.554 I slot launch_slot_: id 1 | task 1789 | processing task, is_child = 0 1.26.505.420 I slot print_timing: id 0 | task 1765 | prompt eval time = 100.79 ms / 105 tokens ( 0.96 ms per token, 1041.73 tokens per second) 1.26.505.425 I slot print_timing: id 0 | task 1765 | eval time = 1504.72 ms / 84 tokens ( 18.13 ms per token, 55.16 tokens per second) 1.26.505.426 I slot print_timing: id 0 | task 1765 | total time = 1605.51 ms / 189 tokens 1.26.505.427 I slot print_timing: id 0 | task 1765 | graphs reused = 1329 1.26.505.428 I slot print_timing: id 0 | task 1765 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.505.477 I slot release: id 0 | task 1765 | stop processing: n_tokens = 1313, truncated = 0 1.26.537.215 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.873 1.26.537.320 I slot launch_slot_: id 0 | task 1856 | processing task, is_child = 0 1.26.728.491 I slot print_timing: id 2 | task 1783 | prompt eval time = 178.19 ms / 95 tokens ( 1.88 ms per token, 533.14 tokens per second) 1.26.728.496 I slot print_timing: id 2 | task 1783 | eval time = 1276.66 ms / 76 tokens ( 17.02 ms per token, 58.75 tokens per second) 1.26.728.498 I slot print_timing: id 2 | task 1783 | total time = 1454.85 ms / 171 tokens 1.26.728.498 I slot print_timing: id 2 | task 1783 | graphs reused = 1335 1.26.728.500 I slot print_timing: id 2 | task 1783 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.728.549 I slot release: id 2 | task 1783 | stop processing: n_tokens = 1295, truncated = 0 1.26.782.319 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.885 1.26.782.423 I slot launch_slot_: id 2 | task 1866 | processing task, is_child = 0 1.26.946.734 I slot print_timing: id 1 | task 1789 | prompt eval time = 131.41 ms / 110 tokens ( 1.19 ms per token, 837.08 tokens per second) 1.26.946.740 I slot print_timing: id 1 | task 1789 | eval time = 1309.75 ms / 78 tokens ( 17.01 ms per token, 58.79 tokens per second) 1.26.946.742 I slot print_timing: id 1 | task 1789 | total time = 1441.16 ms / 188 tokens 1.26.946.742 I slot print_timing: id 1 | task 1789 | graphs reused = 1336 1.26.946.743 I slot print_timing: id 1 | task 1789 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.946.798 I slot release: id 1 | task 1789 | stop processing: n_tokens = 1312, truncated = 0 1.26.974.334 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.873 1.26.974.438 I slot launch_slot_: id 1 | task 1872 | processing task, is_child = 0 1.27.624.801 I slot print_timing: id 3 | task 1784 | prompt eval time = 159.30 ms / 144 tokens ( 1.11 ms per token, 903.98 tokens per second) 1.27.624.807 I slot print_timing: id 3 | task 1784 | eval time = 2172.36 ms / 122 tokens ( 17.95 ms per token, 55.70 tokens per second) 1.27.624.807 I slot print_timing: id 3 | task 1784 | total time = 2331.66 ms / 266 tokens 1.27.624.808 I slot print_timing: id 3 | task 1784 | graphs reused = 1372 1.27.624.809 I slot print_timing: id 3 | task 1784 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.624.859 I slot release: id 3 | task 1784 | stop processing: n_tokens = 1390, truncated = 0 1.27.656.619 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.824 1.27.656.727 I slot launch_slot_: id 3 | task 1914 | processing task, is_child = 0 1.28.221.533 I slot print_timing: id 2 | task 1866 | prompt eval time = 131.00 ms / 115 tokens ( 1.14 ms per token, 877.90 tokens per second) 1.28.221.538 I slot print_timing: id 2 | task 1866 | eval time = 1308.10 ms / 80 tokens ( 16.56 ms per token, 60.39 tokens per second) 1.28.221.539 I slot print_timing: id 2 | task 1866 | total time = 1439.09 ms / 195 tokens 1.28.221.540 I slot print_timing: id 2 | task 1866 | graphs reused = 1405 1.28.221.541 I slot print_timing: id 2 | task 1866 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.221.591 I slot release: id 2 | task 1866 | stop processing: n_tokens = 1319, truncated = 0 1.28.248.874 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.869 1.28.248.985 I slot launch_slot_: id 2 | task 1951 | processing task, is_child = 0 1.28.687.124 I slot print_timing: id 3 | task 1914 | prompt eval time = 103.47 ms / 81 tokens ( 1.28 ms per token, 782.85 tokens per second) 1.28.687.129 I slot print_timing: id 3 | task 1914 | eval time = 926.91 ms / 58 tokens ( 16.26 ms per token, 61.49 tokens per second) 1.28.687.130 I slot print_timing: id 3 | task 1914 | total time = 1030.38 ms / 139 tokens 1.28.687.132 I slot print_timing: id 3 | task 1914 | graphs reused = 1425 1.28.687.133 I slot print_timing: id 3 | task 1914 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.687.187 I slot release: id 3 | task 1914 | stop processing: n_tokens = 1263, truncated = 0 1.28.703.134 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.907 1.28.703.241 I slot launch_slot_: id 3 | task 1976 | processing task, is_child = 0 1.29.638.661 I slot print_timing: id 2 | task 1951 | prompt eval time = 132.62 ms / 104 tokens ( 1.28 ms per token, 784.17 tokens per second) 1.29.638.667 I slot print_timing: id 2 | task 1951 | eval time = 1257.04 ms / 83 tokens ( 15.33 ms per token, 65.23 tokens per second) 1.29.638.668 I slot print_timing: id 2 | task 1951 | total time = 1389.66 ms / 187 tokens 1.29.638.669 I slot print_timing: id 2 | task 1951 | graphs reused = 1482 1.29.638.669 I slot print_timing: id 2 | task 1951 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.638.720 I slot release: id 2 | task 1951 | stop processing: n_tokens = 1311, truncated = 0 1.29.665.527 I slot print_timing: id 0 | task 1856 | n_gen = 175, tg = 57.75 t/s, tg_3s = 58.08 t/s 1.29.693.140 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.874 1.29.693.255 I slot launch_slot_: id 2 | task 2039 | processing task, is_child = 0 1.30.038.082 I slot print_timing: id 3 | task 1976 | prompt eval time = 112.16 ms / 125 tokens ( 0.90 ms per token, 1114.49 tokens per second) 1.30.038.088 I slot print_timing: id 3 | task 1976 | eval time = 1222.67 ms / 78 tokens ( 15.88 ms per token, 62.98 tokens per second) 1.30.038.089 I slot print_timing: id 3 | task 1976 | total time = 1334.83 ms / 203 tokens 1.30.038.090 I slot print_timing: id 3 | task 1976 | graphs reused = 1496 1.30.038.090 I slot print_timing: id 3 | task 1976 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.038.138 I slot release: id 3 | task 1976 | stop processing: n_tokens = 1327, truncated = 0 1.30.069.575 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.864 1.30.069.681 I slot launch_slot_: id 3 | task 2059 | processing task, is_child = 0 1.30.138.667 I slot print_timing: id 1 | task 1872 | n_gen = 182, tg = 59.73 t/s, tg_3s = 60.06 t/s 1.30.227.852 I slot print_timing: id 0 | task 1856 | prompt eval time = 114.99 ms / 158 tokens ( 0.73 ms per token, 1374.04 tokens per second) 1.30.227.857 I slot print_timing: id 0 | task 1856 | eval time = 3575.53 ms / 200 tokens ( 17.97 ms per token, 55.66 tokens per second) 1.30.227.858 I slot print_timing: id 0 | task 1856 | total time = 3690.52 ms / 358 tokens 1.30.227.859 I slot print_timing: id 0 | task 1856 | graphs reused = 1499 1.30.227.860 I slot print_timing: id 0 | task 1856 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.227.911 I slot release: id 0 | task 1856 | stop processing: n_tokens = 1482, truncated = 0 1.30.259.784 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.773 1.30.259.891 I slot launch_slot_: id 0 | task 2067 | processing task, is_child = 0 1.30.759.210 I slot print_timing: id 1 | task 1872 | prompt eval time = 133.71 ms / 128 tokens ( 1.04 ms per token, 957.30 tokens per second) 1.30.759.215 I slot print_timing: id 1 | task 1872 | eval time = 3651.05 ms / 218 tokens ( 16.83 ms per token, 59.43 tokens per second) 1.30.759.217 I slot print_timing: id 1 | task 1872 | total time = 3784.76 ms / 346 tokens 1.30.759.217 I slot print_timing: id 1 | task 1872 | graphs reused = 1528 1.30.759.218 I slot print_timing: id 1 | task 1872 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.759.265 I slot release: id 1 | task 1872 | stop processing: n_tokens = 1470, truncated = 0 1.30.786.732 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.782 1.30.786.842 I slot launch_slot_: id 1 | task 2099 | processing task, is_child = 0 1.31.414.019 I slot print_timing: id 3 | task 2059 | prompt eval time = 111.86 ms / 126 tokens ( 0.89 ms per token, 1126.42 tokens per second) 1.31.414.025 I slot print_timing: id 3 | task 2059 | eval time = 1232.46 ms / 74 tokens ( 16.88 ms per token, 59.23 tokens per second) 1.31.414.026 I slot print_timing: id 3 | task 2059 | total time = 1344.32 ms / 200 tokens 1.31.414.026 I slot print_timing: id 3 | task 2059 | graphs reused = 1562 1.31.414.027 I slot print_timing: id 3 | task 2059 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.414.076 I slot release: id 3 | task 2059 | stop processing: n_tokens = 1324, truncated = 0 1.31.445.929 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.866 1.31.446.036 I slot launch_slot_: id 3 | task 2139 | processing task, is_child = 0 1.32.157.503 I slot print_timing: id 1 | task 2099 | prompt eval time = 131.67 ms / 108 tokens ( 1.22 ms per token, 820.21 tokens per second) 1.32.157.509 I slot print_timing: id 1 | task 2099 | eval time = 1238.97 ms / 83 tokens ( 15.11 ms per token, 66.18 tokens per second) 1.32.157.510 I slot print_timing: id 1 | task 2099 | total time = 1370.64 ms / 191 tokens 1.32.157.511 I slot print_timing: id 1 | task 2099 | graphs reused = 1605 1.32.157.512 I slot print_timing: id 1 | task 2099 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.157.565 I slot release: id 1 | task 2099 | stop processing: n_tokens = 1315, truncated = 0 1.32.185.190 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.871 1.32.185.292 I slot launch_slot_: id 1 | task 2186 | processing task, is_child = 0 1.32.673.121 I slot print_timing: id 3 | task 2139 | prompt eval time = 106.98 ms / 100 tokens ( 1.07 ms per token, 934.79 tokens per second) 1.32.673.126 I slot print_timing: id 3 | task 2139 | eval time = 1120.09 ms / 71 tokens ( 16.00 ms per token, 62.49 tokens per second) 1.32.673.127 I slot print_timing: id 3 | task 2139 | total time = 1227.07 ms / 171 tokens 1.32.673.129 I slot print_timing: id 3 | task 2139 | graphs reused = 1628 1.32.673.129 I slot print_timing: id 3 | task 2139 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.673.178 I slot release: id 3 | task 2139 | stop processing: n_tokens = 1295, truncated = 0 1.32.704.608 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.885 1.32.704.717 I slot launch_slot_: id 3 | task 2215 | processing task, is_child = 0 1.32.827.907 I slot print_timing: id 2 | task 2039 | n_gen = 172, tg = 56.93 t/s, tg_3s = 57.27 t/s 1.32.898.968 I slot print_timing: id 0 | task 2067 | prompt eval time = 105.91 ms / 125 tokens ( 0.85 ms per token, 1180.27 tokens per second) 1.32.898.974 I slot print_timing: id 0 | task 2067 | eval time = 2533.16 ms / 151 tokens ( 16.89 ms per token, 59.21 tokens per second) 1.32.898.975 I slot print_timing: id 0 | task 2067 | total time = 2639.06 ms / 276 tokens 1.32.898.976 I slot print_timing: id 0 | task 2067 | graphs reused = 1634 1.32.898.977 I slot print_timing: id 0 | task 2067 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.899.025 I slot release: id 0 | task 2067 | stop processing: n_tokens = 1400, truncated = 0 1.32.943.302 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.949 (> 0.100 thold), f_keep = 0.819 1.32.943.408 I slot launch_slot_: id 0 | task 2227 | processing task, is_child = 0 1.33.002.814 I slot print_timing: id 2 | task 2039 | prompt eval time = 131.06 ms / 103 tokens ( 1.27 ms per token, 785.87 tokens per second) 1.33.002.820 I slot print_timing: id 2 | task 2039 | eval time = 3178.48 ms / 181 tokens ( 17.66 ms per token, 56.63 tokens per second) 1.33.002.821 I slot print_timing: id 2 | task 2039 | total time = 3309.54 ms / 284 tokens 1.33.002.822 I slot print_timing: id 2 | task 2039 | graphs reused = 1637 1.33.002.823 I slot print_timing: id 2 | task 2039 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.002.871 I slot release: id 2 | task 2039 | stop processing: n_tokens = 1408, truncated = 0 1.33.055.331 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.814 1.33.055.443 I slot launch_slot_: id 2 | task 2230 | processing task, is_child = 0 1.33.429.820 I slot print_timing: id 1 | task 2186 | prompt eval time = 148.62 ms / 171 tokens ( 0.87 ms per token, 1150.55 tokens per second) 1.33.429.826 I slot print_timing: id 1 | task 2186 | eval time = 1095.89 ms / 59 tokens ( 18.89 ms per token, 52.93 tokens per second) 1.33.429.827 I slot print_timing: id 1 | task 2186 | total time = 1244.51 ms / 230 tokens 1.33.429.829 I slot print_timing: id 1 | task 2186 | graphs reused = 1653 1.33.429.830 I slot print_timing: id 1 | task 2186 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.429.884 I slot release: id 1 | task 2186 | stop processing: n_tokens = 1354, truncated = 0 1.33.484.461 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.846 1.33.484.572 I slot launch_slot_: id 1 | task 2252 | processing task, is_child = 0 1.34.095.533 I slot print_timing: id 0 | task 2227 | prompt eval time = 111.33 ms / 82 tokens ( 1.36 ms per token, 736.58 tokens per second) 1.34.095.538 I slot print_timing: id 0 | task 2227 | eval time = 1040.79 ms / 58 tokens ( 18.26 ms per token, 54.77 tokens per second) 1.34.095.539 I slot print_timing: id 0 | task 2227 | total time = 1152.11 ms / 140 tokens 1.34.095.540 I slot print_timing: id 0 | task 2227 | graphs reused = 1685 1.34.095.541 I slot print_timing: id 0 | task 2227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.095.590 I slot release: id 0 | task 2227 | stop processing: n_tokens = 1264, truncated = 0 1.34.112.120 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.907 1.34.112.220 I slot launch_slot_: id 0 | task 2290 | processing task, is_child = 0 1.34.406.231 I slot print_timing: id 2 | task 2230 | prompt eval time = 131.42 ms / 114 tokens ( 1.15 ms per token, 867.45 tokens per second) 1.34.406.237 I slot print_timing: id 2 | task 2230 | eval time = 1219.35 ms / 72 tokens ( 17.17 ms per token, 58.23 tokens per second) 1.34.406.238 I slot print_timing: id 2 | task 2230 | total time = 1350.77 ms / 186 tokens 1.34.406.239 I slot print_timing: id 2 | task 2230 | graphs reused = 1698 1.34.406.239 I slot print_timing: id 2 | task 2230 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.406.289 I slot release: id 2 | task 2230 | stop processing: n_tokens = 1310, truncated = 0 1.34.406.509 I slot print_timing: id 3 | task 2215 | prompt eval time = 106.37 ms / 89 tokens ( 1.20 ms per token, 836.68 tokens per second) 1.34.406.512 I slot print_timing: id 3 | task 2215 | eval time = 1595.41 ms / 85 tokens ( 18.99 ms per token, 52.65 tokens per second) 1.34.406.513 I slot print_timing: id 3 | task 2215 | total time = 1701.78 ms / 174 tokens 1.34.406.514 I slot print_timing: id 3 | task 2215 | graphs reused = 1698 1.34.406.514 I slot print_timing: id 3 | task 2215 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.406.544 I slot release: id 3 | task 2215 | stop processing: n_tokens = 1298, truncated = 0 1.34.435.502 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.875 1.34.435.612 I slot launch_slot_: id 2 | task 2308 | processing task, is_child = 0 1.34.435.703 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.723 MiB) 1.34.437.260 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 1.34.438.846 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.162 MiB) 1.34.488.882 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.883 1.34.489.008 I slot launch_slot_: id 3 | task 2309 | processing task, is_child = 0 1.34.812.556 I slot print_timing: id 1 | task 2252 | prompt eval time = 128.44 ms / 98 tokens ( 1.31 ms per token, 763.01 tokens per second) 1.34.812.561 I slot print_timing: id 1 | task 2252 | eval time = 1199.53 ms / 65 tokens ( 18.74 ms per token, 53.35 tokens per second) 1.34.812.562 I slot print_timing: id 1 | task 2252 | total time = 1327.97 ms / 163 tokens 1.34.812.563 I slot print_timing: id 1 | task 2252 | graphs reused = 1707 1.34.812.564 I slot print_timing: id 1 | task 2252 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.812.611 I slot release: id 1 | task 2252 | stop processing: n_tokens = 1287, truncated = 0 1.34.866.678 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.890 1.34.866.793 I slot launch_slot_: id 1 | task 2324 | processing task, is_child = 0 1.35.745.593 I slot print_timing: id 3 | task 2309 | prompt eval time = 155.44 ms / 113 tokens ( 1.38 ms per token, 726.97 tokens per second) 1.35.745.599 I slot print_timing: id 3 | task 2309 | eval time = 1081.24 ms / 67 tokens ( 16.38 ms per token, 61.04 tokens per second) 1.35.745.600 I slot print_timing: id 3 | task 2309 | total time = 1236.68 ms / 180 tokens 1.35.745.602 I slot print_timing: id 3 | task 2309 | graphs reused = 1757 1.35.745.603 I slot print_timing: id 3 | task 2309 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.745.654 I slot release: id 3 | task 2309 | stop processing: n_tokens = 1304, truncated = 0 1.35.791.389 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.879 1.35.791.515 I slot launch_slot_: id 3 | task 2382 | processing task, is_child = 0 1.35.995.338 I slot print_timing: id 2 | task 2308 | prompt eval time = 174.77 ms / 97 tokens ( 1.80 ms per token, 555.02 tokens per second) 1.35.995.343 I slot print_timing: id 2 | task 2308 | eval time = 1331.54 ms / 77 tokens ( 17.52 ms per token, 57.08 tokens per second) 1.35.995.344 I slot print_timing: id 2 | task 2308 | total time = 1506.31 ms / 174 tokens 1.35.995.345 I slot print_timing: id 2 | task 2308 | graphs reused = 1763 1.35.995.346 I slot print_timing: id 2 | task 2308 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.995.397 I slot release: id 2 | task 2308 | stop processing: n_tokens = 1298, truncated = 0 1.36.052.293 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.883 1.36.052.407 I slot launch_slot_: id 2 | task 2392 | processing task, is_child = 0 1.36.451.291 I slot print_timing: id 1 | task 2324 | prompt eval time = 138.11 ms / 119 tokens ( 1.16 ms per token, 861.64 tokens per second) 1.36.451.297 I slot print_timing: id 1 | task 2324 | eval time = 1446.38 ms / 85 tokens ( 17.22 ms per token, 58.08 tokens per second) 1.36.451.298 I slot print_timing: id 1 | task 2324 | total time = 1584.48 ms / 204 tokens 1.36.451.299 I slot print_timing: id 1 | task 2324 | graphs reused = 1780 1.36.451.299 I slot print_timing: id 1 | task 2324 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.451.351 I slot release: id 1 | task 2324 | stop processing: n_tokens = 1328, truncated = 0 1.36.479.454 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.864 1.36.479.577 I slot launch_slot_: id 1 | task 2414 | processing task, is_child = 0 1.37.095.264 I slot print_timing: id 0 | task 2290 | prompt eval time = 105.41 ms / 109 tokens ( 0.97 ms per token, 1034.07 tokens per second) 1.37.095.269 I slot print_timing: id 0 | task 2290 | eval time = 2877.62 ms / 153 tokens ( 18.93 ms per token, 52.82 tokens per second) 1.37.095.270 I slot print_timing: id 0 | task 2290 | total time = 2983.03 ms / 262 tokens 1.37.095.271 I slot print_timing: id 0 | task 2290 | graphs reused = 1813 1.37.095.272 I slot print_timing: id 0 | task 2290 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.095.321 I slot release: id 0 | task 2290 | stop processing: n_tokens = 1386, truncated = 0 1.37.127.499 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.827 1.37.127.609 I slot launch_slot_: id 0 | task 2453 | processing task, is_child = 0 1.37.936.126 I slot print_timing: id 1 | task 2414 | prompt eval time = 133.62 ms / 109 tokens ( 1.23 ms per token, 815.77 tokens per second) 1.37.936.131 I slot print_timing: id 1 | task 2414 | eval time = 1322.91 ms / 89 tokens ( 15.03 ms per token, 66.52 tokens per second) 1.37.936.132 I slot print_timing: id 1 | task 2414 | total time = 1456.53 ms / 198 tokens 1.37.936.133 I slot print_timing: id 1 | task 2414 | graphs reused = 1864 1.37.936.133 I slot print_timing: id 1 | task 2414 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.936.193 I slot release: id 1 | task 2414 | stop processing: n_tokens = 1322, truncated = 0 1.37.964.235 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.867 1.37.964.354 I slot launch_slot_: id 1 | task 2507 | processing task, is_child = 0 1.38.403.725 I slot print_timing: id 0 | task 2453 | prompt eval time = 100.50 ms / 95 tokens ( 1.06 ms per token, 945.25 tokens per second) 1.38.403.730 I slot print_timing: id 0 | task 2453 | eval time = 1175.60 ms / 75 tokens ( 15.89 ms per token, 62.95 tokens per second) 1.38.403.731 I slot print_timing: id 0 | task 2453 | total time = 1276.10 ms / 170 tokens 1.38.403.732 I slot print_timing: id 0 | task 2453 | graphs reused = 1884 1.38.403.733 I slot print_timing: id 0 | task 2453 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.403.783 I slot release: id 0 | task 2453 | stop processing: n_tokens = 1294, truncated = 0 1.38.420.572 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.886 1.38.420.686 I slot launch_slot_: id 0 | task 2532 | processing task, is_child = 0 1.38.550.685 I slot print_timing: id 2 | task 2392 | prompt eval time = 135.14 ms / 112 tokens ( 1.21 ms per token, 828.76 tokens per second) 1.38.550.691 I slot print_timing: id 2 | task 2392 | eval time = 2363.12 ms / 138 tokens ( 17.25 ms per token, 57.97 tokens per second) 1.38.550.692 I slot print_timing: id 2 | task 2392 | total time = 2498.26 ms / 250 tokens 1.38.550.693 I slot print_timing: id 2 | task 2392 | graphs reused = 1885 1.38.550.694 I slot print_timing: id 2 | task 2392 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.550.752 I slot release: id 2 | task 2392 | stop processing: n_tokens = 1374, truncated = 0 1.38.606.933 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.834 1.38.607.058 I slot launch_slot_: id 2 | task 2538 | processing task, is_child = 0 1.38.924.812 I slot print_timing: id 3 | task 2382 | n_gen = 162, tg = 53.53 t/s, tg_3s = 53.86 t/s 1.38.953.060 I slot print_timing: id 3 | task 2382 | prompt eval time = 125.42 ms / 134 tokens ( 0.94 ms per token, 1068.37 tokens per second) 1.38.953.065 I slot print_timing: id 3 | task 2382 | eval time = 3036.10 ms / 164 tokens ( 18.63 ms per token, 53.69 tokens per second) 1.38.953.066 I slot print_timing: id 3 | task 2382 | total time = 3161.53 ms / 298 tokens 1.38.953.068 I slot print_timing: id 3 | task 2382 | graphs reused = 1897 1.38.953.068 I slot print_timing: id 3 | task 2382 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.953.119 I slot release: id 3 | task 2382 | stop processing: n_tokens = 1422, truncated = 0 1.38.999.045 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.806 1.38.999.155 I slot launch_slot_: id 3 | task 2557 | processing task, is_child = 0 1.39.742.959 I slot print_timing: id 1 | task 2507 | prompt eval time = 130.88 ms / 96 tokens ( 1.36 ms per token, 733.49 tokens per second) 1.39.742.964 I slot print_timing: id 1 | task 2507 | eval time = 1647.70 ms / 91 tokens ( 18.31 ms per token, 54.62 tokens per second) 1.39.742.965 I slot print_timing: id 1 | task 2507 | total time = 1778.59 ms / 187 tokens 1.39.742.966 I slot print_timing: id 1 | task 2507 | graphs reused = 1941 1.39.742.967 I slot print_timing: id 1 | task 2507 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.743.019 I slot release: id 1 | task 2507 | stop processing: n_tokens = 1311, truncated = 0 1.39.799.173 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.874 1.39.799.295 I slot launch_slot_: id 1 | task 2605 | processing task, is_child = 0 1.40.598.414 I slot print_timing: id 2 | task 2538 | prompt eval time = 150.40 ms / 166 tokens ( 0.91 ms per token, 1103.71 tokens per second) 1.40.598.420 I slot print_timing: id 2 | task 2538 | eval time = 1840.93 ms / 111 tokens ( 16.74 ms per token, 59.75 tokens per second) 1.40.598.421 I slot print_timing: id 2 | task 2538 | total time = 1991.34 ms / 277 tokens 1.40.598.422 I slot print_timing: id 2 | task 2538 | graphs reused = 1985 1.40.598.423 I slot print_timing: id 2 | task 2538 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.598.479 I slot release: id 2 | task 2538 | stop processing: n_tokens = 1401, truncated = 0 1.40.625.502 I slot print_timing: id 0 | task 2532 | prompt eval time = 111.27 ms / 122 tokens ( 0.91 ms per token, 1096.46 tokens per second) 1.40.625.508 I slot print_timing: id 0 | task 2532 | eval time = 2093.53 ms / 117 tokens ( 18.05 ms per token, 55.41 tokens per second) 1.40.625.509 I slot print_timing: id 0 | task 2532 | total time = 2204.80 ms / 239 tokens 1.40.625.510 I slot print_timing: id 0 | task 2532 | graphs reused = 1985 1.40.625.510 I slot print_timing: id 0 | task 2532 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.625.559 I slot release: id 0 | task 2532 | stop processing: n_tokens = 1363, truncated = 0 1.40.651.945 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.841 1.40.652.059 I slot launch_slot_: id 0 | task 2655 | processing task, is_child = 0 1.40.652.160 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.912 MiB) 1.40.653.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.005 MiB) 1.40.655.382 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 1.40.705.645 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.818 1.40.705.778 I slot launch_slot_: id 2 | task 2656 | processing task, is_child = 0 1.41.502.221 I slot print_timing: id 3 | task 2557 | prompt eval time = 113.08 ms / 117 tokens ( 0.97 ms per token, 1034.69 tokens per second) 1.41.502.228 I slot print_timing: id 3 | task 2557 | eval time = 2389.97 ms / 138 tokens ( 17.45 ms per token, 57.32 tokens per second) 1.41.502.229 I slot print_timing: id 3 | task 2557 | total time = 2503.05 ms / 255 tokens 1.41.502.229 I slot print_timing: id 3 | task 2557 | graphs reused = 2025 1.41.502.230 I slot print_timing: id 3 | task 2557 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.502.291 I slot release: id 3 | task 2557 | stop processing: n_tokens = 1379, truncated = 0 1.41.533.951 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.831 1.41.534.062 I slot launch_slot_: id 3 | task 2702 | processing task, is_child = 0 1.41.777.053 I slot print_timing: id 1 | task 2605 | prompt eval time = 133.58 ms / 104 tokens ( 1.28 ms per token, 778.57 tokens per second) 1.41.777.059 I slot print_timing: id 1 | task 2605 | eval time = 1844.16 ms / 104 tokens ( 17.90 ms per token, 55.85 tokens per second) 1.41.777.060 I slot print_timing: id 1 | task 2605 | total time = 1977.74 ms / 208 tokens 1.41.777.062 I slot print_timing: id 1 | task 2605 | graphs reused = 2034 1.41.777.063 I slot print_timing: id 1 | task 2605 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.777.117 I slot release: id 1 | task 2605 | stop processing: n_tokens = 1332, truncated = 0 1.41.805.134 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.860 1.41.805.261 I slot launch_slot_: id 1 | task 2715 | processing task, is_child = 0 1.43.118.422 I slot print_timing: id 0 | task 2655 | prompt eval time = 207.46 ms / 108 tokens ( 1.92 ms per token, 520.59 tokens per second) 1.43.118.428 I slot print_timing: id 0 | task 2655 | eval time = 2205.17 ms / 139 tokens ( 15.98 ms per token, 62.58 tokens per second) 1.43.118.429 I slot print_timing: id 0 | task 2655 | total time = 2412.62 ms / 247 tokens 1.43.118.430 I slot print_timing: id 0 | task 2655 | graphs reused = 2114 1.43.118.431 I slot print_timing: id 0 | task 2655 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.118.483 I slot release: id 0 | task 2655 | stop processing: n_tokens = 1371, truncated = 0 1.43.135.149 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.836 1.43.135.257 I slot launch_slot_: id 0 | task 2800 | processing task, is_child = 0 1.43.246.925 I slot print_timing: id 3 | task 2702 | prompt eval time = 111.41 ms / 112 tokens ( 0.99 ms per token, 1005.34 tokens per second) 1.43.246.931 I slot print_timing: id 3 | task 2702 | eval time = 1601.44 ms / 97 tokens ( 16.68 ms per token, 59.95 tokens per second) 1.43.246.932 I slot print_timing: id 3 | task 2702 | total time = 1712.85 ms / 209 tokens 1.43.246.933 I slot print_timing: id 3 | task 2702 | graphs reused = 2115 1.43.246.934 I slot print_timing: id 3 | task 2702 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.246.984 I slot release: id 3 | task 2702 | stop processing: n_tokens = 1333, truncated = 0 1.43.277.482 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.860 1.43.277.592 I slot launch_slot_: id 3 | task 2805 | processing task, is_child = 0 1.43.351.149 I slot print_timing: id 1 | task 2715 | prompt eval time = 132.54 ms / 116 tokens ( 1.14 ms per token, 875.19 tokens per second) 1.43.351.155 I slot print_timing: id 1 | task 2715 | eval time = 1413.33 ms / 88 tokens ( 16.25 ms per token, 61.56 tokens per second) 1.43.351.156 I slot print_timing: id 1 | task 2715 | total time = 1545.87 ms / 204 tokens 1.43.351.158 I slot print_timing: id 1 | task 2715 | graphs reused = 2116 1.43.351.159 I slot print_timing: id 1 | task 2715 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.351.212 I slot release: id 1 | task 2715 | stop processing: n_tokens = 1328, truncated = 0 1.43.405.552 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.863 1.43.405.665 I slot launch_slot_: id 1 | task 2808 | processing task, is_child = 0 1.43.926.566 I slot print_timing: id 2 | task 2656 | n_gen = 174, tg = 57.43 t/s, tg_3s = 57.76 t/s 1.44.795.298 I slot print_timing: id 1 | task 2808 | prompt eval time = 135.83 ms / 103 tokens ( 1.32 ms per token, 758.28 tokens per second) 1.44.795.305 I slot print_timing: id 1 | task 2808 | eval time = 1253.78 ms / 87 tokens ( 14.58 ms per token, 68.59 tokens per second) 1.44.795.306 I slot print_timing: id 1 | task 2808 | total time = 1389.61 ms / 190 tokens 1.44.795.308 I slot print_timing: id 1 | task 2808 | graphs reused = 2201 1.44.795.309 I slot print_timing: id 1 | task 2808 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.795.366 I slot release: id 1 | task 2808 | stop processing: n_tokens = 1314, truncated = 0 1.44.822.792 I slot print_timing: id 2 | task 2656 | prompt eval time = 189.11 ms / 133 tokens ( 1.42 ms per token, 703.31 tokens per second) 1.44.822.798 I slot print_timing: id 2 | task 2656 | eval time = 3908.57 ms / 235 tokens ( 16.70 ms per token, 59.87 tokens per second) 1.44.822.798 I slot print_timing: id 2 | task 2656 | total time = 4097.68 ms / 368 tokens 1.44.822.799 I slot print_timing: id 2 | task 2656 | graphs reused = 2201 1.44.822.800 I slot print_timing: id 2 | task 2656 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.822.848 I slot release: id 2 | task 2656 | stop processing: n_tokens = 1492, truncated = 0 1.44.823.139 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.872 1.44.823.251 I slot launch_slot_: id 1 | task 2898 | processing task, is_child = 0 1.44.823.352 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 1.44.824.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.504 MiB) 1.44.826.737 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 1.44.876.442 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.768 1.44.876.571 I slot launch_slot_: id 2 | task 2899 | processing task, is_child = 0 1.45.217.619 I slot print_timing: id 3 | task 2805 | prompt eval time = 127.94 ms / 119 tokens ( 1.08 ms per token, 930.15 tokens per second) 1.45.217.625 I slot print_timing: id 3 | task 2805 | eval time = 1812.08 ms / 102 tokens ( 17.94 ms per token, 55.74 tokens per second) 1.45.217.626 I slot print_timing: id 3 | task 2805 | total time = 1940.01 ms / 221 tokens 1.45.217.628 I slot print_timing: id 3 | task 2805 | graphs reused = 2210 1.45.217.629 I slot print_timing: id 3 | task 2805 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.217.678 I slot release: id 3 | task 2805 | stop processing: n_tokens = 1345, truncated = 0 1.45.233.564 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.852 1.45.233.668 I slot launch_slot_: id 3 | task 2913 | processing task, is_child = 0 1.45.443.152 I slot print_timing: id 0 | task 2800 | prompt eval time = 110.74 ms / 119 tokens ( 0.93 ms per token, 1074.55 tokens per second) 1.45.443.157 I slot print_timing: id 0 | task 2800 | eval time = 2197.13 ms / 116 tokens ( 19.11 ms per token, 52.34 tokens per second) 1.45.443.158 I slot print_timing: id 0 | task 2800 | total time = 2307.88 ms / 235 tokens 1.45.443.159 I slot print_timing: id 0 | task 2800 | graphs reused = 2216 1.45.443.159 I slot print_timing: id 0 | task 2800 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.443.208 I slot release: id 0 | task 2800 | stop processing: n_tokens = 1359, truncated = 0 1.45.459.772 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.843 1.45.459.884 I slot launch_slot_: id 0 | task 2924 | processing task, is_child = 0 1.46.424.594 I slot print_timing: id 3 | task 2913 | prompt eval time = 107.61 ms / 97 tokens ( 1.11 ms per token, 901.36 tokens per second) 1.46.424.599 I slot print_timing: id 3 | task 2913 | eval time = 1083.29 ms / 71 tokens ( 15.48 ms per token, 64.62 tokens per second) 1.46.424.601 I slot print_timing: id 3 | task 2913 | total time = 1190.91 ms / 168 tokens 1.46.424.602 I slot print_timing: id 3 | task 2913 | graphs reused = 2275 1.46.424.603 I slot print_timing: id 3 | task 2913 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.424.654 I slot release: id 3 | task 2913 | stop processing: n_tokens = 1292, truncated = 0 1.46.456.360 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.887 1.46.456.473 I slot launch_slot_: id 3 | task 2989 | processing task, is_child = 0 1.46.664.131 I slot print_timing: id 2 | task 2899 | prompt eval time = 177.08 ms / 108 tokens ( 1.64 ms per token, 609.91 tokens per second) 1.46.664.137 I slot print_timing: id 2 | task 2899 | eval time = 1591.01 ms / 93 tokens ( 17.29 ms per token, 57.82 tokens per second) 1.46.664.138 I slot print_timing: id 2 | task 2899 | total time = 1768.09 ms / 201 tokens 1.46.664.139 I slot print_timing: id 2 | task 2899 | graphs reused = 2280 1.46.664.140 I slot print_timing: id 2 | task 2899 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.664.192 I slot release: id 2 | task 2899 | stop processing: n_tokens = 1325, truncated = 0 1.46.692.086 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.865 1.46.692.197 I slot launch_slot_: id 2 | task 2998 | processing task, is_child = 0 1.46.846.469 I slot print_timing: id 0 | task 2924 | prompt eval time = 103.12 ms / 100 tokens ( 1.03 ms per token, 969.73 tokens per second) 1.46.846.474 I slot print_timing: id 0 | task 2924 | eval time = 1283.45 ms / 74 tokens ( 17.58 ms per token, 56.88 tokens per second) 1.46.846.476 I slot print_timing: id 0 | task 2924 | total time = 1386.57 ms / 174 tokens 1.46.846.476 I slot print_timing: id 0 | task 2924 | graphs reused = 2280 1.46.846.477 I slot print_timing: id 0 | task 2924 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.846.527 I slot release: id 0 | task 2924 | stop processing: n_tokens = 1298, truncated = 0 1.46.880.006 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.883 1.46.880.119 I slot launch_slot_: id 0 | task 3004 | processing task, is_child = 0 1.48.081.970 I slot print_timing: id 1 | task 2898 | n_gen = 176, tg = 58.15 t/s, tg_3s = 58.48 t/s 1.48.341.533 I slot print_timing: id 0 | task 3004 | prompt eval time = 108.08 ms / 114 tokens ( 0.95 ms per token, 1054.76 tokens per second) 1.48.341.539 I slot print_timing: id 0 | task 3004 | eval time = 1353.32 ms / 94 tokens ( 14.55 ms per token, 68.72 tokens per second) 1.48.341.540 I slot print_timing: id 0 | task 3004 | total time = 1461.40 ms / 208 tokens 1.48.341.541 I slot print_timing: id 0 | task 3004 | graphs reused = 2374 1.48.341.542 I slot print_timing: id 0 | task 3004 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.341.591 I slot release: id 0 | task 3004 | stop processing: n_tokens = 1332, truncated = 0 1.48.374.353 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.860 1.48.374.465 I slot launch_slot_: id 0 | task 3102 | processing task, is_child = 0 1.48.499.354 I slot print_timing: id 1 | task 2898 | prompt eval time = 195.97 ms / 120 tokens ( 1.63 ms per token, 612.33 tokens per second) 1.48.499.360 I slot print_timing: id 1 | task 2898 | eval time = 3426.79 ms / 199 tokens ( 17.31 ms per token, 57.78 tokens per second) 1.48.499.361 I slot print_timing: id 1 | task 2898 | total time = 3622.76 ms / 319 tokens 1.48.499.362 I slot print_timing: id 1 | task 2898 | graphs reused = 2376 1.48.499.362 I slot print_timing: id 1 | task 2898 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.499.414 I slot release: id 1 | task 2898 | stop processing: n_tokens = 1443, truncated = 0 1.48.527.990 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.794 1.48.528.102 I slot launch_slot_: id 1 | task 3107 | processing task, is_child = 0 1.49.371.230 I slot print_timing: id 2 | task 2998 | prompt eval time = 137.00 ms / 119 tokens ( 1.15 ms per token, 868.61 tokens per second) 1.49.371.235 I slot print_timing: id 2 | task 2998 | eval time = 2542.02 ms / 157 tokens ( 16.29 ms per token, 61.37 tokens per second) 1.49.371.236 I slot print_timing: id 2 | task 2998 | total time = 2679.02 ms / 276 tokens 1.49.371.237 I slot print_timing: id 2 | task 2998 | graphs reused = 2425 1.49.371.238 I slot print_timing: id 2 | task 2998 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.371.289 I slot release: id 2 | task 2998 | stop processing: n_tokens = 1400, truncated = 0 1.49.398.613 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.819 1.49.398.719 I slot launch_slot_: id 2 | task 3161 | processing task, is_child = 0 1.49.560.860 I slot print_timing: id 3 | task 2989 | prompt eval time = 129.93 ms / 172 tokens ( 0.76 ms per token, 1323.80 tokens per second) 1.49.560.866 I slot print_timing: id 3 | task 2989 | eval time = 2974.44 ms / 170 tokens ( 17.60 ms per token, 56.82 tokens per second) 1.49.560.867 I slot print_timing: id 3 | task 2989 | total time = 3104.37 ms / 342 tokens 1.49.560.868 I slot print_timing: id 3 | task 2989 | graphs reused = 2426 1.49.560.869 I slot print_timing: id 3 | task 2989 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.560.924 I slot release: id 3 | task 2989 | stop processing: n_tokens = 1466, truncated = 0 1.49.592.392 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.782 1.49.592.504 I slot launch_slot_: id 3 | task 3168 | processing task, is_child = 0 1.49.866.105 I slot print_timing: id 0 | task 3102 | prompt eval time = 106.60 ms / 104 tokens ( 1.02 ms per token, 975.65 tokens per second) 1.49.866.111 I slot print_timing: id 0 | task 3102 | eval time = 1385.03 ms / 75 tokens ( 18.72 ms per token, 53.43 tokens per second) 1.49.866.112 I slot print_timing: id 0 | task 3102 | total time = 1491.62 ms / 179 tokens 1.49.866.113 I slot print_timing: id 0 | task 3102 | graphs reused = 2437 1.49.866.114 I slot print_timing: id 0 | task 3102 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.866.165 I slot release: id 0 | task 3102 | stop processing: n_tokens = 1303, truncated = 0 1.49.898.570 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.880 1.49.898.684 I slot launch_slot_: id 0 | task 3184 | processing task, is_child = 0 1.50.332.852 I slot print_timing: id 1 | task 3107 | prompt eval time = 133.76 ms / 117 tokens ( 1.14 ms per token, 874.67 tokens per second) 1.50.332.857 I slot print_timing: id 1 | task 3107 | eval time = 1670.97 ms / 98 tokens ( 17.23 ms per token, 58.05 tokens per second) 1.50.332.858 I slot print_timing: id 1 | task 3107 | total time = 1804.73 ms / 215 tokens 1.50.332.859 I slot print_timing: id 1 | task 3107 | graphs reused = 2461 1.50.332.860 I slot print_timing: id 1 | task 3107 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.332.911 I slot release: id 1 | task 3107 | stop processing: n_tokens = 1339, truncated = 0 1.50.388.933 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.856 1.50.389.060 I slot launch_slot_: id 1 | task 3212 | processing task, is_child = 0 1.50.936.266 I slot print_timing: id 2 | task 3161 | prompt eval time = 128.38 ms / 88 tokens ( 1.46 ms per token, 685.44 tokens per second) 1.50.936.273 I slot print_timing: id 2 | task 3161 | eval time = 1409.14 ms / 76 tokens ( 18.79 ms per token, 53.22 tokens per second) 1.50.936.274 I slot print_timing: id 2 | task 3161 | total time = 1537.53 ms / 164 tokens 1.50.936.275 I slot print_timing: id 2 | task 3161 | graphs reused = 2487 1.50.936.276 I slot print_timing: id 2 | task 3161 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.936.332 I slot release: id 2 | task 3161 | stop processing: n_tokens = 1288, truncated = 0 1.50.991.178 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.890 1.50.991.290 I slot launch_slot_: id 2 | task 3244 | processing task, is_child = 0 1.51.330.594 I slot print_timing: id 0 | task 3184 | prompt eval time = 98.34 ms / 87 tokens ( 1.13 ms per token, 884.67 tokens per second) 1.51.330.600 I slot print_timing: id 0 | task 3184 | eval time = 1333.55 ms / 73 tokens ( 18.52 ms per token, 53.99 tokens per second) 1.51.330.601 I slot print_timing: id 0 | task 3184 | total time = 1431.89 ms / 160 tokens 1.51.330.602 I slot print_timing: id 0 | task 3184 | graphs reused = 2500 1.51.330.603 I slot print_timing: id 0 | task 3184 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.330.653 I slot release: id 0 | task 3184 | stop processing: n_tokens = 1284, truncated = 0 1.51.364.574 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.893 1.51.364.697 I slot launch_slot_: id 0 | task 3263 | processing task, is_child = 0 1.51.844.588 I slot print_timing: id 3 | task 3168 | prompt eval time = 113.34 ms / 129 tokens ( 0.88 ms per token, 1138.20 tokens per second) 1.51.844.594 I slot print_timing: id 3 | task 3168 | eval time = 2138.73 ms / 117 tokens ( 18.44 ms per token, 54.24 tokens per second) 1.51.844.595 I slot print_timing: id 3 | task 3168 | total time = 2252.07 ms / 246 tokens 1.51.844.597 I slot print_timing: id 3 | task 3168 | graphs reused = 2526 1.51.844.597 I slot print_timing: id 3 | task 3168 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.844.654 I slot release: id 3 | task 3168 | stop processing: n_tokens = 1370, truncated = 0 1.51.861.378 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.836 1.51.861.490 I slot launch_slot_: id 3 | task 3292 | processing task, is_child = 0 1.52.626.242 I slot print_timing: id 2 | task 3244 | prompt eval time = 133.64 ms / 118 tokens ( 1.13 ms per token, 882.98 tokens per second) 1.52.626.248 I slot print_timing: id 2 | task 3244 | eval time = 1501.30 ms / 90 tokens ( 16.87 ms per token, 59.28 tokens per second) 1.52.626.249 I slot print_timing: id 2 | task 3244 | total time = 1634.94 ms / 208 tokens 1.52.626.250 I slot print_timing: id 2 | task 3244 | graphs reused = 2568 1.52.626.250 I slot print_timing: id 2 | task 3244 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.626.303 I slot release: id 2 | task 3244 | stop processing: n_tokens = 1332, truncated = 0 1.52.654.741 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.860 1.52.654.863 I slot launch_slot_: id 2 | task 3339 | processing task, is_child = 0 1.52.804.063 I slot print_timing: id 0 | task 3263 | prompt eval time = 107.54 ms / 110 tokens ( 0.98 ms per token, 1022.87 tokens per second) 1.52.804.069 I slot print_timing: id 0 | task 3263 | eval time = 1331.81 ms / 76 tokens ( 17.76 ms per token, 56.31 tokens per second) 1.52.804.070 I slot print_timing: id 0 | task 3263 | total time = 1439.35 ms / 186 tokens 1.52.804.071 I slot print_timing: id 0 | task 3263 | graphs reused = 2568 1.52.804.072 I slot print_timing: id 0 | task 3263 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.804.127 I slot release: id 0 | task 3263 | stop processing: n_tokens = 1310, truncated = 0 1.52.804.473 I slot print_timing: id 1 | task 3212 | prompt eval time = 146.13 ms / 152 tokens ( 0.96 ms per token, 1040.13 tokens per second) 1.52.804.476 I slot print_timing: id 1 | task 3212 | eval time = 2269.27 ms / 125 tokens ( 18.30 ms per token, 54.64 tokens per second) 1.52.804.477 I slot print_timing: id 1 | task 3212 | total time = 2415.40 ms / 277 tokens 1.52.804.477 I slot print_timing: id 1 | task 3212 | graphs reused = 2568 1.52.804.478 I slot print_timing: id 1 | task 3212 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.804.515 I slot release: id 1 | task 3212 | stop processing: n_tokens = 1401, truncated = 0 1.52.835.357 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.875 1.52.835.467 I slot launch_slot_: id 0 | task 3345 | processing task, is_child = 0 1.52.835.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 1.52.837.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.536 MiB) 1.52.889.927 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.818 1.52.890.057 I slot launch_slot_: id 1 | task 3346 | processing task, is_child = 0 1.53.412.893 I slot print_timing: id 3 | task 3292 | prompt eval time = 125.35 ms / 135 tokens ( 0.93 ms per token, 1076.96 tokens per second) 1.53.412.899 I slot print_timing: id 3 | task 3292 | eval time = 1426.03 ms / 76 tokens ( 19.01 ms per token, 52.59 tokens per second) 1.53.412.900 I slot print_timing: id 3 | task 3292 | total time = 1551.38 ms / 211 tokens 1.53.412.900 I slot print_timing: id 3 | task 3292 | graphs reused = 2593 1.53.412.901 I slot print_timing: id 3 | task 3292 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.412.951 I slot release: id 3 | task 3292 | stop processing: n_tokens = 1335, truncated = 0 1.53.444.652 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.858 1.53.444.763 I slot launch_slot_: id 3 | task 3375 | processing task, is_child = 0 1.54.162.049 I slot print_timing: id 2 | task 3339 | prompt eval time = 131.73 ms / 92 tokens ( 1.43 ms per token, 698.39 tokens per second) 1.54.162.055 I slot print_timing: id 2 | task 3339 | eval time = 1375.44 ms / 77 tokens ( 18.10 ms per token, 55.26 tokens per second) 1.54.162.056 I slot print_timing: id 2 | task 3339 | total time = 1507.17 ms / 169 tokens 1.54.162.057 I slot print_timing: id 2 | task 3339 | graphs reused = 2636 1.54.162.058 I slot print_timing: id 2 | task 3339 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.162.106 I slot release: id 2 | task 3339 | stop processing: n_tokens = 1293, truncated = 0 1.54.216.557 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.886 1.54.216.678 I slot launch_slot_: id 2 | task 3423 | processing task, is_child = 0 1.54.835.055 I slot print_timing: id 1 | task 3346 | prompt eval time = 157.26 ms / 120 tokens ( 1.31 ms per token, 763.04 tokens per second) 1.54.835.061 I slot print_timing: id 1 | task 3346 | eval time = 1768.17 ms / 110 tokens ( 16.22 ms per token, 61.65 tokens per second) 1.54.835.062 I slot print_timing: id 1 | task 3346 | total time = 1925.44 ms / 230 tokens 1.54.835.063 I slot print_timing: id 1 | task 3346 | graphs reused = 2669 1.54.835.064 I slot print_timing: id 1 | task 3346 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.835.117 I slot release: id 1 | task 3346 | stop processing: n_tokens = 1354, truncated = 0 1.54.891.636 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.846 1.54.891.753 I slot launch_slot_: id 1 | task 3462 | processing task, is_child = 0 1.55.894.624 I slot print_timing: id 0 | task 3345 | prompt eval time = 176.22 ms / 131 tokens ( 1.35 ms per token, 743.37 tokens per second) 1.55.894.629 I slot print_timing: id 0 | task 3345 | eval time = 2828.32 ms / 173 tokens ( 16.44 ms per token, 60.81 tokens per second) 1.55.894.630 I slot print_timing: id 0 | task 3345 | total time = 3004.55 ms / 304 tokens 1.55.894.631 I slot print_timing: id 0 | task 3345 | graphs reused = 2727 1.55.894.632 I slot print_timing: id 0 | task 3345 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.894.684 I slot release: id 0 | task 3345 | stop processing: n_tokens = 1428, truncated = 0 1.55.928.208 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.803 1.55.928.329 I slot launch_slot_: id 0 | task 3526 | processing task, is_child = 0 1.56.148.671 I slot print_timing: id 2 | task 3423 | prompt eval time = 128.60 ms / 98 tokens ( 1.31 ms per token, 762.04 tokens per second) 1.56.148.677 I slot print_timing: id 2 | task 3423 | eval time = 1803.37 ms / 109 tokens ( 16.70 ms per token, 59.89 tokens per second) 1.56.148.678 I slot print_timing: id 2 | task 3423 | total time = 1931.98 ms / 207 tokens 1.56.148.679 I slot print_timing: id 2 | task 3423 | graphs reused = 2735 1.56.148.679 I slot print_timing: id 2 | task 3423 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.148.730 I slot release: id 2 | task 3423 | stop processing: n_tokens = 1331, truncated = 0 1.56.176.725 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.861 1.56.176.837 I slot launch_slot_: id 2 | task 3537 | processing task, is_child = 0 1.56.422.177 I slot print_timing: id 3 | task 3375 | prompt eval time = 108.78 ms / 95 tokens ( 1.15 ms per token, 873.33 tokens per second) 1.56.422.183 I slot print_timing: id 3 | task 3375 | eval time = 2868.62 ms / 166 tokens ( 17.39 ms per token, 57.52 tokens per second) 1.56.422.185 I slot print_timing: id 3 | task 3375 | total time = 2977.40 ms / 261 tokens 1.56.422.185 I slot print_timing: id 3 | task 3375 | graphs reused = 2741 1.56.422.187 I slot print_timing: id 3 | task 3375 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.422.237 I slot release: id 3 | task 3375 | stop processing: n_tokens = 1385, truncated = 0 1.56.468.299 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.827 1.56.468.412 I slot launch_slot_: id 3 | task 3550 | processing task, is_child = 0 1.57.133.735 I slot print_timing: id 1 | task 3462 | prompt eval time = 132.42 ms / 116 tokens ( 1.14 ms per token, 876.03 tokens per second) 1.57.133.741 I slot print_timing: id 1 | task 3462 | eval time = 2109.55 ms / 123 tokens ( 17.29 ms per token, 57.83 tokens per second) 1.57.133.743 I slot print_timing: id 1 | task 3462 | total time = 2241.96 ms / 239 tokens 1.57.133.743 I slot print_timing: id 1 | task 3462 | graphs reused = 2779 1.57.133.744 I slot print_timing: id 1 | task 3462 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.133.794 I slot release: id 1 | task 3462 | stop processing: n_tokens = 1363, truncated = 0 1.57.162.016 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.841 1.57.162.134 I slot launch_slot_: id 1 | task 3591 | processing task, is_child = 0 1.57.684.861 I slot print_timing: id 0 | task 3526 | prompt eval time = 110.10 ms / 130 tokens ( 0.85 ms per token, 1180.79 tokens per second) 1.57.684.867 I slot print_timing: id 0 | task 3526 | eval time = 1646.42 ms / 90 tokens ( 18.50 ms per token, 54.06 tokens per second) 1.57.684.867 I slot print_timing: id 0 | task 3526 | total time = 1756.52 ms / 220 tokens 1.57.684.868 I slot print_timing: id 0 | task 3526 | graphs reused = 2805 1.57.684.869 I slot print_timing: id 0 | task 3526 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.684.921 I slot release: id 0 | task 3526 | stop processing: n_tokens = 1344, truncated = 0 1.57.717.695 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.853 1.57.717.807 I slot launch_slot_: id 0 | task 3623 | processing task, is_child = 0 1.58.326.954 I slot print_timing: id 2 | task 3537 | prompt eval time = 136.63 ms / 103 tokens ( 1.33 ms per token, 753.84 tokens per second) 1.58.326.960 I slot print_timing: id 2 | task 3537 | eval time = 2013.47 ms / 119 tokens ( 17.06 ms per token, 58.61 tokens per second) 1.58.326.961 I slot print_timing: id 2 | task 3537 | total time = 2150.10 ms / 222 tokens 1.58.326.962 I slot print_timing: id 2 | task 3537 | graphs reused = 2841 1.58.326.963 I slot print_timing: id 2 | task 3537 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.327.011 I slot release: id 2 | task 3537 | stop processing: n_tokens = 1346, truncated = 0 1.58.381.831 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.851 1.58.381.953 I slot launch_slot_: id 2 | task 3663 | processing task, is_child = 0 1.59.113.504 I slot print_timing: id 0 | task 3623 | prompt eval time = 106.41 ms / 123 tokens ( 0.87 ms per token, 1155.88 tokens per second) 1.59.113.510 I slot print_timing: id 0 | task 3623 | eval time = 1289.27 ms / 81 tokens ( 16.12 ms per token, 62.05 tokens per second) 1.59.113.511 I slot print_timing: id 0 | task 3623 | total time = 1395.68 ms / 204 tokens 1.59.113.511 I slot print_timing: id 0 | task 3623 | graphs reused = 2881 1.59.113.512 I slot print_timing: id 0 | task 3623 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.113.567 I slot release: id 0 | task 3623 | stop processing: n_tokens = 1328, truncated = 0 1.59.147.242 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.863 1.59.147.357 I slot launch_slot_: id 0 | task 3709 | processing task, is_child = 0 1.59.333.050 I slot print_timing: id 3 | task 3550 | prompt eval time = 116.14 ms / 122 tokens ( 0.95 ms per token, 1050.44 tokens per second) 1.59.333.057 I slot print_timing: id 3 | task 3550 | eval time = 2748.48 ms / 161 tokens ( 17.18 ms per token, 58.21 tokens per second) 1.59.333.058 I slot print_timing: id 3 | task 3550 | total time = 2864.62 ms / 283 tokens 1.59.333.059 I slot print_timing: id 3 | task 3550 | graphs reused = 2887 1.59.333.060 I slot print_timing: id 3 | task 3550 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.333.115 I slot release: id 3 | task 3550 | stop processing: n_tokens = 1407, truncated = 0 1.59.365.908 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.814 1.59.366.024 I slot launch_slot_: id 3 | task 3719 | processing task, is_child = 0 2.00.105.955 I slot print_timing: id 1 | task 3591 | prompt eval time = 136.62 ms / 133 tokens ( 1.03 ms per token, 973.51 tokens per second) 2.00.105.960 I slot print_timing: id 1 | task 3591 | eval time = 2807.19 ms / 168 tokens ( 16.81 ms per token, 59.49 tokens per second) 2.00.105.962 I slot print_timing: id 1 | task 3591 | total time = 2943.81 ms / 301 tokens 2.00.105.963 I slot print_timing: id 1 | task 3591 | graphs reused = 2930 2.00.105.965 I slot print_timing: id 1 | task 3591 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.106.017 I slot release: id 1 | task 3591 | stop processing: n_tokens = 1425, truncated = 0 2.00.162.601 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.804 2.00.162.733 I slot launch_slot_: id 1 | task 3767 | processing task, is_child = 0 2.00.561.695 I slot print_timing: id 2 | task 3663 | prompt eval time = 133.77 ms / 118 tokens ( 1.13 ms per token, 882.12 tokens per second) 2.00.561.701 I slot print_timing: id 2 | task 3663 | eval time = 2045.95 ms / 119 tokens ( 17.34 ms per token, 57.67 tokens per second) 2.00.561.701 I slot print_timing: id 2 | task 3663 | total time = 2179.72 ms / 237 tokens 2.00.561.702 I slot print_timing: id 2 | task 3663 | graphs reused = 2946 2.00.561.703 I slot print_timing: id 2 | task 3663 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.561.755 I slot release: id 2 | task 3663 | stop processing: n_tokens = 1361, truncated = 0 2.00.589.731 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.842 2.00.589.853 I slot launch_slot_: id 2 | task 3788 | processing task, is_child = 0 2.00.784.102 I slot print_timing: id 0 | task 3709 | prompt eval time = 105.79 ms / 101 tokens ( 1.05 ms per token, 954.72 tokens per second) 2.00.784.108 I slot print_timing: id 0 | task 3709 | eval time = 1530.94 ms / 81 tokens ( 19.14 ms per token, 52.26 tokens per second) 2.00.784.109 I slot print_timing: id 0 | task 3709 | total time = 1636.73 ms / 182 tokens 2.00.784.110 I slot print_timing: id 0 | task 3709 | graphs reused = 2949 2.00.784.111 I slot print_timing: id 0 | task 3709 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.784.165 I slot release: id 0 | task 3709 | stop processing: n_tokens = 1306, truncated = 0 2.00.817.647 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.877 2.00.817.762 I slot launch_slot_: id 0 | task 3797 | processing task, is_child = 0 2.01.204.835 I slot print_timing: id 3 | task 3719 | prompt eval time = 111.13 ms / 95 tokens ( 1.17 ms per token, 854.84 tokens per second) 2.01.204.841 I slot print_timing: id 3 | task 3719 | eval time = 1727.66 ms / 95 tokens ( 18.38 ms per token, 54.41 tokens per second) 2.01.204.842 I slot print_timing: id 3 | task 3719 | total time = 1838.80 ms / 190 tokens 2.01.204.843 I slot print_timing: id 3 | task 3719 | graphs reused = 2969 2.01.204.844 I slot print_timing: id 3 | task 3719 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.204.893 I slot release: id 3 | task 3719 | stop processing: n_tokens = 1314, truncated = 0 2.01.237.449 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.872 2.01.237.572 I slot launch_slot_: id 3 | task 3821 | processing task, is_child = 0 2.01.756.542 I slot print_timing: id 2 | task 3788 | prompt eval time = 131.77 ms / 89 tokens ( 1.48 ms per token, 675.42 tokens per second) 2.01.756.548 I slot print_timing: id 2 | task 3788 | eval time = 1034.90 ms / 61 tokens ( 17.25 ms per token, 57.98 tokens per second) 2.01.756.549 I slot print_timing: id 2 | task 3788 | total time = 1166.67 ms / 150 tokens 2.01.756.549 I slot print_timing: id 2 | task 3788 | graphs reused = 2998 2.01.756.550 I slot print_timing: id 2 | task 3788 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.756.599 I slot release: id 2 | task 3788 | stop processing: n_tokens = 1274, truncated = 0 2.01.810.629 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.900 2.01.810.745 I slot launch_slot_: id 2 | task 3855 | processing task, is_child = 0 2.02.378.500 I slot print_timing: id 3 | task 3821 | prompt eval time = 109.42 ms / 92 tokens ( 1.19 ms per token, 840.83 tokens per second) 2.02.378.505 I slot print_timing: id 3 | task 3821 | eval time = 1031.49 ms / 65 tokens ( 16.12 ms per token, 62.05 tokens per second) 2.02.378.507 I slot print_timing: id 3 | task 3821 | total time = 1140.91 ms / 157 tokens 2.02.378.507 I slot print_timing: id 3 | task 3821 | graphs reused = 3028 2.02.378.508 I slot print_timing: id 3 | task 3821 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.378.557 I slot release: id 3 | task 3821 | stop processing: n_tokens = 1281, truncated = 0 2.02.393.712 I slot print_timing: id 0 | task 3797 | prompt eval time = 104.24 ms / 99 tokens ( 1.05 ms per token, 949.73 tokens per second) 2.02.393.717 I slot print_timing: id 0 | task 3797 | eval time = 1471.70 ms / 89 tokens ( 16.72 ms per token, 59.79 tokens per second) 2.02.393.718 I slot print_timing: id 0 | task 3797 | total time = 1575.94 ms / 188 tokens 2.02.393.718 I slot print_timing: id 0 | task 3797 | graphs reused = 3028 2.02.393.719 I slot print_timing: id 0 | task 3797 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.393.764 I slot release: id 0 | task 3797 | stop processing: n_tokens = 1312, truncated = 0 2.02.394.362 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.873 2.02.394.467 I slot launch_slot_: id 0 | task 3890 | processing task, is_child = 0 2.02.394.560 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 2.02.396.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.567 MiB) 2.02.397.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.568 MiB) 2.02.445.862 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.895 2.02.445.999 I slot launch_slot_: id 3 | task 3891 | processing task, is_child = 0 2.03.256.580 I slot print_timing: id 2 | task 3855 | prompt eval time = 131.82 ms / 113 tokens ( 1.17 ms per token, 857.22 tokens per second) 2.03.256.586 I slot print_timing: id 2 | task 3855 | eval time = 1314.00 ms / 78 tokens ( 17.06 ms per token, 58.60 tokens per second) 2.03.256.587 I slot print_timing: id 2 | task 3855 | total time = 1445.82 ms / 191 tokens 2.03.256.588 I slot print_timing: id 2 | task 3855 | graphs reused = 3070 2.03.256.589 I slot print_timing: id 2 | task 3855 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.256.641 I slot release: id 2 | task 3855 | stop processing: n_tokens = 1315, truncated = 0 2.03.284.489 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.871 2.03.284.601 I slot launch_slot_: id 2 | task 3938 | processing task, is_child = 0 2.03.380.748 I slot print_timing: id 1 | task 3767 | n_gen = 164, tg = 53.06 t/s, tg_3s = 53.38 t/s 2.03.746.422 I slot print_timing: id 3 | task 3891 | prompt eval time = 163.24 ms / 90 tokens ( 1.81 ms per token, 551.35 tokens per second) 2.03.746.428 I slot print_timing: id 3 | task 3891 | eval time = 1117.76 ms / 68 tokens ( 16.68 ms per token, 59.94 tokens per second) 2.03.746.429 I slot print_timing: id 3 | task 3891 | total time = 1280.99 ms / 158 tokens 2.03.746.430 I slot print_timing: id 3 | task 3891 | graphs reused = 3090 2.03.746.431 I slot print_timing: id 3 | task 3891 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.746.482 I slot release: id 3 | task 3891 | stop processing: n_tokens = 1282, truncated = 0 2.03.762.881 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.894 2.03.762.994 I slot launch_slot_: id 3 | task 3963 | processing task, is_child = 0 2.04.013.775 I slot print_timing: id 1 | task 3767 | prompt eval time = 145.74 ms / 152 tokens ( 0.96 ms per token, 1042.95 tokens per second) 2.04.013.781 I slot print_timing: id 1 | task 3767 | eval time = 3705.28 ms / 198 tokens ( 18.81 ms per token, 53.17 tokens per second) 2.04.013.782 I slot print_timing: id 1 | task 3767 | total time = 3851.02 ms / 350 tokens 2.04.013.783 I slot print_timing: id 1 | task 3767 | graphs reused = 3098 2.04.013.783 I slot print_timing: id 1 | task 3767 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.013.837 I slot release: id 1 | task 3767 | stop processing: n_tokens = 1474, truncated = 0 2.04.042.329 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.777 2.04.042.479 I slot launch_slot_: id 1 | task 3976 | processing task, is_child = 0 2.05.060.096 I slot print_timing: id 3 | task 3963 | prompt eval time = 113.24 ms / 107 tokens ( 1.06 ms per token, 944.89 tokens per second) 2.05.060.103 I slot print_timing: id 3 | task 3963 | eval time = 1183.84 ms / 72 tokens ( 16.67 ms per token, 59.97 tokens per second) 2.05.060.104 I slot print_timing: id 3 | task 3963 | total time = 1297.08 ms / 179 tokens 2.05.060.105 I slot print_timing: id 3 | task 3963 | graphs reused = 3156 2.05.060.106 I slot print_timing: id 3 | task 3963 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.060.161 I slot release: id 3 | task 3963 | stop processing: n_tokens = 1303, truncated = 0 2.05.076.839 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.880 2.05.076.954 I slot launch_slot_: id 3 | task 4039 | processing task, is_child = 0 2.05.145.251 I slot print_timing: id 0 | task 3890 | prompt eval time = 181.40 ms / 118 tokens ( 1.54 ms per token, 650.48 tokens per second) 2.05.145.257 I slot print_timing: id 0 | task 3890 | eval time = 2517.82 ms / 144 tokens ( 17.61 ms per token, 56.80 tokens per second) 2.05.145.258 I slot print_timing: id 0 | task 3890 | total time = 2699.23 ms / 262 tokens 2.05.145.259 I slot print_timing: id 0 | task 3890 | graphs reused = 3156 2.05.145.259 I slot print_timing: id 0 | task 3890 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.145.312 I slot release: id 0 | task 3890 | stop processing: n_tokens = 1386, truncated = 0 2.05.189.552 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.827 2.05.189.668 I slot launch_slot_: id 0 | task 4042 | processing task, is_child = 0 2.05.814.094 I slot print_timing: id 2 | task 3938 | prompt eval time = 151.77 ms / 170 tokens ( 0.89 ms per token, 1120.11 tokens per second) 2.05.814.099 I slot print_timing: id 2 | task 3938 | eval time = 2377.70 ms / 136 tokens ( 17.61 ms per token, 56.78 tokens per second) 2.05.814.100 I slot print_timing: id 2 | task 3938 | total time = 2529.48 ms / 306 tokens 2.05.814.101 I slot print_timing: id 2 | task 3938 | graphs reused = 3190 2.05.814.102 I slot print_timing: id 2 | task 3938 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.814.156 I slot release: id 2 | task 3938 | stop processing: n_tokens = 1430, truncated = 0 2.05.868.367 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.801 2.05.868.489 I slot launch_slot_: id 2 | task 4082 | processing task, is_child = 0 2.06.217.302 I slot print_timing: id 1 | task 3976 | prompt eval time = 147.19 ms / 147 tokens ( 1.00 ms per token, 998.68 tokens per second) 2.06.217.307 I slot print_timing: id 1 | task 3976 | eval time = 2027.61 ms / 119 tokens ( 17.18 ms per token, 58.20 tokens per second) 2.06.217.309 I slot print_timing: id 1 | task 3976 | total time = 2174.81 ms / 266 tokens 2.06.217.311 I slot print_timing: id 1 | task 3976 | graphs reused = 3204 2.06.217.312 I slot print_timing: id 1 | task 3976 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.217.363 I slot release: id 1 | task 3976 | stop processing: n_tokens = 1390, truncated = 0 2.06.272.206 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.824 2.06.272.324 I slot launch_slot_: id 1 | task 4102 | processing task, is_child = 0 2.06.448.865 I slot print_timing: id 3 | task 4039 | prompt eval time = 112.57 ms / 109 tokens ( 1.03 ms per token, 968.26 tokens per second) 2.06.448.872 I slot print_timing: id 3 | task 4039 | eval time = 1259.32 ms / 63 tokens ( 20.31 ms per token, 49.23 tokens per second) 2.06.448.873 I slot print_timing: id 3 | task 4039 | total time = 1371.89 ms / 172 tokens 2.06.448.874 I slot print_timing: id 3 | task 4039 | graphs reused = 3205 2.06.448.875 I slot print_timing: id 3 | task 4039 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.448.930 I slot release: id 3 | task 4039 | stop processing: n_tokens = 1296, truncated = 0 2.06.493.076 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.884 2.06.493.186 I slot launch_slot_: id 3 | task 4110 | processing task, is_child = 0 2.07.600.806 I slot print_timing: id 2 | task 4082 | prompt eval time = 131.42 ms / 110 tokens ( 1.19 ms per token, 837.02 tokens per second) 2.07.600.812 I slot print_timing: id 2 | task 4082 | eval time = 1600.88 ms / 95 tokens ( 17.03 ms per token, 58.72 tokens per second) 2.07.600.813 I slot print_timing: id 2 | task 4082 | total time = 1732.30 ms / 205 tokens 2.07.600.814 I slot print_timing: id 2 | task 4082 | graphs reused = 3274 2.07.600.814 I slot print_timing: id 2 | task 4082 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.600.865 I slot release: id 2 | task 4082 | stop processing: n_tokens = 1329, truncated = 0 2.07.629.183 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.862 2.07.629.302 I slot launch_slot_: id 2 | task 4182 | processing task, is_child = 0 2.08.311.246 I slot print_timing: id 0 | task 4042 | n_gen = 174, tg = 57.66 t/s, tg_3s = 57.99 t/s 2.08.518.840 I slot print_timing: id 3 | task 4110 | prompt eval time = 114.06 ms / 122 tokens ( 0.93 ms per token, 1069.64 tokens per second) 2.08.518.846 I slot print_timing: id 3 | task 4110 | eval time = 1911.58 ms / 123 tokens ( 15.67 ms per token, 63.82 tokens per second) 2.08.518.847 I slot print_timing: id 3 | task 4110 | total time = 2025.64 ms / 245 tokens 2.08.518.848 I slot print_timing: id 3 | task 4110 | graphs reused = 3324 2.08.518.848 I slot print_timing: id 3 | task 4110 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.518.902 I slot release: id 3 | task 4110 | stop processing: n_tokens = 1369, truncated = 0 2.08.534.656 I slot print_timing: id 0 | task 4042 | prompt eval time = 121.25 ms / 139 tokens ( 0.87 ms per token, 1146.39 tokens per second) 2.08.534.661 I slot print_timing: id 0 | task 4042 | eval time = 3223.72 ms / 189 tokens ( 17.15 ms per token, 58.32 tokens per second) 2.08.534.663 I slot print_timing: id 0 | task 4042 | total time = 3344.97 ms / 328 tokens 2.08.534.663 I slot print_timing: id 0 | task 4042 | graphs reused = 3324 2.08.534.664 I slot print_timing: id 0 | task 4042 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.534.714 I slot release: id 0 | task 4042 | stop processing: n_tokens = 1452, truncated = 0 2.08.550.615 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.789 2.08.550.728 I slot launch_slot_: id 0 | task 4238 | processing task, is_child = 0 2.08.550.830 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.661 MiB) 2.08.552.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 2.08.553.774 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.349 MiB) 2.08.608.828 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.837 2.08.608.957 I slot launch_slot_: id 3 | task 4239 | processing task, is_child = 0 2.08.793.207 I slot print_timing: id 1 | task 4102 | prompt eval time = 141.99 ms / 134 tokens ( 1.06 ms per token, 943.76 tokens per second) 2.08.793.213 I slot print_timing: id 1 | task 4102 | eval time = 2378.88 ms / 134 tokens ( 17.89 ms per token, 55.91 tokens per second) 2.08.793.214 I slot print_timing: id 1 | task 4102 | total time = 2520.87 ms / 268 tokens 2.08.793.215 I slot print_timing: id 1 | task 4102 | graphs reused = 3324 2.08.793.215 I slot print_timing: id 1 | task 4102 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.793.267 I slot release: id 1 | task 4102 | stop processing: n_tokens = 1392, truncated = 0 2.08.822.491 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.823 2.08.822.617 I slot launch_slot_: id 1 | task 4243 | processing task, is_child = 0 2.09.357.424 I slot print_timing: id 2 | task 4182 | prompt eval time = 131.42 ms / 96 tokens ( 1.37 ms per token, 730.49 tokens per second) 2.09.357.430 I slot print_timing: id 2 | task 4182 | eval time = 1596.69 ms / 86 tokens ( 18.78 ms per token, 53.24 tokens per second) 2.09.357.431 I slot print_timing: id 2 | task 4182 | total time = 1728.11 ms / 182 tokens 2.09.357.432 I slot print_timing: id 2 | task 4182 | graphs reused = 3349 2.09.357.432 I slot print_timing: id 2 | task 4182 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.357.483 I slot release: id 2 | task 4182 | stop processing: n_tokens = 1306, truncated = 0 2.09.412.824 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.877 2.09.412.949 I slot launch_slot_: id 2 | task 4275 | processing task, is_child = 0 2.10.304.432 I slot print_timing: id 2 | task 4275 | prompt eval time = 147.66 ms / 166 tokens ( 0.89 ms per token, 1124.19 tokens per second) 2.10.304.439 I slot print_timing: id 2 | task 4275 | eval time = 743.80 ms / 54 tokens ( 14.03 ms per token, 71.26 tokens per second) 2.10.304.440 I slot print_timing: id 2 | task 4275 | total time = 891.47 ms / 220 tokens 2.10.304.440 I slot print_timing: id 2 | task 4275 | graphs reused = 3401 2.10.304.441 I slot print_timing: id 2 | task 4275 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.304.496 I slot release: id 2 | task 4275 | stop processing: n_tokens = 1344, truncated = 0 2.10.358.811 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.853 2.10.358.925 I slot launch_slot_: id 2 | task 4333 | processing task, is_child = 0 2.10.648.261 I slot print_timing: id 0 | task 4238 | prompt eval time = 183.88 ms / 111 tokens ( 1.66 ms per token, 603.66 tokens per second) 2.10.648.266 I slot print_timing: id 0 | task 4238 | eval time = 1855.41 ms / 103 tokens ( 18.19 ms per token, 54.97 tokens per second) 2.10.648.268 I slot print_timing: id 0 | task 4238 | total time = 2039.28 ms / 214 tokens 2.10.648.269 I slot print_timing: id 0 | task 4238 | graphs reused = 3411 2.10.648.270 I slot print_timing: id 0 | task 4238 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.648.318 I slot release: id 0 | task 4238 | stop processing: n_tokens = 1338, truncated = 0 2.10.664.829 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.857 2.10.664.944 I slot launch_slot_: id 0 | task 4348 | processing task, is_child = 0 2.10.822.619 I slot print_timing: id 3 | task 4239 | prompt eval time = 165.70 ms / 101 tokens ( 1.64 ms per token, 609.55 tokens per second) 2.10.822.625 I slot print_timing: id 3 | task 4239 | eval time = 2028.28 ms / 109 tokens ( 18.78 ms per token, 53.25 tokens per second) 2.10.822.626 I slot print_timing: id 3 | task 4239 | total time = 2193.97 ms / 210 tokens 2.10.822.627 I slot print_timing: id 3 | task 4239 | graphs reused = 3414 2.10.822.627 I slot print_timing: id 3 | task 4239 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.822.676 I slot release: id 3 | task 4239 | stop processing: n_tokens = 1334, truncated = 0 2.10.853.926 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.859 2.10.854.042 I slot launch_slot_: id 3 | task 4356 | processing task, is_child = 0 2.11.185.956 I slot print_timing: id 1 | task 4243 | prompt eval time = 133.55 ms / 108 tokens ( 1.24 ms per token, 808.71 tokens per second) 2.11.185.962 I slot print_timing: id 1 | task 4243 | eval time = 2229.78 ms / 125 tokens ( 17.98 ms per token, 55.61 tokens per second) 2.11.185.963 I slot print_timing: id 1 | task 4243 | total time = 2363.32 ms / 233 tokens 2.11.185.963 I slot print_timing: id 1 | task 4243 | graphs reused = 3429 2.11.185.964 I slot print_timing: id 1 | task 4243 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.186.015 I slot release: id 1 | task 4243 | stop processing: n_tokens = 1357, truncated = 0 2.11.214.047 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.845 2.11.214.165 I slot launch_slot_: id 1 | task 4375 | processing task, is_child = 0 2.11.732.116 I slot print_timing: id 0 | task 4348 | prompt eval time = 108.49 ms / 128 tokens ( 0.85 ms per token, 1179.81 tokens per second) 2.11.732.121 I slot print_timing: id 0 | task 4348 | eval time = 958.66 ms / 51 tokens ( 19.17 ms per token, 52.16 tokens per second) 2.11.732.123 I slot print_timing: id 0 | task 4348 | total time = 1067.16 ms / 179 tokens 2.11.732.123 I slot print_timing: id 0 | task 4348 | graphs reused = 3452 2.11.732.124 I slot print_timing: id 0 | task 4348 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.732.176 I slot release: id 0 | task 4348 | stop processing: n_tokens = 1303, truncated = 0 2.11.749.271 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.880 2.11.749.386 I slot launch_slot_: id 0 | task 4404 | processing task, is_child = 0 2.12.734.181 I slot print_timing: id 3 | task 4356 | prompt eval time = 109.53 ms / 95 tokens ( 1.15 ms per token, 867.36 tokens per second) 2.12.734.186 I slot print_timing: id 3 | task 4356 | eval time = 1770.59 ms / 107 tokens ( 16.70 ms per token, 59.87 tokens per second) 2.12.734.187 I slot print_timing: id 3 | task 4356 | total time = 1880.12 ms / 202 tokens 2.12.734.187 I slot print_timing: id 3 | task 4356 | graphs reused = 3512 2.12.734.188 I slot print_timing: id 3 | task 4356 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.734.236 I slot release: id 3 | task 4356 | stop processing: n_tokens = 1326, truncated = 0 2.12.868.693 I slot print_timing: id 0 | task 4404 | prompt eval time = 105.71 ms / 96 tokens ( 1.10 ms per token, 908.11 tokens per second) 2.12.868.697 I slot print_timing: id 0 | task 4404 | eval time = 1013.58 ms / 71 tokens ( 14.48 ms per token, 69.06 tokens per second) 2.12.868.698 I slot print_timing: id 0 | task 4404 | total time = 1119.29 ms / 167 tokens 2.12.868.700 I slot print_timing: id 0 | task 4404 | graphs reused = 3521 2.12.868.701 I slot print_timing: id 0 | task 4404 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.868.750 I slot release: id 0 | task 4404 | stop processing: n_tokens = 1291, truncated = 0 2.13.002.988 I slot print_timing: id 2 | task 4333 | prompt eval time = 130.40 ms / 110 tokens ( 1.19 ms per token, 843.56 tokens per second) 2.13.002.993 I slot print_timing: id 2 | task 4333 | eval time = 2513.65 ms / 149 tokens ( 16.98 ms per token, 58.88 tokens per second) 2.13.002.994 I slot print_timing: id 2 | task 4333 | total time = 2644.05 ms / 259 tokens 2.13.002.995 I slot print_timing: id 2 | task 4333 | graphs reused = 3531 2.13.002.995 I slot print_timing: id 2 | task 4333 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.003.042 I slot release: id 2 | task 4333 | stop processing: n_tokens = 1383, truncated = 0 2.13.134.866 I slot print_timing: id 1 | task 4375 | prompt eval time = 144.88 ms / 142 tokens ( 1.02 ms per token, 980.09 tokens per second) 2.13.134.872 I slot print_timing: id 1 | task 4375 | eval time = 1775.80 ms / 122 tokens ( 14.68 ms per token, 68.14 tokens per second) 2.13.134.873 I slot print_timing: id 1 | task 4375 | total time = 1920.68 ms / 264 tokens 2.13.134.874 I slot print_timing: id 1 | task 4375 | graphs reused = 3542 2.13.134.875 I slot print_timing: id 1 | task 4375 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.134.919 I slot release: id 1 | task 4375 | stop processing: n_tokens = 1388, truncated = 0 2.13.156.863 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1326, t_last = 132642506 2.13.156.986 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.973 MiB) 2.13.158.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.817 MiB) 2.13.160.053 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.161 MiB) 2.13.213.390 I slot launch_slot_: id 3 | task 4500 | processing task, is_child = 0 2.13.213.483 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 2.13.215.117 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 2.13.216.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.286 MiB) 2.13.268.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.536 MiB) 2.13.269.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.442 MiB) 2.13.311.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.724 MiB) 2.13.312.569 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.910 MiB) 2.13.314.247 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 2.13.368.202 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 132777020 2.13.368.432 I slot launch_slot_: id 0 | task 4501 | processing task, is_child = 0 2.13.368.588 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1383, t_last = 132911312 2.13.368.770 I slot launch_slot_: id 2 | task 4502 | processing task, is_child = 0 2.13.368.849 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1388, t_last = 133043189 2.13.369.016 I slot launch_slot_: id 1 | task 4503 | processing task, is_child = 0 2.14.532.689 I slot print_timing: id 3 | task 4500 | prompt eval time = 1090.21 ms / 779 tokens ( 1.40 ms per token, 714.54 tokens per second) 2.14.532.698 I slot print_timing: id 3 | task 4500 | eval time = 63.25 ms / 2 tokens ( 63.25 ms per token, 15.81 tokens per second) 2.14.532.699 I slot print_timing: id 3 | task 4500 | total time = 1153.47 ms / 781 tokens 2.14.532.701 I slot print_timing: id 3 | task 4500 | graphs reused = 3542 2.14.532.702 I slot print_timing: id 3 | task 4500 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.532.745 I slot release: id 3 | task 4500 | stop processing: n_tokens = 780, truncated = 0 2.14.548.100 I slot print_timing: id 0 | task 4501 | prompt eval time = 1162.13 ms / 806 tokens ( 1.44 ms per token, 693.56 tokens per second) 2.14.548.105 I slot print_timing: id 0 | task 4501 | eval time = 16.94 ms / 2 tokens ( 16.94 ms per token, 59.03 tokens per second) 2.14.548.106 I slot print_timing: id 0 | task 4501 | total time = 1179.07 ms / 808 tokens 2.14.548.107 I slot print_timing: id 0 | task 4501 | graphs reused = 3542 2.14.548.108 I slot print_timing: id 0 | task 4501 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.548.146 I slot release: id 0 | task 4501 | stop processing: n_tokens = 807, truncated = 0 2.14.548.473 I slot print_timing: id 1 | task 4503 | prompt eval time = 1159.21 ms / 952 tokens ( 1.22 ms per token, 821.25 tokens per second) 2.14.548.476 I slot print_timing: id 1 | task 4503 | eval time = 16.67 ms / 2 tokens ( 16.67 ms per token, 59.99 tokens per second) 2.14.548.477 I slot print_timing: id 1 | task 4503 | total time = 1175.88 ms / 954 tokens 2.14.548.477 I slot print_timing: id 1 | task 4503 | graphs reused = 3542 2.14.548.478 I slot print_timing: id 1 | task 4503 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.548.515 I slot release: id 1 | task 4503 | stop processing: n_tokens = 953, truncated = 0 2.14.548.873 I slot print_timing: id 2 | task 4502 | prompt eval time = 1156.42 ms / 987 tokens ( 1.17 ms per token, 853.50 tokens per second) 2.14.548.877 I slot print_timing: id 2 | task 4502 | eval time = 16.49 ms / 2 tokens ( 16.49 ms per token, 60.65 tokens per second) 2.14.548.878 I slot print_timing: id 2 | task 4502 | total time = 1172.91 ms / 989 tokens 2.14.548.879 I slot print_timing: id 2 | task 4502 | graphs reused = 3542 2.14.548.880 I slot print_timing: id 2 | task 4502 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.548.926 I slot release: id 2 | task 4502 | stop processing: n_tokens = 988, truncated = 0 2.14.548.945 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 134441014 2.14.549.060 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.130 MiB) 2.14.550.818 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.317 MiB) 2.14.552.448 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.160 MiB) 2.14.597.286 I slot launch_slot_: id 3 | task 4511 | processing task, is_child = 0 2.14.597.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.723 MiB) 2.14.598.906 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.754 MiB) 2.14.642.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.474 MiB) 2.14.643.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 2.14.645.528 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.192 MiB) 2.14.692.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.442 MiB) 2.14.694.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.192 MiB) 2.14.695.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.380 MiB) 2.14.747.619 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 134456416 2.14.747.806 I slot launch_slot_: id 0 | task 4512 | processing task, is_child = 0 2.14.747.916 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 134456785 2.14.748.060 I slot launch_slot_: id 1 | task 4513 | processing task, is_child = 0 2.14.748.117 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 134457196 2.14.748.253 I slot launch_slot_: id 2 | task 4514 | processing task, is_child = 0 2.15.827.467 I slot print_timing: id 0 | task 4512 | prompt eval time = 1060.50 ms / 804 tokens ( 1.32 ms per token, 758.13 tokens per second) 2.15.827.473 I slot print_timing: id 0 | task 4512 | eval time = 18.70 ms / 2 tokens ( 18.70 ms per token, 53.48 tokens per second) 2.15.827.474 I slot print_timing: id 0 | task 4512 | total time = 1079.20 ms / 806 tokens 2.15.827.475 I slot print_timing: id 0 | task 4512 | graphs reused = 3542 2.15.827.476 I slot print_timing: id 0 | task 4512 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.827.519 I slot release: id 0 | task 4512 | stop processing: n_tokens = 805, truncated = 0 2.15.827.843 I slot print_timing: id 1 | task 4513 | prompt eval time = 1057.65 ms / 846 tokens ( 1.25 ms per token, 799.89 tokens per second) 2.15.827.846 I slot print_timing: id 1 | task 4513 | eval time = 18.45 ms / 2 tokens ( 18.45 ms per token, 54.19 tokens per second) 2.15.827.847 I slot print_timing: id 1 | task 4513 | total time = 1076.11 ms / 848 tokens 2.15.827.847 I slot print_timing: id 1 | task 4513 | graphs reused = 3542 2.15.827.848 I slot print_timing: id 1 | task 4513 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.827.877 I slot release: id 1 | task 4513 | stop processing: n_tokens = 847, truncated = 0 2.15.828.186 I slot print_timing: id 2 | task 4514 | prompt eval time = 1054.83 ms / 855 tokens ( 1.23 ms per token, 810.56 tokens per second) 2.15.828.188 I slot print_timing: id 2 | task 4514 | eval time = 18.24 ms / 2 tokens ( 18.24 ms per token, 54.82 tokens per second) 2.15.828.189 I slot print_timing: id 2 | task 4514 | total time = 1073.07 ms / 857 tokens 2.15.828.190 I slot print_timing: id 2 | task 4514 | graphs reused = 3542 2.15.828.190 I slot print_timing: id 2 | task 4514 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.828.215 I slot release: id 2 | task 4514 | stop processing: n_tokens = 856, truncated = 0 2.15.828.515 I slot print_timing: id 3 | task 4511 | prompt eval time = 1052.04 ms / 801 tokens ( 1.31 ms per token, 761.38 tokens per second) 2.15.828.518 I slot print_timing: id 3 | task 4511 | eval time = 17.96 ms / 2 tokens ( 17.96 ms per token, 55.68 tokens per second) 2.15.828.519 I slot print_timing: id 3 | task 4511 | total time = 1070.00 ms / 803 tokens 2.15.828.519 I slot print_timing: id 3 | task 4511 | graphs reused = 3542 2.15.828.520 I slot print_timing: id 3 | task 4511 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.828.540 I slot release: id 3 | task 4511 | stop processing: n_tokens = 802, truncated = 0 2.15.841.794 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 805, t_last = 135735788 2.15.841.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.349 MiB) 2.15.843.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.536 MiB) 2.15.890.060 I slot launch_slot_: id 0 | task 4522 | processing task, is_child = 0 2.15.890.124 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.098 MiB) 2.15.891.911 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.318 MiB) 2.15.893.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.973 MiB) 2.15.937.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 2.15.939.224 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.473 MiB) 2.15.940.917 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.661 MiB) 2.15.998.606 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.442 MiB) 2.16.002.535 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 2.16.047.592 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 135736147 2.16.047.799 I slot launch_slot_: id 1 | task 4523 | processing task, is_child = 0 2.16.047.906 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 2.16.048.001 I slot launch_slot_: id 2 | task 4524 | processing task, is_child = 0 2.16.048.052 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 802, t_last = 135736809 2.16.048.190 I slot launch_slot_: id 3 | task 4525 | processing task, is_child = 0 2.16.510.617 I slot print_timing: id 2 | task 4524 | prompt eval time = 374.38 ms / 129 tokens ( 2.90 ms per token, 344.57 tokens per second) 2.16.510.624 I slot print_timing: id 2 | task 4524 | eval time = 81.10 ms / 2 tokens ( 81.10 ms per token, 12.33 tokens per second) 2.16.510.625 I slot print_timing: id 2 | task 4524 | total time = 455.48 ms / 131 tokens 2.16.510.626 I slot print_timing: id 2 | task 4524 | graphs reused = 3542 2.16.510.627 I slot print_timing: id 2 | task 4524 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.510.678 I slot release: id 2 | task 4524 | stop processing: n_tokens = 826, truncated = 0 2.16.745.462 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 136418947 2.16.745.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.848 MiB) 2.16.747.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.817 MiB) 2.16.748.955 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.474 MiB) 2.16.833.133 I slot launch_slot_: id 2 | task 4530 | processing task, is_child = 0 2.17.204.288 I slot print_timing: id 0 | task 4522 | prompt eval time = 1102.11 ms / 880 tokens ( 1.25 ms per token, 798.47 tokens per second) 2.17.204.294 I slot print_timing: id 0 | task 4522 | eval time = 53.97 ms / 2 tokens ( 53.97 ms per token, 18.53 tokens per second) 2.17.204.295 I slot print_timing: id 0 | task 4522 | total time = 1156.08 ms / 882 tokens 2.17.204.296 I slot print_timing: id 0 | task 4522 | graphs reused = 3542 2.17.204.297 I slot print_timing: id 0 | task 4522 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.204.350 I slot release: id 0 | task 4522 | stop processing: n_tokens = 881, truncated = 0 2.17.204.680 I slot print_timing: id 1 | task 4523 | prompt eval time = 1099.21 ms / 896 tokens ( 1.23 ms per token, 815.13 tokens per second) 2.17.204.683 I slot print_timing: id 1 | task 4523 | eval time = 53.73 ms / 2 tokens ( 53.73 ms per token, 18.61 tokens per second) 2.17.204.684 I slot print_timing: id 1 | task 4523 | total time = 1152.94 ms / 898 tokens 2.17.204.685 I slot print_timing: id 1 | task 4523 | graphs reused = 3542 2.17.204.685 I slot print_timing: id 1 | task 4523 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.204.715 I slot release: id 1 | task 4523 | stop processing: n_tokens = 897, truncated = 0 2.17.205.058 I slot print_timing: id 3 | task 4525 | prompt eval time = 1076.70 ms / 963 tokens ( 1.12 ms per token, 894.40 tokens per second) 2.17.205.061 I slot print_timing: id 3 | task 4525 | eval time = 53.48 ms / 2 tokens ( 53.48 ms per token, 18.70 tokens per second) 2.17.205.062 I slot print_timing: id 3 | task 4525 | total time = 1130.17 ms / 965 tokens 2.17.205.062 I slot print_timing: id 3 | task 4525 | graphs reused = 3542 2.17.205.063 I slot print_timing: id 3 | task 4525 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.205.098 I slot release: id 3 | task 4525 | stop processing: n_tokens = 964, truncated = 0 2.17.222.372 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 137112620 2.17.222.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.911 MiB) 2.17.224.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.285 MiB) 2.17.225.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.786 MiB) 2.17.323.689 I slot launch_slot_: id 0 | task 4535 | processing task, is_child = 0 2.17.323.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.754 MiB) 2.17.325.438 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.692 MiB) 2.17.365.586 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.380 MiB) 2.17.367.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.224 MiB) 2.17.368.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 2.17.418.025 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 137112985 2.17.418.236 I slot launch_slot_: id 1 | task 4536 | processing task, is_child = 0 2.17.418.298 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 964, t_last = 137113368 2.17.418.454 I slot launch_slot_: id 3 | task 4537 | processing task, is_child = 0 2.17.986.633 I slot print_timing: id 2 | task 4530 | prompt eval time = 941.33 ms / 987 tokens ( 0.95 ms per token, 1048.51 tokens per second) 2.17.986.639 I slot print_timing: id 2 | task 4530 | eval time = 187.40 ms / 2 tokens ( 187.40 ms per token, 5.34 tokens per second) 2.17.986.640 I slot print_timing: id 2 | task 4530 | total time = 1128.74 ms / 989 tokens 2.17.986.642 I slot print_timing: id 2 | task 4530 | graphs reused = 3542 2.17.986.643 I slot print_timing: id 2 | task 4530 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.986.697 I slot release: id 2 | task 4530 | stop processing: n_tokens = 988, truncated = 0 2.18.197.081 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 137894967 2.18.197.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.410 MiB) 2.18.198.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.940 MiB) 2.18.308.804 I slot launch_slot_: id 2 | task 4542 | processing task, is_child = 0 2.18.759.117 I slot print_timing: id 0 | task 4535 | prompt eval time = 1271.74 ms / 1022 tokens ( 1.24 ms per token, 803.62 tokens per second) 2.18.759.123 I slot print_timing: id 0 | task 4535 | eval time = 68.90 ms / 2 tokens ( 68.90 ms per token, 14.51 tokens per second) 2.18.759.125 I slot print_timing: id 0 | task 4535 | total time = 1340.64 ms / 1024 tokens 2.18.759.125 I slot print_timing: id 0 | task 4535 | graphs reused = 3542 2.18.759.126 I slot print_timing: id 0 | task 4535 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.759.181 I slot release: id 0 | task 4535 | stop processing: n_tokens = 1023, truncated = 0 2.18.759.529 I slot print_timing: id 1 | task 4536 | prompt eval time = 1268.76 ms / 924 tokens ( 1.37 ms per token, 728.27 tokens per second) 2.18.759.533 I slot print_timing: id 1 | task 4536 | eval time = 68.69 ms / 2 tokens ( 68.69 ms per token, 14.56 tokens per second) 2.18.759.533 I slot print_timing: id 1 | task 4536 | total time = 1337.45 ms / 926 tokens 2.18.759.534 I slot print_timing: id 1 | task 4536 | graphs reused = 3542 2.18.759.535 I slot print_timing: id 1 | task 4536 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.759.577 I slot release: id 1 | task 4536 | stop processing: n_tokens = 925, truncated = 0 2.18.759.927 I slot print_timing: id 3 | task 4537 | prompt eval time = 1253.46 ms / 1780 tokens ( 0.70 ms per token, 1420.06 tokens per second) 2.18.759.930 I slot print_timing: id 3 | task 4537 | eval time = 68.53 ms / 2 tokens ( 68.53 ms per token, 14.59 tokens per second) 2.18.759.931 I slot print_timing: id 3 | task 4537 | total time = 1322.00 ms / 1782 tokens 2.18.759.932 I slot print_timing: id 3 | task 4537 | graphs reused = 3542 2.18.759.932 I slot print_timing: id 3 | task 4537 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.760.000 I slot release: id 3 | task 4537 | stop processing: n_tokens = 1781, truncated = 0 2.18.776.363 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1023, t_last = 138667450 2.18.776.439 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.157 MiB) 2.18.853.487 I slot launch_slot_: id 0 | task 4547 | processing task, is_child = 0 2.18.853.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.378 MiB) 2.18.899.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 295.692 MiB) 2.18.976.789 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 138667846 2.18.976.996 I slot launch_slot_: id 1 | task 4548 | processing task, is_child = 0 2.18.977.086 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1781, t_last = 138668271 2.18.977.261 I slot launch_slot_: id 3 | task 4549 | processing task, is_child = 0 2.19.555.322 I slot print_timing: id 2 | task 4542 | prompt eval time = 971.03 ms / 937 tokens ( 1.04 ms per token, 964.95 tokens per second) 2.19.555.327 I slot print_timing: id 2 | task 4542 | eval time = 250.90 ms / 2 tokens ( 250.90 ms per token, 3.99 tokens per second) 2.19.555.328 I slot print_timing: id 2 | task 4542 | total time = 1221.93 ms / 939 tokens 2.19.555.330 I slot print_timing: id 2 | task 4542 | graphs reused = 3542 2.19.555.331 I slot print_timing: id 2 | task 4542 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.555.385 I slot release: id 2 | task 4542 | stop processing: n_tokens = 938, truncated = 0 2.19.734.221 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 139463655 2.19.734.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.565 MiB) 2.19.781.751 I slot launch_slot_: id 2 | task 4554 | processing task, is_child = 0 2.19.997.339 I slot print_timing: id 1 | task 4548 | prompt eval time = 922.02 ms / 741 tokens ( 1.24 ms per token, 803.67 tokens per second) 2.19.997.345 I slot print_timing: id 1 | task 4548 | eval time = 94.34 ms / 2 tokens ( 94.34 ms per token, 10.60 tokens per second) 2.19.997.346 I slot print_timing: id 1 | task 4548 | total time = 1016.37 ms / 743 tokens 2.19.997.347 I slot print_timing: id 1 | task 4548 | graphs reused = 3542 2.19.997.347 I slot print_timing: id 1 | task 4548 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.997.392 I slot release: id 1 | task 4548 | stop processing: n_tokens = 742, truncated = 0 2.19.997.692 I slot print_timing: id 3 | task 4549 | prompt eval time = 907.25 ms / 713 tokens ( 1.27 ms per token, 785.89 tokens per second) 2.19.997.695 I slot print_timing: id 3 | task 4549 | eval time = 93.98 ms / 2 tokens ( 93.98 ms per token, 10.64 tokens per second) 2.19.997.696 I slot print_timing: id 3 | task 4549 | total time = 1001.23 ms / 715 tokens 2.19.997.697 I slot print_timing: id 3 | task 4549 | graphs reused = 3542 2.19.997.698 I slot print_timing: id 3 | task 4549 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.997.721 I slot release: id 3 | task 4549 | stop processing: n_tokens = 714, truncated = 0 2.20.118.828 I slot print_timing: id 0 | task 4547 | prompt eval time = 1019.78 ms / 880 tokens ( 1.16 ms per token, 862.93 tokens per second) 2.20.118.834 I slot print_timing: id 0 | task 4547 | eval time = 121.77 ms / 2 tokens ( 121.77 ms per token, 8.21 tokens per second) 2.20.118.835 I slot print_timing: id 0 | task 4547 | total time = 1141.54 ms / 882 tokens 2.20.118.836 I slot print_timing: id 0 | task 4547 | graphs reused = 3542 2.20.118.837 I slot print_timing: id 0 | task 4547 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.118.884 I slot release: id 0 | task 4547 | stop processing: n_tokens = 881, truncated = 0 2.20.118.900 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.850 2.20.119.050 I slot launch_slot_: id 1 | task 4558 | processing task, is_child = 0 2.20.119.122 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.627 MiB) 2.20.170.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.845 MiB) 2.20.218.210 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 2.20.218.364 I slot launch_slot_: id 3 | task 4559 | processing task, is_child = 0 2.20.218.429 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 140027153 2.20.218.578 I slot launch_slot_: id 0 | task 4560 | processing task, is_child = 0 2.20.566.523 I slot print_timing: id 1 | task 4558 | prompt eval time = 300.08 ms / 122 tokens ( 2.46 ms per token, 406.56 tokens per second) 2.20.566.528 I slot print_timing: id 1 | task 4558 | eval time = 44.33 ms / 2 tokens ( 44.33 ms per token, 22.56 tokens per second) 2.20.566.529 I slot print_timing: id 1 | task 4558 | total time = 344.41 ms / 124 tokens 2.20.566.531 I slot print_timing: id 1 | task 4558 | graphs reused = 3542 2.20.566.532 I slot print_timing: id 1 | task 4558 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.566.574 I slot release: id 1 | task 4558 | stop processing: n_tokens = 726, truncated = 0 2.20.566.883 I slot print_timing: id 2 | task 4554 | prompt eval time = 720.59 ms / 716 tokens ( 1.01 ms per token, 993.64 tokens per second) 2.20.566.889 I slot print_timing: id 2 | task 4554 | eval time = 44.07 ms / 2 tokens ( 44.07 ms per token, 22.69 tokens per second) 2.20.566.890 I slot print_timing: id 2 | task 4554 | total time = 764.65 ms / 718 tokens 2.20.566.891 I slot print_timing: id 2 | task 4554 | graphs reused = 3542 2.20.566.891 I slot print_timing: id 2 | task 4554 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.566.916 I slot release: id 2 | task 4554 | stop processing: n_tokens = 717, truncated = 0 2.20.567.224 I slot print_timing: id 3 | task 4559 | prompt eval time = 269.39 ms / 116 tokens ( 2.32 ms per token, 430.61 tokens per second) 2.20.567.227 I slot print_timing: id 3 | task 4559 | eval time = 43.77 ms / 2 tokens ( 43.77 ms per token, 22.85 tokens per second) 2.20.567.227 I slot print_timing: id 3 | task 4559 | total time = 313.16 ms / 118 tokens 2.20.567.228 I slot print_timing: id 3 | task 4559 | graphs reused = 3542 2.20.567.228 I slot print_timing: id 3 | task 4559 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.567.249 I slot release: id 3 | task 4559 | stop processing: n_tokens = 720, truncated = 0 2.20.584.297 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 140474843 2.20.584.361 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 295.066 MiB) 2.20.685.835 I slot launch_slot_: id 1 | task 4565 | processing task, is_child = 0 2.20.685.898 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 297.912 MiB) 2.20.734.786 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 295.066 MiB) 2.20.786.151 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 140475185 2.20.786.350 I slot launch_slot_: id 2 | task 4566 | processing task, is_child = 0 2.20.786.403 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 140475518 2.20.786.548 I slot launch_slot_: id 3 | task 4567 | processing task, is_child = 0 2.21.325.470 I slot print_timing: id 0 | task 4560 | prompt eval time = 957.52 ms / 876 tokens ( 1.09 ms per token, 914.86 tokens per second) 2.21.325.476 I slot print_timing: id 0 | task 4560 | eval time = 149.35 ms / 2 tokens ( 149.35 ms per token, 6.70 tokens per second) 2.21.325.477 I slot print_timing: id 0 | task 4560 | total time = 1106.87 ms / 878 tokens 2.21.325.479 I slot print_timing: id 0 | task 4560 | graphs reused = 3542 2.21.325.479 I slot print_timing: id 0 | task 4560 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.325.523 I slot release: id 0 | task 4560 | stop processing: n_tokens = 877, truncated = 0 2.21.619.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 141233793 2.21.656.152 I slot launch_slot_: id 0 | task 4572 | processing task, is_child = 0 2.22.018.000 I slot print_timing: id 1 | task 4565 | prompt eval time = 1163.80 ms / 992 tokens ( 1.17 ms per token, 852.38 tokens per second) 2.22.018.006 I slot print_timing: id 1 | task 4565 | eval time = 57.35 ms / 2 tokens ( 57.35 ms per token, 17.44 tokens per second) 2.22.018.007 I slot print_timing: id 1 | task 4565 | total time = 1221.15 ms / 994 tokens 2.22.018.008 I slot print_timing: id 1 | task 4565 | graphs reused = 3542 2.22.018.008 I slot print_timing: id 1 | task 4565 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.018.054 I slot release: id 1 | task 4565 | stop processing: n_tokens = 993, truncated = 0 2.22.018.377 I slot print_timing: id 2 | task 4566 | prompt eval time = 1160.91 ms / 1034 tokens ( 1.12 ms per token, 890.68 tokens per second) 2.22.018.380 I slot print_timing: id 2 | task 4566 | eval time = 57.11 ms / 2 tokens ( 57.11 ms per token, 17.51 tokens per second) 2.22.018.381 I slot print_timing: id 2 | task 4566 | total time = 1218.02 ms / 1036 tokens 2.22.018.381 I slot print_timing: id 2 | task 4566 | graphs reused = 3542 2.22.018.382 I slot print_timing: id 2 | task 4566 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.018.412 I slot release: id 2 | task 4566 | stop processing: n_tokens = 1035, truncated = 0 2.22.018.729 I slot print_timing: id 3 | task 4567 | prompt eval time = 1158.08 ms / 1006 tokens ( 1.15 ms per token, 868.68 tokens per second) 2.22.018.732 I slot print_timing: id 3 | task 4567 | eval time = 56.90 ms / 2 tokens ( 56.90 ms per token, 17.58 tokens per second) 2.22.018.733 I slot print_timing: id 3 | task 4567 | total time = 1214.98 ms / 1008 tokens 2.22.018.733 I slot print_timing: id 3 | task 4567 | graphs reused = 3542 2.22.018.734 I slot print_timing: id 3 | task 4567 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.018.758 I slot release: id 3 | task 4567 | stop processing: n_tokens = 1007, truncated = 0 2.22.035.829 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.895 2.22.035.943 I slot launch_slot_: id 1 | task 4577 | processing task, is_child = 0 2.22.036.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.314 MiB) 2.22.121.134 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 294.066 MiB) 2.22.175.785 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 141926682 2.22.175.990 I slot launch_slot_: id 2 | task 4578 | processing task, is_child = 0 2.22.176.052 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1007, t_last = 141927028 2.22.176.200 I slot launch_slot_: id 3 | task 4579 | processing task, is_child = 0 2.22.612.554 I slot print_timing: id 0 | task 4572 | prompt eval time = 868.17 ms / 999 tokens ( 0.87 ms per token, 1150.69 tokens per second) 2.22.612.560 I slot print_timing: id 0 | task 4572 | eval time = 88.20 ms / 2 tokens ( 88.20 ms per token, 11.34 tokens per second) 2.22.612.561 I slot print_timing: id 0 | task 4572 | total time = 956.37 ms / 1001 tokens 2.22.612.562 I slot print_timing: id 0 | task 4572 | graphs reused = 3542 2.22.612.562 I slot print_timing: id 0 | task 4572 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.612.608 I slot release: id 0 | task 4572 | stop processing: n_tokens = 1000, truncated = 0 2.22.612.986 I slot print_timing: id 1 | task 4577 | prompt eval time = 338.36 ms / 132 tokens ( 2.56 ms per token, 390.12 tokens per second) 2.22.612.989 I slot print_timing: id 1 | task 4577 | eval time = 87.81 ms / 2 tokens ( 87.81 ms per token, 11.39 tokens per second) 2.22.612.990 I slot print_timing: id 1 | task 4577 | total time = 426.17 ms / 134 tokens 2.22.612.991 I slot print_timing: id 1 | task 4577 | graphs reused = 3542 2.22.612.991 I slot print_timing: id 1 | task 4577 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.613.025 I slot release: id 1 | task 4577 | stop processing: n_tokens = 994, truncated = 0 2.22.767.556 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 142520878 2.22.767.633 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.721 MiB) 2.22.823.868 I slot launch_slot_: id 0 | task 4584 | processing task, is_child = 0 2.22.823.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.626 MiB) 2.22.877.633 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 142521295 2.22.877.830 I slot launch_slot_: id 1 | task 4585 | processing task, is_child = 0 2.23.300.050 I slot print_timing: id 2 | task 4578 | prompt eval time = 997.63 ms / 879 tokens ( 1.13 ms per token, 881.08 tokens per second) 2.23.300.055 I slot print_timing: id 2 | task 4578 | eval time = 96.06 ms / 2 tokens ( 96.06 ms per token, 10.41 tokens per second) 2.23.300.056 I slot print_timing: id 2 | task 4578 | total time = 1093.70 ms / 881 tokens 2.23.300.057 I slot print_timing: id 2 | task 4578 | graphs reused = 3542 2.23.300.058 I slot print_timing: id 2 | task 4578 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.300.101 I slot release: id 2 | task 4578 | stop processing: n_tokens = 880, truncated = 0 2.23.300.473 I slot print_timing: id 3 | task 4579 | prompt eval time = 994.80 ms / 1018 tokens ( 0.98 ms per token, 1023.32 tokens per second) 2.23.300.476 I slot print_timing: id 3 | task 4579 | eval time = 95.86 ms / 2 tokens ( 95.86 ms per token, 10.43 tokens per second) 2.23.300.477 I slot print_timing: id 3 | task 4579 | total time = 1090.66 ms / 1020 tokens 2.23.300.478 I slot print_timing: id 3 | task 4579 | graphs reused = 3542 2.23.300.478 I slot print_timing: id 3 | task 4579 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.300.521 I slot release: id 3 | task 4579 | stop processing: n_tokens = 1019, truncated = 0 2.23.459.246 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 2.23.459.384 I slot launch_slot_: id 3 | task 4590 | processing task, is_child = 0 2.23.459.455 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 294.660 MiB) 2.23.502.260 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 143208370 2.23.502.465 I slot launch_slot_: id 2 | task 4591 | processing task, is_child = 0 2.23.908.734 I slot print_timing: id 0 | task 4584 | prompt eval time = 954.57 ms / 896 tokens ( 1.07 ms per token, 938.64 tokens per second) 2.23.908.740 I slot print_timing: id 0 | task 4584 | eval time = 76.31 ms / 2 tokens ( 76.31 ms per token, 13.10 tokens per second) 2.23.908.741 I slot print_timing: id 0 | task 4584 | total time = 1030.88 ms / 898 tokens 2.23.908.742 I slot print_timing: id 0 | task 4584 | graphs reused = 3542 2.23.908.743 I slot print_timing: id 0 | task 4584 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.908.792 I slot release: id 0 | task 4584 | stop processing: n_tokens = 897, truncated = 0 2.23.909.133 I slot print_timing: id 1 | task 4585 | prompt eval time = 951.95 ms / 1009 tokens ( 0.94 ms per token, 1059.93 tokens per second) 2.23.909.136 I slot print_timing: id 1 | task 4585 | eval time = 75.92 ms / 2 tokens ( 75.92 ms per token, 13.17 tokens per second) 2.23.909.137 I slot print_timing: id 1 | task 4585 | total time = 1027.87 ms / 1011 tokens 2.23.909.137 I slot print_timing: id 1 | task 4585 | graphs reused = 3542 2.23.909.138 I slot print_timing: id 1 | task 4585 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.909.173 I slot release: id 1 | task 4585 | stop processing: n_tokens = 1010, truncated = 0 2.23.909.576 I slot print_timing: id 3 | task 4590 | prompt eval time = 307.97 ms / 129 tokens ( 2.39 ms per token, 418.88 tokens per second) 2.23.909.579 I slot print_timing: id 3 | task 4590 | eval time = 75.65 ms / 2 tokens ( 75.65 ms per token, 13.22 tokens per second) 2.23.909.580 I slot print_timing: id 3 | task 4590 | total time = 383.62 ms / 131 tokens 2.23.909.580 I slot print_timing: id 3 | task 4590 | graphs reused = 3542 2.23.909.581 I slot print_timing: id 3 | task 4590 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.909.607 I slot release: id 3 | task 4590 | stop processing: n_tokens = 903, truncated = 0 2.23.926.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 143817061 2.23.926.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 294.504 MiB) 2.24.005.960 I slot launch_slot_: id 0 | task 4596 | processing task, is_child = 0 2.24.006.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.646 MiB) 2.24.054.528 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.490 MiB) 2.24.101.984 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.793 2.24.102.134 I slot launch_slot_: id 1 | task 4597 | processing task, is_child = 0 2.24.102.201 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 143817876 2.24.102.349 I slot launch_slot_: id 3 | task 4598 | processing task, is_child = 0 2.24.538.766 I slot print_timing: id 1 | task 4597 | prompt eval time = 321.57 ms / 108 tokens ( 2.98 ms per token, 335.85 tokens per second) 2.24.538.771 I slot print_timing: id 1 | task 4597 | eval time = 111.33 ms / 2 tokens ( 111.33 ms per token, 8.98 tokens per second) 2.24.538.772 I slot print_timing: id 1 | task 4597 | total time = 432.90 ms / 110 tokens 2.24.538.774 I slot print_timing: id 1 | task 4597 | graphs reused = 3542 2.24.538.775 I slot print_timing: id 1 | task 4597 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.538.823 I slot release: id 1 | task 4597 | stop processing: n_tokens = 882, truncated = 0 2.24.539.160 I slot print_timing: id 2 | task 4591 | prompt eval time = 905.88 ms / 985 tokens ( 0.92 ms per token, 1087.34 tokens per second) 2.24.539.163 I slot print_timing: id 2 | task 4591 | eval time = 110.93 ms / 2 tokens ( 110.93 ms per token, 9.01 tokens per second) 2.24.539.164 I slot print_timing: id 2 | task 4591 | total time = 1016.81 ms / 987 tokens 2.24.539.165 I slot print_timing: id 2 | task 4591 | graphs reused = 3542 2.24.539.166 I slot print_timing: id 2 | task 4591 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.539.196 I slot release: id 2 | task 4591 | stop processing: n_tokens = 986, truncated = 0 2.24.651.162 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 144447093 2.24.651.243 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.056 MiB) 2.24.737.706 I slot launch_slot_: id 1 | task 4603 | processing task, is_child = 0 2.24.737.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.151 MiB) 2.24.792.513 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 144447466 2.24.792.722 I slot launch_slot_: id 2 | task 4604 | processing task, is_child = 0 2.25.316.791 I slot print_timing: id 0 | task 4596 | prompt eval time = 1048.28 ms / 906 tokens ( 1.16 ms per token, 864.27 tokens per second) 2.25.316.798 I slot print_timing: id 0 | task 4596 | eval time = 166.14 ms / 2 tokens ( 166.14 ms per token, 6.02 tokens per second) 2.25.316.799 I slot print_timing: id 0 | task 4596 | total time = 1214.42 ms / 908 tokens 2.25.316.800 I slot print_timing: id 0 | task 4596 | graphs reused = 3542 2.25.316.801 I slot print_timing: id 0 | task 4596 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.316.854 I slot release: id 0 | task 4596 | stop processing: n_tokens = 907, truncated = 0 2.25.317.296 I slot print_timing: id 3 | task 4598 | prompt eval time = 1013.29 ms / 952 tokens ( 1.06 ms per token, 939.52 tokens per second) 2.25.317.301 I slot print_timing: id 3 | task 4598 | eval time = 166.07 ms / 2 tokens ( 166.07 ms per token, 6.02 tokens per second) 2.25.317.302 I slot print_timing: id 3 | task 4598 | total time = 1179.36 ms / 954 tokens 2.25.317.303 I slot print_timing: id 3 | task 4598 | graphs reused = 3542 2.25.317.304 I slot print_timing: id 3 | task 4598 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.317.346 I slot release: id 3 | task 4598 | stop processing: n_tokens = 953, truncated = 0 2.25.489.159 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 145225123 2.25.489.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.428 MiB) 2.25.538.955 I slot launch_slot_: id 0 | task 4609 | processing task, is_child = 0 2.25.539.028 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.741 MiB) 2.25.586.173 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 145225617 2.25.586.384 I slot launch_slot_: id 3 | task 4610 | processing task, is_child = 0 2.26.182.071 I slot print_timing: id 1 | task 4603 | prompt eval time = 1194.52 ms / 940 tokens ( 1.27 ms per token, 786.92 tokens per second) 2.26.182.076 I slot print_timing: id 1 | task 4603 | eval time = 182.53 ms / 2 tokens ( 182.53 ms per token, 5.48 tokens per second) 2.26.182.077 I slot print_timing: id 1 | task 4603 | total time = 1377.05 ms / 942 tokens 2.26.182.078 I slot print_timing: id 1 | task 4603 | graphs reused = 3542 2.26.182.079 I slot print_timing: id 1 | task 4603 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.182.127 I slot release: id 1 | task 4603 | stop processing: n_tokens = 941, truncated = 0 2.26.182.453 I slot print_timing: id 2 | task 4604 | prompt eval time = 1191.59 ms / 1356 tokens ( 0.88 ms per token, 1137.98 tokens per second) 2.26.182.456 I slot print_timing: id 2 | task 4604 | eval time = 182.35 ms / 2 tokens ( 182.35 ms per token, 5.48 tokens per second) 2.26.182.457 I slot print_timing: id 2 | task 4604 | total time = 1373.94 ms / 1358 tokens 2.26.182.458 I slot print_timing: id 2 | task 4604 | graphs reused = 3542 2.26.182.459 I slot print_timing: id 2 | task 4604 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.182.507 I slot release: id 2 | task 4604 | stop processing: n_tokens = 1357, truncated = 0 2.26.281.979 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 2.26.282.094 I slot launch_slot_: id 2 | task 4615 | processing task, is_child = 0 2.26.282.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.023 MiB) 2.26.381.012 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 146090397 2.26.381.222 I slot launch_slot_: id 1 | task 4616 | processing task, is_child = 0 2.26.825.866 I slot print_timing: id 0 | task 4609 | prompt eval time = 1106.48 ms / 1342 tokens ( 0.82 ms per token, 1212.86 tokens per second) 2.26.825.871 I slot print_timing: id 0 | task 4609 | eval time = 132.98 ms / 2 tokens ( 132.98 ms per token, 7.52 tokens per second) 2.26.825.873 I slot print_timing: id 0 | task 4609 | total time = 1239.46 ms / 1344 tokens 2.26.825.873 I slot print_timing: id 0 | task 4609 | graphs reused = 3542 2.26.825.874 I slot print_timing: id 0 | task 4609 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.825.930 I slot release: id 0 | task 4609 | stop processing: n_tokens = 1343, truncated = 0 2.26.826.307 I slot print_timing: id 2 | task 4615 | prompt eval time = 298.44 ms / 148 tokens ( 2.02 ms per token, 495.91 tokens per second) 2.26.826.310 I slot print_timing: id 2 | task 4615 | eval time = 132.78 ms / 2 tokens ( 132.78 ms per token, 7.53 tokens per second) 2.26.826.311 I slot print_timing: id 2 | task 4615 | total time = 431.23 ms / 150 tokens 2.26.826.311 I slot print_timing: id 2 | task 4615 | graphs reused = 3542 2.26.826.312 I slot print_timing: id 2 | task 4615 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.826.354 I slot release: id 2 | task 4615 | stop processing: n_tokens = 1301, truncated = 0 2.26.826.748 I slot print_timing: id 3 | task 4610 | prompt eval time = 1079.10 ms / 1259 tokens ( 0.86 ms per token, 1166.72 tokens per second) 2.26.826.752 I slot print_timing: id 3 | task 4610 | eval time = 132.60 ms / 2 tokens ( 132.60 ms per token, 7.54 tokens per second) 2.26.826.753 I slot print_timing: id 3 | task 4610 | total time = 1211.69 ms / 1261 tokens 2.26.826.753 I slot print_timing: id 3 | task 4610 | graphs reused = 3542 2.26.826.754 I slot print_timing: id 3 | task 4610 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.826.791 I slot release: id 3 | task 4610 | stop processing: n_tokens = 1260, truncated = 0 2.26.842.173 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1343, t_last = 146734199 2.26.842.264 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.334 MiB) 2.26.891.764 I slot launch_slot_: id 0 | task 4621 | processing task, is_child = 0 2.26.891.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.085 MiB) 2.26.953.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.805 MiB) 2.27.007.331 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1301, t_last = 146734624 2.27.007.542 I slot launch_slot_: id 2 | task 4622 | processing task, is_child = 0 2.27.007.614 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1260, t_last = 146735061 2.27.007.773 I slot launch_slot_: id 3 | task 4623 | processing task, is_child = 0 2.27.325.519 I slot print_timing: id 1 | task 4616 | prompt eval time = 771.66 ms / 792 tokens ( 0.97 ms per token, 1026.36 tokens per second) 2.27.325.525 I slot print_timing: id 1 | task 4616 | eval time = 162.33 ms / 2 tokens ( 162.33 ms per token, 6.16 tokens per second) 2.27.325.526 I slot print_timing: id 1 | task 4616 | total time = 933.99 ms / 794 tokens 2.27.325.528 I slot print_timing: id 1 | task 4616 | graphs reused = 3542 2.27.325.529 I slot print_timing: id 1 | task 4616 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.325.574 I slot release: id 1 | task 4616 | stop processing: n_tokens = 793, truncated = 0 2.27.376.978 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 147233843 2.27.377.048 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.305 MiB) 2.27.429.676 I slot launch_slot_: id 1 | task 4627 | processing task, is_child = 0 2.28.207.427 I slot print_timing: id 0 | task 4621 | prompt eval time = 1117.95 ms / 808 tokens ( 1.38 ms per token, 722.75 tokens per second) 2.28.207.433 I slot print_timing: id 0 | task 4621 | eval time = 81.68 ms / 2 tokens ( 81.68 ms per token, 12.24 tokens per second) 2.28.207.434 I slot print_timing: id 0 | task 4621 | total time = 1199.63 ms / 810 tokens 2.28.207.435 I slot print_timing: id 0 | task 4621 | graphs reused = 3542 2.28.207.436 I slot print_timing: id 0 | task 4621 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.207.482 I slot release: id 0 | task 4621 | stop processing: n_tokens = 809, truncated = 0 2.28.207.801 I slot print_timing: id 2 | task 4622 | prompt eval time = 1102.91 ms / 859 tokens ( 1.28 ms per token, 778.85 tokens per second) 2.28.207.804 I slot print_timing: id 2 | task 4622 | eval time = 81.38 ms / 2 tokens ( 81.38 ms per token, 12.29 tokens per second) 2.28.207.805 I slot print_timing: id 2 | task 4622 | total time = 1184.29 ms / 861 tokens 2.28.207.805 I slot print_timing: id 2 | task 4622 | graphs reused = 3542 2.28.207.806 I slot print_timing: id 2 | task 4622 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.207.840 I slot release: id 2 | task 4622 | stop processing: n_tokens = 860, truncated = 0 2.28.208.170 I slot print_timing: id 3 | task 4623 | prompt eval time = 1100.09 ms / 891 tokens ( 1.23 ms per token, 809.94 tokens per second) 2.28.208.173 I slot print_timing: id 3 | task 4623 | eval time = 81.09 ms / 2 tokens ( 81.09 ms per token, 12.33 tokens per second) 2.28.208.174 I slot print_timing: id 3 | task 4623 | total time = 1181.18 ms / 893 tokens 2.28.208.175 I slot print_timing: id 3 | task 4623 | graphs reused = 3542 2.28.208.175 I slot print_timing: id 3 | task 4623 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.208.202 I slot release: id 3 | task 4623 | stop processing: n_tokens = 892, truncated = 0 2.28.234.551 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 809, t_last = 148115751 2.28.234.621 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.400 MiB) 2.28.282.656 I slot launch_slot_: id 0 | task 4633 | processing task, is_child = 0 2.28.282.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.151 MiB) 2.28.336.251 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.245 MiB) 2.28.383.737 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 148116110 2.28.383.936 I slot launch_slot_: id 2 | task 4634 | processing task, is_child = 0 2.28.383.993 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 892, t_last = 148116471 2.28.384.136 I slot launch_slot_: id 3 | task 4635 | processing task, is_child = 0 2.28.532.762 I slot print_timing: id 1 | task 4627 | prompt eval time = 793.46 ms / 790 tokens ( 1.00 ms per token, 995.64 tokens per second) 2.28.532.768 I slot print_timing: id 1 | task 4627 | eval time = 298.21 ms / 2 tokens ( 298.21 ms per token, 3.35 tokens per second) 2.28.532.769 I slot print_timing: id 1 | task 4627 | total time = 1091.67 ms / 792 tokens 2.28.532.770 I slot print_timing: id 1 | task 4627 | graphs reused = 3542 2.28.532.771 I slot print_timing: id 1 | task 4627 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.532.816 I slot release: id 1 | task 4627 | stop processing: n_tokens = 791, truncated = 0 2.28.655.330 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.852 (> 0.100 thold), f_keep = 0.863 2.28.655.478 I slot launch_slot_: id 1 | task 4638 | processing task, is_child = 0 2.29.292.635 I slot print_timing: id 1 | task 4638 | prompt eval time = 493.74 ms / 147 tokens ( 3.36 ms per token, 297.73 tokens per second) 2.29.292.640 I slot print_timing: id 1 | task 4638 | eval time = 124.12 ms / 2 tokens ( 124.12 ms per token, 8.06 tokens per second) 2.29.292.641 I slot print_timing: id 1 | task 4638 | total time = 617.86 ms / 149 tokens 2.29.292.642 I slot print_timing: id 1 | task 4638 | graphs reused = 3542 2.29.292.642 I slot print_timing: id 1 | task 4638 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.292.685 I slot release: id 1 | task 4638 | stop processing: n_tokens = 803, truncated = 0 2.29.343.349 I slot print_timing: id 0 | task 4633 | prompt eval time = 908.16 ms / 774 tokens ( 1.17 ms per token, 852.27 tokens per second) 2.29.343.355 I slot print_timing: id 0 | task 4633 | eval time = 51.03 ms / 2 tokens ( 51.03 ms per token, 19.59 tokens per second) 2.29.343.356 I slot print_timing: id 0 | task 4633 | total time = 959.20 ms / 776 tokens 2.29.343.356 I slot print_timing: id 0 | task 4633 | graphs reused = 3542 2.29.343.357 I slot print_timing: id 0 | task 4633 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.343.395 I slot release: id 0 | task 4633 | stop processing: n_tokens = 775, truncated = 0 2.29.344.320 I slot print_timing: id 3 | task 4635 | prompt eval time = 902.40 ms / 778 tokens ( 1.16 ms per token, 862.14 tokens per second) 2.29.344.323 I slot print_timing: id 3 | task 4635 | eval time = 50.89 ms / 2 tokens ( 50.89 ms per token, 19.65 tokens per second) 2.29.344.324 I slot print_timing: id 3 | task 4635 | total time = 953.30 ms / 780 tokens 2.29.344.325 I slot print_timing: id 3 | task 4635 | graphs reused = 3542 2.29.344.325 I slot print_timing: id 3 | task 4635 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.344.356 I slot release: id 3 | task 4635 | stop processing: n_tokens = 779, truncated = 0 2.29.344.367 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 149200955 2.29.344.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.181 MiB) 2.29.391.556 I slot launch_slot_: id 1 | task 4643 | processing task, is_child = 0 2.29.391.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.950 MiB) 2.29.437.763 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.587 MiB) 2.29.488.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 775, t_last = 149251665 2.29.488.559 I slot launch_slot_: id 0 | task 4644 | processing task, is_child = 0 2.29.488.612 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 149252625 2.29.488.753 I slot launch_slot_: id 3 | task 4645 | processing task, is_child = 0 2.29.645.382 I slot print_timing: id 2 | task 4634 | prompt eval time = 956.45 ms / 855 tokens ( 1.12 ms per token, 893.93 tokens per second) 2.29.645.387 I slot print_timing: id 2 | task 4634 | eval time = 301.36 ms / 2 tokens ( 301.36 ms per token, 3.32 tokens per second) 2.29.645.389 I slot print_timing: id 2 | task 4634 | total time = 1257.81 ms / 857 tokens 2.29.645.390 I slot print_timing: id 2 | task 4634 | graphs reused = 3542 2.29.645.391 I slot print_timing: id 2 | task 4634 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.645.434 I slot release: id 2 | task 4634 | stop processing: n_tokens = 856, truncated = 0 2.29.762.207 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 149553704 2.29.762.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.805 MiB) 2.29.816.984 I slot launch_slot_: id 2 | task 4648 | processing task, is_child = 0 2.30.733.446 I slot print_timing: id 0 | task 4644 | prompt eval time = 1176.13 ms / 944 tokens ( 1.25 ms per token, 802.63 tokens per second) 2.30.733.452 I slot print_timing: id 0 | task 4644 | eval time = 68.54 ms / 2 tokens ( 68.54 ms per token, 14.59 tokens per second) 2.30.733.453 I slot print_timing: id 0 | task 4644 | total time = 1244.67 ms / 946 tokens 2.30.733.454 I slot print_timing: id 0 | task 4644 | graphs reused = 3542 2.30.733.455 I slot print_timing: id 0 | task 4644 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.733.501 I slot release: id 0 | task 4644 | stop processing: n_tokens = 945, truncated = 0 2.30.733.831 I slot print_timing: id 1 | task 4643 | prompt eval time = 1173.27 ms / 971 tokens ( 1.21 ms per token, 827.61 tokens per second) 2.30.733.834 I slot print_timing: id 1 | task 4643 | eval time = 68.35 ms / 2 tokens ( 68.35 ms per token, 14.63 tokens per second) 2.30.733.835 I slot print_timing: id 1 | task 4643 | total time = 1241.62 ms / 973 tokens 2.30.733.836 I slot print_timing: id 1 | task 4643 | graphs reused = 3542 2.30.733.836 I slot print_timing: id 1 | task 4643 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.733.866 I slot release: id 1 | task 4643 | stop processing: n_tokens = 972, truncated = 0 2.30.734.197 I slot print_timing: id 3 | task 4645 | prompt eval time = 1170.46 ms / 964 tokens ( 1.21 ms per token, 823.60 tokens per second) 2.30.734.200 I slot print_timing: id 3 | task 4645 | eval time = 68.15 ms / 2 tokens ( 68.15 ms per token, 14.67 tokens per second) 2.30.734.201 I slot print_timing: id 3 | task 4645 | total time = 1238.61 ms / 966 tokens 2.30.734.201 I slot print_timing: id 3 | task 4645 | graphs reused = 3542 2.30.734.202 I slot print_timing: id 3 | task 4645 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.734.226 I slot release: id 3 | task 4645 | stop processing: n_tokens = 965, truncated = 0 2.30.760.002 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.914 2.30.760.105 I slot launch_slot_: id 0 | task 4655 | processing task, is_child = 0 2.30.760.176 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.582 MiB) 2.30.816.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.957 MiB) 2.30.864.310 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 972, t_last = 150642135 2.30.864.518 I slot launch_slot_: id 1 | task 4656 | processing task, is_child = 0 2.30.864.577 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 150642496 2.30.864.727 I slot launch_slot_: id 3 | task 4657 | processing task, is_child = 0 2.31.033.911 I slot print_timing: id 2 | task 4648 | prompt eval time = 942.98 ms / 947 tokens ( 1.00 ms per token, 1004.26 tokens per second) 2.31.033.916 I slot print_timing: id 2 | task 4648 | eval time = 273.91 ms / 2 tokens ( 273.91 ms per token, 3.65 tokens per second) 2.31.033.917 I slot print_timing: id 2 | task 4648 | total time = 1216.89 ms / 949 tokens 2.31.033.918 I slot print_timing: id 2 | task 4648 | graphs reused = 3542 2.31.033.919 I slot print_timing: id 2 | task 4648 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.033.961 I slot release: id 2 | task 4648 | stop processing: n_tokens = 948, truncated = 0 2.31.146.603 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 150942230 2.31.146.676 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.676 MiB) 2.31.196.008 I slot launch_slot_: id 2 | task 4660 | processing task, is_child = 0 2.31.467.178 I slot print_timing: id 0 | task 4655 | prompt eval time = 281.86 ms / 133 tokens ( 2.12 ms per token, 471.87 tokens per second) 2.31.467.184 I slot print_timing: id 0 | task 4655 | eval time = 320.57 ms / 2 tokens ( 320.57 ms per token, 3.12 tokens per second) 2.31.467.185 I slot print_timing: id 0 | task 4655 | total time = 602.43 ms / 135 tokens 2.31.467.186 I slot print_timing: id 0 | task 4655 | graphs reused = 3542 2.31.467.187 I slot print_timing: id 0 | task 4655 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.467.233 I slot release: id 0 | task 4655 | stop processing: n_tokens = 970, truncated = 0 2.31.596.332 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 151375503 2.31.596.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.770 MiB) 2.31.648.512 I slot launch_slot_: id 0 | task 4663 | processing task, is_child = 0 2.31.960.111 I slot print_timing: id 1 | task 4656 | prompt eval time = 890.43 ms / 799 tokens ( 1.11 ms per token, 897.32 tokens per second) 2.31.960.130 I slot print_timing: id 1 | task 4656 | eval time = 187.15 ms / 2 tokens ( 187.15 ms per token, 5.34 tokens per second) 2.31.960.133 I slot print_timing: id 1 | task 4656 | total time = 1077.58 ms / 801 tokens 2.31.960.135 I slot print_timing: id 1 | task 4656 | graphs reused = 3542 2.31.960.136 I slot print_timing: id 1 | task 4656 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.960.227 I slot release: id 1 | task 4656 | stop processing: n_tokens = 800, truncated = 0 2.31.961.053 I slot print_timing: id 3 | task 4657 | prompt eval time = 887.85 ms / 798 tokens ( 1.11 ms per token, 898.80 tokens per second) 2.31.961.056 I slot print_timing: id 3 | task 4657 | eval time = 187.30 ms / 2 tokens ( 187.30 ms per token, 5.34 tokens per second) 2.31.961.057 I slot print_timing: id 3 | task 4657 | total time = 1075.15 ms / 800 tokens 2.31.961.058 I slot print_timing: id 3 | task 4657 | graphs reused = 3542 2.31.961.058 I slot print_timing: id 3 | task 4657 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.961.087 I slot release: id 3 | task 4657 | stop processing: n_tokens = 799, truncated = 0 2.32.007.507 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 151868497 2.32.007.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.679 MiB) 2.32.054.475 I slot launch_slot_: id 1 | task 4668 | processing task, is_child = 0 2.32.054.540 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.621 MiB) 2.32.103.838 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 151869357 2.32.104.049 I slot launch_slot_: id 3 | task 4667 | processing task, is_child = 0 2.32.505.966 I slot print_timing: id 2 | task 4660 | prompt eval time = 1117.75 ms / 975 tokens ( 1.15 ms per token, 872.29 tokens per second) 2.32.505.972 I slot print_timing: id 2 | task 4660 | eval time = 181.95 ms / 2 tokens ( 181.95 ms per token, 5.50 tokens per second) 2.32.505.973 I slot print_timing: id 2 | task 4660 | total time = 1299.70 ms / 977 tokens 2.32.505.974 I slot print_timing: id 2 | task 4660 | graphs reused = 3542 2.32.505.976 I slot print_timing: id 2 | task 4660 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.506.024 I slot release: id 2 | task 4660 | stop processing: n_tokens = 976, truncated = 0 2.32.596.461 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 152414293 2.32.596.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.745 MiB) 2.32.652.093 I slot launch_slot_: id 2 | task 4672 | processing task, is_child = 0 2.32.910.273 I slot print_timing: id 0 | task 4663 | prompt eval time = 947.92 ms / 953 tokens ( 0.99 ms per token, 1005.36 tokens per second) 2.32.910.279 I slot print_timing: id 0 | task 4663 | eval time = 313.81 ms / 2 tokens ( 313.81 ms per token, 3.19 tokens per second) 2.32.910.279 I slot print_timing: id 0 | task 4663 | total time = 1261.74 ms / 955 tokens 2.32.910.280 I slot print_timing: id 0 | task 4663 | graphs reused = 3542 2.32.910.281 I slot print_timing: id 0 | task 4663 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.910.329 I slot release: id 0 | task 4663 | stop processing: n_tokens = 954, truncated = 0 2.33.062.756 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 152818599 2.33.062.832 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.526 MiB) 2.33.118.103 I slot launch_slot_: id 0 | task 4675 | processing task, is_child = 0 2.33.427.343 I slot print_timing: id 1 | task 4668 | prompt eval time = 1119.91 ms / 930 tokens ( 1.20 ms per token, 830.42 tokens per second) 2.33.427.348 I slot print_timing: id 1 | task 4668 | eval time = 192.88 ms / 2 tokens ( 192.88 ms per token, 5.18 tokens per second) 2.33.427.349 I slot print_timing: id 1 | task 4668 | total time = 1312.80 ms / 932 tokens 2.33.427.351 I slot print_timing: id 1 | task 4668 | graphs reused = 3542 2.33.427.352 I slot print_timing: id 1 | task 4668 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.427.406 I slot release: id 1 | task 4668 | stop processing: n_tokens = 931, truncated = 0 2.33.427.731 I slot print_timing: id 3 | task 4667 | prompt eval time = 1104.90 ms / 961 tokens ( 1.15 ms per token, 869.76 tokens per second) 2.33.427.734 I slot print_timing: id 3 | task 4667 | eval time = 192.47 ms / 2 tokens ( 192.47 ms per token, 5.20 tokens per second) 2.33.427.735 I slot print_timing: id 3 | task 4667 | total time = 1297.37 ms / 963 tokens 2.33.427.735 I slot print_timing: id 3 | task 4667 | graphs reused = 3542 2.33.427.736 I slot print_timing: id 3 | task 4667 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.427.769 I slot release: id 3 | task 4667 | stop processing: n_tokens = 962, truncated = 0 2.33.470.568 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.867 2.33.470.688 I slot launch_slot_: id 1 | task 4679 | processing task, is_child = 0 2.33.470.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.338 MiB) 2.33.524.715 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 153336039 2.33.524.935 I slot launch_slot_: id 3 | task 4680 | processing task, is_child = 0 2.33.900.572 I slot print_timing: id 2 | task 4672 | prompt eval time = 1089.47 ms / 898 tokens ( 1.21 ms per token, 824.25 tokens per second) 2.33.900.578 I slot print_timing: id 2 | task 4672 | eval time = 148.77 ms / 2 tokens ( 148.77 ms per token, 6.72 tokens per second) 2.33.900.579 I slot print_timing: id 2 | task 4672 | total time = 1238.24 ms / 900 tokens 2.33.900.580 I slot print_timing: id 2 | task 4672 | graphs reused = 3542 2.33.900.581 I slot print_timing: id 2 | task 4672 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.900.632 I slot release: id 2 | task 4672 | stop processing: n_tokens = 899, truncated = 0 2.33.964.309 I slot print_timing: id 1 | task 4679 | prompt eval time = 365.26 ms / 111 tokens ( 3.29 ms per token, 303.89 tokens per second) 2.33.964.314 I slot print_timing: id 1 | task 4679 | eval time = 64.03 ms / 2 tokens ( 64.03 ms per token, 15.62 tokens per second) 2.33.964.315 I slot print_timing: id 1 | task 4679 | total time = 429.29 ms / 113 tokens 2.33.964.315 I slot print_timing: id 1 | task 4679 | graphs reused = 3542 2.33.964.316 I slot print_timing: id 1 | task 4679 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.964.361 I slot release: id 1 | task 4679 | stop processing: n_tokens = 891, truncated = 0 2.33.964.374 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 153808902 2.33.964.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.773 MiB) 2.34.007.009 I slot launch_slot_: id 2 | task 4684 | processing task, is_child = 0 2.34.007.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.305 MiB) 2.34.055.812 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 153872631 2.34.055.992 I slot launch_slot_: id 1 | task 4685 | processing task, is_child = 0 2.34.272.173 I slot print_timing: id 0 | task 4675 | prompt eval time = 845.89 ms / 902 tokens ( 0.94 ms per token, 1066.33 tokens per second) 2.34.272.179 I slot print_timing: id 0 | task 4675 | eval time = 308.15 ms / 2 tokens ( 308.15 ms per token, 3.25 tokens per second) 2.34.272.180 I slot print_timing: id 0 | task 4675 | total time = 1154.04 ms / 904 tokens 2.34.272.182 I slot print_timing: id 0 | task 4675 | graphs reused = 3542 2.34.272.183 I slot print_timing: id 0 | task 4675 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.272.233 I slot release: id 0 | task 4675 | stop processing: n_tokens = 903, truncated = 0 2.34.392.611 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 154180503 2.34.392.683 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.839 MiB) 2.34.448.041 I slot launch_slot_: id 0 | task 4688 | processing task, is_child = 0 2.34.957.443 I slot print_timing: id 3 | task 4680 | prompt eval time = 1119.21 ms / 899 tokens ( 1.24 ms per token, 803.24 tokens per second) 2.34.957.463 I slot print_timing: id 3 | task 4680 | eval time = 273.23 ms / 2 tokens ( 273.23 ms per token, 3.66 tokens per second) 2.34.957.464 I slot print_timing: id 3 | task 4680 | total time = 1392.44 ms / 901 tokens 2.34.957.466 I slot print_timing: id 3 | task 4680 | graphs reused = 3542 2.34.957.467 I slot print_timing: id 3 | task 4680 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.957.577 I slot release: id 3 | task 4680 | stop processing: n_tokens = 900, truncated = 0 2.35.120.502 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 900, t_last = 154865850 2.35.120.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.493 MiB) 2.35.175.639 I slot launch_slot_: id 3 | task 4692 | processing task, is_child = 0 2.35.622.178 I slot print_timing: id 1 | task 4685 | prompt eval time = 1335.18 ms / 1236 tokens ( 1.08 ms per token, 925.72 tokens per second) 2.35.622.184 I slot print_timing: id 1 | task 4685 | eval time = 230.98 ms / 2 tokens ( 230.98 ms per token, 4.33 tokens per second) 2.35.622.185 I slot print_timing: id 1 | task 4685 | total time = 1566.16 ms / 1238 tokens 2.35.622.186 I slot print_timing: id 1 | task 4685 | graphs reused = 3542 2.35.622.187 I slot print_timing: id 1 | task 4685 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.622.242 I slot release: id 1 | task 4685 | stop processing: n_tokens = 1237, truncated = 0 2.35.622.564 I slot print_timing: id 2 | task 4684 | prompt eval time = 1332.55 ms / 1225 tokens ( 1.09 ms per token, 919.29 tokens per second) 2.35.622.567 I slot print_timing: id 2 | task 4684 | eval time = 230.55 ms / 2 tokens ( 230.55 ms per token, 4.34 tokens per second) 2.35.622.568 I slot print_timing: id 2 | task 4684 | total time = 1563.10 ms / 1227 tokens 2.35.622.569 I slot print_timing: id 2 | task 4684 | graphs reused = 3542 2.35.622.569 I slot print_timing: id 2 | task 4684 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.622.603 I slot release: id 2 | task 4684 | stop processing: n_tokens = 1226, truncated = 0 2.35.902.892 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1237, t_last = 155530511 2.35.902.985 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.836 MiB) 2.35.955.913 I slot launch_slot_: id 1 | task 4696 | processing task, is_child = 0 2.35.956.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.088 MiB) 2.36.011.923 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1226, t_last = 155530873 2.36.012.145 I slot launch_slot_: id 2 | task 4697 | processing task, is_child = 0 2.36.287.459 I slot print_timing: id 0 | task 4688 | prompt eval time = 1454.83 ms / 1290 tokens ( 1.13 ms per token, 886.70 tokens per second) 2.36.287.464 I slot print_timing: id 0 | task 4688 | eval time = 384.57 ms / 2 tokens ( 384.57 ms per token, 2.60 tokens per second) 2.36.287.465 I slot print_timing: id 0 | task 4688 | total time = 1839.39 ms / 1292 tokens 2.36.287.466 I slot print_timing: id 0 | task 4688 | graphs reused = 3542 2.36.287.467 I slot print_timing: id 0 | task 4688 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.287.526 I slot release: id 0 | task 4688 | stop processing: n_tokens = 1291, truncated = 0 2.36.634.957 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 156195796 2.36.635.053 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.618 MiB) 2.36.687.463 I slot launch_slot_: id 0 | task 4700 | processing task, is_child = 0 2.38.003.607 I slot print_timing: id 3 | task 4692 | prompt eval time = 2310.50 ms / 2587 tokens ( 0.89 ms per token, 1119.67 tokens per second) 2.38.003.613 I slot print_timing: id 3 | task 4692 | eval time = 487.25 ms / 2 tokens ( 487.25 ms per token, 2.05 tokens per second) 2.38.003.615 I slot print_timing: id 3 | task 4692 | total time = 2797.75 ms / 2589 tokens 2.38.003.616 I slot print_timing: id 3 | task 4692 | graphs reused = 3542 2.38.003.616 I slot print_timing: id 3 | task 4692 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.003.747 I slot release: id 3 | task 4692 | stop processing: n_tokens = 2588, truncated = 0 2.38.147.252 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2588, t_last = 157912018 2.38.147.402 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.056 MiB) 2.38.151.996 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.681 MiB) 2.38.215.761 I slot launch_slot_: id 3 | task 4705 | processing task, is_child = 0 2.38.403.832 I slot print_timing: id 1 | task 4696 | prompt eval time = 2135.08 ms / 2742 tokens ( 0.78 ms per token, 1284.26 tokens per second) 2.38.403.838 I slot print_timing: id 1 | task 4696 | eval time = 256.58 ms / 2 tokens ( 256.58 ms per token, 3.90 tokens per second) 2.38.403.839 I slot print_timing: id 1 | task 4696 | total time = 2391.66 ms / 2744 tokens 2.38.403.840 I slot print_timing: id 1 | task 4696 | graphs reused = 3542 2.38.403.841 I slot print_timing: id 1 | task 4696 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.403.953 I slot release: id 1 | task 4696 | stop processing: n_tokens = 2743, truncated = 0 2.38.531.083 I slot print_timing: id 2 | task 4697 | prompt eval time = 2389.19 ms / 2500 tokens ( 0.96 ms per token, 1046.38 tokens per second) 2.38.531.088 I slot print_timing: id 2 | task 4697 | eval time = 126.30 ms / 2 tokens ( 126.30 ms per token, 7.92 tokens per second) 2.38.531.089 I slot print_timing: id 2 | task 4697 | total time = 2515.48 ms / 2502 tokens 2.38.531.090 I slot print_timing: id 2 | task 4697 | graphs reused = 3542 2.38.531.090 I slot print_timing: id 2 | task 4697 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.531.195 I slot release: id 2 | task 4697 | stop processing: n_tokens = 2501, truncated = 0 2.38.531.210 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2743, t_last = 158312224 2.38.531.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.253 MiB) 2.38.590.096 I slot launch_slot_: id 1 | task 4708 | processing task, is_child = 0 2.38.590.222 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.939 MiB) 2.38.653.531 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2501, t_last = 158439466 2.38.653.807 I slot launch_slot_: id 2 | task 4709 | processing task, is_child = 0 2.38.940.920 I slot print_timing: id 0 | task 4700 | prompt eval time = 1843.28 ms / 2655 tokens ( 0.69 ms per token, 1440.37 tokens per second) 2.38.940.926 I slot print_timing: id 0 | task 4700 | eval time = 410.14 ms / 2 tokens ( 410.14 ms per token, 2.44 tokens per second) 2.38.940.927 I slot print_timing: id 0 | task 4700 | total time = 2253.42 ms / 2657 tokens 2.38.940.928 I slot print_timing: id 0 | task 4700 | graphs reused = 3542 2.38.940.929 I slot print_timing: id 0 | task 4700 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.941.043 I slot release: id 0 | task 4700 | stop processing: n_tokens = 2656, truncated = 0 2.39.138.730 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2656, t_last = 158849314 2.39.138.876 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 290.657 MiB) 2.39.205.875 I slot launch_slot_: id 0 | task 4712 | processing task, is_child = 0 2.40.489.357 I slot print_timing: id 3 | task 4705 | prompt eval time = 2158.26 ms / 1779 tokens ( 1.21 ms per token, 824.28 tokens per second) 2.40.489.362 I slot print_timing: id 3 | task 4705 | eval time = 94.83 ms / 2 tokens ( 94.83 ms per token, 10.55 tokens per second) 2.40.489.363 I slot print_timing: id 3 | task 4705 | total time = 2253.08 ms / 1781 tokens 2.40.489.364 I slot print_timing: id 3 | task 4705 | graphs reused = 3542 2.40.489.365 I slot print_timing: id 3 | task 4705 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.489.448 I slot release: id 3 | task 4705 | stop processing: n_tokens = 1780, truncated = 0 2.40.613.133 I slot print_timing: id 1 | task 4708 | prompt eval time = 1834.63 ms / 1841 tokens ( 1.00 ms per token, 1003.47 tokens per second) 2.40.613.139 I slot print_timing: id 1 | task 4708 | eval time = 124.67 ms / 2 tokens ( 124.67 ms per token, 8.02 tokens per second) 2.40.613.140 I slot print_timing: id 1 | task 4708 | total time = 1959.30 ms / 1843 tokens 2.40.613.141 I slot print_timing: id 1 | task 4708 | graphs reused = 3542 2.40.613.142 I slot print_timing: id 1 | task 4708 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.613.228 I slot release: id 1 | task 4708 | stop processing: n_tokens = 1842, truncated = 0 2.40.613.539 I slot print_timing: id 2 | task 4709 | prompt eval time = 1831.57 ms / 2048 tokens ( 0.89 ms per token, 1118.17 tokens per second) 2.40.613.542 I slot print_timing: id 2 | task 4709 | eval time = 124.47 ms / 2 tokens ( 124.47 ms per token, 8.03 tokens per second) 2.40.613.543 I slot print_timing: id 2 | task 4709 | total time = 1956.03 ms / 2050 tokens 2.40.613.543 I slot print_timing: id 2 | task 4709 | graphs reused = 3542 2.40.613.544 I slot print_timing: id 2 | task 4709 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.613.606 I slot release: id 2 | task 4709 | stop processing: n_tokens = 2049, truncated = 0 2.40.613.621 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.756 (> 0.100 thold), f_keep = 0.806 2.40.613.774 I slot launch_slot_: id 1 | task 4718 | processing task, is_child = 0 2.40.613.903 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.052 MiB) 2.40.674.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.553 MiB) 2.40.733.035 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.833 (> 0.100 thold), f_keep = 0.724 2.40.733.182 I slot launch_slot_: id 2 | task 4719 | processing task, is_child = 0 2.40.733.287 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1780, t_last = 160397719 2.40.733.470 I slot launch_slot_: id 3 | task 4720 | processing task, is_child = 0 2.41.127.616 I slot print_timing: id 0 | task 4712 | prompt eval time = 1830.74 ms / 1852 tokens ( 0.99 ms per token, 1011.61 tokens per second) 2.41.127.622 I slot print_timing: id 0 | task 4712 | eval time = 90.98 ms / 2 tokens ( 90.98 ms per token, 10.99 tokens per second) 2.41.127.623 I slot print_timing: id 0 | task 4712 | total time = 1921.71 ms / 1854 tokens 2.41.127.624 I slot print_timing: id 0 | task 4712 | graphs reused = 3542 2.41.127.624 I slot print_timing: id 0 | task 4712 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.127.710 I slot release: id 0 | task 4712 | stop processing: n_tokens = 1853, truncated = 0 2.41.252.703 I slot print_timing: id 1 | task 4718 | prompt eval time = 384.36 ms / 515 tokens ( 0.75 ms per token, 1339.88 tokens per second) 2.41.252.709 I slot print_timing: id 1 | task 4718 | eval time = 124.26 ms / 2 tokens ( 124.26 ms per token, 8.05 tokens per second) 2.41.252.710 I slot print_timing: id 1 | task 4718 | total time = 508.62 ms / 517 tokens 2.41.252.711 I slot print_timing: id 1 | task 4718 | graphs reused = 3542 2.41.252.712 I slot print_timing: id 1 | task 4718 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.252.800 I slot release: id 1 | task 4718 | stop processing: n_tokens = 1963, truncated = 0 2.41.253.125 I slot print_timing: id 2 | task 4719 | prompt eval time = 367.30 ms / 334 tokens ( 1.10 ms per token, 909.35 tokens per second) 2.41.253.128 I slot print_timing: id 2 | task 4719 | eval time = 124.12 ms / 2 tokens ( 124.12 ms per token, 8.06 tokens per second) 2.41.253.129 I slot print_timing: id 2 | task 4719 | total time = 491.41 ms / 336 tokens 2.41.253.129 I slot print_timing: id 2 | task 4719 | graphs reused = 3542 2.41.253.130 I slot print_timing: id 2 | task 4719 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.253.183 I slot release: id 2 | task 4719 | stop processing: n_tokens = 1782, truncated = 0 2.41.253.195 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1853, t_last = 161035981 2.41.253.310 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.148 MiB) 2.41.258.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.149 MiB) 2.41.319.663 I slot launch_slot_: id 0 | task 4724 | processing task, is_child = 0 2.41.319.777 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.365 MiB) 2.41.379.694 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.490 MiB) 2.41.426.424 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1963, t_last = 161161071 2.41.426.675 I slot launch_slot_: id 1 | task 4725 | processing task, is_child = 0 2.41.426.773 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1782, t_last = 161161454 2.41.426.965 I slot launch_slot_: id 2 | task 4726 | processing task, is_child = 0 2.42.061.712 I slot print_timing: id 3 | task 4720 | prompt eval time = 953.27 ms / 726 tokens ( 1.31 ms per token, 761.59 tokens per second) 2.42.061.718 I slot print_timing: id 3 | task 4720 | eval time = 328.08 ms / 2 tokens ( 328.08 ms per token, 3.05 tokens per second) 2.42.061.719 I slot print_timing: id 3 | task 4720 | total time = 1281.35 ms / 728 tokens 2.42.061.721 I slot print_timing: id 3 | task 4720 | graphs reused = 3542 2.42.061.721 I slot print_timing: id 3 | task 4720 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.061.763 I slot release: id 3 | task 4720 | stop processing: n_tokens = 727, truncated = 0 2.42.184.404 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.884 2.42.184.554 I slot launch_slot_: id 3 | task 4731 | processing task, is_child = 0 2.42.340.604 I slot print_timing: id 0 | task 4724 | prompt eval time = 870.92 ms / 748 tokens ( 1.16 ms per token, 858.86 tokens per second) 2.42.340.610 I slot print_timing: id 0 | task 4724 | eval time = 42.70 ms / 2 tokens ( 42.70 ms per token, 23.42 tokens per second) 2.42.340.611 I slot print_timing: id 0 | task 4724 | total time = 913.62 ms / 750 tokens 2.42.340.612 I slot print_timing: id 0 | task 4724 | graphs reused = 3542 2.42.340.612 I slot print_timing: id 0 | task 4724 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.340.653 I slot release: id 0 | task 4724 | stop processing: n_tokens = 749, truncated = 0 2.42.340.926 I slot print_timing: id 1 | task 4725 | prompt eval time = 868.10 ms / 725 tokens ( 1.20 ms per token, 835.16 tokens per second) 2.42.340.929 I slot print_timing: id 1 | task 4725 | eval time = 42.34 ms / 2 tokens ( 42.34 ms per token, 23.62 tokens per second) 2.42.340.930 I slot print_timing: id 1 | task 4725 | total time = 910.43 ms / 727 tokens 2.42.340.930 I slot print_timing: id 1 | task 4725 | graphs reused = 3542 2.42.340.931 I slot print_timing: id 1 | task 4725 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.340.953 I slot release: id 1 | task 4725 | stop processing: n_tokens = 726, truncated = 0 2.42.341.216 I slot print_timing: id 2 | task 4726 | prompt eval time = 862.85 ms / 761 tokens ( 1.13 ms per token, 881.97 tokens per second) 2.42.341.219 I slot print_timing: id 2 | task 4726 | eval time = 41.95 ms / 2 tokens ( 41.95 ms per token, 23.84 tokens per second) 2.42.341.220 I slot print_timing: id 2 | task 4726 | total time = 904.79 ms / 763 tokens 2.42.341.220 I slot print_timing: id 2 | task 4726 | graphs reused = 3542 2.42.341.221 I slot print_timing: id 2 | task 4726 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.341.241 I slot release: id 2 | task 4726 | stop processing: n_tokens = 762, truncated = 0 2.42.355.027 I slot print_timing: id 3 | task 4731 | prompt eval time = 116.79 ms / 124 tokens ( 0.94 ms per token, 1061.72 tokens per second) 2.42.355.032 I slot print_timing: id 3 | task 4731 | eval time = 13.14 ms / 2 tokens ( 13.14 ms per token, 76.09 tokens per second) 2.42.355.033 I slot print_timing: id 3 | task 4731 | total time = 129.94 ms / 126 tokens 2.42.355.033 I slot print_timing: id 3 | task 4731 | graphs reused = 3542 2.42.355.034 I slot print_timing: id 3 | task 4731 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.355.069 I slot release: id 3 | task 4731 | stop processing: n_tokens = 740, truncated = 0 2.42.355.077 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 749, t_last = 162248923 2.42.355.139 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.615 MiB) 2.42.401.663 I slot launch_slot_: id 0 | task 4735 | processing task, is_child = 0 2.42.401.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.023 MiB) 2.42.453.693 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.650 MiB) 2.42.503.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.431 MiB) 2.42.550.315 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 162249223 2.42.550.513 I slot launch_slot_: id 1 | task 4736 | processing task, is_child = 0 2.42.550.612 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 162249511 2.42.550.752 I slot launch_slot_: id 2 | task 4737 | processing task, is_child = 0 2.42.550.801 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 162263338 2.42.550.929 I slot launch_slot_: id 3 | task 4738 | processing task, is_child = 0 2.43.669.811 I slot print_timing: id 0 | task 4735 | prompt eval time = 1100.37 ms / 798 tokens ( 1.38 ms per token, 725.21 tokens per second) 2.43.669.817 I slot print_timing: id 0 | task 4735 | eval time = 18.50 ms / 2 tokens ( 18.50 ms per token, 54.07 tokens per second) 2.43.669.818 I slot print_timing: id 0 | task 4735 | total time = 1118.86 ms / 800 tokens 2.43.669.819 I slot print_timing: id 0 | task 4735 | graphs reused = 3542 2.43.669.820 I slot print_timing: id 0 | task 4735 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.669.865 I slot release: id 0 | task 4735 | stop processing: n_tokens = 799, truncated = 0 2.43.670.187 I slot print_timing: id 1 | task 4736 | prompt eval time = 1097.59 ms / 809 tokens ( 1.36 ms per token, 737.07 tokens per second) 2.43.670.191 I slot print_timing: id 1 | task 4736 | eval time = 18.23 ms / 2 tokens ( 18.23 ms per token, 54.85 tokens per second) 2.43.670.191 I slot print_timing: id 1 | task 4736 | total time = 1115.82 ms / 811 tokens 2.43.670.192 I slot print_timing: id 1 | task 4736 | graphs reused = 3542 2.43.670.193 I slot print_timing: id 1 | task 4736 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.670.224 I slot release: id 1 | task 4736 | stop processing: n_tokens = 810, truncated = 0 2.43.670.527 I slot print_timing: id 2 | task 4737 | prompt eval time = 1094.73 ms / 1042 tokens ( 1.05 ms per token, 951.83 tokens per second) 2.43.670.530 I slot print_timing: id 2 | task 4737 | eval time = 18.01 ms / 2 tokens ( 18.01 ms per token, 55.52 tokens per second) 2.43.670.531 I slot print_timing: id 2 | task 4737 | total time = 1112.74 ms / 1044 tokens 2.43.670.532 I slot print_timing: id 2 | task 4737 | graphs reused = 3542 2.43.670.532 I slot print_timing: id 2 | task 4737 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.670.566 I slot release: id 2 | task 4737 | stop processing: n_tokens = 1043, truncated = 0 2.43.670.867 I slot print_timing: id 3 | task 4738 | prompt eval time = 1090.12 ms / 799 tokens ( 1.36 ms per token, 732.94 tokens per second) 2.43.670.871 I slot print_timing: id 3 | task 4738 | eval time = 17.78 ms / 2 tokens ( 17.78 ms per token, 56.24 tokens per second) 2.43.670.871 I slot print_timing: id 3 | task 4738 | total time = 1107.91 ms / 801 tokens 2.43.670.872 I slot print_timing: id 3 | task 4738 | graphs reused = 3542 2.43.670.872 I slot print_timing: id 3 | task 4738 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.670.899 I slot release: id 3 | task 4738 | stop processing: n_tokens = 800, truncated = 0 2.43.684.478 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 163578134 2.43.684.550 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.900 MiB) 2.43.733.803 I slot launch_slot_: id 0 | task 4746 | processing task, is_child = 0 2.43.733.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.588 MiB) 2.43.784.857 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.271 MiB) 2.43.833.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.240 MiB) 2.43.882.108 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 163578494 2.43.882.309 I slot launch_slot_: id 1 | task 4747 | processing task, is_child = 0 2.43.882.419 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1043, t_last = 163578836 2.43.882.568 I slot launch_slot_: id 2 | task 4748 | processing task, is_child = 0 2.43.882.618 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 163579168 2.43.882.751 I slot launch_slot_: id 3 | task 4749 | processing task, is_child = 0 2.44.995.584 I slot print_timing: id 0 | task 4746 | prompt eval time = 1093.86 ms / 839 tokens ( 1.30 ms per token, 767.01 tokens per second) 2.44.995.589 I slot print_timing: id 0 | task 4746 | eval time = 18.95 ms / 2 tokens ( 18.95 ms per token, 52.76 tokens per second) 2.44.995.590 I slot print_timing: id 0 | task 4746 | total time = 1112.81 ms / 841 tokens 2.44.995.591 I slot print_timing: id 0 | task 4746 | graphs reused = 3543 2.44.995.591 I slot print_timing: id 0 | task 4746 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.995.639 I slot release: id 0 | task 4746 | stop processing: n_tokens = 840, truncated = 0 2.44.995.990 I slot print_timing: id 1 | task 4747 | prompt eval time = 1090.97 ms / 910 tokens ( 1.20 ms per token, 834.12 tokens per second) 2.44.995.994 I slot print_timing: id 1 | task 4747 | eval time = 18.74 ms / 2 tokens ( 18.74 ms per token, 53.37 tokens per second) 2.44.995.994 I slot print_timing: id 1 | task 4747 | total time = 1109.71 ms / 912 tokens 2.44.995.995 I slot print_timing: id 1 | task 4747 | graphs reused = 3543 2.44.995.996 I slot print_timing: id 1 | task 4747 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.996.031 I slot release: id 1 | task 4747 | stop processing: n_tokens = 911, truncated = 0 2.44.996.403 I slot print_timing: id 2 | task 4748 | prompt eval time = 1088.22 ms / 901 tokens ( 1.21 ms per token, 827.96 tokens per second) 2.44.996.406 I slot print_timing: id 2 | task 4748 | eval time = 18.51 ms / 2 tokens ( 18.51 ms per token, 54.03 tokens per second) 2.44.996.406 I slot print_timing: id 2 | task 4748 | total time = 1106.73 ms / 903 tokens 2.44.996.407 I slot print_timing: id 2 | task 4748 | graphs reused = 3543 2.44.996.407 I slot print_timing: id 2 | task 4748 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.996.438 I slot release: id 2 | task 4748 | stop processing: n_tokens = 902, truncated = 0 2.44.996.814 I slot print_timing: id 3 | task 4749 | prompt eval time = 1085.48 ms / 845 tokens ( 1.28 ms per token, 778.46 tokens per second) 2.44.996.817 I slot print_timing: id 3 | task 4749 | eval time = 18.27 ms / 2 tokens ( 18.27 ms per token, 54.73 tokens per second) 2.44.996.817 I slot print_timing: id 3 | task 4749 | total time = 1103.75 ms / 847 tokens 2.44.996.818 I slot print_timing: id 3 | task 4749 | graphs reused = 3543 2.44.996.819 I slot print_timing: id 3 | task 4749 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.996.845 I slot release: id 3 | task 4749 | stop processing: n_tokens = 846, truncated = 0 2.45.010.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 840, t_last = 164903908 2.45.010.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.775 MiB) 2.45.065.164 I slot launch_slot_: id 0 | task 4757 | processing task, is_child = 0 2.45.065.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.087 MiB) 2.45.119.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.338 MiB) 2.45.173.626 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.367 MiB) 2.45.216.471 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 164904300 2.45.216.680 I slot launch_slot_: id 1 | task 4758 | processing task, is_child = 0 2.45.216.784 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 902, t_last = 164904708 2.45.216.935 I slot launch_slot_: id 2 | task 4759 | processing task, is_child = 0 2.45.216.991 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 2.45.217.076 I slot launch_slot_: id 3 | task 4760 | processing task, is_child = 0 2.45.705.415 I slot print_timing: id 3 | task 4760 | prompt eval time = 306.93 ms / 139 tokens ( 2.21 ms per token, 452.87 tokens per second) 2.45.705.421 I slot print_timing: id 3 | task 4760 | eval time = 171.05 ms / 2 tokens ( 171.05 ms per token, 5.85 tokens per second) 2.45.705.422 I slot print_timing: id 3 | task 4760 | total time = 477.98 ms / 141 tokens 2.45.705.423 I slot print_timing: id 3 | task 4760 | graphs reused = 3543 2.45.705.424 I slot print_timing: id 3 | task 4760 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.705.472 I slot release: id 3 | task 4760 | stop processing: n_tokens = 863, truncated = 0 2.45.945.779 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 165613742 2.45.945.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.117 MiB) 2.46.024.204 I slot launch_slot_: id 3 | task 4765 | processing task, is_child = 0 2.46.284.630 I slot print_timing: id 0 | task 4757 | prompt eval time = 965.83 ms / 688 tokens ( 1.40 ms per token, 712.34 tokens per second) 2.46.284.636 I slot print_timing: id 0 | task 4757 | eval time = 101.70 ms / 2 tokens ( 101.70 ms per token, 9.83 tokens per second) 2.46.284.637 I slot print_timing: id 0 | task 4757 | total time = 1067.53 ms / 690 tokens 2.46.284.638 I slot print_timing: id 0 | task 4757 | graphs reused = 3543 2.46.284.639 I slot print_timing: id 0 | task 4757 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.284.680 I slot release: id 0 | task 4757 | stop processing: n_tokens = 689, truncated = 0 2.46.391.950 I slot print_timing: id 1 | task 4758 | prompt eval time = 1064.77 ms / 851 tokens ( 1.25 ms per token, 799.24 tokens per second) 2.46.391.956 I slot print_timing: id 1 | task 4758 | eval time = 106.58 ms / 2 tokens ( 106.58 ms per token, 9.38 tokens per second) 2.46.391.957 I slot print_timing: id 1 | task 4758 | total time = 1171.35 ms / 853 tokens 2.46.391.958 I slot print_timing: id 1 | task 4758 | graphs reused = 3543 2.46.391.958 I slot print_timing: id 1 | task 4758 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.392.004 I slot release: id 1 | task 4758 | stop processing: n_tokens = 852, truncated = 0 2.46.392.336 I slot print_timing: id 2 | task 4759 | prompt eval time = 1061.94 ms / 825 tokens ( 1.29 ms per token, 776.88 tokens per second) 2.46.392.339 I slot print_timing: id 2 | task 4759 | eval time = 106.38 ms / 2 tokens ( 106.38 ms per token, 9.40 tokens per second) 2.46.392.340 I slot print_timing: id 2 | task 4759 | total time = 1168.31 ms / 827 tokens 2.46.392.340 I slot print_timing: id 2 | task 4759 | graphs reused = 3543 2.46.392.341 I slot print_timing: id 2 | task 4759 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.392.368 I slot release: id 2 | task 4759 | stop processing: n_tokens = 826, truncated = 0 2.46.392.381 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 689, t_last = 166192949 2.46.428.342 I slot launch_slot_: id 0 | task 4769 | processing task, is_child = 0 2.46.428.407 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.493 MiB) 2.46.476.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.399 MiB) 2.46.523.362 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 852, t_last = 166300273 2.46.523.551 I slot launch_slot_: id 1 | task 4770 | processing task, is_child = 0 2.46.523.605 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 166300637 2.46.523.747 I slot launch_slot_: id 2 | task 4771 | processing task, is_child = 0 2.47.169.441 I slot print_timing: id 3 | task 4765 | prompt eval time = 779.75 ms / 769 tokens ( 1.01 ms per token, 986.22 tokens per second) 2.47.169.448 I slot print_timing: id 3 | task 4765 | eval time = 335.63 ms / 2 tokens ( 335.63 ms per token, 2.98 tokens per second) 2.47.169.449 I slot print_timing: id 3 | task 4765 | total time = 1115.38 ms / 771 tokens 2.47.169.450 I slot print_timing: id 3 | task 4765 | graphs reused = 3543 2.47.169.451 I slot print_timing: id 3 | task 4765 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.169.498 I slot release: id 3 | task 4765 | stop processing: n_tokens = 770, truncated = 0 2.47.291.069 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 167077767 2.47.291.135 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.938 MiB) 2.47.335.416 I slot launch_slot_: id 3 | task 4776 | processing task, is_child = 0 2.47.479.936 I slot print_timing: id 0 | task 4769 | prompt eval time = 896.15 ms / 752 tokens ( 1.19 ms per token, 839.15 tokens per second) 2.47.479.942 I slot print_timing: id 0 | task 4769 | eval time = 60.02 ms / 2 tokens ( 60.02 ms per token, 16.66 tokens per second) 2.47.479.943 I slot print_timing: id 0 | task 4769 | total time = 956.17 ms / 754 tokens 2.47.479.943 I slot print_timing: id 0 | task 4769 | graphs reused = 3543 2.47.479.944 I slot print_timing: id 0 | task 4769 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.479.983 I slot release: id 0 | task 4769 | stop processing: n_tokens = 753, truncated = 0 2.47.480.287 I slot print_timing: id 1 | task 4770 | prompt eval time = 893.55 ms / 713 tokens ( 1.25 ms per token, 797.94 tokens per second) 2.47.480.291 I slot print_timing: id 1 | task 4770 | eval time = 59.61 ms / 2 tokens ( 59.61 ms per token, 16.78 tokens per second) 2.47.480.292 I slot print_timing: id 1 | task 4770 | total time = 953.16 ms / 715 tokens 2.47.480.292 I slot print_timing: id 1 | task 4770 | graphs reused = 3543 2.47.480.293 I slot print_timing: id 1 | task 4770 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.480.323 I slot release: id 1 | task 4770 | stop processing: n_tokens = 714, truncated = 0 2.47.480.641 I slot print_timing: id 2 | task 4771 | prompt eval time = 890.86 ms / 736 tokens ( 1.21 ms per token, 826.17 tokens per second) 2.47.480.644 I slot print_timing: id 2 | task 4771 | eval time = 59.22 ms / 2 tokens ( 59.22 ms per token, 16.89 tokens per second) 2.47.480.645 I slot print_timing: id 2 | task 4771 | total time = 950.08 ms / 738 tokens 2.47.480.645 I slot print_timing: id 2 | task 4771 | graphs reused = 3543 2.47.480.646 I slot print_timing: id 2 | task 4771 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.480.671 I slot release: id 2 | task 4771 | stop processing: n_tokens = 737, truncated = 0 2.47.499.973 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.884 2.47.500.086 I slot launch_slot_: id 1 | task 4780 | processing task, is_child = 0 2.47.500.147 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.594 MiB) 2.47.598.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.626 MiB) 2.47.650.223 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.856 2.47.650.371 I slot launch_slot_: id 2 | task 4781 | processing task, is_child = 0 2.47.650.431 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 167388253 2.47.663.555 I slot launch_slot_: id 0 | task 4782 | processing task, is_child = 0 2.47.958.149 I slot print_timing: id 0 | task 4782 | prompt eval time = 274.22 ms / 112 tokens ( 2.45 ms per token, 408.43 tokens per second) 2.47.958.170 I slot print_timing: id 0 | task 4782 | eval time = 20.33 ms / 2 tokens ( 20.33 ms per token, 49.20 tokens per second) 2.47.958.172 I slot print_timing: id 0 | task 4782 | total time = 294.55 ms / 114 tokens 2.47.958.173 I slot print_timing: id 0 | task 4782 | graphs reused = 3543 2.47.958.175 I slot print_timing: id 0 | task 4782 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.958.272 I slot release: id 0 | task 4782 | stop processing: n_tokens = 716, truncated = 0 2.47.959.232 I slot print_timing: id 1 | task 4780 | prompt eval time = 255.33 ms / 106 tokens ( 2.41 ms per token, 415.15 tokens per second) 2.47.959.244 I slot print_timing: id 1 | task 4780 | eval time = 20.63 ms / 2 tokens ( 20.63 ms per token, 48.47 tokens per second) 2.47.959.245 I slot print_timing: id 1 | task 4780 | total time = 275.96 ms / 108 tokens 2.47.959.246 I slot print_timing: id 1 | task 4780 | graphs reused = 3543 2.47.959.247 I slot print_timing: id 1 | task 4780 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.959.299 I slot release: id 1 | task 4780 | stop processing: n_tokens = 710, truncated = 0 2.47.960.268 I slot print_timing: id 2 | task 4781 | prompt eval time = 236.46 ms / 107 tokens ( 2.21 ms per token, 452.52 tokens per second) 2.47.960.286 I slot print_timing: id 2 | task 4781 | eval time = 20.91 ms / 2 tokens ( 20.91 ms per token, 47.83 tokens per second) 2.47.960.287 I slot print_timing: id 2 | task 4781 | total time = 257.36 ms / 109 tokens 2.47.960.288 I slot print_timing: id 2 | task 4781 | graphs reused = 3543 2.47.960.290 I slot print_timing: id 2 | task 4781 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.960.350 I slot release: id 2 | task 4781 | stop processing: n_tokens = 711, truncated = 0 2.47.961.292 I slot print_timing: id 3 | task 4776 | prompt eval time = 574.34 ms / 719 tokens ( 0.80 ms per token, 1251.87 tokens per second) 2.47.961.303 I slot print_timing: id 3 | task 4776 | eval time = 21.16 ms / 2 tokens ( 21.16 ms per token, 47.26 tokens per second) 2.47.961.305 I slot print_timing: id 3 | task 4776 | total time = 595.50 ms / 721 tokens 2.47.961.305 I slot print_timing: id 3 | task 4776 | graphs reused = 3543 2.47.961.307 I slot print_timing: id 3 | task 4776 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.961.353 I slot release: id 3 | task 4776 | stop processing: n_tokens = 720, truncated = 0 2.47.984.052 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.881 2.47.984.213 I slot launch_slot_: id 0 | task 4786 | processing task, is_child = 0 2.48.020.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.187 MiB) 2.48.073.386 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 337.035 MiB) 2.48.120.171 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.893 2.48.120.321 I slot launch_slot_: id 1 | task 4787 | processing task, is_child = 0 2.48.120.422 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.887 2.48.120.517 I slot launch_slot_: id 2 | task 4788 | processing task, is_child = 0 2.48.120.568 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.876 2.48.120.655 I slot launch_slot_: id 3 | task 4789 | processing task, is_child = 0 2.48.424.450 I slot print_timing: id 0 | task 4786 | prompt eval time = 285.15 ms / 104 tokens ( 2.74 ms per token, 364.72 tokens per second) 2.48.424.457 I slot print_timing: id 0 | task 4786 | eval time = 18.62 ms / 2 tokens ( 18.62 ms per token, 53.69 tokens per second) 2.48.424.458 I slot print_timing: id 0 | task 4786 | total time = 303.78 ms / 106 tokens 2.48.424.459 I slot print_timing: id 0 | task 4786 | graphs reused = 3543 2.48.424.459 I slot print_timing: id 0 | task 4786 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.424.500 I slot release: id 0 | task 4786 | stop processing: n_tokens = 708, truncated = 0 2.48.424.793 I slot print_timing: id 1 | task 4787 | prompt eval time = 265.86 ms / 114 tokens ( 2.33 ms per token, 428.80 tokens per second) 2.48.424.797 I slot print_timing: id 1 | task 4787 | eval time = 18.28 ms / 2 tokens ( 18.28 ms per token, 54.70 tokens per second) 2.48.424.798 I slot print_timing: id 1 | task 4787 | total time = 284.14 ms / 116 tokens 2.48.424.798 I slot print_timing: id 1 | task 4787 | graphs reused = 3543 2.48.424.799 I slot print_timing: id 1 | task 4787 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.424.824 I slot release: id 1 | task 4787 | stop processing: n_tokens = 718, truncated = 0 2.48.425.112 I slot print_timing: id 2 | task 4788 | prompt eval time = 245.67 ms / 148 tokens ( 1.66 ms per token, 602.43 tokens per second) 2.48.425.115 I slot print_timing: id 2 | task 4788 | eval time = 17.92 ms / 2 tokens ( 17.92 ms per token, 55.81 tokens per second) 2.48.425.115 I slot print_timing: id 2 | task 4788 | total time = 263.59 ms / 150 tokens 2.48.425.116 I slot print_timing: id 2 | task 4788 | graphs reused = 3543 2.48.425.116 I slot print_timing: id 2 | task 4788 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.425.139 I slot release: id 2 | task 4788 | stop processing: n_tokens = 752, truncated = 0 2.48.425.480 I slot print_timing: id 3 | task 4789 | prompt eval time = 226.18 ms / 113 tokens ( 2.00 ms per token, 499.60 tokens per second) 2.48.425.486 I slot print_timing: id 3 | task 4789 | eval time = 17.58 ms / 2 tokens ( 17.58 ms per token, 56.89 tokens per second) 2.48.425.487 I slot print_timing: id 3 | task 4789 | total time = 243.76 ms / 115 tokens 2.48.425.488 I slot print_timing: id 3 | task 4789 | graphs reused = 3543 2.48.425.489 I slot print_timing: id 3 | task 4789 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.425.516 I slot release: id 3 | task 4789 | stop processing: n_tokens = 717, truncated = 0 2.48.437.751 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.891 2.48.437.900 I slot launch_slot_: id 0 | task 4793 | processing task, is_child = 0 2.48.437.982 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.467 MiB) 2.48.492.155 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.314 MiB) 2.48.593.800 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 718, t_last = 168333093 2.48.594.024 I slot launch_slot_: id 1 | task 4794 | processing task, is_child = 0 2.48.594.123 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 752, t_last = 168333408 2.48.594.265 I slot launch_slot_: id 2 | task 4795 | processing task, is_child = 0 2.48.594.313 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 168333785 2.48.594.440 I slot launch_slot_: id 3 | task 4796 | processing task, is_child = 0 2.49.081.221 I slot print_timing: id 0 | task 4793 | prompt eval time = 361.80 ms / 106 tokens ( 3.41 ms per token, 292.98 tokens per second) 2.49.081.226 I slot print_timing: id 0 | task 4793 | eval time = 124.96 ms / 2 tokens ( 124.96 ms per token, 8.00 tokens per second) 2.49.081.227 I slot print_timing: id 0 | task 4793 | total time = 486.76 ms / 108 tokens 2.49.081.230 I slot print_timing: id 0 | task 4793 | graphs reused = 3543 2.49.081.231 I slot print_timing: id 0 | task 4793 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.081.273 I slot release: id 0 | task 4793 | stop processing: n_tokens = 710, truncated = 0 2.49.370.534 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 168989543 2.49.370.616 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.331 MiB) 2.49.423.000 I slot launch_slot_: id 0 | task 4801 | processing task, is_child = 0 2.49.813.373 I slot print_timing: id 1 | task 4794 | prompt eval time = 1129.86 ms / 880 tokens ( 1.28 ms per token, 778.86 tokens per second) 2.49.813.378 I slot print_timing: id 1 | task 4794 | eval time = 69.50 ms / 2 tokens ( 69.50 ms per token, 14.39 tokens per second) 2.49.813.379 I slot print_timing: id 1 | task 4794 | total time = 1199.36 ms / 882 tokens 2.49.813.380 I slot print_timing: id 1 | task 4794 | graphs reused = 3543 2.49.813.382 I slot print_timing: id 1 | task 4794 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.813.427 I slot release: id 1 | task 4794 | stop processing: n_tokens = 881, truncated = 0 2.49.813.819 I slot print_timing: id 2 | task 4795 | prompt eval time = 1127.12 ms / 896 tokens ( 1.26 ms per token, 794.95 tokens per second) 2.49.813.822 I slot print_timing: id 2 | task 4795 | eval time = 69.32 ms / 2 tokens ( 69.32 ms per token, 14.43 tokens per second) 2.49.813.823 I slot print_timing: id 2 | task 4795 | total time = 1196.44 ms / 898 tokens 2.49.813.823 I slot print_timing: id 2 | task 4795 | graphs reused = 3543 2.49.813.824 I slot print_timing: id 2 | task 4795 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.813.886 I slot release: id 2 | task 4795 | stop processing: n_tokens = 897, truncated = 0 2.49.814.329 I slot print_timing: id 3 | task 4796 | prompt eval time = 1124.36 ms / 1091 tokens ( 1.03 ms per token, 970.33 tokens per second) 2.49.814.334 I slot print_timing: id 3 | task 4796 | eval time = 69.22 ms / 2 tokens ( 69.22 ms per token, 14.45 tokens per second) 2.49.814.335 I slot print_timing: id 3 | task 4796 | total time = 1193.58 ms / 1093 tokens 2.49.814.336 I slot print_timing: id 3 | task 4796 | graphs reused = 3543 2.49.814.337 I slot print_timing: id 3 | task 4796 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.814.378 I slot release: id 3 | task 4796 | stop processing: n_tokens = 1092, truncated = 0 2.49.830.952 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.895 2.49.831.083 I slot launch_slot_: id 3 | task 4806 | processing task, is_child = 0 2.49.831.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 357.169 MiB) 2.49.916.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.202 MiB) 2.49.980.301 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 169721697 2.49.980.510 I slot launch_slot_: id 1 | task 4807 | processing task, is_child = 0 2.49.980.572 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 169722156 2.49.980.722 I slot launch_slot_: id 2 | task 4808 | processing task, is_child = 0 2.50.479.528 I slot print_timing: id 0 | task 4801 | prompt eval time = 932.01 ms / 1082 tokens ( 0.86 ms per token, 1160.93 tokens per second) 2.50.479.534 I slot print_timing: id 0 | task 4801 | eval time = 124.49 ms / 2 tokens ( 124.49 ms per token, 8.03 tokens per second) 2.50.479.535 I slot print_timing: id 0 | task 4801 | total time = 1056.50 ms / 1084 tokens 2.50.479.535 I slot print_timing: id 0 | task 4801 | graphs reused = 3543 2.50.479.537 I slot print_timing: id 0 | task 4801 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.479.582 I slot release: id 0 | task 4801 | stop processing: n_tokens = 1083, truncated = 0 2.50.479.920 I slot print_timing: id 3 | task 4806 | prompt eval time = 357.87 ms / 174 tokens ( 2.06 ms per token, 486.21 tokens per second) 2.50.479.923 I slot print_timing: id 3 | task 4806 | eval time = 124.11 ms / 2 tokens ( 124.11 ms per token, 8.06 tokens per second) 2.50.479.923 I slot print_timing: id 3 | task 4806 | total time = 481.99 ms / 176 tokens 2.50.479.924 I slot print_timing: id 3 | task 4806 | graphs reused = 3543 2.50.479.924 I slot print_timing: id 3 | task 4806 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.479.957 I slot release: id 3 | task 4806 | stop processing: n_tokens = 1080, truncated = 0 2.50.660.680 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.905 2.50.660.831 I slot launch_slot_: id 3 | task 4813 | processing task, is_child = 0 2.50.660.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.642 MiB) 2.50.715.200 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.901 2.50.715.353 I slot launch_slot_: id 0 | task 4814 | processing task, is_child = 0 2.51.048.595 I slot print_timing: id 0 | task 4814 | prompt eval time = 314.91 ms / 168 tokens ( 1.87 ms per token, 533.48 tokens per second) 2.51.048.600 I slot print_timing: id 0 | task 4814 | eval time = 18.31 ms / 2 tokens ( 18.31 ms per token, 54.63 tokens per second) 2.51.048.602 I slot print_timing: id 0 | task 4814 | total time = 333.22 ms / 170 tokens 2.51.048.603 I slot print_timing: id 0 | task 4814 | graphs reused = 3543 2.51.048.604 I slot print_timing: id 0 | task 4814 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.048.651 I slot release: id 0 | task 4814 | stop processing: n_tokens = 1074, truncated = 0 2.51.048.944 I slot print_timing: id 1 | task 4807 | prompt eval time = 1039.92 ms / 1071 tokens ( 0.97 ms per token, 1029.89 tokens per second) 2.51.048.947 I slot print_timing: id 1 | task 4807 | eval time = 18.04 ms / 2 tokens ( 18.04 ms per token, 55.43 tokens per second) 2.51.048.948 I slot print_timing: id 1 | task 4807 | total time = 1057.96 ms / 1073 tokens 2.51.048.948 I slot print_timing: id 1 | task 4807 | graphs reused = 3543 2.51.048.949 I slot print_timing: id 1 | task 4807 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.048.977 I slot release: id 1 | task 4807 | stop processing: n_tokens = 1072, truncated = 0 2.51.049.280 I slot print_timing: id 2 | task 4808 | prompt eval time = 1037.04 ms / 1085 tokens ( 0.96 ms per token, 1046.24 tokens per second) 2.51.049.283 I slot print_timing: id 2 | task 4808 | eval time = 17.75 ms / 2 tokens ( 17.75 ms per token, 56.34 tokens per second) 2.51.049.284 I slot print_timing: id 2 | task 4808 | total time = 1054.79 ms / 1087 tokens 2.51.049.284 I slot print_timing: id 2 | task 4808 | graphs reused = 3543 2.51.049.285 I slot print_timing: id 2 | task 4808 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.049.310 I slot release: id 2 | task 4808 | stop processing: n_tokens = 1086, truncated = 0 2.51.049.558 I slot print_timing: id 3 | task 4813 | prompt eval time = 275.70 ms / 175 tokens ( 1.58 ms per token, 634.74 tokens per second) 2.51.049.561 I slot print_timing: id 3 | task 4813 | eval time = 17.44 ms / 2 tokens ( 17.44 ms per token, 57.33 tokens per second) 2.51.049.562 I slot print_timing: id 3 | task 4813 | total time = 293.15 ms / 177 tokens 2.51.049.562 I slot print_timing: id 3 | task 4813 | graphs reused = 3543 2.51.049.563 I slot print_timing: id 3 | task 4813 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.049.587 I slot release: id 3 | task 4813 | stop processing: n_tokens = 1081, truncated = 0 2.51.063.007 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.910 2.51.063.124 I slot launch_slot_: id 0 | task 4818 | processing task, is_child = 0 2.51.063.208 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 256.731 MiB) 2.51.111.506 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.676 MiB) 2.51.159.164 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.957 MiB) 2.51.213.788 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.911 2.51.213.932 I slot launch_slot_: id 1 | task 4819 | processing task, is_child = 0 2.51.214.063 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.900 2.51.214.156 I slot launch_slot_: id 2 | task 4820 | processing task, is_child = 0 2.51.214.220 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.904 2.51.214.308 I slot launch_slot_: id 3 | task 4821 | processing task, is_child = 0 2.51.564.720 I slot print_timing: id 0 | task 4818 | prompt eval time = 331.60 ms / 177 tokens ( 1.87 ms per token, 533.77 tokens per second) 2.51.564.727 I slot print_timing: id 0 | task 4818 | eval time = 18.79 ms / 2 tokens ( 18.79 ms per token, 53.22 tokens per second) 2.51.564.728 I slot print_timing: id 0 | task 4818 | total time = 350.39 ms / 179 tokens 2.51.564.729 I slot print_timing: id 0 | task 4818 | graphs reused = 3543 2.51.564.730 I slot print_timing: id 0 | task 4818 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.564.782 I slot release: id 0 | task 4818 | stop processing: n_tokens = 1083, truncated = 0 2.51.565.129 I slot print_timing: id 1 | task 4819 | prompt eval time = 312.70 ms / 183 tokens ( 1.71 ms per token, 585.22 tokens per second) 2.51.565.133 I slot print_timing: id 1 | task 4819 | eval time = 18.51 ms / 2 tokens ( 18.51 ms per token, 54.02 tokens per second) 2.51.565.135 I slot print_timing: id 1 | task 4819 | total time = 331.21 ms / 185 tokens 2.51.565.135 I slot print_timing: id 1 | task 4819 | graphs reused = 3543 2.51.565.136 I slot print_timing: id 1 | task 4819 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.565.173 I slot release: id 1 | task 4819 | stop processing: n_tokens = 1089, truncated = 0 2.51.565.517 I slot print_timing: id 2 | task 4820 | prompt eval time = 293.30 ms / 170 tokens ( 1.73 ms per token, 579.62 tokens per second) 2.51.565.520 I slot print_timing: id 2 | task 4820 | eval time = 18.18 ms / 2 tokens ( 18.18 ms per token, 55.01 tokens per second) 2.51.565.521 I slot print_timing: id 2 | task 4820 | total time = 311.48 ms / 172 tokens 2.51.565.522 I slot print_timing: id 2 | task 4820 | graphs reused = 3543 2.51.565.523 I slot print_timing: id 2 | task 4820 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.565.551 I slot release: id 2 | task 4820 | stop processing: n_tokens = 1076, truncated = 0 2.51.565.883 I slot print_timing: id 3 | task 4821 | prompt eval time = 274.34 ms / 178 tokens ( 1.54 ms per token, 648.83 tokens per second) 2.51.565.886 I slot print_timing: id 3 | task 4821 | eval time = 17.84 ms / 2 tokens ( 17.84 ms per token, 56.06 tokens per second) 2.51.565.887 I slot print_timing: id 3 | task 4821 | total time = 292.18 ms / 180 tokens 2.51.565.887 I slot print_timing: id 3 | task 4821 | graphs reused = 3543 2.51.565.888 I slot print_timing: id 3 | task 4821 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.565.915 I slot release: id 3 | task 4821 | stop processing: n_tokens = 1084, truncated = 0 2.51.579.676 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.902 2.51.579.799 I slot launch_slot_: id 0 | task 4825 | processing task, is_child = 0 2.51.579.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.083 MiB) 2.51.635.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.395 MiB) 2.51.691.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.240 MiB) 2.51.747.094 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.897 2.51.747.231 I slot launch_slot_: id 1 | task 4826 | processing task, is_child = 0 2.51.747.361 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.908 2.51.747.453 I slot launch_slot_: id 2 | task 4827 | processing task, is_child = 0 2.51.747.518 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.901 2.51.747.601 I slot launch_slot_: id 3 | task 4828 | processing task, is_child = 0 2.52.089.660 I slot print_timing: id 0 | task 4825 | prompt eval time = 323.79 ms / 173 tokens ( 1.87 ms per token, 534.31 tokens per second) 2.52.089.666 I slot print_timing: id 0 | task 4825 | eval time = 18.26 ms / 2 tokens ( 18.26 ms per token, 54.77 tokens per second) 2.52.089.667 I slot print_timing: id 0 | task 4825 | total time = 342.04 ms / 175 tokens 2.52.089.667 I slot print_timing: id 0 | task 4825 | graphs reused = 3543 2.52.089.668 I slot print_timing: id 0 | task 4825 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.089.716 I slot release: id 0 | task 4825 | stop processing: n_tokens = 1079, truncated = 0 2.52.090.018 I slot print_timing: id 1 | task 4826 | prompt eval time = 304.68 ms / 175 tokens ( 1.74 ms per token, 574.37 tokens per second) 2.52.090.021 I slot print_timing: id 1 | task 4826 | eval time = 17.98 ms / 2 tokens ( 17.98 ms per token, 55.61 tokens per second) 2.52.090.022 I slot print_timing: id 1 | task 4826 | total time = 322.66 ms / 177 tokens 2.52.090.022 I slot print_timing: id 1 | task 4826 | graphs reused = 3543 2.52.090.023 I slot print_timing: id 1 | task 4826 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.090.051 I slot release: id 1 | task 4826 | stop processing: n_tokens = 1081, truncated = 0 2.52.090.333 I slot print_timing: id 2 | task 4827 | prompt eval time = 285.88 ms / 171 tokens ( 1.67 ms per token, 598.16 tokens per second) 2.52.090.336 I slot print_timing: id 2 | task 4827 | eval time = 17.68 ms / 2 tokens ( 17.68 ms per token, 56.57 tokens per second) 2.52.090.337 I slot print_timing: id 2 | task 4827 | total time = 303.55 ms / 173 tokens 2.52.090.338 I slot print_timing: id 2 | task 4827 | graphs reused = 3543 2.52.090.338 I slot print_timing: id 2 | task 4827 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.090.364 I slot release: id 2 | task 4827 | stop processing: n_tokens = 1077, truncated = 0 2.52.090.617 I slot print_timing: id 3 | task 4828 | prompt eval time = 266.87 ms / 174 tokens ( 1.53 ms per token, 652.01 tokens per second) 2.52.090.619 I slot print_timing: id 3 | task 4828 | eval time = 17.40 ms / 2 tokens ( 17.40 ms per token, 57.47 tokens per second) 2.52.090.620 I slot print_timing: id 3 | task 4828 | total time = 284.27 ms / 176 tokens 2.52.090.621 I slot print_timing: id 3 | task 4828 | graphs reused = 3543 2.52.090.621 I slot print_timing: id 3 | task 4828 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.090.651 I slot release: id 3 | task 4828 | stop processing: n_tokens = 1080, truncated = 0 2.52.102.792 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1079, t_last = 171997986 2.52.102.897 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.584 MiB) 2.52.156.833 I slot launch_slot_: id 0 | task 4832 | processing task, is_child = 0 2.52.156.909 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.871 MiB) 2.52.205.953 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.271 MiB) 2.52.256.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.522 MiB) 2.52.313.353 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1081, t_last = 171998321 2.52.313.575 I slot launch_slot_: id 1 | task 4833 | processing task, is_child = 0 2.52.313.704 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1077, t_last = 171998633 2.52.313.858 I slot launch_slot_: id 2 | task 4834 | processing task, is_child = 0 2.52.313.922 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1080, t_last = 171998920 2.52.314.069 I slot launch_slot_: id 3 | task 4835 | processing task, is_child = 0 2.53.550.758 I slot print_timing: id 0 | task 4832 | prompt eval time = 1218.41 ms / 1017 tokens ( 1.20 ms per token, 834.69 tokens per second) 2.53.550.763 I slot print_timing: id 0 | task 4832 | eval time = 18.26 ms / 2 tokens ( 18.26 ms per token, 54.76 tokens per second) 2.53.550.765 I slot print_timing: id 0 | task 4832 | total time = 1236.67 ms / 1019 tokens 2.53.550.765 I slot print_timing: id 0 | task 4832 | graphs reused = 3543 2.53.550.766 I slot print_timing: id 0 | task 4832 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.550.814 I slot release: id 0 | task 4832 | stop processing: n_tokens = 1018, truncated = 0 2.53.551.103 I slot print_timing: id 1 | task 4833 | prompt eval time = 1215.58 ms / 1106 tokens ( 1.10 ms per token, 909.85 tokens per second) 2.53.551.106 I slot print_timing: id 1 | task 4833 | eval time = 17.97 ms / 2 tokens ( 17.97 ms per token, 55.66 tokens per second) 2.53.551.107 I slot print_timing: id 1 | task 4833 | total time = 1233.55 ms / 1108 tokens 2.53.551.107 I slot print_timing: id 1 | task 4833 | graphs reused = 3543 2.53.551.108 I slot print_timing: id 1 | task 4833 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.551.141 I slot release: id 1 | task 4833 | stop processing: n_tokens = 1107, truncated = 0 2.53.551.454 I slot print_timing: id 2 | task 4834 | prompt eval time = 1212.74 ms / 1071 tokens ( 1.13 ms per token, 883.13 tokens per second) 2.53.551.458 I slot print_timing: id 2 | task 4834 | eval time = 17.64 ms / 2 tokens ( 17.64 ms per token, 56.67 tokens per second) 2.53.551.459 I slot print_timing: id 2 | task 4834 | total time = 1230.38 ms / 1073 tokens 2.53.551.460 I slot print_timing: id 2 | task 4834 | graphs reused = 3543 2.53.551.460 I slot print_timing: id 2 | task 4834 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.551.491 I slot release: id 2 | task 4834 | stop processing: n_tokens = 1072, truncated = 0 2.53.551.735 I slot print_timing: id 3 | task 4835 | prompt eval time = 1209.83 ms / 1031 tokens ( 1.17 ms per token, 852.19 tokens per second) 2.53.551.738 I slot print_timing: id 3 | task 4835 | eval time = 17.37 ms / 2 tokens ( 17.37 ms per token, 57.58 tokens per second) 2.53.551.739 I slot print_timing: id 3 | task 4835 | total time = 1227.20 ms / 1033 tokens 2.53.551.740 I slot print_timing: id 3 | task 4835 | graphs reused = 3543 2.53.551.740 I slot print_timing: id 3 | task 4835 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.551.765 I slot release: id 3 | task 4835 | stop processing: n_tokens = 1032, truncated = 0 2.53.565.044 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.890 2.53.565.187 I slot launch_slot_: id 0 | task 4843 | processing task, is_child = 0 2.53.565.282 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.743 MiB) 2.53.621.386 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.461 MiB) 2.53.676.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.710 MiB) 2.53.719.439 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.818 2.53.719.580 I slot launch_slot_: id 1 | task 4844 | processing task, is_child = 0 2.53.719.705 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1072, t_last = 173459761 2.53.719.863 I slot launch_slot_: id 2 | task 4845 | processing task, is_child = 0 2.53.719.925 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1032, t_last = 173460035 2.53.720.068 I slot launch_slot_: id 3 | task 4846 | processing task, is_child = 0 2.54.203.611 I slot print_timing: id 0 | task 4843 | prompt eval time = 356.66 ms / 167 tokens ( 2.14 ms per token, 468.23 tokens per second) 2.54.203.617 I slot print_timing: id 0 | task 4843 | eval time = 126.86 ms / 2 tokens ( 126.86 ms per token, 7.88 tokens per second) 2.54.203.618 I slot print_timing: id 0 | task 4843 | total time = 483.52 ms / 169 tokens 2.54.203.619 I slot print_timing: id 0 | task 4843 | graphs reused = 3543 2.54.203.620 I slot print_timing: id 0 | task 4843 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.203.678 I slot release: id 0 | task 4843 | stop processing: n_tokens = 1046, truncated = 0 2.54.203.998 I slot print_timing: id 1 | task 4844 | prompt eval time = 336.88 ms / 152 tokens ( 2.22 ms per token, 451.19 tokens per second) 2.54.204.001 I slot print_timing: id 1 | task 4844 | eval time = 126.60 ms / 2 tokens ( 126.60 ms per token, 7.90 tokens per second) 2.54.204.002 I slot print_timing: id 1 | task 4844 | total time = 463.49 ms / 154 tokens 2.54.204.003 I slot print_timing: id 1 | task 4844 | graphs reused = 3543 2.54.204.003 I slot print_timing: id 1 | task 4844 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.204.034 I slot release: id 1 | task 4844 | stop processing: n_tokens = 1031, truncated = 0 2.54.286.924 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1046, t_last = 174111947 2.54.287.028 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.242 MiB) 2.54.343.863 I slot launch_slot_: id 0 | task 4851 | processing task, is_child = 0 2.54.343.935 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.800 MiB) 2.54.385.709 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 174112303 2.54.385.912 I slot launch_slot_: id 1 | task 4852 | processing task, is_child = 0 2.54.669.615 I slot print_timing: id 2 | task 4845 | prompt eval time = 788.80 ms / 753 tokens ( 1.05 ms per token, 954.62 tokens per second) 2.54.669.622 I slot print_timing: id 2 | task 4845 | eval time = 120.82 ms / 2 tokens ( 120.82 ms per token, 8.28 tokens per second) 2.54.669.623 I slot print_timing: id 2 | task 4845 | total time = 909.62 ms / 755 tokens 2.54.669.624 I slot print_timing: id 2 | task 4845 | graphs reused = 3543 2.54.669.626 I slot print_timing: id 2 | task 4845 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.669.671 I slot release: id 2 | task 4845 | stop processing: n_tokens = 754, truncated = 0 2.54.898.349 I slot print_timing: id 3 | task 4846 | prompt eval time = 903.58 ms / 797 tokens ( 1.13 ms per token, 882.05 tokens per second) 2.54.898.356 I slot print_timing: id 3 | task 4846 | eval time = 227.70 ms / 2 tokens ( 227.70 ms per token, 4.39 tokens per second) 2.54.898.357 I slot print_timing: id 3 | task 4846 | total time = 1131.28 ms / 799 tokens 2.54.898.358 I slot print_timing: id 3 | task 4846 | graphs reused = 3543 2.54.898.360 I slot print_timing: id 3 | task 4846 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.898.409 I slot release: id 3 | task 4846 | stop processing: n_tokens = 798, truncated = 0 2.54.898.427 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.863 2.54.898.595 I slot launch_slot_: id 2 | task 4856 | processing task, is_child = 0 2.54.898.665 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.898 MiB) 2.54.954.634 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.816 2.54.954.884 I slot launch_slot_: id 3 | task 4857 | processing task, is_child = 0 2.55.237.584 I slot print_timing: id 0 | task 4851 | prompt eval time = 833.68 ms / 729 tokens ( 1.14 ms per token, 874.44 tokens per second) 2.55.237.590 I slot print_timing: id 0 | task 4851 | eval time = 17.97 ms / 2 tokens ( 17.97 ms per token, 55.64 tokens per second) 2.55.237.591 I slot print_timing: id 0 | task 4851 | total time = 851.65 ms / 731 tokens 2.55.237.592 I slot print_timing: id 0 | task 4851 | graphs reused = 3543 2.55.237.592 I slot print_timing: id 0 | task 4851 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.237.631 I slot release: id 0 | task 4851 | stop processing: n_tokens = 730, truncated = 0 2.55.237.859 I slot print_timing: id 1 | task 4852 | prompt eval time = 830.87 ms / 740 tokens ( 1.12 ms per token, 890.63 tokens per second) 2.55.237.861 I slot print_timing: id 1 | task 4852 | eval time = 17.63 ms / 2 tokens ( 17.63 ms per token, 56.71 tokens per second) 2.55.237.862 I slot print_timing: id 1 | task 4852 | total time = 848.51 ms / 742 tokens 2.55.237.863 I slot print_timing: id 1 | task 4852 | graphs reused = 3543 2.55.237.863 I slot print_timing: id 1 | task 4852 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.237.887 I slot release: id 1 | task 4852 | stop processing: n_tokens = 741, truncated = 0 2.55.238.115 I slot print_timing: id 2 | task 4856 | prompt eval time = 235.22 ms / 123 tokens ( 1.91 ms per token, 522.91 tokens per second) 2.55.238.118 I slot print_timing: id 2 | task 4856 | eval time = 17.33 ms / 2 tokens ( 17.33 ms per token, 57.71 tokens per second) 2.55.238.118 I slot print_timing: id 2 | task 4856 | total time = 252.55 ms / 125 tokens 2.55.238.119 I slot print_timing: id 2 | task 4856 | graphs reused = 3543 2.55.238.119 I slot print_timing: id 2 | task 4856 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.238.173 I slot release: id 2 | task 4856 | stop processing: n_tokens = 747, truncated = 0 2.55.238.471 I slot print_timing: id 3 | task 4857 | prompt eval time = 216.43 ms / 116 tokens ( 1.87 ms per token, 535.96 tokens per second) 2.55.238.475 I slot print_timing: id 3 | task 4857 | eval time = 17.11 ms / 2 tokens ( 17.11 ms per token, 58.44 tokens per second) 2.55.238.476 I slot print_timing: id 3 | task 4857 | total time = 233.54 ms / 118 tokens 2.55.238.477 I slot print_timing: id 3 | task 4857 | graphs reused = 3543 2.55.238.478 I slot print_timing: id 3 | task 4857 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.238.504 I slot release: id 3 | task 4857 | stop processing: n_tokens = 740, truncated = 0 2.55.251.220 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.892 2.55.251.347 I slot launch_slot_: id 0 | task 4861 | processing task, is_child = 0 2.55.251.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.085 MiB) 2.55.298.538 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.333 MiB) 2.55.343.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.802 MiB) 2.55.396.495 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 175146157 2.55.396.698 I slot launch_slot_: id 1 | task 4862 | processing task, is_child = 0 2.55.396.798 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.871 2.55.396.896 I slot launch_slot_: id 2 | task 4863 | processing task, is_child = 0 2.55.396.946 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.862 (> 0.100 thold), f_keep = 0.880 2.55.397.037 I slot launch_slot_: id 3 | task 4864 | processing task, is_child = 0 2.55.783.466 I slot print_timing: id 0 | task 4861 | prompt eval time = 325.31 ms / 110 tokens ( 2.96 ms per token, 338.14 tokens per second) 2.55.783.472 I slot print_timing: id 0 | task 4861 | eval time = 61.10 ms / 2 tokens ( 61.10 ms per token, 16.37 tokens per second) 2.55.783.473 I slot print_timing: id 0 | task 4861 | total time = 386.41 ms / 112 tokens 2.55.783.473 I slot print_timing: id 0 | task 4861 | graphs reused = 3543 2.55.783.474 I slot print_timing: id 0 | task 4861 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.783.514 I slot release: id 0 | task 4861 | stop processing: n_tokens = 734, truncated = 0 2.55.783.839 I slot print_timing: id 2 | task 4863 | prompt eval time = 302.99 ms / 124 tokens ( 2.44 ms per token, 409.25 tokens per second) 2.55.783.842 I slot print_timing: id 2 | task 4863 | eval time = 60.71 ms / 2 tokens ( 60.71 ms per token, 16.47 tokens per second) 2.55.783.843 I slot print_timing: id 2 | task 4863 | total time = 363.70 ms / 126 tokens 2.55.783.843 I slot print_timing: id 2 | task 4863 | graphs reused = 3543 2.55.783.844 I slot print_timing: id 2 | task 4863 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.783.870 I slot release: id 2 | task 4863 | stop processing: n_tokens = 748, truncated = 0 2.55.784.194 I slot print_timing: id 3 | task 4864 | prompt eval time = 279.63 ms / 132 tokens ( 2.12 ms per token, 472.05 tokens per second) 2.55.784.197 I slot print_timing: id 3 | task 4864 | eval time = 60.28 ms / 2 tokens ( 60.28 ms per token, 16.59 tokens per second) 2.55.784.197 I slot print_timing: id 3 | task 4864 | total time = 339.91 ms / 134 tokens 2.55.784.198 I slot print_timing: id 3 | task 4864 | graphs reused = 3543 2.55.784.198 I slot print_timing: id 3 | task 4864 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.784.220 I slot release: id 3 | task 4864 | stop processing: n_tokens = 756, truncated = 0 2.55.802.985 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 734, t_last = 175691784 2.55.803.052 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.457 MiB) 2.55.885.996 I slot launch_slot_: id 0 | task 4869 | processing task, is_child = 0 2.55.886.060 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 2.55.938.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.770 MiB) 2.56.004.928 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 175692139 2.56.005.122 I slot launch_slot_: id 2 | task 4870 | processing task, is_child = 0 2.56.005.178 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 175692490 2.56.005.315 I slot launch_slot_: id 3 | task 4871 | processing task, is_child = 0 2.56.500.342 I slot print_timing: id 1 | task 4862 | prompt eval time = 965.34 ms / 990 tokens ( 0.98 ms per token, 1025.55 tokens per second) 2.56.500.347 I slot print_timing: id 1 | task 4862 | eval time = 118.26 ms / 2 tokens ( 118.26 ms per token, 8.46 tokens per second) 2.56.500.348 I slot print_timing: id 1 | task 4862 | total time = 1083.60 ms / 992 tokens 2.56.500.349 I slot print_timing: id 1 | task 4862 | graphs reused = 3543 2.56.500.350 I slot print_timing: id 1 | task 4862 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.500.400 I slot release: id 1 | task 4862 | stop processing: n_tokens = 991, truncated = 0 2.56.757.703 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 176408669 2.56.757.782 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.707 MiB) 2.56.812.404 I slot launch_slot_: id 1 | task 4876 | processing task, is_child = 0 2.57.234.727 I slot print_timing: id 0 | task 4869 | prompt eval time = 1136.48 ms / 955 tokens ( 1.19 ms per token, 840.31 tokens per second) 2.57.234.733 I slot print_timing: id 0 | task 4869 | eval time = 92.91 ms / 2 tokens ( 92.91 ms per token, 10.76 tokens per second) 2.57.234.734 I slot print_timing: id 0 | task 4869 | total time = 1229.39 ms / 957 tokens 2.57.234.735 I slot print_timing: id 0 | task 4869 | graphs reused = 3543 2.57.234.736 I slot print_timing: id 0 | task 4869 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.234.787 I slot release: id 0 | task 4869 | stop processing: n_tokens = 956, truncated = 0 2.57.235.113 I slot print_timing: id 2 | task 4870 | prompt eval time = 1121.54 ms / 973 tokens ( 1.15 ms per token, 867.55 tokens per second) 2.57.235.116 I slot print_timing: id 2 | task 4870 | eval time = 92.73 ms / 2 tokens ( 92.73 ms per token, 10.78 tokens per second) 2.57.235.117 I slot print_timing: id 2 | task 4870 | total time = 1214.27 ms / 975 tokens 2.57.235.117 I slot print_timing: id 2 | task 4870 | graphs reused = 3543 2.57.235.118 I slot print_timing: id 2 | task 4870 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.235.147 I slot release: id 2 | task 4870 | stop processing: n_tokens = 974, truncated = 0 2.57.235.462 I slot print_timing: id 3 | task 4871 | prompt eval time = 1118.75 ms / 1044 tokens ( 1.07 ms per token, 933.18 tokens per second) 2.57.235.465 I slot print_timing: id 3 | task 4871 | eval time = 92.53 ms / 2 tokens ( 92.53 ms per token, 10.81 tokens per second) 2.57.235.466 I slot print_timing: id 3 | task 4871 | total time = 1211.28 ms / 1046 tokens 2.57.235.466 I slot print_timing: id 3 | task 4871 | graphs reused = 3543 2.57.235.467 I slot print_timing: id 3 | task 4871 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.235.496 I slot release: id 3 | task 4871 | stop processing: n_tokens = 1045, truncated = 0 2.57.251.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 177143056 2.57.252.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.770 MiB) 2.57.336.817 I slot launch_slot_: id 0 | task 4881 | processing task, is_child = 0 2.57.336.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.676 MiB) 2.57.378.196 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.457 MiB) 2.57.434.522 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 974, t_last = 177143417 2.57.434.734 I slot launch_slot_: id 2 | task 4882 | processing task, is_child = 0 2.57.434.802 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1045, t_last = 177143765 2.57.434.954 I slot launch_slot_: id 3 | task 4883 | processing task, is_child = 0 2.58.422.186 I slot print_timing: id 1 | task 4876 | prompt eval time = 1121.63 ms / 1124 tokens ( 1.00 ms per token, 1002.11 tokens per second) 2.58.422.192 I slot print_timing: id 1 | task 4876 | eval time = 477.41 ms / 2 tokens ( 477.41 ms per token, 2.09 tokens per second) 2.58.422.193 I slot print_timing: id 1 | task 4876 | total time = 1599.04 ms / 1126 tokens 2.58.422.195 I slot print_timing: id 1 | task 4876 | graphs reused = 3543 2.58.422.195 I slot print_timing: id 1 | task 4876 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.422.249 I slot release: id 1 | task 4876 | stop processing: n_tokens = 1125, truncated = 0 2.58.578.841 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1125, t_last = 178330519 2.58.578.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.805 MiB) 2.58.629.705 I slot launch_slot_: id 1 | task 4888 | processing task, is_child = 0 2.59.391.739 I slot print_timing: id 0 | task 4881 | prompt eval time = 1702.51 ms / 1161 tokens ( 1.47 ms per token, 681.94 tokens per second) 2.59.391.744 I slot print_timing: id 0 | task 4881 | eval time = 254.26 ms / 2 tokens ( 254.26 ms per token, 3.93 tokens per second) 2.59.391.745 I slot print_timing: id 0 | task 4881 | total time = 1956.77 ms / 1163 tokens 2.59.391.745 I slot print_timing: id 0 | task 4881 | graphs reused = 3543 2.59.391.746 I slot print_timing: id 0 | task 4881 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.391.793 I slot release: id 0 | task 4881 | stop processing: n_tokens = 1162, truncated = 0 2.59.392.198 I slot print_timing: id 2 | task 4882 | prompt eval time = 1687.39 ms / 2094 tokens ( 0.81 ms per token, 1240.97 tokens per second) 2.59.392.201 I slot print_timing: id 2 | task 4882 | eval time = 254.11 ms / 2 tokens ( 254.11 ms per token, 3.94 tokens per second) 2.59.392.202 I slot print_timing: id 2 | task 4882 | total time = 1941.50 ms / 2096 tokens 2.59.392.203 I slot print_timing: id 2 | task 4882 | graphs reused = 3543 2.59.392.204 I slot print_timing: id 2 | task 4882 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.392.284 I slot release: id 2 | task 4882 | stop processing: n_tokens = 2095, truncated = 0 2.59.468.746 I slot print_timing: id 3 | task 4883 | prompt eval time = 1938.84 ms / 2091 tokens ( 0.93 ms per token, 1078.48 tokens per second) 2.59.468.751 I slot print_timing: id 3 | task 4883 | eval time = 75.80 ms / 2 tokens ( 75.80 ms per token, 13.19 tokens per second) 2.59.468.752 I slot print_timing: id 3 | task 4883 | total time = 2014.64 ms / 2093 tokens 2.59.468.755 I slot print_timing: id 3 | task 4883 | graphs reused = 3543 2.59.468.755 I slot print_timing: id 3 | task 4883 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.468.843 I slot release: id 3 | task 4883 | stop processing: n_tokens = 2092, truncated = 0 2.59.468.861 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.854 2.59.469.005 I slot launch_slot_: id 2 | task 4893 | processing task, is_child = 0 2.59.469.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.305 MiB) 2.59.525.507 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.122 MiB) 2.59.530.164 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.778 MiB) 2.59.592.106 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.850 (> 0.100 thold), f_keep = 0.856 2.59.592.244 I slot launch_slot_: id 3 | task 4894 | processing task, is_child = 0 2.59.592.318 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1162, t_last = 179300063 2.59.610.246 I slot launch_slot_: id 0 | task 4895 | processing task, is_child = 0 3.00.069.461 I slot print_timing: id 0 | task 4895 | prompt eval time = 440.79 ms / 369 tokens ( 1.19 ms per token, 837.13 tokens per second) 3.00.069.467 I slot print_timing: id 0 | task 4895 | eval time = 18.40 ms / 2 tokens ( 18.40 ms per token, 54.35 tokens per second) 3.00.069.469 I slot print_timing: id 0 | task 4895 | total time = 459.19 ms / 371 tokens 3.00.069.470 I slot print_timing: id 0 | task 4895 | graphs reused = 3544 3.00.069.471 I slot print_timing: id 0 | task 4895 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.069.575 I slot release: id 0 | task 4895 | stop processing: n_tokens = 2131, truncated = 0 3.00.069.987 I slot print_timing: id 1 | task 4888 | prompt eval time = 1411.70 ms / 2057 tokens ( 0.69 ms per token, 1457.11 tokens per second) 3.00.069.993 I slot print_timing: id 1 | task 4888 | eval time = 18.33 ms / 2 tokens ( 18.33 ms per token, 54.56 tokens per second) 3.00.069.994 I slot print_timing: id 1 | task 4888 | total time = 1430.02 ms / 2059 tokens 3.00.069.995 I slot print_timing: id 1 | task 4888 | graphs reused = 3544 3.00.069.995 I slot print_timing: id 1 | task 4888 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.070.085 I slot release: id 1 | task 4888 | stop processing: n_tokens = 2058, truncated = 0 3.00.070.468 I slot print_timing: id 2 | task 4893 | prompt eval time = 410.28 ms / 280 tokens ( 1.47 ms per token, 682.46 tokens per second) 3.00.070.473 I slot print_timing: id 2 | task 4893 | eval time = 18.24 ms / 2 tokens ( 18.24 ms per token, 54.84 tokens per second) 3.00.070.474 I slot print_timing: id 2 | task 4893 | total time = 428.52 ms / 282 tokens 3.00.070.475 I slot print_timing: id 2 | task 4893 | graphs reused = 3544 3.00.070.475 I slot print_timing: id 2 | task 4893 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.070.526 I slot release: id 2 | task 4893 | stop processing: n_tokens = 2042, truncated = 0 3.00.070.867 I slot print_timing: id 3 | task 4894 | prompt eval time = 391.35 ms / 344 tokens ( 1.14 ms per token, 879.00 tokens per second) 3.00.070.870 I slot print_timing: id 3 | task 4894 | eval time = 18.08 ms / 2 tokens ( 18.08 ms per token, 55.32 tokens per second) 3.00.070.871 I slot print_timing: id 3 | task 4894 | total time = 409.43 ms / 346 tokens 3.00.070.871 I slot print_timing: id 3 | task 4894 | graphs reused = 3544 3.00.070.872 I slot print_timing: id 3 | task 4894 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.070.935 I slot release: id 3 | task 4894 | stop processing: n_tokens = 2106, truncated = 0 3.00.085.969 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 3.00.086.134 I slot launch_slot_: id 0 | task 4900 | processing task, is_child = 0 3.00.129.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.215 MiB) 3.00.183.903 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.059 MiB) 3.00.244.866 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.869 3.00.245.013 I slot launch_slot_: id 1 | task 4899 | processing task, is_child = 0 3.00.245.240 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.877 3.00.245.353 I slot launch_slot_: id 2 | task 4901 | processing task, is_child = 0 3.00.245.465 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.803 (> 0.100 thold), f_keep = 0.850 3.00.245.559 I slot launch_slot_: id 3 | task 4902 | processing task, is_child = 0 3.00.729.434 I slot print_timing: id 0 | task 4900 | prompt eval time = 465.07 ms / 380 tokens ( 1.22 ms per token, 817.07 tokens per second) 3.00.729.440 I slot print_timing: id 0 | task 4900 | eval time = 18.78 ms / 2 tokens ( 18.78 ms per token, 53.24 tokens per second) 3.00.729.441 I slot print_timing: id 0 | task 4900 | total time = 483.86 ms / 382 tokens 3.00.729.441 I slot print_timing: id 0 | task 4900 | graphs reused = 3544 3.00.729.442 I slot print_timing: id 0 | task 4900 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.729.529 I slot release: id 0 | task 4900 | stop processing: n_tokens = 2142, truncated = 0 3.00.729.881 I slot print_timing: id 1 | task 4899 | prompt eval time = 445.93 ms / 300 tokens ( 1.49 ms per token, 672.75 tokens per second) 3.00.729.885 I slot print_timing: id 1 | task 4899 | eval time = 18.44 ms / 2 tokens ( 18.44 ms per token, 54.22 tokens per second) 3.00.729.886 I slot print_timing: id 1 | task 4899 | total time = 464.37 ms / 302 tokens 3.00.729.887 I slot print_timing: id 1 | task 4899 | graphs reused = 3544 3.00.729.888 I slot print_timing: id 1 | task 4899 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.729.941 I slot release: id 1 | task 4899 | stop processing: n_tokens = 2062, truncated = 0 3.00.730.287 I slot print_timing: id 2 | task 4901 | prompt eval time = 427.17 ms / 210 tokens ( 2.03 ms per token, 491.61 tokens per second) 3.00.730.290 I slot print_timing: id 2 | task 4901 | eval time = 18.12 ms / 2 tokens ( 18.12 ms per token, 55.17 tokens per second) 3.00.730.291 I slot print_timing: id 2 | task 4901 | total time = 445.29 ms / 212 tokens 3.00.730.292 I slot print_timing: id 2 | task 4901 | graphs reused = 3544 3.00.730.293 I slot print_timing: id 2 | task 4901 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.730.337 I slot release: id 2 | task 4901 | stop processing: n_tokens = 1972, truncated = 0 3.00.730.622 I slot print_timing: id 3 | task 4902 | prompt eval time = 408.26 ms / 467 tokens ( 0.87 ms per token, 1143.89 tokens per second) 3.00.730.625 I slot print_timing: id 3 | task 4902 | eval time = 17.84 ms / 2 tokens ( 17.84 ms per token, 56.06 tokens per second) 3.00.730.626 I slot print_timing: id 3 | task 4902 | total time = 426.09 ms / 469 tokens 3.00.730.627 I slot print_timing: id 3 | task 4902 | graphs reused = 3544 3.00.730.627 I slot print_timing: id 3 | task 4902 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.730.675 I slot release: id 3 | task 4902 | stop processing: n_tokens = 2229, truncated = 0 3.00.745.326 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.836 3.00.745.467 I slot launch_slot_: id 0 | task 4906 | processing task, is_child = 0 3.00.745.617 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.309 MiB) 3.00.803.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.903 MiB) 3.00.858.917 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.153 MiB) 3.00.919.182 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.908 3.00.919.333 I slot launch_slot_: id 2 | task 4907 | processing task, is_child = 0 3.00.919.561 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.850 (> 0.100 thold), f_keep = 0.803 3.00.919.657 I slot launch_slot_: id 3 | task 4908 | processing task, is_child = 0 3.00.919.765 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.868 3.00.919.853 I slot launch_slot_: id 1 | task 4909 | processing task, is_child = 0 3.01.375.153 I slot print_timing: id 0 | task 4906 | prompt eval time = 436.47 ms / 258 tokens ( 1.69 ms per token, 591.10 tokens per second) 3.01.375.159 I slot print_timing: id 0 | task 4906 | eval time = 18.81 ms / 2 tokens ( 18.81 ms per token, 53.17 tokens per second) 3.01.375.160 I slot print_timing: id 0 | task 4906 | total time = 455.28 ms / 260 tokens 3.01.375.160 I slot print_timing: id 0 | task 4906 | graphs reused = 3544 3.01.375.161 I slot print_timing: id 0 | task 4906 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.375.246 I slot release: id 0 | task 4906 | stop processing: n_tokens = 2020, truncated = 0 3.01.375.584 I slot print_timing: id 1 | task 4909 | prompt eval time = 417.50 ms / 253 tokens ( 1.65 ms per token, 606.00 tokens per second) 3.01.375.587 I slot print_timing: id 1 | task 4909 | eval time = 18.46 ms / 2 tokens ( 18.46 ms per token, 54.18 tokens per second) 3.01.375.588 I slot print_timing: id 1 | task 4909 | total time = 435.95 ms / 255 tokens 3.01.375.589 I slot print_timing: id 1 | task 4909 | graphs reused = 3544 3.01.375.589 I slot print_timing: id 1 | task 4909 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.375.641 I slot release: id 1 | task 4909 | stop processing: n_tokens = 2015, truncated = 0 3.01.375.991 I slot print_timing: id 2 | task 4907 | prompt eval time = 382.48 ms / 304 tokens ( 1.26 ms per token, 794.82 tokens per second) 3.01.375.994 I slot print_timing: id 2 | task 4907 | eval time = 18.10 ms / 2 tokens ( 18.10 ms per token, 55.25 tokens per second) 3.01.375.995 I slot print_timing: id 2 | task 4907 | total time = 400.58 ms / 306 tokens 3.01.375.995 I slot print_timing: id 2 | task 4907 | graphs reused = 3544 3.01.375.996 I slot print_timing: id 2 | task 4907 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.376.043 I slot release: id 2 | task 4907 | stop processing: n_tokens = 2066, truncated = 0 3.01.376.302 I slot print_timing: id 3 | task 4908 | prompt eval time = 365.28 ms / 345 tokens ( 1.06 ms per token, 944.47 tokens per second) 3.01.376.305 I slot print_timing: id 3 | task 4908 | eval time = 17.84 ms / 2 tokens ( 17.84 ms per token, 56.06 tokens per second) 3.01.376.305 I slot print_timing: id 3 | task 4908 | total time = 383.12 ms / 347 tokens 3.01.376.306 I slot print_timing: id 3 | task 4908 | graphs reused = 3544 3.01.376.307 I slot print_timing: id 3 | task 4908 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.376.352 I slot release: id 3 | task 4908 | stop processing: n_tokens = 2107, truncated = 0 3.01.391.557 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.886 3.01.391.701 I slot launch_slot_: id 0 | task 4913 | processing task, is_child = 0 3.01.391.854 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.997 MiB) 3.01.450.517 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.059 MiB) 3.01.504.769 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.934 MiB) 3.01.561.811 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.888 3.01.561.956 I slot launch_slot_: id 1 | task 4914 | processing task, is_child = 0 3.01.562.178 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.866 3.01.562.281 I slot launch_slot_: id 2 | task 4915 | processing task, is_child = 0 3.01.562.393 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.847 (> 0.100 thold), f_keep = 0.850 3.01.562.478 I slot launch_slot_: id 3 | task 4916 | processing task, is_child = 0 3.02.033.927 I slot print_timing: id 0 | task 4913 | prompt eval time = 453.03 ms / 212 tokens ( 2.14 ms per token, 467.96 tokens per second) 3.02.033.932 I slot print_timing: id 0 | task 4913 | eval time = 18.41 ms / 2 tokens ( 18.41 ms per token, 54.33 tokens per second) 3.02.033.933 I slot print_timing: id 0 | task 4913 | total time = 471.43 ms / 214 tokens 3.02.033.934 I slot print_timing: id 0 | task 4913 | graphs reused = 3544 3.02.033.935 I slot print_timing: id 0 | task 4913 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.034.018 I slot release: id 0 | task 4913 | stop processing: n_tokens = 1974, truncated = 0 3.02.034.394 I slot print_timing: id 1 | task 4914 | prompt eval time = 434.06 ms / 304 tokens ( 1.43 ms per token, 700.37 tokens per second) 3.02.034.397 I slot print_timing: id 1 | task 4914 | eval time = 18.25 ms / 2 tokens ( 18.25 ms per token, 54.79 tokens per second) 3.02.034.398 I slot print_timing: id 1 | task 4914 | total time = 452.31 ms / 306 tokens 3.02.034.399 I slot print_timing: id 1 | task 4914 | graphs reused = 3544 3.02.034.399 I slot print_timing: id 1 | task 4914 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.034.453 I slot release: id 1 | task 4914 | stop processing: n_tokens = 2066, truncated = 0 3.02.034.723 I slot print_timing: id 2 | task 4915 | prompt eval time = 415.01 ms / 405 tokens ( 1.02 ms per token, 975.88 tokens per second) 3.02.034.726 I slot print_timing: id 2 | task 4915 | eval time = 18.02 ms / 2 tokens ( 18.02 ms per token, 55.48 tokens per second) 3.02.034.728 I slot print_timing: id 2 | task 4915 | total time = 433.04 ms / 407 tokens 3.02.034.728 I slot print_timing: id 2 | task 4915 | graphs reused = 3544 3.02.034.729 I slot print_timing: id 2 | task 4915 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.034.777 I slot release: id 2 | task 4915 | stop processing: n_tokens = 2167, truncated = 0 3.02.035.022 I slot print_timing: id 3 | task 4916 | prompt eval time = 396.00 ms / 353 tokens ( 1.12 ms per token, 891.40 tokens per second) 3.02.035.025 I slot print_timing: id 3 | task 4916 | eval time = 17.77 ms / 2 tokens ( 17.77 ms per token, 56.27 tokens per second) 3.02.035.026 I slot print_timing: id 3 | task 4916 | total time = 413.78 ms / 355 tokens 3.02.035.026 I slot print_timing: id 3 | task 4916 | graphs reused = 3544 3.02.035.027 I slot print_timing: id 3 | task 4916 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.035.073 I slot release: id 3 | task 4916 | stop processing: n_tokens = 2115, truncated = 0 3.02.049.988 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.846 3.02.050.121 I slot launch_slot_: id 3 | task 4920 | processing task, is_child = 0 3.02.050.251 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.028 MiB) 3.02.055.135 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.872 MiB) 3.02.118.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.778 MiB) 3.02.181.479 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.527 MiB) 3.02.241.730 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.907 3.02.241.870 I slot launch_slot_: id 0 | task 4921 | processing task, is_child = 0 3.02.242.094 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.866 3.02.242.195 I slot launch_slot_: id 1 | task 4922 | processing task, is_child = 0 3.02.242.308 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.826 3.02.242.394 I slot launch_slot_: id 2 | task 4923 | processing task, is_child = 0 3.02.682.737 I slot print_timing: id 0 | task 4921 | prompt eval time = 421.22 ms / 236 tokens ( 1.78 ms per token, 560.27 tokens per second) 3.02.682.742 I slot print_timing: id 0 | task 4921 | eval time = 19.10 ms / 2 tokens ( 19.10 ms per token, 52.35 tokens per second) 3.02.682.744 I slot print_timing: id 0 | task 4921 | total time = 440.33 ms / 238 tokens 3.02.682.744 I slot print_timing: id 0 | task 4921 | graphs reused = 3544 3.02.682.745 I slot print_timing: id 0 | task 4921 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.682.828 I slot release: id 0 | task 4921 | stop processing: n_tokens = 1998, truncated = 0 3.02.683.188 I slot print_timing: id 1 | task 4922 | prompt eval time = 402.15 ms / 272 tokens ( 1.48 ms per token, 676.37 tokens per second) 3.02.683.191 I slot print_timing: id 1 | task 4922 | eval time = 18.76 ms / 2 tokens ( 18.76 ms per token, 53.30 tokens per second) 3.02.683.192 I slot print_timing: id 1 | task 4922 | total time = 420.91 ms / 274 tokens 3.02.683.192 I slot print_timing: id 1 | task 4922 | graphs reused = 3544 3.02.683.193 I slot print_timing: id 1 | task 4922 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.683.247 I slot release: id 1 | task 4922 | stop processing: n_tokens = 2034, truncated = 0 3.02.683.665 I slot print_timing: id 2 | task 4923 | prompt eval time = 383.24 ms / 413 tokens ( 0.93 ms per token, 1077.66 tokens per second) 3.02.683.668 I slot print_timing: id 2 | task 4923 | eval time = 18.42 ms / 2 tokens ( 18.42 ms per token, 54.28 tokens per second) 3.02.683.668 I slot print_timing: id 2 | task 4923 | total time = 401.66 ms / 415 tokens 3.02.683.669 I slot print_timing: id 2 | task 4923 | graphs reused = 3544 3.02.683.670 I slot print_timing: id 2 | task 4923 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.683.726 I slot release: id 2 | task 4923 | stop processing: n_tokens = 2175, truncated = 0 3.02.684.060 I slot print_timing: id 3 | task 4920 | prompt eval time = 364.06 ms / 210 tokens ( 1.73 ms per token, 576.83 tokens per second) 3.02.684.063 I slot print_timing: id 3 | task 4920 | eval time = 18.13 ms / 2 tokens ( 18.13 ms per token, 55.15 tokens per second) 3.02.684.063 I slot print_timing: id 3 | task 4920 | total time = 382.19 ms / 212 tokens 3.02.684.064 I slot print_timing: id 3 | task 4920 | graphs reused = 3544 3.02.684.064 I slot print_timing: id 3 | task 4920 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.684.110 I slot release: id 3 | task 4920 | stop processing: n_tokens = 1972, truncated = 0 3.02.699.539 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.895 3.02.699.675 I slot launch_slot_: id 0 | task 4927 | processing task, is_child = 0 3.02.699.832 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.965 MiB) 3.02.758.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.495 MiB) 3.02.816.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.209 MiB) 3.02.878.188 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.880 3.02.878.334 I slot launch_slot_: id 1 | task 4928 | processing task, is_child = 0 3.02.878.558 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.823 3.02.878.661 I slot launch_slot_: id 2 | task 4929 | processing task, is_child = 0 3.02.878.767 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.908 3.02.878.852 I slot launch_slot_: id 3 | task 4930 | processing task, is_child = 0 3.03.275.325 I slot print_timing: id 0 | task 4927 | prompt eval time = 377.98 ms / 149 tokens ( 2.54 ms per token, 394.21 tokens per second) 3.03.275.331 I slot print_timing: id 0 | task 4927 | eval time = 18.48 ms / 2 tokens ( 18.48 ms per token, 54.11 tokens per second) 3.03.275.332 I slot print_timing: id 0 | task 4927 | total time = 396.46 ms / 151 tokens 3.03.275.334 I slot print_timing: id 0 | task 4927 | graphs reused = 3544 3.03.275.335 I slot print_timing: id 0 | task 4927 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.275.415 I slot release: id 0 | task 4927 | stop processing: n_tokens = 1911, truncated = 0 3.03.275.659 I slot print_timing: id 1 | task 4928 | prompt eval time = 358.43 ms / 196 tokens ( 1.83 ms per token, 546.82 tokens per second) 3.03.275.662 I slot print_timing: id 1 | task 4928 | eval time = 18.12 ms / 2 tokens ( 18.12 ms per token, 55.17 tokens per second) 3.03.275.663 I slot print_timing: id 1 | task 4928 | total time = 376.56 ms / 198 tokens 3.03.275.664 I slot print_timing: id 1 | task 4928 | graphs reused = 3544 3.03.275.665 I slot print_timing: id 1 | task 4928 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.275.711 I slot release: id 1 | task 4928 | stop processing: n_tokens = 1958, truncated = 0 3.03.275.949 I slot print_timing: id 2 | task 4929 | prompt eval time = 339.01 ms / 230 tokens ( 1.47 ms per token, 678.44 tokens per second) 3.03.275.952 I slot print_timing: id 2 | task 4929 | eval time = 17.72 ms / 2 tokens ( 17.72 ms per token, 56.42 tokens per second) 3.03.275.952 I slot print_timing: id 2 | task 4929 | total time = 356.74 ms / 232 tokens 3.03.275.953 I slot print_timing: id 2 | task 4929 | graphs reused = 3544 3.03.275.954 I slot print_timing: id 2 | task 4929 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.275.998 I slot release: id 2 | task 4929 | stop processing: n_tokens = 1992, truncated = 0 3.03.276.242 I slot print_timing: id 3 | task 4930 | prompt eval time = 319.81 ms / 264 tokens ( 1.21 ms per token, 825.50 tokens per second) 3.03.276.245 I slot print_timing: id 3 | task 4930 | eval time = 17.45 ms / 2 tokens ( 17.45 ms per token, 57.29 tokens per second) 3.03.276.246 I slot print_timing: id 3 | task 4930 | total time = 337.26 ms / 266 tokens 3.03.276.246 I slot print_timing: id 3 | task 4930 | graphs reused = 3544 3.03.276.247 I slot print_timing: id 3 | task 4930 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.276.291 I slot release: id 3 | task 4930 | stop processing: n_tokens = 2026, truncated = 0 3.03.290.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1911, t_last = 183183686 3.03.290.327 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.426 MiB) 3.03.344.142 I slot launch_slot_: id 0 | task 4934 | processing task, is_child = 0 3.03.344.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.614 MiB) 3.03.394.638 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.395 MiB) 3.03.399.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.207 MiB) 3.03.459.735 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.645 MiB) 3.03.521.450 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1958, t_last = 183183981 3.03.521.714 I slot launch_slot_: id 1 | task 4935 | processing task, is_child = 0 3.03.521.933 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1992, t_last = 183184268 3.03.522.146 I slot launch_slot_: id 2 | task 4936 | processing task, is_child = 0 3.03.522.258 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2026, t_last = 183184560 3.03.522.453 I slot launch_slot_: id 3 | task 4937 | processing task, is_child = 0 3.05.070.705 I slot print_timing: id 0 | task 4934 | prompt eval time = 1530.10 ms / 999 tokens ( 1.53 ms per token, 652.90 tokens per second) 3.05.070.711 I slot print_timing: id 0 | task 4934 | eval time = 18.13 ms / 2 tokens ( 18.13 ms per token, 55.15 tokens per second) 3.05.070.712 I slot print_timing: id 0 | task 4934 | total time = 1548.24 ms / 1001 tokens 3.05.070.713 I slot print_timing: id 0 | task 4934 | graphs reused = 3544 3.05.070.714 I slot print_timing: id 0 | task 4934 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.070.764 I slot release: id 0 | task 4934 | stop processing: n_tokens = 1000, truncated = 0 3.05.071.000 I slot print_timing: id 1 | task 4935 | prompt eval time = 1527.01 ms / 1475 tokens ( 1.04 ms per token, 965.94 tokens per second) 3.05.071.003 I slot print_timing: id 1 | task 4935 | eval time = 17.87 ms / 2 tokens ( 17.87 ms per token, 55.96 tokens per second) 3.05.071.004 I slot print_timing: id 1 | task 4935 | total time = 1544.88 ms / 1477 tokens 3.05.071.004 I slot print_timing: id 1 | task 4935 | graphs reused = 3544 3.05.071.005 I slot print_timing: id 1 | task 4935 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.071.061 I slot release: id 1 | task 4935 | stop processing: n_tokens = 1476, truncated = 0 3.05.071.289 I slot print_timing: id 2 | task 4936 | prompt eval time = 1523.99 ms / 1555 tokens ( 0.98 ms per token, 1020.35 tokens per second) 3.05.071.292 I slot print_timing: id 2 | task 4936 | eval time = 17.59 ms / 2 tokens ( 17.59 ms per token, 56.84 tokens per second) 3.05.071.293 I slot print_timing: id 2 | task 4936 | total time = 1541.58 ms / 1557 tokens 3.05.071.293 I slot print_timing: id 2 | task 4936 | graphs reused = 3544 3.05.071.294 I slot print_timing: id 2 | task 4936 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.071.336 I slot release: id 2 | task 4936 | stop processing: n_tokens = 1556, truncated = 0 3.05.071.570 I slot print_timing: id 3 | task 4937 | prompt eval time = 1520.88 ms / 1677 tokens ( 0.91 ms per token, 1102.65 tokens per second) 3.05.071.573 I slot print_timing: id 3 | task 4937 | eval time = 17.32 ms / 2 tokens ( 17.32 ms per token, 57.73 tokens per second) 3.05.071.573 I slot print_timing: id 3 | task 4937 | total time = 1538.20 ms / 1679 tokens 3.05.071.574 I slot print_timing: id 3 | task 4937 | graphs reused = 3544 3.05.071.574 I slot print_timing: id 3 | task 4937 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.071.614 I slot release: id 3 | task 4937 | stop processing: n_tokens = 1678, truncated = 0 3.05.085.066 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.882 3.05.085.195 I slot launch_slot_: id 0 | task 4945 | processing task, is_child = 0 3.05.085.315 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.895 MiB) 3.05.136.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.245 MiB) 3.05.193.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.150 MiB) 3.05.245.046 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 184979330 3.05.245.258 I slot launch_slot_: id 1 | task 4946 | processing task, is_child = 0 3.05.245.432 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1556, t_last = 184979605 3.05.245.600 I slot launch_slot_: id 2 | task 4947 | processing task, is_child = 0 3.05.245.687 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1678, t_last = 184979883 3.05.245.854 I slot launch_slot_: id 3 | task 4948 | processing task, is_child = 0 3.05.717.366 I slot print_timing: id 0 | task 4945 | prompt eval time = 390.85 ms / 124 tokens ( 3.15 ms per token, 317.26 tokens per second) 3.05.717.371 I slot print_timing: id 0 | task 4945 | eval time = 80.64 ms / 2 tokens ( 80.64 ms per token, 12.40 tokens per second) 3.05.717.372 I slot print_timing: id 0 | task 4945 | total time = 471.50 ms / 126 tokens 3.05.717.373 I slot print_timing: id 0 | task 4945 | graphs reused = 3544 3.05.717.374 I slot print_timing: id 0 | task 4945 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.717.421 I slot release: id 0 | task 4945 | stop processing: n_tokens = 978, truncated = 0 3.06.025.515 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.901 3.06.025.675 I slot launch_slot_: id 0 | task 4953 | processing task, is_child = 0 3.06.306.953 I slot print_timing: id 0 | task 4953 | prompt eval time = 263.17 ms / 119 tokens ( 2.21 ms per token, 452.18 tokens per second) 3.06.306.959 I slot print_timing: id 0 | task 4953 | eval time = 18.09 ms / 2 tokens ( 18.09 ms per token, 55.29 tokens per second) 3.06.306.960 I slot print_timing: id 0 | task 4953 | total time = 281.26 ms / 121 tokens 3.06.306.960 I slot print_timing: id 0 | task 4953 | graphs reused = 3544 3.06.306.961 I slot print_timing: id 0 | task 4953 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.307.010 I slot release: id 0 | task 4953 | stop processing: n_tokens = 973, truncated = 0 3.06.307.249 I slot print_timing: id 1 | task 4946 | prompt eval time = 1024.01 ms / 960 tokens ( 1.07 ms per token, 937.49 tokens per second) 3.06.307.253 I slot print_timing: id 1 | task 4946 | eval time = 17.79 ms / 2 tokens ( 17.79 ms per token, 56.20 tokens per second) 3.06.307.253 I slot print_timing: id 1 | task 4946 | total time = 1041.81 ms / 962 tokens 3.06.307.254 I slot print_timing: id 1 | task 4946 | graphs reused = 3544 3.06.307.254 I slot print_timing: id 1 | task 4946 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.307.280 I slot release: id 1 | task 4946 | stop processing: n_tokens = 961, truncated = 0 3.06.307.500 I slot print_timing: id 2 | task 4947 | prompt eval time = 1021.04 ms / 983 tokens ( 1.04 ms per token, 962.74 tokens per second) 3.06.307.503 I slot print_timing: id 2 | task 4947 | eval time = 17.47 ms / 2 tokens ( 17.47 ms per token, 57.25 tokens per second) 3.06.307.503 I slot print_timing: id 2 | task 4947 | total time = 1038.51 ms / 985 tokens 3.06.307.504 I slot print_timing: id 2 | task 4947 | graphs reused = 3544 3.06.307.504 I slot print_timing: id 2 | task 4947 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.307.529 I slot release: id 2 | task 4947 | stop processing: n_tokens = 984, truncated = 0 3.06.307.754 I slot print_timing: id 3 | task 4948 | prompt eval time = 1018.10 ms / 989 tokens ( 1.03 ms per token, 971.42 tokens per second) 3.06.307.757 I slot print_timing: id 3 | task 4948 | eval time = 17.15 ms / 2 tokens ( 17.15 ms per token, 58.32 tokens per second) 3.06.307.757 I slot print_timing: id 3 | task 4948 | total time = 1035.25 ms / 991 tokens 3.06.307.758 I slot print_timing: id 3 | task 4948 | graphs reused = 3544 3.06.307.758 I slot print_timing: id 3 | task 4948 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.307.782 I slot release: id 3 | task 4948 | stop processing: n_tokens = 990, truncated = 0 3.06.321.486 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 186215279 3.06.321.581 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.713 MiB) 3.06.363.808 I slot launch_slot_: id 0 | task 4957 | processing task, is_child = 0 3.06.363.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.933 MiB) 3.06.417.770 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 286.435 MiB) 3.06.471.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 287.592 MiB) 3.06.527.239 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.917 3.06.527.379 I slot launch_slot_: id 1 | task 4958 | processing task, is_child = 0 3.06.527.502 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 984, t_last = 186215799 3.06.527.655 I slot launch_slot_: id 2 | task 4959 | processing task, is_child = 0 3.06.527.715 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 990, t_last = 186216051 3.06.527.856 I slot launch_slot_: id 3 | task 4960 | processing task, is_child = 0 3.07.356.392 I slot print_timing: id 1 | task 4958 | prompt eval time = 444.18 ms / 123 tokens ( 3.61 ms per token, 276.92 tokens per second) 3.07.356.398 I slot print_timing: id 1 | task 4958 | eval time = 380.81 ms / 2 tokens ( 380.81 ms per token, 2.63 tokens per second) 3.07.356.399 I slot print_timing: id 1 | task 4958 | total time = 824.99 ms / 125 tokens 3.07.356.400 I slot print_timing: id 1 | task 4958 | graphs reused = 3544 3.07.356.401 I slot print_timing: id 1 | task 4958 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.356.448 I slot release: id 1 | task 4958 | stop processing: n_tokens = 977, truncated = 0 3.07.547.785 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 187264718 3.07.547.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.613 MiB) 3.07.593.258 I slot launch_slot_: id 1 | task 4965 | processing task, is_child = 0 3.07.967.225 I slot print_timing: id 0 | task 4957 | prompt eval time = 1324.64 ms / 825 tokens ( 1.61 ms per token, 622.81 tokens per second) 3.07.967.231 I slot print_timing: id 0 | task 4957 | eval time = 114.71 ms / 2 tokens ( 114.71 ms per token, 8.72 tokens per second) 3.07.967.232 I slot print_timing: id 0 | task 4957 | total time = 1439.35 ms / 827 tokens 3.07.967.233 I slot print_timing: id 0 | task 4957 | graphs reused = 3544 3.07.967.234 I slot print_timing: id 0 | task 4957 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.967.276 I slot release: id 0 | task 4957 | stop processing: n_tokens = 826, truncated = 0 3.08.112.309 I slot print_timing: id 2 | task 4959 | prompt eval time = 1416.69 ms / 1587 tokens ( 0.89 ms per token, 1120.21 tokens per second) 3.08.112.314 I slot print_timing: id 2 | task 4959 | eval time = 144.41 ms / 2 tokens ( 144.41 ms per token, 6.92 tokens per second) 3.08.112.315 I slot print_timing: id 2 | task 4959 | total time = 1561.11 ms / 1589 tokens 3.08.112.316 I slot print_timing: id 2 | task 4959 | graphs reused = 3544 3.08.112.317 I slot print_timing: id 2 | task 4959 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.112.387 I slot release: id 2 | task 4959 | stop processing: n_tokens = 1588, truncated = 0 3.08.112.709 I slot print_timing: id 3 | task 4960 | prompt eval time = 1413.89 ms / 1629 tokens ( 0.87 ms per token, 1152.14 tokens per second) 3.08.112.712 I slot print_timing: id 3 | task 4960 | eval time = 144.24 ms / 2 tokens ( 144.24 ms per token, 6.93 tokens per second) 3.08.112.712 I slot print_timing: id 3 | task 4960 | total time = 1558.14 ms / 1631 tokens 3.08.112.713 I slot print_timing: id 3 | task 4960 | graphs reused = 3544 3.08.112.714 I slot print_timing: id 3 | task 4960 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.112.759 I slot release: id 3 | task 4960 | stop processing: n_tokens = 1630, truncated = 0 3.08.112.773 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.861 (> 0.100 thold), f_keep = 0.883 3.08.112.906 I slot launch_slot_: id 2 | task 4969 | processing task, is_child = 0 3.08.112.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.112 MiB) 3.08.161.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.114 MiB) 3.08.219.294 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.816 (> 0.100 thold), f_keep = 0.860 3.08.219.432 I slot launch_slot_: id 3 | task 4970 | processing task, is_child = 0 3.08.219.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 187875546 3.08.219.637 I slot launch_slot_: id 0 | task 4971 | processing task, is_child = 0 3.08.726.417 I slot print_timing: id 2 | task 4969 | prompt eval time = 423.84 ms / 255 tokens ( 1.66 ms per token, 601.64 tokens per second) 3.08.726.423 I slot print_timing: id 2 | task 4969 | eval time = 66.83 ms / 2 tokens ( 66.83 ms per token, 14.96 tokens per second) 3.08.726.424 I slot print_timing: id 2 | task 4969 | total time = 490.68 ms / 257 tokens 3.08.726.424 I slot print_timing: id 2 | task 4969 | graphs reused = 3544 3.08.726.425 I slot print_timing: id 2 | task 4969 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.726.498 I slot release: id 2 | task 4969 | stop processing: n_tokens = 1630, truncated = 0 3.08.726.815 I slot print_timing: id 3 | task 4970 | prompt eval time = 404.92 ms / 344 tokens ( 1.18 ms per token, 849.54 tokens per second) 3.08.726.818 I slot print_timing: id 3 | task 4970 | eval time = 66.60 ms / 2 tokens ( 66.60 ms per token, 15.02 tokens per second) 3.08.726.819 I slot print_timing: id 3 | task 4970 | total time = 471.52 ms / 346 tokens 3.08.726.819 I slot print_timing: id 3 | task 4970 | graphs reused = 3544 3.08.726.820 I slot print_timing: id 3 | task 4970 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.726.868 I slot release: id 3 | task 4970 | stop processing: n_tokens = 1719, truncated = 0 3.08.844.526 I slot print_timing: id 1 | task 4965 | prompt eval time = 1122.59 ms / 1615 tokens ( 0.70 ms per token, 1438.64 tokens per second) 3.08.844.532 I slot print_timing: id 1 | task 4965 | eval time = 118.41 ms / 2 tokens ( 118.41 ms per token, 8.45 tokens per second) 3.08.844.533 I slot print_timing: id 1 | task 4965 | total time = 1240.99 ms / 1617 tokens 3.08.844.534 I slot print_timing: id 1 | task 4965 | graphs reused = 3544 3.08.844.534 I slot print_timing: id 1 | task 4965 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.844.604 I slot release: id 1 | task 4965 | stop processing: n_tokens = 1616, truncated = 0 3.08.844.618 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 188634769 3.08.844.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.738 MiB) 3.08.900.525 I slot launch_slot_: id 2 | task 4976 | processing task, is_child = 0 3.08.900.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.923 MiB) 3.08.967.271 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.960 MiB) 3.09.026.741 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1719, t_last = 188635138 3.09.026.990 I slot launch_slot_: id 3 | task 4977 | processing task, is_child = 0 3.09.027.080 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1616, t_last = 188752875 3.09.027.262 I slot launch_slot_: id 1 | task 4978 | processing task, is_child = 0 3.09.443.900 I slot print_timing: id 0 | task 4971 | prompt eval time = 1128.67 ms / 838 tokens ( 1.35 ms per token, 742.47 tokens per second) 3.09.443.905 I slot print_timing: id 0 | task 4971 | eval time = 95.57 ms / 2 tokens ( 95.57 ms per token, 10.46 tokens per second) 3.09.443.907 I slot print_timing: id 0 | task 4971 | total time = 1224.24 ms / 840 tokens 3.09.443.909 I slot print_timing: id 0 | task 4971 | graphs reused = 3544 3.09.443.910 I slot print_timing: id 0 | task 4971 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.443.959 I slot release: id 0 | task 4971 | stop processing: n_tokens = 839, truncated = 0 3.09.752.144 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 839, t_last = 189352229 3.09.796.368 I slot launch_slot_: id 0 | task 4983 | processing task, is_child = 0 3.10.123.877 I slot print_timing: id 1 | task 4978 | prompt eval time = 1039.24 ms / 859 tokens ( 1.21 ms per token, 826.57 tokens per second) 3.10.123.883 I slot print_timing: id 1 | task 4978 | eval time = 43.61 ms / 2 tokens ( 43.61 ms per token, 22.93 tokens per second) 3.10.123.884 I slot print_timing: id 1 | task 4978 | total time = 1082.84 ms / 861 tokens 3.10.123.885 I slot print_timing: id 1 | task 4978 | graphs reused = 3545 3.10.123.886 I slot print_timing: id 1 | task 4978 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.123.930 I slot release: id 1 | task 4978 | stop processing: n_tokens = 860, truncated = 0 3.10.124.246 I slot print_timing: id 2 | task 4976 | prompt eval time = 1036.32 ms / 842 tokens ( 1.23 ms per token, 812.49 tokens per second) 3.10.124.249 I slot print_timing: id 2 | task 4976 | eval time = 43.33 ms / 2 tokens ( 43.33 ms per token, 23.08 tokens per second) 3.10.124.250 I slot print_timing: id 2 | task 4976 | total time = 1079.65 ms / 844 tokens 3.10.124.250 I slot print_timing: id 2 | task 4976 | graphs reused = 3545 3.10.124.251 I slot print_timing: id 2 | task 4976 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.124.283 I slot release: id 2 | task 4976 | stop processing: n_tokens = 843, truncated = 0 3.10.124.574 I slot print_timing: id 3 | task 4977 | prompt eval time = 1033.33 ms / 865 tokens ( 1.19 ms per token, 837.10 tokens per second) 3.10.124.577 I slot print_timing: id 3 | task 4977 | eval time = 43.04 ms / 2 tokens ( 43.04 ms per token, 23.24 tokens per second) 3.10.124.578 I slot print_timing: id 3 | task 4977 | total time = 1076.37 ms / 867 tokens 3.10.124.578 I slot print_timing: id 3 | task 4977 | graphs reused = 3545 3.10.124.579 I slot print_timing: id 3 | task 4977 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.124.612 I slot release: id 3 | task 4977 | stop processing: n_tokens = 866, truncated = 0 3.10.140.744 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 190032199 3.10.140.815 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.268 MiB) 3.10.224.256 I slot launch_slot_: id 1 | task 4988 | processing task, is_child = 0 3.10.224.320 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.863 MiB) 3.10.272.185 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.145 MiB) 3.10.324.064 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 190032552 3.10.324.266 I slot launch_slot_: id 2 | task 4989 | processing task, is_child = 0 3.10.324.324 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 866, t_last = 190032882 3.10.324.462 I slot launch_slot_: id 3 | task 4990 | processing task, is_child = 0 3.10.887.110 I slot print_timing: id 0 | task 4983 | prompt eval time = 848.50 ms / 886 tokens ( 0.96 ms per token, 1044.20 tokens per second) 3.10.887.116 I slot print_timing: id 0 | task 4983 | eval time = 242.22 ms / 2 tokens ( 242.22 ms per token, 4.13 tokens per second) 3.10.887.117 I slot print_timing: id 0 | task 4983 | total time = 1090.71 ms / 888 tokens 3.10.887.118 I slot print_timing: id 0 | task 4983 | graphs reused = 3545 3.10.887.119 I slot print_timing: id 0 | task 4983 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.887.167 I slot release: id 0 | task 4983 | stop processing: n_tokens = 887, truncated = 0 3.11.019.134 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 190795437 3.11.019.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.986 MiB) 3.11.080.354 I slot launch_slot_: id 0 | task 4995 | processing task, is_child = 0 3.11.285.529 I slot print_timing: id 2 | task 4989 | prompt eval time = 870.61 ms / 749 tokens ( 1.16 ms per token, 860.32 tokens per second) 3.11.285.534 I slot print_timing: id 2 | task 4989 | eval time = 76.76 ms / 2 tokens ( 76.76 ms per token, 13.03 tokens per second) 3.11.285.535 I slot print_timing: id 2 | task 4989 | total time = 947.37 ms / 751 tokens 3.11.285.536 I slot print_timing: id 2 | task 4989 | graphs reused = 3545 3.11.285.537 I slot print_timing: id 2 | task 4989 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.285.582 I slot release: id 2 | task 4989 | stop processing: n_tokens = 750, truncated = 0 3.11.285.966 I slot print_timing: id 3 | task 4990 | prompt eval time = 867.77 ms / 691 tokens ( 1.26 ms per token, 796.29 tokens per second) 3.11.285.969 I slot print_timing: id 3 | task 4990 | eval time = 76.55 ms / 2 tokens ( 76.55 ms per token, 13.06 tokens per second) 3.11.285.970 I slot print_timing: id 3 | task 4990 | total time = 944.32 ms / 693 tokens 3.11.285.971 I slot print_timing: id 3 | task 4990 | graphs reused = 3545 3.11.285.972 I slot print_timing: id 3 | task 4990 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.286.001 I slot release: id 3 | task 4990 | stop processing: n_tokens = 692, truncated = 0 3.11.389.953 I slot print_timing: id 1 | task 4988 | prompt eval time = 950.55 ms / 780 tokens ( 1.22 ms per token, 820.58 tokens per second) 3.11.389.958 I slot print_timing: id 1 | task 4988 | eval time = 104.75 ms / 2 tokens ( 104.75 ms per token, 9.55 tokens per second) 3.11.389.959 I slot print_timing: id 1 | task 4988 | total time = 1055.30 ms / 782 tokens 3.11.389.960 I slot print_timing: id 1 | task 4988 | graphs reused = 3545 3.11.389.961 I slot print_timing: id 1 | task 4988 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.390.002 I slot release: id 1 | task 4988 | stop processing: n_tokens = 781, truncated = 0 3.11.390.019 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.866 3.11.390.155 I slot launch_slot_: id 3 | task 4999 | processing task, is_child = 0 3.11.390.222 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.863 MiB) 3.11.444.664 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.021 MiB) 3.11.668.645 I slot print_timing: id 0 | task 4995 | prompt eval time = 562.74 ms / 712 tokens ( 0.79 ms per token, 1265.23 tokens per second) 3.11.668.650 I slot print_timing: id 0 | task 4995 | eval time = 25.53 ms / 2 tokens ( 25.53 ms per token, 39.17 tokens per second) 3.11.668.651 I slot print_timing: id 0 | task 4995 | total time = 588.27 ms / 714 tokens 3.11.668.652 I slot print_timing: id 0 | task 4995 | graphs reused = 3545 3.11.668.653 I slot print_timing: id 0 | task 4995 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.668.687 I slot release: id 0 | task 4995 | stop processing: n_tokens = 713, truncated = 0 3.11.668.907 I slot print_timing: id 3 | task 4999 | prompt eval time = 134.40 ms / 107 tokens ( 1.26 ms per token, 796.12 tokens per second) 3.11.668.910 I slot print_timing: id 3 | task 4999 | eval time = 25.22 ms / 2 tokens ( 25.22 ms per token, 39.64 tokens per second) 3.11.668.911 I slot print_timing: id 3 | task 4999 | total time = 159.63 ms / 109 tokens 3.11.668.912 I slot print_timing: id 3 | task 4999 | graphs reused = 3545 3.11.668.912 I slot print_timing: id 3 | task 4999 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.668.931 I slot release: id 3 | task 4999 | stop processing: n_tokens = 679, truncated = 0