/Users/minipro/quantdiff/work/llama-b11869/src/build/bin/llama-server -m /Users/minipro/quantdiff/models/campaign/be92beb4e0fd/Sage-A1.5-IQ4_XS-exps.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 0.00.046.455 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.046.514 I srv llama_server: initializing ... 0.00.046.520 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.046.606 I srv init_listene: The UI is disabled 0.00.046.608 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.046.650 W srv server_setup: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.048.309 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/be92beb4e0fd/Sage-A1.5-IQ4_XS-exps.gguf' 0.00.350.211 W model has unused tensor blk.40.attn_norm.weight (size = 8192 bytes) -- ignoring 0.00.350.219 W model has unused tensor blk.40.post_attention_norm.weight (size = 8192 bytes) -- ignoring 0.00.350.225 W model has unused tensor blk.40.attn_q.weight (size = 9437184 bytes) -- ignoring 0.00.350.228 W model has unused tensor blk.40.attn_k.weight (size = 589824 bytes) -- ignoring 0.00.350.230 W model has unused tensor blk.40.attn_v.weight (size = 860160 bytes) -- ignoring 0.00.350.237 W model has unused tensor blk.40.attn_output.weight (size = 4718592 bytes) -- ignoring 0.00.350.240 W model has unused tensor blk.40.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.350.242 W model has unused tensor blk.40.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.350.244 W model has unused tensor blk.40.ffn_gate_inp.weight (size = 2097152 bytes) -- ignoring 0.00.350.246 W model has unused tensor blk.40.ffn_down_exps.weight (size = 220200960 bytes) -- ignoring 0.00.350.250 W model has unused tensor blk.40.ffn_gate_exps.weight (size = 150994944 bytes) -- ignoring 0.00.350.253 W model has unused tensor blk.40.ffn_up_exps.weight (size = 150994944 bytes) -- ignoring 0.00.350.255 W model has unused tensor blk.40.ffn_gate_inp_shexp.weight (size = 8192 bytes) -- ignoring 0.00.350.257 W model has unused tensor blk.40.ffn_gate_shexp.weight (size = 589824 bytes) -- ignoring 0.00.350.260 W model has unused tensor blk.40.ffn_up_shexp.weight (size = 589824 bytes) -- ignoring 0.00.350.262 W model has unused tensor blk.40.ffn_down_shexp.weight (size = 860160 bytes) -- ignoring 0.00.350.264 W model has unused tensor blk.40.nextn.eh_proj.weight (size = 4718592 bytes) -- ignoring 0.00.350.267 W model has unused tensor blk.40.nextn.enorm.weight (size = 8192 bytes) -- ignoring 0.00.350.269 W model has unused tensor blk.40.nextn.hnorm.weight (size = 8192 bytes) -- ignoring 0.00.350.276 W model has unused tensor blk.40.nextn.shared_head_norm.weight (size = 8192 bytes) -- ignoring 0.01.217.912 I cmn init: llama threadpool init, n_threads = 8 0.01.298.254 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.01.302.525 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.302.535 I srv server_run_i: model loaded 0.01.302.538 I srv server_on_li: listening on http://127.0.0.1:8091 0.32.244.251 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.32.244.278 I slot launch_slot_: id 0 | task 2 | processing task, is_child = 0 0.32.244.279 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.32.244.292 I slot launch_slot_: id 1 | task 0 | processing task, is_child = 0 0.32.244.293 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.32.244.305 I slot launch_slot_: id 2 | task 1 | processing task, is_child = 0 0.32.244.305 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.32.244.317 I slot launch_slot_: id 3 | task 3 | processing task, is_child = 0 0.33.346.795 I slot print_timing: id 0 | task 2 | prompt eval time = 1049.54 ms / 122 tokens ( 8.60 ms per token, 116.24 tokens per second) 0.33.346.801 I slot print_timing: id 0 | task 2 | eval time = 52.92 ms / 2 tokens ( 52.92 ms per token, 18.89 tokens per second) 0.33.346.801 I slot print_timing: id 0 | task 2 | total time = 1102.47 ms / 124 tokens 0.33.346.802 I slot print_timing: id 0 | task 2 | graphs reused = 1 0.33.346.802 I slot print_timing: id 0 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.346.819 I slot release: id 0 | task 2 | stop processing: n_tokens = 123, truncated = 0 0.33.346.974 I slot print_timing: id 1 | task 0 | prompt eval time = 1049.83 ms / 115 tokens ( 9.13 ms per token, 109.54 tokens per second) 0.33.346.979 I slot print_timing: id 1 | task 0 | eval time = 52.81 ms / 2 tokens ( 52.81 ms per token, 18.93 tokens per second) 0.33.346.980 I slot print_timing: id 1 | task 0 | total time = 1102.64 ms / 117 tokens 0.33.346.980 I slot print_timing: id 1 | task 0 | graphs reused = 1 0.33.346.980 I slot print_timing: id 1 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.346.989 I slot release: id 1 | task 0 | stop processing: n_tokens = 116, truncated = 0 0.33.347.154 I slot print_timing: id 2 | task 1 | prompt eval time = 1050.15 ms / 115 tokens ( 9.13 ms per token, 109.51 tokens per second) 0.33.347.155 I slot print_timing: id 2 | task 1 | eval time = 52.67 ms / 2 tokens ( 52.67 ms per token, 18.98 tokens per second) 0.33.347.155 I slot print_timing: id 2 | task 1 | total time = 1102.82 ms / 117 tokens 0.33.347.155 I slot print_timing: id 2 | task 1 | graphs reused = 1 0.33.347.156 I slot print_timing: id 2 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.347.164 I slot release: id 2 | task 1 | stop processing: n_tokens = 116, truncated = 0 0.33.347.333 I slot print_timing: id 3 | task 3 | prompt eval time = 1050.59 ms / 130 tokens ( 8.08 ms per token, 123.74 tokens per second) 0.33.347.338 I slot print_timing: id 3 | task 3 | eval time = 52.41 ms / 2 tokens ( 52.41 ms per token, 19.08 tokens per second) 0.33.347.338 I slot print_timing: id 3 | task 3 | total time = 1103.00 ms / 132 tokens 0.33.347.338 I slot print_timing: id 3 | task 3 | graphs reused = 1 0.33.347.339 I slot print_timing: id 3 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.347.345 I slot release: id 3 | task 3 | stop processing: n_tokens = 131, truncated = 0 0.33.355.169 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.236 0.33.364.536 I slot launch_slot_: id 0 | task 7 | processing task, is_child = 0 0.33.392.016 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.250 0.33.392.091 I slot launch_slot_: id 2 | task 8 | processing task, is_child = 0 0.33.392.125 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 0.33.392.158 I slot launch_slot_: id 1 | task 9 | processing task, is_child = 0 0.33.392.176 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.214 0.33.392.206 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 0.34.886.268 I slot print_timing: id 0 | task 7 | prompt eval time = 1441.61 ms / 108 tokens ( 13.35 ms per token, 74.92 tokens per second) 0.34.886.270 I slot print_timing: id 0 | task 7 | eval time = 52.44 ms / 2 tokens ( 52.44 ms per token, 19.07 tokens per second) 0.34.886.271 I slot print_timing: id 0 | task 7 | total time = 1494.05 ms / 110 tokens 0.34.886.271 I slot print_timing: id 0 | task 7 | graphs reused = 1 0.34.886.271 I slot print_timing: id 0 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.886.289 I slot release: id 0 | task 7 | stop processing: n_tokens = 109, truncated = 0 0.34.886.451 I slot print_timing: id 1 | task 9 | prompt eval time = 1441.76 ms / 160 tokens ( 9.01 ms per token, 110.98 tokens per second) 0.34.886.454 I slot print_timing: id 1 | task 9 | eval time = 52.47 ms / 2 tokens ( 52.47 ms per token, 19.06 tokens per second) 0.34.886.455 I slot print_timing: id 1 | task 9 | total time = 1494.22 ms / 162 tokens 0.34.886.455 I slot print_timing: id 1 | task 9 | graphs reused = 1 0.34.886.455 I slot print_timing: id 1 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.886.474 I slot release: id 1 | task 9 | stop processing: n_tokens = 161, truncated = 0 0.34.886.638 I slot print_timing: id 2 | task 8 | prompt eval time = 1441.91 ms / 152 tokens ( 9.49 ms per token, 105.42 tokens per second) 0.34.886.645 I slot print_timing: id 2 | task 8 | eval time = 52.48 ms / 2 tokens ( 52.48 ms per token, 19.06 tokens per second) 0.34.886.645 I slot print_timing: id 2 | task 8 | total time = 1494.39 ms / 154 tokens 0.34.886.645 I slot print_timing: id 2 | task 8 | graphs reused = 1 0.34.886.646 I slot print_timing: id 2 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.886.657 I slot release: id 2 | task 8 | stop processing: n_tokens = 153, truncated = 0 0.34.886.817 I slot print_timing: id 3 | task 10 | prompt eval time = 1442.07 ms / 200 tokens ( 7.21 ms per token, 138.69 tokens per second) 0.34.886.820 I slot print_timing: id 3 | task 10 | eval time = 52.48 ms / 2 tokens ( 52.48 ms per token, 19.05 tokens per second) 0.34.886.821 I slot print_timing: id 3 | task 10 | total time = 1494.55 ms / 202 tokens 0.34.886.821 I slot print_timing: id 3 | task 10 | graphs reused = 1 0.34.886.821 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.886.833 I slot release: id 3 | task 10 | stop processing: n_tokens = 201, truncated = 0 0.34.891.888 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.257 0.34.901.148 I slot launch_slot_: id 0 | task 14 | processing task, is_child = 0 0.34.929.939 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 0.34.929.995 I slot launch_slot_: id 2 | task 15 | processing task, is_child = 0 0.34.930.029 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 0.34.930.060 I slot launch_slot_: id 1 | task 16 | processing task, is_child = 0 0.34.930.080 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.139 0.34.930.113 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 0.36.128.114 I slot print_timing: id 0 | task 14 | prompt eval time = 1145.48 ms / 117 tokens ( 9.79 ms per token, 102.14 tokens per second) 0.36.128.116 I slot print_timing: id 0 | task 14 | eval time = 52.51 ms / 2 tokens ( 52.51 ms per token, 19.05 tokens per second) 0.36.128.116 I slot print_timing: id 0 | task 14 | total time = 1197.99 ms / 119 tokens 0.36.128.117 I slot print_timing: id 0 | task 14 | graphs reused = 1 0.36.128.117 I slot print_timing: id 0 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.128.135 I slot release: id 0 | task 14 | stop processing: n_tokens = 118, truncated = 0 0.36.128.291 I slot print_timing: id 1 | task 16 | prompt eval time = 1145.63 ms / 125 tokens ( 9.17 ms per token, 109.11 tokens per second) 0.36.128.293 I slot print_timing: id 1 | task 16 | eval time = 52.53 ms / 2 tokens ( 52.53 ms per token, 19.04 tokens per second) 0.36.128.294 I slot print_timing: id 1 | task 16 | total time = 1198.16 ms / 127 tokens 0.36.128.294 I slot print_timing: id 1 | task 16 | graphs reused = 1 0.36.128.294 I slot print_timing: id 1 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.128.304 I slot release: id 1 | task 16 | stop processing: n_tokens = 126, truncated = 0 0.36.128.473 I slot print_timing: id 2 | task 15 | prompt eval time = 1145.79 ms / 118 tokens ( 9.71 ms per token, 102.99 tokens per second) 0.36.128.474 I slot print_timing: id 2 | task 15 | eval time = 52.54 ms / 2 tokens ( 52.54 ms per token, 19.03 tokens per second) 0.36.128.475 I slot print_timing: id 2 | task 15 | total time = 1198.33 ms / 120 tokens 0.36.128.475 I slot print_timing: id 2 | task 15 | graphs reused = 1 0.36.128.475 I slot print_timing: id 2 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.128.483 I slot release: id 2 | task 15 | stop processing: n_tokens = 119, truncated = 0 0.36.128.667 I slot print_timing: id 3 | task 17 | prompt eval time = 1145.98 ms / 150 tokens ( 7.64 ms per token, 130.89 tokens per second) 0.36.128.668 I slot print_timing: id 3 | task 17 | eval time = 52.52 ms / 2 tokens ( 52.52 ms per token, 19.04 tokens per second) 0.36.128.669 I slot print_timing: id 3 | task 17 | total time = 1198.50 ms / 152 tokens 0.36.128.669 I slot print_timing: id 3 | task 17 | graphs reused = 1 0.36.128.669 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.128.680 I slot release: id 3 | task 17 | stop processing: n_tokens = 151, truncated = 0 0.36.133.333 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.235 (> 0.100 thold), f_keep = 0.237 0.36.143.430 I slot launch_slot_: id 0 | task 21 | processing task, is_child = 0 0.36.174.108 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.222 0.36.174.156 I slot launch_slot_: id 1 | task 23 | processing task, is_child = 0 0.36.174.189 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.235 0.36.174.220 I slot launch_slot_: id 2 | task 22 | processing task, is_child = 0 0.36.174.239 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.185 0.36.174.270 I slot launch_slot_: id 3 | task 24 | processing task, is_child = 0 0.37.594.645 I slot print_timing: id 0 | task 21 | prompt eval time = 1367.87 ms / 119 tokens ( 11.49 ms per token, 87.00 tokens per second) 0.37.594.648 I slot print_timing: id 0 | task 21 | eval time = 52.49 ms / 2 tokens ( 52.49 ms per token, 19.05 tokens per second) 0.37.594.649 I slot print_timing: id 0 | task 21 | total time = 1420.36 ms / 121 tokens 0.37.594.649 I slot print_timing: id 0 | task 21 | graphs reused = 1 0.37.594.649 I slot print_timing: id 0 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.594.669 I slot release: id 0 | task 21 | stop processing: n_tokens = 120, truncated = 0 0.37.594.824 I slot print_timing: id 1 | task 23 | prompt eval time = 1368.05 ms / 143 tokens ( 9.57 ms per token, 104.53 tokens per second) 0.37.594.826 I slot print_timing: id 1 | task 23 | eval time = 52.48 ms / 2 tokens ( 52.48 ms per token, 19.05 tokens per second) 0.37.594.827 I slot print_timing: id 1 | task 23 | total time = 1420.53 ms / 145 tokens 0.37.594.827 I slot print_timing: id 1 | task 23 | graphs reused = 1 0.37.594.827 I slot print_timing: id 1 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.594.838 I slot release: id 1 | task 23 | stop processing: n_tokens = 144, truncated = 0 0.37.595.006 I slot print_timing: id 2 | task 22 | prompt eval time = 1368.23 ms / 136 tokens ( 10.06 ms per token, 99.40 tokens per second) 0.37.595.008 I slot print_timing: id 2 | task 22 | eval time = 52.47 ms / 2 tokens ( 52.47 ms per token, 19.06 tokens per second) 0.37.595.009 I slot print_timing: id 2 | task 22 | total time = 1420.70 ms / 138 tokens 0.37.595.009 I slot print_timing: id 2 | task 22 | graphs reused = 1 0.37.595.010 I slot print_timing: id 2 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.595.023 I slot release: id 2 | task 22 | stop processing: n_tokens = 137, truncated = 0 0.37.595.195 I slot print_timing: id 3 | task 24 | prompt eval time = 1368.43 ms / 181 tokens ( 7.56 ms per token, 132.27 tokens per second) 0.37.595.196 I slot print_timing: id 3 | task 24 | eval time = 52.45 ms / 2 tokens ( 52.45 ms per token, 19.07 tokens per second) 0.37.595.197 I slot print_timing: id 3 | task 24 | total time = 1420.88 ms / 183 tokens 0.37.595.197 I slot print_timing: id 3 | task 24 | graphs reused = 1 0.37.595.197 I slot print_timing: id 3 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.595.206 I slot release: id 3 | task 24 | stop processing: n_tokens = 182, truncated = 0 0.37.600.427 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.233 0.37.612.063 I slot launch_slot_: id 0 | task 28 | processing task, is_child = 0 0.37.636.981 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.194 0.37.637.041 I slot launch_slot_: id 1 | task 30 | processing task, is_child = 0 0.37.637.083 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.204 0.37.638.505 I slot launch_slot_: id 2 | task 29 | processing task, is_child = 0 0.37.638.533 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.154 0.37.638.569 I slot launch_slot_: id 3 | task 31 | processing task, is_child = 0 0.39.060.139 I slot print_timing: id 0 | task 28 | prompt eval time = 1369.08 ms / 122 tokens ( 11.22 ms per token, 89.11 tokens per second) 0.39.060.142 I slot print_timing: id 0 | task 28 | eval time = 52.48 ms / 2 tokens ( 52.48 ms per token, 19.06 tokens per second) 0.39.060.143 I slot print_timing: id 0 | task 28 | total time = 1421.56 ms / 124 tokens 0.39.060.143 I slot print_timing: id 0 | task 28 | graphs reused = 1 0.39.060.143 I slot print_timing: id 0 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.060.166 I slot release: id 0 | task 28 | stop processing: n_tokens = 123, truncated = 0 0.39.060.320 I slot print_timing: id 1 | task 30 | prompt eval time = 1369.22 ms / 144 tokens ( 9.51 ms per token, 105.17 tokens per second) 0.39.060.323 I slot print_timing: id 1 | task 30 | eval time = 52.51 ms / 2 tokens ( 52.51 ms per token, 19.05 tokens per second) 0.39.060.323 I slot print_timing: id 1 | task 30 | total time = 1421.73 ms / 146 tokens 0.39.060.323 I slot print_timing: id 1 | task 30 | graphs reused = 1 0.39.060.324 I slot print_timing: id 1 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.060.334 I slot release: id 1 | task 30 | stop processing: n_tokens = 145, truncated = 0 0.39.060.508 I slot print_timing: id 2 | task 29 | prompt eval time = 1369.40 ms / 131 tokens ( 10.45 ms per token, 95.66 tokens per second) 0.39.060.511 I slot print_timing: id 2 | task 29 | eval time = 52.50 ms / 2 tokens ( 52.50 ms per token, 19.05 tokens per second) 0.39.060.511 I slot print_timing: id 2 | task 29 | total time = 1421.91 ms / 133 tokens 0.39.060.511 I slot print_timing: id 2 | task 29 | graphs reused = 1 0.39.060.512 I slot print_timing: id 2 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.060.520 I slot release: id 2 | task 29 | stop processing: n_tokens = 132, truncated = 0 0.39.060.685 I slot print_timing: id 3 | task 31 | prompt eval time = 1369.61 ms / 178 tokens ( 7.69 ms per token, 129.96 tokens per second) 0.39.060.689 I slot print_timing: id 3 | task 31 | eval time = 52.47 ms / 2 tokens ( 52.47 ms per token, 19.06 tokens per second) 0.39.060.689 I slot print_timing: id 3 | task 31 | total time = 1422.07 ms / 180 tokens 0.39.060.690 I slot print_timing: id 3 | task 31 | graphs reused = 1 0.39.060.690 I slot print_timing: id 3 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.060.700 I slot release: id 3 | task 31 | stop processing: n_tokens = 179, truncated = 0 0.39.065.600 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.236 0.39.072.709 I slot launch_slot_: id 0 | task 36 | processing task, is_child = 0 0.39.100.296 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.162 0.39.100.352 I slot launch_slot_: id 3 | task 37 | processing task, is_child = 0 0.39.100.384 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.193 0.39.100.415 I slot launch_slot_: id 1 | task 35 | processing task, is_child = 0 0.39.100.432 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.212 0.39.100.469 I slot launch_slot_: id 2 | task 38 | processing task, is_child = 0 0.40.304.674 I slot print_timing: id 0 | task 36 | prompt eval time = 1151.89 ms / 120 tokens ( 9.60 ms per token, 104.18 tokens per second) 0.40.304.678 I slot print_timing: id 0 | task 36 | eval time = 52.30 ms / 2 tokens ( 52.30 ms per token, 19.12 tokens per second) 0.40.304.678 I slot print_timing: id 0 | task 36 | total time = 1204.19 ms / 122 tokens 0.40.304.678 I slot print_timing: id 0 | task 36 | graphs reused = 1 0.40.304.679 I slot print_timing: id 0 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.304.703 I slot release: id 0 | task 36 | stop processing: n_tokens = 121, truncated = 0 0.40.304.856 I slot print_timing: id 1 | task 35 | prompt eval time = 1152.09 ms / 113 tokens ( 10.20 ms per token, 98.08 tokens per second) 0.40.304.859 I slot print_timing: id 1 | task 35 | eval time = 52.27 ms / 2 tokens ( 52.27 ms per token, 19.13 tokens per second) 0.40.304.860 I slot print_timing: id 1 | task 35 | total time = 1204.37 ms / 115 tokens 0.40.304.860 I slot print_timing: id 1 | task 35 | graphs reused = 1 0.40.304.860 I slot print_timing: id 1 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.304.871 I slot release: id 1 | task 35 | stop processing: n_tokens = 114, truncated = 0 0.40.305.043 I slot print_timing: id 2 | task 38 | prompt eval time = 1152.30 ms / 142 tokens ( 8.11 ms per token, 123.23 tokens per second) 0.40.305.048 I slot print_timing: id 2 | task 38 | eval time = 52.24 ms / 2 tokens ( 52.24 ms per token, 19.14 tokens per second) 0.40.305.049 I slot print_timing: id 2 | task 38 | total time = 1204.54 ms / 144 tokens 0.40.305.049 I slot print_timing: id 2 | task 38 | graphs reused = 1 0.40.305.049 I slot print_timing: id 2 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.305.059 I slot release: id 2 | task 38 | stop processing: n_tokens = 143, truncated = 0 0.40.305.233 I slot print_timing: id 3 | task 37 | prompt eval time = 1152.51 ms / 144 tokens ( 8.00 ms per token, 124.95 tokens per second) 0.40.305.235 I slot print_timing: id 3 | task 37 | eval time = 52.21 ms / 2 tokens ( 52.21 ms per token, 19.15 tokens per second) 0.40.305.236 I slot print_timing: id 3 | task 37 | total time = 1204.72 ms / 146 tokens 0.40.305.236 I slot print_timing: id 3 | task 37 | graphs reused = 1 0.40.305.236 I slot print_timing: id 3 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.305.244 I slot release: id 3 | task 37 | stop processing: n_tokens = 145, truncated = 0 0.40.310.214 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.240 0.40.320.279 I slot launch_slot_: id 0 | task 43 | processing task, is_child = 0 0.40.352.333 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.246 0.40.352.381 I slot launch_slot_: id 1 | task 42 | processing task, is_child = 0 0.40.352.421 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.196 0.40.352.451 I slot launch_slot_: id 2 | task 44 | processing task, is_child = 0 0.40.352.470 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.193 0.40.352.501 I slot launch_slot_: id 3 | task 45 | processing task, is_child = 0 0.41.597.675 I slot print_timing: id 0 | task 43 | prompt eval time = 1192.78 ms / 112 tokens ( 10.65 ms per token, 93.90 tokens per second) 0.41.597.678 I slot print_timing: id 0 | task 43 | eval time = 52.38 ms / 2 tokens ( 52.38 ms per token, 19.09 tokens per second) 0.41.597.679 I slot print_timing: id 0 | task 43 | total time = 1245.16 ms / 114 tokens 0.41.597.679 I slot print_timing: id 0 | task 43 | graphs reused = 1 0.41.597.680 I slot print_timing: id 0 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.597.697 I slot release: id 0 | task 43 | stop processing: n_tokens = 113, truncated = 0 0.41.597.847 I slot print_timing: id 1 | task 42 | prompt eval time = 1192.92 ms / 109 tokens ( 10.94 ms per token, 91.37 tokens per second) 0.41.597.850 I slot print_timing: id 1 | task 42 | eval time = 52.40 ms / 2 tokens ( 52.40 ms per token, 19.08 tokens per second) 0.41.597.850 I slot print_timing: id 1 | task 42 | total time = 1245.33 ms / 111 tokens 0.41.597.851 I slot print_timing: id 1 | task 42 | graphs reused = 1 0.41.597.851 I slot print_timing: id 1 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.597.862 I slot release: id 1 | task 42 | stop processing: n_tokens = 110, truncated = 0 0.41.598.030 I slot print_timing: id 2 | task 44 | prompt eval time = 1193.12 ms / 143 tokens ( 8.34 ms per token, 119.85 tokens per second) 0.41.598.032 I slot print_timing: id 2 | task 44 | eval time = 52.38 ms / 2 tokens ( 52.38 ms per token, 19.09 tokens per second) 0.41.598.032 I slot print_timing: id 2 | task 44 | total time = 1245.50 ms / 145 tokens 0.41.598.032 I slot print_timing: id 2 | task 44 | graphs reused = 1 0.41.598.033 I slot print_timing: id 2 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.598.043 I slot release: id 2 | task 44 | stop processing: n_tokens = 144, truncated = 0 0.41.598.210 I slot print_timing: id 3 | task 45 | prompt eval time = 1193.30 ms / 123 tokens ( 9.70 ms per token, 103.08 tokens per second) 0.41.598.212 I slot print_timing: id 3 | task 45 | eval time = 52.35 ms / 2 tokens ( 52.35 ms per token, 19.10 tokens per second) 0.41.598.212 I slot print_timing: id 3 | task 45 | total time = 1245.65 ms / 125 tokens 0.41.598.213 I slot print_timing: id 3 | task 45 | graphs reused = 1 0.41.598.213 I slot print_timing: id 3 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.598.219 I slot release: id 3 | task 45 | stop processing: n_tokens = 124, truncated = 0 0.41.603.246 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.257 0.41.613.857 I slot launch_slot_: id 0 | task 50 | processing task, is_child = 0 0.41.644.708 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 0.41.644.761 I slot launch_slot_: id 1 | task 49 | processing task, is_child = 0 0.41.644.793 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 0.41.646.226 I slot launch_slot_: id 2 | task 51 | processing task, is_child = 0 0.41.646.248 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.226 0.41.646.279 I slot launch_slot_: id 3 | task 52 | processing task, is_child = 0 0.42.846.331 I slot print_timing: id 0 | task 50 | prompt eval time = 1147.44 ms / 112 tokens ( 10.24 ms per token, 97.61 tokens per second) 0.42.846.334 I slot print_timing: id 0 | task 50 | eval time = 52.60 ms / 2 tokens ( 52.60 ms per token, 19.01 tokens per second) 0.42.846.335 I slot print_timing: id 0 | task 50 | total time = 1200.04 ms / 114 tokens 0.42.846.335 I slot print_timing: id 0 | task 50 | graphs reused = 1 0.42.846.336 I slot print_timing: id 0 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.846.355 I slot release: id 0 | task 50 | stop processing: n_tokens = 113, truncated = 0 0.42.846.504 I slot print_timing: id 1 | task 49 | prompt eval time = 1147.62 ms / 102 tokens ( 11.25 ms per token, 88.88 tokens per second) 0.42.846.509 I slot print_timing: id 1 | task 49 | eval time = 52.59 ms / 2 tokens ( 52.59 ms per token, 19.02 tokens per second) 0.42.846.510 I slot print_timing: id 1 | task 49 | total time = 1200.21 ms / 104 tokens 0.42.846.510 I slot print_timing: id 1 | task 49 | graphs reused = 1 0.42.846.510 I slot print_timing: id 1 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.846.518 I slot release: id 1 | task 49 | stop processing: n_tokens = 103, truncated = 0 0.42.846.674 I slot print_timing: id 2 | task 51 | prompt eval time = 1147.81 ms / 129 tokens ( 8.90 ms per token, 112.39 tokens per second) 0.42.846.675 I slot print_timing: id 2 | task 51 | eval time = 52.56 ms / 2 tokens ( 52.56 ms per token, 19.03 tokens per second) 0.42.846.676 I slot print_timing: id 2 | task 51 | total time = 1200.37 ms / 131 tokens 0.42.846.676 I slot print_timing: id 2 | task 51 | graphs reused = 1 0.42.846.676 I slot print_timing: id 2 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.846.683 I slot release: id 2 | task 51 | stop processing: n_tokens = 130, truncated = 0 0.42.846.855 I slot print_timing: id 3 | task 52 | prompt eval time = 1148.01 ms / 136 tokens ( 8.44 ms per token, 118.47 tokens per second) 0.42.846.857 I slot print_timing: id 3 | task 52 | eval time = 52.53 ms / 2 tokens ( 52.53 ms per token, 19.04 tokens per second) 0.42.846.857 I slot print_timing: id 3 | task 52 | total time = 1200.54 ms / 138 tokens 0.42.846.858 I slot print_timing: id 3 | task 52 | graphs reused = 1 0.42.846.858 I slot print_timing: id 3 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.846.864 I slot release: id 3 | task 52 | stop processing: n_tokens = 137, truncated = 0 0.42.852.039 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.248 0.42.855.893 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.42.886.749 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.272 0.42.886.798 I slot launch_slot_: id 1 | task 57 | processing task, is_child = 0 0.42.886.831 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 0.42.886.864 I slot launch_slot_: id 2 | task 58 | processing task, is_child = 0 0.42.886.883 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.204 0.42.886.919 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 0.44.395.637 I slot print_timing: id 0 | task 56 | prompt eval time = 1456.03 ms / 166 tokens ( 8.77 ms per token, 114.01 tokens per second) 0.44.395.639 I slot print_timing: id 0 | task 56 | eval time = 52.67 ms / 2 tokens ( 52.67 ms per token, 18.99 tokens per second) 0.44.395.640 I slot print_timing: id 0 | task 56 | total time = 1508.71 ms / 168 tokens 0.44.395.641 I slot print_timing: id 0 | task 56 | graphs reused = 1 0.44.395.641 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.395.671 I slot release: id 0 | task 56 | stop processing: n_tokens = 167, truncated = 0 0.44.395.826 I slot print_timing: id 1 | task 57 | prompt eval time = 1456.20 ms / 132 tokens ( 11.03 ms per token, 90.65 tokens per second) 0.44.395.828 I slot print_timing: id 1 | task 57 | eval time = 52.69 ms / 2 tokens ( 52.69 ms per token, 18.98 tokens per second) 0.44.395.828 I slot print_timing: id 1 | task 57 | total time = 1508.89 ms / 134 tokens 0.44.395.829 I slot print_timing: id 1 | task 57 | graphs reused = 1 0.44.395.829 I slot print_timing: id 1 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.395.839 I slot release: id 1 | task 57 | stop processing: n_tokens = 133, truncated = 0 0.44.396.006 I slot print_timing: id 2 | task 58 | prompt eval time = 1456.37 ms / 182 tokens ( 8.00 ms per token, 124.97 tokens per second) 0.44.396.007 I slot print_timing: id 2 | task 58 | eval time = 52.68 ms / 2 tokens ( 52.68 ms per token, 18.98 tokens per second) 0.44.396.008 I slot print_timing: id 2 | task 58 | total time = 1509.06 ms / 184 tokens 0.44.396.008 I slot print_timing: id 2 | task 58 | graphs reused = 1 0.44.396.008 I slot print_timing: id 2 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.396.019 I slot release: id 2 | task 58 | stop processing: n_tokens = 183, truncated = 0 0.44.396.191 I slot print_timing: id 3 | task 59 | prompt eval time = 1456.57 ms / 177 tokens ( 8.23 ms per token, 121.52 tokens per second) 0.44.396.195 I slot print_timing: id 3 | task 59 | eval time = 52.65 ms / 2 tokens ( 52.65 ms per token, 18.99 tokens per second) 0.44.396.195 I slot print_timing: id 3 | task 59 | total time = 1509.23 ms / 179 tokens 0.44.396.195 I slot print_timing: id 3 | task 59 | graphs reused = 1 0.44.396.195 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.396.206 I slot release: id 3 | task 59 | stop processing: n_tokens = 178, truncated = 0 0.44.401.474 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 0.44.412.318 I slot launch_slot_: id 0 | task 63 | processing task, is_child = 0 0.44.443.030 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.211 0.44.443.086 I slot launch_slot_: id 1 | task 64 | processing task, is_child = 0 0.44.443.125 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.153 0.44.444.668 I slot launch_slot_: id 2 | task 65 | processing task, is_child = 0 0.44.444.691 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.157 0.44.444.732 I slot launch_slot_: id 3 | task 66 | processing task, is_child = 0 0.45.881.620 I slot print_timing: id 0 | task 63 | prompt eval time = 1384.60 ms / 123 tokens ( 11.26 ms per token, 88.83 tokens per second) 0.45.881.622 I slot print_timing: id 0 | task 63 | eval time = 52.28 ms / 2 tokens ( 52.28 ms per token, 19.13 tokens per second) 0.45.881.622 I slot print_timing: id 0 | task 63 | total time = 1436.88 ms / 125 tokens 0.45.881.623 I slot print_timing: id 0 | task 63 | graphs reused = 1 0.45.881.623 I slot print_timing: id 0 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.881.641 I slot release: id 0 | task 63 | stop processing: n_tokens = 124, truncated = 0 0.45.881.797 I slot print_timing: id 1 | task 64 | prompt eval time = 1384.74 ms / 169 tokens ( 8.19 ms per token, 122.04 tokens per second) 0.45.881.800 I slot print_timing: id 1 | task 64 | eval time = 52.30 ms / 2 tokens ( 52.30 ms per token, 19.12 tokens per second) 0.45.881.800 I slot print_timing: id 1 | task 64 | total time = 1437.04 ms / 171 tokens 0.45.881.801 I slot print_timing: id 1 | task 64 | graphs reused = 1 0.45.881.801 I slot print_timing: id 1 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.881.813 I slot release: id 1 | task 64 | stop processing: n_tokens = 170, truncated = 0 0.45.881.983 I slot print_timing: id 2 | task 65 | prompt eval time = 1384.88 ms / 140 tokens ( 9.89 ms per token, 101.09 tokens per second) 0.45.881.989 I slot print_timing: id 2 | task 65 | eval time = 52.33 ms / 2 tokens ( 52.33 ms per token, 19.11 tokens per second) 0.45.881.990 I slot print_timing: id 2 | task 65 | total time = 1437.21 ms / 142 tokens 0.45.881.990 I slot print_timing: id 2 | task 65 | graphs reused = 1 0.45.881.990 I slot print_timing: id 2 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.882.000 I slot release: id 2 | task 65 | stop processing: n_tokens = 141, truncated = 0 0.45.882.195 I slot print_timing: id 3 | task 66 | prompt eval time = 1385.03 ms / 149 tokens ( 9.30 ms per token, 107.58 tokens per second) 0.45.882.197 I slot print_timing: id 3 | task 66 | eval time = 52.38 ms / 2 tokens ( 52.38 ms per token, 19.09 tokens per second) 0.45.882.197 I slot print_timing: id 3 | task 66 | total time = 1437.41 ms / 151 tokens 0.45.882.197 I slot print_timing: id 3 | task 66 | graphs reused = 1 0.45.882.197 I slot print_timing: id 3 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.882.205 I slot release: id 3 | task 66 | stop processing: n_tokens = 150, truncated = 0 0.45.886.910 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 0.45.894.072 I slot launch_slot_: id 0 | task 70 | processing task, is_child = 0 0.45.921.897 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.165 0.45.921.952 I slot launch_slot_: id 1 | task 71 | processing task, is_child = 0 0.45.921.989 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.206 0.45.922.022 I slot launch_slot_: id 2 | task 72 | processing task, is_child = 0 0.45.922.042 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.187 0.45.922.075 I slot launch_slot_: id 3 | task 73 | processing task, is_child = 0 0.47.409.162 I slot print_timing: id 0 | task 70 | prompt eval time = 1434.25 ms / 128 tokens ( 11.21 ms per token, 89.25 tokens per second) 0.47.409.164 I slot print_timing: id 0 | task 70 | eval time = 52.82 ms / 2 tokens ( 52.82 ms per token, 18.93 tokens per second) 0.47.409.165 I slot print_timing: id 0 | task 70 | total time = 1487.08 ms / 130 tokens 0.47.409.165 I slot print_timing: id 0 | task 70 | graphs reused = 1 0.47.409.165 I slot print_timing: id 0 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.409.184 I slot release: id 0 | task 70 | stop processing: n_tokens = 129, truncated = 0 0.47.409.336 I slot print_timing: id 1 | task 71 | prompt eval time = 1434.43 ms / 163 tokens ( 8.80 ms per token, 113.63 tokens per second) 0.47.409.339 I slot print_timing: id 1 | task 71 | eval time = 52.80 ms / 2 tokens ( 52.80 ms per token, 18.94 tokens per second) 0.47.409.339 I slot print_timing: id 1 | task 71 | total time = 1487.23 ms / 165 tokens 0.47.409.339 I slot print_timing: id 1 | task 71 | graphs reused = 1 0.47.409.339 I slot print_timing: id 1 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.409.351 I slot release: id 1 | task 71 | stop processing: n_tokens = 164, truncated = 0 0.47.409.530 I slot print_timing: id 2 | task 72 | prompt eval time = 1434.61 ms / 111 tokens ( 12.92 ms per token, 77.37 tokens per second) 0.47.409.531 I slot print_timing: id 2 | task 72 | eval time = 52.80 ms / 2 tokens ( 52.80 ms per token, 18.94 tokens per second) 0.47.409.531 I slot print_timing: id 2 | task 72 | total time = 1487.41 ms / 113 tokens 0.47.409.532 I slot print_timing: id 2 | task 72 | graphs reused = 1 0.47.409.532 I slot print_timing: id 2 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.409.540 I slot release: id 2 | task 72 | stop processing: n_tokens = 112, truncated = 0 0.47.409.731 I slot print_timing: id 3 | task 73 | prompt eval time = 1434.82 ms / 161 tokens ( 8.91 ms per token, 112.21 tokens per second) 0.47.409.733 I slot print_timing: id 3 | task 73 | eval time = 52.78 ms / 2 tokens ( 52.78 ms per token, 18.95 tokens per second) 0.47.409.734 I slot print_timing: id 3 | task 73 | total time = 1487.60 ms / 163 tokens 0.47.409.734 I slot print_timing: id 3 | task 73 | graphs reused = 1 0.47.409.734 I slot print_timing: id 3 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.409.746 I slot release: id 3 | task 73 | stop processing: n_tokens = 162, truncated = 0 0.47.414.618 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 0.47.424.866 I slot launch_slot_: id 1 | task 77 | processing task, is_child = 0 0.47.455.366 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.217 0.47.455.419 I slot launch_slot_: id 0 | task 78 | processing task, is_child = 0 0.47.455.451 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.250 0.47.455.482 I slot launch_slot_: id 2 | task 79 | processing task, is_child = 0 0.47.455.505 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.179 0.47.455.538 I slot launch_slot_: id 3 | task 80 | processing task, is_child = 0 0.48.733.838 I slot print_timing: id 0 | task 78 | prompt eval time = 1225.59 ms / 112 tokens ( 10.94 ms per token, 91.38 tokens per second) 0.48.733.840 I slot print_timing: id 0 | task 78 | eval time = 52.70 ms / 2 tokens ( 52.70 ms per token, 18.97 tokens per second) 0.48.733.840 I slot print_timing: id 0 | task 78 | total time = 1278.29 ms / 114 tokens 0.48.733.841 I slot print_timing: id 0 | task 78 | graphs reused = 1 0.48.733.841 I slot print_timing: id 0 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.733.860 I slot release: id 0 | task 78 | stop processing: n_tokens = 113, truncated = 0 0.48.734.012 I slot print_timing: id 1 | task 77 | prompt eval time = 1225.77 ms / 109 tokens ( 11.25 ms per token, 88.92 tokens per second) 0.48.734.014 I slot print_timing: id 1 | task 77 | eval time = 52.69 ms / 2 tokens ( 52.69 ms per token, 18.98 tokens per second) 0.48.734.016 I slot print_timing: id 1 | task 77 | total time = 1278.45 ms / 111 tokens 0.48.734.016 I slot print_timing: id 1 | task 77 | graphs reused = 1 0.48.734.016 I slot print_timing: id 1 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.734.026 I slot release: id 1 | task 77 | stop processing: n_tokens = 110, truncated = 0 0.48.734.194 I slot print_timing: id 2 | task 79 | prompt eval time = 1225.94 ms / 167 tokens ( 7.34 ms per token, 136.22 tokens per second) 0.48.734.199 I slot print_timing: id 2 | task 79 | eval time = 52.67 ms / 2 tokens ( 52.67 ms per token, 18.99 tokens per second) 0.48.734.199 I slot print_timing: id 2 | task 79 | total time = 1278.61 ms / 169 tokens 0.48.734.199 I slot print_timing: id 2 | task 79 | graphs reused = 1 0.48.734.200 I slot print_timing: id 2 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.734.213 I slot release: id 2 | task 79 | stop processing: n_tokens = 168, truncated = 0 0.48.734.372 I slot print_timing: id 3 | task 80 | prompt eval time = 1226.16 ms / 164 tokens ( 7.48 ms per token, 133.75 tokens per second) 0.48.734.378 I slot print_timing: id 3 | task 80 | eval time = 52.63 ms / 2 tokens ( 52.63 ms per token, 19.00 tokens per second) 0.48.734.378 I slot print_timing: id 3 | task 80 | total time = 1278.78 ms / 166 tokens 0.48.734.379 I slot print_timing: id 3 | task 80 | graphs reused = 1 0.48.734.379 I slot print_timing: id 3 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.734.391 I slot release: id 3 | task 80 | stop processing: n_tokens = 165, truncated = 0 0.48.739.824 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.248 0.48.752.175 I slot launch_slot_: id 0 | task 84 | processing task, is_child = 0 0.48.776.163 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.255 0.48.776.226 I slot launch_slot_: id 1 | task 85 | processing task, is_child = 0 0.48.776.268 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.167 0.48.776.309 I slot launch_slot_: id 2 | task 86 | processing task, is_child = 0 0.48.776.330 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 0.48.776.374 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 0.50.013.388 I slot print_timing: id 0 | task 84 | prompt eval time = 1184.50 ms / 122 tokens ( 9.71 ms per token, 103.00 tokens per second) 0.50.013.390 I slot print_timing: id 0 | task 84 | eval time = 52.50 ms / 2 tokens ( 52.50 ms per token, 19.05 tokens per second) 0.50.013.390 I slot print_timing: id 0 | task 84 | total time = 1237.00 ms / 124 tokens 0.50.013.391 I slot print_timing: id 0 | task 84 | graphs reused = 1 0.50.013.391 I slot print_timing: id 0 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.013.409 I slot release: id 0 | task 84 | stop processing: n_tokens = 123, truncated = 0 0.50.013.567 I slot print_timing: id 1 | task 85 | prompt eval time = 1184.68 ms / 120 tokens ( 9.87 ms per token, 101.29 tokens per second) 0.50.013.569 I slot print_timing: id 1 | task 85 | eval time = 52.48 ms / 2 tokens ( 52.48 ms per token, 19.05 tokens per second) 0.50.013.570 I slot print_timing: id 1 | task 85 | total time = 1237.16 ms / 122 tokens 0.50.013.570 I slot print_timing: id 1 | task 85 | graphs reused = 1 0.50.013.570 I slot print_timing: id 1 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.013.581 I slot release: id 1 | task 85 | stop processing: n_tokens = 121, truncated = 0 0.50.013.736 I slot print_timing: id 2 | task 86 | prompt eval time = 1184.87 ms / 147 tokens ( 8.06 ms per token, 124.06 tokens per second) 0.50.013.737 I slot print_timing: id 2 | task 86 | eval time = 52.45 ms / 2 tokens ( 52.45 ms per token, 19.07 tokens per second) 0.50.013.738 I slot print_timing: id 2 | task 86 | total time = 1237.32 ms / 149 tokens 0.50.013.738 I slot print_timing: id 2 | task 86 | graphs reused = 1 0.50.013.738 I slot print_timing: id 2 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.013.751 I slot release: id 2 | task 86 | stop processing: n_tokens = 148, truncated = 0 0.50.013.918 I slot print_timing: id 3 | task 87 | prompt eval time = 1185.06 ms / 131 tokens ( 9.05 ms per token, 110.54 tokens per second) 0.50.013.920 I slot print_timing: id 3 | task 87 | eval time = 52.43 ms / 2 tokens ( 52.43 ms per token, 19.07 tokens per second) 0.50.013.920 I slot print_timing: id 3 | task 87 | total time = 1237.48 ms / 133 tokens 0.50.013.921 I slot print_timing: id 3 | task 87 | graphs reused = 1 0.50.013.921 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.013.929 I slot release: id 3 | task 87 | stop processing: n_tokens = 132, truncated = 0 0.50.018.867 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.236 0.50.029.216 I slot launch_slot_: id 0 | task 91 | processing task, is_child = 0 0.50.060.082 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.231 0.50.060.133 I slot launch_slot_: id 1 | task 92 | processing task, is_child = 0 0.50.060.169 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.189 0.50.061.602 I slot launch_slot_: id 2 | task 93 | processing task, is_child = 0 0.50.061.622 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 0.50.061.654 I slot launch_slot_: id 3 | task 94 | processing task, is_child = 0 0.51.294.076 I slot print_timing: id 0 | task 91 | prompt eval time = 1180.24 ms / 131 tokens ( 9.01 ms per token, 110.99 tokens per second) 0.51.294.078 I slot print_timing: id 0 | task 91 | eval time = 52.17 ms / 2 tokens ( 52.17 ms per token, 19.17 tokens per second) 0.51.294.078 I slot print_timing: id 0 | task 91 | total time = 1232.41 ms / 133 tokens 0.51.294.079 I slot print_timing: id 0 | task 91 | graphs reused = 1 0.51.294.079 I slot print_timing: id 0 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.294.099 I slot release: id 0 | task 91 | stop processing: n_tokens = 132, truncated = 0 0.51.294.256 I slot print_timing: id 1 | task 92 | prompt eval time = 1180.44 ms / 124 tokens ( 9.52 ms per token, 105.05 tokens per second) 0.51.294.261 I slot print_timing: id 1 | task 92 | eval time = 52.14 ms / 2 tokens ( 52.14 ms per token, 19.18 tokens per second) 0.51.294.262 I slot print_timing: id 1 | task 92 | total time = 1232.59 ms / 126 tokens 0.51.294.262 I slot print_timing: id 1 | task 92 | graphs reused = 1 0.51.294.263 I slot print_timing: id 1 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.294.274 I slot release: id 1 | task 92 | stop processing: n_tokens = 125, truncated = 0 0.51.294.460 I slot print_timing: id 2 | task 93 | prompt eval time = 1180.63 ms / 141 tokens ( 8.37 ms per token, 119.43 tokens per second) 0.51.294.464 I slot print_timing: id 2 | task 93 | eval time = 52.15 ms / 2 tokens ( 52.15 ms per token, 19.18 tokens per second) 0.51.294.465 I slot print_timing: id 2 | task 93 | total time = 1232.78 ms / 143 tokens 0.51.294.465 I slot print_timing: id 2 | task 93 | graphs reused = 1 0.51.294.465 I slot print_timing: id 2 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.294.475 I slot release: id 2 | task 93 | stop processing: n_tokens = 142, truncated = 0 0.51.294.662 I slot print_timing: id 3 | task 94 | prompt eval time = 1180.85 ms / 144 tokens ( 8.20 ms per token, 121.95 tokens per second) 0.51.294.664 I slot print_timing: id 3 | task 94 | eval time = 52.12 ms / 2 tokens ( 52.12 ms per token, 19.19 tokens per second) 0.51.294.665 I slot print_timing: id 3 | task 94 | total time = 1232.97 ms / 146 tokens 0.51.294.665 I slot print_timing: id 3 | task 94 | graphs reused = 1 0.51.294.665 I slot print_timing: id 3 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.294.673 I slot release: id 3 | task 94 | stop processing: n_tokens = 145, truncated = 0 0.51.299.455 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.212 0.51.307.151 I slot launch_slot_: id 0 | task 99 | processing task, is_child = 0 0.51.335.551 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 0.51.335.620 I slot launch_slot_: id 3 | task 98 | processing task, is_child = 0 0.51.335.656 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.224 0.51.335.698 I slot launch_slot_: id 1 | task 100 | processing task, is_child = 0 0.51.335.724 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 0.51.335.763 I slot launch_slot_: id 2 | task 101 | processing task, is_child = 0 0.52.674.248 I slot print_timing: id 0 | task 99 | prompt eval time = 1285.90 ms / 121 tokens ( 10.63 ms per token, 94.10 tokens per second) 0.52.674.251 I slot print_timing: id 0 | task 99 | eval time = 52.57 ms / 2 tokens ( 52.57 ms per token, 19.02 tokens per second) 0.52.674.251 I slot print_timing: id 0 | task 99 | total time = 1338.47 ms / 123 tokens 0.52.674.252 I slot print_timing: id 0 | task 99 | graphs reused = 1 0.52.674.252 I slot print_timing: id 0 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.674.272 I slot release: id 0 | task 99 | stop processing: n_tokens = 122, truncated = 0 0.52.674.428 I slot print_timing: id 1 | task 100 | prompt eval time = 1286.08 ms / 107 tokens ( 12.02 ms per token, 83.20 tokens per second) 0.52.674.431 I slot print_timing: id 1 | task 100 | eval time = 52.55 ms / 2 tokens ( 52.55 ms per token, 19.03 tokens per second) 0.52.674.432 I slot print_timing: id 1 | task 100 | total time = 1338.64 ms / 109 tokens 0.52.674.432 I slot print_timing: id 1 | task 100 | graphs reused = 1 0.52.674.432 I slot print_timing: id 1 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.674.443 I slot release: id 1 | task 100 | stop processing: n_tokens = 108, truncated = 0 0.52.674.605 I slot print_timing: id 2 | task 101 | prompt eval time = 1286.27 ms / 172 tokens ( 7.48 ms per token, 133.72 tokens per second) 0.52.674.607 I slot print_timing: id 2 | task 101 | eval time = 52.52 ms / 2 tokens ( 52.52 ms per token, 19.04 tokens per second) 0.52.674.607 I slot print_timing: id 2 | task 101 | total time = 1338.80 ms / 174 tokens 0.52.674.607 I slot print_timing: id 2 | task 101 | graphs reused = 1 0.52.674.608 I slot print_timing: id 2 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.674.622 I slot release: id 2 | task 101 | stop processing: n_tokens = 173, truncated = 0 0.52.674.785 I slot print_timing: id 3 | task 98 | prompt eval time = 1286.47 ms / 118 tokens ( 10.90 ms per token, 91.72 tokens per second) 0.52.674.787 I slot print_timing: id 3 | task 98 | eval time = 52.49 ms / 2 tokens ( 52.49 ms per token, 19.05 tokens per second) 0.52.674.787 I slot print_timing: id 3 | task 98 | total time = 1338.96 ms / 120 tokens 0.52.674.787 I slot print_timing: id 3 | task 98 | graphs reused = 1 0.52.674.787 I slot print_timing: id 3 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.674.793 I slot release: id 3 | task 98 | stop processing: n_tokens = 119, truncated = 0 0.52.679.828 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 0.52.695.787 I slot launch_slot_: id 1 | task 105 | processing task, is_child = 0 0.52.747.954 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 0.52.748.042 I slot launch_slot_: id 3 | task 106 | processing task, is_child = 0 0.52.748.082 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 0.52.748.121 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.52.748.143 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 0.52.748.183 I slot launch_slot_: id 2 | task 108 | processing task, is_child = 0 0.54.397.367 I slot print_timing: id 0 | task 107 | prompt eval time = 1596.69 ms / 177 tokens ( 9.02 ms per token, 110.85 tokens per second) 0.54.397.370 I slot print_timing: id 0 | task 107 | eval time = 52.48 ms / 2 tokens ( 52.48 ms per token, 19.05 tokens per second) 0.54.397.371 I slot print_timing: id 0 | task 107 | total time = 1649.17 ms / 179 tokens 0.54.397.371 I slot print_timing: id 0 | task 107 | graphs reused = 1 0.54.397.371 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.397.394 I slot release: id 0 | task 107 | stop processing: n_tokens = 178, truncated = 0 0.54.397.550 I slot print_timing: id 1 | task 105 | prompt eval time = 1596.88 ms / 136 tokens ( 11.74 ms per token, 85.17 tokens per second) 0.54.397.554 I slot print_timing: id 1 | task 105 | eval time = 52.46 ms / 2 tokens ( 52.46 ms per token, 19.06 tokens per second) 0.54.397.554 I slot print_timing: id 1 | task 105 | total time = 1649.34 ms / 138 tokens 0.54.397.555 I slot print_timing: id 1 | task 105 | graphs reused = 1 0.54.397.555 I slot print_timing: id 1 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.397.565 I slot release: id 1 | task 105 | stop processing: n_tokens = 137, truncated = 0 0.54.397.728 I slot print_timing: id 2 | task 108 | prompt eval time = 1597.07 ms / 240 tokens ( 6.65 ms per token, 150.28 tokens per second) 0.54.397.731 I slot print_timing: id 2 | task 108 | eval time = 52.43 ms / 2 tokens ( 52.43 ms per token, 19.07 tokens per second) 0.54.397.731 I slot print_timing: id 2 | task 108 | total time = 1649.50 ms / 242 tokens 0.54.397.731 I slot print_timing: id 2 | task 108 | graphs reused = 1 0.54.397.732 I slot print_timing: id 2 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.397.745 I slot release: id 2 | task 108 | stop processing: n_tokens = 241, truncated = 0 0.54.397.923 I slot print_timing: id 3 | task 106 | prompt eval time = 1597.26 ms / 116 tokens ( 13.77 ms per token, 72.62 tokens per second) 0.54.397.925 I slot print_timing: id 3 | task 106 | eval time = 52.42 ms / 2 tokens ( 52.42 ms per token, 19.08 tokens per second) 0.54.397.926 I slot print_timing: id 3 | task 106 | total time = 1649.68 ms / 118 tokens 0.54.397.926 I slot print_timing: id 3 | task 106 | graphs reused = 1 0.54.397.926 I slot print_timing: id 3 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.397.934 I slot release: id 3 | task 106 | stop processing: n_tokens = 117, truncated = 0 0.54.402.871 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 0.54.429.715 I slot launch_slot_: id 0 | task 112 | processing task, is_child = 0 0.55.218.513 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 0.55.218.653 I slot launch_slot_: id 3 | task 113 | processing task, is_child = 0 0.55.218.695 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 0.55.220.419 I slot launch_slot_: id 1 | task 114 | processing task, is_child = 0 0.55.220.452 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 0.55.220.489 I slot launch_slot_: id 2 | task 115 | processing task, is_child = 0 0.56.973.314 I slot print_timing: id 0 | task 112 | prompt eval time = 1698.50 ms / 160 tokens ( 10.62 ms per token, 94.20 tokens per second) 0.56.973.316 I slot print_timing: id 0 | task 112 | eval time = 54.31 ms / 2 tokens ( 54.31 ms per token, 18.41 tokens per second) 0.56.973.317 I slot print_timing: id 0 | task 112 | total time = 1752.81 ms / 162 tokens 0.56.973.317 I slot print_timing: id 0 | task 112 | graphs reused = 1 0.56.973.318 I slot print_timing: id 0 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.973.432 I slot release: id 0 | task 112 | stop processing: n_tokens = 161, truncated = 0 0.56.973.800 I slot print_timing: id 1 | task 114 | prompt eval time = 1699.12 ms / 155 tokens ( 10.96 ms per token, 91.22 tokens per second) 0.56.973.802 I slot print_timing: id 1 | task 114 | eval time = 54.17 ms / 2 tokens ( 54.17 ms per token, 18.46 tokens per second) 0.56.973.802 I slot print_timing: id 1 | task 114 | total time = 1753.29 ms / 157 tokens 0.56.973.803 I slot print_timing: id 1 | task 114 | graphs reused = 1 0.56.973.803 I slot print_timing: id 1 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.973.835 I slot release: id 1 | task 114 | stop processing: n_tokens = 156, truncated = 0 0.56.974.189 I slot print_timing: id 2 | task 115 | prompt eval time = 1699.84 ms / 226 tokens ( 7.52 ms per token, 132.95 tokens per second) 0.56.974.194 I slot print_timing: id 2 | task 115 | eval time = 53.82 ms / 2 tokens ( 53.82 ms per token, 18.58 tokens per second) 0.56.974.194 I slot print_timing: id 2 | task 115 | total time = 1753.67 ms / 228 tokens 0.56.974.194 I slot print_timing: id 2 | task 115 | graphs reused = 1 0.56.974.195 I slot print_timing: id 2 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.974.238 I slot release: id 2 | task 115 | stop processing: n_tokens = 227, truncated = 0 0.56.974.434 I slot print_timing: id 3 | task 113 | prompt eval time = 1700.74 ms / 142 tokens ( 11.98 ms per token, 83.49 tokens per second) 0.56.974.438 I slot print_timing: id 3 | task 113 | eval time = 53.16 ms / 2 tokens ( 53.16 ms per token, 18.81 tokens per second) 0.56.974.439 I slot print_timing: id 3 | task 113 | total time = 1753.89 ms / 144 tokens 0.56.974.439 I slot print_timing: id 3 | task 113 | graphs reused = 1 0.56.974.439 I slot print_timing: id 3 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.974.453 I slot release: id 3 | task 113 | stop processing: n_tokens = 143, truncated = 0 0.56.992.049 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.174 0.57.022.669 I slot launch_slot_: id 0 | task 121 | processing task, is_child = 0 0.57.085.974 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 0.57.086.083 I slot launch_slot_: id 3 | task 120 | processing task, is_child = 0 0.57.086.125 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 0.57.086.171 I slot launch_slot_: id 1 | task 119 | processing task, is_child = 0 0.57.086.194 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.123 0.57.100.535 I slot launch_slot_: id 2 | task 122 | processing task, is_child = 0 0.58.595.495 I slot print_timing: id 0 | task 121 | prompt eval time = 1442.45 ms / 141 tokens ( 10.23 ms per token, 97.75 tokens per second) 0.58.595.498 I slot print_timing: id 0 | task 121 | eval time = 52.49 ms / 2 tokens ( 52.49 ms per token, 19.05 tokens per second) 0.58.595.498 I slot print_timing: id 0 | task 121 | total time = 1494.94 ms / 143 tokens 0.58.595.499 I slot print_timing: id 0 | task 121 | graphs reused = 1 0.58.595.499 I slot print_timing: id 0 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.595.545 I slot release: id 0 | task 121 | stop processing: n_tokens = 142, truncated = 0 0.58.595.700 I slot print_timing: id 1 | task 119 | prompt eval time = 1442.64 ms / 114 tokens ( 12.65 ms per token, 79.02 tokens per second) 0.58.595.702 I slot print_timing: id 1 | task 119 | eval time = 52.49 ms / 2 tokens ( 52.49 ms per token, 19.05 tokens per second) 0.58.595.702 I slot print_timing: id 1 | task 119 | total time = 1495.13 ms / 116 tokens 0.58.595.702 I slot print_timing: id 1 | task 119 | graphs reused = 1 0.58.595.703 I slot print_timing: id 1 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.595.748 I slot release: id 1 | task 119 | stop processing: n_tokens = 115, truncated = 0 0.58.595.912 I slot print_timing: id 2 | task 122 | prompt eval time = 1442.94 ms / 192 tokens ( 7.52 ms per token, 133.06 tokens per second) 0.58.595.913 I slot print_timing: id 2 | task 122 | eval time = 52.38 ms / 2 tokens ( 52.38 ms per token, 19.09 tokens per second) 0.58.595.914 I slot print_timing: id 2 | task 122 | total time = 1495.33 ms / 194 tokens 0.58.595.914 I slot print_timing: id 2 | task 122 | graphs reused = 1 0.58.595.914 I slot print_timing: id 2 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.595.994 I slot release: id 2 | task 122 | stop processing: n_tokens = 193, truncated = 0 0.58.596.180 I slot print_timing: id 3 | task 120 | prompt eval time = 1443.14 ms / 105 tokens ( 13.74 ms per token, 72.76 tokens per second) 0.58.596.193 I slot print_timing: id 3 | task 120 | eval time = 52.45 ms / 2 tokens ( 52.45 ms per token, 19.07 tokens per second) 0.58.596.193 I slot print_timing: id 3 | task 120 | total time = 1495.58 ms / 107 tokens 0.58.596.193 I slot print_timing: id 3 | task 120 | graphs reused = 1 0.58.596.194 I slot print_timing: id 3 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.596.207 I slot release: id 3 | task 120 | stop processing: n_tokens = 106, truncated = 0 0.58.601.300 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.252 0.58.623.346 I slot launch_slot_: id 1 | task 126 | processing task, is_child = 0 0.58.654.878 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 0.58.677.653 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.274 0.58.677.740 I slot launch_slot_: id 3 | task 127 | processing task, is_child = 0 0.58.677.789 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.197 0.58.677.833 I slot launch_slot_: id 0 | task 128 | processing task, is_child = 0 0.58.677.855 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.145 0.58.677.895 I slot launch_slot_: id 2 | task 129 | processing task, is_child = 0 1.00.103.754 I slot print_timing: id 0 | task 128 | prompt eval time = 1373.59 ms / 135 tokens ( 10.17 ms per token, 98.28 tokens per second) 1.00.103.756 I slot print_timing: id 0 | task 128 | eval time = 52.25 ms / 2 tokens ( 52.25 ms per token, 19.14 tokens per second) 1.00.103.757 I slot print_timing: id 0 | task 128 | total time = 1425.85 ms / 137 tokens 1.00.103.757 I slot print_timing: id 0 | task 128 | graphs reused = 1 1.00.103.758 I slot print_timing: id 0 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.103.805 I slot release: id 0 | task 128 | stop processing: n_tokens = 136, truncated = 0 1.00.103.956 I slot print_timing: id 1 | task 126 | prompt eval time = 1373.77 ms / 108 tokens ( 12.72 ms per token, 78.62 tokens per second) 1.00.103.958 I slot print_timing: id 1 | task 126 | eval time = 52.26 ms / 2 tokens ( 52.26 ms per token, 19.13 tokens per second) 1.00.103.958 I slot print_timing: id 1 | task 126 | total time = 1426.03 ms / 110 tokens 1.00.103.959 I slot print_timing: id 1 | task 126 | graphs reused = 1 1.00.103.959 I slot print_timing: id 1 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.103.982 I slot release: id 1 | task 126 | stop processing: n_tokens = 109, truncated = 0 1.00.104.140 I slot print_timing: id 2 | task 129 | prompt eval time = 1373.95 ms / 172 tokens ( 7.99 ms per token, 125.19 tokens per second) 1.00.104.141 I slot print_timing: id 2 | task 129 | eval time = 52.25 ms / 2 tokens ( 52.25 ms per token, 19.14 tokens per second) 1.00.104.142 I slot print_timing: id 2 | task 129 | total time = 1426.20 ms / 174 tokens 1.00.104.142 I slot print_timing: id 2 | task 129 | graphs reused = 1 1.00.104.142 I slot print_timing: id 2 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.104.176 I slot release: id 2 | task 129 | stop processing: n_tokens = 173, truncated = 0 1.00.104.347 I slot print_timing: id 3 | task 127 | prompt eval time = 1374.13 ms / 122 tokens ( 11.26 ms per token, 88.78 tokens per second) 1.00.104.349 I slot print_timing: id 3 | task 127 | eval time = 52.26 ms / 2 tokens ( 52.26 ms per token, 19.14 tokens per second) 1.00.104.349 I slot print_timing: id 3 | task 127 | total time = 1426.39 ms / 124 tokens 1.00.104.349 I slot print_timing: id 3 | task 127 | graphs reused = 1 1.00.104.350 I slot print_timing: id 3 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.104.363 I slot release: id 3 | task 127 | stop processing: n_tokens = 123, truncated = 0 1.00.109.717 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.206 1.00.109.749 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.895 MiB) 1.00.143.984 I slot launch_slot_: id 0 | task 133 | processing task, is_child = 0 1.00.144.018 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 1.00.166.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.775 MiB) 1.00.193.099 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.618 MiB) 1.00.216.080 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.257 1.00.216.169 I slot launch_slot_: id 1 | task 134 | processing task, is_child = 0 1.00.216.210 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 1.00.221.382 I slot launch_slot_: id 3 | task 135 | processing task, is_child = 0 1.00.221.408 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.162 1.00.221.443 I slot launch_slot_: id 2 | task 136 | processing task, is_child = 0 1.01.558.299 I slot print_timing: id 0 | task 133 | prompt eval time = 1284.21 ms / 135 tokens ( 9.51 ms per token, 105.12 tokens per second) 1.01.558.303 I slot print_timing: id 0 | task 133 | eval time = 52.63 ms / 2 tokens ( 52.63 ms per token, 19.00 tokens per second) 1.01.558.304 I slot print_timing: id 0 | task 133 | total time = 1336.84 ms / 137 tokens 1.01.558.304 I slot print_timing: id 0 | task 133 | graphs reused = 1 1.01.558.305 I slot print_timing: id 0 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.558.343 I slot release: id 0 | task 133 | stop processing: n_tokens = 136, truncated = 0 1.01.558.494 I slot print_timing: id 1 | task 134 | prompt eval time = 1284.39 ms / 134 tokens ( 9.58 ms per token, 104.33 tokens per second) 1.01.558.498 I slot print_timing: id 1 | task 134 | eval time = 52.64 ms / 2 tokens ( 52.64 ms per token, 19.00 tokens per second) 1.01.558.499 I slot print_timing: id 1 | task 134 | total time = 1337.02 ms / 136 tokens 1.01.558.499 I slot print_timing: id 1 | task 134 | graphs reused = 1 1.01.558.500 I slot print_timing: id 1 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.558.541 I slot release: id 1 | task 134 | stop processing: n_tokens = 135, truncated = 0 1.01.558.702 I slot print_timing: id 2 | task 136 | prompt eval time = 1284.58 ms / 159 tokens ( 8.08 ms per token, 123.78 tokens per second) 1.01.558.707 I slot print_timing: id 2 | task 136 | eval time = 52.64 ms / 2 tokens ( 52.64 ms per token, 19.00 tokens per second) 1.01.558.707 I slot print_timing: id 2 | task 136 | total time = 1337.22 ms / 161 tokens 1.01.558.708 I slot print_timing: id 2 | task 136 | graphs reused = 1 1.01.558.708 I slot print_timing: id 2 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.558.770 I slot release: id 2 | task 136 | stop processing: n_tokens = 160, truncated = 0 1.01.558.934 I slot print_timing: id 3 | task 135 | prompt eval time = 1284.77 ms / 120 tokens ( 10.71 ms per token, 93.40 tokens per second) 1.01.558.936 I slot print_timing: id 3 | task 135 | eval time = 52.67 ms / 2 tokens ( 52.67 ms per token, 18.99 tokens per second) 1.01.558.937 I slot print_timing: id 3 | task 135 | total time = 1337.44 ms / 122 tokens 1.01.558.937 I slot print_timing: id 3 | task 135 | graphs reused = 1 1.01.558.937 I slot print_timing: id 3 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.558.968 I slot release: id 3 | task 135 | stop processing: n_tokens = 121, truncated = 0 1.01.564.610 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.206 1.01.578.079 I slot launch_slot_: id 0 | task 140 | processing task, is_child = 0 1.01.578.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.557 MiB) 1.01.600.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.934 MiB) 1.01.621.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.091 MiB) 1.01.634.239 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.207 1.01.634.313 I slot launch_slot_: id 1 | task 141 | processing task, is_child = 0 1.01.634.349 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.175 1.01.634.386 I slot launch_slot_: id 2 | task 142 | processing task, is_child = 0 1.01.634.406 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.231 1.01.634.437 I slot launch_slot_: id 3 | task 143 | processing task, is_child = 0 1.03.045.852 I slot print_timing: id 0 | task 140 | prompt eval time = 1358.92 ms / 130 tokens ( 10.45 ms per token, 95.66 tokens per second) 1.03.045.854 I slot print_timing: id 0 | task 140 | eval time = 52.48 ms / 2 tokens ( 52.48 ms per token, 19.05 tokens per second) 1.03.045.855 I slot print_timing: id 0 | task 140 | total time = 1411.40 ms / 132 tokens 1.03.045.855 I slot print_timing: id 0 | task 140 | graphs reused = 1 1.03.045.856 I slot print_timing: id 0 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.045.907 I slot release: id 0 | task 140 | stop processing: n_tokens = 131, truncated = 0 1.03.046.063 I slot print_timing: id 1 | task 141 | prompt eval time = 1359.11 ms / 175 tokens ( 7.77 ms per token, 128.76 tokens per second) 1.03.046.068 I slot print_timing: id 1 | task 141 | eval time = 52.50 ms / 2 tokens ( 52.50 ms per token, 19.05 tokens per second) 1.03.046.069 I slot print_timing: id 1 | task 141 | total time = 1411.60 ms / 177 tokens 1.03.046.069 I slot print_timing: id 1 | task 141 | graphs reused = 1 1.03.046.069 I slot print_timing: id 1 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.046.099 I slot release: id 1 | task 141 | stop processing: n_tokens = 176, truncated = 0 1.03.046.270 I slot print_timing: id 2 | task 142 | prompt eval time = 1359.29 ms / 172 tokens ( 7.90 ms per token, 126.54 tokens per second) 1.03.046.271 I slot print_timing: id 2 | task 142 | eval time = 52.51 ms / 2 tokens ( 52.51 ms per token, 19.05 tokens per second) 1.03.046.272 I slot print_timing: id 2 | task 142 | total time = 1411.80 ms / 174 tokens 1.03.046.272 I slot print_timing: id 2 | task 142 | graphs reused = 1 1.03.046.273 I slot print_timing: id 2 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.046.303 I slot release: id 2 | task 142 | stop processing: n_tokens = 173, truncated = 0 1.03.046.462 I slot print_timing: id 3 | task 143 | prompt eval time = 1359.49 ms / 180 tokens ( 7.55 ms per token, 132.40 tokens per second) 1.03.046.464 I slot print_timing: id 3 | task 143 | eval time = 52.49 ms / 2 tokens ( 52.49 ms per token, 19.05 tokens per second) 1.03.046.464 I slot print_timing: id 3 | task 143 | total time = 1411.98 ms / 182 tokens 1.03.046.468 I slot print_timing: id 3 | task 143 | graphs reused = 1 1.03.046.468 I slot print_timing: id 3 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.046.485 I slot release: id 3 | task 143 | stop processing: n_tokens = 181, truncated = 0 1.03.051.449 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 1.03.051.480 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.954 MiB) 1.03.104.233 I slot launch_slot_: id 0 | task 147 | processing task, is_child = 0 1.03.123.543 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.579 MiB) 1.03.151.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.973 MiB) 1.03.189.078 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.159 1.03.189.198 I slot launch_slot_: id 1 | task 149 | processing task, is_child = 0 1.03.189.243 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 1.03.189.293 I slot launch_slot_: id 2 | task 148 | processing task, is_child = 0 1.03.189.315 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.155 1.03.191.251 I slot launch_slot_: id 3 | task 150 | processing task, is_child = 0 1.04.249.523 I slot print_timing: id 0 | task 147 | prompt eval time = 1005.98 ms / 115 tokens ( 8.75 ms per token, 114.32 tokens per second) 1.04.249.526 I slot print_timing: id 0 | task 147 | eval time = 52.28 ms / 2 tokens ( 52.28 ms per token, 19.13 tokens per second) 1.04.249.527 I slot print_timing: id 0 | task 147 | total time = 1058.26 ms / 117 tokens 1.04.249.528 I slot print_timing: id 0 | task 147 | graphs reused = 1 1.04.249.528 I slot print_timing: id 0 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.249.560 I slot release: id 0 | task 147 | stop processing: n_tokens = 116, truncated = 0 1.04.249.709 I slot print_timing: id 1 | task 149 | prompt eval time = 1006.15 ms / 115 tokens ( 8.75 ms per token, 114.30 tokens per second) 1.04.249.711 I slot print_timing: id 1 | task 149 | eval time = 52.27 ms / 2 tokens ( 52.27 ms per token, 19.13 tokens per second) 1.04.249.712 I slot print_timing: id 1 | task 149 | total time = 1058.42 ms / 117 tokens 1.04.249.712 I slot print_timing: id 1 | task 149 | graphs reused = 1 1.04.249.713 I slot print_timing: id 1 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.249.736 I slot release: id 1 | task 149 | stop processing: n_tokens = 116, truncated = 0 1.04.249.903 I slot print_timing: id 2 | task 148 | prompt eval time = 1006.34 ms / 123 tokens ( 8.18 ms per token, 122.22 tokens per second) 1.04.249.907 I slot print_timing: id 2 | task 148 | eval time = 52.26 ms / 2 tokens ( 52.26 ms per token, 19.13 tokens per second) 1.04.249.908 I slot print_timing: id 2 | task 148 | total time = 1058.60 ms / 125 tokens 1.04.249.908 I slot print_timing: id 2 | task 148 | graphs reused = 1 1.04.249.909 I slot print_timing: id 2 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.249.929 I slot release: id 2 | task 148 | stop processing: n_tokens = 124, truncated = 0 1.04.250.091 I slot print_timing: id 3 | task 150 | prompt eval time = 1006.52 ms / 123 tokens ( 8.18 ms per token, 122.20 tokens per second) 1.04.250.093 I slot print_timing: id 3 | task 150 | eval time = 52.25 ms / 2 tokens ( 52.25 ms per token, 19.14 tokens per second) 1.04.250.093 I slot print_timing: id 3 | task 150 | total time = 1058.77 ms / 125 tokens 1.04.250.093 I slot print_timing: id 3 | task 150 | graphs reused = 1 1.04.250.093 I slot print_timing: id 3 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.250.112 I slot release: id 3 | task 150 | stop processing: n_tokens = 124, truncated = 0 1.04.255.550 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 1.04.273.386 I slot launch_slot_: id 0 | task 154 | processing task, is_child = 0 1.04.273.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.442 MiB) 1.04.295.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.306 MiB) 1.04.314.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.186 MiB) 1.04.355.746 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.241 1.04.355.828 I slot launch_slot_: id 1 | task 155 | processing task, is_child = 0 1.04.355.867 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 1.04.355.907 I slot launch_slot_: id 2 | task 156 | processing task, is_child = 0 1.04.355.927 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.226 1.04.365.580 I slot launch_slot_: id 3 | task 157 | processing task, is_child = 0 1.05.546.565 I slot print_timing: id 0 | task 154 | prompt eval time = 1126.55 ms / 127 tokens ( 8.87 ms per token, 112.73 tokens per second) 1.05.546.568 I slot print_timing: id 0 | task 154 | eval time = 54.42 ms / 2 tokens ( 54.42 ms per token, 18.37 tokens per second) 1.05.546.569 I slot print_timing: id 0 | task 154 | total time = 1180.97 ms / 129 tokens 1.05.546.569 I slot print_timing: id 0 | task 154 | graphs reused = 1 1.05.546.570 I slot print_timing: id 0 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.546.603 I slot release: id 0 | task 154 | stop processing: n_tokens = 128, truncated = 0 1.05.546.776 I slot print_timing: id 1 | task 155 | prompt eval time = 1126.84 ms / 130 tokens ( 8.67 ms per token, 115.37 tokens per second) 1.05.546.778 I slot print_timing: id 1 | task 155 | eval time = 54.33 ms / 2 tokens ( 54.33 ms per token, 18.41 tokens per second) 1.05.546.779 I slot print_timing: id 1 | task 155 | total time = 1181.17 ms / 132 tokens 1.05.546.779 I slot print_timing: id 1 | task 155 | graphs reused = 1 1.05.546.780 I slot print_timing: id 1 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.546.797 I slot release: id 1 | task 155 | stop processing: n_tokens = 131, truncated = 0 1.05.546.975 I slot print_timing: id 2 | task 156 | prompt eval time = 1127.15 ms / 141 tokens ( 7.99 ms per token, 125.09 tokens per second) 1.05.546.977 I slot print_timing: id 2 | task 156 | eval time = 54.21 ms / 2 tokens ( 54.21 ms per token, 18.45 tokens per second) 1.05.546.977 I slot print_timing: id 2 | task 156 | total time = 1181.36 ms / 143 tokens 1.05.546.983 I slot print_timing: id 2 | task 156 | graphs reused = 1 1.05.546.987 I slot print_timing: id 2 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.547.011 I slot release: id 2 | task 156 | stop processing: n_tokens = 142, truncated = 0 1.05.547.197 I slot print_timing: id 3 | task 157 | prompt eval time = 1127.51 ms / 128 tokens ( 8.81 ms per token, 113.52 tokens per second) 1.05.547.200 I slot print_timing: id 3 | task 157 | eval time = 54.06 ms / 2 tokens ( 54.06 ms per token, 18.50 tokens per second) 1.05.547.200 I slot print_timing: id 3 | task 157 | total time = 1181.57 ms / 130 tokens 1.05.547.200 I slot print_timing: id 3 | task 157 | graphs reused = 1 1.05.547.201 I slot print_timing: id 3 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.547.223 I slot release: id 3 | task 157 | stop processing: n_tokens = 129, truncated = 0 1.05.554.081 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.227 1.05.572.352 I slot launch_slot_: id 0 | task 161 | processing task, is_child = 0 1.05.572.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 1.05.597.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 1.05.619.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.208 MiB) 1.05.640.295 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.214 1.05.640.373 I slot launch_slot_: id 1 | task 162 | processing task, is_child = 0 1.05.640.406 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 1.05.640.446 I slot launch_slot_: id 2 | task 163 | processing task, is_child = 0 1.05.640.465 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 1.05.640.496 I slot launch_slot_: id 3 | task 164 | processing task, is_child = 0 1.06.992.120 I slot print_timing: id 0 | task 161 | prompt eval time = 1299.00 ms / 105 tokens ( 12.37 ms per token, 80.83 tokens per second) 1.06.992.122 I slot print_timing: id 0 | task 161 | eval time = 52.61 ms / 2 tokens ( 52.61 ms per token, 19.01 tokens per second) 1.06.992.122 I slot print_timing: id 0 | task 161 | total time = 1351.61 ms / 107 tokens 1.06.992.123 I slot print_timing: id 0 | task 161 | graphs reused = 1 1.06.992.123 I slot print_timing: id 0 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.992.173 I slot release: id 0 | task 161 | stop processing: n_tokens = 106, truncated = 0 1.06.992.322 I slot print_timing: id 1 | task 162 | prompt eval time = 1299.18 ms / 123 tokens ( 10.56 ms per token, 94.67 tokens per second) 1.06.992.327 I slot print_timing: id 1 | task 162 | eval time = 52.62 ms / 2 tokens ( 52.62 ms per token, 19.01 tokens per second) 1.06.992.327 I slot print_timing: id 1 | task 162 | total time = 1351.80 ms / 125 tokens 1.06.992.327 I slot print_timing: id 1 | task 162 | graphs reused = 1 1.06.992.328 I slot print_timing: id 1 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.992.339 I slot release: id 1 | task 162 | stop processing: n_tokens = 124, truncated = 0 1.06.992.512 I slot print_timing: id 2 | task 163 | prompt eval time = 1299.37 ms / 129 tokens ( 10.07 ms per token, 99.28 tokens per second) 1.06.992.514 I slot print_timing: id 2 | task 163 | eval time = 52.61 ms / 2 tokens ( 52.61 ms per token, 19.01 tokens per second) 1.06.992.514 I slot print_timing: id 2 | task 163 | total time = 1351.98 ms / 131 tokens 1.06.992.514 I slot print_timing: id 2 | task 163 | graphs reused = 1 1.06.992.515 I slot print_timing: id 2 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.992.542 I slot release: id 2 | task 163 | stop processing: n_tokens = 130, truncated = 0 1.06.992.712 I slot print_timing: id 3 | task 164 | prompt eval time = 1299.57 ms / 161 tokens ( 8.07 ms per token, 123.89 tokens per second) 1.06.992.714 I slot print_timing: id 3 | task 164 | eval time = 52.60 ms / 2 tokens ( 52.60 ms per token, 19.01 tokens per second) 1.06.992.720 I slot print_timing: id 3 | task 164 | total time = 1352.16 ms / 163 tokens 1.06.992.723 I slot print_timing: id 3 | task 164 | graphs reused = 1 1.06.992.723 I slot print_timing: id 3 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.992.778 I slot release: id 3 | task 164 | stop processing: n_tokens = 162, truncated = 0 1.06.997.550 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.274 1.06.997.576 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.127 MiB) 1.07.014.420 I slot launch_slot_: id 0 | task 168 | processing task, is_child = 0 1.07.014.449 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.993 MiB) 1.07.034.976 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.856 MiB) 1.07.054.796 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.423 MiB) 1.07.105.850 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.226 1.07.105.958 I slot launch_slot_: id 1 | task 169 | processing task, is_child = 0 1.07.106.000 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.215 1.07.106.041 I slot launch_slot_: id 2 | task 170 | processing task, is_child = 0 1.07.106.065 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 1.07.106.117 I slot launch_slot_: id 3 | task 171 | processing task, is_child = 0 1.08.535.547 I slot print_timing: id 0 | task 168 | prompt eval time = 1376.66 ms / 110 tokens ( 12.52 ms per token, 79.90 tokens per second) 1.08.535.549 I slot print_timing: id 0 | task 168 | eval time = 52.72 ms / 2 tokens ( 52.72 ms per token, 18.97 tokens per second) 1.08.535.549 I slot print_timing: id 0 | task 168 | total time = 1429.39 ms / 112 tokens 1.08.535.550 I slot print_timing: id 0 | task 168 | graphs reused = 1 1.08.535.550 I slot print_timing: id 0 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.535.590 I slot release: id 0 | task 168 | stop processing: n_tokens = 111, truncated = 0 1.08.535.745 I slot print_timing: id 1 | task 169 | prompt eval time = 1376.85 ms / 141 tokens ( 9.76 ms per token, 102.41 tokens per second) 1.08.535.747 I slot print_timing: id 1 | task 169 | eval time = 52.73 ms / 2 tokens ( 52.73 ms per token, 18.97 tokens per second) 1.08.535.752 I slot print_timing: id 1 | task 169 | total time = 1429.58 ms / 143 tokens 1.08.535.753 I slot print_timing: id 1 | task 169 | graphs reused = 1 1.08.535.753 I slot print_timing: id 1 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.535.782 I slot release: id 1 | task 169 | stop processing: n_tokens = 142, truncated = 0 1.08.535.949 I slot print_timing: id 2 | task 170 | prompt eval time = 1377.03 ms / 164 tokens ( 8.40 ms per token, 119.10 tokens per second) 1.08.535.951 I slot print_timing: id 2 | task 170 | eval time = 52.74 ms / 2 tokens ( 52.74 ms per token, 18.96 tokens per second) 1.08.535.951 I slot print_timing: id 2 | task 170 | total time = 1429.77 ms / 166 tokens 1.08.535.951 I slot print_timing: id 2 | task 170 | graphs reused = 1 1.08.535.952 I slot print_timing: id 2 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.536.007 I slot release: id 2 | task 170 | stop processing: n_tokens = 165, truncated = 0 1.08.536.192 I slot print_timing: id 3 | task 171 | prompt eval time = 1377.22 ms / 154 tokens ( 8.94 ms per token, 111.82 tokens per second) 1.08.536.194 I slot print_timing: id 3 | task 171 | eval time = 52.77 ms / 2 tokens ( 52.77 ms per token, 18.95 tokens per second) 1.08.536.194 I slot print_timing: id 3 | task 171 | total time = 1429.99 ms / 156 tokens 1.08.536.194 I slot print_timing: id 3 | task 171 | graphs reused = 1 1.08.536.194 I slot print_timing: id 3 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.536.209 I slot release: id 3 | task 171 | stop processing: n_tokens = 155, truncated = 0 1.08.541.274 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.252 1.08.541.323 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 1.08.558.188 I slot launch_slot_: id 0 | task 177 | processing task, is_child = 0 1.08.558.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.442 MiB) 1.08.577.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 1.08.611.246 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.641 MiB) 1.08.640.613 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.197 1.08.640.680 I slot launch_slot_: id 1 | task 175 | processing task, is_child = 0 1.08.640.715 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.170 1.08.659.765 I slot launch_slot_: id 2 | task 176 | processing task, is_child = 0 1.08.659.791 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 1.08.659.826 I slot launch_slot_: id 3 | task 178 | processing task, is_child = 0 1.09.958.643 I slot print_timing: id 0 | task 177 | prompt eval time = 1246.22 ms / 137 tokens ( 9.10 ms per token, 109.93 tokens per second) 1.09.958.645 I slot print_timing: id 0 | task 177 | eval time = 52.58 ms / 2 tokens ( 52.58 ms per token, 19.02 tokens per second) 1.09.958.646 I slot print_timing: id 0 | task 177 | total time = 1298.81 ms / 139 tokens 1.09.958.647 I slot print_timing: id 0 | task 177 | graphs reused = 1 1.09.958.647 I slot print_timing: id 0 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.958.687 I slot release: id 0 | task 177 | stop processing: n_tokens = 138, truncated = 0 1.09.958.841 I slot print_timing: id 1 | task 175 | prompt eval time = 1246.41 ms / 110 tokens ( 11.33 ms per token, 88.25 tokens per second) 1.09.958.845 I slot print_timing: id 1 | task 175 | eval time = 52.58 ms / 2 tokens ( 52.58 ms per token, 19.02 tokens per second) 1.09.958.846 I slot print_timing: id 1 | task 175 | total time = 1299.00 ms / 112 tokens 1.09.958.846 I slot print_timing: id 1 | task 175 | graphs reused = 1 1.09.958.847 I slot print_timing: id 1 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.958.865 I slot release: id 1 | task 175 | stop processing: n_tokens = 111, truncated = 0 1.09.959.025 I slot print_timing: id 2 | task 176 | prompt eval time = 1246.61 ms / 110 tokens ( 11.33 ms per token, 88.24 tokens per second) 1.09.959.030 I slot print_timing: id 2 | task 176 | eval time = 52.56 ms / 2 tokens ( 52.56 ms per token, 19.03 tokens per second) 1.09.959.030 I slot print_timing: id 2 | task 176 | total time = 1299.17 ms / 112 tokens 1.09.959.031 I slot print_timing: id 2 | task 176 | graphs reused = 1 1.09.959.031 I slot print_timing: id 2 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.959.039 I slot release: id 2 | task 176 | stop processing: n_tokens = 111, truncated = 0 1.09.959.221 I slot print_timing: id 3 | task 178 | prompt eval time = 1246.79 ms / 148 tokens ( 8.42 ms per token, 118.70 tokens per second) 1.09.959.222 I slot print_timing: id 3 | task 178 | eval time = 52.56 ms / 2 tokens ( 52.56 ms per token, 19.03 tokens per second) 1.09.959.223 I slot print_timing: id 3 | task 178 | total time = 1299.35 ms / 150 tokens 1.09.959.223 I slot print_timing: id 3 | task 178 | graphs reused = 1 1.09.959.223 I slot print_timing: id 3 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.959.238 I slot release: id 3 | task 178 | stop processing: n_tokens = 149, truncated = 0 1.09.964.741 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.203 1.09.977.003 I slot launch_slot_: id 0 | task 182 | processing task, is_child = 0 1.09.977.026 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.169 MiB) 1.09.991.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.306 MiB) 1.10.009.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.892 MiB) 1.10.031.023 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.261 1.10.031.099 I slot launch_slot_: id 2 | task 184 | processing task, is_child = 0 1.10.031.135 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.252 1.10.031.169 I slot launch_slot_: id 1 | task 183 | processing task, is_child = 0 1.10.031.192 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.188 1.10.031.226 I slot launch_slot_: id 3 | task 185 | processing task, is_child = 0 1.11.397.433 I slot print_timing: id 0 | task 182 | prompt eval time = 1313.49 ms / 123 tokens ( 10.68 ms per token, 93.64 tokens per second) 1.11.397.443 I slot print_timing: id 0 | task 182 | eval time = 52.70 ms / 2 tokens ( 52.70 ms per token, 18.97 tokens per second) 1.11.397.445 I slot print_timing: id 0 | task 182 | total time = 1366.19 ms / 125 tokens 1.11.397.446 I slot print_timing: id 0 | task 182 | graphs reused = 1 1.11.397.446 I slot print_timing: id 0 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.397.474 I slot release: id 0 | task 182 | stop processing: n_tokens = 124, truncated = 0 1.11.397.626 I slot print_timing: id 1 | task 183 | prompt eval time = 1313.69 ms / 152 tokens ( 8.64 ms per token, 115.70 tokens per second) 1.11.397.631 I slot print_timing: id 1 | task 183 | eval time = 52.69 ms / 2 tokens ( 52.69 ms per token, 18.98 tokens per second) 1.11.397.632 I slot print_timing: id 1 | task 183 | total time = 1366.38 ms / 154 tokens 1.11.397.632 I slot print_timing: id 1 | task 183 | graphs reused = 1 1.11.397.632 I slot print_timing: id 1 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.397.644 I slot release: id 1 | task 183 | stop processing: n_tokens = 153, truncated = 0 1.11.397.823 I slot print_timing: id 2 | task 184 | prompt eval time = 1313.89 ms / 112 tokens ( 11.73 ms per token, 85.24 tokens per second) 1.11.397.825 I slot print_timing: id 2 | task 184 | eval time = 52.67 ms / 2 tokens ( 52.67 ms per token, 18.99 tokens per second) 1.11.397.825 I slot print_timing: id 2 | task 184 | total time = 1366.56 ms / 114 tokens 1.11.397.825 I slot print_timing: id 2 | task 184 | graphs reused = 1 1.11.397.826 I slot print_timing: id 2 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.397.858 I slot release: id 2 | task 184 | stop processing: n_tokens = 113, truncated = 0 1.11.398.027 I slot print_timing: id 3 | task 185 | prompt eval time = 1314.09 ms / 130 tokens ( 10.11 ms per token, 98.93 tokens per second) 1.11.398.029 I slot print_timing: id 3 | task 185 | eval time = 52.67 ms / 2 tokens ( 52.67 ms per token, 18.99 tokens per second) 1.11.398.029 I slot print_timing: id 3 | task 185 | total time = 1366.75 ms / 132 tokens 1.11.398.030 I slot print_timing: id 3 | task 185 | graphs reused = 1 1.11.398.030 I slot print_timing: id 3 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.398.071 I slot release: id 3 | task 185 | stop processing: n_tokens = 131, truncated = 0 1.11.403.183 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.257 1.11.403.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.227 MiB) 1.11.425.801 I slot launch_slot_: id 2 | task 189 | processing task, is_child = 0 1.11.425.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.205 MiB) 1.11.445.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.107 MiB) 1.11.465.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 1.11.484.342 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.221 1.11.484.421 I slot launch_slot_: id 3 | task 190 | processing task, is_child = 0 1.11.484.463 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.226 1.11.484.502 I slot launch_slot_: id 0 | task 191 | processing task, is_child = 0 1.11.484.523 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.183 1.11.484.556 I slot launch_slot_: id 1 | task 192 | processing task, is_child = 0 1.12.831.358 I slot print_timing: id 0 | task 191 | prompt eval time = 1294.42 ms / 157 tokens ( 8.24 ms per token, 121.29 tokens per second) 1.12.831.361 I slot print_timing: id 0 | task 191 | eval time = 52.36 ms / 2 tokens ( 52.36 ms per token, 19.10 tokens per second) 1.12.831.362 I slot print_timing: id 0 | task 191 | total time = 1346.78 ms / 159 tokens 1.12.831.362 I slot print_timing: id 0 | task 191 | graphs reused = 1 1.12.831.363 I slot print_timing: id 0 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.831.422 I slot release: id 0 | task 191 | stop processing: n_tokens = 158, truncated = 0 1.12.831.581 I slot print_timing: id 1 | task 192 | prompt eval time = 1294.57 ms / 166 tokens ( 7.80 ms per token, 128.23 tokens per second) 1.12.831.583 I slot print_timing: id 1 | task 192 | eval time = 52.43 ms / 2 tokens ( 52.43 ms per token, 19.07 tokens per second) 1.12.831.583 I slot print_timing: id 1 | task 192 | total time = 1347.00 ms / 168 tokens 1.12.831.583 I slot print_timing: id 1 | task 192 | graphs reused = 1 1.12.831.584 I slot print_timing: id 1 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.831.622 I slot release: id 1 | task 192 | stop processing: n_tokens = 167, truncated = 0 1.12.831.795 I slot print_timing: id 2 | task 189 | prompt eval time = 1294.71 ms / 114 tokens ( 11.36 ms per token, 88.05 tokens per second) 1.12.831.796 I slot print_timing: id 2 | task 189 | eval time = 52.48 ms / 2 tokens ( 52.48 ms per token, 19.05 tokens per second) 1.12.831.796 I slot print_timing: id 2 | task 189 | total time = 1347.20 ms / 116 tokens 1.12.831.797 I slot print_timing: id 2 | task 189 | graphs reused = 1 1.12.831.797 I slot print_timing: id 2 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.831.821 I slot release: id 2 | task 189 | stop processing: n_tokens = 115, truncated = 0 1.12.831.997 I slot print_timing: id 3 | task 190 | prompt eval time = 1294.87 ms / 128 tokens ( 10.12 ms per token, 98.85 tokens per second) 1.12.831.999 I slot print_timing: id 3 | task 190 | eval time = 52.52 ms / 2 tokens ( 52.52 ms per token, 19.04 tokens per second) 1.12.832.000 I slot print_timing: id 3 | task 190 | total time = 1347.39 ms / 130 tokens 1.12.832.000 I slot print_timing: id 3 | task 190 | graphs reused = 1 1.12.832.000 I slot print_timing: id 3 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.832.020 I slot release: id 3 | task 190 | stop processing: n_tokens = 129, truncated = 0 1.12.836.762 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.177 1.12.836.797 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.951 MiB) 1.12.874.422 I slot launch_slot_: id 0 | task 197 | processing task, is_child = 0 1.12.897.105 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.384 MiB) 1.12.913.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.560 MiB) 1.12.937.349 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.168 1.12.937.437 I slot launch_slot_: id 1 | task 196 | processing task, is_child = 0 1.12.937.472 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.243 1.12.937.509 I slot launch_slot_: id 2 | task 198 | processing task, is_child = 0 1.12.937.529 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.217 1.12.937.563 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 1.14.462.404 I slot print_timing: id 0 | task 197 | prompt eval time = 1472.13 ms / 141 tokens ( 10.44 ms per token, 95.78 tokens per second) 1.14.462.407 I slot print_timing: id 0 | task 197 | eval time = 52.69 ms / 2 tokens ( 52.69 ms per token, 18.98 tokens per second) 1.14.462.407 I slot print_timing: id 0 | task 197 | total time = 1524.82 ms / 143 tokens 1.14.462.407 I slot print_timing: id 0 | task 197 | graphs reused = 1 1.14.462.408 I slot print_timing: id 0 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.462.486 I slot release: id 0 | task 197 | stop processing: n_tokens = 142, truncated = 0 1.14.462.642 I slot print_timing: id 1 | task 196 | prompt eval time = 1472.31 ms / 108 tokens ( 13.63 ms per token, 73.35 tokens per second) 1.14.462.645 I slot print_timing: id 1 | task 196 | eval time = 52.74 ms / 2 tokens ( 52.74 ms per token, 18.96 tokens per second) 1.14.462.645 I slot print_timing: id 1 | task 196 | total time = 1525.05 ms / 110 tokens 1.14.462.646 I slot print_timing: id 1 | task 196 | graphs reused = 1 1.14.462.646 I slot print_timing: id 1 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.462.659 I slot release: id 1 | task 196 | stop processing: n_tokens = 109, truncated = 0 1.14.462.831 I slot print_timing: id 2 | task 198 | prompt eval time = 1472.49 ms / 153 tokens ( 9.62 ms per token, 103.91 tokens per second) 1.14.462.832 I slot print_timing: id 2 | task 198 | eval time = 52.73 ms / 2 tokens ( 52.73 ms per token, 18.97 tokens per second) 1.14.462.832 I slot print_timing: id 2 | task 198 | total time = 1525.22 ms / 155 tokens 1.14.462.833 I slot print_timing: id 2 | task 198 | graphs reused = 1 1.14.462.833 I slot print_timing: id 2 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.462.848 I slot release: id 2 | task 198 | stop processing: n_tokens = 154, truncated = 0 1.14.463.025 I slot print_timing: id 3 | task 199 | prompt eval time = 1472.68 ms / 179 tokens ( 8.23 ms per token, 121.55 tokens per second) 1.14.463.027 I slot print_timing: id 3 | task 199 | eval time = 52.72 ms / 2 tokens ( 52.72 ms per token, 18.97 tokens per second) 1.14.463.027 I slot print_timing: id 3 | task 199 | total time = 1525.39 ms / 181 tokens 1.14.463.028 I slot print_timing: id 3 | task 199 | graphs reused = 1 1.14.463.028 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.463.091 I slot release: id 3 | task 199 | stop processing: n_tokens = 180, truncated = 0 1.14.469.210 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.197 1.14.469.290 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.834 MiB) 1.14.506.456 I slot launch_slot_: id 0 | task 204 | processing task, is_child = 0 1.14.533.850 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.149 MiB) 1.14.563.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.794 MiB) 1.14.617.213 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.257 1.14.617.333 I slot launch_slot_: id 1 | task 203 | processing task, is_child = 0 1.14.617.367 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.182 1.14.617.402 I slot launch_slot_: id 2 | task 206 | processing task, is_child = 0 1.14.617.419 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.156 1.14.617.452 I slot launch_slot_: id 3 | task 205 | processing task, is_child = 0 1.15.944.424 I slot print_timing: id 0 | task 204 | prompt eval time = 1273.32 ms / 116 tokens ( 10.98 ms per token, 91.10 tokens per second) 1.15.944.427 I slot print_timing: id 0 | task 204 | eval time = 53.65 ms / 2 tokens ( 53.65 ms per token, 18.64 tokens per second) 1.15.944.428 I slot print_timing: id 0 | task 204 | total time = 1326.96 ms / 118 tokens 1.15.944.428 I slot print_timing: id 0 | task 204 | graphs reused = 1 1.15.944.429 I slot print_timing: id 0 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.944.473 I slot release: id 0 | task 204 | stop processing: n_tokens = 117, truncated = 0 1.15.944.624 I slot print_timing: id 1 | task 203 | prompt eval time = 1273.62 ms / 134 tokens ( 9.50 ms per token, 105.21 tokens per second) 1.15.944.628 I slot print_timing: id 1 | task 203 | eval time = 53.53 ms / 2 tokens ( 53.53 ms per token, 18.68 tokens per second) 1.15.944.628 I slot print_timing: id 1 | task 203 | total time = 1327.15 ms / 136 tokens 1.15.944.629 I slot print_timing: id 1 | task 203 | graphs reused = 1 1.15.944.629 I slot print_timing: id 1 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.944.662 I slot release: id 1 | task 203 | stop processing: n_tokens = 135, truncated = 0 1.15.944.910 I slot print_timing: id 2 | task 206 | prompt eval time = 1274.38 ms / 135 tokens ( 9.44 ms per token, 105.93 tokens per second) 1.15.944.912 I slot print_timing: id 2 | task 206 | eval time = 53.05 ms / 2 tokens ( 53.05 ms per token, 18.85 tokens per second) 1.15.944.913 I slot print_timing: id 2 | task 206 | total time = 1327.43 ms / 137 tokens 1.15.944.913 I slot print_timing: id 2 | task 206 | graphs reused = 1 1.15.944.913 I slot print_timing: id 2 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.944.951 I slot release: id 2 | task 206 | stop processing: n_tokens = 136, truncated = 0 1.15.945.123 I slot print_timing: id 3 | task 205 | prompt eval time = 1275.02 ms / 158 tokens ( 8.07 ms per token, 123.92 tokens per second) 1.15.945.126 I slot print_timing: id 3 | task 205 | eval time = 52.60 ms / 2 tokens ( 52.60 ms per token, 19.01 tokens per second) 1.15.945.126 I slot print_timing: id 3 | task 205 | total time = 1327.63 ms / 160 tokens 1.15.945.126 I slot print_timing: id 3 | task 205 | graphs reused = 1 1.15.945.127 I slot print_timing: id 3 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.945.162 I slot release: id 3 | task 205 | stop processing: n_tokens = 159, truncated = 0 1.15.950.228 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.248 1.15.950.258 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.912 MiB) 1.15.980.469 I slot launch_slot_: id 0 | task 210 | processing task, is_child = 0 1.15.980.493 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.853 MiB) 1.16.003.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 1.16.026.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.993 MiB) 1.16.050.049 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.207 1.16.060.123 I slot launch_slot_: id 1 | task 211 | processing task, is_child = 0 1.16.060.172 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.206 1.16.060.206 I slot launch_slot_: id 2 | task 212 | processing task, is_child = 0 1.16.060.223 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.176 1.16.060.268 I slot launch_slot_: id 3 | task 213 | processing task, is_child = 0 1.17.401.822 I slot print_timing: id 0 | task 210 | prompt eval time = 1288.74 ms / 117 tokens ( 11.01 ms per token, 90.79 tokens per second) 1.17.401.825 I slot print_timing: id 0 | task 210 | eval time = 52.80 ms / 2 tokens ( 52.80 ms per token, 18.94 tokens per second) 1.17.401.826 I slot print_timing: id 0 | task 210 | total time = 1341.54 ms / 119 tokens 1.17.401.826 I slot print_timing: id 0 | task 210 | graphs reused = 1 1.17.401.827 I slot print_timing: id 0 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.401.852 I slot release: id 0 | task 210 | stop processing: n_tokens = 118, truncated = 0 1.17.402.009 I slot print_timing: id 1 | task 211 | prompt eval time = 1289.02 ms / 122 tokens ( 10.57 ms per token, 94.65 tokens per second) 1.17.402.013 I slot print_timing: id 1 | task 211 | eval time = 52.70 ms / 2 tokens ( 52.70 ms per token, 18.98 tokens per second) 1.17.402.014 I slot print_timing: id 1 | task 211 | total time = 1341.72 ms / 124 tokens 1.17.402.014 I slot print_timing: id 1 | task 211 | graphs reused = 1 1.17.402.014 I slot print_timing: id 1 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.402.026 I slot release: id 1 | task 211 | stop processing: n_tokens = 123, truncated = 0 1.17.402.197 I slot print_timing: id 2 | task 212 | prompt eval time = 1289.21 ms / 149 tokens ( 8.65 ms per token, 115.57 tokens per second) 1.17.402.202 I slot print_timing: id 2 | task 212 | eval time = 52.68 ms / 2 tokens ( 52.68 ms per token, 18.98 tokens per second) 1.17.402.202 I slot print_timing: id 2 | task 212 | total time = 1341.89 ms / 151 tokens 1.17.402.202 I slot print_timing: id 2 | task 212 | graphs reused = 1 1.17.402.203 I slot print_timing: id 2 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.402.232 I slot release: id 2 | task 212 | stop processing: n_tokens = 150, truncated = 0 1.17.402.411 I slot print_timing: id 3 | task 213 | prompt eval time = 1289.57 ms / 157 tokens ( 8.21 ms per token, 121.75 tokens per second) 1.17.402.412 I slot print_timing: id 3 | task 213 | eval time = 52.52 ms / 2 tokens ( 52.52 ms per token, 19.04 tokens per second) 1.17.402.413 I slot print_timing: id 3 | task 213 | total time = 1342.09 ms / 159 tokens 1.17.402.413 I slot print_timing: id 3 | task 213 | graphs reused = 1 1.17.402.413 I slot print_timing: id 3 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.402.478 I slot release: id 3 | task 213 | stop processing: n_tokens = 158, truncated = 0 1.17.407.338 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.237 1.17.421.486 I slot launch_slot_: id 0 | task 217 | processing task, is_child = 0 1.17.421.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.521 MiB) 1.17.438.373 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.208 MiB) 1.17.462.023 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.208 MiB) 1.17.484.479 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.228 1.17.484.576 I slot launch_slot_: id 1 | task 218 | processing task, is_child = 0 1.17.484.644 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.187 1.17.484.699 I slot launch_slot_: id 2 | task 219 | processing task, is_child = 0 1.17.484.728 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.177 1.17.484.770 I slot launch_slot_: id 3 | task 220 | processing task, is_child = 0 1.18.979.201 I slot print_timing: id 0 | task 217 | prompt eval time = 1441.36 ms / 149 tokens ( 9.67 ms per token, 103.37 tokens per second) 1.18.979.206 I slot print_timing: id 0 | task 217 | eval time = 53.05 ms / 2 tokens ( 53.05 ms per token, 18.85 tokens per second) 1.18.979.207 I slot print_timing: id 0 | task 217 | total time = 1494.42 ms / 151 tokens 1.18.979.207 I slot print_timing: id 0 | task 217 | graphs reused = 1 1.18.979.208 I slot print_timing: id 0 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.979.236 I slot release: id 0 | task 217 | stop processing: n_tokens = 150, truncated = 0 1.18.979.399 I slot print_timing: id 1 | task 218 | prompt eval time = 1441.56 ms / 155 tokens ( 9.30 ms per token, 107.52 tokens per second) 1.18.979.401 I slot print_timing: id 1 | task 218 | eval time = 53.04 ms / 2 tokens ( 53.04 ms per token, 18.85 tokens per second) 1.18.979.401 I slot print_timing: id 1 | task 218 | total time = 1494.60 ms / 157 tokens 1.18.979.402 I slot print_timing: id 1 | task 218 | graphs reused = 1 1.18.979.402 I slot print_timing: id 1 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.979.446 I slot release: id 1 | task 218 | stop processing: n_tokens = 156, truncated = 0 1.18.979.604 I slot print_timing: id 2 | task 219 | prompt eval time = 1441.74 ms / 160 tokens ( 9.01 ms per token, 110.98 tokens per second) 1.18.979.606 I slot print_timing: id 2 | task 219 | eval time = 53.05 ms / 2 tokens ( 53.05 ms per token, 18.85 tokens per second) 1.18.979.606 I slot print_timing: id 2 | task 219 | total time = 1494.79 ms / 162 tokens 1.18.979.606 I slot print_timing: id 2 | task 219 | graphs reused = 1 1.18.979.615 I slot print_timing: id 2 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.979.637 I slot release: id 2 | task 219 | stop processing: n_tokens = 161, truncated = 0 1.18.979.810 I slot print_timing: id 3 | task 220 | prompt eval time = 1442.15 ms / 154 tokens ( 9.36 ms per token, 106.78 tokens per second) 1.18.979.811 I slot print_timing: id 3 | task 220 | eval time = 52.81 ms / 2 tokens ( 52.81 ms per token, 18.93 tokens per second) 1.18.979.812 I slot print_timing: id 3 | task 220 | total time = 1494.97 ms / 156 tokens 1.18.979.812 I slot print_timing: id 3 | task 220 | graphs reused = 1 1.18.979.812 I slot print_timing: id 3 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.979.848 I slot release: id 3 | task 220 | stop processing: n_tokens = 155, truncated = 0 1.18.984.918 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.187 1.18.984.943 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.071 MiB) 1.19.008.475 I slot launch_slot_: id 0 | task 224 | processing task, is_child = 0 1.19.008.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 1.19.025.430 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 1.19.042.388 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.012 MiB) 1.19.060.068 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.179 1.19.071.823 I slot launch_slot_: id 1 | task 225 | processing task, is_child = 0 1.19.071.867 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.174 1.19.071.902 I slot launch_slot_: id 2 | task 226 | processing task, is_child = 0 1.19.071.920 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.181 1.19.071.952 I slot launch_slot_: id 3 | task 227 | processing task, is_child = 0 1.20.401.963 I slot print_timing: id 0 | task 224 | prompt eval time = 1277.57 ms / 107 tokens ( 11.94 ms per token, 83.75 tokens per second) 1.20.401.965 I slot print_timing: id 0 | task 224 | eval time = 52.43 ms / 2 tokens ( 52.43 ms per token, 19.07 tokens per second) 1.20.401.966 I slot print_timing: id 0 | task 224 | total time = 1330.00 ms / 109 tokens 1.20.401.966 I slot print_timing: id 0 | task 224 | graphs reused = 1 1.20.401.967 I slot print_timing: id 0 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.401.995 I slot release: id 0 | task 224 | stop processing: n_tokens = 108, truncated = 0 1.20.402.154 I slot print_timing: id 1 | task 225 | prompt eval time = 1277.72 ms / 102 tokens ( 12.53 ms per token, 79.83 tokens per second) 1.20.402.156 I slot print_timing: id 1 | task 225 | eval time = 52.46 ms / 2 tokens ( 52.46 ms per token, 19.06 tokens per second) 1.20.402.157 I slot print_timing: id 1 | task 225 | total time = 1330.18 ms / 104 tokens 1.20.402.157 I slot print_timing: id 1 | task 225 | graphs reused = 1 1.20.402.157 I slot print_timing: id 1 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.402.207 I slot release: id 1 | task 225 | stop processing: n_tokens = 103, truncated = 0 1.20.402.380 I slot print_timing: id 2 | task 226 | prompt eval time = 1277.87 ms / 114 tokens ( 11.21 ms per token, 89.21 tokens per second) 1.20.402.381 I slot print_timing: id 2 | task 226 | eval time = 52.52 ms / 2 tokens ( 52.52 ms per token, 19.04 tokens per second) 1.20.402.382 I slot print_timing: id 2 | task 226 | total time = 1330.39 ms / 116 tokens 1.20.402.382 I slot print_timing: id 2 | task 226 | graphs reused = 1 1.20.402.382 I slot print_timing: id 2 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.402.414 I slot release: id 2 | task 226 | stop processing: n_tokens = 115, truncated = 0 1.20.402.590 I slot print_timing: id 3 | task 227 | prompt eval time = 1278.03 ms / 185 tokens ( 6.91 ms per token, 144.75 tokens per second) 1.20.402.591 I slot print_timing: id 3 | task 227 | eval time = 52.56 ms / 2 tokens ( 52.56 ms per token, 19.03 tokens per second) 1.20.402.592 I slot print_timing: id 3 | task 227 | total time = 1330.59 ms / 187 tokens 1.20.402.592 I slot print_timing: id 3 | task 227 | graphs reused = 1 1.20.402.592 I slot print_timing: id 3 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.402.604 I slot release: id 3 | task 227 | stop processing: n_tokens = 186, truncated = 0 1.20.407.731 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.259 1.20.422.252 I slot launch_slot_: id 0 | task 231 | processing task, is_child = 0 1.20.422.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.010 MiB) 1.20.436.177 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.954 MiB) 1.20.460.480 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.107 MiB) 1.20.479.605 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.282 1.20.479.685 I slot launch_slot_: id 1 | task 232 | processing task, is_child = 0 1.20.479.724 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.243 1.20.479.763 I slot launch_slot_: id 2 | task 233 | processing task, is_child = 0 1.20.479.785 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 1.20.479.833 I slot launch_slot_: id 3 | task 234 | processing task, is_child = 0 1.21.833.139 I slot print_timing: id 0 | task 231 | prompt eval time = 1300.57 ms / 122 tokens ( 10.66 ms per token, 93.81 tokens per second) 1.21.833.141 I slot print_timing: id 0 | task 231 | eval time = 52.73 ms / 2 tokens ( 52.73 ms per token, 18.96 tokens per second) 1.21.833.142 I slot print_timing: id 0 | task 231 | total time = 1353.30 ms / 124 tokens 1.21.833.143 I slot print_timing: id 0 | task 231 | graphs reused = 1 1.21.833.143 I slot print_timing: id 0 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.833.170 I slot release: id 0 | task 231 | stop processing: n_tokens = 123, truncated = 0 1.21.833.328 I slot print_timing: id 1 | task 232 | prompt eval time = 1300.74 ms / 110 tokens ( 11.82 ms per token, 84.57 tokens per second) 1.21.833.330 I slot print_timing: id 1 | task 232 | eval time = 52.73 ms / 2 tokens ( 52.73 ms per token, 18.96 tokens per second) 1.21.833.330 I slot print_timing: id 1 | task 232 | total time = 1353.47 ms / 112 tokens 1.21.833.336 I slot print_timing: id 1 | task 232 | graphs reused = 1 1.21.833.338 I slot print_timing: id 1 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.833.361 I slot release: id 1 | task 232 | stop processing: n_tokens = 111, truncated = 0 1.21.833.527 I slot print_timing: id 2 | task 233 | prompt eval time = 1300.95 ms / 126 tokens ( 10.32 ms per token, 96.85 tokens per second) 1.21.833.534 I slot print_timing: id 2 | task 233 | eval time = 52.71 ms / 2 tokens ( 52.71 ms per token, 18.97 tokens per second) 1.21.833.534 I slot print_timing: id 2 | task 233 | total time = 1353.66 ms / 128 tokens 1.21.833.534 I slot print_timing: id 2 | task 233 | graphs reused = 1 1.21.833.535 I slot print_timing: id 2 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.833.562 I slot release: id 2 | task 233 | stop processing: n_tokens = 127, truncated = 0 1.21.833.722 I slot print_timing: id 3 | task 234 | prompt eval time = 1301.20 ms / 164 tokens ( 7.93 ms per token, 126.04 tokens per second) 1.21.833.725 I slot print_timing: id 3 | task 234 | eval time = 52.64 ms / 2 tokens ( 52.64 ms per token, 19.00 tokens per second) 1.21.833.725 I slot print_timing: id 3 | task 234 | total time = 1353.84 ms / 166 tokens 1.21.833.725 I slot print_timing: id 3 | task 234 | graphs reused = 1 1.21.833.726 I slot print_timing: id 3 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.833.737 I slot release: id 3 | task 234 | stop processing: n_tokens = 165, truncated = 0 1.21.838.758 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 1.21.838.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.306 MiB) 1.21.852.179 I slot launch_slot_: id 0 | task 238 | processing task, is_child = 0 1.21.852.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.339 MiB) 1.21.874.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.775 MiB) 1.21.897.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.677 MiB) 1.21.919.721 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.252 1.21.919.799 I slot launch_slot_: id 1 | task 239 | processing task, is_child = 0 1.21.919.844 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.220 1.21.930.468 I slot launch_slot_: id 2 | task 240 | processing task, is_child = 0 1.21.930.495 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.170 1.21.932.098 I slot launch_slot_: id 3 | task 241 | processing task, is_child = 0 1.23.157.192 I slot print_timing: id 0 | task 238 | prompt eval time = 1172.13 ms / 125 tokens ( 9.38 ms per token, 106.64 tokens per second) 1.23.157.194 I slot print_timing: id 0 | task 238 | eval time = 52.95 ms / 2 tokens ( 52.95 ms per token, 18.89 tokens per second) 1.23.157.195 I slot print_timing: id 0 | task 238 | total time = 1225.08 ms / 127 tokens 1.23.157.195 I slot print_timing: id 0 | task 238 | graphs reused = 1 1.23.157.196 I slot print_timing: id 0 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.157.219 I slot release: id 0 | task 238 | stop processing: n_tokens = 126, truncated = 0 1.23.157.375 I slot print_timing: id 1 | task 239 | prompt eval time = 1172.33 ms / 122 tokens ( 9.61 ms per token, 104.07 tokens per second) 1.23.157.377 I slot print_timing: id 1 | task 239 | eval time = 52.93 ms / 2 tokens ( 52.93 ms per token, 18.89 tokens per second) 1.23.157.377 I slot print_timing: id 1 | task 239 | total time = 1225.26 ms / 124 tokens 1.23.157.378 I slot print_timing: id 1 | task 239 | graphs reused = 1 1.23.157.378 I slot print_timing: id 1 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.157.389 I slot release: id 1 | task 239 | stop processing: n_tokens = 123, truncated = 0 1.23.157.561 I slot print_timing: id 2 | task 240 | prompt eval time = 1172.54 ms / 137 tokens ( 8.56 ms per token, 116.84 tokens per second) 1.23.157.563 I slot print_timing: id 2 | task 240 | eval time = 52.89 ms / 2 tokens ( 52.89 ms per token, 18.91 tokens per second) 1.23.157.564 I slot print_timing: id 2 | task 240 | total time = 1225.43 ms / 139 tokens 1.23.157.564 I slot print_timing: id 2 | task 240 | graphs reused = 1 1.23.157.564 I slot print_timing: id 2 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.157.601 I slot release: id 2 | task 240 | stop processing: n_tokens = 138, truncated = 0 1.23.157.777 I slot print_timing: id 3 | task 241 | prompt eval time = 1172.74 ms / 138 tokens ( 8.50 ms per token, 117.67 tokens per second) 1.23.157.779 I slot print_timing: id 3 | task 241 | eval time = 52.90 ms / 2 tokens ( 52.90 ms per token, 18.90 tokens per second) 1.23.157.779 I slot print_timing: id 3 | task 241 | total time = 1225.64 ms / 140 tokens 1.23.157.779 I slot print_timing: id 3 | task 241 | graphs reused = 1 1.23.157.779 I slot print_timing: id 3 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.157.801 I slot release: id 3 | task 241 | stop processing: n_tokens = 139, truncated = 0 1.23.162.656 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.222 1.23.176.807 I slot launch_slot_: id 0 | task 245 | processing task, is_child = 0 1.23.195.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.065 MiB) 1.23.219.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.423 MiB) 1.23.235.317 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.228 1.23.236.812 I slot launch_slot_: id 1 | task 246 | processing task, is_child = 0 1.23.236.851 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.203 1.23.236.891 I slot launch_slot_: id 2 | task 247 | processing task, is_child = 0 1.23.236.913 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.201 1.23.236.949 I slot launch_slot_: id 3 | task 248 | processing task, is_child = 0 1.24.727.699 I slot print_timing: id 0 | task 245 | prompt eval time = 1437.88 ms / 120 tokens ( 11.98 ms per token, 83.46 tokens per second) 1.24.727.701 I slot print_timing: id 0 | task 245 | eval time = 52.86 ms / 2 tokens ( 52.86 ms per token, 18.92 tokens per second) 1.24.727.702 I slot print_timing: id 0 | task 245 | total time = 1490.74 ms / 122 tokens 1.24.727.702 I slot print_timing: id 0 | task 245 | graphs reused = 1 1.24.727.702 I slot print_timing: id 0 | task 245 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.727.720 I slot release: id 0 | task 245 | stop processing: n_tokens = 121, truncated = 0 1.24.727.883 I slot print_timing: id 1 | task 246 | prompt eval time = 1438.08 ms / 158 tokens ( 9.10 ms per token, 109.87 tokens per second) 1.24.727.888 I slot print_timing: id 1 | task 246 | eval time = 52.83 ms / 2 tokens ( 52.83 ms per token, 18.93 tokens per second) 1.24.727.889 I slot print_timing: id 1 | task 246 | total time = 1490.92 ms / 160 tokens 1.24.727.890 I slot print_timing: id 1 | task 246 | graphs reused = 1 1.24.727.890 I slot print_timing: id 1 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.727.912 I slot release: id 1 | task 246 | stop processing: n_tokens = 159, truncated = 0 1.24.728.076 I slot print_timing: id 2 | task 247 | prompt eval time = 1438.28 ms / 140 tokens ( 10.27 ms per token, 97.34 tokens per second) 1.24.728.078 I slot print_timing: id 2 | task 247 | eval time = 52.82 ms / 2 tokens ( 52.82 ms per token, 18.93 tokens per second) 1.24.728.079 I slot print_timing: id 2 | task 247 | total time = 1491.10 ms / 142 tokens 1.24.728.079 I slot print_timing: id 2 | task 247 | graphs reused = 1 1.24.728.079 I slot print_timing: id 2 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.728.098 I slot release: id 2 | task 247 | stop processing: n_tokens = 141, truncated = 0 1.24.728.281 I slot print_timing: id 3 | task 248 | prompt eval time = 1438.48 ms / 168 tokens ( 8.56 ms per token, 116.79 tokens per second) 1.24.728.284 I slot print_timing: id 3 | task 248 | eval time = 52.81 ms / 2 tokens ( 52.81 ms per token, 18.93 tokens per second) 1.24.728.284 I slot print_timing: id 3 | task 248 | total time = 1491.29 ms / 170 tokens 1.24.728.284 I slot print_timing: id 3 | task 248 | graphs reused = 1 1.24.728.285 I slot print_timing: id 3 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.728.324 I slot release: id 3 | task 248 | stop processing: n_tokens = 169, truncated = 0 1.24.733.299 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.231 1.24.737.292 I slot launch_slot_: id 0 | task 252 | processing task, is_child = 0 1.24.737.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 1.24.758.168 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.401 MiB) 1.24.771.528 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.286 MiB) 1.24.794.448 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.176 1.24.803.383 I slot launch_slot_: id 1 | task 253 | processing task, is_child = 0 1.24.803.426 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.199 1.24.803.460 I slot launch_slot_: id 2 | task 254 | processing task, is_child = 0 1.24.803.478 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.166 1.24.803.514 I slot launch_slot_: id 3 | task 255 | processing task, is_child = 0 1.26.347.353 I slot print_timing: id 0 | task 252 | prompt eval time = 1491.57 ms / 103 tokens ( 14.48 ms per token, 69.05 tokens per second) 1.26.347.355 I slot print_timing: id 0 | task 252 | eval time = 52.25 ms / 2 tokens ( 52.25 ms per token, 19.14 tokens per second) 1.26.347.356 I slot print_timing: id 0 | task 252 | total time = 1543.82 ms / 105 tokens 1.26.347.356 I slot print_timing: id 0 | task 252 | graphs reused = 1 1.26.347.357 I slot print_timing: id 0 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.347.380 I slot release: id 0 | task 252 | stop processing: n_tokens = 104, truncated = 0 1.26.347.537 I slot print_timing: id 1 | task 253 | prompt eval time = 1491.74 ms / 133 tokens ( 11.22 ms per token, 89.16 tokens per second) 1.26.347.539 I slot print_timing: id 1 | task 253 | eval time = 52.26 ms / 2 tokens ( 52.26 ms per token, 19.13 tokens per second) 1.26.347.540 I slot print_timing: id 1 | task 253 | total time = 1544.00 ms / 135 tokens 1.26.347.540 I slot print_timing: id 1 | task 253 | graphs reused = 1 1.26.347.540 I slot print_timing: id 1 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.347.552 I slot release: id 1 | task 253 | stop processing: n_tokens = 134, truncated = 0 1.26.347.744 I slot print_timing: id 2 | task 254 | prompt eval time = 1491.91 ms / 182 tokens ( 8.20 ms per token, 121.99 tokens per second) 1.26.347.745 I slot print_timing: id 2 | task 254 | eval time = 52.29 ms / 2 tokens ( 52.29 ms per token, 19.12 tokens per second) 1.26.347.746 I slot print_timing: id 2 | task 254 | total time = 1544.20 ms / 184 tokens 1.26.347.746 I slot print_timing: id 2 | task 254 | graphs reused = 1 1.26.347.746 I slot print_timing: id 2 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.347.762 I slot release: id 2 | task 254 | stop processing: n_tokens = 183, truncated = 0 1.26.347.940 I slot print_timing: id 3 | task 255 | prompt eval time = 1492.07 ms / 155 tokens ( 9.63 ms per token, 103.88 tokens per second) 1.26.347.942 I slot print_timing: id 3 | task 255 | eval time = 52.32 ms / 2 tokens ( 52.32 ms per token, 19.11 tokens per second) 1.26.347.943 I slot print_timing: id 3 | task 255 | total time = 1544.38 ms / 157 tokens 1.26.347.943 I slot print_timing: id 3 | task 255 | graphs reused = 1 1.26.347.943 I slot print_timing: id 3 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.347.970 I slot release: id 3 | task 255 | stop processing: n_tokens = 156, truncated = 0 1.26.353.204 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 1.26.361.681 I slot launch_slot_: id 0 | task 260 | processing task, is_child = 0 1.26.361.705 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.010 MiB) 1.26.387.007 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 1.26.401.384 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.286 MiB) 1.26.421.722 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 1.26.421.813 I slot launch_slot_: id 1 | task 259 | processing task, is_child = 0 1.27.149.046 I slot print_timing: id 0 | task 260 | prompt eval time = 692.15 ms / 144 tokens ( 4.81 ms per token, 208.05 tokens per second) 1.27.149.048 I slot print_timing: id 0 | task 260 | eval time = 35.04 ms / 2 tokens ( 35.04 ms per token, 28.54 tokens per second) 1.27.149.050 I slot print_timing: id 0 | task 260 | total time = 727.19 ms / 146 tokens 1.27.149.050 I slot print_timing: id 0 | task 260 | graphs reused = 1 1.27.149.050 I slot print_timing: id 0 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.149.066 I slot release: id 0 | task 260 | stop processing: n_tokens = 145, truncated = 0 1.27.149.201 I slot print_timing: id 1 | task 259 | prompt eval time = 692.30 ms / 124 tokens ( 5.58 ms per token, 179.11 tokens per second) 1.27.149.206 I slot print_timing: id 1 | task 259 | eval time = 35.03 ms / 2 tokens ( 35.03 ms per token, 28.55 tokens per second) 1.27.149.206 I slot print_timing: id 1 | task 259 | total time = 727.33 ms / 126 tokens 1.27.149.206 I slot print_timing: id 1 | task 259 | graphs reused = 1 1.27.149.207 I slot print_timing: id 1 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.149.227 I slot release: id 1 | task 259 | stop processing: n_tokens = 125, truncated = 0 1.27.167.645 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 183, t_last = 391410215340 1.27.167.692 I slot launch_slot_: id 2 | task 264 | processing task, is_child = 0 1.27.167.714 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.266 MiB) 1.27.189.338 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.755 MiB) 1.27.203.457 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 156, t_last = 391410215549 1.27.203.523 I slot launch_slot_: id 3 | task 265 | processing task, is_child = 0 1.27.203.560 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 145, t_last = 391411016644 1.27.203.594 I slot launch_slot_: id 0 | task 266 | processing task, is_child = 0 1.27.203.615 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 125, t_last = 391411016805 1.27.203.662 I slot launch_slot_: id 1 | task 267 | processing task, is_child = 0 1.31.961.444 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 714, progress = 0.58, t = 4.76 s / 150.07 tokens per second 1.32.028.451 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 718, progress = 0.58, t = 4.76 s / 150.91 tokens per second 1.32.038.734 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 727, progress = 0.58, t = 4.76 s / 152.80 tokens per second 1.32.048.017 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 699, progress = 0.58, t = 4.76 s / 146.92 tokens per second 1.34.952.001 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 1125, progress = 0.91, t = 7.75 s / 145.19 tokens per second 1.35.122.380 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 1125, progress = 0.91, t = 7.75 s / 145.19 tokens per second 1.35.135.070 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 1125, progress = 0.91, t = 7.75 s / 145.19 tokens per second 1.35.140.900 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 1125, progress = 0.93, t = 7.75 s / 145.19 tokens per second 1.36.057.763 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 1226, progress = 1.00, t = 8.85 s / 138.47 tokens per second 1.36.131.568 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 1230, progress = 1.00, t = 8.85 s / 138.92 tokens per second 1.36.196.865 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 1239, progress = 1.00, t = 8.85 s / 139.94 tokens per second 1.36.567.764 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 1211, progress = 1.00, t = 8.85 s / 136.77 tokens per second 1.39.981.000 I slot print_timing: id 3 | task 265 | prompt eval time = 9515.33 ms / 1215 tokens ( 7.83 ms per token, 127.69 tokens per second) 1.39.981.006 I slot print_timing: id 3 | task 265 | eval time = 3261.94 ms / 63 tokens ( 52.61 ms per token, 19.01 tokens per second) 1.39.981.008 I slot print_timing: id 3 | task 265 | total time = 12777.27 ms / 1278 tokens 1.39.981.012 I slot print_timing: id 3 | task 265 | graphs reused = 63 1.39.981.013 I slot print_timing: id 3 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.981.252 I slot release: id 3 | task 265 | stop processing: n_tokens = 1277, truncated = 0 1.40.030.014 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.897 1.40.030.063 I slot launch_slot_: id 3 | task 337 | processing task, is_child = 0 1.40.847.200 I slot print_timing: id 0 | task 266 | prompt eval time = 9513.32 ms / 1230 tokens ( 7.73 ms per token, 129.29 tokens per second) 1.40.847.205 I slot print_timing: id 0 | task 266 | eval time = 4130.21 ms / 72 tokens ( 58.17 ms per token, 17.19 tokens per second) 1.40.847.206 I slot print_timing: id 0 | task 266 | total time = 13643.53 ms / 1302 tokens 1.40.847.206 I slot print_timing: id 0 | task 266 | graphs reused = 68 1.40.847.207 I slot print_timing: id 0 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.847.283 I slot release: id 0 | task 266 | stop processing: n_tokens = 1301, truncated = 0 1.40.893.115 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.881 1.40.893.157 I slot launch_slot_: id 0 | task 347 | processing task, is_child = 0 1.41.828.044 I slot print_timing: id 1 | task 267 | prompt eval time = 9514.01 ms / 1234 tokens ( 7.71 ms per token, 129.70 tokens per second) 1.41.828.048 I slot print_timing: id 1 | task 267 | eval time = 5110.34 ms / 83 tokens ( 62.32 ms per token, 16.05 tokens per second) 1.41.828.048 I slot print_timing: id 1 | task 267 | total time = 14624.35 ms / 1317 tokens 1.41.828.049 I slot print_timing: id 1 | task 267 | graphs reused = 76 1.41.828.049 I slot print_timing: id 1 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.834.105 I slot release: id 1 | task 267 | stop processing: n_tokens = 1316, truncated = 0 1.41.890.313 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.871 1.41.890.370 I slot launch_slot_: id 1 | task 359 | processing task, is_child = 0 1.43.180.358 I slot print_timing: id 2 | task 264 | n_gen = 100, tg = 15.32 t/s, tg_3s = 15.48 t/s 1.45.810.028 I slot print_timing: id 3 | task 337 | prompt eval time = 507.51 ms / 132 tokens ( 3.84 ms per token, 260.09 tokens per second) 1.45.810.036 I slot print_timing: id 3 | task 337 | eval time = 5272.44 ms / 85 tokens ( 62.77 ms per token, 15.93 tokens per second) 1.45.810.038 I slot print_timing: id 3 | task 337 | total time = 5779.95 ms / 217 tokens 1.45.810.039 I slot print_timing: id 3 | task 337 | graphs reused = 139 1.45.810.040 I slot print_timing: id 3 | task 337 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.810.167 I slot release: id 3 | task 337 | stop processing: n_tokens = 1341, truncated = 0 1.45.858.888 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.855 1.45.858.947 I slot launch_slot_: id 3 | task 427 | processing task, is_child = 0 1.46.249.255 I slot print_timing: id 2 | task 264 | n_gen = 152, tg = 15.84 t/s, tg_3s = 16.94 t/s 1.46.858.922 I slot print_timing: id 2 | task 264 | prompt eval time = 9514.67 ms / 1243 tokens ( 7.65 ms per token, 130.64 tokens per second) 1.46.858.927 I slot print_timing: id 2 | task 264 | eval time = 10140.54 ms / 163 tokens ( 62.60 ms per token, 15.98 tokens per second) 1.46.858.928 I slot print_timing: id 2 | task 264 | total time = 19655.22 ms / 1406 tokens 1.46.858.928 I slot print_timing: id 2 | task 264 | graphs reused = 148 1.46.858.929 I slot print_timing: id 2 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.858.985 I slot release: id 2 | task 264 | stop processing: n_tokens = 1405, truncated = 0 1.46.913.871 I slot print_timing: id 0 | task 347 | prompt eval time = 519.57 ms / 139 tokens ( 3.74 ms per token, 267.53 tokens per second) 1.46.913.877 I slot print_timing: id 0 | task 347 | eval time = 5501.14 ms / 90 tokens ( 61.81 ms per token, 16.18 tokens per second) 1.46.913.878 I slot print_timing: id 0 | task 347 | total time = 6020.71 ms / 229 tokens 1.46.913.878 I slot print_timing: id 0 | task 347 | graphs reused = 148 1.46.913.878 I slot print_timing: id 0 | task 347 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.913.931 I slot release: id 0 | task 347 | stop processing: n_tokens = 1353, truncated = 0 1.46.914.240 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.847 1.46.914.270 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 1.46.914.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 1.46.914.354 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.068 MiB) 1.47.062.072 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.816 1.47.062.125 I slot launch_slot_: id 2 | task 442 | processing task, is_child = 0 1.49.055.331 I slot print_timing: id 1 | task 359 | n_gen = 100, tg = 15.01 t/s, tg_3s = 15.16 t/s 1.50.153.199 I slot print_timing: id 1 | task 359 | prompt eval time = 568.82 ms / 139 tokens ( 4.09 ms per token, 244.36 tokens per second) 1.50.153.207 I slot print_timing: id 1 | task 359 | eval time = 7693.99 ms / 121 tokens ( 64.12 ms per token, 15.60 tokens per second) 1.50.153.208 I slot print_timing: id 1 | task 359 | total time = 8262.82 ms / 260 tokens 1.50.153.209 I slot print_timing: id 1 | task 359 | graphs reused = 187 1.50.153.210 I slot print_timing: id 1 | task 359 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.154.752 I slot release: id 1 | task 359 | stop processing: n_tokens = 1384, truncated = 0 1.50.215.526 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.828 1.50.215.584 I slot launch_slot_: id 1 | task 486 | processing task, is_child = 0 1.52.977.605 I slot print_timing: id 3 | task 427 | n_gen = 100, tg = 14.92 t/s, tg_3s = 15.07 t/s 1.53.343.404 I slot print_timing: id 0 | task 441 | prompt eval time = 986.55 ms / 141 tokens ( 7.00 ms per token, 142.92 tokens per second) 1.53.343.409 I slot print_timing: id 0 | task 441 | eval time = 5294.72 ms / 94 tokens ( 56.93 ms per token, 17.56 tokens per second) 1.53.343.410 I slot print_timing: id 0 | task 441 | total time = 6281.27 ms / 235 tokens 1.53.343.411 I slot print_timing: id 0 | task 441 | graphs reused = 236 1.53.343.412 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.344.779 I slot release: id 0 | task 441 | stop processing: n_tokens = 1359, truncated = 0 1.53.394.749 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.843 1.53.394.818 I slot launch_slot_: id 0 | task 540 | processing task, is_child = 0 1.54.006.968 I slot print_timing: id 2 | task 442 | n_gen = 100, tg = 16.62 t/s, tg_3s = 16.78 t/s 1.54.213.365 I slot print_timing: id 3 | task 427 | prompt eval time = 484.12 ms / 114 tokens ( 4.25 ms per token, 235.48 tokens per second) 1.54.213.368 I slot print_timing: id 3 | task 427 | eval time = 7870.28 ms / 117 tokens ( 67.85 ms per token, 14.74 tokens per second) 1.54.213.368 I slot print_timing: id 3 | task 427 | total time = 8354.41 ms / 231 tokens 1.54.213.369 I slot print_timing: id 3 | task 427 | graphs reused = 243 1.54.213.369 I slot print_timing: id 3 | task 427 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.213.428 I slot release: id 3 | task 427 | stop processing: n_tokens = 1355, truncated = 0 1.54.259.667 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.846 1.54.259.714 I slot launch_slot_: id 3 | task 551 | processing task, is_child = 0 1.55.525.495 I slot print_timing: id 1 | task 486 | prompt eval time = 525.68 ms / 125 tokens ( 4.21 ms per token, 237.79 tokens per second) 1.55.525.501 I slot print_timing: id 1 | task 486 | eval time = 4784.22 ms / 80 tokens ( 60.56 ms per token, 16.51 tokens per second) 1.55.525.501 I slot print_timing: id 1 | task 486 | total time = 5309.90 ms / 205 tokens 1.55.525.502 I slot print_timing: id 1 | task 486 | graphs reused = 258 1.55.525.502 I slot print_timing: id 1 | task 486 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.525.559 I slot release: id 1 | task 486 | stop processing: n_tokens = 1329, truncated = 0 1.55.582.336 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.862 1.55.582.365 I slot launch_slot_: id 1 | task 571 | processing task, is_child = 0 1.56.613.020 I slot print_timing: id 2 | task 442 | prompt eval time = 972.46 ms / 169 tokens ( 5.75 ms per token, 173.79 tokens per second) 1.56.613.023 I slot print_timing: id 2 | task 442 | eval time = 8563.83 ms / 137 tokens ( 62.97 ms per token, 15.88 tokens per second) 1.56.613.024 I slot print_timing: id 2 | task 442 | total time = 9536.29 ms / 306 tokens 1.56.613.024 I slot print_timing: id 2 | task 442 | graphs reused = 268 1.56.613.024 I slot print_timing: id 2 | task 442 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.613.086 I slot release: id 2 | task 442 | stop processing: n_tokens = 1430, truncated = 0 1.56.669.491 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.801 1.56.669.531 I slot launch_slot_: id 2 | task 586 | processing task, is_child = 0 1.58.564.805 I slot print_timing: id 3 | task 551 | prompt eval time = 440.08 ms / 101 tokens ( 4.36 ms per token, 229.51 tokens per second) 1.58.564.811 I slot print_timing: id 3 | task 551 | eval time = 3865.01 ms / 61 tokens ( 64.42 ms per token, 15.52 tokens per second) 1.58.564.811 I slot print_timing: id 3 | task 551 | total time = 4305.08 ms / 162 tokens 1.58.564.812 I slot print_timing: id 3 | task 551 | graphs reused = 293 1.58.564.812 I slot print_timing: id 3 | task 551 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.564.868 I slot release: id 3 | task 551 | stop processing: n_tokens = 1286, truncated = 0 1.58.610.577 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.891 1.58.610.617 I slot launch_slot_: id 3 | task 617 | processing task, is_child = 0 1.59.438.377 I slot print_timing: id 0 | task 540 | prompt eval time = 455.22 ms / 101 tokens ( 4.51 ms per token, 221.87 tokens per second) 1.59.438.382 I slot print_timing: id 0 | task 540 | eval time = 5588.33 ms / 80 tokens ( 70.74 ms per token, 14.14 tokens per second) 1.59.438.383 I slot print_timing: id 0 | task 540 | total time = 6043.55 ms / 181 tokens 1.59.438.383 I slot print_timing: id 0 | task 540 | graphs reused = 298 1.59.438.384 I slot print_timing: id 0 | task 540 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.438.431 I slot release: id 0 | task 540 | stop processing: n_tokens = 1305, truncated = 0 1.59.484.539 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.878 1.59.484.577 I slot launch_slot_: id 0 | task 627 | processing task, is_child = 0 2.01.546.208 I slot print_timing: id 2 | task 586 | prompt eval time = 500.06 ms / 120 tokens ( 4.17 ms per token, 239.97 tokens per second) 2.01.546.217 I slot print_timing: id 2 | task 586 | eval time = 4376.61 ms / 72 tokens ( 61.64 ms per token, 16.22 tokens per second) 2.01.546.217 I slot print_timing: id 2 | task 586 | total time = 4876.67 ms / 192 tokens 2.01.546.218 I slot print_timing: id 2 | task 586 | graphs reused = 330 2.01.546.218 I slot print_timing: id 2 | task 586 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.546.277 I slot release: id 2 | task 586 | stop processing: n_tokens = 1316, truncated = 0 2.01.602.627 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.871 2.01.602.657 I slot launch_slot_: id 2 | task 663 | processing task, is_child = 0 2.02.678.855 I slot print_timing: id 1 | task 571 | n_gen = 100, tg = 14.92 t/s, tg_3s = 15.07 t/s 2.03.474.858 I slot print_timing: id 1 | task 571 | prompt eval time = 461.14 ms / 95 tokens ( 4.85 ms per token, 206.01 tokens per second) 2.03.474.864 I slot print_timing: id 1 | task 571 | eval time = 7431.34 ms / 115 tokens ( 65.19 ms per token, 15.34 tokens per second) 2.03.474.865 I slot print_timing: id 1 | task 571 | total time = 7892.48 ms / 210 tokens 2.03.474.866 I slot print_timing: id 1 | task 571 | graphs reused = 355 2.03.474.867 I slot print_timing: id 1 | task 571 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.474.989 I slot release: id 1 | task 571 | stop processing: n_tokens = 1334, truncated = 0 2.03.535.415 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.859 2.03.535.481 I slot launch_slot_: id 1 | task 693 | processing task, is_child = 0 2.04.884.025 I slot print_timing: id 0 | task 627 | prompt eval time = 409.51 ms / 86 tokens ( 4.76 ms per token, 210.00 tokens per second) 2.04.884.032 I slot print_timing: id 0 | task 627 | eval time = 4989.92 ms / 82 tokens ( 61.60 ms per token, 16.23 tokens per second) 2.04.884.034 I slot print_timing: id 0 | task 627 | total time = 5399.44 ms / 168 tokens 2.04.884.034 I slot print_timing: id 0 | task 627 | graphs reused = 371 2.04.884.035 I slot print_timing: id 0 | task 627 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.884.120 I slot release: id 0 | task 627 | stop processing: n_tokens = 1292, truncated = 0 2.04.934.718 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.948 (> 0.100 thold), f_keep = 0.887 2.04.934.791 I slot launch_slot_: id 0 | task 714 | processing task, is_child = 0 2.05.651.344 I slot print_timing: id 3 | task 617 | n_gen = 100, tg = 15.18 t/s, tg_3s = 15.33 t/s 2.07.611.415 I slot print_timing: id 1 | task 693 | prompt eval time = 457.13 ms / 97 tokens ( 4.71 ms per token, 212.19 tokens per second) 2.07.611.421 I slot print_timing: id 1 | task 693 | eval time = 3618.80 ms / 65 tokens ( 56.54 ms per token, 17.69 tokens per second) 2.07.611.422 I slot print_timing: id 1 | task 693 | total time = 4075.93 ms / 162 tokens 2.07.611.423 I slot print_timing: id 1 | task 693 | graphs reused = 415 2.07.611.423 I slot print_timing: id 1 | task 693 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.611.487 I slot release: id 1 | task 693 | stop processing: n_tokens = 1286, truncated = 0 2.07.668.240 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.891 2.07.668.281 I slot launch_slot_: id 1 | task 762 | processing task, is_child = 0 2.08.287.517 I slot print_timing: id 2 | task 663 | n_gen = 100, tg = 16.03 t/s, tg_3s = 16.19 t/s 2.08.700.847 I slot print_timing: id 3 | task 617 | n_gen = 152, tg = 15.77 t/s, tg_3s = 17.05 t/s 2.08.753.126 I slot print_timing: id 2 | task 663 | prompt eval time = 507.74 ms / 133 tokens ( 3.82 ms per token, 261.95 tokens per second) 2.08.753.133 I slot print_timing: id 2 | task 663 | eval time = 6642.72 ms / 109 tokens ( 61.51 ms per token, 16.26 tokens per second) 2.08.753.136 I slot print_timing: id 2 | task 663 | total time = 7150.45 ms / 242 tokens 2.08.753.137 I slot print_timing: id 2 | task 663 | graphs reused = 426 2.08.753.138 I slot print_timing: id 2 | task 663 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.753.295 I slot release: id 2 | task 663 | stop processing: n_tokens = 1366, truncated = 0 2.08.823.202 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.839 2.08.823.255 I slot launch_slot_: id 2 | task 778 | processing task, is_child = 0 2.09.697.384 I slot print_timing: id 0 | task 714 | prompt eval time = 405.32 ms / 84 tokens ( 4.83 ms per token, 207.24 tokens per second) 2.09.697.390 I slot print_timing: id 0 | task 714 | eval time = 4357.26 ms / 71 tokens ( 62.25 ms per token, 16.07 tokens per second) 2.09.697.391 I slot print_timing: id 0 | task 714 | total time = 4762.58 ms / 155 tokens 2.09.697.392 I slot print_timing: id 0 | task 714 | graphs reused = 433 2.09.697.392 I slot print_timing: id 0 | task 714 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.697.442 I slot release: id 0 | task 714 | stop processing: n_tokens = 1279, truncated = 0 2.09.744.478 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.896 2.09.744.542 I slot launch_slot_: id 0 | task 790 | processing task, is_child = 0 2.10.557.714 I slot print_timing: id 3 | task 617 | prompt eval time = 517.26 ms / 148 tokens ( 3.49 ms per token, 286.12 tokens per second) 2.10.557.722 I slot print_timing: id 3 | task 617 | eval time = 11429.83 ms / 173 tokens ( 66.45 ms per token, 15.05 tokens per second) 2.10.557.724 I slot print_timing: id 3 | task 617 | total time = 11947.08 ms / 321 tokens 2.10.557.725 I slot print_timing: id 3 | task 617 | graphs reused = 439 2.10.557.726 I slot print_timing: id 3 | task 617 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.559.923 I slot release: id 3 | task 617 | stop processing: n_tokens = 1445, truncated = 0 2.10.608.993 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.793 2.10.609.058 I slot launch_slot_: id 3 | task 800 | processing task, is_child = 0 2.12.394.645 I slot print_timing: id 1 | task 762 | prompt eval time = 461.50 ms / 101 tokens ( 4.57 ms per token, 218.85 tokens per second) 2.12.394.654 I slot print_timing: id 1 | task 762 | eval time = 4264.86 ms / 62 tokens ( 69.92 ms per token, 14.30 tokens per second) 2.12.394.656 I slot print_timing: id 1 | task 762 | total time = 4726.35 ms / 163 tokens 2.12.394.657 I slot print_timing: id 1 | task 762 | graphs reused = 463 2.12.394.658 I slot print_timing: id 1 | task 762 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.394.764 I slot release: id 1 | task 762 | stop processing: n_tokens = 1287, truncated = 0 2.12.455.866 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.890 2.12.455.940 I slot launch_slot_: id 1 | task 830 | processing task, is_child = 0 2.13.278.257 I slot print_timing: id 2 | task 778 | prompt eval time = 459.91 ms / 95 tokens ( 4.84 ms per token, 206.56 tokens per second) 2.13.278.262 I slot print_timing: id 2 | task 778 | eval time = 3995.09 ms / 57 tokens ( 71.34 ms per token, 14.02 tokens per second) 2.13.278.263 I slot print_timing: id 2 | task 778 | total time = 4454.99 ms / 152 tokens 2.13.278.264 I slot print_timing: id 2 | task 778 | graphs reused = 469 2.13.278.264 I slot print_timing: id 2 | task 778 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.278.315 I slot release: id 2 | task 778 | stop processing: n_tokens = 1276, truncated = 0 2.13.334.928 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.898 2.13.334.975 I slot launch_slot_: id 2 | task 841 | processing task, is_child = 0 2.16.480.656 I slot print_timing: id 0 | task 790 | n_gen = 100, tg = 15.84 t/s, tg_3s = 16.00 t/s 2.16.692.348 I slot print_timing: id 3 | task 800 | prompt eval time = 422.11 ms / 90 tokens ( 4.69 ms per token, 213.22 tokens per second) 2.16.692.354 I slot print_timing: id 3 | task 800 | eval time = 5661.17 ms / 95 tokens ( 60.23 ms per token, 16.60 tokens per second) 2.16.692.355 I slot print_timing: id 3 | task 800 | total time = 6083.28 ms / 185 tokens 2.16.692.356 I slot print_timing: id 3 | task 800 | graphs reused = 523 2.16.692.356 I slot print_timing: id 3 | task 800 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.692.452 I slot release: id 3 | task 800 | stop processing: n_tokens = 1309, truncated = 0 2.16.741.829 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.876 2.16.741.885 I slot launch_slot_: id 3 | task 900 | processing task, is_child = 0 2.17.334.833 I slot print_timing: id 1 | task 830 | prompt eval time = 458.98 ms / 96 tokens ( 4.78 ms per token, 209.16 tokens per second) 2.17.334.835 I slot print_timing: id 1 | task 830 | eval time = 4419.89 ms / 71 tokens ( 63.14 ms per token, 15.84 tokens per second) 2.17.334.837 I slot print_timing: id 1 | task 830 | total time = 4878.88 ms / 167 tokens 2.17.334.837 I slot print_timing: id 1 | task 830 | graphs reused = 524 2.17.334.838 I slot print_timing: id 1 | task 830 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.334.888 I slot release: id 1 | task 830 | stop processing: n_tokens = 1291, truncated = 0 2.17.390.880 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.888 2.17.390.913 I slot launch_slot_: id 1 | task 906 | processing task, is_child = 0 2.19.015.647 I slot print_timing: id 0 | task 790 | prompt eval time = 486.69 ms / 130 tokens ( 3.74 ms per token, 267.11 tokens per second) 2.19.015.655 I slot print_timing: id 0 | task 790 | eval time = 8784.40 ms / 133 tokens ( 66.55 ms per token, 15.03 tokens per second) 2.19.015.656 I slot print_timing: id 0 | task 790 | total time = 9271.09 ms / 263 tokens 2.19.015.657 I slot print_timing: id 0 | task 790 | graphs reused = 544 2.19.015.658 I slot print_timing: id 0 | task 790 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.015.753 I slot release: id 0 | task 790 | stop processing: n_tokens = 1387, truncated = 0 2.19.066.879 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.826 2.19.066.947 I slot launch_slot_: id 0 | task 931 | processing task, is_child = 0 2.19.993.964 I slot print_timing: id 2 | task 841 | prompt eval time = 457.21 ms / 87 tokens ( 5.26 ms per token, 190.29 tokens per second) 2.19.993.970 I slot print_timing: id 2 | task 841 | eval time = 6201.77 ms / 96 tokens ( 65.28 ms per token, 15.32 tokens per second) 2.19.993.970 I slot print_timing: id 2 | task 841 | total time = 6658.98 ms / 183 tokens 2.19.993.971 I slot print_timing: id 2 | task 841 | graphs reused = 552 2.19.993.971 I slot print_timing: id 2 | task 841 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.994.025 I slot release: id 2 | task 841 | stop processing: n_tokens = 1307, truncated = 0 2.20.050.209 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.877 2.20.050.244 I slot launch_slot_: id 2 | task 943 | processing task, is_child = 0 2.23.602.174 I slot print_timing: id 3 | task 900 | n_gen = 100, tg = 15.54 t/s, tg_3s = 15.69 t/s 2.23.812.310 I slot print_timing: id 2 | task 943 | prompt eval time = 445.74 ms / 93 tokens ( 4.79 ms per token, 208.64 tokens per second) 2.23.812.316 I slot print_timing: id 2 | task 943 | eval time = 3316.32 ms / 64 tokens ( 52.64 ms per token, 19.00 tokens per second) 2.23.812.317 I slot print_timing: id 2 | task 943 | total time = 3762.06 ms / 157 tokens 2.23.812.318 I slot print_timing: id 2 | task 943 | graphs reused = 614 2.23.812.319 I slot print_timing: id 2 | task 943 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.812.427 I slot release: id 2 | task 943 | stop processing: n_tokens = 1281, truncated = 0 2.23.873.513 I slot print_timing: id 1 | task 906 | n_gen = 100, tg = 16.65 t/s, tg_3s = 16.82 t/s 2.23.873.910 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.895 2.23.873.976 I slot launch_slot_: id 2 | task 1010 | processing task, is_child = 0 2.25.249.867 I slot print_timing: id 3 | task 900 | prompt eval time = 488.26 ms / 131 tokens ( 3.73 ms per token, 268.30 tokens per second) 2.25.249.870 I slot print_timing: id 3 | task 900 | eval time = 8019.71 ms / 125 tokens ( 64.68 ms per token, 15.46 tokens per second) 2.25.249.871 I slot print_timing: id 3 | task 900 | total time = 8507.97 ms / 256 tokens 2.25.249.871 I slot print_timing: id 3 | task 900 | graphs reused = 631 2.25.249.872 I slot print_timing: id 3 | task 900 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.249.951 I slot release: id 3 | task 900 | stop processing: n_tokens = 1380, truncated = 0 2.25.295.770 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.830 2.25.295.805 I slot launch_slot_: id 3 | task 1032 | processing task, is_child = 0 2.25.788.542 I slot print_timing: id 0 | task 931 | n_gen = 100, tg = 15.94 t/s, tg_3s = 16.11 t/s 2.26.923.355 I slot print_timing: id 1 | task 906 | n_gen = 146, tg = 16.12 t/s, tg_3s = 15.08 t/s 2.27.544.231 I slot print_timing: id 2 | task 1010 | prompt eval time = 445.22 ms / 87 tokens ( 5.12 ms per token, 195.41 tokens per second) 2.27.544.237 I slot print_timing: id 2 | task 1010 | eval time = 3225.02 ms / 57 tokens ( 57.59 ms per token, 17.36 tokens per second) 2.27.544.238 I slot print_timing: id 2 | task 1010 | total time = 3670.24 ms / 144 tokens 2.27.544.239 I slot print_timing: id 2 | task 1010 | graphs reused = 665 2.27.544.239 I slot print_timing: id 2 | task 1010 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.544.293 I slot release: id 2 | task 1010 | stop processing: n_tokens = 1268, truncated = 0 2.27.603.083 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.904 2.27.603.192 I slot launch_slot_: id 2 | task 1071 | processing task, is_child = 0 2.28.352.872 I slot print_timing: id 1 | task 906 | prompt eval time = 535.54 ms / 137 tokens ( 3.91 ms per token, 255.82 tokens per second) 2.28.352.877 I slot print_timing: id 1 | task 906 | eval time = 10426.41 ms / 166 tokens ( 63.19 ms per token, 15.83 tokens per second) 2.28.352.878 I slot print_timing: id 1 | task 906 | total time = 10961.95 ms / 303 tokens 2.28.352.878 I slot print_timing: id 1 | task 906 | graphs reused = 669 2.28.352.879 I slot print_timing: id 1 | task 906 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.352.933 I slot release: id 1 | task 906 | stop processing: n_tokens = 1427, truncated = 0 2.28.409.454 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.803 2.28.409.495 I slot launch_slot_: id 1 | task 1080 | processing task, is_child = 0 2.28.795.323 I slot print_timing: id 0 | task 931 | n_gen = 144, tg = 15.52 t/s, tg_3s = 14.63 t/s 2.29.007.888 I slot print_timing: id 3 | task 1032 | prompt eval time = 439.42 ms / 98 tokens ( 4.48 ms per token, 223.02 tokens per second) 2.29.007.891 I slot print_timing: id 3 | task 1032 | eval time = 3272.66 ms / 49 tokens ( 68.18 ms per token, 14.67 tokens per second) 2.29.007.892 I slot print_timing: id 3 | task 1032 | total time = 3712.07 ms / 147 tokens 2.29.007.892 I slot print_timing: id 3 | task 1032 | graphs reused = 670 2.29.007.893 I slot print_timing: id 3 | task 1032 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.008.413 I slot release: id 3 | task 1032 | stop processing: n_tokens = 1271, truncated = 0 2.29.054.265 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.902 2.29.054.299 I slot launch_slot_: id 3 | task 1086 | processing task, is_child = 0 2.31.611.993 I slot print_timing: id 0 | task 931 | prompt eval time = 512.71 ms / 153 tokens ( 3.35 ms per token, 298.42 tokens per second) 2.31.612.002 I slot print_timing: id 0 | task 931 | eval time = 12032.33 ms / 190 tokens ( 63.66 ms per token, 15.71 tokens per second) 2.31.612.003 I slot print_timing: id 0 | task 931 | total time = 12545.04 ms / 343 tokens 2.31.612.004 I slot print_timing: id 0 | task 931 | graphs reused = 709 2.31.612.005 I slot print_timing: id 0 | task 931 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.612.106 I slot release: id 0 | task 931 | stop processing: n_tokens = 1467, truncated = 0 2.31.662.454 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 2.31.662.508 I slot launch_slot_: id 0 | task 1130 | processing task, is_child = 0 2.33.786.875 I slot print_timing: id 2 | task 1071 | prompt eval time = 488.25 ms / 105 tokens ( 4.65 ms per token, 215.05 tokens per second) 2.33.786.878 I slot print_timing: id 2 | task 1071 | eval time = 5695.41 ms / 90 tokens ( 63.99 ms per token, 15.63 tokens per second) 2.33.786.879 I slot print_timing: id 2 | task 1071 | total time = 6183.67 ms / 195 tokens 2.33.786.879 I slot print_timing: id 2 | task 1071 | graphs reused = 742 2.33.786.879 I slot print_timing: id 2 | task 1071 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.786.929 I slot release: id 2 | task 1071 | stop processing: n_tokens = 1319, truncated = 0 2.33.844.790 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.869 2.33.844.827 I slot launch_slot_: id 2 | task 1167 | processing task, is_child = 0 2.35.117.794 I slot print_timing: id 1 | task 1080 | n_gen = 100, tg = 15.93 t/s, tg_3s = 16.09 t/s 2.35.376.676 I slot print_timing: id 3 | task 1086 | n_gen = 100, tg = 16.92 t/s, tg_3s = 17.09 t/s 2.35.591.337 I slot print_timing: id 3 | task 1086 | prompt eval time = 471.56 ms / 122 tokens ( 3.87 ms per token, 258.72 tokens per second) 2.35.591.346 I slot print_timing: id 3 | task 1086 | eval time = 6065.47 ms / 104 tokens ( 58.89 ms per token, 16.98 tokens per second) 2.35.591.353 I slot print_timing: id 3 | task 1086 | total time = 6537.03 ms / 226 tokens 2.35.591.354 I slot print_timing: id 3 | task 1086 | graphs reused = 765 2.35.591.369 I slot print_timing: id 3 | task 1086 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.591.494 I slot release: id 3 | task 1086 | stop processing: n_tokens = 1350, truncated = 0 2.35.640.644 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.849 2.35.640.707 I slot launch_slot_: id 3 | task 1195 | processing task, is_child = 0 2.36.416.400 I slot print_timing: id 1 | task 1080 | prompt eval time = 493.03 ms / 113 tokens ( 4.36 ms per token, 229.19 tokens per second) 2.36.416.406 I slot print_timing: id 1 | task 1080 | eval time = 7513.87 ms / 117 tokens ( 64.77 ms per token, 15.44 tokens per second) 2.36.416.407 I slot print_timing: id 1 | task 1080 | total time = 8006.90 ms / 230 tokens 2.36.416.408 I slot print_timing: id 1 | task 1080 | graphs reused = 769 2.36.416.408 I slot print_timing: id 1 | task 1080 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.416.459 I slot release: id 1 | task 1080 | stop processing: n_tokens = 1354, truncated = 0 2.36.472.843 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.846 2.36.472.878 I slot launch_slot_: id 1 | task 1204 | processing task, is_child = 0 2.38.431.230 I slot print_timing: id 0 | task 1130 | n_gen = 100, tg = 15.59 t/s, tg_3s = 15.75 t/s 2.38.638.963 I slot print_timing: id 0 | task 1130 | prompt eval time = 418.19 ms / 96 tokens ( 4.36 ms per token, 229.56 tokens per second) 2.38.638.968 I slot print_timing: id 0 | task 1130 | eval time = 6558.26 ms / 104 tokens ( 63.67 ms per token, 15.71 tokens per second) 2.38.638.969 I slot print_timing: id 0 | task 1130 | total time = 6976.45 ms / 200 tokens 2.38.638.969 I slot print_timing: id 0 | task 1130 | graphs reused = 800 2.38.638.970 I slot print_timing: id 0 | task 1130 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.639.012 I slot release: id 0 | task 1130 | stop processing: n_tokens = 1324, truncated = 0 2.38.685.099 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.866 2.38.685.133 I slot launch_slot_: id 0 | task 1240 | processing task, is_child = 0 2.40.639.533 I slot print_timing: id 2 | task 1167 | n_gen = 100, tg = 15.72 t/s, tg_3s = 15.88 t/s 2.40.691.001 I slot print_timing: id 2 | task 1167 | prompt eval time = 498.25 ms / 113 tokens ( 4.41 ms per token, 226.79 tokens per second) 2.40.691.004 I slot print_timing: id 2 | task 1167 | eval time = 6347.91 ms / 101 tokens ( 63.48 ms per token, 15.75 tokens per second) 2.40.691.004 I slot print_timing: id 2 | task 1167 | total time = 6846.17 ms / 214 tokens 2.40.691.005 I slot print_timing: id 2 | task 1167 | graphs reused = 830 2.40.691.005 I slot print_timing: id 2 | task 1167 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.691.071 I slot release: id 2 | task 1167 | stop processing: n_tokens = 1338, truncated = 0 2.40.746.609 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.857 2.40.746.642 I slot launch_slot_: id 2 | task 1274 | processing task, is_child = 0 2.42.331.810 I slot print_timing: id 1 | task 1204 | prompt eval time = 511.95 ms / 131 tokens ( 3.91 ms per token, 255.89 tokens per second) 2.42.331.815 I slot print_timing: id 1 | task 1204 | eval time = 5346.98 ms / 90 tokens ( 60.08 ms per token, 16.64 tokens per second) 2.42.331.816 I slot print_timing: id 1 | task 1204 | total time = 5858.93 ms / 221 tokens 2.42.331.816 I slot print_timing: id 1 | task 1204 | graphs reused = 850 2.42.331.817 I slot print_timing: id 1 | task 1204 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.331.877 I slot release: id 1 | task 1204 | stop processing: n_tokens = 1345, truncated = 0 2.42.387.536 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.852 2.42.387.576 I slot launch_slot_: id 1 | task 1299 | processing task, is_child = 0 2.42.812.716 I slot print_timing: id 3 | task 1195 | n_gen = 100, tg = 14.88 t/s, tg_3s = 15.03 t/s 2.43.911.385 I slot print_timing: id 0 | task 1240 | prompt eval time = 460.08 ms / 117 tokens ( 3.93 ms per token, 254.31 tokens per second) 2.43.911.392 I slot print_timing: id 0 | task 1240 | eval time = 4766.16 ms / 77 tokens ( 62.71 ms per token, 15.95 tokens per second) 2.43.911.393 I slot print_timing: id 0 | task 1240 | total time = 5226.24 ms / 194 tokens 2.43.911.394 I slot print_timing: id 0 | task 1240 | graphs reused = 868 2.43.911.395 I slot print_timing: id 0 | task 1240 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.911.498 I slot release: id 0 | task 1240 | stop processing: n_tokens = 1318, truncated = 0 2.43.961.890 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.869 2.43.961.951 I slot launch_slot_: id 0 | task 1322 | processing task, is_child = 0 2.45.823.601 I slot print_timing: id 3 | task 1195 | n_gen = 151, tg = 15.52 t/s, tg_3s = 16.94 t/s 2.45.926.398 I slot print_timing: id 3 | task 1195 | prompt eval time = 516.73 ms / 149 tokens ( 3.47 ms per token, 288.35 tokens per second) 2.45.926.401 I slot print_timing: id 3 | task 1195 | eval time = 9768.95 ms / 153 tokens ( 64.27 ms per token, 15.56 tokens per second) 2.45.926.402 I slot print_timing: id 3 | task 1195 | total time = 10285.68 ms / 302 tokens 2.45.926.402 I slot print_timing: id 3 | task 1195 | graphs reused = 898 2.45.926.403 I slot print_timing: id 3 | task 1195 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.926.464 I slot release: id 3 | task 1195 | stop processing: n_tokens = 1426, truncated = 0 2.45.972.004 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.804 2.45.972.037 I slot launch_slot_: id 3 | task 1356 | processing task, is_child = 0 2.47.458.919 I slot print_timing: id 2 | task 1274 | n_gen = 100, tg = 15.94 t/s, tg_3s = 16.10 t/s 2.48.195.844 I slot print_timing: id 2 | task 1274 | prompt eval time = 501.47 ms / 127 tokens ( 3.95 ms per token, 253.26 tokens per second) 2.48.195.852 I slot print_timing: id 2 | task 1274 | eval time = 6947.72 ms / 114 tokens ( 61.48 ms per token, 16.26 tokens per second) 2.48.195.853 I slot print_timing: id 2 | task 1274 | total time = 7449.19 ms / 241 tokens 2.48.195.854 I slot print_timing: id 2 | task 1274 | graphs reused = 931 2.48.195.855 I slot print_timing: id 2 | task 1274 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.195.973 I slot release: id 2 | task 1274 | stop processing: n_tokens = 1365, truncated = 0 2.48.257.040 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.840 2.48.257.127 I slot launch_slot_: id 2 | task 1394 | processing task, is_child = 0 2.49.079.261 I slot print_timing: id 1 | task 1299 | n_gen = 100, tg = 16.08 t/s, tg_3s = 16.24 t/s 2.49.953.358 I slot print_timing: id 0 | task 1322 | prompt eval time = 416.81 ms / 96 tokens ( 4.34 ms per token, 230.32 tokens per second) 2.49.953.363 I slot print_timing: id 0 | task 1322 | eval time = 5574.59 ms / 95 tokens ( 59.30 ms per token, 16.86 tokens per second) 2.49.953.364 I slot print_timing: id 0 | task 1322 | total time = 5991.40 ms / 191 tokens 2.49.953.364 I slot print_timing: id 0 | task 1322 | graphs reused = 954 2.49.953.365 I slot print_timing: id 0 | task 1322 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.953.411 I slot release: id 0 | task 1322 | stop processing: n_tokens = 1315, truncated = 0 2.49.999.320 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.871 2.49.999.354 I slot launch_slot_: id 0 | task 1422 | processing task, is_child = 0 2.50.598.669 I slot print_timing: id 3 | task 1356 | prompt eval time = 457.09 ms / 104 tokens ( 4.40 ms per token, 227.53 tokens per second) 2.50.598.676 I slot print_timing: id 3 | task 1356 | eval time = 4169.53 ms / 68 tokens ( 62.23 ms per token, 16.07 tokens per second) 2.50.598.676 I slot print_timing: id 3 | task 1356 | total time = 4626.63 ms / 172 tokens 2.50.598.677 I slot print_timing: id 3 | task 1356 | graphs reused = 957 2.50.598.677 I slot print_timing: id 3 | task 1356 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.598.748 I slot release: id 3 | task 1356 | stop processing: n_tokens = 1296, truncated = 0 2.50.644.102 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.884 2.50.644.132 I slot launch_slot_: id 3 | task 1429 | processing task, is_child = 0 2.52.085.009 I slot print_timing: id 1 | task 1299 | n_gen = 145, tg = 15.72 t/s, tg_3s = 14.97 t/s 2.52.805.809 I slot print_timing: id 1 | task 1299 | prompt eval time = 534.40 ms / 137 tokens ( 3.90 ms per token, 256.36 tokens per second) 2.52.805.814 I slot print_timing: id 1 | task 1299 | eval time = 9883.83 ms / 159 tokens ( 62.56 ms per token, 15.99 tokens per second) 2.52.805.814 I slot print_timing: id 1 | task 1299 | total time = 10418.23 ms / 296 tokens 2.52.805.815 I slot print_timing: id 1 | task 1299 | graphs reused = 989 2.52.805.815 I slot print_timing: id 1 | task 1299 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.805.860 I slot release: id 1 | task 1299 | stop processing: n_tokens = 1420, truncated = 0 2.52.862.259 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.807 2.52.862.296 I slot launch_slot_: id 1 | task 1466 | processing task, is_child = 0 2.53.671.487 I slot print_timing: id 2 | task 1394 | prompt eval time = 460.42 ms / 98 tokens ( 4.70 ms per token, 212.85 tokens per second) 2.53.671.493 I slot print_timing: id 2 | task 1394 | eval time = 4953.93 ms / 76 tokens ( 66.05 ms per token, 15.14 tokens per second) 2.53.671.494 I slot print_timing: id 2 | task 1394 | total time = 5414.35 ms / 174 tokens 2.53.671.494 I slot print_timing: id 2 | task 1394 | graphs reused = 994 2.53.671.495 I slot print_timing: id 2 | task 1394 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.671.550 I slot release: id 2 | task 1394 | stop processing: n_tokens = 1298, truncated = 0 2.53.728.699 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.883 2.53.728.747 I slot launch_slot_: id 2 | task 1476 | processing task, is_child = 0 2.55.062.139 I slot print_timing: id 0 | task 1422 | prompt eval time = 442.28 ms / 102 tokens ( 4.34 ms per token, 230.62 tokens per second) 2.55.062.142 I slot print_timing: id 0 | task 1422 | eval time = 4620.50 ms / 68 tokens ( 68.96 ms per token, 14.50 tokens per second) 2.55.062.142 I slot print_timing: id 0 | task 1422 | total time = 5062.77 ms / 170 tokens 2.55.062.143 I slot print_timing: id 0 | task 1422 | graphs reused = 1008 2.55.062.143 I slot print_timing: id 0 | task 1422 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.062.191 I slot release: id 0 | task 1422 | stop processing: n_tokens = 1294, truncated = 0 2.55.107.818 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.886 2.55.107.850 I slot launch_slot_: id 0 | task 1496 | processing task, is_child = 0 2.57.393.210 I slot print_timing: id 3 | task 1429 | n_gen = 100, tg = 15.75 t/s, tg_3s = 15.90 t/s 2.58.132.550 I slot print_timing: id 3 | task 1429 | prompt eval time = 461.55 ms / 108 tokens ( 4.27 ms per token, 233.99 tokens per second) 2.58.132.557 I slot print_timing: id 3 | task 1429 | eval time = 7026.85 ms / 114 tokens ( 62.18 ms per token, 16.08 tokens per second) 2.58.132.559 I slot print_timing: id 3 | task 1429 | total time = 7488.41 ms / 222 tokens 2.58.132.560 I slot print_timing: id 3 | task 1429 | graphs reused = 1057 2.58.132.561 I slot print_timing: id 3 | task 1429 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.132.654 I slot release: id 3 | task 1429 | stop processing: n_tokens = 1346, truncated = 0 2.58.181.553 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.851 2.58.181.609 I slot launch_slot_: id 3 | task 1549 | processing task, is_child = 0 2.59.602.324 I slot print_timing: id 1 | task 1466 | n_gen = 100, tg = 15.86 t/s, tg_3s = 16.02 t/s 2.59.919.242 I slot print_timing: id 2 | task 1476 | prompt eval time = 505.19 ms / 124 tokens ( 4.07 ms per token, 245.45 tokens per second) 2.59.919.251 I slot print_timing: id 2 | task 1476 | eval time = 5685.30 ms / 97 tokens ( 59.22 ms per token, 16.89 tokens per second) 2.59.919.252 I slot print_timing: id 2 | task 1476 | total time = 6190.48 ms / 221 tokens 2.59.919.253 I slot print_timing: id 2 | task 1476 | graphs reused = 1081 2.59.919.254 I slot print_timing: id 2 | task 1476 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.919.364 I slot release: id 2 | task 1476 | stop processing: n_tokens = 1345, truncated = 0 2.59.980.688 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.852 2.59.980.750 I slot launch_slot_: id 2 | task 1578 | processing task, is_child = 0 3.00.473.993 I slot print_timing: id 1 | task 1466 | prompt eval time = 499.55 ms / 122 tokens ( 4.09 ms per token, 244.22 tokens per second) 3.00.473.995 I slot print_timing: id 1 | task 1466 | eval time = 7112.14 ms / 109 tokens ( 65.85 ms per token, 15.19 tokens per second) 3.00.473.996 I slot print_timing: id 1 | task 1466 | total time = 7611.69 ms / 231 tokens 3.00.474.010 I slot print_timing: id 1 | task 1466 | graphs reused = 1081 3.00.474.014 I slot print_timing: id 1 | task 1466 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.474.059 I slot release: id 1 | task 1466 | stop processing: n_tokens = 1355, truncated = 0 3.00.530.210 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 3.00.530.242 I slot launch_slot_: id 1 | task 1582 | processing task, is_child = 0 3.01.826.022 I slot print_timing: id 0 | task 1496 | n_gen = 100, tg = 15.80 t/s, tg_3s = 15.96 t/s 3.02.249.108 I slot print_timing: id 3 | task 1549 | prompt eval time = 420.14 ms / 86 tokens ( 4.89 ms per token, 204.70 tokens per second) 3.02.249.123 I slot print_timing: id 3 | task 1549 | eval time = 3647.34 ms / 56 tokens ( 66.32 ms per token, 15.08 tokens per second) 3.02.249.125 I slot print_timing: id 3 | task 1549 | total time = 4067.48 ms / 142 tokens 3.02.249.126 I slot print_timing: id 3 | task 1549 | graphs reused = 1104 3.02.249.127 I slot print_timing: id 3 | task 1549 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.249.244 I slot release: id 3 | task 1549 | stop processing: n_tokens = 1266, truncated = 0 3.02.299.053 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.905 3.02.299.110 I slot launch_slot_: id 3 | task 1610 | processing task, is_child = 0 3.04.149.080 I slot print_timing: id 0 | task 1496 | prompt eval time = 453.02 ms / 111 tokens ( 4.08 ms per token, 245.02 tokens per second) 3.04.149.088 I slot print_timing: id 0 | task 1496 | eval time = 8588.20 ms / 138 tokens ( 62.69 ms per token, 15.95 tokens per second) 3.04.149.089 I slot print_timing: id 0 | task 1496 | total time = 9041.22 ms / 249 tokens 3.04.149.090 I slot print_timing: id 0 | task 1496 | graphs reused = 1130 3.04.149.091 I slot print_timing: id 0 | task 1496 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.149.189 I slot release: id 0 | task 1496 | stop processing: n_tokens = 1373, truncated = 0 3.04.199.939 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.835 3.04.199.994 I slot launch_slot_: id 0 | task 1641 | processing task, is_child = 0 3.06.704.055 I slot print_timing: id 2 | task 1578 | n_gen = 100, tg = 15.89 t/s, tg_3s = 16.05 t/s 3.06.860.961 I slot print_timing: id 1 | task 1582 | n_gen = 100, tg = 16.85 t/s, tg_3s = 17.02 t/s 3.07.123.400 I slot print_timing: id 2 | task 1578 | prompt eval time = 493.54 ms / 106 tokens ( 4.66 ms per token, 214.77 tokens per second) 3.07.123.406 I slot print_timing: id 2 | task 1578 | eval time = 6649.10 ms / 108 tokens ( 62.14 ms per token, 16.09 tokens per second) 3.07.123.408 I slot print_timing: id 2 | task 1578 | total time = 7142.64 ms / 214 tokens 3.07.123.408 I slot print_timing: id 2 | task 1578 | graphs reused = 1177 3.07.123.410 I slot print_timing: id 2 | task 1578 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.123.533 I slot release: id 2 | task 1578 | stop processing: n_tokens = 1338, truncated = 0 3.07.185.775 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.857 3.07.185.851 I slot launch_slot_: id 2 | task 1692 | processing task, is_child = 0 3.07.995.219 I slot print_timing: id 0 | task 1641 | prompt eval time = 468.64 ms / 121 tokens ( 3.87 ms per token, 258.19 tokens per second) 3.07.995.230 I slot print_timing: id 0 | task 1641 | eval time = 3326.57 ms / 57 tokens ( 59.40 ms per token, 16.83 tokens per second) 3.07.995.231 I slot print_timing: id 0 | task 1641 | total time = 3795.21 ms / 178 tokens 3.07.995.232 I slot print_timing: id 0 | task 1641 | graphs reused = 1182 3.07.995.233 I slot print_timing: id 0 | task 1641 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.995.343 I slot release: id 0 | task 1641 | stop processing: n_tokens = 1302, truncated = 0 3.08.045.621 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 3.08.045.676 I slot launch_slot_: id 0 | task 1702 | processing task, is_child = 0 3.08.461.783 I slot print_timing: id 1 | task 1582 | prompt eval time = 456.63 ms / 98 tokens ( 4.66 ms per token, 214.61 tokens per second) 3.08.461.789 I slot print_timing: id 1 | task 1582 | eval time = 7474.90 ms / 117 tokens ( 64.44 ms per token, 15.52 tokens per second) 3.08.461.789 I slot print_timing: id 1 | task 1582 | total time = 7931.53 ms / 215 tokens 3.08.461.790 I slot print_timing: id 1 | task 1582 | graphs reused = 1183 3.08.461.790 I slot print_timing: id 1 | task 1582 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.461.837 I slot release: id 1 | task 1582 | stop processing: n_tokens = 1339, truncated = 0 3.08.518.208 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.856 3.08.518.243 I slot launch_slot_: id 1 | task 1706 | processing task, is_child = 0 3.09.160.014 I slot print_timing: id 3 | task 1610 | prompt eval time = 425.58 ms / 91 tokens ( 4.68 ms per token, 213.83 tokens per second) 3.09.160.019 I slot print_timing: id 3 | task 1610 | eval time = 6435.32 ms / 95 tokens ( 68.46 ms per token, 14.61 tokens per second) 3.09.160.020 I slot print_timing: id 3 | task 1610 | total time = 6860.90 ms / 186 tokens 3.09.160.020 I slot print_timing: id 3 | task 1610 | graphs reused = 1184 3.09.160.020 I slot print_timing: id 3 | task 1610 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.160.066 I slot release: id 3 | task 1610 | stop processing: n_tokens = 1310, truncated = 0 3.09.205.852 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.875 3.09.205.890 I slot launch_slot_: id 3 | task 1712 | processing task, is_child = 0 3.12.575.340 I slot print_timing: id 2 | task 1692 | prompt eval time = 492.37 ms / 105 tokens ( 4.69 ms per token, 213.26 tokens per second) 3.12.575.349 I slot print_timing: id 2 | task 1692 | eval time = 4897.11 ms / 74 tokens ( 67.08 ms per token, 14.91 tokens per second) 3.12.575.350 I slot print_timing: id 2 | task 1692 | total time = 5389.47 ms / 179 tokens 3.12.575.351 I slot print_timing: id 2 | task 1692 | graphs reused = 1238 3.12.575.352 I slot print_timing: id 2 | task 1692 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.575.530 I slot release: id 2 | task 1692 | stop processing: n_tokens = 1303, truncated = 0 3.12.636.598 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.880 3.12.636.657 I slot launch_slot_: id 2 | task 1772 | processing task, is_child = 0 3.13.550.704 I slot print_timing: id 3 | task 1712 | prompt eval time = 467.09 ms / 110 tokens ( 4.25 ms per token, 235.50 tokens per second) 3.13.550.707 I slot print_timing: id 3 | task 1712 | eval time = 3877.71 ms / 67 tokens ( 58.75 ms per token, 17.02 tokens per second) 3.13.550.708 I slot print_timing: id 3 | task 1712 | total time = 4344.80 ms / 177 tokens 3.13.550.708 I slot print_timing: id 3 | task 1712 | graphs reused = 1244 3.13.550.708 I slot print_timing: id 3 | task 1712 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.550.756 I slot release: id 3 | task 1712 | stop processing: n_tokens = 1301, truncated = 0 3.13.596.289 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.881 3.13.596.322 I slot launch_slot_: id 3 | task 1783 | processing task, is_child = 0 3.14.118.169 I slot print_timing: id 0 | task 1702 | prompt eval time = 415.95 ms / 95 tokens ( 4.38 ms per token, 228.39 tokens per second) 3.14.118.174 I slot print_timing: id 0 | task 1702 | eval time = 5656.53 ms / 79 tokens ( 72.52 ms per token, 13.79 tokens per second) 3.14.118.174 I slot print_timing: id 0 | task 1702 | total time = 6072.48 ms / 174 tokens 3.14.118.175 I slot print_timing: id 0 | task 1702 | graphs reused = 1244 3.14.118.175 I slot print_timing: id 0 | task 1702 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.118.221 I slot release: id 0 | task 1702 | stop processing: n_tokens = 1298, truncated = 0 3.14.164.021 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.883 3.14.164.057 I slot launch_slot_: id 0 | task 1788 | processing task, is_child = 0 3.15.741.082 I slot print_timing: id 1 | task 1706 | n_gen = 100, tg = 14.80 t/s, tg_3s = 14.95 t/s 3.17.999.024 I slot print_timing: id 3 | task 1783 | prompt eval time = 468.50 ms / 115 tokens ( 4.07 ms per token, 245.46 tokens per second) 3.17.999.034 I slot print_timing: id 3 | task 1783 | eval time = 3934.18 ms / 69 tokens ( 57.86 ms per token, 17.28 tokens per second) 3.17.999.043 I slot print_timing: id 3 | task 1783 | total time = 4402.68 ms / 184 tokens 3.17.999.044 I slot print_timing: id 3 | task 1783 | graphs reused = 1308 3.17.999.045 I slot print_timing: id 3 | task 1783 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.999.211 I slot release: id 3 | task 1783 | stop processing: n_tokens = 1308, truncated = 0 3.18.049.264 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.876 3.18.049.327 I slot launch_slot_: id 3 | task 1856 | processing task, is_child = 0 3.18.775.259 I slot print_timing: id 1 | task 1706 | n_gen = 152, tg = 15.53 t/s, tg_3s = 17.14 t/s 3.18.930.399 I slot print_timing: id 1 | task 1706 | prompt eval time = 535.89 ms / 144 tokens ( 3.72 ms per token, 268.71 tokens per second) 3.18.930.401 I slot print_timing: id 1 | task 1706 | eval time = 9876.25 ms / 155 tokens ( 64.13 ms per token, 15.59 tokens per second) 3.18.930.402 I slot print_timing: id 1 | task 1706 | total time = 10412.15 ms / 299 tokens 3.18.930.402 I slot print_timing: id 1 | task 1706 | graphs reused = 1316 3.18.930.403 I slot print_timing: id 1 | task 1706 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.930.449 I slot release: id 1 | task 1706 | stop processing: n_tokens = 1423, truncated = 0 3.18.987.108 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.805 3.18.987.143 I slot launch_slot_: id 1 | task 1869 | processing task, is_child = 0 3.19.781.721 I slot print_timing: id 2 | task 1772 | n_gen = 100, tg = 15.01 t/s, tg_3s = 15.16 t/s 3.20.503.081 I slot print_timing: id 0 | task 1788 | n_gen = 100, tg = 16.89 t/s, tg_3s = 17.06 t/s 3.21.845.499 I slot print_timing: id 3 | task 1856 | prompt eval time = 415.22 ms / 81 tokens ( 5.13 ms per token, 195.08 tokens per second) 3.21.845.501 I slot print_timing: id 3 | task 1856 | eval time = 3380.94 ms / 59 tokens ( 58.29 ms per token, 17.15 tokens per second) 3.21.845.502 I slot print_timing: id 3 | task 1856 | total time = 3796.16 ms / 140 tokens 3.21.845.502 I slot print_timing: id 3 | task 1856 | graphs reused = 1361 3.21.845.503 I slot print_timing: id 3 | task 1856 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.845.573 I slot release: id 3 | task 1856 | stop processing: n_tokens = 1264, truncated = 0 3.21.891.506 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 3.21.891.541 I slot launch_slot_: id 3 | task 1919 | processing task, is_child = 0 3.22.787.311 I slot print_timing: id 2 | task 1772 | n_gen = 151, tg = 15.62 t/s, tg_3s = 16.97 t/s 3.23.509.629 I slot print_timing: id 0 | task 1788 | n_gen = 151, tg = 16.91 t/s, tg_3s = 16.96 t/s 3.23.871.643 I slot print_timing: id 1 | task 1869 | prompt eval time = 483.32 ms / 104 tokens ( 4.65 ms per token, 215.18 tokens per second) 3.23.871.647 I slot print_timing: id 1 | task 1869 | eval time = 4401.17 ms / 79 tokens ( 56.43 ms per token, 17.72 tokens per second) 3.23.871.648 I slot print_timing: id 1 | task 1869 | total time = 4884.49 ms / 183 tokens 3.23.871.648 I slot print_timing: id 1 | task 1869 | graphs reused = 1389 3.23.871.649 I slot print_timing: id 1 | task 1869 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.871.694 I slot release: id 1 | task 1869 | stop processing: n_tokens = 1307, truncated = 0 3.23.928.525 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.877 3.23.928.558 I slot launch_slot_: id 1 | task 1952 | processing task, is_child = 0 3.25.718.901 I slot print_timing: id 2 | task 1772 | prompt eval time = 550.26 ms / 158 tokens ( 3.48 ms per token, 287.14 tokens per second) 3.25.718.913 I slot print_timing: id 2 | task 1772 | eval time = 12531.97 ms / 200 tokens ( 62.97 ms per token, 15.88 tokens per second) 3.25.718.915 I slot print_timing: id 2 | task 1772 | total time = 13082.23 ms / 358 tokens 3.25.718.916 I slot print_timing: id 2 | task 1772 | graphs reused = 1413 3.25.718.917 I slot print_timing: id 2 | task 1772 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.719.020 I slot release: id 2 | task 1772 | stop processing: n_tokens = 1482, truncated = 0 3.25.779.309 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.773 3.25.779.370 I slot launch_slot_: id 2 | task 1981 | processing task, is_child = 0 3.26.344.110 I slot print_timing: id 0 | task 1788 | prompt eval time = 476.45 ms / 128 tokens ( 3.72 ms per token, 268.66 tokens per second) 3.26.344.112 I slot print_timing: id 0 | task 1788 | eval time = 11703.60 ms / 190 tokens ( 61.92 ms per token, 16.15 tokens per second) 3.26.344.113 I slot print_timing: id 0 | task 1788 | total time = 12180.04 ms / 318 tokens 3.26.344.113 I slot print_timing: id 0 | task 1788 | graphs reused = 1413 3.26.344.114 I slot print_timing: id 0 | task 1788 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.344.165 I slot release: id 0 | task 1788 | stop processing: n_tokens = 1442, truncated = 0 3.26.390.261 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.795 3.26.390.298 I slot launch_slot_: id 0 | task 1986 | processing task, is_child = 0 3.28.226.263 I slot print_timing: id 3 | task 1919 | prompt eval time = 480.57 ms / 125 tokens ( 3.84 ms per token, 260.11 tokens per second) 3.28.226.272 I slot print_timing: id 3 | task 1919 | eval time = 5854.14 ms / 91 tokens ( 65.05 ms per token, 15.37 tokens per second) 3.28.226.273 I slot print_timing: id 3 | task 1919 | total time = 6334.71 ms / 216 tokens 3.28.226.274 I slot print_timing: id 3 | task 1919 | graphs reused = 1439 3.28.226.275 I slot print_timing: id 3 | task 1919 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.226.435 I slot release: id 3 | task 1919 | stop processing: n_tokens = 1340, truncated = 0 3.28.276.261 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.855 3.28.276.319 I slot launch_slot_: id 3 | task 2016 | processing task, is_child = 0 3.30.730.392 I slot print_timing: id 1 | task 1952 | n_gen = 100, tg = 15.67 t/s, tg_3s = 15.83 t/s 3.30.994.582 I slot print_timing: id 1 | task 1952 | prompt eval time = 482.86 ms / 103 tokens ( 4.69 ms per token, 213.31 tokens per second) 3.30.994.588 I slot print_timing: id 1 | task 1952 | eval time = 6583.16 ms / 105 tokens ( 63.30 ms per token, 15.80 tokens per second) 3.30.994.590 I slot print_timing: id 1 | task 1952 | total time = 7066.01 ms / 208 tokens 3.30.994.591 I slot print_timing: id 1 | task 1952 | graphs reused = 1481 3.30.994.597 I slot print_timing: id 1 | task 1952 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.994.689 I slot release: id 1 | task 1952 | stop processing: n_tokens = 1332, truncated = 0 3.31.055.649 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.860 3.31.055.722 I slot launch_slot_: id 1 | task 2063 | processing task, is_child = 0 3.32.037.095 I slot print_timing: id 2 | task 1981 | prompt eval time = 510.50 ms / 126 tokens ( 4.05 ms per token, 246.81 tokens per second) 3.32.037.100 I slot print_timing: id 2 | task 1981 | eval time = 5747.21 ms / 90 tokens ( 64.58 ms per token, 15.49 tokens per second) 3.32.037.101 I slot print_timing: id 2 | task 1981 | total time = 6257.72 ms / 216 tokens 3.32.037.101 I slot print_timing: id 2 | task 1981 | graphs reused = 1490 3.32.037.102 I slot print_timing: id 2 | task 1981 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.037.165 I slot release: id 2 | task 1981 | stop processing: n_tokens = 1340, truncated = 0 3.32.094.353 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.855 3.32.094.393 I slot launch_slot_: id 2 | task 2077 | processing task, is_child = 0 3.33.245.268 I slot print_timing: id 0 | task 1986 | n_gen = 100, tg = 15.50 t/s, tg_3s = 15.65 t/s 3.33.722.747 I slot print_timing: id 3 | task 2016 | prompt eval time = 460.41 ms / 108 tokens ( 4.26 ms per token, 234.57 tokens per second) 3.33.722.753 I slot print_timing: id 3 | task 2016 | eval time = 4986.00 ms / 80 tokens ( 63.11 ms per token, 15.84 tokens per second) 3.33.722.754 I slot print_timing: id 3 | task 2016 | total time = 5446.42 ms / 188 tokens 3.33.722.755 I slot print_timing: id 3 | task 2016 | graphs reused = 1509 3.33.722.756 I slot print_timing: id 3 | task 2016 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.722.848 I slot release: id 3 | task 2016 | stop processing: n_tokens = 1312, truncated = 0 3.33.772.051 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.873 3.33.772.120 I slot launch_slot_: id 3 | task 2101 | processing task, is_child = 0 3.36.279.420 I slot print_timing: id 0 | task 1986 | n_gen = 152, tg = 16.02 t/s, tg_3s = 17.14 t/s 3.36.332.247 I slot print_timing: id 2 | task 2077 | prompt eval time = 581.26 ms / 171 tokens ( 3.40 ms per token, 294.19 tokens per second) 3.36.332.255 I slot print_timing: id 2 | task 2077 | eval time = 3656.59 ms / 65 tokens ( 57.13 ms per token, 17.50 tokens per second) 3.36.332.256 I slot print_timing: id 2 | task 2077 | total time = 4237.85 ms / 236 tokens 3.36.332.257 I slot print_timing: id 2 | task 2077 | graphs reused = 1549 3.36.332.258 I slot print_timing: id 2 | task 2077 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.332.342 I slot release: id 2 | task 2077 | stop processing: n_tokens = 1360, truncated = 0 3.36.393.207 I slot print_timing: id 1 | task 2063 | prompt eval time = 463.50 ms / 100 tokens ( 4.63 ms per token, 215.75 tokens per second) 3.36.393.213 I slot print_timing: id 1 | task 2063 | eval time = 4873.98 ms / 79 tokens ( 62.49 ms per token, 16.00 tokens per second) 3.36.393.216 I slot print_timing: id 1 | task 2063 | total time = 5337.48 ms / 179 tokens 3.36.393.217 I slot print_timing: id 1 | task 2063 | graphs reused = 1549 3.36.393.218 I slot print_timing: id 1 | task 2063 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.393.314 I slot release: id 1 | task 2063 | stop processing: n_tokens = 1303, truncated = 0 3.36.393.701 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.949 (> 0.100 thold), f_keep = 0.880 3.36.393.780 I slot launch_slot_: id 1 | task 2146 | processing task, is_child = 0 3.36.393.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.010 MiB) 3.36.393.985 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.166 MiB) 3.36.393.995 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 3.36.991.014 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.843 3.36.991.073 I slot launch_slot_: id 2 | task 2147 | processing task, is_child = 0 3.37.762.690 I slot print_timing: id 0 | task 1986 | prompt eval time = 466.06 ms / 125 tokens ( 3.73 ms per token, 268.20 tokens per second) 3.37.762.695 I slot print_timing: id 0 | task 1986 | eval time = 10906.32 ms / 156 tokens ( 70.36 ms per token, 14.21 tokens per second) 3.37.762.695 I slot print_timing: id 0 | task 1986 | total time = 11372.38 ms / 281 tokens 3.37.762.695 I slot print_timing: id 0 | task 1986 | graphs reused = 1549 3.37.762.697 I slot print_timing: id 0 | task 1986 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.762.746 I slot release: id 0 | task 1986 | stop processing: n_tokens = 1405, truncated = 0 3.37.809.189 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.816 3.37.809.225 I slot launch_slot_: id 0 | task 2151 | processing task, is_child = 0 3.39.387.693 I slot print_timing: id 3 | task 2101 | prompt eval time = 423.10 ms / 89 tokens ( 4.75 ms per token, 210.35 tokens per second) 3.39.387.701 I slot print_timing: id 3 | task 2101 | eval time = 5192.47 ms / 70 tokens ( 75.25 ms per token, 13.29 tokens per second) 3.39.387.702 I slot print_timing: id 3 | task 2101 | total time = 5615.56 ms / 159 tokens 3.39.387.703 I slot print_timing: id 3 | task 2101 | graphs reused = 1570 3.39.387.704 I slot print_timing: id 3 | task 2101 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.387.805 I slot release: id 3 | task 2101 | stop processing: n_tokens = 1283, truncated = 0 3.39.436.548 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.893 3.39.436.614 I slot launch_slot_: id 3 | task 2177 | processing task, is_child = 0 3.40.936.588 I slot print_timing: id 2 | task 2147 | prompt eval time = 768.89 ms / 114 tokens ( 6.74 ms per token, 148.27 tokens per second) 3.40.936.592 I slot print_timing: id 2 | task 2147 | eval time = 3173.36 ms / 49 tokens ( 66.11 ms per token, 15.13 tokens per second) 3.40.936.592 I slot print_timing: id 2 | task 2147 | total time = 3942.25 ms / 163 tokens 3.40.936.593 I slot print_timing: id 2 | task 2147 | graphs reused = 1588 3.40.936.593 I slot print_timing: id 2 | task 2147 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.936.640 I slot release: id 2 | task 2147 | stop processing: n_tokens = 1287, truncated = 0 3.40.993.193 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.890 3.40.993.233 I slot launch_slot_: id 2 | task 2201 | processing task, is_child = 0 3.41.710.441 I slot print_timing: id 1 | task 2146 | prompt eval time = 771.91 ms / 82 tokens ( 9.41 ms per token, 106.23 tokens per second) 3.41.710.445 I slot print_timing: id 1 | task 2146 | eval time = 3947.45 ms / 57 tokens ( 70.49 ms per token, 14.19 tokens per second) 3.41.710.446 I slot print_timing: id 1 | task 2146 | total time = 4719.36 ms / 139 tokens 3.41.710.447 I slot print_timing: id 1 | task 2146 | graphs reused = 1592 3.41.710.447 I slot print_timing: id 1 | task 2146 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.710.495 I slot release: id 1 | task 2146 | stop processing: n_tokens = 1263, truncated = 0 3.41.767.377 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.907 3.41.767.414 I slot launch_slot_: id 1 | task 2210 | processing task, is_child = 0 3.42.730.028 I slot print_timing: id 0 | task 2151 | prompt eval time = 417.27 ms / 98 tokens ( 4.26 ms per token, 234.86 tokens per second) 3.42.730.034 I slot print_timing: id 0 | task 2151 | eval time = 4503.53 ms / 66 tokens ( 69.29 ms per token, 14.43 tokens per second) 3.42.730.034 I slot print_timing: id 0 | task 2151 | total time = 4920.80 ms / 164 tokens 3.42.730.035 I slot print_timing: id 0 | task 2151 | graphs reused = 1599 3.42.730.035 I slot print_timing: id 0 | task 2151 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.730.087 I slot release: id 0 | task 2151 | stop processing: n_tokens = 1288, truncated = 0 3.42.776.118 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.890 3.42.776.151 I slot launch_slot_: id 0 | task 2223 | processing task, is_child = 0 3.44.985.049 I slot print_timing: id 2 | task 2201 | prompt eval time = 458.25 ms / 97 tokens ( 4.72 ms per token, 211.68 tokens per second) 3.44.985.057 I slot print_timing: id 2 | task 2201 | eval time = 3533.55 ms / 54 tokens ( 66.67 ms per token, 15.00 tokens per second) 3.44.985.059 I slot print_timing: id 2 | task 2201 | total time = 3991.80 ms / 151 tokens 3.44.985.060 I slot print_timing: id 2 | task 2201 | graphs reused = 1631 3.44.985.061 I slot print_timing: id 2 | task 2201 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.985.162 I slot release: id 2 | task 2201 | stop processing: n_tokens = 1275, truncated = 0 3.45.046.588 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.899 3.45.046.647 I slot launch_slot_: id 2 | task 2260 | processing task, is_child = 0 3.46.638.969 I slot print_timing: id 3 | task 2177 | n_gen = 100, tg = 14.69 t/s, tg_3s = 14.84 t/s 3.47.533.568 I slot print_timing: id 1 | task 2210 | prompt eval time = 494.49 ms / 113 tokens ( 4.38 ms per token, 228.52 tokens per second) 3.47.533.577 I slot print_timing: id 1 | task 2210 | eval time = 5271.66 ms / 86 tokens ( 62.02 ms per token, 16.12 tokens per second) 3.47.533.579 I slot print_timing: id 1 | task 2210 | total time = 5766.15 ms / 199 tokens 3.47.533.580 I slot print_timing: id 1 | task 2210 | graphs reused = 1667 3.47.533.581 I slot print_timing: id 1 | task 2210 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.533.675 I slot release: id 1 | task 2210 | stop processing: n_tokens = 1323, truncated = 0 3.47.595.097 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.866 3.47.595.165 I slot launch_slot_: id 1 | task 2301 | processing task, is_child = 0 3.48.473.612 I slot print_timing: id 0 | task 2223 | prompt eval time = 458.96 ms / 119 tokens ( 3.86 ms per token, 259.28 tokens per second) 3.48.473.619 I slot print_timing: id 0 | task 2223 | eval time = 5238.49 ms / 84 tokens ( 63.11 ms per token, 15.84 tokens per second) 3.48.473.620 I slot print_timing: id 0 | task 2223 | total time = 5697.45 ms / 203 tokens 3.48.473.621 I slot print_timing: id 0 | task 2223 | graphs reused = 1673 3.48.473.621 I slot print_timing: id 0 | task 2223 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.473.688 I slot release: id 0 | task 2223 | stop processing: n_tokens = 1327, truncated = 0 3.48.522.129 I slot print_timing: id 3 | task 2177 | prompt eval time = 465.08 ms / 109 tokens ( 4.27 ms per token, 234.37 tokens per second) 3.48.522.134 I slot print_timing: id 3 | task 2177 | eval time = 8620.42 ms / 128 tokens ( 67.88 ms per token, 14.73 tokens per second) 3.48.522.135 I slot print_timing: id 3 | task 2177 | total time = 9085.50 ms / 237 tokens 3.48.522.135 I slot print_timing: id 3 | task 2177 | graphs reused = 1673 3.48.522.136 I slot print_timing: id 3 | task 2177 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.522.203 I slot release: id 3 | task 2177 | stop processing: n_tokens = 1361, truncated = 0 3.48.522.217 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.864 3.48.522.265 I slot launch_slot_: id 0 | task 2312 | processing task, is_child = 0 3.48.522.392 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 3.48.522.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.130 MiB) 3.48.522.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 3.48.931.533 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.842 3.48.931.663 I slot launch_slot_: id 3 | task 2313 | processing task, is_child = 0 3.52.270.470 I slot print_timing: id 2 | task 2260 | n_gen = 100, tg = 14.81 t/s, tg_3s = 14.96 t/s 3.53.583.694 I slot print_timing: id 3 | task 2313 | prompt eval time = 776.41 ms / 95 tokens ( 8.17 ms per token, 122.36 tokens per second) 3.53.583.703 I slot print_timing: id 3 | task 2313 | eval time = 3872.29 ms / 75 tokens ( 52.33 ms per token, 19.11 tokens per second) 3.53.583.705 I slot print_timing: id 3 | task 2313 | total time = 4648.70 ms / 170 tokens 3.53.583.706 I slot print_timing: id 3 | task 2313 | graphs reused = 1746 3.53.583.707 I slot print_timing: id 3 | task 2313 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.583.846 I slot release: id 3 | task 2313 | stop processing: n_tokens = 1294, truncated = 0 3.53.632.834 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.886 3.53.632.899 I slot launch_slot_: id 3 | task 2391 | processing task, is_child = 0 3.54.429.817 I slot print_timing: id 2 | task 2260 | prompt eval time = 537.10 ms / 134 tokens ( 4.01 ms per token, 249.49 tokens per second) 3.54.429.820 I slot print_timing: id 2 | task 2260 | eval time = 8846.06 ms / 135 tokens ( 66.02 ms per token, 15.15 tokens per second) 3.54.429.821 I slot print_timing: id 2 | task 2260 | total time = 9383.16 ms / 269 tokens 3.54.429.821 I slot print_timing: id 2 | task 2260 | graphs reused = 1752 3.54.429.822 I slot print_timing: id 2 | task 2260 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.429.899 I slot release: id 2 | task 2260 | stop processing: n_tokens = 1393, truncated = 0 3.54.486.448 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.823 3.54.486.483 I slot launch_slot_: id 2 | task 2402 | processing task, is_child = 0 3.54.998.604 I slot print_timing: id 0 | task 2312 | prompt eval time = 779.16 ms / 109 tokens ( 7.15 ms per token, 139.89 tokens per second) 3.54.998.606 I slot print_timing: id 0 | task 2312 | eval time = 5287.76 ms / 88 tokens ( 60.78 ms per token, 16.45 tokens per second) 3.54.998.607 I slot print_timing: id 0 | task 2312 | total time = 6066.93 ms / 197 tokens 3.54.998.607 I slot print_timing: id 0 | task 2312 | graphs reused = 1752 3.54.998.607 I slot print_timing: id 0 | task 2312 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.998.652 I slot release: id 0 | task 2312 | stop processing: n_tokens = 1321, truncated = 0 3.55.044.812 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.868 3.55.044.854 I slot launch_slot_: id 0 | task 2406 | processing task, is_child = 0 3.55.492.943 I slot print_timing: id 1 | task 2301 | n_gen = 100, tg = 13.40 t/s, tg_3s = 13.53 t/s 3.57.821.694 I slot print_timing: id 3 | task 2391 | prompt eval time = 433.87 ms / 96 tokens ( 4.52 ms per token, 221.26 tokens per second) 3.57.821.704 I slot print_timing: id 3 | task 2391 | eval time = 3754.91 ms / 57 tokens ( 67.05 ms per token, 14.91 tokens per second) 3.57.821.705 I slot print_timing: id 3 | task 2391 | total time = 4188.78 ms / 153 tokens 3.57.821.706 I slot print_timing: id 3 | task 2391 | graphs reused = 1795 3.57.821.707 I slot print_timing: id 3 | task 2391 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.821.825 I slot release: id 3 | task 2391 | stop processing: n_tokens = 1277, truncated = 0 3.57.871.320 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.897 3.57.871.373 I slot launch_slot_: id 3 | task 2453 | processing task, is_child = 0 3.58.501.991 I slot print_timing: id 1 | task 2301 | n_gen = 150, tg = 14.33 t/s, tg_3s = 16.62 t/s 3.59.856.694 I slot print_timing: id 1 | task 2301 | prompt eval time = 509.23 ms / 112 tokens ( 4.55 ms per token, 219.94 tokens per second) 3.59.856.699 I slot print_timing: id 1 | task 2301 | eval time = 11752.29 ms / 176 tokens ( 67.16 ms per token, 14.89 tokens per second) 3.59.856.700 I slot print_timing: id 1 | task 2301 | total time = 12261.52 ms / 288 tokens 3.59.856.701 I slot print_timing: id 1 | task 2301 | graphs reused = 1823 3.59.856.702 I slot print_timing: id 1 | task 2301 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.856.797 I slot release: id 1 | task 2301 | stop processing: n_tokens = 1412, truncated = 0 3.59.917.680 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.812 3.59.917.823 I slot launch_slot_: id 1 | task 2486 | processing task, is_child = 0 4.01.354.150 I slot print_timing: id 2 | task 2402 | n_gen = 100, tg = 15.58 t/s, tg_3s = 15.74 t/s 4.01.519.486 I slot print_timing: id 0 | task 2406 | n_gen = 100, tg = 16.68 t/s, tg_3s = 16.85 t/s 4.01.888.776 I slot print_timing: id 0 | task 2406 | prompt eval time = 539.48 ms / 166 tokens ( 3.25 ms per token, 307.70 tokens per second) 4.01.888.781 I slot print_timing: id 0 | task 2406 | eval time = 6304.43 ms / 107 tokens ( 59.48 ms per token, 16.81 tokens per second) 4.01.888.782 I slot print_timing: id 0 | task 2406 | total time = 6843.91 ms / 273 tokens 4.01.888.786 I slot print_timing: id 0 | task 2406 | graphs reused = 1850 4.01.888.787 I slot print_timing: id 0 | task 2406 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.890.763 I slot release: id 0 | task 2406 | stop processing: n_tokens = 1397, truncated = 0 4.01.940.700 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.820 4.01.940.766 I slot launch_slot_: id 0 | task 2518 | processing task, is_child = 0 4.03.013.009 I slot print_timing: id 2 | task 2402 | prompt eval time = 512.50 ms / 122 tokens ( 4.20 ms per token, 238.05 tokens per second) 4.03.013.013 I slot print_timing: id 2 | task 2402 | eval time = 8014.02 ms / 125 tokens ( 64.63 ms per token, 15.47 tokens per second) 4.03.013.014 I slot print_timing: id 2 | task 2402 | total time = 8526.52 ms / 247 tokens 4.03.013.014 I slot print_timing: id 2 | task 2402 | graphs reused = 1862 4.03.013.014 I slot print_timing: id 2 | task 2402 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.013.058 I slot release: id 2 | task 2402 | stop processing: n_tokens = 1371, truncated = 0 4.03.069.655 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.836 4.03.069.689 I slot launch_slot_: id 2 | task 2534 | processing task, is_child = 0 4.04.689.167 I slot print_timing: id 3 | task 2453 | n_gen = 100, tg = 15.61 t/s, tg_3s = 15.76 t/s 4.05.582.967 I slot print_timing: id 1 | task 2486 | prompt eval time = 502.73 ms / 104 tokens ( 4.83 ms per token, 206.87 tokens per second) 4.05.582.973 I slot print_timing: id 1 | task 2486 | eval time = 5162.40 ms / 85 tokens ( 61.46 ms per token, 16.27 tokens per second) 4.05.582.974 I slot print_timing: id 1 | task 2486 | total time = 5665.13 ms / 189 tokens 4.05.582.975 I slot print_timing: id 1 | task 2486 | graphs reused = 1899 4.05.582.976 I slot print_timing: id 1 | task 2486 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.583.066 I slot release: id 1 | task 2486 | stop processing: n_tokens = 1313, truncated = 0 4.05.643.691 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.873 4.05.643.762 I slot launch_slot_: id 1 | task 2576 | processing task, is_child = 0 4.06.554.509 I slot print_timing: id 3 | task 2453 | prompt eval time = 474.41 ms / 117 tokens ( 4.05 ms per token, 246.62 tokens per second) 4.06.554.514 I slot print_timing: id 3 | task 2453 | eval time = 8208.72 ms / 128 tokens ( 64.64 ms per token, 15.47 tokens per second) 4.06.554.516 I slot print_timing: id 3 | task 2453 | total time = 8683.12 ms / 245 tokens 4.06.554.516 I slot print_timing: id 3 | task 2453 | graphs reused = 1906 4.06.554.517 I slot print_timing: id 3 | task 2453 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.554.568 I slot release: id 3 | task 2453 | stop processing: n_tokens = 1369, truncated = 0 4.06.600.485 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.837 4.06.600.516 I slot launch_slot_: id 3 | task 2588 | processing task, is_child = 0 4.08.756.747 I slot print_timing: id 0 | task 2518 | n_gen = 100, tg = 15.55 t/s, tg_3s = 15.71 t/s 4.09.544.636 I slot print_timing: id 2 | task 2534 | n_gen = 100, tg = 16.60 t/s, tg_3s = 16.76 t/s 4.09.806.549 I slot print_timing: id 0 | task 2518 | prompt eval time = 450.22 ms / 108 tokens ( 4.17 ms per token, 239.88 tokens per second) 4.09.806.558 I slot print_timing: id 0 | task 2518 | eval time = 7415.55 ms / 120 tokens ( 62.32 ms per token, 16.05 tokens per second) 4.09.806.559 I slot print_timing: id 0 | task 2518 | total time = 7865.77 ms / 228 tokens 4.09.806.560 I slot print_timing: id 0 | task 2518 | graphs reused = 1957 4.09.806.561 I slot print_timing: id 0 | task 2518 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.806.660 I slot release: id 0 | task 2518 | stop processing: n_tokens = 1352, truncated = 0 4.09.857.866 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.848 4.09.857.924 I slot launch_slot_: id 0 | task 2644 | processing task, is_child = 0 4.11.514.742 I slot print_timing: id 2 | task 2534 | prompt eval time = 509.68 ms / 133 tokens ( 3.83 ms per token, 260.95 tokens per second) 4.11.514.748 I slot print_timing: id 2 | task 2534 | eval time = 7935.36 ms / 131 tokens ( 61.04 ms per token, 16.38 tokens per second) 4.11.514.749 I slot print_timing: id 2 | task 2534 | total time = 8445.04 ms / 264 tokens 4.11.514.750 I slot print_timing: id 2 | task 2534 | graphs reused = 1980 4.11.514.751 I slot print_timing: id 2 | task 2534 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.514.859 I slot release: id 2 | task 2534 | stop processing: n_tokens = 1388, truncated = 0 4.11.576.065 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.826 4.11.576.121 I slot launch_slot_: id 2 | task 2671 | processing task, is_child = 0 4.12.184.237 I slot print_timing: id 3 | task 2588 | prompt eval time = 471.21 ms / 116 tokens ( 4.06 ms per token, 246.18 tokens per second) 4.12.184.241 I slot print_timing: id 3 | task 2588 | eval time = 5112.51 ms / 84 tokens ( 61.60 ms per token, 16.23 tokens per second) 4.12.184.241 I slot print_timing: id 3 | task 2588 | total time = 5583.71 ms / 200 tokens 4.12.184.242 I slot print_timing: id 3 | task 2588 | graphs reused = 1981 4.12.184.242 I slot print_timing: id 3 | task 2588 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.184.302 I slot release: id 3 | task 2588 | stop processing: n_tokens = 1324, truncated = 0 4.12.229.565 I slot print_timing: id 1 | task 2576 | prompt eval time = 495.93 ms / 112 tokens ( 4.43 ms per token, 225.84 tokens per second) 4.12.229.569 I slot print_timing: id 1 | task 2576 | eval time = 6089.87 ms / 96 tokens ( 64.10 ms per token, 15.60 tokens per second) 4.12.229.569 I slot print_timing: id 1 | task 2576 | total time = 6585.79 ms / 208 tokens 4.12.229.570 I slot print_timing: id 1 | task 2576 | graphs reused = 1981 4.12.229.570 I slot print_timing: id 1 | task 2576 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.229.612 I slot release: id 1 | task 2576 | stop processing: n_tokens = 1332, truncated = 0 4.12.229.768 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.860 4.12.229.805 I slot launch_slot_: id 1 | task 2677 | processing task, is_child = 0 4.12.229.880 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 4.12.229.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.149 MiB) 4.12.945.560 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.866 4.12.945.616 I slot launch_slot_: id 3 | task 2678 | processing task, is_child = 0 4.17.191.331 I slot print_timing: id 3 | task 2678 | prompt eval time = 856.96 ms / 120 tokens ( 7.14 ms per token, 140.03 tokens per second) 4.17.191.341 I slot print_timing: id 3 | task 2678 | eval time = 3385.50 ms / 65 tokens ( 52.90 ms per token, 18.90 tokens per second) 4.17.191.345 I slot print_timing: id 3 | task 2678 | total time = 4242.45 ms / 185 tokens 4.17.191.346 I slot print_timing: id 3 | task 2678 | graphs reused = 2043 4.17.191.347 I slot print_timing: id 3 | task 2678 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.191.506 I slot release: id 3 | task 2678 | stop processing: n_tokens = 1309, truncated = 0 4.17.241.486 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.875 4.17.241.548 I slot launch_slot_: id 3 | task 2746 | processing task, is_child = 0 4.17.763.861 I slot print_timing: id 0 | task 2644 | n_gen = 100, tg = 13.30 t/s, tg_3s = 13.44 t/s 4.19.105.008 I slot print_timing: id 2 | task 2671 | n_gen = 100, tg = 14.09 t/s, tg_3s = 14.23 t/s 4.19.156.673 I slot print_timing: id 2 | task 2671 | prompt eval time = 502.96 ms / 119 tokens ( 4.23 ms per token, 236.60 tokens per second) 4.19.156.679 I slot print_timing: id 2 | task 2671 | eval time = 7077.59 ms / 101 tokens ( 70.78 ms per token, 14.13 tokens per second) 4.19.156.680 I slot print_timing: id 2 | task 2671 | total time = 7580.55 ms / 220 tokens 4.19.156.680 I slot print_timing: id 2 | task 2671 | graphs reused = 2070 4.19.156.681 I slot print_timing: id 2 | task 2671 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.156.756 I slot release: id 2 | task 2671 | stop processing: n_tokens = 1344, truncated = 0 4.19.213.007 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.853 4.19.213.041 I slot launch_slot_: id 2 | task 2778 | processing task, is_child = 0 4.19.561.308 I slot print_timing: id 1 | task 2677 | prompt eval time = 859.68 ms / 103 tokens ( 8.35 ms per token, 119.81 tokens per second) 4.19.561.310 I slot print_timing: id 1 | task 2677 | eval time = 5756.00 ms / 98 tokens ( 59.34 ms per token, 16.85 tokens per second) 4.19.561.311 I slot print_timing: id 1 | task 2677 | total time = 6615.68 ms / 201 tokens 4.19.561.311 I slot print_timing: id 1 | task 2677 | graphs reused = 2070 4.19.561.312 I slot print_timing: id 1 | task 2677 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.561.357 I slot release: id 1 | task 2677 | stop processing: n_tokens = 1325, truncated = 0 4.19.650.619 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.865 4.19.650.651 I slot launch_slot_: id 1 | task 2781 | processing task, is_child = 0 4.20.783.312 I slot print_timing: id 0 | task 2644 | n_gen = 145, tg = 13.77 t/s, tg_3s = 14.90 t/s 4.21.607.947 I slot print_timing: id 0 | task 2644 | prompt eval time = 465.04 ms / 119 tokens ( 3.91 ms per token, 255.89 tokens per second) 4.21.607.952 I slot print_timing: id 0 | task 2644 | eval time = 11284.98 ms / 161 tokens ( 70.53 ms per token, 14.18 tokens per second) 4.21.607.953 I slot print_timing: id 0 | task 2644 | total time = 11750.02 ms / 280 tokens 4.21.607.953 I slot print_timing: id 0 | task 2644 | graphs reused = 2098 4.21.607.954 I slot print_timing: id 0 | task 2644 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.608.009 I slot release: id 0 | task 2644 | stop processing: n_tokens = 1404, truncated = 0 4.21.654.790 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.816 4.21.654.825 I slot launch_slot_: id 0 | task 2814 | processing task, is_child = 0 4.22.769.142 I slot print_timing: id 3 | task 2746 | prompt eval time = 469.29 ms / 108 tokens ( 4.35 ms per token, 230.14 tokens per second) 4.22.769.146 I slot print_timing: id 3 | task 2746 | eval time = 5058.30 ms / 77 tokens ( 66.56 ms per token, 15.02 tokens per second) 4.22.769.147 I slot print_timing: id 3 | task 2746 | total time = 5527.59 ms / 185 tokens 4.22.769.147 I slot print_timing: id 3 | task 2746 | graphs reused = 2109 4.22.769.148 I slot print_timing: id 3 | task 2746 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.769.193 I slot release: id 3 | task 2746 | stop processing: n_tokens = 1309, truncated = 0 4.22.814.981 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.875 4.22.815.014 I slot launch_slot_: id 3 | task 2829 | processing task, is_child = 0 4.24.319.805 I slot print_timing: id 2 | task 2778 | prompt eval time = 437.43 ms / 97 tokens ( 4.51 ms per token, 221.75 tokens per second) 4.24.319.819 I slot print_timing: id 2 | task 2778 | eval time = 4669.32 ms / 69 tokens ( 68.67 ms per token, 14.56 tokens per second) 4.24.319.820 I slot print_timing: id 2 | task 2778 | total time = 5106.75 ms / 166 tokens 4.24.319.821 I slot print_timing: id 2 | task 2778 | graphs reused = 2128 4.24.319.822 I slot print_timing: id 2 | task 2778 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.319.980 I slot release: id 2 | task 2778 | stop processing: n_tokens = 1290, truncated = 0 4.24.390.114 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.888 4.24.390.173 I slot launch_slot_: id 2 | task 2853 | processing task, is_child = 0 4.25.095.688 I slot print_timing: id 1 | task 2781 | prompt eval time = 461.08 ms / 100 tokens ( 4.61 ms per token, 216.88 tokens per second) 4.25.095.694 I slot print_timing: id 1 | task 2781 | eval time = 4983.95 ms / 74 tokens ( 68.27 ms per token, 14.65 tokens per second) 4.25.095.694 I slot print_timing: id 1 | task 2781 | total time = 5445.03 ms / 174 tokens 4.25.095.695 I slot print_timing: id 1 | task 2781 | graphs reused = 2131 4.25.095.695 I slot print_timing: id 1 | task 2781 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.095.741 I slot release: id 1 | task 2781 | stop processing: n_tokens = 1298, truncated = 0 4.25.153.282 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.883 4.25.153.333 I slot launch_slot_: id 1 | task 2861 | processing task, is_child = 0 4.28.518.804 I slot print_timing: id 0 | task 2814 | n_gen = 100, tg = 15.66 t/s, tg_3s = 15.82 t/s 4.28.676.741 I slot print_timing: id 2 | task 2853 | prompt eval time = 497.58 ms / 114 tokens ( 4.36 ms per token, 229.11 tokens per second) 4.28.676.753 I slot print_timing: id 2 | task 2853 | eval time = 3788.98 ms / 66 tokens ( 58.29 ms per token, 17.16 tokens per second) 4.28.676.754 I slot print_timing: id 2 | task 2853 | total time = 4286.56 ms / 180 tokens 4.28.676.755 I slot print_timing: id 2 | task 2853 | graphs reused = 2188 4.28.676.756 I slot print_timing: id 2 | task 2853 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.676.910 I slot release: id 2 | task 2853 | stop processing: n_tokens = 1304, truncated = 0 4.28.738.533 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.879 4.28.738.602 I slot launch_slot_: id 2 | task 2923 | processing task, is_child = 0 4.29.443.805 I slot print_timing: id 1 | task 2861 | prompt eval time = 484.16 ms / 104 tokens ( 4.66 ms per token, 214.80 tokens per second) 4.29.443.808 I slot print_timing: id 1 | task 2861 | eval time = 3806.30 ms / 66 tokens ( 58.56 ms per token, 17.08 tokens per second) 4.29.443.809 I slot print_timing: id 1 | task 2861 | total time = 4290.47 ms / 170 tokens 4.29.443.809 I slot print_timing: id 1 | task 2861 | graphs reused = 2191 4.29.443.810 I slot print_timing: id 1 | task 2861 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.443.868 I slot release: id 1 | task 2861 | stop processing: n_tokens = 1294, truncated = 0 4.29.500.339 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.886 4.29.500.371 I slot launch_slot_: id 1 | task 2931 | processing task, is_child = 0 4.30.001.943 I slot print_timing: id 3 | task 2829 | n_gen = 100, tg = 14.74 t/s, tg_3s = 14.89 t/s 4.30.053.190 I slot print_timing: id 0 | task 2814 | prompt eval time = 543.51 ms / 172 tokens ( 3.16 ms per token, 316.46 tokens per second) 4.30.053.195 I slot print_timing: id 0 | task 2814 | eval time = 7854.85 ms / 115 tokens ( 68.90 ms per token, 14.51 tokens per second) 4.30.053.196 I slot print_timing: id 0 | task 2814 | total time = 8398.36 ms / 287 tokens 4.30.053.196 I slot print_timing: id 0 | task 2814 | graphs reused = 2192 4.30.053.197 I slot print_timing: id 0 | task 2814 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.053.244 I slot release: id 0 | task 2814 | stop processing: n_tokens = 1411, truncated = 0 4.30.099.120 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.812 4.30.099.156 I slot launch_slot_: id 0 | task 2937 | processing task, is_child = 0 4.32.452.909 I slot print_timing: id 3 | task 2829 | prompt eval time = 470.40 ms / 119 tokens ( 3.95 ms per token, 252.98 tokens per second) 4.32.452.918 I slot print_timing: id 3 | task 2829 | eval time = 9167.48 ms / 140 tokens ( 65.95 ms per token, 15.16 tokens per second) 4.32.452.919 I slot print_timing: id 3 | task 2829 | total time = 9637.88 ms / 259 tokens 4.32.452.920 I slot print_timing: id 3 | task 2829 | graphs reused = 2228 4.32.452.921 I slot print_timing: id 3 | task 2829 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.453.020 I slot release: id 3 | task 2829 | stop processing: n_tokens = 1383, truncated = 0 4.32.502.190 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.829 4.32.502.261 I slot launch_slot_: id 3 | task 2977 | processing task, is_child = 0 4.34.343.787 I slot print_timing: id 2 | task 2923 | prompt eval time = 497.26 ms / 117 tokens ( 4.25 ms per token, 235.29 tokens per second) 4.34.343.796 I slot print_timing: id 2 | task 2923 | eval time = 5107.91 ms / 79 tokens ( 65.49 ms per token, 15.27 tokens per second) 4.34.343.797 I slot print_timing: id 2 | task 2923 | total time = 5605.17 ms / 196 tokens 4.34.343.798 I slot print_timing: id 2 | task 2923 | graphs reused = 2254 4.34.343.800 I slot print_timing: id 2 | task 2923 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.343.923 I slot release: id 2 | task 2923 | stop processing: n_tokens = 1320, truncated = 0 4.34.403.921 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.868 4.34.403.981 I slot launch_slot_: id 2 | task 3008 | processing task, is_child = 0 4.35.316.932 I slot print_timing: id 1 | task 2931 | prompt eval time = 447.82 ms / 88 tokens ( 5.09 ms per token, 196.51 tokens per second) 4.35.316.935 I slot print_timing: id 1 | task 2931 | eval time = 5368.73 ms / 82 tokens ( 66.28 ms per token, 15.09 tokens per second) 4.35.316.935 I slot print_timing: id 1 | task 2931 | total time = 5816.55 ms / 170 tokens 4.35.316.936 I slot print_timing: id 1 | task 2931 | graphs reused = 2260 4.35.316.936 I slot print_timing: id 1 | task 2931 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.316.983 I slot release: id 1 | task 2931 | stop processing: n_tokens = 1294, truncated = 0 4.35.373.184 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.886 4.35.373.218 I slot launch_slot_: id 1 | task 3019 | processing task, is_child = 0 4.36.390.974 I slot print_timing: id 3 | task 2977 | prompt eval time = 426.02 ms / 87 tokens ( 4.90 ms per token, 204.22 tokens per second) 4.36.390.980 I slot print_timing: id 3 | task 2977 | eval time = 3462.69 ms / 51 tokens ( 69.25 ms per token, 14.44 tokens per second) 4.36.390.980 I slot print_timing: id 3 | task 2977 | total time = 3888.70 ms / 138 tokens 4.36.390.981 I slot print_timing: id 3 | task 2977 | graphs reused = 2269 4.36.390.981 I slot print_timing: id 3 | task 2977 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.391.030 I slot release: id 3 | task 2977 | stop processing: n_tokens = 1262, truncated = 0 4.36.436.723 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.908 4.36.436.755 I slot launch_slot_: id 3 | task 3033 | processing task, is_child = 0 4.37.261.516 I slot print_timing: id 0 | task 2937 | n_gen = 100, tg = 14.80 t/s, tg_3s = 14.95 t/s 4.37.944.588 I slot print_timing: id 0 | task 2937 | prompt eval time = 471.95 ms / 129 tokens ( 3.66 ms per token, 273.33 tokens per second) 4.37.944.596 I slot print_timing: id 0 | task 2937 | eval time = 7373.47 ms / 113 tokens ( 65.83 ms per token, 15.19 tokens per second) 4.37.944.597 I slot print_timing: id 0 | task 2937 | total time = 7845.42 ms / 242 tokens 4.37.944.598 I slot print_timing: id 0 | task 2937 | graphs reused = 2288 4.37.944.599 I slot print_timing: id 0 | task 2937 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.944.689 I slot release: id 0 | task 2937 | stop processing: n_tokens = 1366, truncated = 0 4.37.994.751 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.839 4.37.994.813 I slot launch_slot_: id 0 | task 3057 | processing task, is_child = 0 4.41.286.521 I slot print_timing: id 1 | task 3019 | prompt eval time = 499.03 ms / 118 tokens ( 4.23 ms per token, 236.46 tokens per second) 4.41.286.527 I slot print_timing: id 1 | task 3019 | eval time = 5414.26 ms / 90 tokens ( 60.83 ms per token, 16.44 tokens per second) 4.41.286.528 I slot print_timing: id 1 | task 3019 | total time = 5913.29 ms / 208 tokens 4.41.286.529 I slot print_timing: id 1 | task 3019 | graphs reused = 2341 4.41.286.530 I slot print_timing: id 1 | task 3019 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.286.631 I slot release: id 1 | task 3019 | stop processing: n_tokens = 1332, truncated = 0 4.41.287.008 I slot print_timing: id 2 | task 3008 | n_gen = 100, tg = 15.63 t/s, tg_3s = 15.79 t/s 4.41.348.242 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.860 4.41.348.336 I slot launch_slot_: id 1 | task 3114 | processing task, is_child = 0 4.42.321.438 I slot print_timing: id 2 | task 3008 | prompt eval time = 549.41 ms / 152 tokens ( 3.61 ms per token, 276.66 tokens per second) 4.42.321.441 I slot print_timing: id 2 | task 3008 | eval time = 7368.04 ms / 113 tokens ( 65.79 ms per token, 15.20 tokens per second) 4.42.321.441 I slot print_timing: id 2 | task 3008 | total time = 7917.45 ms / 265 tokens 4.42.321.442 I slot print_timing: id 2 | task 3008 | graphs reused = 2350 4.42.321.442 I slot print_timing: id 2 | task 3008 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.321.490 I slot release: id 2 | task 3008 | stop processing: n_tokens = 1389, truncated = 0 4.42.379.007 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.825 4.42.379.051 I slot launch_slot_: id 2 | task 3128 | processing task, is_child = 0 4.43.243.396 I slot print_timing: id 3 | task 3033 | n_gen = 100, tg = 15.60 t/s, tg_3s = 15.76 t/s 4.43.975.209 I slot print_timing: id 0 | task 3057 | prompt eval time = 496.00 ms / 135 tokens ( 3.67 ms per token, 272.17 tokens per second) 4.43.975.218 I slot print_timing: id 0 | task 3057 | eval time = 5484.38 ms / 91 tokens ( 60.94 ms per token, 16.41 tokens per second) 4.43.975.219 I slot print_timing: id 0 | task 3057 | total time = 5980.38 ms / 226 tokens 4.43.975.220 I slot print_timing: id 0 | task 3057 | graphs reused = 2370 4.43.975.221 I slot print_timing: id 0 | task 3057 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.975.309 I slot release: id 0 | task 3057 | stop processing: n_tokens = 1350, truncated = 0 4.44.026.411 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.849 4.44.026.474 I slot launch_slot_: id 0 | task 3153 | processing task, is_child = 0 4.44.501.370 I slot print_timing: id 3 | task 3033 | prompt eval time = 461.71 ms / 110 tokens ( 4.20 ms per token, 238.25 tokens per second) 4.44.501.376 I slot print_timing: id 3 | task 3033 | eval time = 7602.90 ms / 117 tokens ( 65.54 ms per token, 15.26 tokens per second) 4.44.501.376 I slot print_timing: id 3 | task 3033 | total time = 8064.61 ms / 227 tokens 4.44.501.377 I slot print_timing: id 3 | task 3033 | graphs reused = 2371 4.44.501.377 I slot print_timing: id 3 | task 3033 | graph reallocs = 0 / 0 (same size) / (changed size) 4.44.502.492 I slot release: id 3 | task 3033 | stop processing: n_tokens = 1351, truncated = 0 4.44.548.003 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.848 4.44.548.037 I slot launch_slot_: id 3 | task 3157 | processing task, is_child = 0 4.47.114.016 I slot print_timing: id 1 | task 3114 | prompt eval time = 453.38 ms / 92 tokens ( 4.93 ms per token, 202.92 tokens per second) 4.47.114.023 I slot print_timing: id 1 | task 3114 | eval time = 5312.27 ms / 82 tokens ( 65.58 ms per token, 15.25 tokens per second) 4.47.114.025 I slot print_timing: id 1 | task 3114 | total time = 5765.66 ms / 174 tokens 4.47.114.026 I slot print_timing: id 1 | task 3114 | graphs reused = 2410 4.47.114.027 I slot print_timing: id 1 | task 3114 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.114.128 I slot release: id 1 | task 3114 | stop processing: n_tokens = 1298, truncated = 0 4.47.175.842 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.883 4.47.175.923 I slot launch_slot_: id 1 | task 3202 | processing task, is_child = 0 4.48.066.747 I slot print_timing: id 2 | task 3128 | prompt eval time = 501.71 ms / 120 tokens ( 4.18 ms per token, 239.18 tokens per second) 4.48.066.756 I slot print_timing: id 2 | task 3128 | eval time = 5185.96 ms / 80 tokens ( 65.65 ms per token, 15.23 tokens per second) 4.48.066.757 I slot print_timing: id 2 | task 3128 | total time = 5687.67 ms / 200 tokens 4.48.066.758 I slot print_timing: id 2 | task 3128 | graphs reused = 2417 4.48.066.759 I slot print_timing: id 2 | task 3128 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.068.848 I slot release: id 2 | task 3128 | stop processing: n_tokens = 1324, truncated = 0 4.48.130.133 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.866 4.48.130.201 I slot launch_slot_: id 2 | task 3214 | processing task, is_child = 0 4.50.779.960 I slot print_timing: id 0 | task 3153 | n_gen = 100, tg = 15.77 t/s, tg_3s = 15.93 t/s 4.50.938.710 I slot print_timing: id 3 | task 3157 | n_gen = 100, tg = 16.60 t/s, tg_3s = 16.76 t/s 4.52.263.334 I slot print_timing: id 3 | task 3157 | prompt eval time = 425.25 ms / 95 tokens ( 4.48 ms per token, 223.40 tokens per second) 4.52.263.343 I slot print_timing: id 3 | task 3157 | eval time = 7290.03 ms / 125 tokens ( 58.79 ms per token, 17.01 tokens per second) 4.52.263.346 I slot print_timing: id 3 | task 3157 | total time = 7715.28 ms / 220 tokens 4.52.263.347 I slot print_timing: id 3 | task 3157 | graphs reused = 2485 4.52.263.348 I slot print_timing: id 3 | task 3157 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.263.497 I slot release: id 3 | task 3157 | stop processing: n_tokens = 1344, truncated = 0 4.52.313.264 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.853 4.52.313.320 I slot launch_slot_: id 3 | task 3287 | processing task, is_child = 0 4.53.639.774 I slot print_timing: id 1 | task 3202 | n_gen = 100, tg = 16.50 t/s, tg_3s = 16.66 t/s 4.53.692.421 I slot print_timing: id 1 | task 3202 | prompt eval time = 463.10 ms / 98 tokens ( 4.73 ms per token, 211.62 tokens per second) 4.53.692.430 I slot print_timing: id 1 | task 3202 | eval time = 6053.39 ms / 101 tokens ( 60.53 ms per token, 16.52 tokens per second) 4.53.692.431 I slot print_timing: id 1 | task 3202 | total time = 6516.49 ms / 199 tokens 4.53.692.432 I slot print_timing: id 1 | task 3202 | graphs reused = 2501 4.53.692.433 I slot print_timing: id 1 | task 3202 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.692.533 I slot release: id 1 | task 3202 | stop processing: n_tokens = 1323, truncated = 0 4.53.753.473 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.866 4.53.753.532 I slot launch_slot_: id 1 | task 3308 | processing task, is_child = 0 4.54.132.460 I slot print_timing: id 0 | task 3153 | n_gen = 150, tg = 15.47 t/s, tg_3s = 14.91 t/s 4.54.602.950 I slot print_timing: id 2 | task 3214 | n_gen = 100, tg = 16.58 t/s, tg_3s = 16.75 t/s 4.54.860.115 I slot print_timing: id 2 | task 3214 | prompt eval time = 501.37 ms / 116 tokens ( 4.32 ms per token, 231.37 tokens per second) 4.54.860.121 I slot print_timing: id 2 | task 3214 | eval time = 6228.53 ms / 105 tokens ( 59.89 ms per token, 16.70 tokens per second) 4.54.860.122 I slot print_timing: id 2 | task 3214 | total time = 6729.91 ms / 221 tokens 4.54.860.122 I slot print_timing: id 2 | task 3214 | graphs reused = 2512 4.54.860.123 I slot print_timing: id 2 | task 3214 | graph reallocs = 0 / 0 (same size) / (changed size) 4.54.860.172 I slot release: id 2 | task 3214 | stop processing: n_tokens = 1345, truncated = 0 4.54.916.439 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.852 4.54.916.476 I slot launch_slot_: id 2 | task 3324 | processing task, is_child = 0 4.55.414.395 I slot print_timing: id 0 | task 3153 | prompt eval time = 474.48 ms / 131 tokens ( 3.62 ms per token, 276.09 tokens per second) 4.55.414.401 I slot print_timing: id 0 | task 3153 | eval time = 10913.43 ms / 166 tokens ( 66.14 ms per token, 15.12 tokens per second) 4.55.414.401 I slot print_timing: id 0 | task 3153 | total time = 11387.91 ms / 297 tokens 4.55.414.402 I slot print_timing: id 0 | task 3153 | graphs reused = 2512 4.55.414.402 I slot print_timing: id 0 | task 3153 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.414.446 I slot release: id 0 | task 3153 | stop processing: n_tokens = 1421, truncated = 0 4.55.460.558 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.806 4.55.460.594 I slot launch_slot_: id 0 | task 3328 | processing task, is_child = 0 4.59.119.934 I slot print_timing: id 3 | task 3287 | n_gen = 100, tg = 15.67 t/s, tg_3s = 15.83 t/s 5.00.172.179 I slot print_timing: id 1 | task 3308 | n_gen = 100, tg = 16.69 t/s, tg_3s = 16.86 t/s 5.00.700.171 I slot print_timing: id 3 | task 3287 | prompt eval time = 487.96 ms / 130 tokens ( 3.75 ms per token, 266.42 tokens per second) 5.00.700.179 I slot print_timing: id 3 | task 3287 | eval time = 7898.88 ms / 130 tokens ( 61.23 ms per token, 16.33 tokens per second) 5.00.700.180 I slot print_timing: id 3 | task 3287 | total time = 8386.84 ms / 260 tokens 5.00.700.181 I slot print_timing: id 3 | task 3287 | graphs reused = 2603 5.00.700.197 I slot print_timing: id 3 | task 3287 | graph reallocs = 0 / 0 (same size) / (changed size) 5.00.700.362 I slot release: id 3 | task 3287 | stop processing: n_tokens = 1384, truncated = 0 5.00.750.019 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.828 5.00.750.103 I slot launch_slot_: id 3 | task 3423 | processing task, is_child = 0 5.01.331.407 I slot print_timing: id 2 | task 3324 | n_gen = 100, tg = 16.73 t/s, tg_3s = 16.90 t/s 5.01.486.715 I slot print_timing: id 0 | task 3328 | n_gen = 100, tg = 17.88 t/s, tg_3s = 18.06 t/s 5.02.328.711 I slot print_timing: id 1 | task 3308 | prompt eval time = 486.51 ms / 103 tokens ( 4.72 ms per token, 211.71 tokens per second) 5.02.328.722 I slot print_timing: id 1 | task 3308 | eval time = 8088.66 ms / 134 tokens ( 60.82 ms per token, 16.44 tokens per second) 5.02.328.723 I slot print_timing: id 1 | task 3308 | total time = 8575.17 ms / 237 tokens 5.02.328.724 I slot print_timing: id 1 | task 3308 | graphs reused = 2623 5.02.328.725 I slot print_timing: id 1 | task 3308 | graph reallocs = 0 / 0 (same size) / (changed size) 5.02.328.807 I slot release: id 1 | task 3308 | stop processing: n_tokens = 1361, truncated = 0 5.02.390.134 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.842 5.02.390.208 I slot launch_slot_: id 1 | task 3448 | processing task, is_child = 0 5.04.317.902 I slot print_timing: id 2 | task 3324 | prompt eval time = 498.40 ms / 122 tokens ( 4.09 ms per token, 244.78 tokens per second) 5.04.317.908 I slot print_timing: id 2 | task 3324 | eval time = 8903.01 ms / 149 tokens ( 60.16 ms per token, 16.62 tokens per second) 5.04.317.909 I slot print_timing: id 2 | task 3324 | total time = 9401.42 ms / 271 tokens 5.04.317.910 I slot print_timing: id 2 | task 3324 | graphs reused = 2649 5.04.317.911 I slot print_timing: id 2 | task 3324 | graph reallocs = 0 / 0 (same size) / (changed size) 5.04.318.008 I slot release: id 2 | task 3324 | stop processing: n_tokens = 1395, truncated = 0 5.04.380.515 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.822 5.04.380.569 I slot launch_slot_: id 2 | task 3479 | processing task, is_child = 0 5.04.733.768 I slot print_timing: id 0 | task 3328 | n_gen = 148, tg = 16.73 t/s, tg_3s = 14.78 t/s 5.07.044.636 I slot print_timing: id 3 | task 3423 | prompt eval time = 476.46 ms / 123 tokens ( 3.87 ms per token, 258.16 tokens per second) 5.07.044.643 I slot print_timing: id 3 | task 3423 | eval time = 5818.06 ms / 97 tokens ( 60.60 ms per token, 16.50 tokens per second) 5.07.044.644 I slot print_timing: id 3 | task 3423 | total time = 6294.52 ms / 220 tokens 5.07.044.645 I slot print_timing: id 3 | task 3423 | graphs reused = 2690 5.07.044.646 I slot print_timing: id 3 | task 3423 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.044.748 I slot release: id 3 | task 3423 | stop processing: n_tokens = 1344, truncated = 0 5.07.094.063 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.853 5.07.094.130 I slot launch_slot_: id 3 | task 3525 | processing task, is_child = 0 5.07.784.665 I slot print_timing: id 0 | task 3328 | prompt eval time = 487.87 ms / 133 tokens ( 3.67 ms per token, 272.61 tokens per second) 5.07.784.670 I slot print_timing: id 0 | task 3328 | eval time = 11836.19 ms / 199 tokens ( 59.78 ms per token, 16.73 tokens per second) 5.07.784.671 I slot print_timing: id 0 | task 3328 | total time = 12324.07 ms / 332 tokens 5.07.784.671 I slot print_timing: id 0 | task 3328 | graphs reused = 2694 5.07.784.672 I slot print_timing: id 0 | task 3328 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.784.720 I slot release: id 0 | task 3328 | stop processing: n_tokens = 1456, truncated = 0 5.07.830.732 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.787 5.07.830.769 I slot launch_slot_: id 0 | task 3534 | processing task, is_child = 0 5.09.163.750 I slot print_timing: id 1 | task 3448 | n_gen = 100, tg = 15.79 t/s, tg_3s = 15.95 t/s 5.10.350.932 I slot print_timing: id 1 | task 3448 | prompt eval time = 503.01 ms / 118 tokens ( 4.26 ms per token, 234.59 tokens per second) 5.10.350.937 I slot print_timing: id 1 | task 3448 | eval time = 7457.71 ms / 123 tokens ( 61.13 ms per token, 16.36 tokens per second) 5.10.350.939 I slot print_timing: id 1 | task 3448 | total time = 7960.72 ms / 241 tokens 5.10.350.939 I slot print_timing: id 1 | task 3448 | graphs reused = 2733 5.10.350.940 I slot print_timing: id 1 | task 3448 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.350.985 I slot release: id 1 | task 3448 | stop processing: n_tokens = 1365, truncated = 0 5.10.407.534 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.840 5.10.407.585 I slot launch_slot_: id 1 | task 3577 | processing task, is_child = 0 5.11.065.819 I slot print_timing: id 2 | task 3479 | n_gen = 100, tg = 15.90 t/s, tg_3s = 16.06 t/s 5.11.272.711 I slot print_timing: id 2 | task 3479 | prompt eval time = 459.36 ms / 101 tokens ( 4.55 ms per token, 219.87 tokens per second) 5.11.272.713 I slot print_timing: id 2 | task 3479 | eval time = 6432.77 ms / 104 tokens ( 62.45 ms per token, 16.01 tokens per second) 5.11.272.714 I slot print_timing: id 2 | task 3479 | total time = 6892.13 ms / 205 tokens 5.11.272.714 I slot print_timing: id 2 | task 3479 | graphs reused = 2740 5.11.272.715 I slot print_timing: id 2 | task 3479 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.272.767 I slot release: id 2 | task 3479 | stop processing: n_tokens = 1329, truncated = 0 5.11.329.177 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.862 5.11.329.211 I slot launch_slot_: id 2 | task 3589 | processing task, is_child = 0 5.12.324.135 I slot print_timing: id 3 | task 3525 | prompt eval time = 431.33 ms / 95 tokens ( 4.54 ms per token, 220.25 tokens per second) 5.12.324.142 I slot print_timing: id 3 | task 3525 | eval time = 4798.66 ms / 72 tokens ( 67.59 ms per token, 14.80 tokens per second) 5.12.324.143 I slot print_timing: id 3 | task 3525 | total time = 5229.99 ms / 167 tokens 5.12.324.144 I slot print_timing: id 3 | task 3525 | graphs reused = 2749 5.12.324.145 I slot print_timing: id 3 | task 3525 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.324.261 I slot release: id 3 | task 3525 | stop processing: n_tokens = 1291, truncated = 0 5.12.373.568 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.888 5.12.373.621 I slot launch_slot_: id 3 | task 3603 | processing task, is_child = 0 5.14.533.275 I slot print_timing: id 0 | task 3534 | n_gen = 100, tg = 15.98 t/s, tg_3s = 16.14 t/s 5.14.691.334 I slot print_timing: id 1 | task 3577 | prompt eval time = 448.95 ms / 89 tokens ( 5.04 ms per token, 198.24 tokens per second) 5.14.691.340 I slot print_timing: id 1 | task 3577 | eval time = 3834.78 ms / 61 tokens ( 63.91 ms per token, 15.65 tokens per second) 5.14.691.341 I slot print_timing: id 1 | task 3577 | total time = 4283.73 ms / 150 tokens 5.14.691.342 I slot print_timing: id 1 | task 3577 | graphs reused = 2784 5.14.691.343 I slot print_timing: id 1 | task 3577 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.691.464 I slot release: id 1 | task 3577 | stop processing: n_tokens = 1274, truncated = 0 5.14.752.063 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.900 5.14.752.132 I slot launch_slot_: id 1 | task 3643 | processing task, is_child = 0 5.16.092.406 I slot print_timing: id 3 | task 3603 | prompt eval time = 430.83 ms / 92 tokens ( 4.68 ms per token, 213.54 tokens per second) 5.16.092.416 I slot print_timing: id 3 | task 3603 | eval time = 3287.93 ms / 56 tokens ( 59.78 ms per token, 16.73 tokens per second) 5.16.092.418 I slot print_timing: id 3 | task 3603 | total time = 3718.76 ms / 148 tokens 5.16.092.419 I slot print_timing: id 3 | task 3603 | graphs reused = 2799 5.16.092.420 I slot print_timing: id 3 | task 3603 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.092.603 I slot release: id 3 | task 3603 | stop processing: n_tokens = 1272, truncated = 0 5.16.142.131 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.901 5.16.142.181 I slot launch_slot_: id 3 | task 3663 | processing task, is_child = 0 5.16.729.821 I slot print_timing: id 2 | task 3589 | prompt eval time = 460.89 ms / 99 tokens ( 4.66 ms per token, 214.80 tokens per second) 5.16.729.829 I slot print_timing: id 2 | task 3589 | eval time = 4939.71 ms / 74 tokens ( 67.67 ms per token, 14.78 tokens per second) 5.16.729.830 I slot print_timing: id 2 | task 3589 | total time = 5400.60 ms / 173 tokens 5.16.729.831 I slot print_timing: id 2 | task 3589 | graphs reused = 2800 5.16.729.831 I slot print_timing: id 2 | task 3589 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.729.881 I slot release: id 2 | task 3589 | stop processing: n_tokens = 1297, truncated = 0 5.16.786.234 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.884 5.16.786.277 I slot launch_slot_: id 2 | task 3669 | processing task, is_child = 0 5.17.546.415 I slot print_timing: id 0 | task 3534 | n_gen = 136, tg = 14.66 t/s, tg_3s = 11.95 t/s 5.19.971.617 I slot print_timing: id 0 | task 3534 | prompt eval time = 505.66 ms / 152 tokens ( 3.33 ms per token, 300.60 tokens per second) 5.19.971.624 I slot print_timing: id 0 | task 3534 | eval time = 11635.18 ms / 183 tokens ( 63.93 ms per token, 15.64 tokens per second) 5.19.971.624 I slot print_timing: id 0 | task 3534 | total time = 12140.84 ms / 335 tokens 5.19.971.625 I slot print_timing: id 0 | task 3534 | graphs reused = 2852 5.19.971.625 I slot print_timing: id 0 | task 3534 | graph reallocs = 0 / 0 (same size) / (changed size) 5.19.971.684 I slot release: id 0 | task 3534 | stop processing: n_tokens = 1459, truncated = 0 5.20.018.367 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.785 5.20.018.407 I slot launch_slot_: id 0 | task 3726 | processing task, is_child = 0 5.20.918.310 I slot print_timing: id 1 | task 3643 | prompt eval time = 496.08 ms / 113 tokens ( 4.39 ms per token, 227.79 tokens per second) 5.20.918.314 I slot print_timing: id 1 | task 3643 | eval time = 5670.09 ms / 88 tokens ( 65.17 ms per token, 15.34 tokens per second) 5.20.918.315 I slot print_timing: id 1 | task 3643 | total time = 6166.17 ms / 201 tokens 5.20.918.315 I slot print_timing: id 1 | task 3643 | graphs reused = 2859 5.20.918.316 I slot print_timing: id 1 | task 3643 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.918.374 I slot release: id 1 | task 3643 | stop processing: n_tokens = 1325, truncated = 0 5.20.975.497 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.865 5.20.975.530 I slot launch_slot_: id 1 | task 3737 | processing task, is_child = 0 5.21.724.784 I slot print_timing: id 2 | task 3669 | prompt eval time = 448.89 ms / 90 tokens ( 4.99 ms per token, 200.49 tokens per second) 5.21.724.789 I slot print_timing: id 2 | task 3669 | eval time = 4489.60 ms / 72 tokens ( 63.23 ms per token, 15.81 tokens per second) 5.21.724.790 I slot print_timing: id 2 | task 3669 | total time = 4938.50 ms / 162 tokens 5.21.724.790 I slot print_timing: id 2 | task 3669 | graphs reused = 2863 5.21.724.791 I slot print_timing: id 2 | task 3669 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.724.842 I slot release: id 2 | task 3669 | stop processing: n_tokens = 1286, truncated = 0 5.21.781.494 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.891 5.21.781.539 I slot launch_slot_: id 2 | task 3746 | processing task, is_child = 0 5.23.373.868 I slot print_timing: id 3 | task 3663 | n_gen = 100, tg = 14.67 t/s, tg_3s = 14.82 t/s 5.26.231.067 I slot print_timing: id 1 | task 3737 | prompt eval time = 489.16 ms / 107 tokens ( 4.57 ms per token, 218.74 tokens per second) 5.26.231.073 I slot print_timing: id 1 | task 3737 | eval time = 4766.36 ms / 83 tokens ( 58.13 ms per token, 17.20 tokens per second) 5.26.231.074 I slot print_timing: id 1 | task 3737 | total time = 5255.52 ms / 190 tokens 5.26.231.075 I slot print_timing: id 1 | task 3737 | graphs reused = 2936 5.26.231.076 I slot print_timing: id 1 | task 3737 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.231.180 I slot release: id 1 | task 3737 | stop processing: n_tokens = 1314, truncated = 0 5.26.292.221 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.872 5.26.292.309 I slot launch_slot_: id 1 | task 3824 | processing task, is_child = 0 5.26.683.632 I slot print_timing: id 3 | task 3663 | n_gen = 156, tg = 15.41 t/s, tg_3s = 16.92 t/s 5.26.895.876 I slot print_timing: id 3 | task 3663 | prompt eval time = 482.70 ms / 118 tokens ( 4.09 ms per token, 244.46 tokens per second) 5.26.895.881 I slot print_timing: id 3 | task 3663 | eval time = 10270.98 ms / 159 tokens ( 65.01 ms per token, 15.38 tokens per second) 5.26.895.882 I slot print_timing: id 3 | task 3663 | total time = 10753.68 ms / 277 tokens 5.26.895.883 I slot print_timing: id 3 | task 3663 | graphs reused = 2937 5.26.895.883 I slot print_timing: id 3 | task 3663 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.895.930 I slot release: id 3 | task 3663 | stop processing: n_tokens = 1401, truncated = 0 5.26.941.522 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.818 5.26.941.560 I slot launch_slot_: id 3 | task 3830 | processing task, is_child = 0 5.27.358.650 I slot print_timing: id 0 | task 3726 | n_gen = 100, tg = 14.55 t/s, tg_3s = 14.70 t/s 5.28.346.483 I slot print_timing: id 2 | task 3746 | n_gen = 100, tg = 16.44 t/s, tg_3s = 16.60 t/s 5.29.085.019 I slot print_timing: id 2 | task 3746 | prompt eval time = 541.75 ms / 147 tokens ( 3.69 ms per token, 271.34 tokens per second) 5.29.085.026 I slot print_timing: id 2 | task 3746 | eval time = 6761.72 ms / 114 tokens ( 59.84 ms per token, 16.71 tokens per second) 5.29.085.027 I slot print_timing: id 2 | task 3746 | total time = 7303.47 ms / 261 tokens 5.29.085.028 I slot print_timing: id 2 | task 3746 | graphs reused = 2967 5.29.085.029 I slot print_timing: id 2 | task 3746 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.085.132 I slot release: id 2 | task 3746 | stop processing: n_tokens = 1385, truncated = 0 5.29.146.668 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.827 5.29.146.739 I slot launch_slot_: id 2 | task 3865 | processing task, is_child = 0 5.30.367.645 I slot print_timing: id 0 | task 3726 | n_gen = 149, tg = 15.08 t/s, tg_3s = 16.28 t/s 5.31.055.443 I slot print_timing: id 0 | task 3726 | prompt eval time = 535.78 ms / 170 tokens ( 3.15 ms per token, 317.30 tokens per second) 5.31.055.452 I slot print_timing: id 0 | task 3726 | eval time = 10501.25 ms / 162 tokens ( 65.23 ms per token, 15.33 tokens per second) 5.31.055.453 I slot print_timing: id 0 | task 3726 | total time = 11037.03 ms / 332 tokens 5.31.055.454 I slot print_timing: id 0 | task 3726 | graphs reused = 2993 5.31.055.455 I slot print_timing: id 0 | task 3726 | graph reallocs = 0 / 0 (same size) / (changed size) 5.31.055.555 I slot release: id 0 | task 3726 | stop processing: n_tokens = 1456, truncated = 0 5.31.106.093 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.787 5.31.106.157 I slot launch_slot_: id 0 | task 3896 | processing task, is_child = 0 5.31.765.364 I slot print_timing: id 1 | task 3824 | prompt eval time = 498.10 ms / 109 tokens ( 4.57 ms per token, 218.83 tokens per second) 5.31.765.370 I slot print_timing: id 1 | task 3824 | eval time = 4974.94 ms / 73 tokens ( 69.10 ms per token, 14.47 tokens per second) 5.31.765.370 I slot print_timing: id 1 | task 3824 | total time = 5473.04 ms / 182 tokens 5.31.765.371 I slot print_timing: id 1 | task 3824 | graphs reused = 2996 5.31.765.371 I slot print_timing: id 1 | task 3824 | graph reallocs = 0 / 0 (same size) / (changed size) 5.31.765.440 I slot release: id 1 | task 3824 | stop processing: n_tokens = 1306, truncated = 0 5.31.821.391 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.877 5.31.821.434 I slot launch_slot_: id 1 | task 3903 | processing task, is_child = 0 5.33.841.358 I slot print_timing: id 3 | task 3830 | n_gen = 100, tg = 15.50 t/s, tg_3s = 15.65 t/s 5.35.640.982 I slot print_timing: id 2 | task 3865 | n_gen = 100, tg = 16.50 t/s, tg_3s = 16.67 t/s 5.36.535.477 I slot print_timing: id 2 | task 3865 | prompt eval time = 495.53 ms / 110 tokens ( 4.50 ms per token, 221.98 tokens per second) 5.36.535.489 I slot print_timing: id 2 | task 3865 | eval time = 6893.20 ms / 117 tokens ( 59.42 ms per token, 16.83 tokens per second) 5.36.535.490 I slot print_timing: id 2 | task 3865 | total time = 7388.73 ms / 227 tokens 5.36.535.491 I slot print_timing: id 2 | task 3865 | graphs reused = 3075 5.36.535.492 I slot print_timing: id 2 | task 3865 | graph reallocs = 0 / 0 (same size) / (changed size) 5.36.535.588 I slot release: id 2 | task 3865 | stop processing: n_tokens = 1351, truncated = 0 5.36.596.958 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.848 5.36.597.031 I slot launch_slot_: id 2 | task 3987 | processing task, is_child = 0 5.36.952.519 I slot print_timing: id 3 | task 3830 | n_gen = 153, tg = 16.00 t/s, tg_3s = 17.04 t/s 5.37.058.318 I slot print_timing: id 3 | task 3830 | prompt eval time = 511.03 ms / 139 tokens ( 3.68 ms per token, 272.00 tokens per second) 5.37.058.321 I slot print_timing: id 3 | task 3830 | eval time = 9605.73 ms / 154 tokens ( 62.78 ms per token, 15.93 tokens per second) 5.37.058.321 I slot print_timing: id 3 | task 3830 | total time = 10116.75 ms / 293 tokens 5.37.058.322 I slot print_timing: id 3 | task 3830 | graphs reused = 3075 5.37.058.322 I slot print_timing: id 3 | task 3830 | graph reallocs = 0 / 0 (same size) / (changed size) 5.37.058.370 I slot release: id 3 | task 3830 | stop processing: n_tokens = 1417, truncated = 0 5.37.103.813 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.809 5.37.103.841 I slot launch_slot_: id 3 | task 3991 | processing task, is_child = 0 5.37.935.294 I slot print_timing: id 0 | task 3896 | n_gen = 100, tg = 15.65 t/s, tg_3s = 15.81 t/s 5.38.246.057 I slot print_timing: id 1 | task 3903 | n_gen = 100, tg = 16.72 t/s, tg_3s = 16.89 t/s 5.39.122.799 I slot print_timing: id 0 | task 3896 | prompt eval time = 502.59 ms / 134 tokens ( 3.75 ms per token, 266.62 tokens per second) 5.39.122.801 I slot print_timing: id 0 | task 3896 | eval time = 7514.04 ms / 123 tokens ( 61.59 ms per token, 16.24 tokens per second) 5.39.122.801 I slot print_timing: id 0 | task 3896 | total time = 8016.63 ms / 257 tokens 5.39.122.802 I slot print_timing: id 0 | task 3896 | graphs reused = 3104 5.39.122.802 I slot print_timing: id 0 | task 3896 | graph reallocs = 0 / 0 (same size) / (changed size) 5.39.122.850 I slot release: id 0 | task 3896 | stop processing: n_tokens = 1381, truncated = 0 5.39.169.144 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.830 5.39.169.178 I slot launch_slot_: id 0 | task 4025 | processing task, is_child = 0 5.39.516.532 I slot print_timing: id 1 | task 3903 | prompt eval time = 503.01 ms / 122 tokens ( 4.12 ms per token, 242.54 tokens per second) 5.39.516.534 I slot print_timing: id 1 | task 3903 | eval time = 7192.07 ms / 119 tokens ( 60.95 ms per token, 16.41 tokens per second) 5.39.516.534 I slot print_timing: id 1 | task 3903 | total time = 7695.09 ms / 241 tokens 5.39.516.535 I slot print_timing: id 1 | task 3903 | graphs reused = 3105 5.39.516.535 I slot print_timing: id 1 | task 3903 | graph reallocs = 0 / 0 (same size) / (changed size) 5.39.516.585 I slot release: id 1 | task 3903 | stop processing: n_tokens = 1365, truncated = 0 5.39.597.264 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.840 5.39.597.297 I slot launch_slot_: id 1 | task 4028 | processing task, is_child = 0 5.42.565.282 I slot print_timing: id 2 | task 3987 | prompt eval time = 461.13 ms / 96 tokens ( 4.80 ms per token, 208.19 tokens per second) 5.42.565.286 I slot print_timing: id 2 | task 3987 | eval time = 5507.11 ms / 87 tokens ( 64.04 ms per token, 15.62 tokens per second) 5.42.565.287 I slot print_timing: id 2 | task 3987 | total time = 5968.24 ms / 183 tokens 5.42.565.287 I slot print_timing: id 2 | task 3987 | graphs reused = 3151 5.42.565.288 I slot print_timing: id 2 | task 3987 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.565.352 I slot release: id 2 | task 3987 | stop processing: n_tokens = 1307, truncated = 0 5.42.621.941 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 5.42.621.982 I slot launch_slot_: id 2 | task 4080 | processing task, is_child = 0 5.43.884.022 I slot print_timing: id 3 | task 3991 | n_gen = 100, tg = 15.68 t/s, tg_3s = 15.84 t/s 5.44.041.817 I slot print_timing: id 3 | task 3991 | prompt eval time = 467.53 ms / 111 tokens ( 4.21 ms per token, 237.42 tokens per second) 5.44.041.823 I slot print_timing: id 3 | task 3991 | eval time = 6470.43 ms / 103 tokens ( 63.44 ms per token, 15.76 tokens per second) 5.44.041.824 I slot print_timing: id 3 | task 3991 | total time = 6937.96 ms / 214 tokens 5.44.041.825 I slot print_timing: id 3 | task 3991 | graphs reused = 3166 5.44.041.826 I slot print_timing: id 3 | task 3991 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.041.939 I slot release: id 3 | task 3991 | stop processing: n_tokens = 1338, truncated = 0 5.44.091.680 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.857 5.44.091.748 I slot launch_slot_: id 3 | task 4100 | processing task, is_child = 0 5.44.765.902 I slot print_timing: id 0 | task 4025 | prompt eval time = 427.78 ms / 101 tokens ( 4.24 ms per token, 236.10 tokens per second) 5.44.765.909 I slot print_timing: id 0 | task 4025 | eval time = 5168.94 ms / 77 tokens ( 68.01 ms per token, 14.70 tokens per second) 5.44.765.909 I slot print_timing: id 0 | task 4025 | total time = 5596.71 ms / 178 tokens 5.44.765.910 I slot print_timing: id 0 | task 4025 | graphs reused = 3169 5.44.765.910 I slot print_timing: id 0 | task 4025 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.765.960 I slot release: id 0 | task 4025 | stop processing: n_tokens = 1302, truncated = 0 5.44.811.872 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.880 5.44.811.920 I slot launch_slot_: id 0 | task 4108 | processing task, is_child = 0 5.46.419.102 I slot print_timing: id 1 | task 4028 | n_gen = 100, tg = 15.62 t/s, tg_3s = 15.78 t/s 5.47.800.992 I slot print_timing: id 1 | task 4028 | prompt eval time = 485.55 ms / 108 tokens ( 4.50 ms per token, 222.43 tokens per second) 5.47.800.998 I slot print_timing: id 1 | task 4028 | eval time = 7718.14 ms / 126 tokens ( 61.75 ms per token, 16.20 tokens per second) 5.47.800.999 I slot print_timing: id 1 | task 4028 | total time = 8203.68 ms / 234 tokens 5.47.801.000 I slot print_timing: id 1 | task 4028 | graphs reused = 3217 5.47.801.001 I slot print_timing: id 1 | task 4028 | graph reallocs = 0 / 0 (same size) / (changed size) 5.47.801.079 I slot release: id 1 | task 4028 | stop processing: n_tokens = 1358, truncated = 0 5.47.861.333 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.844 5.47.861.401 I slot launch_slot_: id 1 | task 4160 | processing task, is_child = 0 5.48.324.964 I slot print_timing: id 0 | task 4108 | prompt eval time = 469.90 ms / 128 tokens ( 3.67 ms per token, 272.40 tokens per second) 5.48.324.967 I slot print_timing: id 0 | task 4108 | eval time = 3043.14 ms / 52 tokens ( 59.67 ms per token, 16.76 tokens per second) 5.48.324.968 I slot print_timing: id 0 | task 4108 | total time = 3513.04 ms / 180 tokens 5.48.324.969 I slot print_timing: id 0 | task 4108 | graphs reused = 3217 5.48.324.969 I slot print_timing: id 0 | task 4108 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.325.051 I slot release: id 0 | task 4108 | stop processing: n_tokens = 1304, truncated = 0 5.48.371.280 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.879 5.48.371.316 I slot launch_slot_: id 0 | task 4164 | processing task, is_child = 0 5.49.849.762 I slot print_timing: id 2 | task 4080 | n_gen = 100, tg = 14.89 t/s, tg_3s = 15.04 t/s 5.50.622.802 I slot print_timing: id 3 | task 4100 | prompt eval time = 466.57 ms / 110 tokens ( 4.24 ms per token, 235.76 tokens per second) 5.50.622.807 I slot print_timing: id 3 | task 4100 | eval time = 6064.47 ms / 96 tokens ( 63.84 ms per token, 15.67 tokens per second) 5.50.622.807 I slot print_timing: id 3 | task 4100 | total time = 6531.04 ms / 206 tokens 5.50.622.808 I slot print_timing: id 3 | task 4100 | graphs reused = 3251 5.50.622.808 I slot print_timing: id 3 | task 4100 | graph reallocs = 0 / 0 (same size) / (changed size) 5.50.622.878 I slot release: id 3 | task 4100 | stop processing: n_tokens = 1330, truncated = 0 5.50.668.469 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.862 5.50.668.498 I slot launch_slot_: id 3 | task 4202 | processing task, is_child = 0 5.51.303.852 I slot print_timing: id 2 | task 4080 | prompt eval time = 577.05 ms / 166 tokens ( 3.48 ms per token, 287.67 tokens per second) 5.51.303.856 I slot print_timing: id 2 | task 4080 | eval time = 8104.81 ms / 122 tokens ( 66.98 ms per token, 14.93 tokens per second) 5.51.303.856 I slot print_timing: id 2 | task 4080 | total time = 8681.86 ms / 288 tokens 5.51.303.857 I slot print_timing: id 2 | task 4080 | graphs reused = 3254 5.51.303.857 I slot print_timing: id 2 | task 4080 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.303.906 I slot release: id 2 | task 4080 | stop processing: n_tokens = 1412, truncated = 0 5.52.872.139 I slot print_timing: id 1 | task 4160 | prompt eval time = 463.91 ms / 95 tokens ( 4.88 ms per token, 204.78 tokens per second) 5.52.872.144 I slot print_timing: id 1 | task 4160 | eval time = 4546.82 ms / 73 tokens ( 63.15 ms per token, 15.84 tokens per second) 5.52.872.145 I slot print_timing: id 1 | task 4160 | total time = 5010.73 ms / 168 tokens 5.52.872.145 I slot print_timing: id 1 | task 4160 | graphs reused = 3254 5.52.872.146 I slot print_timing: id 1 | task 4160 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.872.191 I slot release: id 1 | task 4160 | stop processing: n_tokens = 1292, truncated = 0 5.54.247.420 I slot print_timing: id 0 | task 4164 | prompt eval time = 497.06 ms / 142 tokens ( 3.50 ms per token, 285.68 tokens per second) 5.54.247.425 I slot print_timing: id 0 | task 4164 | eval time = 5379.03 ms / 100 tokens ( 54.33 ms per token, 18.40 tokens per second) 5.54.247.426 I slot print_timing: id 0 | task 4164 | total time = 5876.10 ms / 242 tokens 5.54.247.427 I slot print_timing: id 0 | task 4164 | graphs reused = 3254 5.54.247.428 I slot print_timing: id 0 | task 4164 | graph reallocs = 0 / 0 (same size) / (changed size) 5.54.247.505 I slot release: id 0 | task 4164 | stop processing: n_tokens = 1366, truncated = 0 5.54.452.529 I slot print_timing: id 3 | task 4202 | prompt eval time = 427.32 ms / 96 tokens ( 4.45 ms per token, 224.66 tokens per second) 5.54.452.532 I slot print_timing: id 3 | task 4202 | eval time = 3356.71 ms / 73 tokens ( 46.62 ms per token, 21.45 tokens per second) 5.54.452.533 I slot print_timing: id 3 | task 4202 | total time = 3784.02 ms / 169 tokens 5.54.452.534 I slot print_timing: id 3 | task 4202 | graphs reused = 3264 5.54.452.534 I slot print_timing: id 3 | task 4202 | graph reallocs = 0 / 0 (same size) / (changed size) 5.54.452.581 I slot release: id 3 | task 4202 | stop processing: n_tokens = 1293, truncated = 0 5.54.492.189 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1412, t_last = 391675171484 5.54.492.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 5.54.492.744 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.169 MiB) 5.54.492.754 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.794 MiB) 5.55.299.455 I slot launch_slot_: id 2 | task 4277 | processing task, is_child = 0 5.55.299.528 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 5.55.299.803 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.853 MiB) 5.55.299.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.658 MiB) 5.55.979.392 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.325 MiB) 5.55.979.414 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.797 MiB) 5.56.376.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.540 MiB) 5.56.376.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 5.56.376.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.618 MiB) 5.57.029.296 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1292, t_last = 391676739769 5.57.029.443 I slot launch_slot_: id 1 | task 4278 | processing task, is_child = 0 5.57.029.561 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1366, t_last = 391678115083 5.57.029.639 I slot launch_slot_: id 0 | task 4279 | processing task, is_child = 0 5.57.029.695 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1293, t_last = 391678320159 5.57.029.774 I slot launch_slot_: id 3 | task 4280 | processing task, is_child = 0 6.00.910.267 I slot print_timing: id 0 | task 4279 | prompt processing, n_tokens = 471, progress = 0.48, t = 3.88 s / 121.38 tokens per second 6.01.400.422 I slot print_timing: id 1 | task 4278 | prompt processing, n_tokens = 290, progress = 0.36, t = 3.88 s / 74.74 tokens per second 6.01.406.888 I slot print_timing: id 2 | task 4277 | prompt processing, n_tokens = 656, progress = 0.84, t = 3.88 s / 169.06 tokens per second 6.01.412.074 I slot print_timing: id 3 | task 4280 | prompt processing, n_tokens = 436, progress = 0.46, t = 3.88 s / 112.37 tokens per second 6.03.252.848 I slot print_timing: id 0 | task 4279 | prompt processing, n_tokens = 877, progress = 0.89, t = 6.22 s / 140.93 tokens per second 6.03.793.710 I slot print_timing: id 1 | task 4278 | prompt processing, n_tokens = 642, progress = 0.80, t = 6.22 s / 103.17 tokens per second 6.03.800.160 I slot print_timing: id 2 | task 4277 | prompt processing, n_tokens = 775, progress = 0.99, t = 6.22 s / 124.54 tokens per second 6.03.806.415 I slot print_timing: id 3 | task 4280 | prompt processing, n_tokens = 835, progress = 0.88, t = 6.22 s / 134.19 tokens per second 6.04.899.544 I slot print_timing: id 0 | task 4279 | prompt processing, n_tokens = 983, progress = 1.00, t = 7.87 s / 124.92 tokens per second 6.04.907.207 I slot print_timing: id 1 | task 4278 | prompt processing, n_tokens = 802, progress = 1.00, t = 7.87 s / 101.92 tokens per second 6.04.913.712 I slot print_timing: id 3 | task 4280 | prompt processing, n_tokens = 948, progress = 1.00, t = 7.87 s / 120.47 tokens per second 6.05.055.620 I slot print_timing: id 2 | task 4277 | prompt eval time = 7869.54 ms / 779 tokens ( 10.10 ms per token, 98.99 tokens per second) 6.05.055.624 I slot print_timing: id 2 | task 4277 | eval time = 156.09 ms / 2 tokens ( 156.09 ms per token, 6.41 tokens per second) 6.05.055.624 I slot print_timing: id 2 | task 4277 | total time = 8025.62 ms / 781 tokens 6.05.055.625 I slot print_timing: id 2 | task 4277 | graphs reused = 3264 6.05.055.625 I slot print_timing: id 2 | task 4277 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.056.969 I slot release: id 2 | task 4277 | stop processing: n_tokens = 780, truncated = 0 6.05.112.869 I slot print_timing: id 0 | task 4279 | prompt eval time = 8025.26 ms / 987 tokens ( 8.13 ms per token, 122.99 tokens per second) 6.05.112.874 I slot print_timing: id 0 | task 4279 | eval time = 57.82 ms / 2 tokens ( 57.82 ms per token, 17.29 tokens per second) 6.05.112.876 I slot print_timing: id 0 | task 4279 | total time = 8083.09 ms / 989 tokens 6.05.112.876 I slot print_timing: id 0 | task 4279 | graphs reused = 3264 6.05.112.876 I slot print_timing: id 0 | task 4279 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.112.984 I slot release: id 0 | task 4279 | stop processing: n_tokens = 988, truncated = 0 6.05.113.150 I slot print_timing: id 1 | task 4278 | prompt eval time = 8025.51 ms / 806 tokens ( 9.96 ms per token, 100.43 tokens per second) 6.05.113.152 I slot print_timing: id 1 | task 4278 | eval time = 57.73 ms / 2 tokens ( 57.73 ms per token, 17.32 tokens per second) 6.05.113.152 I slot print_timing: id 1 | task 4278 | total time = 8083.23 ms / 808 tokens 6.05.113.153 I slot print_timing: id 1 | task 4278 | graphs reused = 3264 6.05.113.153 I slot print_timing: id 1 | task 4278 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.113.222 I slot release: id 1 | task 4278 | stop processing: n_tokens = 807, truncated = 0 6.05.113.387 I slot print_timing: id 3 | task 4280 | prompt eval time = 8027.28 ms / 952 tokens ( 8.43 ms per token, 118.60 tokens per second) 6.05.113.389 I slot print_timing: id 3 | task 4280 | eval time = 56.01 ms / 2 tokens ( 56.01 ms per token, 17.85 tokens per second) 6.05.113.390 I slot print_timing: id 3 | task 4280 | total time = 8083.30 ms / 954 tokens 6.05.113.390 I slot print_timing: id 3 | task 4280 | graphs reused = 3264 6.05.113.390 I slot print_timing: id 3 | task 4280 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.114.643 I slot release: id 3 | task 4280 | stop processing: n_tokens = 953, truncated = 0 6.05.114.656 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 391688924548 6.05.114.708 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 6.05.114.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.716 MiB) 6.05.593.490 I slot launch_slot_: id 2 | task 4288 | processing task, is_child = 0 6.05.593.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.892 MiB) 6.05.593.832 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.875 MiB) 6.05.593.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.149 MiB) 6.06.015.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 6.06.015.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.758 MiB) 6.06.015.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.638 MiB) 6.06.316.815 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.146 MiB) 6.06.316.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.915 MiB) 6.06.640.343 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 391688980563 6.06.640.472 I slot launch_slot_: id 0 | task 4289 | processing task, is_child = 0 6.06.640.561 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 391688980802 6.06.640.623 I slot launch_slot_: id 1 | task 4290 | processing task, is_child = 0 6.06.640.668 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 391688982228 6.06.640.732 I slot launch_slot_: id 3 | task 4291 | processing task, is_child = 0 6.11.786.974 I slot print_timing: id 0 | task 4289 | prompt processing, n_tokens = 696, progress = 0.81, t = 5.15 s / 135.24 tokens per second 6.11.820.951 I slot print_timing: id 1 | task 4290 | prompt processing, n_tokens = 696, progress = 0.87, t = 5.15 s / 135.25 tokens per second 6.11.826.047 I slot print_timing: id 2 | task 4288 | prompt processing, n_tokens = 696, progress = 0.87, t = 5.15 s / 135.25 tokens per second 6.11.828.050 I slot print_timing: id 3 | task 4291 | prompt processing, n_tokens = 696, progress = 0.82, t = 5.15 s / 135.25 tokens per second 6.12.824.517 I slot print_timing: id 0 | task 4289 | prompt processing, n_tokens = 851, progress = 1.00, t = 6.18 s / 137.62 tokens per second 6.13.023.209 I slot print_timing: id 1 | task 4290 | prompt processing, n_tokens = 800, progress = 1.00, t = 6.18 s / 129.37 tokens per second 6.13.027.711 I slot print_timing: id 2 | task 4288 | prompt processing, n_tokens = 797, progress = 1.00, t = 6.18 s / 128.89 tokens per second 6.13.029.684 I slot print_timing: id 3 | task 4291 | prompt processing, n_tokens = 842, progress = 1.00, t = 6.18 s / 136.17 tokens per second 6.13.301.908 I slot print_timing: id 0 | task 4289 | prompt eval time = 6607.25 ms / 855 tokens ( 7.73 ms per token, 129.40 tokens per second) 6.13.301.914 I slot print_timing: id 0 | task 4289 | eval time = 53.92 ms / 2 tokens ( 53.92 ms per token, 18.55 tokens per second) 6.13.301.914 I slot print_timing: id 0 | task 4289 | total time = 6661.17 ms / 857 tokens 6.13.301.915 I slot print_timing: id 0 | task 4289 | graphs reused = 3264 6.13.301.915 I slot print_timing: id 0 | task 4289 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.302.989 I slot release: id 0 | task 4289 | stop processing: n_tokens = 856, truncated = 0 6.13.303.174 I slot print_timing: id 1 | task 4290 | prompt eval time = 6607.52 ms / 804 tokens ( 8.22 ms per token, 121.68 tokens per second) 6.13.303.176 I slot print_timing: id 1 | task 4290 | eval time = 54.83 ms / 2 tokens ( 54.83 ms per token, 18.24 tokens per second) 6.13.303.177 I slot print_timing: id 1 | task 4290 | total time = 6662.35 ms / 806 tokens 6.13.303.177 I slot print_timing: id 1 | task 4290 | graphs reused = 3264 6.13.303.178 I slot print_timing: id 1 | task 4290 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.303.203 I slot release: id 1 | task 4290 | stop processing: n_tokens = 805, truncated = 0 6.13.303.412 I slot print_timing: id 2 | task 4288 | prompt eval time = 6607.80 ms / 801 tokens ( 8.25 ms per token, 121.22 tokens per second) 6.13.303.415 I slot print_timing: id 2 | task 4288 | eval time = 54.74 ms / 2 tokens ( 54.74 ms per token, 18.27 tokens per second) 6.13.303.416 I slot print_timing: id 2 | task 4288 | total time = 6662.54 ms / 803 tokens 6.13.303.416 I slot print_timing: id 2 | task 4288 | graphs reused = 3264 6.13.303.416 I slot print_timing: id 2 | task 4288 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.303.436 I slot release: id 2 | task 4288 | stop processing: n_tokens = 802, truncated = 0 6.13.303.620 I slot print_timing: id 3 | task 4291 | prompt eval time = 6608.19 ms / 846 tokens ( 7.81 ms per token, 128.02 tokens per second) 6.13.303.621 I slot print_timing: id 3 | task 4291 | eval time = 54.51 ms / 2 tokens ( 54.51 ms per token, 18.35 tokens per second) 6.13.303.622 I slot print_timing: id 3 | task 4291 | total time = 6662.69 ms / 848 tokens 6.13.303.622 I slot print_timing: id 3 | task 4291 | graphs reused = 3264 6.13.303.622 I slot print_timing: id 3 | task 4291 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.304.420 I slot release: id 3 | task 4291 | stop processing: n_tokens = 847, truncated = 0 6.13.313.303 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.846 6.13.313.352 I slot launch_slot_: id 0 | task 4299 | processing task, is_child = 0 6.13.313.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.266 MiB) 6.13.313.417 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.286 MiB) 6.13.313.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.736 MiB) 6.14.134.821 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.934 MiB) 6.14.134.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 6.14.516.372 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.560 MiB) 6.14.516.408 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.716 MiB) 6.14.516.415 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.560 MiB) 6.15.236.176 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 805, t_last = 391697170781 6.15.236.298 I slot launch_slot_: id 1 | task 4300 | processing task, is_child = 0 6.15.236.381 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 802, t_last = 391697171014 6.15.236.442 I slot launch_slot_: id 2 | task 4301 | processing task, is_child = 0 6.15.236.483 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 391697171999 6.15.236.541 I slot launch_slot_: id 3 | task 4302 | processing task, is_child = 0 6.18.211.794 I slot print_timing: id 0 | task 4299 | prompt eval time = 2380.34 ms / 129 tokens ( 18.45 ms per token, 54.19 tokens per second) 6.18.211.796 I slot print_timing: id 0 | task 4299 | eval time = 594.90 ms / 2 tokens ( 594.90 ms per token, 1.68 tokens per second) 6.18.211.796 I slot print_timing: id 0 | task 4299 | total time = 2975.24 ms / 131 tokens 6.18.211.797 I slot print_timing: id 0 | task 4299 | graphs reused = 3264 6.18.211.797 I slot print_timing: id 0 | task 4299 | graph reallocs = 0 / 0 (same size) / (changed size) 6.18.213.117 I slot release: id 0 | task 4299 | stop processing: n_tokens = 826, truncated = 0 6.20.356.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 391702080697 6.20.356.639 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.677 MiB) 6.20.356.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.775 MiB) 6.20.356.668 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.658 MiB) 6.20.524.151 I slot launch_slot_: id 0 | task 4307 | processing task, is_child = 0 6.20.524.229 I slot print_timing: id 1 | task 4300 | prompt processing, n_tokens = 831, progress = 0.86, t = 5.12 s / 162.43 tokens per second 6.20.526.129 I slot print_timing: id 2 | task 4301 | prompt processing, n_tokens = 754, progress = 0.86, t = 5.12 s / 147.38 tokens per second 6.20.528.006 I slot print_timing: id 3 | task 4302 | prompt processing, n_tokens = 754, progress = 0.84, t = 5.12 s / 147.38 tokens per second 6.21.778.163 I slot print_timing: id 1 | task 4300 | prompt processing, n_tokens = 959, progress = 1.00, t = 6.44 s / 149.01 tokens per second 6.21.781.334 I slot print_timing: id 2 | task 4301 | prompt processing, n_tokens = 876, progress = 1.00, t = 6.44 s / 136.12 tokens per second 6.21.788.266 I slot print_timing: id 3 | task 4302 | prompt processing, n_tokens = 892, progress = 1.00, t = 6.44 s / 138.61 tokens per second 6.22.651.794 I slot print_timing: id 1 | task 4300 | prompt eval time = 7129.02 ms / 963 tokens ( 7.40 ms per token, 135.08 tokens per second) 6.22.651.799 I slot print_timing: id 1 | task 4300 | eval time = 282.25 ms / 2 tokens ( 282.25 ms per token, 3.54 tokens per second) 6.22.651.800 I slot print_timing: id 1 | task 4300 | total time = 7411.27 ms / 965 tokens 6.22.651.800 I slot print_timing: id 1 | task 4300 | graphs reused = 3264 6.22.651.800 I slot print_timing: id 1 | task 4300 | graph reallocs = 0 / 0 (same size) / (changed size) 6.22.653.518 I slot release: id 1 | task 4300 | stop processing: n_tokens = 964, truncated = 0 6.22.654.212 I slot print_timing: id 2 | task 4301 | prompt eval time = 7129.38 ms / 880 tokens ( 8.10 ms per token, 123.43 tokens per second) 6.22.654.216 I slot print_timing: id 2 | task 4301 | eval time = 284.24 ms / 2 tokens ( 284.24 ms per token, 3.52 tokens per second) 6.22.654.216 I slot print_timing: id 2 | task 4301 | total time = 7413.61 ms / 882 tokens 6.22.654.217 I slot print_timing: id 2 | task 4301 | graphs reused = 3264 6.22.654.217 I slot print_timing: id 2 | task 4301 | graph reallocs = 0 / 0 (same size) / (changed size) 6.22.655.849 I slot release: id 2 | task 4301 | stop processing: n_tokens = 881, truncated = 0 6.22.656.178 I slot print_timing: id 3 | task 4302 | prompt eval time = 7129.71 ms / 896 tokens ( 7.96 ms per token, 125.67 tokens per second) 6.22.656.181 I slot print_timing: id 3 | task 4302 | eval time = 285.81 ms / 2 tokens ( 285.81 ms per token, 3.50 tokens per second) 6.22.656.182 I slot print_timing: id 3 | task 4302 | total time = 7415.52 ms / 898 tokens 6.22.656.182 I slot print_timing: id 3 | task 4302 | graphs reused = 3264 6.22.656.183 I slot print_timing: id 3 | task 4302 | graph reallocs = 0 / 0 (same size) / (changed size) 6.22.656.227 I slot release: id 3 | task 4302 | stop processing: n_tokens = 897, truncated = 0 6.22.675.396 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 964, t_last = 391706521098 6.22.675.454 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.641 MiB) 6.22.675.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.875 MiB) 6.23.379.964 I slot launch_slot_: id 1 | task 4312 | processing task, is_child = 0 6.23.380.017 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.264 MiB) 6.23.380.026 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 6.23.380.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.797 MiB) 6.23.552.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.110 MiB) 6.23.552.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.853 MiB) 6.23.691.200 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 391706523428 6.23.691.315 I slot launch_slot_: id 2 | task 4313 | processing task, is_child = 0 6.23.691.360 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 391706523805 6.23.691.425 I slot launch_slot_: id 3 | task 4314 | processing task, is_child = 0 6.24.669.487 I slot print_timing: id 0 | task 4307 | prompt processing, n_tokens = 983, progress = 1.00, t = 4.15 s / 237.14 tokens per second 6.27.398.849 I slot print_timing: id 0 | task 4307 | prompt eval time = 5477.46 ms / 987 tokens ( 5.55 ms per token, 180.19 tokens per second) 6.27.398.854 I slot print_timing: id 0 | task 4307 | eval time = 1397.22 ms / 2 tokens ( 1397.22 ms per token, 0.72 tokens per second) 6.27.398.855 I slot print_timing: id 0 | task 4307 | total time = 6874.68 ms / 989 tokens 6.27.398.855 I slot print_timing: id 0 | task 4307 | graphs reused = 3264 6.27.398.856 I slot print_timing: id 0 | task 4307 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.400.163 I slot release: id 0 | task 4307 | stop processing: n_tokens = 988, truncated = 0 6.27.400.189 I slot print_timing: id 1 | task 4312 | prompt processing, n_tokens = 506, progress = 0.50, t = 3.70 s / 136.93 tokens per second 6.27.404.689 I slot print_timing: id 2 | task 4313 | prompt processing, n_tokens = 408, progress = 0.44, t = 3.70 s / 110.41 tokens per second 6.27.406.910 I slot print_timing: id 3 | task 4314 | prompt processing, n_tokens = 753, progress = 0.42, t = 3.70 s / 203.78 tokens per second 6.29.390.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 391711267743 6.29.390.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.091 MiB) 6.29.390.821 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 6.29.390.834 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.325 MiB) 6.29.784.766 I slot launch_slot_: id 0 | task 4319 | processing task, is_child = 0 6.29.784.856 I slot print_timing: id 1 | task 4312 | prompt processing, n_tokens = 872, progress = 0.85, t = 5.69 s / 153.32 tokens per second 6.29.787.189 I slot print_timing: id 2 | task 4313 | prompt processing, n_tokens = 753, progress = 0.81, t = 5.69 s / 132.40 tokens per second 6.29.789.352 I slot print_timing: id 3 | task 4314 | prompt processing, n_tokens = 1264, progress = 0.71, t = 5.69 s / 222.25 tokens per second 6.31.831.676 I slot print_timing: id 1 | task 4312 | prompt processing, n_tokens = 1018, progress = 1.00, t = 7.48 s / 136.09 tokens per second 6.31.886.296 I slot print_timing: id 2 | task 4313 | prompt processing, n_tokens = 920, progress = 1.00, t = 7.48 s / 122.99 tokens per second 6.31.933.475 I slot print_timing: id 3 | task 4314 | prompt processing, n_tokens = 1776, progress = 1.00, t = 7.48 s / 237.43 tokens per second 6.32.819.483 I slot print_timing: id 1 | task 4312 | prompt eval time = 8723.20 ms / 1022 tokens ( 8.54 ms per token, 117.16 tokens per second) 6.32.819.485 I slot print_timing: id 1 | task 4312 | eval time = 393.08 ms / 2 tokens ( 393.08 ms per token, 2.54 tokens per second) 6.32.819.485 I slot print_timing: id 1 | task 4312 | total time = 9116.28 ms / 1024 tokens 6.32.819.486 I slot print_timing: id 1 | task 4312 | graphs reused = 3264 6.32.819.486 I slot print_timing: id 1 | task 4312 | graph reallocs = 0 / 0 (same size) / (changed size) 6.32.820.310 I slot release: id 1 | task 4312 | stop processing: n_tokens = 1023, truncated = 0 6.32.820.515 I slot print_timing: id 2 | task 4313 | prompt eval time = 8723.30 ms / 924 tokens ( 9.44 ms per token, 105.92 tokens per second) 6.32.820.521 I slot print_timing: id 2 | task 4313 | eval time = 393.93 ms / 2 tokens ( 393.93 ms per token, 2.54 tokens per second) 6.32.820.523 I slot print_timing: id 2 | task 4313 | total time = 9117.24 ms / 926 tokens 6.32.820.523 I slot print_timing: id 2 | task 4313 | graphs reused = 3264 6.32.820.524 I slot print_timing: id 2 | task 4313 | graph reallocs = 0 / 0 (same size) / (changed size) 6.32.820.656 I slot release: id 2 | task 4313 | stop processing: n_tokens = 925, truncated = 0 6.32.820.992 I slot print_timing: id 3 | task 4314 | prompt eval time = 8723.48 ms / 1780 tokens ( 4.90 ms per token, 204.05 tokens per second) 6.32.820.997 I slot print_timing: id 3 | task 4314 | eval time = 394.19 ms / 2 tokens ( 394.19 ms per token, 2.54 tokens per second) 6.32.820.997 I slot print_timing: id 3 | task 4314 | total time = 9117.66 ms / 1782 tokens 6.32.820.998 I slot print_timing: id 3 | task 4314 | graphs reused = 3264 6.32.820.998 I slot print_timing: id 3 | task 4314 | graph reallocs = 0 / 0 (same size) / (changed size) 6.32.823.433 I slot release: id 3 | task 4314 | stop processing: n_tokens = 1781, truncated = 0 6.32.823.450 I slot print_timing: id 0 | task 4319 | prompt processing, n_tokens = 421, progress = 0.45, t = 3.03 s / 138.73 tokens per second 6.32.831.170 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1023, t_last = 391716687889 6.32.831.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.345 MiB) 6.32.831.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.993 MiB) 6.33.451.714 I slot launch_slot_: id 1 | task 4324 | processing task, is_child = 0 6.33.451.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.736 MiB) 6.33.451.778 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.384 MiB) 6.33.451.787 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.931 MiB) 6.33.635.553 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.660 MiB) 6.33.635.630 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.247 MiB) 6.33.636.025 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.205 MiB) 6.34.104.979 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 391716688235 6.34.105.141 I slot launch_slot_: id 2 | task 4325 | processing task, is_child = 0 6.34.105.229 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1781, t_last = 391716691012 6.34.105.372 I slot launch_slot_: id 3 | task 4326 | processing task, is_child = 0 6.34.105.384 I slot print_timing: id 0 | task 4319 | prompt processing, n_tokens = 753, progress = 0.80, t = 3.05 s / 247.18 tokens per second 6.35.251.430 I slot print_timing: id 0 | task 4319 | prompt processing, n_tokens = 933, progress = 1.00, t = 5.47 s / 170.67 tokens per second 6.38.020.064 I slot print_timing: id 0 | task 4319 | prompt eval time = 6522.53 ms / 937 tokens ( 6.96 ms per token, 143.66 tokens per second) 6.38.020.067 I slot print_timing: id 0 | task 4319 | eval time = 1712.75 ms / 2 tokens ( 1712.75 ms per token, 0.58 tokens per second) 6.38.020.068 I slot print_timing: id 0 | task 4319 | total time = 8235.28 ms / 939 tokens 6.38.020.068 I slot print_timing: id 0 | task 4319 | graphs reused = 3264 6.38.020.069 I slot print_timing: id 0 | task 4319 | graph reallocs = 0 / 0 (same size) / (changed size) 6.38.020.196 I slot release: id 0 | task 4319 | stop processing: n_tokens = 938, truncated = 0 6.38.020.212 I slot print_timing: id 1 | task 4324 | prompt processing, n_tokens = 603, progress = 0.85, t = 3.81 s / 158.27 tokens per second 6.38.023.779 I slot print_timing: id 2 | task 4325 | prompt processing, n_tokens = 364, progress = 0.41, t = 3.81 s / 95.54 tokens per second 6.38.030.639 I slot print_timing: id 3 | task 4326 | prompt processing, n_tokens = 603, progress = 0.81, t = 3.81 s / 158.28 tokens per second 6.38.848.333 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 391721887775 6.38.848.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.677 MiB) 6.38.848.419 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 6.39.396.155 I slot launch_slot_: id 0 | task 4331 | processing task, is_child = 0 6.39.396.277 I slot print_timing: id 1 | task 4324 | prompt processing, n_tokens = 709, progress = 0.99, t = 4.64 s / 152.86 tokens per second 6.39.398.373 I slot print_timing: id 2 | task 4325 | prompt processing, n_tokens = 769, progress = 0.87, t = 4.64 s / 165.80 tokens per second 6.39.402.279 I slot print_timing: id 3 | task 4326 | prompt processing, n_tokens = 737, progress = 0.99, t = 4.64 s / 158.90 tokens per second 6.40.260.824 I slot print_timing: id 2 | task 4325 | prompt processing, n_tokens = 876, progress = 1.00, t = 5.93 s / 147.71 tokens per second 6.40.625.646 I slot print_timing: id 1 | task 4324 | prompt eval time = 5930.78 ms / 713 tokens ( 8.32 ms per token, 120.22 tokens per second) 6.40.625.649 I slot print_timing: id 1 | task 4324 | eval time = 484.83 ms / 2 tokens ( 484.83 ms per token, 2.06 tokens per second) 6.40.625.650 I slot print_timing: id 1 | task 4324 | total time = 6415.61 ms / 715 tokens 6.40.625.650 I slot print_timing: id 1 | task 4324 | graphs reused = 3264 6.40.625.651 I slot print_timing: id 1 | task 4324 | graph reallocs = 0 / 0 (same size) / (changed size) 6.40.626.908 I slot release: id 1 | task 4324 | stop processing: n_tokens = 714, truncated = 0 6.40.628.166 I slot print_timing: id 3 | task 4326 | prompt eval time = 5931.33 ms / 741 tokens ( 8.00 ms per token, 124.93 tokens per second) 6.40.628.175 I slot print_timing: id 3 | task 4326 | eval time = 486.65 ms / 2 tokens ( 486.65 ms per token, 2.05 tokens per second) 6.40.628.175 I slot print_timing: id 3 | task 4326 | total time = 6417.98 ms / 743 tokens 6.40.628.176 I slot print_timing: id 3 | task 4326 | graphs reused = 3264 6.40.628.176 I slot print_timing: id 3 | task 4326 | graph reallocs = 0 / 0 (same size) / (changed size) 6.40.628.207 I slot release: id 3 | task 4326 | stop processing: n_tokens = 742, truncated = 0 6.41.397.508 I slot print_timing: id 2 | task 4325 | prompt eval time = 6417.56 ms / 880 tokens ( 7.29 ms per token, 137.12 tokens per second) 6.41.397.511 I slot print_timing: id 2 | task 4325 | eval time = 769.83 ms / 2 tokens ( 769.83 ms per token, 1.30 tokens per second) 6.41.397.512 I slot print_timing: id 2 | task 4325 | total time = 7187.39 ms / 882 tokens 6.41.397.512 I slot print_timing: id 2 | task 4325 | graphs reused = 3264 6.41.397.513 I slot print_timing: id 2 | task 4325 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.399.315 I slot release: id 2 | task 4325 | stop processing: n_tokens = 881, truncated = 0 6.41.399.336 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.884 6.41.399.444 I slot launch_slot_: id 1 | task 4335 | processing task, is_child = 0 6.41.399.531 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.071 MiB) 6.41.399.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 341.540 MiB) 6.41.567.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.660 MiB) 6.41.614.825 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.850 6.41.614.900 I slot launch_slot_: id 3 | task 4336 | processing task, is_child = 0 6.41.614.951 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 391725266894 6.41.615.018 I slot launch_slot_: id 2 | task 4337 | processing task, is_child = 0 6.42.563.748 I slot print_timing: id 0 | task 4331 | prompt processing, n_tokens = 712, progress = 0.99, t = 3.17 s / 224.78 tokens per second 6.43.446.715 I slot print_timing: id 0 | task 4331 | prompt eval time = 3738.57 ms / 716 tokens ( 5.22 ms per token, 191.52 tokens per second) 6.43.446.717 I slot print_timing: id 0 | task 4331 | eval time = 311.96 ms / 2 tokens ( 311.96 ms per token, 3.21 tokens per second) 6.43.446.718 I slot print_timing: id 0 | task 4331 | total time = 4050.53 ms / 718 tokens 6.43.446.718 I slot print_timing: id 0 | task 4331 | graphs reused = 3264 6.43.446.719 I slot print_timing: id 0 | task 4331 | graph reallocs = 0 / 0 (same size) / (changed size) 6.43.446.764 I slot release: id 0 | task 4331 | stop processing: n_tokens = 717, truncated = 0 6.43.446.999 I slot print_timing: id 1 | task 4335 | prompt eval time = 1507.93 ms / 116 tokens ( 13.00 ms per token, 76.93 tokens per second) 6.43.447.001 I slot print_timing: id 1 | task 4335 | eval time = 312.08 ms / 2 tokens ( 312.08 ms per token, 3.20 tokens per second) 6.43.447.002 I slot print_timing: id 1 | task 4335 | total time = 1820.02 ms / 118 tokens 6.43.447.002 I slot print_timing: id 1 | task 4335 | graphs reused = 3264 6.43.447.002 I slot print_timing: id 1 | task 4335 | graph reallocs = 0 / 0 (same size) / (changed size) 6.43.447.024 I slot release: id 1 | task 4335 | stop processing: n_tokens = 720, truncated = 0 6.43.447.284 I slot print_timing: id 3 | task 4336 | prompt eval time = 1504.86 ms / 122 tokens ( 12.33 ms per token, 81.07 tokens per second) 6.43.447.290 I slot print_timing: id 3 | task 4336 | eval time = 312.12 ms / 2 tokens ( 312.12 ms per token, 3.20 tokens per second) 6.43.447.292 I slot print_timing: id 3 | task 4336 | total time = 1816.98 ms / 124 tokens 6.43.447.292 I slot print_timing: id 3 | task 4336 | graphs reused = 3264 6.43.447.292 I slot print_timing: id 3 | task 4336 | graph reallocs = 0 / 0 (same size) / (changed size) 6.43.447.312 I slot release: id 3 | task 4336 | stop processing: n_tokens = 726, truncated = 0 6.44.164.700 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 391727314342 6.44.164.749 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.680 MiB) 6.44.474.009 I slot launch_slot_: id 0 | task 4343 | processing task, is_child = 0 6.44.474.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.956 MiB) 6.44.520.574 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 341.677 MiB) 6.44.558.240 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 391727314602 6.44.558.341 I slot launch_slot_: id 1 | task 4344 | processing task, is_child = 0 6.44.558.381 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 391727314890 6.44.558.440 I slot launch_slot_: id 3 | task 4345 | processing task, is_child = 0 6.46.702.925 I slot print_timing: id 2 | task 4337 | prompt eval time = 3912.20 ms / 876 tokens ( 4.47 ms per token, 223.91 tokens per second) 6.46.702.930 I slot print_timing: id 2 | task 4337 | eval time = 1160.48 ms / 2 tokens ( 1160.48 ms per token, 0.86 tokens per second) 6.46.702.932 I slot print_timing: id 2 | task 4337 | total time = 5072.68 ms / 878 tokens 6.46.702.932 I slot print_timing: id 2 | task 4337 | graphs reused = 3264 6.46.702.933 I slot print_timing: id 2 | task 4337 | graph reallocs = 0 / 0 (same size) / (changed size) 6.46.704.507 I slot release: id 2 | task 4337 | stop processing: n_tokens = 877, truncated = 0 6.47.295.618 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 391730572086 6.47.295.675 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.777 MiB) 6.47.690.219 I slot launch_slot_: id 2 | task 4349 | processing task, is_child = 0 6.49.633.097 I slot print_timing: id 0 | task 4343 | prompt processing, n_tokens = 861, progress = 0.87, t = 5.07 s / 169.67 tokens per second 6.50.064.671 I slot print_timing: id 1 | task 4344 | prompt processing, n_tokens = 861, progress = 0.86, t = 5.07 s / 169.67 tokens per second 6.50.068.859 I slot print_timing: id 3 | task 4345 | prompt processing, n_tokens = 861, progress = 0.83, t = 5.07 s / 169.74 tokens per second 6.51.379.447 I slot print_timing: id 0 | task 4343 | prompt processing, n_tokens = 988, progress = 1.00, t = 6.82 s / 144.85 tokens per second 6.51.558.939 I slot print_timing: id 1 | task 4344 | prompt processing, n_tokens = 1002, progress = 1.00, t = 6.82 s / 146.90 tokens per second 6.51.571.479 I slot print_timing: id 2 | task 4349 | prompt processing, n_tokens = 345, progress = 0.35, t = 3.69 s / 93.61 tokens per second 6.51.571.490 I slot print_timing: id 3 | task 4345 | prompt processing, n_tokens = 1030, progress = 1.00, t = 6.82 s / 151.05 tokens per second 6.52.031.059 I slot print_timing: id 2 | task 4349 | prompt processing, n_tokens = 483, progress = 0.48, t = 4.34 s / 111.38 tokens per second 6.52.762.996 I slot print_timing: id 0 | task 4343 | prompt eval time = 7472.16 ms / 992 tokens ( 7.53 ms per token, 132.76 tokens per second) 6.52.763.001 I slot print_timing: id 0 | task 4343 | eval time = 732.38 ms / 2 tokens ( 732.38 ms per token, 1.37 tokens per second) 6.52.763.002 I slot print_timing: id 0 | task 4343 | total time = 8204.54 ms / 994 tokens 6.52.763.002 I slot print_timing: id 0 | task 4343 | graphs reused = 3264 6.52.763.003 I slot print_timing: id 0 | task 4343 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.763.050 I slot release: id 0 | task 4343 | stop processing: n_tokens = 993, truncated = 0 6.52.763.290 I slot print_timing: id 1 | task 4344 | prompt eval time = 7472.33 ms / 1006 tokens ( 7.43 ms per token, 134.63 tokens per second) 6.52.763.294 I slot print_timing: id 1 | task 4344 | eval time = 732.46 ms / 2 tokens ( 732.46 ms per token, 1.37 tokens per second) 6.52.763.295 I slot print_timing: id 1 | task 4344 | total time = 8204.79 ms / 1008 tokens 6.52.763.295 I slot print_timing: id 1 | task 4344 | graphs reused = 3264 6.52.763.295 I slot print_timing: id 1 | task 4344 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.763.320 I slot release: id 1 | task 4344 | stop processing: n_tokens = 1007, truncated = 0 6.52.763.483 I slot print_timing: id 3 | task 4345 | prompt eval time = 7470.54 ms / 1034 tokens ( 7.22 ms per token, 138.41 tokens per second) 6.52.763.487 I slot print_timing: id 3 | task 4345 | eval time = 732.43 ms / 2 tokens ( 732.43 ms per token, 1.37 tokens per second) 6.52.763.488 I slot print_timing: id 3 | task 4345 | total time = 8202.97 ms / 1036 tokens 6.52.763.488 I slot print_timing: id 3 | task 4345 | graphs reused = 3264 6.52.763.488 I slot print_timing: id 3 | task 4345 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.763.525 I slot release: id 3 | task 4345 | stop processing: n_tokens = 1035, truncated = 0 6.52.763.533 I slot print_timing: id 2 | task 4349 | prompt processing, n_tokens = 861, progress = 0.86, t = 5.07 s / 169.86 tokens per second 6.52.771.735 I slot print_timing: id 2 | task 4349 | prompt processing, n_tokens = 995, progress = 1.00, t = 5.08 s / 195.96 tokens per second 6.53.163.189 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 993, t_last = 391736630628 6.53.163.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.330 MiB) 6.53.209.989 I slot launch_slot_: id 0 | task 4356 | processing task, is_child = 0 6.53.210.045 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.350 MiB) 6.53.257.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.319 MiB) 6.53.308.423 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.883 6.53.308.496 I slot launch_slot_: id 1 | task 4357 | processing task, is_child = 0 6.53.308.554 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 391736631103 6.53.308.632 I slot launch_slot_: id 3 | task 4358 | processing task, is_child = 0 6.54.435.249 I slot print_timing: id 2 | task 4349 | prompt eval time = 5469.14 ms / 999 tokens ( 5.47 ms per token, 182.66 tokens per second) 6.54.435.252 I slot print_timing: id 2 | task 4349 | eval time = 1272.06 ms / 2 tokens ( 1272.06 ms per token, 0.79 tokens per second) 6.54.435.252 I slot print_timing: id 2 | task 4349 | total time = 6741.19 ms / 1001 tokens 6.54.435.253 I slot print_timing: id 2 | task 4349 | graphs reused = 3264 6.54.435.253 I slot print_timing: id 2 | task 4349 | graph reallocs = 0 / 0 (same size) / (changed size) 6.54.435.300 I slot release: id 2 | task 4349 | stop processing: n_tokens = 1000, truncated = 0 6.55.253.071 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 391738302878 6.55.253.134 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.386 MiB) 6.55.343.954 I slot launch_slot_: id 2 | task 4361 | processing task, is_child = 0 6.56.316.642 I slot print_timing: id 1 | task 4357 | prompt eval time = 1944.35 ms / 132 tokens ( 14.73 ms per token, 67.89 tokens per second) 6.56.316.644 I slot print_timing: id 1 | task 4357 | eval time = 1063.57 ms / 2 tokens ( 1063.57 ms per token, 0.94 tokens per second) 6.56.316.645 I slot print_timing: id 1 | task 4357 | total time = 3007.92 ms / 134 tokens 6.56.316.645 I slot print_timing: id 1 | task 4357 | graphs reused = 3264 6.56.316.646 I slot print_timing: id 1 | task 4357 | graph reallocs = 0 / 0 (same size) / (changed size) 6.56.316.693 I slot release: id 1 | task 4357 | stop processing: n_tokens = 994, truncated = 0 6.56.316.704 I slot print_timing: id 0 | task 4356 | prompt processing, n_tokens = 363, progress = 0.41, t = 3.01 s / 120.69 tokens per second 6.56.333.661 I slot print_timing: id 3 | task 4358 | prompt processing, n_tokens = 502, progress = 0.49, t = 3.00 s / 167.09 tokens per second 6.57.657.269 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 391740184271 6.57.657.339 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.847 MiB) 6.57.931.233 I slot launch_slot_: id 1 | task 4364 | processing task, is_child = 0 6.57.931.249 I slot print_timing: id 0 | task 4356 | prompt processing, n_tokens = 730, progress = 0.83, t = 4.35 s / 167.87 tokens per second 6.57.933.992 I slot print_timing: id 3 | task 4358 | prompt processing, n_tokens = 773, progress = 0.76, t = 4.35 s / 177.89 tokens per second 6.58.984.151 I slot print_timing: id 0 | task 4356 | prompt processing, n_tokens = 875, progress = 1.00, t = 5.68 s / 154.17 tokens per second 6.59.356.443 I slot print_timing: id 2 | task 4361 | prompt processing, n_tokens = 380, progress = 0.42, t = 3.64 s / 104.39 tokens per second 6.59.358.324 I slot print_timing: id 3 | task 4358 | prompt processing, n_tokens = 1014, progress = 1.00, t = 5.67 s / 178.77 tokens per second 7.00.558.775 I slot print_timing: id 2 | task 4361 | prompt processing, n_tokens = 773, progress = 0.86, t = 5.21 s / 148.26 tokens per second 7.01.389.688 I slot print_timing: id 0 | task 4356 | prompt eval time = 7249.40 ms / 879 tokens ( 8.25 ms per token, 121.25 tokens per second) 7.01.389.693 I slot print_timing: id 0 | task 4356 | eval time = 831.64 ms / 2 tokens ( 831.64 ms per token, 1.20 tokens per second) 7.01.389.693 I slot print_timing: id 0 | task 4356 | total time = 8081.04 ms / 881 tokens 7.01.389.694 I slot print_timing: id 0 | task 4356 | graphs reused = 3264 7.01.389.694 I slot print_timing: id 0 | task 4356 | graph reallocs = 0 / 0 (same size) / (changed size) 7.01.389.759 I slot release: id 0 | task 4356 | stop processing: n_tokens = 880, truncated = 0 7.01.390.009 I slot print_timing: id 3 | task 4358 | prompt eval time = 7246.83 ms / 1018 tokens ( 7.12 ms per token, 140.48 tokens per second) 7.01.390.012 I slot print_timing: id 3 | task 4358 | eval time = 831.26 ms / 2 tokens ( 831.26 ms per token, 1.20 tokens per second) 7.01.390.012 I slot print_timing: id 3 | task 4358 | total time = 8078.08 ms / 1020 tokens 7.01.390.013 I slot print_timing: id 3 | task 4358 | graphs reused = 3264 7.01.390.013 I slot print_timing: id 3 | task 4358 | graph reallocs = 0 / 0 (same size) / (changed size) 7.01.391.781 I slot release: id 3 | task 4358 | stop processing: n_tokens = 1019, truncated = 0 7.01.391.803 I slot print_timing: id 1 | task 4364 | prompt processing, n_tokens = 493, progress = 0.49, t = 3.46 s / 142.67 tokens per second 7.01.405.630 I slot print_timing: id 2 | task 4361 | prompt processing, n_tokens = 892, progress = 1.00, t = 6.05 s / 147.55 tokens per second 7.02.013.649 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 7.02.013.717 I slot launch_slot_: id 3 | task 4369 | processing task, is_child = 0 7.02.013.773 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.701 MiB) 7.02.076.754 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 391745257340 7.02.076.868 I slot launch_slot_: id 0 | task 4370 | processing task, is_child = 0 7.02.076.952 I slot print_timing: id 1 | task 4364 | prompt processing, n_tokens = 773, progress = 0.77, t = 4.08 s / 189.50 tokens per second 7.03.250.494 I slot print_timing: id 2 | task 4361 | prompt eval time = 6669.66 ms / 896 tokens ( 7.44 ms per token, 134.34 tokens per second) 7.03.250.497 I slot print_timing: id 2 | task 4361 | eval time = 1236.84 ms / 2 tokens ( 1236.84 ms per token, 0.81 tokens per second) 7.03.250.497 I slot print_timing: id 2 | task 4361 | total time = 7906.51 ms / 898 tokens 7.03.250.498 I slot print_timing: id 2 | task 4361 | graphs reused = 3264 7.03.250.498 I slot print_timing: id 2 | task 4361 | graph reallocs = 0 / 0 (same size) / (changed size) 7.03.250.587 I slot release: id 2 | task 4361 | stop processing: n_tokens = 897, truncated = 0 7.03.254.244 I slot print_timing: id 1 | task 4364 | prompt processing, n_tokens = 1005, progress = 1.00, t = 5.32 s / 189.04 tokens per second 7.03.763.797 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.893 7.03.763.872 I slot launch_slot_: id 2 | task 4373 | processing task, is_child = 0 7.04.536.711 I slot print_timing: id 1 | task 4364 | prompt eval time = 5829.74 ms / 1009 tokens ( 5.78 ms per token, 173.08 tokens per second) 7.04.536.713 I slot print_timing: id 1 | task 4364 | eval time = 773.08 ms / 2 tokens ( 773.08 ms per token, 1.29 tokens per second) 7.04.536.714 I slot print_timing: id 1 | task 4364 | total time = 6602.83 ms / 1011 tokens 7.04.536.714 I slot print_timing: id 1 | task 4364 | graphs reused = 3264 7.04.536.715 I slot print_timing: id 1 | task 4364 | graph reallocs = 0 / 0 (same size) / (changed size) 7.04.537.162 I slot release: id 1 | task 4364 | stop processing: n_tokens = 1010, truncated = 0 7.04.537.624 I slot print_timing: id 3 | task 4369 | prompt eval time = 1684.96 ms / 129 tokens ( 13.06 ms per token, 76.56 tokens per second) 7.04.537.626 I slot print_timing: id 3 | task 4369 | eval time = 773.83 ms / 2 tokens ( 773.83 ms per token, 1.29 tokens per second) 7.04.537.627 I slot print_timing: id 3 | task 4369 | total time = 2458.79 ms / 131 tokens 7.04.537.627 I slot print_timing: id 3 | task 4369 | graphs reused = 3264 7.04.537.628 I slot print_timing: id 3 | task 4369 | graph reallocs = 0 / 0 (same size) / (changed size) 7.04.537.663 I slot release: id 3 | task 4369 | stop processing: n_tokens = 903, truncated = 0 7.05.156.275 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1010, t_last = 391748404741 7.05.156.335 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.807 MiB) 7.05.231.687 I slot launch_slot_: id 1 | task 4376 | processing task, is_child = 0 7.05.231.741 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.749 MiB) 7.05.289.795 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 391748405241 7.05.289.904 I slot launch_slot_: id 3 | task 4377 | processing task, is_child = 0 7.05.289.912 I slot print_timing: id 0 | task 4370 | prompt processing, n_tokens = 773, progress = 0.78, t = 3.08 s / 251.05 tokens per second 7.06.416.427 I slot print_timing: id 2 | task 4373 | prompt eval time = 1392.38 ms / 108 tokens ( 12.89 ms per token, 77.56 tokens per second) 7.06.416.430 I slot print_timing: id 2 | task 4373 | eval time = 1260.15 ms / 2 tokens ( 1260.15 ms per token, 0.79 tokens per second) 7.06.416.430 I slot print_timing: id 2 | task 4373 | total time = 2652.53 ms / 110 tokens 7.06.416.431 I slot print_timing: id 2 | task 4373 | graphs reused = 3264 7.06.416.431 I slot print_timing: id 2 | task 4373 | graph reallocs = 0 / 0 (same size) / (changed size) 7.06.416.491 I slot release: id 2 | task 4373 | stop processing: n_tokens = 882, truncated = 0 7.06.416.502 I slot print_timing: id 0 | task 4370 | prompt processing, n_tokens = 981, progress = 1.00, t = 4.34 s / 226.07 tokens per second 7.07.124.399 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 391750284069 7.07.124.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.629 MiB) 7.07.178.424 I slot launch_slot_: id 2 | task 4380 | processing task, is_child = 0 7.08.283.500 I slot print_timing: id 0 | task 4370 | prompt eval time = 5047.51 ms / 985 tokens ( 5.12 ms per token, 195.15 tokens per second) 7.08.283.503 I slot print_timing: id 0 | task 4370 | eval time = 1159.11 ms / 2 tokens ( 1159.11 ms per token, 0.86 tokens per second) 7.08.283.503 I slot print_timing: id 0 | task 4370 | total time = 6206.62 ms / 987 tokens 7.08.283.504 I slot print_timing: id 0 | task 4370 | graphs reused = 3264 7.08.283.504 I slot print_timing: id 0 | task 4370 | graph reallocs = 0 / 0 (same size) / (changed size) 7.08.283.575 I slot release: id 0 | task 4370 | stop processing: n_tokens = 986, truncated = 0 7.09.395.534 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 391752151154 7.09.395.596 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.218 MiB) 7.09.931.213 I slot launch_slot_: id 0 | task 4383 | processing task, is_child = 0 7.09.931.305 I slot print_timing: id 1 | task 4376 | prompt processing, n_tokens = 774, progress = 0.81, t = 4.09 s / 189.06 tokens per second 7.09.933.223 I slot print_timing: id 3 | task 4377 | prompt processing, n_tokens = 774, progress = 0.85, t = 4.09 s / 189.06 tokens per second 7.11.315.629 I slot print_timing: id 1 | task 4376 | prompt processing, n_tokens = 948, progress = 1.00, t = 5.89 s / 160.93 tokens per second 7.11.319.573 I slot print_timing: id 2 | task 4380 | prompt processing, n_tokens = 424, progress = 0.45, t = 4.01 s / 105.63 tokens per second 7.11.321.662 I slot print_timing: id 3 | task 4377 | prompt processing, n_tokens = 902, progress = 1.00, t = 5.89 s / 153.12 tokens per second 7.12.565.096 I slot print_timing: id 2 | task 4380 | prompt processing, n_tokens = 774, progress = 0.82, t = 5.39 s / 143.70 tokens per second 7.13.745.854 I slot print_timing: id 1 | task 4376 | prompt eval time = 7263.28 ms / 952 tokens ( 7.63 ms per token, 131.07 tokens per second) 7.13.745.857 I slot print_timing: id 1 | task 4376 | eval time = 1180.99 ms / 2 tokens ( 1180.99 ms per token, 0.85 tokens per second) 7.13.745.857 I slot print_timing: id 1 | task 4376 | total time = 8444.27 ms / 954 tokens 7.13.745.858 I slot print_timing: id 1 | task 4376 | graphs reused = 3264 7.13.745.858 I slot print_timing: id 1 | task 4376 | graph reallocs = 0 / 0 (same size) / (changed size) 7.13.747.982 I slot release: id 1 | task 4376 | stop processing: n_tokens = 953, truncated = 0 7.13.748.444 I slot print_timing: id 3 | task 4377 | prompt eval time = 7263.43 ms / 906 tokens ( 8.02 ms per token, 124.73 tokens per second) 7.13.748.447 I slot print_timing: id 3 | task 4377 | eval time = 1183.36 ms / 2 tokens ( 1183.36 ms per token, 0.85 tokens per second) 7.13.748.448 I slot print_timing: id 3 | task 4377 | total time = 8446.80 ms / 908 tokens 7.13.748.448 I slot print_timing: id 3 | task 4377 | graphs reused = 3264 7.13.748.449 I slot print_timing: id 3 | task 4377 | graph reallocs = 0 / 0 (same size) / (changed size) 7.13.748.522 I slot release: id 3 | task 4377 | stop processing: n_tokens = 907, truncated = 0 7.13.748.543 I slot print_timing: id 0 | task 4383 | prompt processing, n_tokens = 840, progress = 0.62, t = 3.81 s / 220.22 tokens per second 7.13.760.056 I slot print_timing: id 2 | task 4380 | prompt processing, n_tokens = 936, progress = 1.00, t = 6.57 s / 142.53 tokens per second 7.14.400.956 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 391757615561 7.14.401.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.917 MiB) 7.14.460.762 I slot launch_slot_: id 1 | task 4388 | processing task, is_child = 0 7.14.460.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.294 MiB) 7.14.512.473 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 391757616100 7.14.512.586 I slot launch_slot_: id 3 | task 4389 | processing task, is_child = 0 7.14.512.595 I slot print_timing: id 0 | task 4383 | prompt processing, n_tokens = 1152, progress = 0.85, t = 4.47 s / 257.74 tokens per second 7.15.791.937 I slot print_timing: id 2 | task 4380 | prompt eval time = 7222.49 ms / 940 tokens ( 7.68 ms per token, 130.15 tokens per second) 7.15.791.940 I slot print_timing: id 2 | task 4380 | eval time = 1390.99 ms / 2 tokens ( 1390.99 ms per token, 0.72 tokens per second) 7.15.791.940 I slot print_timing: id 2 | task 4380 | total time = 8613.48 ms / 942 tokens 7.15.791.941 I slot print_timing: id 2 | task 4380 | graphs reused = 3264 7.15.791.941 I slot print_timing: id 2 | task 4380 | graph reallocs = 0 / 0 (same size) / (changed size) 7.15.791.986 I slot release: id 2 | task 4380 | stop processing: n_tokens = 941, truncated = 0 7.15.791.996 I slot print_timing: id 0 | task 4383 | prompt processing, n_tokens = 1352, progress = 1.00, t = 5.86 s / 230.70 tokens per second 7.16.860.443 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 391759659564 7.16.860.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.606 MiB) 7.16.897.329 I slot launch_slot_: id 2 | task 4392 | processing task, is_child = 0 7.18.718.914 I slot print_timing: id 0 | task 4383 | prompt eval time = 6929.20 ms / 1356 tokens ( 5.11 ms per token, 195.69 tokens per second) 7.18.718.920 I slot print_timing: id 0 | task 4383 | eval time = 1858.48 ms / 2 tokens ( 1858.48 ms per token, 0.54 tokens per second) 7.18.718.920 I slot print_timing: id 0 | task 4383 | total time = 8787.68 ms / 1358 tokens 7.18.718.921 I slot print_timing: id 0 | task 4383 | graphs reused = 3264 7.18.718.921 I slot print_timing: id 0 | task 4383 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.721.046 I slot release: id 0 | task 4383 | stop processing: n_tokens = 1357, truncated = 0 7.18.721.074 I slot print_timing: id 1 | task 4388 | prompt processing, n_tokens = 826, progress = 0.62, t = 4.19 s / 196.91 tokens per second 7.18.738.769 I slot print_timing: id 3 | task 4389 | prompt processing, n_tokens = 743, progress = 0.59, t = 4.19 s / 177.12 tokens per second 7.20.379.254 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1357, t_last = 391762588625 7.20.379.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.386 MiB) 7.20.747.138 I slot launch_slot_: id 0 | task 4395 | processing task, is_child = 0 7.20.747.252 I slot print_timing: id 1 | task 4388 | prompt processing, n_tokens = 1152, progress = 0.86, t = 5.86 s / 196.74 tokens per second 7.20.749.460 I slot print_timing: id 2 | task 4392 | prompt processing, n_tokens = 431, progress = 0.33, t = 3.48 s / 123.78 tokens per second 7.20.749.473 I slot print_timing: id 3 | task 4389 | prompt processing, n_tokens = 1152, progress = 0.92, t = 5.86 s / 196.74 tokens per second 7.22.511.799 I slot print_timing: id 1 | task 4388 | prompt processing, n_tokens = 1338, progress = 1.00, t = 7.59 s / 176.38 tokens per second 7.22.514.104 I slot print_timing: id 2 | task 4392 | prompt processing, n_tokens = 784, progress = 0.60, t = 5.21 s / 150.41 tokens per second 7.22.516.265 I slot print_timing: id 3 | task 4389 | prompt processing, n_tokens = 1255, progress = 1.00, t = 7.59 s / 165.44 tokens per second 7.23.645.686 I slot print_timing: id 2 | task 4392 | prompt processing, n_tokens = 1152, progress = 0.89, t = 6.74 s / 170.81 tokens per second 7.24.767.353 I slot print_timing: id 1 | task 4388 | prompt eval time = 9118.29 ms / 1342 tokens ( 6.79 ms per token, 147.18 tokens per second) 7.24.767.358 I slot print_timing: id 1 | task 4388 | eval time = 1125.29 ms / 2 tokens ( 1125.29 ms per token, 0.89 tokens per second) 7.24.767.358 I slot print_timing: id 1 | task 4388 | total time = 10243.57 ms / 1344 tokens 7.24.767.359 I slot print_timing: id 1 | task 4388 | graphs reused = 3264 7.24.767.359 I slot print_timing: id 1 | task 4388 | graph reallocs = 0 / 0 (same size) / (changed size) 7.24.767.427 I slot release: id 1 | task 4388 | stop processing: n_tokens = 1343, truncated = 0 7.24.767.669 I slot print_timing: id 3 | task 4389 | prompt eval time = 9118.43 ms / 1259 tokens ( 7.24 ms per token, 138.07 tokens per second) 7.24.767.675 I slot print_timing: id 3 | task 4389 | eval time = 1125.40 ms / 2 tokens ( 1125.40 ms per token, 0.89 tokens per second) 7.24.767.675 I slot print_timing: id 3 | task 4389 | total time = 10243.83 ms / 1261 tokens 7.24.767.675 I slot print_timing: id 3 | task 4389 | graphs reused = 3264 7.24.767.676 I slot print_timing: id 3 | task 4389 | graph reallocs = 0 / 0 (same size) / (changed size) 7.24.767.712 I slot release: id 3 | task 4389 | stop processing: n_tokens = 1260, truncated = 0 7.24.767.720 I slot print_timing: id 0 | task 4395 | prompt processing, n_tokens = 681, progress = 0.86, t = 4.02 s / 169.40 tokens per second 7.24.771.603 I slot print_timing: id 2 | task 4392 | prompt processing, n_tokens = 1296, progress = 1.00, t = 7.87 s / 164.68 tokens per second 7.25.125.325 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1343, t_last = 391768635005 7.25.125.402 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.070 MiB) 7.25.260.318 I slot launch_slot_: id 1 | task 4400 | processing task, is_child = 0 7.25.260.384 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.154 MiB) 7.25.391.169 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1260, t_last = 391768635290 7.25.391.340 I slot launch_slot_: id 3 | task 4401 | processing task, is_child = 0 7.25.391.353 I slot print_timing: id 0 | task 4395 | prompt processing, n_tokens = 788, progress = 0.99, t = 4.38 s / 179.99 tokens per second 7.26.229.919 I slot print_timing: id 2 | task 4392 | prompt eval time = 8227.96 ms / 1300 tokens ( 6.33 ms per token, 158.00 tokens per second) 7.26.229.927 I slot print_timing: id 2 | task 4392 | eval time = 1104.60 ms / 2 tokens ( 1104.60 ms per token, 0.91 tokens per second) 7.26.229.928 I slot print_timing: id 2 | task 4392 | total time = 9332.55 ms / 1302 tokens 7.26.229.928 I slot print_timing: id 2 | task 4392 | graphs reused = 3264 7.26.229.929 I slot print_timing: id 2 | task 4392 | graph reallocs = 0 / 0 (same size) / (changed size) 7.26.230.067 I slot release: id 2 | task 4392 | stop processing: n_tokens = 1301, truncated = 0 7.26.966.055 I slot print_timing: id 0 | task 4395 | prompt eval time = 5482.53 ms / 792 tokens ( 6.92 ms per token, 144.46 tokens per second) 7.26.966.057 I slot print_timing: id 0 | task 4395 | eval time = 736.37 ms / 2 tokens ( 736.37 ms per token, 1.36 tokens per second) 7.26.966.058 I slot print_timing: id 0 | task 4395 | total time = 6218.90 ms / 794 tokens 7.26.966.058 I slot print_timing: id 0 | task 4395 | graphs reused = 3264 7.26.966.059 I slot print_timing: id 0 | task 4395 | graph reallocs = 0 / 0 (same size) / (changed size) 7.26.966.164 I slot release: id 0 | task 4395 | stop processing: n_tokens = 793, truncated = 0 7.26.966.175 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1301, t_last = 391770097645 7.26.966.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 348.892 MiB) 7.27.036.996 I slot launch_slot_: id 2 | task 4404 | processing task, is_child = 0 7.27.037.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.408 MiB) 7.27.106.064 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 391770833744 7.27.106.167 I slot launch_slot_: id 0 | task 4405 | processing task, is_child = 0 7.30.241.880 I slot print_timing: id 1 | task 4400 | prompt processing, n_tokens = 741, progress = 0.83, t = 4.34 s / 170.92 tokens per second 7.30.246.681 I slot print_timing: id 3 | task 4401 | prompt processing, n_tokens = 681, progress = 0.84, t = 4.34 s / 157.09 tokens per second 7.31.616.701 I slot print_timing: id 0 | task 4405 | prompt processing, n_tokens = 655, progress = 0.83, t = 4.51 s / 145.22 tokens per second 7.31.861.659 I slot print_timing: id 1 | task 4400 | prompt processing, n_tokens = 887, progress = 1.00, t = 6.21 s / 142.84 tokens per second 7.31.867.758 I slot print_timing: id 2 | task 4404 | prompt processing, n_tokens = 343, progress = 0.40, t = 4.51 s / 76.05 tokens per second 7.31.873.109 I slot print_timing: id 3 | task 4401 | prompt processing, n_tokens = 804, progress = 1.00, t = 6.21 s / 129.48 tokens per second 7.33.016.523 I slot print_timing: id 0 | task 4405 | prompt processing, n_tokens = 786, progress = 0.99, t = 5.91 s / 133.00 tokens per second 7.33.024.582 I slot print_timing: id 2 | task 4404 | prompt processing, n_tokens = 741, progress = 0.86, t = 5.91 s / 125.39 tokens per second 7.33.429.075 I slot print_timing: id 1 | task 4400 | prompt eval time = 7609.02 ms / 891 tokens ( 8.54 ms per token, 117.10 tokens per second) 7.33.429.078 I slot print_timing: id 1 | task 4400 | eval time = 412.90 ms / 2 tokens ( 412.90 ms per token, 2.42 tokens per second) 7.33.429.090 I slot print_timing: id 1 | task 4400 | total time = 8021.92 ms / 893 tokens 7.33.429.092 I slot print_timing: id 1 | task 4400 | graphs reused = 3264 7.33.429.093 I slot print_timing: id 1 | task 4400 | graph reallocs = 0 / 0 (same size) / (changed size) 7.33.430.870 I slot release: id 1 | task 4400 | stop processing: n_tokens = 892, truncated = 0 7.33.431.458 I slot print_timing: id 3 | task 4401 | prompt eval time = 7609.23 ms / 808 tokens ( 9.42 ms per token, 106.19 tokens per second) 7.33.431.461 I slot print_timing: id 3 | task 4401 | eval time = 414.94 ms / 2 tokens ( 414.94 ms per token, 2.41 tokens per second) 7.33.431.462 I slot print_timing: id 3 | task 4401 | total time = 8024.17 ms / 810 tokens 7.33.431.462 I slot print_timing: id 3 | task 4401 | graphs reused = 3264 7.33.431.462 I slot print_timing: id 3 | task 4401 | graph reallocs = 0 / 0 (same size) / (changed size) 7.33.431.528 I slot release: id 3 | task 4401 | stop processing: n_tokens = 809, truncated = 0 7.33.431.549 I slot print_timing: id 2 | task 4404 | prompt processing, n_tokens = 855, progress = 1.00, t = 6.32 s / 135.24 tokens per second 7.33.504.666 I slot print_timing: id 0 | task 4405 | prompt eval time = 6322.67 ms / 790 tokens ( 8.00 ms per token, 124.95 tokens per second) 7.33.504.669 I slot print_timing: id 0 | task 4405 | eval time = 75.81 ms / 2 tokens ( 75.81 ms per token, 13.19 tokens per second) 7.33.504.670 I slot print_timing: id 0 | task 4405 | total time = 6398.48 ms / 792 tokens 7.33.504.670 I slot print_timing: id 0 | task 4405 | graphs reused = 3264 7.33.504.671 I slot print_timing: id 0 | task 4405 | graph reallocs = 0 / 0 (same size) / (changed size) 7.33.504.724 I slot release: id 0 | task 4405 | stop processing: n_tokens = 791, truncated = 0 7.33.505.089 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.865 7.33.505.132 I slot launch_slot_: id 0 | task 4412 | processing task, is_child = 0 7.33.505.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.294 MiB) 7.33.554.762 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.576 MiB) 7.33.612.306 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 892, t_last = 391777298449 7.33.612.425 I slot launch_slot_: id 1 | task 4413 | processing task, is_child = 0 7.33.612.466 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 809, t_last = 391777299107 7.33.612.535 I slot launch_slot_: id 3 | task 4414 | processing task, is_child = 0 7.34.747.533 I slot print_timing: id 2 | task 4404 | prompt eval time = 6398.82 ms / 859 tokens ( 7.45 ms per token, 134.24 tokens per second) 7.34.747.535 I slot print_timing: id 2 | task 4404 | eval time = 1242.43 ms / 2 tokens ( 1242.43 ms per token, 0.80 tokens per second) 7.34.747.536 I slot print_timing: id 2 | task 4404 | total time = 7641.25 ms / 861 tokens 7.34.747.536 I slot print_timing: id 2 | task 4404 | graphs reused = 3264 7.34.747.537 I slot print_timing: id 2 | task 4404 | graph reallocs = 0 / 0 (same size) / (changed size) 7.34.747.587 I slot release: id 2 | task 4404 | stop processing: n_tokens = 860, truncated = 0 7.35.409.456 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 391778615165 7.35.409.511 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.087 MiB) 7.35.472.708 I slot launch_slot_: id 2 | task 4417 | processing task, is_child = 0 7.36.825.595 I slot print_timing: id 0 | task 4412 | prompt eval time = 1796.90 ms / 123 tokens ( 14.61 ms per token, 68.45 tokens per second) 7.36.825.598 I slot print_timing: id 0 | task 4412 | eval time = 1416.14 ms / 2 tokens ( 1416.14 ms per token, 0.71 tokens per second) 7.36.825.599 I slot print_timing: id 0 | task 4412 | total time = 3213.05 ms / 125 tokens 7.36.825.599 I slot print_timing: id 0 | task 4412 | graphs reused = 3264 7.36.825.600 I slot print_timing: id 0 | task 4412 | graph reallocs = 0 / 0 (same size) / (changed size) 7.36.825.639 I slot release: id 0 | task 4412 | stop processing: n_tokens = 779, truncated = 0 7.36.825.650 I slot print_timing: id 1 | task 4413 | prompt processing, n_tokens = 339, progress = 0.40, t = 3.21 s / 105.62 tokens per second 7.36.829.942 I slot print_timing: id 3 | task 4414 | prompt processing, n_tokens = 655, progress = 0.85, t = 3.21 s / 204.08 tokens per second 7.37.566.840 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 391780693217 7.37.566.906 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.145 MiB) 7.37.995.944 I slot launch_slot_: id 0 | task 4420 | processing task, is_child = 0 7.37.996.052 I slot print_timing: id 1 | task 4413 | prompt processing, n_tokens = 655, progress = 0.77, t = 3.95 s / 165.78 tokens per second 7.38.001.289 I slot print_timing: id 3 | task 4414 | prompt processing, n_tokens = 770, progress = 0.99, t = 3.95 s / 194.89 tokens per second 7.39.707.448 I slot print_timing: id 1 | task 4413 | prompt processing, n_tokens = 851, progress = 1.00, t = 6.09 s / 139.77 tokens per second 7.39.709.411 I slot print_timing: id 2 | task 4417 | prompt processing, n_tokens = 655, progress = 0.82, t = 4.23 s / 154.79 tokens per second 7.40.547.331 I slot print_timing: id 3 | task 4414 | prompt eval time = 6088.71 ms / 774 tokens ( 7.87 ms per token, 127.12 tokens per second) 7.40.547.334 I slot print_timing: id 3 | task 4414 | eval time = 842.70 ms / 2 tokens ( 842.70 ms per token, 1.19 tokens per second) 7.40.547.335 I slot print_timing: id 3 | task 4414 | total time = 6931.42 ms / 776 tokens 7.40.547.335 I slot print_timing: id 3 | task 4414 | graphs reused = 3264 7.40.547.336 I slot print_timing: id 3 | task 4414 | graph reallocs = 0 / 0 (same size) / (changed size) 7.40.547.373 I slot release: id 3 | task 4414 | stop processing: n_tokens = 775, truncated = 0 7.40.547.394 I slot print_timing: id 2 | task 4417 | prompt processing, n_tokens = 798, progress = 1.00, t = 5.07 s / 157.27 tokens per second 7.40.934.161 I slot print_timing: id 1 | task 4413 | prompt eval time = 6931.28 ms / 855 tokens ( 8.11 ms per token, 123.35 tokens per second) 7.40.934.164 I slot print_timing: id 1 | task 4413 | eval time = 387.04 ms / 2 tokens ( 387.04 ms per token, 2.58 tokens per second) 7.40.934.164 I slot print_timing: id 1 | task 4413 | total time = 7318.31 ms / 857 tokens 7.40.934.165 I slot print_timing: id 1 | task 4413 | graphs reused = 3264 7.40.934.165 I slot print_timing: id 1 | task 4413 | graph reallocs = 0 / 0 (same size) / (changed size) 7.40.934.204 I slot release: id 1 | task 4413 | stop processing: n_tokens = 856, truncated = 0 7.40.934.383 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 775, t_last = 391784414951 7.40.934.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.263 MiB) 7.40.974.593 I slot launch_slot_: id 3 | task 4424 | processing task, is_child = 0 7.40.974.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.215 MiB) 7.41.018.298 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 391784801782 7.41.018.403 I slot launch_slot_: id 1 | task 4425 | processing task, is_child = 0 7.42.584.435 I slot print_timing: id 2 | task 4417 | prompt eval time = 5461.65 ms / 802 tokens ( 6.81 ms per token, 146.84 tokens per second) 7.42.584.437 I slot print_timing: id 2 | task 4417 | eval time = 1650.05 ms / 2 tokens ( 1650.05 ms per token, 0.61 tokens per second) 7.42.584.437 I slot print_timing: id 2 | task 4417 | total time = 7111.70 ms / 804 tokens 7.42.584.438 I slot print_timing: id 2 | task 4417 | graphs reused = 3264 7.42.584.438 I slot print_timing: id 2 | task 4417 | graph reallocs = 0 / 0 (same size) / (changed size) 7.42.586.048 I slot release: id 2 | task 4417 | stop processing: n_tokens = 803, truncated = 0 7.42.586.077 I slot print_timing: id 0 | task 4420 | prompt processing, n_tokens = 836, progress = 0.86, t = 4.59 s / 182.20 tokens per second 7.43.260.300 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 391786453627 7.43.260.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.484 MiB) 7.43.624.778 I slot launch_slot_: id 2 | task 4428 | processing task, is_child = 0 7.43.624.809 I slot print_timing: id 0 | task 4420 | prompt processing, n_tokens = 967, progress = 1.00, t = 5.26 s / 183.69 tokens per second 7.44.726.450 I slot print_timing: id 1 | task 4425 | prompt processing, n_tokens = 448, progress = 0.46, t = 3.71 s / 120.91 tokens per second 7.44.731.757 I slot print_timing: id 3 | task 4424 | prompt processing, n_tokens = 428, progress = 0.45, t = 3.71 s / 115.51 tokens per second 7.46.555.606 I slot print_timing: id 0 | task 4420 | prompt eval time = 6730.47 ms / 971 tokens ( 6.93 ms per token, 144.27 tokens per second) 7.46.555.608 I slot print_timing: id 0 | task 4420 | eval time = 1829.16 ms / 2 tokens ( 1829.16 ms per token, 0.55 tokens per second) 7.46.555.609 I slot print_timing: id 0 | task 4420 | total time = 8559.63 ms / 973 tokens 7.46.555.609 I slot print_timing: id 0 | task 4420 | graphs reused = 3264 7.46.555.610 I slot print_timing: id 0 | task 4420 | graph reallocs = 0 / 0 (same size) / (changed size) 7.46.555.664 I slot release: id 0 | task 4420 | stop processing: n_tokens = 972, truncated = 0 7.46.555.677 I slot print_timing: id 1 | task 4425 | prompt processing, n_tokens = 836, progress = 0.87, t = 5.53 s / 151.05 tokens per second 7.46.559.196 I slot print_timing: id 3 | task 4424 | prompt processing, n_tokens = 836, progress = 0.89, t = 5.53 s / 151.05 tokens per second 7.47.304.059 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.889 7.47.304.142 I slot launch_slot_: id 0 | task 4432 | processing task, is_child = 0 7.47.354.760 I slot print_timing: id 1 | task 4425 | prompt processing, n_tokens = 960, progress = 1.00, t = 6.28 s / 152.79 tokens per second 7.47.357.909 I slot print_timing: id 2 | task 4428 | prompt processing, n_tokens = 431, progress = 0.46, t = 3.65 s / 118.07 tokens per second 7.47.369.789 I slot print_timing: id 3 | task 4424 | prompt processing, n_tokens = 940, progress = 1.00, t = 6.28 s / 149.61 tokens per second 7.48.524.169 I slot print_timing: id 2 | task 4428 | prompt processing, n_tokens = 836, progress = 0.88, t = 4.87 s / 171.75 tokens per second 7.48.947.186 I slot print_timing: id 1 | task 4425 | prompt eval time = 7500.53 ms / 964 tokens ( 7.78 ms per token, 128.52 tokens per second) 7.48.947.191 I slot print_timing: id 1 | task 4425 | eval time = 425.79 ms / 2 tokens ( 425.79 ms per token, 2.35 tokens per second) 7.48.947.192 I slot print_timing: id 1 | task 4425 | total time = 7926.32 ms / 966 tokens 7.48.947.192 I slot print_timing: id 1 | task 4425 | graphs reused = 3264 7.48.947.193 I slot print_timing: id 1 | task 4425 | graph reallocs = 0 / 0 (same size) / (changed size) 7.48.947.238 I slot release: id 1 | task 4425 | stop processing: n_tokens = 965, truncated = 0 7.48.947.395 I slot print_timing: id 3 | task 4424 | prompt eval time = 7500.79 ms / 944 tokens ( 7.95 ms per token, 125.85 tokens per second) 7.48.947.399 I slot print_timing: id 3 | task 4424 | eval time = 425.67 ms / 2 tokens ( 425.67 ms per token, 2.35 tokens per second) 7.48.947.399 I slot print_timing: id 3 | task 4424 | total time = 7926.46 ms / 946 tokens 7.48.947.399 I slot print_timing: id 3 | task 4424 | graphs reused = 3264 7.48.947.400 I slot print_timing: id 3 | task 4424 | graph reallocs = 0 / 0 (same size) / (changed size) 7.48.947.424 I slot release: id 3 | task 4424 | stop processing: n_tokens = 945, truncated = 0 7.48.947.433 I slot print_timing: id 2 | task 4428 | prompt processing, n_tokens = 943, progress = 1.00, t = 5.29 s / 178.15 tokens per second 7.49.015.449 I slot print_timing: id 0 | task 4432 | prompt eval time = 1642.87 ms / 133 tokens ( 12.35 ms per token, 80.96 tokens per second) 7.49.015.452 I slot print_timing: id 0 | task 4432 | eval time = 68.43 ms / 2 tokens ( 68.43 ms per token, 14.61 tokens per second) 7.49.015.452 I slot print_timing: id 0 | task 4432 | total time = 1711.30 ms / 135 tokens 7.49.015.452 I slot print_timing: id 0 | task 4432 | graphs reused = 3264 7.49.015.453 I slot print_timing: id 0 | task 4432 | graph reallocs = 0 / 0 (same size) / (changed size) 7.49.015.491 I slot release: id 0 | task 4432 | stop processing: n_tokens = 970, truncated = 0 7.49.015.705 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 391792814816 7.49.015.770 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.757 MiB) 7.49.061.652 I slot launch_slot_: id 1 | task 4436 | processing task, is_child = 0 7.49.061.706 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.305 MiB) 7.49.119.053 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.620 MiB) 7.49.167.014 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 391792815002 7.49.167.122 I slot launch_slot_: id 3 | task 4437 | processing task, is_child = 0 7.49.167.175 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 391792883069 7.49.167.250 I slot launch_slot_: id 0 | task 4438 | processing task, is_child = 0 7.50.286.672 I slot print_timing: id 2 | task 4428 | prompt eval time = 5362.12 ms / 947 tokens ( 5.66 ms per token, 176.61 tokens per second) 7.50.286.675 I slot print_timing: id 2 | task 4428 | eval time = 1270.96 ms / 2 tokens ( 1270.96 ms per token, 0.79 tokens per second) 7.50.286.675 I slot print_timing: id 2 | task 4428 | total time = 6633.08 ms / 949 tokens 7.50.286.676 I slot print_timing: id 2 | task 4428 | graphs reused = 3264 7.50.286.676 I slot print_timing: id 2 | task 4428 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.286.720 I slot release: id 2 | task 4428 | stop processing: n_tokens = 948, truncated = 0 7.51.045.214 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 391794154298 7.51.045.277 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.503 MiB) 7.51.361.227 I slot launch_slot_: id 2 | task 4441 | processing task, is_child = 0 7.52.919.339 I slot print_timing: id 0 | task 4438 | prompt processing, n_tokens = 459, progress = 0.47, t = 3.75 s / 122.33 tokens per second 7.53.441.238 I slot print_timing: id 1 | task 4436 | prompt processing, n_tokens = 679, progress = 0.85, t = 3.75 s / 180.97 tokens per second 7.53.447.045 I slot print_timing: id 3 | task 4437 | prompt processing, n_tokens = 679, progress = 0.85, t = 3.75 s / 180.97 tokens per second 7.54.790.621 I slot print_timing: id 0 | task 4438 | prompt processing, n_tokens = 826, progress = 0.85, t = 5.62 s / 146.89 tokens per second 7.55.050.918 I slot print_timing: id 1 | task 4436 | prompt processing, n_tokens = 794, progress = 0.99, t = 5.62 s / 141.20 tokens per second 7.55.054.283 I slot print_timing: id 2 | task 4441 | prompt processing, n_tokens = 335, progress = 0.35, t = 3.42 s / 98.04 tokens per second 7.55.054.291 I slot print_timing: id 3 | task 4437 | prompt processing, n_tokens = 795, progress = 0.99, t = 5.62 s / 141.38 tokens per second 7.55.826.833 I slot print_timing: id 0 | task 4438 | prompt processing, n_tokens = 971, progress = 1.00, t = 6.66 s / 145.82 tokens per second 7.55.830.506 I slot print_timing: id 2 | task 4441 | prompt processing, n_tokens = 437, progress = 0.46, t = 4.45 s / 98.14 tokens per second 7.56.630.522 I slot print_timing: id 1 | task 4436 | prompt eval time = 6659.26 ms / 798 tokens ( 8.34 ms per token, 119.83 tokens per second) 7.56.630.524 I slot print_timing: id 1 | task 4436 | eval time = 803.93 ms / 2 tokens ( 803.93 ms per token, 1.24 tokens per second) 7.56.630.525 I slot print_timing: id 1 | task 4436 | total time = 7463.19 ms / 800 tokens 7.56.630.525 I slot print_timing: id 1 | task 4436 | graphs reused = 3264 7.56.630.526 I slot print_timing: id 1 | task 4436 | graph reallocs = 0 / 0 (same size) / (changed size) 7.56.632.316 I slot release: id 1 | task 4436 | stop processing: n_tokens = 799, truncated = 0 7.56.632.738 I slot print_timing: id 3 | task 4437 | prompt eval time = 6659.43 ms / 799 tokens ( 8.33 ms per token, 119.98 tokens per second) 7.56.632.742 I slot print_timing: id 3 | task 4437 | eval time = 805.91 ms / 2 tokens ( 805.91 ms per token, 1.24 tokens per second) 7.56.632.742 I slot print_timing: id 3 | task 4437 | total time = 7465.34 ms / 801 tokens 7.56.632.743 I slot print_timing: id 3 | task 4437 | graphs reused = 3264 7.56.632.743 I slot print_timing: id 3 | task 4437 | graph reallocs = 0 / 0 (same size) / (changed size) 7.56.632.776 I slot release: id 3 | task 4437 | stop processing: n_tokens = 800, truncated = 0 7.56.632.805 I slot print_timing: id 2 | task 4441 | prompt processing, n_tokens = 826, progress = 0.87, t = 5.26 s / 157.14 tokens per second 7.56.982.100 I slot print_timing: id 0 | task 4438 | prompt eval time = 7463.07 ms / 975 tokens ( 7.65 ms per token, 130.64 tokens per second) 7.56.982.102 I slot print_timing: id 0 | task 4438 | eval time = 351.77 ms / 2 tokens ( 351.77 ms per token, 2.84 tokens per second) 7.56.982.103 I slot print_timing: id 0 | task 4438 | total time = 7814.84 ms / 977 tokens 7.56.982.103 I slot print_timing: id 0 | task 4438 | graphs reused = 3264 7.56.982.104 I slot print_timing: id 0 | task 4438 | graph reallocs = 0 / 0 (same size) / (changed size) 7.56.982.173 I slot release: id 0 | task 4438 | stop processing: n_tokens = 976, truncated = 0 7.56.982.180 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.875 7.56.982.235 I slot launch_slot_: id 0 | task 4447 | processing task, is_child = 0 7.56.982.287 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.274 MiB) 7.57.042.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.816 MiB) 7.57.078.430 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 391800499896 7.57.078.540 I slot launch_slot_: id 1 | task 4448 | processing task, is_child = 0 7.57.078.583 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 391800500354 7.57.078.648 I slot launch_slot_: id 3 | task 4449 | processing task, is_child = 0 7.57.082.005 I slot print_timing: id 2 | task 4441 | prompt processing, n_tokens = 949, progress = 1.00, t = 5.61 s / 169.21 tokens per second 7.58.990.364 I slot print_timing: id 2 | task 4441 | prompt eval time = 6741.82 ms / 953 tokens ( 7.07 ms per token, 141.36 tokens per second) 7.58.990.368 I slot print_timing: id 2 | task 4441 | eval time = 874.97 ms / 2 tokens ( 874.97 ms per token, 1.14 tokens per second) 7.58.990.369 I slot print_timing: id 2 | task 4441 | total time = 7616.78 ms / 955 tokens 7.58.990.369 I slot print_timing: id 2 | task 4441 | graphs reused = 3264 7.58.990.370 I slot print_timing: id 2 | task 4441 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.990.417 I slot release: id 2 | task 4441 | stop processing: n_tokens = 954, truncated = 0 7.59.592.145 I slot print_timing: id 0 | task 4447 | prompt eval time = 1911.48 ms / 135 tokens ( 14.16 ms per token, 70.63 tokens per second) 7.59.592.148 I slot print_timing: id 0 | task 4447 | eval time = 602.00 ms / 2 tokens ( 602.00 ms per token, 1.66 tokens per second) 7.59.592.148 I slot print_timing: id 0 | task 4447 | total time = 2513.48 ms / 137 tokens 7.59.592.149 I slot print_timing: id 0 | task 4447 | graphs reused = 3264 7.59.592.149 I slot print_timing: id 0 | task 4447 | graph reallocs = 0 / 0 (same size) / (changed size) 7.59.592.187 I slot release: id 0 | task 4447 | stop processing: n_tokens = 962, truncated = 0 7.59.592.195 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 391802857995 7.59.592.251 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.724 MiB) 7.59.630.572 I slot launch_slot_: id 2 | task 4453 | processing task, is_child = 0 7.59.630.631 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.313 MiB) 7.59.662.071 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 391803459765 7.59.662.183 I slot launch_slot_: id 0 | task 4454 | processing task, is_child = 0 8.01.705.804 I slot print_timing: id 1 | task 4448 | prompt processing, n_tokens = 779, progress = 0.84, t = 4.10 s / 189.94 tokens per second 8.01.711.039 I slot print_timing: id 3 | task 4449 | prompt processing, n_tokens = 779, progress = 0.87, t = 4.10 s / 190.04 tokens per second 8.02.882.115 I slot print_timing: id 0 | task 4454 | prompt processing, n_tokens = 304, progress = 0.34, t = 3.22 s / 94.41 tokens per second 8.02.882.126 I slot print_timing: id 1 | task 4448 | prompt processing, n_tokens = 926, progress = 1.00, t = 5.80 s / 159.65 tokens per second 8.03.005.597 I slot print_timing: id 2 | task 4453 | prompt processing, n_tokens = 304, progress = 0.34, t = 3.22 s / 94.47 tokens per second 8.03.005.621 I slot print_timing: id 3 | task 4449 | prompt processing, n_tokens = 894, progress = 1.00, t = 5.80 s / 154.19 tokens per second 8.03.639.468 I slot print_timing: id 0 | task 4454 | prompt processing, n_tokens = 383, progress = 0.43, t = 3.98 s / 96.31 tokens per second 8.03.642.953 I slot print_timing: id 2 | task 4453 | prompt processing, n_tokens = 386, progress = 0.43, t = 3.97 s / 97.11 tokens per second 8.05.100.858 I slot print_timing: id 1 | task 4448 | prompt eval time = 6557.27 ms / 930 tokens ( 7.05 ms per token, 141.83 tokens per second) 8.05.100.861 I slot print_timing: id 1 | task 4448 | eval time = 1461.63 ms / 2 tokens ( 1461.63 ms per token, 0.68 tokens per second) 8.05.100.861 I slot print_timing: id 1 | task 4448 | total time = 8018.90 ms / 932 tokens 8.05.100.861 I slot print_timing: id 1 | task 4448 | graphs reused = 3264 8.05.100.862 I slot print_timing: id 1 | task 4448 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.102.367 I slot release: id 1 | task 4448 | stop processing: n_tokens = 931, truncated = 0 8.05.102.818 I slot print_timing: id 3 | task 4449 | prompt eval time = 6555.47 ms / 898 tokens ( 7.30 ms per token, 136.98 tokens per second) 8.05.102.826 I slot print_timing: id 3 | task 4449 | eval time = 1463.36 ms / 2 tokens ( 1463.36 ms per token, 0.68 tokens per second) 8.05.102.826 I slot print_timing: id 3 | task 4449 | total time = 8018.82 ms / 900 tokens 8.05.102.827 I slot print_timing: id 3 | task 4449 | graphs reused = 3264 8.05.102.827 I slot print_timing: id 3 | task 4449 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.102.905 I slot release: id 3 | task 4449 | stop processing: n_tokens = 899, truncated = 0 8.05.102.928 I slot print_timing: id 0 | task 4454 | prompt processing, n_tokens = 779, progress = 0.87, t = 5.44 s / 143.24 tokens per second 8.05.107.558 I slot print_timing: id 2 | task 4453 | prompt processing, n_tokens = 779, progress = 0.86, t = 5.44 s / 143.29 tokens per second 8.05.433.724 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 391808969946 8.05.433.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.347 MiB) 8.05.760.035 I slot launch_slot_: id 1 | task 4460 | processing task, is_child = 0 8.05.760.110 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.701 MiB) 8.05.815.295 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.898 8.05.815.360 I slot launch_slot_: id 3 | task 4461 | processing task, is_child = 0 8.05.815.367 I slot print_timing: id 0 | task 4454 | prompt processing, n_tokens = 895, progress = 1.00, t = 5.77 s / 155.07 tokens per second 8.05.819.931 I slot print_timing: id 2 | task 4453 | prompt processing, n_tokens = 898, progress = 1.00, t = 5.77 s / 155.64 tokens per second 8.07.197.983 I slot print_timing: id 0 | task 4454 | prompt eval time = 6983.72 ms / 899 tokens ( 7.77 ms per token, 128.73 tokens per second) 8.07.197.989 I slot print_timing: id 0 | task 4454 | eval time = 552.07 ms / 2 tokens ( 552.07 ms per token, 1.81 tokens per second) 8.07.197.990 I slot print_timing: id 0 | task 4454 | total time = 7535.79 ms / 901 tokens 8.07.197.990 I slot print_timing: id 0 | task 4454 | graphs reused = 3264 8.07.197.990 I slot print_timing: id 0 | task 4454 | graph reallocs = 0 / 0 (same size) / (changed size) 8.07.198.043 I slot release: id 0 | task 4454 | stop processing: n_tokens = 900, truncated = 0 8.07.198.295 I slot print_timing: id 2 | task 4453 | prompt eval time = 6982.01 ms / 902 tokens ( 7.74 ms per token, 129.19 tokens per second) 8.07.198.297 I slot print_timing: id 2 | task 4453 | eval time = 552.14 ms / 2 tokens ( 552.14 ms per token, 1.81 tokens per second) 8.07.198.297 I slot print_timing: id 2 | task 4453 | total time = 7534.15 ms / 904 tokens 8.07.198.298 I slot print_timing: id 2 | task 4453 | graphs reused = 3264 8.07.198.298 I slot print_timing: id 2 | task 4453 | graph reallocs = 0 / 0 (same size) / (changed size) 8.07.198.337 I slot release: id 2 | task 4453 | stop processing: n_tokens = 903, truncated = 0 8.07.807.923 I slot print_timing: id 3 | task 4461 | prompt eval time = 1376.61 ms / 111 tokens ( 12.40 ms per token, 80.63 tokens per second) 8.07.807.925 I slot print_timing: id 3 | task 4461 | eval time = 609.39 ms / 2 tokens ( 609.39 ms per token, 1.64 tokens per second) 8.07.807.925 I slot print_timing: id 3 | task 4461 | total time = 1986.01 ms / 113 tokens 8.07.807.926 I slot print_timing: id 3 | task 4461 | graphs reused = 3264 8.07.807.926 I slot print_timing: id 3 | task 4461 | graph reallocs = 0 / 0 (same size) / (changed size) 8.07.807.966 I slot release: id 3 | task 4461 | stop processing: n_tokens = 891, truncated = 0 8.07.807.972 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 900, t_last = 391811065621 8.07.808.028 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.802 MiB) 8.07.869.602 I slot launch_slot_: id 0 | task 4465 | processing task, is_child = 0 8.07.869.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.467 MiB) 8.07.908.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.601 MiB) 8.07.952.583 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 391811065915 8.07.952.690 I slot launch_slot_: id 2 | task 4466 | processing task, is_child = 0 8.07.952.738 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 391811675544 8.07.952.808 I slot launch_slot_: id 3 | task 4467 | processing task, is_child = 0 8.10.157.130 I slot print_timing: id 1 | task 4460 | prompt processing, n_tokens = 1061, progress = 0.87, t = 3.89 s / 272.43 tokens per second 8.11.879.672 I slot print_timing: id 0 | task 4465 | prompt processing, n_tokens = 402, progress = 0.31, t = 3.93 s / 102.37 tokens per second 8.11.879.691 I slot print_timing: id 1 | task 4460 | prompt processing, n_tokens = 1221, progress = 1.00, t = 6.06 s / 201.49 tokens per second 8.12.506.451 I slot print_timing: id 2 | task 4466 | prompt processing, n_tokens = 402, progress = 0.33, t = 3.92 s / 102.42 tokens per second 8.12.506.470 I slot print_timing: id 3 | task 4467 | prompt processing, n_tokens = 961, progress = 0.37, t = 3.92 s / 244.85 tokens per second 8.15.916.404 I slot print_timing: id 0 | task 4465 | prompt processing, n_tokens = 774, progress = 0.60, t = 7.96 s / 97.20 tokens per second 8.15.919.324 I slot print_timing: id 2 | task 4466 | prompt processing, n_tokens = 720, progress = 0.58, t = 7.96 s / 90.44 tokens per second 8.15.921.235 I slot print_timing: id 3 | task 4467 | prompt processing, n_tokens = 2071, progress = 0.80, t = 7.96 s / 260.13 tokens per second 8.17.633.033 I slot print_timing: id 1 | task 4460 | prompt eval time = 10096.53 ms / 1225 tokens ( 8.24 ms per token, 121.33 tokens per second) 8.17.633.038 I slot print_timing: id 1 | task 4460 | eval time = 1716.64 ms / 2 tokens ( 1716.64 ms per token, 0.58 tokens per second) 8.17.633.040 I slot print_timing: id 1 | task 4460 | total time = 11813.16 ms / 1227 tokens 8.17.633.040 I slot print_timing: id 1 | task 4460 | graphs reused = 3264 8.17.633.040 I slot print_timing: id 1 | task 4460 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.633.099 I slot release: id 1 | task 4460 | stop processing: n_tokens = 1226, truncated = 0 8.17.633.118 I slot print_timing: id 0 | task 4465 | prompt processing, n_tokens = 1061, progress = 0.82, t = 9.68 s / 109.61 tokens per second 8.17.635.889 I slot print_timing: id 2 | task 4466 | prompt processing, n_tokens = 1061, progress = 0.86, t = 9.68 s / 109.63 tokens per second 8.17.637.754 I slot print_timing: id 3 | task 4467 | prompt processing, n_tokens = 2288, progress = 0.88, t = 9.68 s / 236.41 tokens per second 8.18.798.468 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1226, t_last = 391821500679 8.18.798.558 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.328 MiB) 8.19.140.204 I slot launch_slot_: id 1 | task 4473 | processing task, is_child = 0 8.19.140.225 I slot print_timing: id 0 | task 4465 | prompt processing, n_tokens = 1286, progress = 1.00, t = 10.85 s / 118.57 tokens per second 8.19.143.079 I slot print_timing: id 2 | task 4466 | prompt processing, n_tokens = 1232, progress = 1.00, t = 10.84 s / 113.61 tokens per second 8.19.145.051 I slot print_timing: id 3 | task 4467 | prompt processing, n_tokens = 2583, progress = 1.00, t = 10.84 s / 238.20 tokens per second 8.21.067.109 I slot print_timing: id 0 | task 4465 | prompt eval time = 12009.28 ms / 1290 tokens ( 9.31 ms per token, 107.42 tokens per second) 8.21.067.116 I slot print_timing: id 0 | task 4465 | eval time = 1105.01 ms / 2 tokens ( 1105.01 ms per token, 0.90 tokens per second) 8.21.067.117 I slot print_timing: id 0 | task 4465 | total time = 13114.29 ms / 1292 tokens 8.21.067.117 I slot print_timing: id 0 | task 4465 | graphs reused = 3264 8.21.067.118 I slot print_timing: id 0 | task 4465 | graph reallocs = 0 / 0 (same size) / (changed size) 8.21.067.204 I slot release: id 0 | task 4465 | stop processing: n_tokens = 1291, truncated = 0 8.21.067.482 I slot print_timing: id 2 | task 4466 | prompt eval time = 12007.49 ms / 1236 tokens ( 9.71 ms per token, 102.94 tokens per second) 8.21.067.488 I slot print_timing: id 2 | task 4466 | eval time = 1105.21 ms / 2 tokens ( 1105.21 ms per token, 0.90 tokens per second) 8.21.067.488 I slot print_timing: id 2 | task 4466 | total time = 13112.69 ms / 1238 tokens 8.21.067.489 I slot print_timing: id 2 | task 4466 | graphs reused = 3264 8.21.067.489 I slot print_timing: id 2 | task 4466 | graph reallocs = 0 / 0 (same size) / (changed size) 8.21.067.535 I slot release: id 2 | task 4466 | stop processing: n_tokens = 1237, truncated = 0 8.21.067.774 I slot print_timing: id 3 | task 4467 | prompt eval time = 12007.65 ms / 2587 tokens ( 4.64 ms per token, 215.45 tokens per second) 8.21.067.777 I slot print_timing: id 3 | task 4467 | eval time = 1105.27 ms / 2 tokens ( 1105.27 ms per token, 0.90 tokens per second) 8.21.067.777 I slot print_timing: id 3 | task 4467 | total time = 13112.92 ms / 2589 tokens 8.21.067.778 I slot print_timing: id 3 | task 4467 | graphs reused = 3264 8.21.067.778 I slot print_timing: id 3 | task 4467 | graph reallocs = 0 / 0 (same size) / (changed size) 8.21.071.611 I slot release: id 3 | task 4467 | stop processing: n_tokens = 2588, truncated = 0 8.21.935.979 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.848 (> 0.100 thold), f_keep = 0.898 8.21.936.041 I slot launch_slot_: id 3 | task 4477 | processing task, is_child = 0 8.21.936.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 338.705 MiB) 8.22.810.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.506 MiB) 8.22.834.179 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 391824934782 8.22.834.316 I slot launch_slot_: id 0 | task 4478 | processing task, is_child = 0 8.22.834.374 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1237, t_last = 391824935113 8.22.834.453 I slot launch_slot_: id 2 | task 4479 | processing task, is_child = 0 8.25.546.883 I slot print_timing: id 1 | task 4473 | prompt processing, n_tokens = 2288, progress = 0.92, t = 6.20 s / 369.21 tokens per second 8.27.815.420 I slot print_timing: id 0 | task 4478 | prompt processing, n_tokens = 520, progress = 0.29, t = 4.98 s / 104.40 tokens per second 8.27.815.445 I slot print_timing: id 1 | task 4473 | prompt processing, n_tokens = 2496, progress = 1.00, t = 8.67 s / 287.82 tokens per second 8.27.830.305 I slot print_timing: id 2 | task 4479 | prompt processing, n_tokens = 961, progress = 0.36, t = 4.98 s / 193.02 tokens per second 8.31.368.688 I slot print_timing: id 3 | task 4477 | prompt eval time = 4978.87 ms / 454 tokens ( 10.97 ms per token, 91.19 tokens per second) 8.31.368.691 I slot print_timing: id 3 | task 4477 | eval time = 3553.27 ms / 2 tokens ( 3553.27 ms per token, 0.28 tokens per second) 8.31.368.691 I slot print_timing: id 3 | task 4477 | total time = 8532.14 ms / 456 tokens 8.31.368.692 I slot print_timing: id 3 | task 4477 | graphs reused = 3264 8.31.368.692 I slot print_timing: id 3 | task 4477 | graph reallocs = 0 / 0 (same size) / (changed size) 8.31.368.843 I slot release: id 3 | task 4477 | stop processing: n_tokens = 2743, truncated = 0 8.31.368.859 I slot print_timing: id 0 | task 4478 | prompt processing, n_tokens = 1263, progress = 0.71, t = 8.53 s / 148.00 tokens per second 8.31.372.741 I slot print_timing: id 2 | task 4479 | prompt processing, n_tokens = 2139, progress = 0.81, t = 8.53 s / 250.71 tokens per second 8.32.201.832 I slot print_timing: id 1 | task 4473 | prompt eval time = 12225.47 ms / 2500 tokens ( 4.89 ms per token, 204.49 tokens per second) 8.32.201.837 I slot print_timing: id 1 | task 4473 | eval time = 833.37 ms / 2 tokens ( 833.37 ms per token, 1.20 tokens per second) 8.32.201.838 I slot print_timing: id 1 | task 4473 | total time = 13058.84 ms / 2502 tokens 8.32.201.838 I slot print_timing: id 1 | task 4473 | graphs reused = 3264 8.32.201.839 I slot print_timing: id 1 | task 4473 | graph reallocs = 0 / 0 (same size) / (changed size) 8.32.201.933 I slot release: id 1 | task 4473 | stop processing: n_tokens = 2501, truncated = 0 8.32.201.942 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2743, t_last = 391835236421 8.32.202.053 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.573 MiB) 8.32.223.174 I slot launch_slot_: id 3 | task 4484 | processing task, is_child = 0 8.32.223.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.509 MiB) 8.32.244.041 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2501, t_last = 391836069511 8.32.244.188 I slot launch_slot_: id 1 | task 4485 | processing task, is_child = 0 8.32.244.196 I slot print_timing: id 0 | task 4478 | prompt processing, n_tokens = 1447, progress = 0.81, t = 9.37 s / 154.47 tokens per second 8.32.246.251 I slot print_timing: id 2 | task 4479 | prompt processing, n_tokens = 2288, progress = 0.86, t = 9.37 s / 244.31 tokens per second 8.34.022.129 I slot print_timing: id 0 | task 4478 | prompt processing, n_tokens = 1775, progress = 1.00, t = 11.19 s / 158.66 tokens per second 8.34.410.244 I slot print_timing: id 2 | task 4479 | prompt processing, n_tokens = 2651, progress = 1.00, t = 11.19 s / 237.00 tokens per second 8.35.681.068 I slot print_timing: id 1 | task 4485 | prompt processing, n_tokens = 520, progress = 0.25, t = 3.43 s / 151.40 tokens per second 8.35.681.093 I slot print_timing: id 3 | task 4484 | prompt processing, n_tokens = 520, progress = 0.28, t = 3.43 s / 151.49 tokens per second 8.38.748.760 I slot print_timing: id 0 | task 4478 | prompt eval time = 12846.38 ms / 1779 tokens ( 7.22 ms per token, 138.48 tokens per second) 8.38.748.765 I slot print_timing: id 0 | task 4478 | eval time = 3067.91 ms / 2 tokens ( 3067.91 ms per token, 0.33 tokens per second) 8.38.748.767 I slot print_timing: id 0 | task 4478 | total time = 15914.30 ms / 1781 tokens 8.38.748.767 I slot print_timing: id 0 | task 4478 | graphs reused = 3264 8.38.748.767 I slot print_timing: id 0 | task 4478 | graph reallocs = 0 / 0 (same size) / (changed size) 8.38.750.099 I slot release: id 0 | task 4478 | stop processing: n_tokens = 1780, truncated = 0 8.38.750.564 I slot print_timing: id 2 | task 4479 | prompt eval time = 12844.61 ms / 2655 tokens ( 4.84 ms per token, 206.70 tokens per second) 8.38.750.569 I slot print_timing: id 2 | task 4479 | eval time = 3069.50 ms / 2 tokens ( 3069.50 ms per token, 0.33 tokens per second) 8.38.750.570 I slot print_timing: id 2 | task 4479 | total time = 15914.11 ms / 2657 tokens 8.38.750.570 I slot print_timing: id 2 | task 4479 | graphs reused = 3264 8.38.750.570 I slot print_timing: id 2 | task 4479 | graph reallocs = 0 / 0 (same size) / (changed size) 8.38.750.737 I slot release: id 2 | task 4479 | stop processing: n_tokens = 2656, truncated = 0 8.38.750.765 I slot print_timing: id 1 | task 4485 | prompt processing, n_tokens = 1447, progress = 0.71, t = 6.50 s / 222.53 tokens per second 8.38.755.427 I slot print_timing: id 3 | task 4484 | prompt processing, n_tokens = 1325, progress = 0.72, t = 6.50 s / 203.83 tokens per second 8.39.031.608 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.756 (> 0.100 thold), f_keep = 0.834 8.39.031.658 I slot launch_slot_: id 0 | task 4490 | processing task, is_child = 0 8.39.031.787 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.886 MiB) 8.39.364.832 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2656, t_last = 391842618316 8.39.365.033 I slot launch_slot_: id 2 | task 4491 | processing task, is_child = 0 8.39.368.462 I slot print_timing: id 1 | task 4485 | prompt processing, n_tokens = 1532, progress = 0.75, t = 6.79 s / 225.78 tokens per second 8.39.370.511 I slot print_timing: id 3 | task 4484 | prompt processing, n_tokens = 1447, progress = 0.79, t = 6.78 s / 213.31 tokens per second 8.42.454.812 I slot print_timing: id 1 | task 4485 | prompt processing, n_tokens = 2044, progress = 1.00, t = 9.78 s / 208.93 tokens per second 8.42.470.056 I slot print_timing: id 3 | task 4484 | prompt processing, n_tokens = 1837, progress = 1.00, t = 9.78 s / 187.81 tokens per second 8.43.163.688 I slot print_timing: id 2 | task 4491 | prompt processing, n_tokens = 520, progress = 0.28, t = 3.79 s / 137.10 tokens per second 8.44.663.764 I slot print_timing: id 0 | task 4490 | prompt eval time = 3798.27 ms / 515 tokens ( 7.38 ms per token, 135.59 tokens per second) 8.44.663.766 I slot print_timing: id 0 | task 4490 | eval time = 1500.44 ms / 2 tokens ( 1500.44 ms per token, 0.67 tokens per second) 8.44.663.767 I slot print_timing: id 0 | task 4490 | total time = 5298.72 ms / 517 tokens 8.44.663.768 I slot print_timing: id 0 | task 4490 | graphs reused = 3264 8.44.663.768 I slot print_timing: id 0 | task 4490 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.665.634 I slot release: id 0 | task 4490 | stop processing: n_tokens = 1963, truncated = 0 8.44.666.087 I slot print_timing: id 1 | task 4485 | prompt eval time = 10917.40 ms / 2048 tokens ( 5.33 ms per token, 187.59 tokens per second) 8.44.666.090 I slot print_timing: id 1 | task 4485 | eval time = 1502.60 ms / 2 tokens ( 1502.60 ms per token, 0.67 tokens per second) 8.44.666.091 I slot print_timing: id 1 | task 4485 | total time = 12420.00 ms / 2050 tokens 8.44.666.091 I slot print_timing: id 1 | task 4485 | graphs reused = 3264 8.44.666.091 I slot print_timing: id 1 | task 4485 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.668.002 I slot release: id 1 | task 4485 | stop processing: n_tokens = 2049, truncated = 0 8.44.668.456 I slot print_timing: id 3 | task 4484 | prompt eval time = 10915.54 ms / 1841 tokens ( 5.93 ms per token, 168.66 tokens per second) 8.44.668.461 I slot print_timing: id 3 | task 4484 | eval time = 1504.78 ms / 2 tokens ( 1504.78 ms per token, 0.66 tokens per second) 8.44.668.461 I slot print_timing: id 3 | task 4484 | total time = 12420.31 ms / 1843 tokens 8.44.668.462 I slot print_timing: id 3 | task 4484 | graphs reused = 3264 8.44.668.462 I slot print_timing: id 3 | task 4484 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.668.522 I slot release: id 3 | task 4484 | stop processing: n_tokens = 1842, truncated = 0 8.44.668.543 I slot print_timing: id 2 | task 4491 | prompt processing, n_tokens = 1336, progress = 0.72, t = 5.29 s / 252.40 tokens per second 8.44.675.327 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1963, t_last = 391848533213 8.44.675.416 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.883 MiB) 8.45.184.345 I slot launch_slot_: id 0 | task 4496 | processing task, is_child = 0 8.45.184.447 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.299 MiB) 8.45.650.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.221 MiB) 8.45.789.214 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2049, t_last = 391848535580 8.45.789.482 I slot launch_slot_: id 1 | task 4497 | processing task, is_child = 0 8.45.789.562 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.833 (> 0.100 thold), f_keep = 0.806 8.45.789.592 I slot launch_slot_: id 3 | task 4498 | processing task, is_child = 0 8.45.789.919 I slot print_timing: id 2 | task 4491 | prompt processing, n_tokens = 1447, progress = 0.78, t = 5.30 s / 272.76 tokens per second 8.47.745.180 I slot print_timing: id 2 | task 4491 | prompt processing, n_tokens = 1848, progress = 1.00, t = 8.12 s / 227.72 tokens per second 8.49.859.442 I slot print_timing: id 2 | task 4491 | prompt eval time = 8981.31 ms / 1852 tokens ( 4.85 ms per token, 206.21 tokens per second) 8.49.859.446 I slot print_timing: id 2 | task 4491 | eval time = 1507.79 ms / 2 tokens ( 1507.79 ms per token, 0.66 tokens per second) 8.49.859.447 I slot print_timing: id 2 | task 4491 | total time = 10489.09 ms / 1854 tokens 8.49.859.450 I slot print_timing: id 2 | task 4491 | graphs reused = 3264 8.49.859.451 I slot print_timing: id 2 | task 4491 | graph reallocs = 0 / 0 (same size) / (changed size) 8.49.862.350 I slot release: id 2 | task 4491 | stop processing: n_tokens = 1853, truncated = 0 8.49.863.057 I slot print_timing: id 3 | task 4498 | prompt eval time = 2554.15 ms / 334 tokens ( 7.65 ms per token, 130.77 tokens per second) 8.49.863.362 I slot print_timing: id 3 | task 4498 | eval time = 1510.88 ms / 2 tokens ( 1510.88 ms per token, 0.66 tokens per second) 8.49.863.365 I slot print_timing: id 3 | task 4498 | total time = 4065.03 ms / 336 tokens 8.49.863.365 I slot print_timing: id 3 | task 4498 | graphs reused = 3264 8.49.863.366 I slot print_timing: id 3 | task 4498 | graph reallocs = 0 / 0 (same size) / (changed size) 8.49.863.462 I slot release: id 3 | task 4498 | stop processing: n_tokens = 1782, truncated = 0 8.49.863.812 I slot print_timing: id 0 | task 4496 | prompt processing, n_tokens = 615, progress = 0.82, t = 4.07 s / 151.12 tokens per second 8.49.866.551 I slot print_timing: id 1 | task 4497 | prompt processing, n_tokens = 615, progress = 0.85, t = 4.07 s / 151.13 tokens per second 8.50.333.667 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1853, t_last = 391853729929 8.50.333.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.805 MiB) 8.50.476.546 I slot launch_slot_: id 2 | task 4503 | processing task, is_child = 0 8.50.476.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.768 MiB) 8.50.561.136 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1782, t_last = 391853731041 8.50.561.307 I slot launch_slot_: id 3 | task 4504 | processing task, is_child = 0 8.50.561.318 I slot print_timing: id 0 | task 4496 | prompt processing, n_tokens = 744, progress = 0.99, t = 4.54 s / 163.73 tokens per second 8.50.576.779 I slot print_timing: id 1 | task 4497 | prompt processing, n_tokens = 722, progress = 0.99, t = 4.54 s / 158.90 tokens per second 8.51.763.694 I slot print_timing: id 0 | task 4496 | prompt eval time = 5402.95 ms / 748 tokens ( 7.22 ms per token, 138.44 tokens per second) 8.51.763.697 I slot print_timing: id 0 | task 4496 | eval time = 571.13 ms / 2 tokens ( 571.13 ms per token, 1.75 tokens per second) 8.51.763.698 I slot print_timing: id 0 | task 4496 | total time = 5974.09 ms / 750 tokens 8.51.763.698 I slot print_timing: id 0 | task 4496 | graphs reused = 3264 8.51.763.698 I slot print_timing: id 0 | task 4496 | graph reallocs = 0 / 0 (same size) / (changed size) 8.51.763.771 I slot release: id 0 | task 4496 | stop processing: n_tokens = 749, truncated = 0 8.51.764.028 I slot print_timing: id 1 | task 4497 | prompt eval time = 5403.03 ms / 726 tokens ( 7.44 ms per token, 134.37 tokens per second) 8.51.764.030 I slot print_timing: id 1 | task 4497 | eval time = 571.21 ms / 2 tokens ( 571.21 ms per token, 1.75 tokens per second) 8.51.764.031 I slot print_timing: id 1 | task 4497 | total time = 5974.24 ms / 728 tokens 8.51.764.032 I slot print_timing: id 1 | task 4497 | graphs reused = 3264 8.51.764.032 I slot print_timing: id 1 | task 4497 | graph reallocs = 0 / 0 (same size) / (changed size) 8.51.764.059 I slot release: id 1 | task 4497 | stop processing: n_tokens = 727, truncated = 0 8.53.073.234 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.858 8.53.073.314 I slot launch_slot_: id 0 | task 4508 | processing task, is_child = 0 8.53.073.365 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.936 MiB) 8.53.254.891 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 391855631637 8.53.255.083 I slot launch_slot_: id 1 | task 4509 | processing task, is_child = 0 8.54.379.160 I slot print_timing: id 2 | task 4503 | prompt processing, n_tokens = 721, progress = 0.99, t = 3.61 s / 199.82 tokens per second 8.54.383.683 I slot print_timing: id 3 | task 4504 | prompt processing, n_tokens = 757, progress = 0.99, t = 3.61 s / 209.81 tokens per second 8.55.073.497 I slot print_timing: id 0 | task 4508 | prompt eval time = 1602.67 ms / 124 tokens ( 12.92 ms per token, 77.37 tokens per second) 8.55.073.502 I slot print_timing: id 0 | task 4508 | eval time = 215.73 ms / 2 tokens ( 215.73 ms per token, 4.64 tokens per second) 8.55.073.503 I slot print_timing: id 0 | task 4508 | total time = 1818.39 ms / 126 tokens 8.55.073.504 I slot print_timing: id 0 | task 4508 | graphs reused = 3264 8.55.073.504 I slot print_timing: id 0 | task 4508 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.074.236 I slot release: id 0 | task 4508 | stop processing: n_tokens = 740, truncated = 0 8.55.074.438 I slot print_timing: id 2 | task 4503 | prompt eval time = 4266.51 ms / 725 tokens ( 5.88 ms per token, 169.93 tokens per second) 8.55.074.449 I slot print_timing: id 2 | task 4503 | eval time = 216.50 ms / 2 tokens ( 216.50 ms per token, 4.62 tokens per second) 8.55.074.449 I slot print_timing: id 2 | task 4503 | total time = 4483.01 ms / 727 tokens 8.55.074.450 I slot print_timing: id 2 | task 4503 | graphs reused = 3264 8.55.074.450 I slot print_timing: id 2 | task 4503 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.074.476 I slot release: id 2 | task 4503 | stop processing: n_tokens = 726, truncated = 0 8.55.074.820 I slot print_timing: id 3 | task 4504 | prompt eval time = 4266.76 ms / 761 tokens ( 5.61 ms per token, 178.36 tokens per second) 8.55.074.823 I slot print_timing: id 3 | task 4504 | eval time = 216.47 ms / 2 tokens ( 216.47 ms per token, 4.62 tokens per second) 8.55.074.823 I slot print_timing: id 3 | task 4504 | total time = 4483.23 ms / 763 tokens 8.55.074.823 I slot print_timing: id 3 | task 4504 | graphs reused = 3264 8.55.074.824 I slot print_timing: id 3 | task 4504 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.074.855 I slot release: id 3 | task 4504 | stop processing: n_tokens = 762, truncated = 0 8.55.712.832 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 391858941815 8.55.712.881 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.034 MiB) 8.56.104.241 I slot launch_slot_: id 0 | task 4515 | processing task, is_child = 0 8.56.104.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.545 MiB) 8.56.161.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.604 MiB) 8.56.209.830 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 391858942054 8.56.209.946 I slot launch_slot_: id 2 | task 4516 | processing task, is_child = 0 8.56.209.991 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 391858942433 8.56.210.047 I slot launch_slot_: id 3 | task 4517 | processing task, is_child = 0 8.58.416.961 I slot print_timing: id 1 | task 4509 | prompt eval time = 4053.22 ms / 798 tokens ( 5.08 ms per token, 196.88 tokens per second) 8.58.416.963 I slot print_timing: id 1 | task 4509 | eval time = 1102.98 ms / 2 tokens ( 1102.98 ms per token, 0.91 tokens per second) 8.58.416.964 I slot print_timing: id 1 | task 4509 | total time = 5156.20 ms / 800 tokens 8.58.416.974 I slot print_timing: id 1 | task 4509 | graphs reused = 3264 8.58.416.976 I slot print_timing: id 1 | task 4509 | graph reallocs = 0 / 0 (same size) / (changed size) 8.58.417.039 I slot release: id 1 | task 4509 | stop processing: n_tokens = 799, truncated = 0 8.58.607.658 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 391862284617 8.58.607.725 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.690 MiB) 8.58.972.496 I slot launch_slot_: id 1 | task 4521 | processing task, is_child = 0 9.01.386.072 I slot print_timing: id 0 | task 4515 | prompt processing, n_tokens = 679, progress = 0.85, t = 5.18 s / 131.18 tokens per second 9.01.517.514 I slot print_timing: id 2 | task 4516 | prompt processing, n_tokens = 679, progress = 0.84, t = 5.17 s / 131.23 tokens per second 9.01.519.687 I slot print_timing: id 3 | task 4517 | prompt processing, n_tokens = 893, progress = 0.86, t = 5.17 s / 172.60 tokens per second 9.02.721.115 I slot print_timing: id 0 | task 4515 | prompt processing, n_tokens = 795, progress = 0.99, t = 6.51 s / 122.10 tokens per second 9.02.850.825 I slot print_timing: id 1 | task 4521 | prompt processing, n_tokens = 319, progress = 0.38, t = 3.74 s / 85.38 tokens per second 9.02.850.834 I slot print_timing: id 2 | task 4516 | prompt processing, n_tokens = 805, progress = 1.00, t = 6.51 s / 123.67 tokens per second 9.02.853.826 I slot print_timing: id 3 | task 4517 | prompt processing, n_tokens = 1038, progress = 1.00, t = 6.51 s / 159.47 tokens per second 9.03.022.584 I slot print_timing: id 1 | task 4521 | prompt processing, n_tokens = 329, progress = 0.39, t = 4.04 s / 81.49 tokens per second 9.03.781.705 I slot print_timing: id 0 | task 4515 | prompt eval time = 6812.16 ms / 799 tokens ( 8.53 ms per token, 117.29 tokens per second) 9.03.781.707 I slot print_timing: id 0 | task 4515 | eval time = 759.47 ms / 2 tokens ( 759.47 ms per token, 1.32 tokens per second) 9.03.781.707 I slot print_timing: id 0 | task 4515 | total time = 7571.64 ms / 801 tokens 9.03.781.708 I slot print_timing: id 0 | task 4515 | graphs reused = 3264 9.03.781.708 I slot print_timing: id 0 | task 4515 | graph reallocs = 0 / 0 (same size) / (changed size) 9.03.782.807 I slot release: id 0 | task 4515 | stop processing: n_tokens = 800, truncated = 0 9.03.783.272 I slot print_timing: id 2 | task 4516 | prompt eval time = 6810.31 ms / 809 tokens ( 8.42 ms per token, 118.79 tokens per second) 9.03.783.275 I slot print_timing: id 2 | task 4516 | eval time = 760.87 ms / 2 tokens ( 760.87 ms per token, 1.31 tokens per second) 9.03.783.276 I slot print_timing: id 2 | task 4516 | total time = 7571.19 ms / 811 tokens 9.03.783.276 I slot print_timing: id 2 | task 4516 | graphs reused = 3264 9.03.783.277 I slot print_timing: id 2 | task 4516 | graph reallocs = 0 / 0 (same size) / (changed size) 9.03.783.342 I slot release: id 2 | task 4516 | stop processing: n_tokens = 810, truncated = 0 9.03.783.789 I slot print_timing: id 3 | task 4517 | prompt eval time = 6810.45 ms / 1042 tokens ( 6.54 ms per token, 153.00 tokens per second) 9.03.783.791 I slot print_timing: id 3 | task 4517 | eval time = 761.21 ms / 2 tokens ( 761.21 ms per token, 1.31 tokens per second) 9.03.783.791 I slot print_timing: id 3 | task 4517 | total time = 7571.66 ms / 1044 tokens 9.03.783.792 I slot print_timing: id 3 | task 4517 | graphs reused = 3264 9.03.783.792 I slot print_timing: id 3 | task 4517 | graph reallocs = 0 / 0 (same size) / (changed size) 9.03.783.868 I slot release: id 3 | task 4517 | stop processing: n_tokens = 1043, truncated = 0 9.03.783.889 I slot print_timing: id 1 | task 4521 | prompt processing, n_tokens = 723, progress = 0.86, t = 4.80 s / 150.73 tokens per second 9.03.791.026 I slot print_timing: id 1 | task 4521 | prompt processing, n_tokens = 841, progress = 1.00, t = 4.81 s / 174.98 tokens per second 9.04.154.153 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 391867650386 9.04.154.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.710 MiB) 9.04.190.288 I slot launch_slot_: id 0 | task 4528 | processing task, is_child = 0 9.04.190.339 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.721 MiB) 9.04.221.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.877 MiB) 9.04.270.709 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 391867650920 9.04.270.814 I slot launch_slot_: id 2 | task 4529 | processing task, is_child = 0 9.04.270.863 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1043, t_last = 391867651449 9.04.270.927 I slot launch_slot_: id 3 | task 4530 | processing task, is_child = 0 9.05.169.515 I slot print_timing: id 1 | task 4521 | prompt eval time = 5169.30 ms / 845 tokens ( 6.12 ms per token, 163.47 tokens per second) 9.05.169.518 I slot print_timing: id 1 | task 4521 | eval time = 1015.36 ms / 2 tokens ( 1015.36 ms per token, 0.98 tokens per second) 9.05.169.519 I slot print_timing: id 1 | task 4521 | total time = 6184.66 ms / 847 tokens 9.05.169.519 I slot print_timing: id 1 | task 4521 | graphs reused = 3264 9.05.169.519 I slot print_timing: id 1 | task 4521 | graph reallocs = 0 / 0 (same size) / (changed size) 9.05.171.042 I slot release: id 1 | task 4521 | stop processing: n_tokens = 846, truncated = 0 9.05.577.554 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.888 9.05.577.623 I slot launch_slot_: id 1 | task 4533 | processing task, is_child = 0 9.09.190.753 I slot print_timing: id 0 | task 4528 | prompt processing, n_tokens = 723, progress = 0.79, t = 4.92 s / 146.96 tokens per second 9.09.193.501 I slot print_timing: id 2 | task 4529 | prompt processing, n_tokens = 723, progress = 0.80, t = 4.92 s / 146.97 tokens per second 9.09.196.488 I slot print_timing: id 3 | task 4530 | prompt processing, n_tokens = 723, progress = 0.86, t = 4.92 s / 146.97 tokens per second 9.10.334.384 I slot print_timing: id 1 | task 4533 | prompt eval time = 3613.10 ms / 139 tokens ( 25.99 ms per token, 38.47 tokens per second) 9.10.334.388 I slot print_timing: id 1 | task 4533 | eval time = 1143.64 ms / 2 tokens ( 1143.64 ms per token, 0.87 tokens per second) 9.10.334.388 I slot print_timing: id 1 | task 4533 | total time = 4756.74 ms / 141 tokens 9.10.334.389 I slot print_timing: id 1 | task 4533 | graphs reused = 3264 9.10.334.389 I slot print_timing: id 1 | task 4533 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.334.460 I slot release: id 1 | task 4533 | stop processing: n_tokens = 863, truncated = 0 9.10.334.472 I slot print_timing: id 0 | task 4528 | prompt processing, n_tokens = 906, progress = 1.00, t = 6.06 s / 149.43 tokens per second 9.10.337.477 I slot print_timing: id 2 | task 4529 | prompt processing, n_tokens = 897, progress = 1.00, t = 6.06 s / 147.94 tokens per second 9.10.339.710 I slot print_timing: id 3 | task 4530 | prompt processing, n_tokens = 835, progress = 1.00, t = 6.06 s / 137.72 tokens per second 9.10.450.806 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 391874202038 9.10.450.866 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.271 MiB) 9.10.503.578 I slot launch_slot_: id 1 | task 4538 | processing task, is_child = 0 9.10.888.021 I slot print_timing: id 0 | task 4528 | prompt eval time = 6179.53 ms / 910 tokens ( 6.79 ms per token, 147.26 tokens per second) 9.10.888.023 I slot print_timing: id 0 | task 4528 | eval time = 437.55 ms / 2 tokens ( 437.55 ms per token, 2.29 tokens per second) 9.10.888.024 I slot print_timing: id 0 | task 4528 | total time = 6617.08 ms / 912 tokens 9.10.888.024 I slot print_timing: id 0 | task 4528 | graphs reused = 3264 9.10.888.025 I slot print_timing: id 0 | task 4528 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.889.423 I slot release: id 0 | task 4528 | stop processing: n_tokens = 911, truncated = 0 9.10.889.773 I slot print_timing: id 2 | task 4529 | prompt eval time = 6179.63 ms / 901 tokens ( 6.86 ms per token, 145.80 tokens per second) 9.10.889.779 I slot print_timing: id 2 | task 4529 | eval time = 439.14 ms / 2 tokens ( 439.14 ms per token, 2.28 tokens per second) 9.10.889.779 I slot print_timing: id 2 | task 4529 | total time = 6618.77 ms / 903 tokens 9.10.889.780 I slot print_timing: id 2 | task 4529 | graphs reused = 3264 9.10.889.780 I slot print_timing: id 2 | task 4529 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.889.820 I slot release: id 2 | task 4529 | stop processing: n_tokens = 902, truncated = 0 9.10.890.155 I slot print_timing: id 3 | task 4530 | prompt eval time = 6179.75 ms / 839 tokens ( 7.37 ms per token, 135.77 tokens per second) 9.10.890.158 I slot print_timing: id 3 | task 4530 | eval time = 439.35 ms / 2 tokens ( 439.35 ms per token, 2.28 tokens per second) 9.10.890.160 I slot print_timing: id 3 | task 4530 | total time = 6619.11 ms / 841 tokens 9.10.890.160 I slot print_timing: id 3 | task 4530 | graphs reused = 3264 9.10.890.161 I slot print_timing: id 3 | task 4530 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.890.206 I slot release: id 3 | task 4530 | stop processing: n_tokens = 840, truncated = 0 9.11.105.732 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 391874757003 9.11.105.786 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.646 MiB) 9.11.811.298 I slot launch_slot_: id 0 | task 4542 | processing task, is_child = 0 9.11.811.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.665 MiB) 9.11.866.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.724 MiB) 9.11.916.278 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 902, t_last = 391874757398 9.11.916.388 I slot launch_slot_: id 2 | task 4543 | processing task, is_child = 0 9.11.916.433 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 840, t_last = 391874757784 9.11.916.502 I slot launch_slot_: id 3 | task 4544 | processing task, is_child = 0 9.14.983.860 I slot print_timing: id 1 | task 4538 | prompt eval time = 3329.78 ms / 688 tokens ( 4.84 ms per token, 206.62 tokens per second) 9.14.983.862 I slot print_timing: id 1 | task 4538 | eval time = 1150.48 ms / 2 tokens ( 1150.48 ms per token, 0.87 tokens per second) 9.14.983.863 I slot print_timing: id 1 | task 4538 | total time = 4480.26 ms / 690 tokens 9.14.983.863 I slot print_timing: id 1 | task 4538 | graphs reused = 3264 9.14.983.864 I slot print_timing: id 1 | task 4538 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.985.221 I slot release: id 1 | task 4538 | stop processing: n_tokens = 689, truncated = 0 9.14.985.245 I slot print_timing: id 0 | task 4542 | prompt processing, n_tokens = 632, progress = 0.82, t = 3.07 s / 206.06 tokens per second 9.14.989.669 I slot print_timing: id 2 | task 4543 | prompt processing, n_tokens = 309, progress = 0.37, t = 3.07 s / 100.81 tokens per second 9.14.992.779 I slot print_timing: id 3 | task 4544 | prompt processing, n_tokens = 335, progress = 0.39, t = 3.07 s / 109.30 tokens per second 9.16.652.173 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 689, t_last = 391878852800 9.16.652.230 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.489 MiB) 9.16.812.681 I slot launch_slot_: id 1 | task 4549 | processing task, is_child = 0 9.16.812.703 I slot print_timing: id 0 | task 4542 | prompt processing, n_tokens = 765, progress = 0.99, t = 4.74 s / 161.54 tokens per second 9.16.815.701 I slot print_timing: id 2 | task 4543 | prompt processing, n_tokens = 708, progress = 0.86, t = 4.73 s / 149.57 tokens per second 9.16.818.782 I slot print_timing: id 3 | task 4544 | prompt processing, n_tokens = 708, progress = 0.83, t = 4.73 s / 149.57 tokens per second 9.17.793.121 I slot print_timing: id 2 | task 4543 | prompt processing, n_tokens = 821, progress = 1.00, t = 5.87 s / 139.82 tokens per second 9.17.795.367 I slot print_timing: id 3 | task 4544 | prompt processing, n_tokens = 847, progress = 1.00, t = 5.87 s / 144.25 tokens per second 9.18.236.685 I slot print_timing: id 0 | task 4542 | prompt eval time = 5873.99 ms / 769 tokens ( 7.64 ms per token, 130.92 tokens per second) 9.18.236.687 I slot print_timing: id 0 | task 4542 | eval time = 446.19 ms / 2 tokens ( 446.19 ms per token, 2.24 tokens per second) 9.18.236.697 I slot print_timing: id 0 | task 4542 | total time = 6320.17 ms / 771 tokens 9.18.236.699 I slot print_timing: id 0 | task 4542 | graphs reused = 3264 9.18.236.700 I slot print_timing: id 0 | task 4542 | graph reallocs = 0 / 0 (same size) / (changed size) 9.18.238.722 I slot release: id 0 | task 4542 | stop processing: n_tokens = 770, truncated = 0 9.18.968.803 I slot print_timing: id 2 | task 4543 | prompt eval time = 6320.66 ms / 825 tokens ( 7.66 ms per token, 130.52 tokens per second) 9.18.968.809 I slot print_timing: id 2 | task 4543 | eval time = 729.62 ms / 2 tokens ( 729.62 ms per token, 1.37 tokens per second) 9.18.968.809 I slot print_timing: id 2 | task 4543 | total time = 7050.28 ms / 827 tokens 9.18.968.809 I slot print_timing: id 2 | task 4543 | graphs reused = 3264 9.18.968.810 I slot print_timing: id 2 | task 4543 | graph reallocs = 0 / 0 (same size) / (changed size) 9.18.968.873 I slot release: id 2 | task 4543 | stop processing: n_tokens = 826, truncated = 0 9.18.969.111 I slot print_timing: id 3 | task 4544 | prompt eval time = 6321.12 ms / 851 tokens ( 7.43 ms per token, 134.63 tokens per second) 9.18.969.114 I slot print_timing: id 3 | task 4544 | eval time = 729.42 ms / 2 tokens ( 729.42 ms per token, 1.37 tokens per second) 9.18.969.114 I slot print_timing: id 3 | task 4544 | total time = 7050.54 ms / 853 tokens 9.18.969.115 I slot print_timing: id 3 | task 4544 | graphs reused = 3264 9.18.969.115 I slot print_timing: id 3 | task 4544 | graph reallocs = 0 / 0 (same size) / (changed size) 9.18.969.141 I slot release: id 3 | task 4544 | stop processing: n_tokens = 852, truncated = 0 9.18.969.153 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 391882106301 9.18.969.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 338.040 MiB) 9.19.045.747 I slot launch_slot_: id 0 | task 4553 | processing task, is_child = 0 9.19.045.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.311 MiB) 9.19.117.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 338.255 MiB) 9.19.176.123 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 391882836451 9.19.176.232 I slot launch_slot_: id 2 | task 4554 | processing task, is_child = 0 9.19.176.276 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 852, t_last = 391882836719 9.19.176.339 I slot launch_slot_: id 3 | task 4555 | processing task, is_child = 0 9.20.000.355 I slot print_timing: id 1 | task 4549 | prompt processing, n_tokens = 748, progress = 0.99, t = 3.11 s / 240.59 tokens per second 9.23.061.836 I slot print_timing: id 1 | task 4549 | prompt eval time = 4066.11 ms / 752 tokens ( 5.41 ms per token, 184.94 tokens per second) 9.23.061.841 I slot print_timing: id 1 | task 4549 | eval time = 2180.13 ms / 2 tokens ( 2180.13 ms per token, 0.46 tokens per second) 9.23.061.843 I slot print_timing: id 1 | task 4549 | total time = 6246.24 ms / 754 tokens 9.23.061.843 I slot print_timing: id 1 | task 4549 | graphs reused = 3264 9.23.061.843 I slot print_timing: id 1 | task 4549 | graph reallocs = 0 / 0 (same size) / (changed size) 9.23.061.900 I slot release: id 1 | task 4549 | stop processing: n_tokens = 753, truncated = 0 9.23.061.914 I slot print_timing: id 0 | task 4553 | prompt processing, n_tokens = 603, progress = 0.85, t = 3.89 s / 155.20 tokens per second 9.23.064.488 I slot print_timing: id 2 | task 4554 | prompt processing, n_tokens = 603, progress = 0.82, t = 3.88 s / 155.28 tokens per second 9.23.067.900 I slot print_timing: id 3 | task 4555 | prompt processing, n_tokens = 603, progress = 0.84, t = 3.88 s / 155.28 tokens per second 9.23.845.719 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 391886929479 9.23.845.773 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 367.703 MiB) 9.23.966.202 I slot launch_slot_: id 1 | task 4560 | processing task, is_child = 0 9.23.966.229 I slot print_timing: id 0 | task 4553 | prompt processing, n_tokens = 709, progress = 0.99, t = 4.67 s / 151.84 tokens per second 9.23.968.944 I slot print_timing: id 2 | task 4554 | prompt processing, n_tokens = 732, progress = 0.99, t = 4.67 s / 156.83 tokens per second 9.23.971.439 I slot print_timing: id 3 | task 4555 | prompt processing, n_tokens = 715, progress = 0.99, t = 4.67 s / 153.19 tokens per second 9.24.722.864 I slot print_timing: id 0 | task 4553 | prompt eval time = 5212.96 ms / 713 tokens ( 7.31 ms per token, 136.77 tokens per second) 9.24.722.866 I slot print_timing: id 0 | task 4553 | eval time = 333.55 ms / 2 tokens ( 333.55 ms per token, 3.00 tokens per second) 9.24.722.866 I slot print_timing: id 0 | task 4553 | total time = 5546.51 ms / 715 tokens 9.24.722.867 I slot print_timing: id 0 | task 4553 | graphs reused = 3264 9.24.722.867 I slot print_timing: id 0 | task 4553 | graph reallocs = 0 / 0 (same size) / (changed size) 9.24.722.913 I slot release: id 0 | task 4553 | stop processing: n_tokens = 714, truncated = 0 9.24.723.067 I slot print_timing: id 2 | task 4554 | prompt eval time = 5211.23 ms / 736 tokens ( 7.08 ms per token, 141.23 tokens per second) 9.24.723.072 I slot print_timing: id 2 | task 4554 | eval time = 333.51 ms / 2 tokens ( 333.51 ms per token, 3.00 tokens per second) 9.24.723.072 I slot print_timing: id 2 | task 4554 | total time = 5544.74 ms / 738 tokens 9.24.723.073 I slot print_timing: id 2 | task 4554 | graphs reused = 3264 9.24.723.073 I slot print_timing: id 2 | task 4554 | graph reallocs = 0 / 0 (same size) / (changed size) 9.24.723.109 I slot release: id 2 | task 4554 | stop processing: n_tokens = 737, truncated = 0 9.24.723.284 I slot print_timing: id 3 | task 4555 | prompt eval time = 5211.41 ms / 719 tokens ( 7.25 ms per token, 137.97 tokens per second) 9.24.723.293 I slot print_timing: id 3 | task 4555 | eval time = 333.50 ms / 2 tokens ( 333.50 ms per token, 3.00 tokens per second) 9.24.723.293 I slot print_timing: id 3 | task 4555 | total time = 5544.91 ms / 721 tokens 9.24.723.293 I slot print_timing: id 3 | task 4555 | graphs reused = 3264 9.24.723.294 I slot print_timing: id 3 | task 4555 | graph reallocs = 0 / 0 (same size) / (changed size) 9.24.723.321 I slot release: id 3 | task 4555 | stop processing: n_tokens = 720, truncated = 0 9.25.444.676 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.884 9.25.444.738 I slot launch_slot_: id 0 | task 4565 | processing task, is_child = 0 9.25.444.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 362.971 MiB) 9.25.756.248 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 366.002 MiB) 9.25.798.964 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.856 9.25.799.029 I slot launch_slot_: id 2 | task 4566 | processing task, is_child = 0 9.25.799.074 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.876 9.25.799.095 I slot launch_slot_: id 3 | task 4567 | processing task, is_child = 0 9.26.821.870 I slot print_timing: id 1 | task 4560 | prompt eval time = 2705.82 ms / 710 tokens ( 3.81 ms per token, 262.40 tokens per second) 9.26.821.872 I slot print_timing: id 1 | task 4560 | eval time = 147.20 ms / 2 tokens ( 147.20 ms per token, 6.79 tokens per second) 9.26.821.873 I slot print_timing: id 1 | task 4560 | total time = 2853.02 ms / 712 tokens 9.26.821.873 I slot print_timing: id 1 | task 4560 | graphs reused = 3264 9.26.821.874 I slot print_timing: id 1 | task 4560 | graph reallocs = 0 / 0 (same size) / (changed size) 9.26.822.269 I slot release: id 1 | task 4560 | stop processing: n_tokens = 711, truncated = 0 9.26.878.112 I slot print_timing: id 0 | task 4565 | prompt eval time = 1022.57 ms / 112 tokens ( 9.13 ms per token, 109.53 tokens per second) 9.26.878.114 I slot print_timing: id 0 | task 4565 | eval time = 56.44 ms / 2 tokens ( 56.44 ms per token, 17.72 tokens per second) 9.26.878.115 I slot print_timing: id 0 | task 4565 | total time = 1079.00 ms / 114 tokens 9.26.878.115 I slot print_timing: id 0 | task 4565 | graphs reused = 3264 9.26.878.116 I slot print_timing: id 0 | task 4565 | graph reallocs = 0 / 0 (same size) / (changed size) 9.26.878.147 I slot release: id 0 | task 4565 | stop processing: n_tokens = 716, truncated = 0 9.26.878.368 I slot print_timing: id 2 | task 4566 | prompt eval time = 1018.21 ms / 104 tokens ( 9.79 ms per token, 102.14 tokens per second) 9.26.878.389 I slot print_timing: id 2 | task 4566 | eval time = 55.85 ms / 2 tokens ( 55.85 ms per token, 17.90 tokens per second) 9.26.878.390 I slot print_timing: id 2 | task 4566 | total time = 1074.06 ms / 106 tokens 9.26.878.391 I slot print_timing: id 2 | task 4566 | graphs reused = 3264 9.26.878.391 I slot print_timing: id 2 | task 4566 | graph reallocs = 0 / 0 (same size) / (changed size) 9.26.878.415 I slot release: id 2 | task 4566 | stop processing: n_tokens = 708, truncated = 0 9.26.878.636 I slot print_timing: id 3 | task 4567 | prompt eval time = 1015.24 ms / 106 tokens ( 9.58 ms per token, 104.41 tokens per second) 9.26.878.640 I slot print_timing: id 3 | task 4567 | eval time = 55.90 ms / 2 tokens ( 55.90 ms per token, 17.89 tokens per second) 9.26.878.640 I slot print_timing: id 3 | task 4567 | total time = 1071.13 ms / 108 tokens 9.26.878.641 I slot print_timing: id 3 | task 4567 | graphs reused = 3264 9.26.878.641 I slot print_timing: id 3 | task 4567 | graph reallocs = 0 / 0 (same size) / (changed size) 9.26.878.663 I slot release: id 3 | task 4567 | stop processing: n_tokens = 710, truncated = 0 9.26.878.669 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.893 9.26.878.728 I slot launch_slot_: id 3 | task 4571 | processing task, is_child = 0 9.26.878.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 352.451 MiB) 9.26.904.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 354.133 MiB) 9.26.949.168 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 350.085 MiB) 9.26.993.754 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.881 9.26.993.819 I slot launch_slot_: id 0 | task 4572 | processing task, is_child = 0 9.26.993.911 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.893 9.26.993.933 I slot launch_slot_: id 2 | task 4573 | processing task, is_child = 0 9.26.993.977 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.887 9.26.993.996 I slot launch_slot_: id 1 | task 4574 | processing task, is_child = 0 9.28.269.897 I slot print_timing: id 0 | task 4572 | prompt eval time = 1222.65 ms / 106 tokens ( 11.53 ms per token, 86.70 tokens per second) 9.28.269.902 I slot print_timing: id 0 | task 4572 | eval time = 53.23 ms / 2 tokens ( 53.23 ms per token, 18.78 tokens per second) 9.28.269.902 I slot print_timing: id 0 | task 4572 | total time = 1275.89 ms / 108 tokens 9.28.269.903 I slot print_timing: id 0 | task 4572 | graphs reused = 3264 9.28.269.903 I slot print_timing: id 0 | task 4572 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.269.949 I slot release: id 0 | task 4572 | stop processing: n_tokens = 710, truncated = 0 9.28.270.096 I slot print_timing: id 1 | task 4574 | prompt eval time = 1219.57 ms / 148 tokens ( 8.24 ms per token, 121.35 tokens per second) 9.28.270.102 I slot print_timing: id 1 | task 4574 | eval time = 53.27 ms / 2 tokens ( 53.27 ms per token, 18.77 tokens per second) 9.28.270.103 I slot print_timing: id 1 | task 4574 | total time = 1272.85 ms / 150 tokens 9.28.270.103 I slot print_timing: id 1 | task 4574 | graphs reused = 3264 9.28.270.103 I slot print_timing: id 1 | task 4574 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.270.127 I slot release: id 1 | task 4574 | stop processing: n_tokens = 752, truncated = 0 9.28.270.291 I slot print_timing: id 2 | task 4573 | prompt eval time = 1216.54 ms / 113 tokens ( 10.77 ms per token, 92.89 tokens per second) 9.28.270.293 I slot print_timing: id 2 | task 4573 | eval time = 53.30 ms / 2 tokens ( 53.30 ms per token, 18.76 tokens per second) 9.28.270.294 I slot print_timing: id 2 | task 4573 | total time = 1269.84 ms / 115 tokens 9.28.270.294 I slot print_timing: id 2 | task 4573 | graphs reused = 3264 9.28.270.294 I slot print_timing: id 2 | task 4573 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.270.333 I slot release: id 2 | task 4573 | stop processing: n_tokens = 717, truncated = 0 9.28.270.509 I slot print_timing: id 3 | task 4571 | prompt eval time = 1213.54 ms / 114 tokens ( 10.65 ms per token, 93.94 tokens per second) 9.28.270.515 I slot print_timing: id 3 | task 4571 | eval time = 53.31 ms / 2 tokens ( 53.31 ms per token, 18.76 tokens per second) 9.28.270.515 I slot print_timing: id 3 | task 4571 | total time = 1266.85 ms / 116 tokens 9.28.270.516 I slot print_timing: id 3 | task 4571 | graphs reused = 3264 9.28.270.516 I slot print_timing: id 3 | task 4571 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.270.548 I slot release: id 3 | task 4571 | stop processing: n_tokens = 718, truncated = 0 9.28.279.659 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 391892137527 9.28.279.708 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 350.300 MiB) 9.28.291.080 I slot launch_slot_: id 0 | task 4578 | processing task, is_child = 0 9.28.291.128 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 348.912 MiB) 9.28.301.702 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.282 MiB) 9.28.312.763 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.536 MiB) 9.28.323.499 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 752, t_last = 391892137705 9.28.323.585 I slot launch_slot_: id 1 | task 4579 | processing task, is_child = 0 9.28.323.655 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 391892137911 9.28.323.710 I slot launch_slot_: id 2 | task 4580 | processing task, is_child = 0 9.28.323.747 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 718, t_last = 391892138126 9.28.323.800 I slot launch_slot_: id 3 | task 4581 | processing task, is_child = 0 9.31.919.048 I slot print_timing: id 0 | task 4578 | prompt processing, n_tokens = 575, progress = 0.53, t = 3.60 s / 159.93 tokens per second 9.32.243.718 I slot print_timing: id 1 | task 4579 | prompt processing, n_tokens = 364, progress = 0.41, t = 3.60 s / 101.25 tokens per second 9.32.247.416 I slot print_timing: id 2 | task 4580 | prompt processing, n_tokens = 380, progress = 0.42, t = 3.60 s / 105.70 tokens per second 9.32.249.311 I slot print_timing: id 3 | task 4581 | prompt processing, n_tokens = 566, progress = 0.52, t = 3.60 s / 157.44 tokens per second 9.34.951.801 I slot print_timing: id 0 | task 4578 | prompt processing, n_tokens = 905, progress = 0.83, t = 6.63 s / 136.54 tokens per second 9.35.053.782 I slot print_timing: id 1 | task 4579 | prompt processing, n_tokens = 762, progress = 0.87, t = 6.63 s / 114.97 tokens per second 9.35.057.212 I slot print_timing: id 2 | task 4580 | prompt processing, n_tokens = 762, progress = 0.85, t = 6.63 s / 114.97 tokens per second 9.35.059.112 I slot print_timing: id 3 | task 4581 | prompt processing, n_tokens = 905, progress = 0.84, t = 6.63 s / 136.55 tokens per second 9.36.281.016 I slot print_timing: id 0 | task 4578 | prompt processing, n_tokens = 1087, progress = 1.00, t = 7.96 s / 136.61 tokens per second 9.36.484.083 I slot print_timing: id 1 | task 4579 | prompt processing, n_tokens = 876, progress = 1.00, t = 7.96 s / 110.09 tokens per second 9.36.488.231 I slot print_timing: id 2 | task 4580 | prompt processing, n_tokens = 892, progress = 1.00, t = 7.96 s / 112.10 tokens per second 9.36.490.372 I slot print_timing: id 3 | task 4581 | prompt processing, n_tokens = 1078, progress = 1.00, t = 7.96 s / 135.48 tokens per second 9.36.665.577 I slot print_timing: id 0 | task 4578 | prompt eval time = 8288.12 ms / 1091 tokens ( 7.60 ms per token, 131.63 tokens per second) 9.36.665.579 I slot print_timing: id 0 | task 4578 | eval time = 53.64 ms / 2 tokens ( 53.64 ms per token, 18.64 tokens per second) 9.36.665.580 I slot print_timing: id 0 | task 4578 | total time = 8341.76 ms / 1093 tokens 9.36.665.580 I slot print_timing: id 0 | task 4578 | graphs reused = 3264 9.36.665.581 I slot print_timing: id 0 | task 4578 | graph reallocs = 0 / 0 (same size) / (changed size) 9.36.665.640 I slot release: id 0 | task 4578 | stop processing: n_tokens = 1092, truncated = 0 9.36.665.793 I slot print_timing: id 1 | task 4579 | prompt eval time = 8288.27 ms / 880 tokens ( 9.42 ms per token, 106.17 tokens per second) 9.36.665.795 I slot print_timing: id 1 | task 4579 | eval time = 53.66 ms / 2 tokens ( 53.66 ms per token, 18.64 tokens per second) 9.36.665.796 I slot print_timing: id 1 | task 4579 | total time = 8341.93 ms / 882 tokens 9.36.665.796 I slot print_timing: id 1 | task 4579 | graphs reused = 3264 9.36.665.797 I slot print_timing: id 1 | task 4579 | graph reallocs = 0 / 0 (same size) / (changed size) 9.36.665.841 I slot release: id 1 | task 4579 | stop processing: n_tokens = 881, truncated = 0 9.36.665.994 I slot print_timing: id 2 | task 4580 | prompt eval time = 8288.42 ms / 896 tokens ( 9.25 ms per token, 108.10 tokens per second) 9.36.665.996 I slot print_timing: id 2 | task 4580 | eval time = 53.66 ms / 2 tokens ( 53.66 ms per token, 18.63 tokens per second) 9.36.665.996 I slot print_timing: id 2 | task 4580 | total time = 8342.09 ms / 898 tokens 9.36.665.996 I slot print_timing: id 2 | task 4580 | graphs reused = 3264 9.36.665.997 I slot print_timing: id 2 | task 4580 | graph reallocs = 0 / 0 (same size) / (changed size) 9.36.666.026 I slot release: id 2 | task 4580 | stop processing: n_tokens = 897, truncated = 0 9.36.666.199 I slot print_timing: id 3 | task 4581 | prompt eval time = 8288.59 ms / 1082 tokens ( 7.66 ms per token, 130.54 tokens per second) 9.36.666.200 I slot print_timing: id 3 | task 4581 | eval time = 53.65 ms / 2 tokens ( 53.65 ms per token, 18.64 tokens per second) 9.36.666.201 I slot print_timing: id 3 | task 4581 | total time = 8342.24 ms / 1084 tokens 9.36.666.201 I slot print_timing: id 3 | task 4581 | graphs reused = 3264 9.36.666.201 I slot print_timing: id 3 | task 4581 | graph reallocs = 0 / 0 (same size) / (changed size) 9.36.666.224 I slot release: id 3 | task 4581 | stop processing: n_tokens = 1083, truncated = 0 9.36.676.605 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.895 9.36.676.630 I slot launch_slot_: id 0 | task 4589 | processing task, is_child = 0 9.36.676.680 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.263 MiB) 9.36.688.107 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.967 MiB) 9.36.700.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.690 MiB) 9.36.720.152 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.901 9.36.720.209 I slot launch_slot_: id 3 | task 4590 | processing task, is_child = 0 9.36.720.299 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 391900533419 9.36.723.206 I slot launch_slot_: id 1 | task 4591 | processing task, is_child = 0 9.36.723.259 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 391900533604 9.36.723.328 I slot launch_slot_: id 2 | task 4592 | processing task, is_child = 0 9.39.295.426 I slot print_timing: id 0 | task 4589 | prompt eval time = 2057.26 ms / 166 tokens ( 12.39 ms per token, 80.69 tokens per second) 9.39.295.430 I slot print_timing: id 0 | task 4589 | eval time = 514.83 ms / 2 tokens ( 514.83 ms per token, 1.94 tokens per second) 9.39.295.431 I slot print_timing: id 0 | task 4589 | total time = 2572.09 ms / 168 tokens 9.39.295.432 I slot print_timing: id 0 | task 4589 | graphs reused = 3264 9.39.295.432 I slot print_timing: id 0 | task 4589 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.295.488 I slot release: id 0 | task 4589 | stop processing: n_tokens = 1072, truncated = 0 9.39.295.777 I slot print_timing: id 1 | task 4591 | prompt eval time = 2054.18 ms / 174 tokens ( 11.81 ms per token, 84.71 tokens per second) 9.39.295.780 I slot print_timing: id 1 | task 4591 | eval time = 514.92 ms / 2 tokens ( 514.92 ms per token, 1.94 tokens per second) 9.39.295.780 I slot print_timing: id 1 | task 4591 | total time = 2569.09 ms / 176 tokens 9.39.295.781 I slot print_timing: id 1 | task 4591 | graphs reused = 3264 9.39.295.781 I slot print_timing: id 1 | task 4591 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.295.819 I slot release: id 1 | task 4591 | stop processing: n_tokens = 1080, truncated = 0 9.39.296.090 I slot print_timing: id 3 | task 4590 | prompt eval time = 2051.12 ms / 180 tokens ( 11.40 ms per token, 87.76 tokens per second) 9.39.296.093 I slot print_timing: id 3 | task 4590 | eval time = 514.99 ms / 2 tokens ( 514.99 ms per token, 1.94 tokens per second) 9.39.296.094 I slot print_timing: id 3 | task 4590 | total time = 2566.12 ms / 182 tokens 9.39.296.094 I slot print_timing: id 3 | task 4590 | graphs reused = 3264 9.39.296.095 I slot print_timing: id 3 | task 4590 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.296.125 I slot release: id 3 | task 4590 | stop processing: n_tokens = 1086, truncated = 0 9.39.937.994 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.911 9.39.938.059 I slot launch_slot_: id 0 | task 4598 | processing task, is_child = 0 9.40.355.569 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.710 MiB) 9.40.365.150 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.905 9.40.365.213 I slot launch_slot_: id 1 | task 4599 | processing task, is_child = 0 9.40.365.279 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.900 9.40.365.301 I slot launch_slot_: id 3 | task 4600 | processing task, is_child = 0 9.40.371.794 I slot print_timing: id 2 | task 4592 | prompt processing, n_tokens = 1076, progress = 1.00, t = 3.21 s / 335.40 tokens per second 9.41.727.521 I slot print_timing: id 2 | task 4592 | prompt eval time = 4855.11 ms / 1080 tokens ( 4.50 ms per token, 222.45 tokens per second) 9.41.727.525 I slot print_timing: id 2 | task 4592 | eval time = 142.51 ms / 2 tokens ( 142.51 ms per token, 7.02 tokens per second) 9.41.727.526 I slot print_timing: id 2 | task 4592 | total time = 4997.61 ms / 1082 tokens 9.41.727.526 I slot print_timing: id 2 | task 4592 | graphs reused = 3264 9.41.727.527 I slot print_timing: id 2 | task 4592 | graph reallocs = 0 / 0 (same size) / (changed size) 9.41.727.569 I slot release: id 2 | task 4592 | stop processing: n_tokens = 1081, truncated = 0 9.41.783.523 I slot print_timing: id 0 | task 4598 | prompt eval time = 1361.86 ms / 177 tokens ( 7.69 ms per token, 129.97 tokens per second) 9.41.783.525 I slot print_timing: id 0 | task 4598 | eval time = 56.35 ms / 2 tokens ( 56.35 ms per token, 17.75 tokens per second) 9.41.783.526 I slot print_timing: id 0 | task 4598 | total time = 1418.21 ms / 179 tokens 9.41.783.526 I slot print_timing: id 0 | task 4598 | graphs reused = 3264 9.41.783.527 I slot print_timing: id 0 | task 4598 | graph reallocs = 0 / 0 (same size) / (changed size) 9.41.783.571 I slot release: id 0 | task 4598 | stop processing: n_tokens = 1083, truncated = 0 9.41.783.778 I slot print_timing: id 1 | task 4599 | prompt eval time = 1358.77 ms / 168 tokens ( 8.09 ms per token, 123.64 tokens per second) 9.41.783.781 I slot print_timing: id 1 | task 4599 | eval time = 56.44 ms / 2 tokens ( 56.44 ms per token, 17.72 tokens per second) 9.41.783.782 I slot print_timing: id 1 | task 4599 | total time = 1415.20 ms / 170 tokens 9.41.783.782 I slot print_timing: id 1 | task 4599 | graphs reused = 3264 9.41.783.782 I slot print_timing: id 1 | task 4599 | graph reallocs = 0 / 0 (same size) / (changed size) 9.41.783.813 I slot release: id 1 | task 4599 | stop processing: n_tokens = 1074, truncated = 0 9.41.784.056 I slot print_timing: id 3 | task 4600 | prompt eval time = 1354.05 ms / 183 tokens ( 7.40 ms per token, 135.15 tokens per second) 9.41.784.058 I slot print_timing: id 3 | task 4600 | eval time = 56.23 ms / 2 tokens ( 56.23 ms per token, 17.78 tokens per second) 9.41.784.058 I slot print_timing: id 3 | task 4600 | total time = 1410.28 ms / 185 tokens 9.41.784.059 I slot print_timing: id 3 | task 4600 | graphs reused = 3264 9.41.784.059 I slot print_timing: id 3 | task 4600 | graph reallocs = 0 / 0 (same size) / (changed size) 9.41.784.081 I slot release: id 3 | task 4600 | stop processing: n_tokens = 1089, truncated = 0 9.41.784.088 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.902 9.41.784.158 I slot launch_slot_: id 0 | task 4604 | processing task, is_child = 0 9.41.784.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.905 MiB) 9.41.796.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.461 MiB) 9.41.809.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.942 MiB) 9.41.931.493 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.910 9.41.931.577 I slot launch_slot_: id 1 | task 4605 | processing task, is_child = 0 9.41.931.778 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.904 9.41.931.807 I slot launch_slot_: id 2 | task 4606 | processing task, is_child = 0 9.41.931.858 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.897 9.41.931.881 I slot launch_slot_: id 3 | task 4607 | processing task, is_child = 0 9.43.493.376 I slot print_timing: id 0 | task 4604 | prompt eval time = 1507.25 ms / 178 tokens ( 8.47 ms per token, 118.10 tokens per second) 9.43.493.378 I slot print_timing: id 0 | task 4604 | eval time = 54.23 ms / 2 tokens ( 54.23 ms per token, 18.44 tokens per second) 9.43.493.378 I slot print_timing: id 0 | task 4604 | total time = 1561.48 ms / 180 tokens 9.43.493.379 I slot print_timing: id 0 | task 4604 | graphs reused = 3264 9.43.493.379 I slot print_timing: id 0 | task 4604 | graph reallocs = 0 / 0 (same size) / (changed size) 9.43.493.525 I slot release: id 0 | task 4604 | stop processing: n_tokens = 1084, truncated = 0 9.43.493.687 I slot print_timing: id 1 | task 4605 | prompt eval time = 1503.71 ms / 171 tokens ( 8.79 ms per token, 113.72 tokens per second) 9.43.493.693 I slot print_timing: id 1 | task 4605 | eval time = 54.04 ms / 2 tokens ( 54.04 ms per token, 18.50 tokens per second) 9.43.493.693 I slot print_timing: id 1 | task 4605 | total time = 1557.75 ms / 173 tokens 9.43.493.693 I slot print_timing: id 1 | task 4605 | graphs reused = 3264 9.43.493.694 I slot print_timing: id 1 | task 4605 | graph reallocs = 0 / 0 (same size) / (changed size) 9.43.493.721 I slot release: id 1 | task 4605 | stop processing: n_tokens = 1077, truncated = 0 9.43.493.890 I slot print_timing: id 2 | task 4606 | prompt eval time = 1500.01 ms / 175 tokens ( 8.57 ms per token, 116.67 tokens per second) 9.43.493.894 I slot print_timing: id 2 | task 4606 | eval time = 53.95 ms / 2 tokens ( 53.95 ms per token, 18.53 tokens per second) 9.43.493.895 I slot print_timing: id 2 | task 4606 | total time = 1553.96 ms / 177 tokens 9.43.493.895 I slot print_timing: id 2 | task 4606 | graphs reused = 3264 9.43.493.895 I slot print_timing: id 2 | task 4606 | graph reallocs = 0 / 0 (same size) / (changed size) 9.43.493.943 I slot release: id 2 | task 4606 | stop processing: n_tokens = 1081, truncated = 0 9.43.494.101 I slot print_timing: id 3 | task 4607 | prompt eval time = 1496.38 ms / 170 tokens ( 8.80 ms per token, 113.61 tokens per second) 9.43.494.105 I slot print_timing: id 3 | task 4607 | eval time = 53.85 ms / 2 tokens ( 53.85 ms per token, 18.57 tokens per second) 9.43.494.106 I slot print_timing: id 3 | task 4607 | total time = 1550.24 ms / 172 tokens 9.43.494.106 I slot print_timing: id 3 | task 4607 | graphs reused = 3264 9.43.494.106 I slot print_timing: id 3 | task 4607 | graph reallocs = 0 / 0 (same size) / (changed size) 9.43.494.134 I slot release: id 3 | task 4607 | stop processing: n_tokens = 1076, truncated = 0 9.43.506.382 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 9.43.506.411 I slot launch_slot_: id 0 | task 4611 | processing task, is_child = 0 9.43.506.492 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.880 MiB) 9.43.611.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.704 MiB) 9.43.843.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.492 MiB) 9.43.976.875 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.907 9.43.976.953 I slot launch_slot_: id 1 | task 4612 | processing task, is_child = 0 9.43.977.072 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1081, t_last = 391907361521 9.43.977.144 I slot launch_slot_: id 2 | task 4613 | processing task, is_child = 0 9.43.977.195 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1076, t_last = 391907361712 9.43.977.263 I slot launch_slot_: id 3 | task 4614 | processing task, is_child = 0 9.46.848.427 I slot print_timing: id 0 | task 4611 | prompt eval time = 2304.27 ms / 173 tokens ( 13.32 ms per token, 75.08 tokens per second) 9.46.848.430 I slot print_timing: id 0 | task 4611 | eval time = 566.88 ms / 2 tokens ( 566.88 ms per token, 1.76 tokens per second) 9.46.848.430 I slot print_timing: id 0 | task 4611 | total time = 2871.15 ms / 175 tokens 9.46.848.431 I slot print_timing: id 0 | task 4611 | graphs reused = 3264 9.46.848.431 I slot print_timing: id 0 | task 4611 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.848.504 I slot release: id 0 | task 4611 | stop processing: n_tokens = 1079, truncated = 0 9.46.848.762 I slot print_timing: id 1 | task 4612 | prompt eval time = 2298.34 ms / 174 tokens ( 13.21 ms per token, 75.71 tokens per second) 9.46.848.772 I slot print_timing: id 1 | task 4612 | eval time = 566.83 ms / 2 tokens ( 566.83 ms per token, 1.76 tokens per second) 9.46.848.772 I slot print_timing: id 1 | task 4612 | total time = 2865.17 ms / 176 tokens 9.46.848.772 I slot print_timing: id 1 | task 4612 | graphs reused = 3264 9.46.848.773 I slot print_timing: id 1 | task 4612 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.848.813 I slot release: id 1 | task 4612 | stop processing: n_tokens = 1080, truncated = 0 9.48.134.381 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1079, t_last = 391910716083 9.48.134.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.539 MiB) 9.48.261.391 I slot launch_slot_: id 0 | task 4619 | processing task, is_child = 0 9.48.261.457 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.123 MiB) 9.48.399.978 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1080, t_last = 391910716391 9.48.400.106 I slot launch_slot_: id 1 | task 4620 | processing task, is_child = 0 9.48.400.283 I slot print_timing: id 2 | task 4613 | prompt processing, n_tokens = 878, progress = 0.86, t = 4.13 s / 212.41 tokens per second 9.48.402.182 I slot print_timing: id 3 | task 4614 | prompt processing, n_tokens = 878, progress = 0.85, t = 4.13 s / 212.42 tokens per second 9.49.882.728 I slot print_timing: id 2 | task 4613 | prompt processing, n_tokens = 1013, progress = 1.00, t = 5.79 s / 175.08 tokens per second 9.49.887.113 I slot print_timing: id 3 | task 4614 | prompt processing, n_tokens = 1027, progress = 1.00, t = 5.79 s / 177.50 tokens per second 9.51.448.058 I slot print_timing: id 2 | task 4613 | prompt eval time = 6644.79 ms / 1017 tokens ( 6.53 ms per token, 153.05 tokens per second) 9.51.448.063 I slot print_timing: id 2 | task 4613 | eval time = 802.35 ms / 2 tokens ( 802.35 ms per token, 1.25 tokens per second) 9.51.448.063 I slot print_timing: id 2 | task 4613 | total time = 7447.14 ms / 1019 tokens 9.51.448.064 I slot print_timing: id 2 | task 4613 | graphs reused = 3264 9.51.448.064 I slot print_timing: id 2 | task 4613 | graph reallocs = 0 / 0 (same size) / (changed size) 9.51.448.249 I slot release: id 2 | task 4613 | stop processing: n_tokens = 1018, truncated = 0 9.51.448.588 I slot print_timing: id 3 | task 4614 | prompt eval time = 6645.11 ms / 1031 tokens ( 6.45 ms per token, 155.15 tokens per second) 9.51.448.592 I slot print_timing: id 3 | task 4614 | eval time = 802.48 ms / 2 tokens ( 802.48 ms per token, 1.25 tokens per second) 9.51.448.592 I slot print_timing: id 3 | task 4614 | total time = 7447.58 ms / 1033 tokens 9.51.448.593 I slot print_timing: id 3 | task 4614 | graphs reused = 3264 9.51.448.593 I slot print_timing: id 3 | task 4614 | graph reallocs = 0 / 0 (same size) / (changed size) 9.51.448.644 I slot release: id 3 | task 4614 | stop processing: n_tokens = 1032, truncated = 0 9.51.448.651 I slot print_timing: id 0 | task 4619 | prompt processing, n_tokens = 555, progress = 0.52, t = 3.05 s / 182.11 tokens per second 9.51.475.553 I slot print_timing: id 1 | task 4620 | prompt processing, n_tokens = 590, progress = 0.53, t = 3.05 s / 193.60 tokens per second 9.52.554.479 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.890 9.52.554.558 I slot launch_slot_: id 2 | task 4625 | processing task, is_child = 0 9.52.554.621 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.218 MiB) 9.52.735.658 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.878 9.52.735.773 I slot launch_slot_: id 3 | task 4626 | processing task, is_child = 0 9.52.735.788 I slot print_timing: id 0 | task 4619 | prompt processing, n_tokens = 878, progress = 0.82, t = 4.15 s / 211.34 tokens per second 9.52.752.148 I slot print_timing: id 1 | task 4620 | prompt processing, n_tokens = 878, progress = 0.79, t = 4.15 s / 211.35 tokens per second 9.54.377.632 I slot print_timing: id 0 | task 4619 | prompt processing, n_tokens = 1067, progress = 1.00, t = 5.98 s / 178.50 tokens per second 9.54.474.886 I slot print_timing: id 1 | task 4620 | prompt processing, n_tokens = 1102, progress = 1.00, t = 5.98 s / 184.36 tokens per second 9.54.663.463 I slot print_timing: id 0 | task 4619 | prompt eval time = 6209.14 ms / 1071 tokens ( 5.80 ms per token, 172.49 tokens per second) 9.54.663.468 I slot print_timing: id 0 | task 4619 | eval time = 54.19 ms / 2 tokens ( 54.19 ms per token, 18.45 tokens per second) 9.54.663.469 I slot print_timing: id 0 | task 4619 | total time = 6263.34 ms / 1073 tokens 9.54.663.469 I slot print_timing: id 0 | task 4619 | graphs reused = 3264 9.54.663.469 I slot print_timing: id 0 | task 4619 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.663.580 I slot release: id 0 | task 4619 | stop processing: n_tokens = 1072, truncated = 0 9.54.663.745 I slot print_timing: id 1 | task 4620 | prompt eval time = 6209.24 ms / 1106 tokens ( 5.61 ms per token, 178.12 tokens per second) 9.54.663.748 I slot print_timing: id 1 | task 4620 | eval time = 54.31 ms / 2 tokens ( 54.31 ms per token, 18.41 tokens per second) 9.54.663.749 I slot print_timing: id 1 | task 4620 | total time = 6263.55 ms / 1108 tokens 9.54.663.749 I slot print_timing: id 1 | task 4620 | graphs reused = 3264 9.54.663.753 I slot print_timing: id 1 | task 4620 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.663.828 I slot release: id 1 | task 4620 | stop processing: n_tokens = 1107, truncated = 0 9.54.664.055 I slot print_timing: id 2 | task 4625 | prompt eval time = 1840.50 ms / 152 tokens ( 12.11 ms per token, 82.59 tokens per second) 9.54.664.058 I slot print_timing: id 2 | task 4625 | eval time = 54.10 ms / 2 tokens ( 54.10 ms per token, 18.48 tokens per second) 9.54.664.058 I slot print_timing: id 2 | task 4625 | total time = 1894.60 ms / 154 tokens 9.54.664.059 I slot print_timing: id 2 | task 4625 | graphs reused = 3264 9.54.664.059 I slot print_timing: id 2 | task 4625 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.665.697 I slot release: id 2 | task 4625 | stop processing: n_tokens = 1031, truncated = 0 9.54.665.846 I slot print_timing: id 3 | task 4626 | prompt eval time = 1836.12 ms / 167 tokens ( 10.99 ms per token, 90.95 tokens per second) 9.54.665.848 I slot print_timing: id 3 | task 4626 | eval time = 55.37 ms / 2 tokens ( 55.37 ms per token, 18.06 tokens per second) 9.54.665.849 I slot print_timing: id 3 | task 4626 | total time = 1891.50 ms / 169 tokens 9.54.665.850 I slot print_timing: id 3 | task 4626 | graphs reused = 3264 9.54.665.850 I slot print_timing: id 3 | task 4626 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.665.885 I slot release: id 3 | task 4626 | stop processing: n_tokens = 1046, truncated = 0 9.54.674.619 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1072, t_last = 391918531158 9.54.674.727 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.726 MiB) 9.54.751.607 I slot launch_slot_: id 0 | task 4630 | processing task, is_child = 0 9.54.751.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.791 MiB) 9.54.847.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.478 MiB) 9.54.930.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.145 MiB) 9.55.002.059 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1107, t_last = 391918531406 9.55.002.177 I slot launch_slot_: id 1 | task 4631 | processing task, is_child = 0 9.55.002.274 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 391918533277 9.55.002.349 I slot launch_slot_: id 2 | task 4632 | processing task, is_child = 0 9.55.002.399 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1046, t_last = 391918533464 9.55.002.469 I slot launch_slot_: id 3 | task 4633 | processing task, is_child = 0 9.59.161.702 I slot print_timing: id 0 | task 4630 | prompt processing, n_tokens = 623, progress = 0.85, t = 4.16 s / 149.79 tokens per second 9.59.238.680 I slot print_timing: id 1 | task 4631 | prompt processing, n_tokens = 623, progress = 0.84, t = 4.16 s / 149.79 tokens per second 9.59.241.943 I slot print_timing: id 2 | task 4632 | prompt processing, n_tokens = 623, progress = 0.83, t = 4.16 s / 149.79 tokens per second 9.59.243.889 I slot print_timing: id 3 | task 4633 | prompt processing, n_tokens = 281, progress = 0.35, t = 4.16 s / 67.56 tokens per second 10.00.317.273 I slot print_timing: id 0 | task 4630 | prompt processing, n_tokens = 725, progress = 0.99, t = 5.31 s / 136.41 tokens per second 10.00.765.042 I slot print_timing: id 1 | task 4631 | prompt processing, n_tokens = 736, progress = 0.99, t = 5.31 s / 138.48 tokens per second 10.00.768.789 I slot print_timing: id 2 | task 4632 | prompt processing, n_tokens = 749, progress = 0.99, t = 5.31 s / 140.93 tokens per second 10.00.774.639 I slot print_timing: id 3 | task 4633 | prompt processing, n_tokens = 623, progress = 0.78, t = 5.31 s / 117.23 tokens per second 10.01.296.802 I slot print_timing: id 3 | task 4633 | prompt processing, n_tokens = 793, progress = 0.99, t = 6.29 s / 126.02 tokens per second 10.01.394.662 I slot print_timing: id 0 | task 4630 | prompt eval time = 6293.68 ms / 729 tokens ( 8.63 ms per token, 115.83 tokens per second) 10.01.394.664 I slot print_timing: id 0 | task 4630 | eval time = 98.50 ms / 2 tokens ( 98.50 ms per token, 10.15 tokens per second) 10.01.394.665 I slot print_timing: id 0 | task 4630 | total time = 6392.18 ms / 731 tokens 10.01.394.665 I slot print_timing: id 0 | task 4630 | graphs reused = 3264 10.01.394.666 I slot print_timing: id 0 | task 4630 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.395.141 I slot release: id 0 | task 4630 | stop processing: n_tokens = 730, truncated = 0 10.01.395.399 I slot print_timing: id 1 | task 4631 | prompt eval time = 6293.99 ms / 740 tokens ( 8.51 ms per token, 117.57 tokens per second) 10.01.395.404 I slot print_timing: id 1 | task 4631 | eval time = 98.84 ms / 2 tokens ( 98.84 ms per token, 10.12 tokens per second) 10.01.395.404 I slot print_timing: id 1 | task 4631 | total time = 6392.84 ms / 742 tokens 10.01.395.404 I slot print_timing: id 1 | task 4631 | graphs reused = 3264 10.01.395.405 I slot print_timing: id 1 | task 4631 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.395.769 I slot release: id 1 | task 4631 | stop processing: n_tokens = 741, truncated = 0 10.01.395.931 I slot print_timing: id 2 | task 4632 | prompt eval time = 6294.16 ms / 753 tokens ( 8.36 ms per token, 119.63 tokens per second) 10.01.395.933 I slot print_timing: id 2 | task 4632 | eval time = 99.14 ms / 2 tokens ( 99.14 ms per token, 10.09 tokens per second) 10.01.395.934 I slot print_timing: id 2 | task 4632 | total time = 6393.30 ms / 755 tokens 10.01.395.934 I slot print_timing: id 2 | task 4632 | graphs reused = 3264 10.01.395.935 I slot print_timing: id 2 | task 4632 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.395.983 I slot release: id 2 | task 4632 | stop processing: n_tokens = 754, truncated = 0 10.01.418.239 I slot print_timing: id 3 | task 4633 | prompt eval time = 6393.52 ms / 797 tokens ( 8.02 ms per token, 124.66 tokens per second) 10.01.418.241 I slot print_timing: id 3 | task 4633 | eval time = 22.02 ms / 2 tokens ( 22.02 ms per token, 45.41 tokens per second) 10.01.418.242 I slot print_timing: id 3 | task 4633 | total time = 6415.55 ms / 799 tokens 10.01.418.243 I slot print_timing: id 3 | task 4633 | graphs reused = 3264 10.01.418.243 I slot print_timing: id 3 | task 4633 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.418.302 I slot release: id 3 | task 4633 | stop processing: n_tokens = 798, truncated = 0 10.01.418.310 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.892 10.01.418.349 I slot launch_slot_: id 0 | task 4641 | processing task, is_child = 0 10.01.418.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.067 MiB) 10.01.484.075 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.969 MiB) 10.01.549.391 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.911 MiB) 10.01.610.078 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.881 10.01.610.142 I slot launch_slot_: id 1 | task 4642 | processing task, is_child = 0 10.01.610.226 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.863 10.01.610.248 I slot launch_slot_: id 2 | task 4643 | processing task, is_child = 0 10.01.610.287 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.862 (> 0.100 thold), f_keep = 0.816 10.01.610.304 I slot launch_slot_: id 3 | task 4644 | processing task, is_child = 0 10.02.842.390 I slot print_timing: id 0 | task 4641 | prompt eval time = 1177.83 ms / 123 tokens ( 9.58 ms per token, 104.43 tokens per second) 10.02.842.393 I slot print_timing: id 0 | task 4641 | eval time = 54.24 ms / 2 tokens ( 54.24 ms per token, 18.43 tokens per second) 10.02.842.393 I slot print_timing: id 0 | task 4641 | total time = 1232.08 ms / 125 tokens 10.02.842.394 I slot print_timing: id 0 | task 4641 | graphs reused = 3264 10.02.842.394 I slot print_timing: id 0 | task 4641 | graph reallocs = 0 / 0 (same size) / (changed size) 10.02.842.469 I slot release: id 0 | task 4641 | stop processing: n_tokens = 747, truncated = 0 10.02.842.621 I slot print_timing: id 1 | task 4642 | prompt eval time = 1173.90 ms / 116 tokens ( 10.12 ms per token, 98.82 tokens per second) 10.02.842.624 I slot print_timing: id 1 | task 4642 | eval time = 54.15 ms / 2 tokens ( 54.15 ms per token, 18.47 tokens per second) 10.02.842.624 I slot print_timing: id 1 | task 4642 | total time = 1228.04 ms / 118 tokens 10.02.842.625 I slot print_timing: id 1 | task 4642 | graphs reused = 3264 10.02.842.625 I slot print_timing: id 1 | task 4642 | graph reallocs = 0 / 0 (same size) / (changed size) 10.02.842.655 I slot release: id 1 | task 4642 | stop processing: n_tokens = 740, truncated = 0 10.02.842.820 I slot print_timing: id 2 | task 4643 | prompt eval time = 1170.86 ms / 110 tokens ( 10.64 ms per token, 93.95 tokens per second) 10.02.842.822 I slot print_timing: id 2 | task 4643 | eval time = 54.13 ms / 2 tokens ( 54.13 ms per token, 18.47 tokens per second) 10.02.842.823 I slot print_timing: id 2 | task 4643 | total time = 1225.00 ms / 112 tokens 10.02.842.823 I slot print_timing: id 2 | task 4643 | graphs reused = 3264 10.02.842.823 I slot print_timing: id 2 | task 4643 | graph reallocs = 0 / 0 (same size) / (changed size) 10.02.842.862 I slot release: id 2 | task 4643 | stop processing: n_tokens = 734, truncated = 0 10.02.843.035 I slot print_timing: id 3 | task 4644 | prompt eval time = 1167.83 ms / 132 tokens ( 8.85 ms per token, 113.03 tokens per second) 10.02.843.037 I slot print_timing: id 3 | task 4644 | eval time = 54.13 ms / 2 tokens ( 54.13 ms per token, 18.47 tokens per second) 10.02.843.037 I slot print_timing: id 3 | task 4644 | total time = 1221.96 ms / 134 tokens 10.02.843.038 I slot print_timing: id 3 | task 4644 | graphs reused = 3264 10.02.843.038 I slot print_timing: id 3 | task 4644 | graph reallocs = 0 / 0 (same size) / (changed size) 10.02.843.087 I slot release: id 3 | task 4644 | stop processing: n_tokens = 756, truncated = 0 10.02.852.278 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.871 10.02.852.306 I slot launch_slot_: id 0 | task 4648 | processing task, is_child = 0 10.02.852.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.950 MiB) 10.02.929.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.771 MiB) 10.03.004.198 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.087 MiB) 10.03.061.397 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 391926710233 10.03.061.514 I slot launch_slot_: id 1 | task 4649 | processing task, is_child = 0 10.03.061.592 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 734, t_last = 391926710440 10.03.061.649 I slot launch_slot_: id 2 | task 4650 | processing task, is_child = 0 10.03.061.686 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 391926710665 10.03.061.739 I slot launch_slot_: id 3 | task 4651 | processing task, is_child = 0 10.06.057.077 I slot print_timing: id 0 | task 4648 | prompt eval time = 2153.38 ms / 124 tokens ( 17.37 ms per token, 57.58 tokens per second) 10.06.057.083 I slot print_timing: id 0 | task 4648 | eval time = 841.94 ms / 2 tokens ( 841.94 ms per token, 1.19 tokens per second) 10.06.057.083 I slot print_timing: id 0 | task 4648 | total time = 2995.32 ms / 126 tokens 10.06.057.084 I slot print_timing: id 0 | task 4648 | graphs reused = 3264 10.06.057.084 I slot print_timing: id 0 | task 4648 | graph reallocs = 0 / 0 (same size) / (changed size) 10.06.057.201 I slot release: id 0 | task 4648 | stop processing: n_tokens = 748, truncated = 0 10.08.049.085 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 391929924780 10.08.049.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.106 MiB) 10.08.173.828 I slot launch_slot_: id 0 | task 4656 | processing task, is_child = 0 10.08.173.995 I slot print_timing: id 1 | task 4649 | prompt processing, n_tokens = 820, progress = 0.84, t = 4.98 s / 164.55 tokens per second 10.08.176.646 I slot print_timing: id 2 | task 4650 | prompt processing, n_tokens = 820, progress = 0.86, t = 4.98 s / 164.55 tokens per second 10.08.179.521 I slot print_timing: id 3 | task 4651 | prompt processing, n_tokens = 820, progress = 0.83, t = 4.98 s / 164.55 tokens per second 10.09.599.497 I slot print_timing: id 1 | task 4649 | prompt processing, n_tokens = 969, progress = 1.00, t = 6.35 s / 152.57 tokens per second 10.09.603.560 I slot print_timing: id 2 | task 4650 | prompt processing, n_tokens = 951, progress = 1.00, t = 6.35 s / 149.74 tokens per second 10.09.605.522 I slot print_timing: id 3 | task 4651 | prompt processing, n_tokens = 986, progress = 1.00, t = 6.35 s / 155.25 tokens per second 10.10.583.931 I slot print_timing: id 1 | task 4649 | prompt eval time = 7072.36 ms / 973 tokens ( 7.27 ms per token, 137.58 tokens per second) 10.10.583.935 I slot print_timing: id 1 | task 4649 | eval time = 445.77 ms / 2 tokens ( 445.77 ms per token, 2.24 tokens per second) 10.10.583.935 I slot print_timing: id 1 | task 4649 | total time = 7518.14 ms / 975 tokens 10.10.583.935 I slot print_timing: id 1 | task 4649 | graphs reused = 3264 10.10.583.936 I slot print_timing: id 1 | task 4649 | graph reallocs = 0 / 0 (same size) / (changed size) 10.10.585.386 I slot release: id 1 | task 4649 | stop processing: n_tokens = 974, truncated = 0 10.10.585.935 I slot print_timing: id 2 | task 4650 | prompt eval time = 7072.65 ms / 955 tokens ( 7.41 ms per token, 135.03 tokens per second) 10.10.585.938 I slot print_timing: id 2 | task 4650 | eval time = 447.44 ms / 2 tokens ( 447.44 ms per token, 2.23 tokens per second) 10.10.585.947 I slot print_timing: id 2 | task 4650 | total time = 7520.09 ms / 957 tokens 10.10.585.954 I slot print_timing: id 2 | task 4650 | graphs reused = 3264 10.10.585.955 I slot print_timing: id 2 | task 4650 | graph reallocs = 0 / 0 (same size) / (changed size) 10.10.586.981 I slot release: id 2 | task 4650 | stop processing: n_tokens = 956, truncated = 0 10.10.587.507 I slot print_timing: id 3 | task 4651 | prompt eval time = 7072.84 ms / 990 tokens ( 7.14 ms per token, 139.97 tokens per second) 10.10.587.512 I slot print_timing: id 3 | task 4651 | eval time = 448.77 ms / 2 tokens ( 448.77 ms per token, 2.23 tokens per second) 10.10.587.513 I slot print_timing: id 3 | task 4651 | total time = 7521.61 ms / 992 tokens 10.10.587.513 I slot print_timing: id 3 | task 4651 | graphs reused = 3264 10.10.587.514 I slot print_timing: id 3 | task 4651 | graph reallocs = 0 / 0 (same size) / (changed size) 10.10.587.644 I slot release: id 3 | task 4651 | stop processing: n_tokens = 991, truncated = 0 10.11.173.026 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 974, t_last = 391934452966 10.11.173.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.294 MiB) 10.11.639.663 I slot launch_slot_: id 1 | task 4662 | processing task, is_child = 0 10.11.639.720 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.606 MiB) 10.11.714.795 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.185 MiB) 10.11.788.158 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 391934454565 10.11.788.270 I slot launch_slot_: id 2 | task 4663 | processing task, is_child = 0 10.11.788.320 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 391934455223 10.11.788.391 I slot launch_slot_: id 3 | task 4664 | processing task, is_child = 0 10.14.575.932 I slot print_timing: id 0 | task 4656 | prompt eval time = 5277.98 ms / 1044 tokens ( 5.06 ms per token, 197.80 tokens per second) 10.14.575.935 I slot print_timing: id 0 | task 4656 | eval time = 1124.10 ms / 2 tokens ( 1124.10 ms per token, 0.89 tokens per second) 10.14.575.936 I slot print_timing: id 0 | task 4656 | total time = 6402.07 ms / 1046 tokens 10.14.575.936 I slot print_timing: id 0 | task 4656 | graphs reused = 3264 10.14.575.936 I slot print_timing: id 0 | task 4656 | graph reallocs = 0 / 0 (same size) / (changed size) 10.14.577.759 I slot release: id 0 | task 4656 | stop processing: n_tokens = 1045, truncated = 0 10.16.991.444 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1045, t_last = 391938445338 10.16.991.511 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.302 MiB) 10.17.371.027 I slot launch_slot_: id 0 | task 4668 | processing task, is_child = 0 10.17.371.136 I slot print_timing: id 1 | task 4662 | prompt processing, n_tokens = 645, progress = 0.56, t = 5.15 s / 125.28 tokens per second 10.17.375.043 I slot print_timing: id 2 | task 4663 | prompt processing, n_tokens = 608, progress = 0.54, t = 5.15 s / 118.09 tokens per second 10.17.376.917 I slot print_timing: id 3 | task 4664 | prompt processing, n_tokens = 1575, progress = 0.75, t = 5.15 s / 305.92 tokens per second 10.19.887.962 I slot print_timing: id 1 | task 4662 | prompt processing, n_tokens = 977, progress = 0.84, t = 7.86 s / 124.35 tokens per second 10.19.892.960 I slot print_timing: id 2 | task 4663 | prompt processing, n_tokens = 977, progress = 0.87, t = 7.86 s / 124.35 tokens per second 10.19.895.055 I slot print_timing: id 3 | task 4664 | prompt processing, n_tokens = 1761, progress = 0.84, t = 7.86 s / 224.14 tokens per second 10.21.570.741 I slot print_timing: id 0 | task 4668 | prompt processing, n_tokens = 640, progress = 0.31, t = 4.20 s / 152.39 tokens per second 10.21.570.770 I slot print_timing: id 1 | task 4662 | prompt processing, n_tokens = 1157, progress = 1.00, t = 9.73 s / 118.94 tokens per second 10.21.988.214 I slot print_timing: id 2 | task 4663 | prompt processing, n_tokens = 1120, progress = 1.00, t = 9.73 s / 115.13 tokens per second 10.21.990.986 I slot print_timing: id 3 | task 4664 | prompt processing, n_tokens = 2087, progress = 1.00, t = 9.73 s / 214.54 tokens per second 10.23.737.007 I slot print_timing: id 0 | task 4668 | prompt processing, n_tokens = 1578, progress = 0.75, t = 6.37 s / 247.91 tokens per second 10.24.206.642 I slot print_timing: id 1 | task 4662 | prompt eval time = 11893.65 ms / 1161 tokens ( 10.24 ms per token, 97.62 tokens per second) 10.24.206.647 I slot print_timing: id 1 | task 4662 | eval time = 470.11 ms / 2 tokens ( 470.11 ms per token, 2.13 tokens per second) 10.24.206.648 I slot print_timing: id 1 | task 4662 | total time = 12363.76 ms / 1163 tokens 10.24.206.648 I slot print_timing: id 1 | task 4662 | graphs reused = 3264 10.24.206.649 I slot print_timing: id 1 | task 4662 | graph reallocs = 0 / 0 (same size) / (changed size) 10.24.208.426 I slot release: id 1 | task 4662 | stop processing: n_tokens = 1162, truncated = 0 10.24.208.724 I slot print_timing: id 2 | task 4663 | prompt eval time = 11893.80 ms / 1124 tokens ( 10.58 ms per token, 94.50 tokens per second) 10.24.208.728 I slot print_timing: id 2 | task 4663 | eval time = 471.96 ms / 2 tokens ( 471.96 ms per token, 2.12 tokens per second) 10.24.208.728 I slot print_timing: id 2 | task 4663 | total time = 12365.76 ms / 1126 tokens 10.24.208.728 I slot print_timing: id 2 | task 4663 | graphs reused = 3264 10.24.208.729 I slot print_timing: id 2 | task 4663 | graph reallocs = 0 / 0 (same size) / (changed size) 10.24.208.789 I slot release: id 2 | task 4663 | stop processing: n_tokens = 1125, truncated = 0 10.24.209.118 I slot print_timing: id 3 | task 4664 | prompt eval time = 11893.97 ms / 2091 tokens ( 5.69 ms per token, 175.80 tokens per second) 10.24.209.121 I slot print_timing: id 3 | task 4664 | eval time = 472.13 ms / 2 tokens ( 472.13 ms per token, 2.12 tokens per second) 10.24.209.122 I slot print_timing: id 3 | task 4664 | total time = 12366.09 ms / 2093 tokens 10.24.209.122 I slot print_timing: id 3 | task 4664 | graphs reused = 3264 10.24.209.123 I slot print_timing: id 3 | task 4664 | graph reallocs = 0 / 0 (same size) / (changed size) 10.24.210.133 I slot release: id 3 | task 4664 | stop processing: n_tokens = 2092, truncated = 0 10.24.210.149 I slot print_timing: id 0 | task 4668 | prompt processing, n_tokens = 1761, progress = 0.84, t = 6.84 s / 257.63 tokens per second 10.24.218.784 I slot print_timing: id 0 | task 4668 | prompt processing, n_tokens = 2090, progress = 1.00, t = 6.85 s / 305.21 tokens per second 10.24.899.972 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.856 10.24.900.024 I slot launch_slot_: id 3 | task 4675 | processing task, is_child = 0 10.24.900.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.067 MiB) 10.25.139.449 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.204 MiB) 10.25.537.605 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1162, t_last = 391948076005 10.25.537.769 I slot launch_slot_: id 1 | task 4676 | processing task, is_child = 0 10.25.537.822 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1125, t_last = 391948076367 10.25.537.899 I slot launch_slot_: id 2 | task 4677 | processing task, is_child = 0 10.27.466.121 I slot print_timing: id 0 | task 4668 | prompt eval time = 7528.91 ms / 2094 tokens ( 3.60 ms per token, 278.13 tokens per second) 10.27.466.124 I slot print_timing: id 0 | task 4668 | eval time = 2566.15 ms / 2 tokens ( 2566.15 ms per token, 0.39 tokens per second) 10.27.466.125 I slot print_timing: id 0 | task 4668 | total time = 10095.07 ms / 2096 tokens 10.27.466.125 I slot print_timing: id 0 | task 4668 | graphs reused = 3264 10.27.466.126 I slot print_timing: id 0 | task 4668 | graph reallocs = 0 / 0 (same size) / (changed size) 10.27.466.982 I slot release: id 0 | task 4668 | stop processing: n_tokens = 2095, truncated = 0 10.28.510.980 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.854 10.28.511.053 I slot launch_slot_: id 0 | task 4680 | processing task, is_child = 0 10.32.227.792 I slot print_timing: id 3 | task 4675 | prompt eval time = 2972.86 ms / 296 tokens ( 10.04 ms per token, 99.57 tokens per second) 10.32.227.795 I slot print_timing: id 3 | task 4675 | eval time = 3716.81 ms / 2 tokens ( 3716.81 ms per token, 0.27 tokens per second) 10.32.227.795 I slot print_timing: id 3 | task 4675 | total time = 6689.67 ms / 298 tokens 10.32.227.795 I slot print_timing: id 3 | task 4675 | graphs reused = 3264 10.32.227.796 I slot print_timing: id 3 | task 4675 | graph reallocs = 0 / 0 (same size) / (changed size) 10.32.227.970 I slot release: id 3 | task 4675 | stop processing: n_tokens = 2058, truncated = 0 10.32.227.990 I slot print_timing: id 0 | task 4680 | prompt processing, n_tokens = 365, progress = 1.00, t = 3.72 s / 98.21 tokens per second 10.32.232.055 I slot print_timing: id 1 | task 4676 | prompt processing, n_tokens = 1589, progress = 0.75, t = 6.69 s / 237.53 tokens per second 10.32.238.523 I slot print_timing: id 2 | task 4677 | prompt processing, n_tokens = 1373, progress = 0.67, t = 6.69 s / 205.25 tokens per second 10.33.047.604 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.869 10.33.047.682 I slot launch_slot_: id 3 | task 4683 | processing task, is_child = 0 10.33.047.698 I slot print_timing: id 1 | task 4676 | prompt processing, n_tokens = 1761, progress = 0.84, t = 7.51 s / 234.51 tokens per second 10.33.051.214 I slot print_timing: id 2 | task 4677 | prompt processing, n_tokens = 1525, progress = 0.75, t = 7.51 s / 203.08 tokens per second 10.34.989.941 I slot print_timing: id 0 | task 4680 | prompt eval time = 4536.53 ms / 369 tokens ( 12.29 ms per token, 81.34 tokens per second) 10.34.989.944 I slot print_timing: id 0 | task 4680 | eval time = 1942.34 ms / 2 tokens ( 1942.34 ms per token, 0.51 tokens per second) 10.34.989.945 I slot print_timing: id 0 | task 4680 | total time = 6478.87 ms / 371 tokens 10.34.989.945 I slot print_timing: id 0 | task 4680 | graphs reused = 3264 10.34.989.946 I slot print_timing: id 0 | task 4680 | graph reallocs = 0 / 0 (same size) / (changed size) 10.34.990.077 I slot release: id 0 | task 4680 | stop processing: n_tokens = 2131, truncated = 0 10.34.990.093 I slot print_timing: id 1 | task 4676 | prompt processing, n_tokens = 2101, progress = 1.00, t = 9.45 s / 222.29 tokens per second 10.34.993.392 I slot print_timing: id 2 | task 4677 | prompt processing, n_tokens = 1761, progress = 0.86, t = 9.45 s / 186.32 tokens per second 10.35.648.640 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 10.35.648.713 I slot launch_slot_: id 0 | task 4686 | processing task, is_child = 0 10.35.652.872 I slot print_timing: id 2 | task 4677 | prompt processing, n_tokens = 2037, progress = 1.00, t = 10.11 s / 201.48 tokens per second 10.36.441.300 I slot print_timing: id 1 | task 4676 | prompt eval time = 10110.44 ms / 2105 tokens ( 4.80 ms per token, 208.20 tokens per second) 10.36.441.305 I slot print_timing: id 1 | task 4676 | eval time = 792.95 ms / 2 tokens ( 792.95 ms per token, 1.26 tokens per second) 10.36.441.305 I slot print_timing: id 1 | task 4676 | total time = 10903.38 ms / 2107 tokens 10.36.441.306 I slot print_timing: id 1 | task 4676 | graphs reused = 3264 10.36.441.306 I slot print_timing: id 1 | task 4676 | graph reallocs = 0 / 0 (same size) / (changed size) 10.36.443.117 I slot release: id 1 | task 4676 | stop processing: n_tokens = 2106, truncated = 0 10.36.443.548 I slot print_timing: id 3 | task 4683 | prompt eval time = 2594.67 ms / 300 tokens ( 8.65 ms per token, 115.62 tokens per second) 10.36.443.550 I slot print_timing: id 3 | task 4683 | eval time = 794.92 ms / 2 tokens ( 794.92 ms per token, 1.26 tokens per second) 10.36.443.551 I slot print_timing: id 3 | task 4683 | total time = 3389.59 ms / 302 tokens 10.36.443.551 I slot print_timing: id 3 | task 4683 | graphs reused = 3264 10.36.443.552 I slot print_timing: id 3 | task 4683 | graph reallocs = 0 / 0 (same size) / (changed size) 10.36.443.716 I slot release: id 3 | task 4683 | stop processing: n_tokens = 2062, truncated = 0 10.36.512.193 I slot print_timing: id 2 | task 4677 | prompt eval time = 10905.34 ms / 2041 tokens ( 5.34 ms per token, 187.16 tokens per second) 10.36.512.195 I slot print_timing: id 2 | task 4677 | eval time = 68.82 ms / 2 tokens ( 68.82 ms per token, 14.53 tokens per second) 10.36.512.197 I slot print_timing: id 2 | task 4677 | total time = 10974.15 ms / 2043 tokens 10.36.512.197 I slot print_timing: id 2 | task 4677 | graphs reused = 3264 10.36.512.197 I slot print_timing: id 2 | task 4677 | graph reallocs = 0 / 0 (same size) / (changed size) 10.36.512.278 I slot release: id 2 | task 4677 | stop processing: n_tokens = 2042, truncated = 0 10.36.512.286 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.850 10.36.512.327 I slot launch_slot_: id 1 | task 4689 | processing task, is_child = 0 10.36.512.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.361 MiB) 10.37.102.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.126 MiB) 10.37.804.162 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.803 (> 0.100 thold), f_keep = 0.877 10.37.804.241 I slot launch_slot_: id 2 | task 4690 | processing task, is_child = 0 10.37.804.328 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.868 10.37.804.358 I slot launch_slot_: id 3 | task 4691 | processing task, is_child = 0 10.39.839.765 I slot print_timing: id 0 | task 4686 | prompt eval time = 863.33 ms / 380 tokens ( 2.27 ms per token, 440.15 tokens per second) 10.39.839.768 I slot print_timing: id 0 | task 4686 | eval time = 3327.70 ms / 2 tokens ( 3327.70 ms per token, 0.30 tokens per second) 10.39.839.768 I slot print_timing: id 0 | task 4686 | total time = 4191.04 ms / 382 tokens 10.39.840.896 I slot print_timing: id 0 | task 4686 | graphs reused = 3264 10.39.840.900 I slot print_timing: id 0 | task 4686 | graph reallocs = 0 / 0 (same size) / (changed size) 10.39.841.075 I slot release: id 0 | task 4686 | stop processing: n_tokens = 2142, truncated = 0 10.39.947.993 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.835 10.39.948.058 I slot launch_slot_: id 0 | task 4694 | processing task, is_child = 0 10.40.514.394 I slot print_timing: id 1 | task 4689 | prompt eval time = 2143.22 ms / 210 tokens ( 10.21 ms per token, 97.98 tokens per second) 10.40.514.397 I slot print_timing: id 1 | task 4689 | eval time = 566.80 ms / 2 tokens ( 566.80 ms per token, 1.76 tokens per second) 10.40.514.397 I slot print_timing: id 1 | task 4689 | total time = 2710.02 ms / 212 tokens 10.40.514.398 I slot print_timing: id 1 | task 4689 | graphs reused = 3264 10.40.514.398 I slot print_timing: id 1 | task 4689 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.514.489 I slot release: id 1 | task 4689 | stop processing: n_tokens = 1972, truncated = 0 10.40.514.651 I slot print_timing: id 2 | task 4690 | prompt eval time = 2140.17 ms / 467 tokens ( 4.58 ms per token, 218.21 tokens per second) 10.40.514.654 I slot print_timing: id 2 | task 4690 | eval time = 566.87 ms / 2 tokens ( 566.87 ms per token, 1.76 tokens per second) 10.40.514.654 I slot print_timing: id 2 | task 4690 | total time = 2707.04 ms / 469 tokens 10.40.514.654 I slot print_timing: id 2 | task 4690 | graphs reused = 3264 10.40.514.655 I slot print_timing: id 2 | task 4690 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.514.739 I slot release: id 2 | task 4690 | stop processing: n_tokens = 2229, truncated = 0 10.40.515.009 I slot print_timing: id 3 | task 4691 | prompt eval time = 2137.16 ms / 258 tokens ( 8.28 ms per token, 120.72 tokens per second) 10.40.515.012 I slot print_timing: id 3 | task 4691 | eval time = 567.02 ms / 2 tokens ( 567.02 ms per token, 1.76 tokens per second) 10.40.515.012 I slot print_timing: id 3 | task 4691 | total time = 2704.18 ms / 260 tokens 10.40.515.012 I slot print_timing: id 3 | task 4691 | graphs reused = 3264 10.40.515.012 I slot print_timing: id 3 | task 4691 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.516.694 I slot release: id 3 | task 4691 | stop processing: n_tokens = 2020, truncated = 0 10.40.578.378 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.907 10.40.578.419 I slot launch_slot_: id 1 | task 4697 | processing task, is_child = 0 10.40.578.519 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.204 MiB) 10.41.177.666 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.107 MiB) 10.41.747.348 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.850 (> 0.100 thold), f_keep = 0.803 10.41.747.423 I slot launch_slot_: id 2 | task 4698 | processing task, is_child = 0 10.41.747.511 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.886 10.41.747.540 I slot launch_slot_: id 3 | task 4699 | processing task, is_child = 0 10.43.650.162 I slot print_timing: id 0 | task 4694 | prompt eval time = 630.30 ms / 253 tokens ( 2.49 ms per token, 401.39 tokens per second) 10.43.650.166 I slot print_timing: id 0 | task 4694 | eval time = 3071.78 ms / 2 tokens ( 3071.78 ms per token, 0.33 tokens per second) 10.43.650.166 I slot print_timing: id 0 | task 4694 | total time = 3702.09 ms / 255 tokens 10.43.650.167 I slot print_timing: id 0 | task 4694 | graphs reused = 3264 10.43.650.167 I slot print_timing: id 0 | task 4694 | graph reallocs = 0 / 0 (same size) / (changed size) 10.43.650.287 I slot release: id 0 | task 4694 | stop processing: n_tokens = 2015, truncated = 0 10.43.757.800 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.888 10.43.757.862 I slot launch_slot_: id 0 | task 4702 | processing task, is_child = 0 10.44.403.574 I slot print_timing: id 1 | task 4697 | prompt eval time = 2009.86 ms / 212 tokens ( 9.48 ms per token, 105.48 tokens per second) 10.44.403.578 I slot print_timing: id 1 | task 4697 | eval time = 646.15 ms / 2 tokens ( 646.15 ms per token, 1.55 tokens per second) 10.44.403.578 I slot print_timing: id 1 | task 4697 | total time = 2656.02 ms / 214 tokens 10.44.403.579 I slot print_timing: id 1 | task 4697 | graphs reused = 3264 10.44.403.579 I slot print_timing: id 1 | task 4697 | graph reallocs = 0 / 0 (same size) / (changed size) 10.44.403.696 I slot release: id 1 | task 4697 | stop processing: n_tokens = 1974, truncated = 0 10.44.403.854 I slot print_timing: id 2 | task 4698 | prompt eval time = 2006.80 ms / 345 tokens ( 5.82 ms per token, 171.92 tokens per second) 10.44.403.856 I slot print_timing: id 2 | task 4698 | eval time = 646.23 ms / 2 tokens ( 646.23 ms per token, 1.55 tokens per second) 10.44.403.857 I slot print_timing: id 2 | task 4698 | total time = 2653.04 ms / 347 tokens 10.44.403.857 I slot print_timing: id 2 | task 4698 | graphs reused = 3264 10.44.403.857 I slot print_timing: id 2 | task 4698 | graph reallocs = 0 / 0 (same size) / (changed size) 10.44.403.936 I slot release: id 2 | task 4698 | stop processing: n_tokens = 2107, truncated = 0 10.44.404.096 I slot print_timing: id 3 | task 4699 | prompt eval time = 2003.72 ms / 304 tokens ( 6.59 ms per token, 151.72 tokens per second) 10.44.404.098 I slot print_timing: id 3 | task 4699 | eval time = 646.30 ms / 2 tokens ( 646.30 ms per token, 1.55 tokens per second) 10.44.404.099 I slot print_timing: id 3 | task 4699 | total time = 2650.02 ms / 306 tokens 10.44.404.099 I slot print_timing: id 3 | task 4699 | graphs reused = 3264 10.44.404.099 I slot print_timing: id 3 | task 4699 | graph reallocs = 0 / 0 (same size) / (changed size) 10.44.406.392 I slot release: id 3 | task 4699 | stop processing: n_tokens = 2066, truncated = 0 10.44.478.277 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.847 (> 0.100 thold), f_keep = 0.850 10.44.478.329 I slot launch_slot_: id 2 | task 4705 | processing task, is_child = 0 10.44.478.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.165 MiB) 10.45.381.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.185 MiB) 10.46.081.956 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.866 10.46.082.047 I slot launch_slot_: id 3 | task 4706 | processing task, is_child = 0 10.46.082.250 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.906 10.46.082.774 I slot launch_slot_: id 1 | task 4707 | processing task, is_child = 0 10.48.169.361 I slot print_timing: id 0 | task 4702 | prompt eval time = 720.40 ms / 304 tokens ( 2.37 ms per token, 421.99 tokens per second) 10.48.169.364 I slot print_timing: id 0 | task 4702 | eval time = 3691.09 ms / 2 tokens ( 3691.09 ms per token, 0.27 tokens per second) 10.48.169.365 I slot print_timing: id 0 | task 4702 | total time = 4411.48 ms / 306 tokens 10.48.169.365 I slot print_timing: id 0 | task 4702 | graphs reused = 3264 10.48.169.366 I slot print_timing: id 0 | task 4702 | graph reallocs = 0 / 0 (same size) / (changed size) 10.48.169.513 I slot release: id 0 | task 4702 | stop processing: n_tokens = 2066, truncated = 0 10.48.289.317 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.866 10.48.289.402 I slot launch_slot_: id 0 | task 4710 | processing task, is_child = 0 10.49.080.749 I slot print_timing: id 1 | task 4707 | prompt eval time = 2205.39 ms / 405 tokens ( 5.45 ms per token, 183.64 tokens per second) 10.49.080.755 I slot print_timing: id 1 | task 4707 | eval time = 792.56 ms / 2 tokens ( 792.56 ms per token, 1.26 tokens per second) 10.49.080.755 I slot print_timing: id 1 | task 4707 | total time = 2997.95 ms / 407 tokens 10.49.080.756 I slot print_timing: id 1 | task 4707 | graphs reused = 3264 10.49.080.756 I slot print_timing: id 1 | task 4707 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.082.069 I slot release: id 1 | task 4707 | stop processing: n_tokens = 2167, truncated = 0 10.49.082.602 I slot print_timing: id 2 | task 4705 | prompt eval time = 2202.22 ms / 353 tokens ( 6.24 ms per token, 160.29 tokens per second) 10.49.082.606 I slot print_timing: id 2 | task 4705 | eval time = 793.91 ms / 2 tokens ( 793.91 ms per token, 1.26 tokens per second) 10.49.082.606 I slot print_timing: id 2 | task 4705 | total time = 2996.13 ms / 355 tokens 10.49.082.606 I slot print_timing: id 2 | task 4705 | graphs reused = 3264 10.49.082.607 I slot print_timing: id 2 | task 4705 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.082.745 I slot release: id 2 | task 4705 | stop processing: n_tokens = 2115, truncated = 0 10.49.083.181 I slot print_timing: id 3 | task 4706 | prompt eval time = 2198.98 ms / 210 tokens ( 10.47 ms per token, 95.50 tokens per second) 10.49.083.184 I slot print_timing: id 3 | task 4706 | eval time = 793.88 ms / 2 tokens ( 793.88 ms per token, 1.26 tokens per second) 10.49.083.185 I slot print_timing: id 3 | task 4706 | total time = 2992.86 ms / 212 tokens 10.49.083.185 I slot print_timing: id 3 | task 4706 | graphs reused = 3264 10.49.083.185 I slot print_timing: id 3 | task 4706 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.083.745 I slot release: id 3 | task 4706 | stop processing: n_tokens = 1972, truncated = 0 10.49.141.150 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.826 10.49.141.190 I slot launch_slot_: id 1 | task 4713 | processing task, is_child = 0 10.49.141.308 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.246 MiB) 10.49.321.220 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.028 MiB) 10.49.556.436 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.846 10.49.556.528 I slot launch_slot_: id 2 | task 4714 | processing task, is_child = 0 10.49.556.625 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.907 10.49.556.648 I slot launch_slot_: id 3 | task 4715 | processing task, is_child = 0 10.51.205.567 I slot print_timing: id 0 | task 4710 | prompt eval time = 851.73 ms / 413 tokens ( 2.06 ms per token, 484.90 tokens per second) 10.51.205.569 I slot print_timing: id 0 | task 4710 | eval time = 2064.42 ms / 2 tokens ( 2064.42 ms per token, 0.48 tokens per second) 10.51.205.570 I slot print_timing: id 0 | task 4710 | total time = 2916.14 ms / 415 tokens 10.51.205.571 I slot print_timing: id 0 | task 4710 | graphs reused = 3264 10.51.205.571 I slot print_timing: id 0 | task 4710 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.205.668 I slot release: id 0 | task 4710 | stop processing: n_tokens = 2175, truncated = 0 10.51.311.343 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.823 10.51.311.374 I slot launch_slot_: id 0 | task 4718 | processing task, is_child = 0 10.51.726.199 I slot print_timing: id 1 | task 4713 | prompt eval time = 1754.35 ms / 272 tokens ( 6.45 ms per token, 155.04 tokens per second) 10.51.726.206 I slot print_timing: id 1 | task 4713 | eval time = 415.18 ms / 2 tokens ( 415.18 ms per token, 2.41 tokens per second) 10.51.726.206 I slot print_timing: id 1 | task 4713 | total time = 2169.53 ms / 274 tokens 10.51.726.207 I slot print_timing: id 1 | task 4713 | graphs reused = 3264 10.51.726.207 I slot print_timing: id 1 | task 4713 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.726.326 I slot release: id 1 | task 4713 | stop processing: n_tokens = 2034, truncated = 0 10.51.726.487 I slot print_timing: id 2 | task 4714 | prompt eval time = 1750.51 ms / 264 tokens ( 6.63 ms per token, 150.81 tokens per second) 10.51.726.490 I slot print_timing: id 2 | task 4714 | eval time = 415.31 ms / 2 tokens ( 415.31 ms per token, 2.41 tokens per second) 10.51.726.490 I slot print_timing: id 2 | task 4714 | total time = 2165.82 ms / 266 tokens 10.51.726.490 I slot print_timing: id 2 | task 4714 | graphs reused = 3264 10.51.726.491 I slot print_timing: id 2 | task 4714 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.726.549 I slot release: id 2 | task 4714 | stop processing: n_tokens = 2026, truncated = 0 10.51.726.723 I slot print_timing: id 3 | task 4715 | prompt eval time = 1746.74 ms / 236 tokens ( 7.40 ms per token, 135.11 tokens per second) 10.51.726.726 I slot print_timing: id 3 | task 4715 | eval time = 415.38 ms / 2 tokens ( 415.38 ms per token, 2.41 tokens per second) 10.51.726.726 I slot print_timing: id 3 | task 4715 | total time = 2162.12 ms / 238 tokens 10.51.726.727 I slot print_timing: id 3 | task 4715 | graphs reused = 3264 10.51.726.727 I slot print_timing: id 3 | task 4715 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.727.172 I slot release: id 3 | task 4715 | stop processing: n_tokens = 1998, truncated = 0 10.51.777.673 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.884 10.51.777.709 I slot launch_slot_: id 2 | task 4721 | processing task, is_child = 0 10.51.777.815 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.713 MiB) 10.52.110.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.227 MiB) 10.53.022.756 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 10.53.022.838 I slot launch_slot_: id 1 | task 4722 | processing task, is_child = 0 10.53.022.934 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1998, t_last = 391975594757 10.53.023.047 I slot launch_slot_: id 3 | task 4723 | processing task, is_child = 0 10.54.853.768 I slot print_timing: id 0 | task 4718 | prompt eval time = 466.28 ms / 149 tokens ( 3.13 ms per token, 319.55 tokens per second) 10.54.853.771 I slot print_timing: id 0 | task 4718 | eval time = 3076.10 ms / 2 tokens ( 3076.10 ms per token, 0.33 tokens per second) 10.54.853.772 I slot print_timing: id 0 | task 4718 | total time = 3542.38 ms / 151 tokens 10.54.853.772 I slot print_timing: id 0 | task 4718 | graphs reused = 3264 10.54.853.773 I slot print_timing: id 0 | task 4718 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.853.911 I slot release: id 0 | task 4718 | stop processing: n_tokens = 1911, truncated = 0 10.55.428.220 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1911, t_last = 391978721490 10.55.428.328 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.520 MiB) 10.55.429.562 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.556 MiB) 10.55.762.576 I slot launch_slot_: id 0 | task 4726 | processing task, is_child = 0 10.57.154.908 I slot print_timing: id 1 | task 4722 | prompt eval time = 2404.94 ms / 196 tokens ( 12.27 ms per token, 81.50 tokens per second) 10.57.154.916 I slot print_timing: id 1 | task 4722 | eval time = 1726.90 ms / 2 tokens ( 1726.90 ms per token, 0.58 tokens per second) 10.57.154.917 I slot print_timing: id 1 | task 4722 | total time = 4131.84 ms / 198 tokens 10.57.154.917 I slot print_timing: id 1 | task 4722 | graphs reused = 3264 10.57.154.917 I slot print_timing: id 1 | task 4722 | graph reallocs = 0 / 0 (same size) / (changed size) 10.57.156.047 I slot release: id 1 | task 4722 | stop processing: n_tokens = 1958, truncated = 0 10.57.156.359 I slot print_timing: id 2 | task 4721 | prompt eval time = 2401.38 ms / 230 tokens ( 10.44 ms per token, 95.78 tokens per second) 10.57.156.363 I slot print_timing: id 2 | task 4721 | eval time = 1728.14 ms / 2 tokens ( 1728.14 ms per token, 0.58 tokens per second) 10.57.156.364 I slot print_timing: id 2 | task 4721 | total time = 4129.52 ms / 232 tokens 10.57.156.364 I slot print_timing: id 2 | task 4721 | graphs reused = 3264 10.57.156.364 I slot print_timing: id 2 | task 4721 | graph reallocs = 0 / 0 (same size) / (changed size) 10.57.156.449 I slot release: id 2 | task 4721 | stop processing: n_tokens = 1992, truncated = 0 10.57.173.417 I slot print_timing: id 3 | task 4723 | prompt processing, n_tokens = 959, progress = 0.65, t = 4.12 s / 232.54 tokens per second 10.57.770.616 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1958, t_last = 391981023626 10.57.770.725 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.810 MiB) 10.58.387.046 I slot launch_slot_: id 1 | task 4729 | processing task, is_child = 0 10.58.387.151 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.671 MiB) 10.58.754.144 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1992, t_last = 391981024028 10.58.754.298 I slot launch_slot_: id 2 | task 4730 | processing task, is_child = 0 10.58.754.567 I slot print_timing: id 3 | task 4723 | prompt processing, n_tokens = 1275, progress = 0.86, t = 4.74 s / 268.99 tokens per second 11.01.085.517 I slot print_timing: id 0 | task 4726 | prompt processing, n_tokens = 1161, progress = 0.69, t = 5.32 s / 218.11 tokens per second 11.01.566.721 I slot print_timing: id 3 | task 4723 | prompt processing, n_tokens = 1471, progress = 1.00, t = 8.05 s / 182.62 tokens per second 11.02.804.131 I slot print_timing: id 0 | task 4726 | prompt processing, n_tokens = 1275, progress = 0.76, t = 7.04 s / 181.08 tokens per second 11.02.813.221 I slot print_timing: id 1 | task 4729 | prompt processing, n_tokens = 575, progress = 0.37, t = 4.05 s / 142.00 tokens per second 11.02.813.239 I slot print_timing: id 2 | task 4730 | prompt processing, n_tokens = 409, progress = 0.41, t = 4.05 s / 101.01 tokens per second 11.04.759.226 I slot print_timing: id 3 | task 4723 | prompt eval time = 9773.40 ms / 1475 tokens ( 6.63 ms per token, 150.92 tokens per second) 11.04.759.228 I slot print_timing: id 3 | task 4723 | eval time = 1955.10 ms / 2 tokens ( 1955.10 ms per token, 0.51 tokens per second) 11.04.759.229 I slot print_timing: id 3 | task 4723 | total time = 11728.50 ms / 1477 tokens 11.04.759.230 I slot print_timing: id 3 | task 4723 | graphs reused = 3264 11.04.759.230 I slot print_timing: id 3 | task 4723 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.760.262 I slot release: id 3 | task 4723 | stop processing: n_tokens = 1476, truncated = 0 11.04.760.292 I slot print_timing: id 0 | task 4726 | prompt processing, n_tokens = 1673, progress = 1.00, t = 9.00 s / 185.96 tokens per second 11.04.768.605 I slot print_timing: id 1 | task 4729 | prompt processing, n_tokens = 1039, progress = 0.67, t = 6.00 s / 173.03 tokens per second 11.04.775.158 I slot print_timing: id 2 | task 4730 | prompt processing, n_tokens = 483, progress = 0.48, t = 6.00 s / 80.44 tokens per second 11.06.035.403 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 391988627841 11.06.035.486 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.536 MiB) 11.06.123.656 I slot launch_slot_: id 3 | task 4735 | processing task, is_child = 0 11.06.123.684 I slot print_timing: id 1 | task 4729 | prompt processing, n_tokens = 1275, progress = 0.82, t = 7.28 s / 175.12 tokens per second 11.06.129.527 I slot print_timing: id 2 | task 4730 | prompt processing, n_tokens = 853, progress = 0.85, t = 7.28 s / 117.16 tokens per second 11.07.621.561 I slot print_timing: id 0 | task 4726 | prompt eval time = 10272.79 ms / 1677 tokens ( 6.13 ms per token, 163.25 tokens per second) 11.07.621.565 I slot print_timing: id 0 | task 4726 | eval time = 1586.16 ms / 2 tokens ( 1586.16 ms per token, 0.63 tokens per second) 11.07.621.565 I slot print_timing: id 0 | task 4726 | total time = 11858.96 ms / 1679 tokens 11.07.621.566 I slot print_timing: id 0 | task 4726 | graphs reused = 3264 11.07.621.566 I slot print_timing: id 0 | task 4726 | graph reallocs = 0 / 0 (same size) / (changed size) 11.07.623.397 I slot release: id 0 | task 4726 | stop processing: n_tokens = 1678, truncated = 0 11.07.623.437 I slot print_timing: id 1 | task 4729 | prompt processing, n_tokens = 1551, progress = 1.00, t = 8.87 s / 174.92 tokens per second 11.07.628.090 I slot print_timing: id 2 | task 4730 | prompt processing, n_tokens = 995, progress = 1.00, t = 8.87 s / 112.22 tokens per second 11.08.088.831 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1678, t_last = 391991490976 11.08.088.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.419 MiB) 11.08.183.186 I slot launch_slot_: id 0 | task 4738 | processing task, is_child = 0 11.08.974.782 I slot print_timing: id 1 | task 4729 | prompt eval time = 9334.01 ms / 1555 tokens ( 6.00 ms per token, 166.60 tokens per second) 11.08.974.784 I slot print_timing: id 1 | task 4729 | eval time = 886.44 ms / 2 tokens ( 886.44 ms per token, 1.13 tokens per second) 11.08.974.788 I slot print_timing: id 1 | task 4729 | total time = 10220.46 ms / 1557 tokens 11.08.974.788 I slot print_timing: id 1 | task 4729 | graphs reused = 3264 11.08.974.789 I slot print_timing: id 1 | task 4729 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.976.447 I slot release: id 1 | task 4729 | stop processing: n_tokens = 1556, truncated = 0 11.08.976.876 I slot print_timing: id 2 | task 4730 | prompt eval time = 9334.38 ms / 999 tokens ( 9.34 ms per token, 107.02 tokens per second) 11.08.976.880 I slot print_timing: id 2 | task 4730 | eval time = 888.04 ms / 2 tokens ( 888.04 ms per token, 1.13 tokens per second) 11.08.976.881 I slot print_timing: id 2 | task 4730 | total time = 10222.42 ms / 1001 tokens 11.08.976.881 I slot print_timing: id 2 | task 4730 | graphs reused = 3264 11.08.976.881 I slot print_timing: id 2 | task 4730 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.976.995 I slot release: id 2 | task 4730 | stop processing: n_tokens = 1000, truncated = 0 11.09.351.489 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.882 11.09.351.548 I slot launch_slot_: id 2 | task 4741 | processing task, is_child = 0 11.09.351.630 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.849 MiB) 11.10.030.541 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1556, t_last = 391992844026 11.10.030.937 I slot launch_slot_: id 1 | task 4742 | processing task, is_child = 0 11.10.041.551 I slot print_timing: id 3 | task 4735 | prompt processing, n_tokens = 853, progress = 0.86, t = 3.22 s / 265.24 tokens per second 11.11.252.490 I slot print_timing: id 0 | task 4738 | prompt processing, n_tokens = 461, progress = 0.47, t = 3.07 s / 150.20 tokens per second 11.11.437.156 I slot print_timing: id 3 | task 4735 | prompt processing, n_tokens = 985, progress = 1.00, t = 5.12 s / 192.50 tokens per second 11.12.606.378 I slot print_timing: id 0 | task 4738 | prompt processing, n_tokens = 853, progress = 0.87, t = 4.42 s / 192.87 tokens per second 11.13.181.279 I slot print_timing: id 2 | task 4741 | prompt eval time = 2574.93 ms / 107 tokens ( 24.06 ms per token, 41.55 tokens per second) 11.13.181.285 I slot print_timing: id 2 | task 4741 | eval time = 575.14 ms / 2 tokens ( 575.14 ms per token, 1.74 tokens per second) 11.13.181.285 I slot print_timing: id 2 | task 4741 | total time = 3150.06 ms / 109 tokens 11.13.181.286 I slot print_timing: id 2 | task 4741 | graphs reused = 3264 11.13.181.286 I slot print_timing: id 2 | task 4741 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.181.335 I slot release: id 2 | task 4741 | stop processing: n_tokens = 961, truncated = 0 11.13.181.544 I slot print_timing: id 3 | task 4735 | prompt eval time = 6470.79 ms / 989 tokens ( 6.54 ms per token, 152.84 tokens per second) 11.13.181.548 I slot print_timing: id 3 | task 4735 | eval time = 575.18 ms / 2 tokens ( 575.18 ms per token, 1.74 tokens per second) 11.13.181.549 I slot print_timing: id 3 | task 4735 | total time = 7045.98 ms / 991 tokens 11.13.181.549 I slot print_timing: id 3 | task 4735 | graphs reused = 3264 11.13.181.549 I slot print_timing: id 3 | task 4735 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.183.344 I slot release: id 3 | task 4735 | stop processing: n_tokens = 990, truncated = 0 11.13.183.363 I slot print_timing: id 0 | task 4738 | prompt processing, n_tokens = 973, progress = 1.00, t = 5.00 s / 194.68 tokens per second 11.13.186.476 I slot print_timing: id 1 | task 4742 | prompt processing, n_tokens = 467, progress = 0.48, t = 3.15 s / 148.25 tokens per second 11.13.933.280 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.917 11.13.933.342 I slot launch_slot_: id 2 | task 4747 | processing task, is_child = 0 11.13.933.402 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.693 MiB) 11.13.994.663 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.890 11.13.994.732 I slot launch_slot_: id 3 | task 4748 | processing task, is_child = 0 11.13.994.740 I slot print_timing: id 1 | task 4742 | prompt processing, n_tokens = 853, progress = 0.87, t = 3.90 s / 218.60 tokens per second 11.14.805.090 I slot print_timing: id 0 | task 4738 | prompt eval time = 5750.07 ms / 977 tokens ( 5.89 ms per token, 169.91 tokens per second) 11.14.805.093 I slot print_timing: id 0 | task 4738 | eval time = 871.81 ms / 2 tokens ( 871.81 ms per token, 1.15 tokens per second) 11.14.805.094 I slot print_timing: id 0 | task 4738 | total time = 6621.88 ms / 979 tokens 11.14.805.094 I slot print_timing: id 0 | task 4738 | graphs reused = 3264 11.14.805.095 I slot print_timing: id 0 | task 4738 | graph reallocs = 0 / 0 (same size) / (changed size) 11.14.805.158 I slot release: id 0 | task 4738 | stop processing: n_tokens = 978, truncated = 0 11.14.805.169 I slot print_timing: id 1 | task 4742 | prompt processing, n_tokens = 979, progress = 1.00, t = 4.77 s / 205.07 tokens per second 11.14.912.439 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 978, t_last = 391998672736 11.14.912.500 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.112 MiB) 11.14.969.558 I slot launch_slot_: id 0 | task 4751 | processing task, is_child = 0 11.15.399.072 I slot print_timing: id 1 | task 4742 | prompt eval time = 4880.90 ms / 983 tokens ( 4.97 ms per token, 201.40 tokens per second) 11.15.399.077 I slot print_timing: id 1 | task 4742 | eval time = 487.19 ms / 2 tokens ( 487.19 ms per token, 2.05 tokens per second) 11.15.399.077 I slot print_timing: id 1 | task 4742 | total time = 5368.10 ms / 985 tokens 11.15.399.078 I slot print_timing: id 1 | task 4742 | graphs reused = 3264 11.15.399.078 I slot print_timing: id 1 | task 4742 | graph reallocs = 0 / 0 (same size) / (changed size) 11.15.399.127 I slot release: id 1 | task 4742 | stop processing: n_tokens = 984, truncated = 0 11.15.399.378 I slot print_timing: id 2 | task 4747 | prompt eval time = 905.99 ms / 119 tokens ( 7.61 ms per token, 131.35 tokens per second) 11.15.399.380 I slot print_timing: id 2 | task 4747 | eval time = 487.33 ms / 2 tokens ( 487.33 ms per token, 2.05 tokens per second) 11.15.399.380 I slot print_timing: id 2 | task 4747 | total time = 1393.31 ms / 121 tokens 11.15.399.381 I slot print_timing: id 2 | task 4747 | graphs reused = 3264 11.15.399.381 I slot print_timing: id 2 | task 4747 | graph reallocs = 0 / 0 (same size) / (changed size) 11.15.399.411 I slot release: id 2 | task 4747 | stop processing: n_tokens = 973, truncated = 0 11.15.399.701 I slot print_timing: id 3 | task 4748 | prompt eval time = 903.13 ms / 123 tokens ( 7.34 ms per token, 136.19 tokens per second) 11.15.399.704 I slot print_timing: id 3 | task 4748 | eval time = 487.26 ms / 2 tokens ( 487.26 ms per token, 2.05 tokens per second) 11.15.399.704 I slot print_timing: id 3 | task 4748 | total time = 1390.39 ms / 125 tokens 11.15.399.704 I slot print_timing: id 3 | task 4748 | graphs reused = 3264 11.15.399.705 I slot print_timing: id 3 | task 4748 | graph reallocs = 0 / 0 (same size) / (changed size) 11.15.399.731 I slot release: id 3 | task 4748 | stop processing: n_tokens = 977, truncated = 0 11.15.763.474 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 984, t_last = 391999266705 11.15.763.532 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.760 MiB) 11.16.462.910 I slot launch_slot_: id 1 | task 4755 | processing task, is_child = 0 11.16.462.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.444 MiB) 11.16.503.534 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.500 MiB) 11.16.618.408 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 391999266989 11.16.618.523 I slot launch_slot_: id 2 | task 4756 | processing task, is_child = 0 11.16.618.569 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 391999267309 11.16.618.639 I slot launch_slot_: id 3 | task 4757 | processing task, is_child = 0 11.18.220.092 I slot print_timing: id 0 | task 4751 | prompt processing, n_tokens = 821, progress = 1.00, t = 3.25 s / 252.58 tokens per second 11.19.692.791 I slot print_timing: id 1 | task 4755 | prompt processing, n_tokens = 533, progress = 0.33, t = 3.06 s / 174.05 tokens per second 11.19.692.814 I slot print_timing: id 2 | task 4756 | prompt processing, n_tokens = 533, progress = 0.33, t = 3.06 s / 174.05 tokens per second 11.19.692.827 I slot print_timing: id 3 | task 4757 | prompt processing, n_tokens = 533, progress = 0.34, t = 3.06 s / 174.06 tokens per second 11.22.686.233 I slot print_timing: id 0 | task 4751 | prompt eval time = 4723.20 ms / 825 tokens ( 5.73 ms per token, 174.67 tokens per second) 11.22.686.236 I slot print_timing: id 0 | task 4751 | eval time = 2993.45 ms / 2 tokens ( 2993.45 ms per token, 0.33 tokens per second) 11.22.686.237 I slot print_timing: id 0 | task 4751 | total time = 7716.66 ms / 827 tokens 11.22.686.237 I slot print_timing: id 0 | task 4751 | graphs reused = 3264 11.22.686.238 I slot print_timing: id 0 | task 4751 | graph reallocs = 0 / 0 (same size) / (changed size) 11.22.686.275 I slot release: id 0 | task 4751 | stop processing: n_tokens = 826, truncated = 0 11.22.686.289 I slot print_timing: id 1 | task 4755 | prompt processing, n_tokens = 1113, progress = 0.68, t = 6.06 s / 183.79 tokens per second 11.22.688.774 I slot print_timing: id 2 | task 4756 | prompt processing, n_tokens = 1099, progress = 0.68, t = 6.06 s / 181.48 tokens per second 11.22.692.100 I slot print_timing: id 3 | task 4757 | prompt processing, n_tokens = 1071, progress = 0.67, t = 6.06 s / 176.86 tokens per second 11.24.228.362 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 392006553853 11.24.228.424 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 336.788 MiB) 11.24.398.625 I slot launch_slot_: id 0 | task 4762 | processing task, is_child = 0 11.24.398.733 I slot print_timing: id 1 | task 4755 | prompt processing, n_tokens = 1374, progress = 0.84, t = 7.60 s / 180.83 tokens per second 11.24.401.982 I slot print_timing: id 2 | task 4756 | prompt processing, n_tokens = 1374, progress = 0.85, t = 7.60 s / 180.83 tokens per second 11.24.404.467 I slot print_timing: id 3 | task 4757 | prompt processing, n_tokens = 1374, progress = 0.87, t = 7.60 s / 180.84 tokens per second 11.26.644.600 I slot print_timing: id 1 | task 4755 | prompt processing, n_tokens = 1625, progress = 1.00, t = 9.72 s / 167.20 tokens per second 11.26.658.462 I slot print_timing: id 2 | task 4756 | prompt processing, n_tokens = 1611, progress = 1.00, t = 9.72 s / 165.76 tokens per second 11.26.669.932 I slot print_timing: id 3 | task 4757 | prompt processing, n_tokens = 1583, progress = 1.00, t = 9.72 s / 162.88 tokens per second 11.28.321.307 I slot print_timing: id 1 | task 4755 | prompt eval time = 10562.11 ms / 1629 tokens ( 6.48 ms per token, 154.23 tokens per second) 11.28.321.312 I slot print_timing: id 1 | task 4755 | eval time = 1129.03 ms / 2 tokens ( 1129.03 ms per token, 0.89 tokens per second) 11.28.321.312 I slot print_timing: id 1 | task 4755 | total time = 11691.14 ms / 1631 tokens 11.28.321.313 I slot print_timing: id 1 | task 4755 | graphs reused = 3264 11.28.321.313 I slot print_timing: id 1 | task 4755 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.323.073 I slot release: id 1 | task 4755 | stop processing: n_tokens = 1630, truncated = 0 11.28.323.349 I slot print_timing: id 2 | task 4756 | prompt eval time = 10562.19 ms / 1615 tokens ( 6.54 ms per token, 152.90 tokens per second) 11.28.323.358 I slot print_timing: id 2 | task 4756 | eval time = 1130.91 ms / 2 tokens ( 1130.91 ms per token, 0.88 tokens per second) 11.28.323.359 I slot print_timing: id 2 | task 4756 | total time = 11693.10 ms / 1617 tokens 11.28.323.359 I slot print_timing: id 2 | task 4756 | graphs reused = 3264 11.28.323.359 I slot print_timing: id 2 | task 4756 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.323.412 I slot release: id 2 | task 4756 | stop processing: n_tokens = 1616, truncated = 0 11.28.323.686 I slot print_timing: id 3 | task 4757 | prompt eval time = 10562.30 ms / 1587 tokens ( 6.66 ms per token, 150.25 tokens per second) 11.28.323.689 I slot print_timing: id 3 | task 4757 | eval time = 1131.07 ms / 2 tokens ( 1131.07 ms per token, 0.88 tokens per second) 11.28.323.690 I slot print_timing: id 3 | task 4757 | total time = 11693.38 ms / 1589 tokens 11.28.323.690 I slot print_timing: id 3 | task 4757 | graphs reused = 3264 11.28.323.690 I slot print_timing: id 3 | task 4757 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.323.730 I slot release: id 3 | task 4757 | stop processing: n_tokens = 1588, truncated = 0 11.28.323.739 I slot print_timing: id 0 | task 4762 | prompt processing, n_tokens = 1113, progress = 0.68, t = 3.92 s / 283.75 tokens per second 11.28.330.848 I slot print_timing: id 0 | task 4762 | prompt processing, n_tokens = 1374, progress = 0.84, t = 3.93 s / 349.42 tokens per second 11.28.868.718 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 392012190653 11.28.868.797 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 336.065 MiB) 11.29.380.737 I slot launch_slot_: id 1 | task 4768 | processing task, is_child = 0 11.29.380.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.996 MiB) 11.29.430.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 354.387 MiB) 11.29.476.378 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1616, t_last = 392012190991 11.29.476.510 I slot launch_slot_: id 2 | task 4769 | processing task, is_child = 0 11.29.476.584 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.816 (> 0.100 thold), f_keep = 0.883 11.29.476.607 I slot launch_slot_: id 3 | task 4770 | processing task, is_child = 0 11.29.476.614 I slot print_timing: id 0 | task 4762 | prompt processing, n_tokens = 1625, progress = 1.00, t = 4.47 s / 363.53 tokens per second 11.31.312.289 I slot print_timing: id 0 | task 4762 | prompt eval time = 6325.95 ms / 1629 tokens ( 3.88 ms per token, 257.51 tokens per second) 11.31.312.292 I slot print_timing: id 0 | task 4762 | eval time = 587.70 ms / 2 tokens ( 587.70 ms per token, 1.70 tokens per second) 11.31.312.293 I slot print_timing: id 0 | task 4762 | total time = 6913.64 ms / 1631 tokens 11.31.312.293 I slot print_timing: id 0 | task 4762 | graphs reused = 3264 11.31.312.293 I slot print_timing: id 0 | task 4762 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.312.354 I slot release: id 0 | task 4762 | stop processing: n_tokens = 1630, truncated = 0 11.31.827.605 I slot print_timing: id 3 | task 4770 | prompt eval time = 1828.44 ms / 344 tokens ( 5.32 ms per token, 188.14 tokens per second) 11.31.827.607 I slot print_timing: id 3 | task 4770 | eval time = 515.06 ms / 2 tokens ( 515.06 ms per token, 1.94 tokens per second) 11.31.827.607 I slot print_timing: id 3 | task 4770 | total time = 2343.50 ms / 346 tokens 11.31.827.608 I slot print_timing: id 3 | task 4770 | graphs reused = 3264 11.31.827.608 I slot print_timing: id 3 | task 4770 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.827.704 I slot release: id 3 | task 4770 | stop processing: n_tokens = 1719, truncated = 0 11.31.827.712 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 392015179932 11.31.827.796 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 357.653 MiB) 11.31.869.767 I slot launch_slot_: id 0 | task 4774 | processing task, is_child = 0 11.31.869.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.566 MiB) 11.31.907.435 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1719, t_last = 392015695283 11.31.907.566 I slot launch_slot_: id 3 | task 4775 | processing task, is_child = 0 11.33.949.899 I slot print_timing: id 1 | task 4768 | prompt processing, n_tokens = 725, progress = 0.84, t = 4.30 s / 168.51 tokens per second 11.33.952.560 I slot print_timing: id 2 | task 4769 | prompt processing, n_tokens = 725, progress = 0.87, t = 4.30 s / 168.51 tokens per second 11.34.969.344 I slot print_timing: id 0 | task 4774 | prompt processing, n_tokens = 277, progress = 0.33, t = 3.06 s / 90.47 tokens per second 11.34.969.358 I slot print_timing: id 1 | task 4768 | prompt processing, n_tokens = 861, progress = 1.00, t = 5.49 s / 156.96 tokens per second 11.35.097.805 I slot print_timing: id 2 | task 4769 | prompt processing, n_tokens = 834, progress = 1.00, t = 5.49 s / 152.04 tokens per second 11.35.099.975 I slot print_timing: id 3 | task 4775 | prompt processing, n_tokens = 277, progress = 0.32, t = 3.06 s / 90.59 tokens per second 11.35.624.427 I slot print_timing: id 0 | task 4774 | prompt processing, n_tokens = 326, progress = 0.39, t = 3.72 s / 87.72 tokens per second 11.35.627.925 I slot print_timing: id 3 | task 4775 | prompt processing, n_tokens = 343, progress = 0.40, t = 3.71 s / 92.39 tokens per second 11.37.022.771 I slot print_timing: id 1 | task 4768 | prompt eval time = 6140.27 ms / 865 tokens ( 7.10 ms per token, 140.87 tokens per second) 11.37.022.773 I slot print_timing: id 1 | task 4768 | eval time = 1398.59 ms / 2 tokens ( 1398.59 ms per token, 0.72 tokens per second) 11.37.022.774 I slot print_timing: id 1 | task 4768 | total time = 7538.87 ms / 867 tokens 11.37.022.774 I slot print_timing: id 1 | task 4768 | graphs reused = 3264 11.37.022.775 I slot print_timing: id 1 | task 4768 | graph reallocs = 0 / 0 (same size) / (changed size) 11.37.022.838 I slot release: id 1 | task 4768 | stop processing: n_tokens = 866, truncated = 0 11.37.023.064 I slot print_timing: id 2 | task 4769 | prompt eval time = 6140.41 ms / 838 tokens ( 7.33 ms per token, 136.47 tokens per second) 11.37.023.067 I slot print_timing: id 2 | task 4769 | eval time = 1398.65 ms / 2 tokens ( 1398.65 ms per token, 0.71 tokens per second) 11.37.023.067 I slot print_timing: id 2 | task 4769 | total time = 7539.06 ms / 840 tokens 11.37.023.067 I slot print_timing: id 2 | task 4769 | graphs reused = 3264 11.37.023.068 I slot print_timing: id 2 | task 4769 | graph reallocs = 0 / 0 (same size) / (changed size) 11.37.023.091 I slot release: id 2 | task 4769 | stop processing: n_tokens = 839, truncated = 0 11.37.023.100 I slot print_timing: id 0 | task 4774 | prompt processing, n_tokens = 716, progress = 0.85, t = 5.11 s / 139.98 tokens per second 11.37.037.998 I slot print_timing: id 3 | task 4775 | prompt processing, n_tokens = 716, progress = 0.83, t = 5.11 s / 140.09 tokens per second 11.37.364.071 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 866, t_last = 392020890416 11.37.364.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 352.666 MiB) 11.37.714.799 I slot launch_slot_: id 1 | task 4781 | processing task, is_child = 0 11.37.714.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 354.465 MiB) 11.37.764.210 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 839, t_last = 392020890669 11.37.764.315 I slot launch_slot_: id 2 | task 4782 | processing task, is_child = 0 11.37.764.323 I slot print_timing: id 0 | task 4774 | prompt processing, n_tokens = 838, progress = 1.00, t = 5.46 s / 153.58 tokens per second 11.37.775.628 I slot print_timing: id 3 | task 4775 | prompt processing, n_tokens = 855, progress = 1.00, t = 5.45 s / 156.81 tokens per second 11.39.158.332 I slot print_timing: id 0 | task 4774 | prompt eval time = 6624.48 ms / 842 tokens ( 7.87 ms per token, 127.10 tokens per second) 11.39.158.335 I slot print_timing: id 0 | task 4774 | eval time = 626.27 ms / 2 tokens ( 626.27 ms per token, 1.60 tokens per second) 11.39.158.335 I slot print_timing: id 0 | task 4774 | total time = 7250.76 ms / 844 tokens 11.39.158.336 I slot print_timing: id 0 | task 4774 | graphs reused = 3264 11.39.158.336 I slot print_timing: id 0 | task 4774 | graph reallocs = 0 / 0 (same size) / (changed size) 11.39.158.393 I slot release: id 0 | task 4774 | stop processing: n_tokens = 843, truncated = 0 11.39.158.594 I slot print_timing: id 3 | task 4775 | prompt eval time = 6620.84 ms / 859 tokens ( 7.71 ms per token, 129.74 tokens per second) 11.39.158.598 I slot print_timing: id 3 | task 4775 | eval time = 626.30 ms / 2 tokens ( 626.30 ms per token, 1.60 tokens per second) 11.39.158.598 I slot print_timing: id 3 | task 4775 | total time = 7247.14 ms / 861 tokens 11.39.158.599 I slot print_timing: id 3 | task 4775 | graphs reused = 3264 11.39.158.599 I slot print_timing: id 3 | task 4775 | graph reallocs = 0 / 0 (same size) / (changed size) 11.39.158.628 I slot release: id 3 | task 4775 | stop processing: n_tokens = 860, truncated = 0 11.39.222.479 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 392023025971 11.39.222.537 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 355.423 MiB) 11.39.484.486 I slot launch_slot_: id 0 | task 4786 | processing task, is_child = 0 11.39.484.543 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 352.627 MiB) 11.39.530.006 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 392023026206 11.39.530.113 I slot launch_slot_: id 3 | task 4787 | processing task, is_child = 0 11.41.401.668 I slot print_timing: id 1 | task 4781 | prompt processing, n_tokens = 628, progress = 0.81, t = 3.50 s / 179.31 tokens per second 11.41.404.534 I slot print_timing: id 2 | task 4782 | prompt processing, n_tokens = 716, progress = 0.81, t = 3.50 s / 204.44 tokens per second 11.42.549.945 I slot print_timing: id 0 | task 4786 | prompt processing, n_tokens = 175, progress = 0.25, t = 3.02 s / 57.95 tokens per second 11.42.674.455 I slot print_timing: id 1 | task 4781 | prompt processing, n_tokens = 776, progress = 0.99, t = 4.77 s / 162.53 tokens per second 11.42.677.979 I slot print_timing: id 2 | task 4782 | prompt processing, n_tokens = 882, progress = 1.00, t = 4.77 s / 184.74 tokens per second 11.42.679.914 I slot print_timing: id 3 | task 4787 | prompt processing, n_tokens = 233, progress = 0.31, t = 3.02 s / 77.25 tokens per second 11.44.180.449 I slot print_timing: id 0 | task 4786 | prompt processing, n_tokens = 571, progress = 0.83, t = 4.65 s / 122.80 tokens per second 11.44.195.205 I slot print_timing: id 3 | task 4787 | prompt processing, n_tokens = 628, progress = 0.84, t = 4.65 s / 135.17 tokens per second 11.44.876.926 I slot print_timing: id 1 | task 4781 | prompt eval time = 6404.70 ms / 780 tokens ( 8.21 ms per token, 121.79 tokens per second) 11.44.876.928 I slot print_timing: id 1 | task 4781 | eval time = 696.72 ms / 2 tokens ( 696.72 ms per token, 1.44 tokens per second) 11.44.876.929 I slot print_timing: id 1 | task 4781 | total time = 7101.42 ms / 782 tokens 11.44.876.929 I slot print_timing: id 1 | task 4781 | graphs reused = 3264 11.44.876.929 I slot print_timing: id 1 | task 4781 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.878.613 I slot release: id 1 | task 4781 | stop processing: n_tokens = 781, truncated = 0 11.44.879.063 I slot print_timing: id 2 | task 4782 | prompt eval time = 6404.86 ms / 886 tokens ( 7.23 ms per token, 138.33 tokens per second) 11.44.879.066 I slot print_timing: id 2 | task 4782 | eval time = 698.62 ms / 2 tokens ( 698.62 ms per token, 1.43 tokens per second) 11.44.879.066 I slot print_timing: id 2 | task 4782 | total time = 7103.49 ms / 888 tokens 11.44.879.067 I slot print_timing: id 2 | task 4782 | graphs reused = 3264 11.44.879.067 I slot print_timing: id 2 | task 4782 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.879.118 I slot release: id 2 | task 4782 | stop processing: n_tokens = 887, truncated = 0 11.44.879.133 I slot print_timing: id 0 | task 4786 | prompt processing, n_tokens = 687, progress = 0.99, t = 5.35 s / 128.49 tokens per second 11.44.882.552 I slot print_timing: id 3 | task 4787 | prompt processing, n_tokens = 745, progress = 0.99, t = 5.34 s / 139.44 tokens per second 11.44.970.055 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 781, t_last = 392028746192 11.45.921.536 I slot launch_slot_: id 1 | task 4793 | processing task, is_child = 0 11.45.921.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.839 MiB) 11.46.026.215 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 392028746696 11.46.026.355 I slot launch_slot_: id 2 | task 4794 | processing task, is_child = 0 11.46.521.418 I slot print_timing: id 0 | task 4786 | prompt eval time = 5439.77 ms / 691 tokens ( 7.87 ms per token, 127.03 tokens per second) 11.46.521.423 I slot print_timing: id 0 | task 4786 | eval time = 1551.52 ms / 2 tokens ( 1551.52 ms per token, 0.64 tokens per second) 11.46.521.424 I slot print_timing: id 0 | task 4786 | total time = 6991.29 ms / 693 tokens 11.46.521.424 I slot print_timing: id 0 | task 4786 | graphs reused = 3264 11.46.521.425 I slot print_timing: id 0 | task 4786 | graph reallocs = 0 / 0 (same size) / (changed size) 11.46.523.760 I slot release: id 0 | task 4786 | stop processing: n_tokens = 692, truncated = 0 11.46.524.765 I slot print_timing: id 3 | task 4787 | prompt eval time = 5436.12 ms / 749 tokens ( 7.26 ms per token, 137.78 tokens per second) 11.46.524.768 I slot print_timing: id 3 | task 4787 | eval time = 1554.70 ms / 2 tokens ( 1554.70 ms per token, 0.64 tokens per second) 11.46.524.769 I slot print_timing: id 3 | task 4787 | total time = 6990.82 ms / 751 tokens 11.46.524.769 I slot print_timing: id 3 | task 4787 | graphs reused = 3264 11.46.524.770 I slot print_timing: id 3 | task 4787 | graph reallocs = 0 / 0 (same size) / (changed size) 11.46.524.873 I slot release: id 3 | task 4787 | stop processing: n_tokens = 750, truncated = 0 11.49.204.097 I slot print_timing: id 1 | task 4793 | prompt eval time = 3142.29 ms / 678 tokens ( 4.63 ms per token, 215.77 tokens per second) 11.49.204.100 I slot print_timing: id 1 | task 4793 | eval time = 35.44 ms / 2 tokens ( 35.44 ms per token, 28.22 tokens per second) 11.49.204.100 I slot print_timing: id 1 | task 4793 | total time = 3177.73 ms / 680 tokens 11.49.204.101 I slot print_timing: id 1 | task 4793 | graphs reused = 3264 11.49.204.101 I slot print_timing: id 1 | task 4793 | graph reallocs = 0 / 0 (same size) / (changed size) 11.49.204.142 I slot release: id 1 | task 4793 | stop processing: n_tokens = 679, truncated = 0 11.49.204.279 I slot print_timing: id 2 | task 4794 | prompt eval time = 3142.63 ms / 712 tokens ( 4.41 ms per token, 226.56 tokens per second) 11.49.204.280 I slot print_timing: id 2 | task 4794 | eval time = 35.21 ms / 2 tokens ( 35.21 ms per token, 28.40 tokens per second) 11.49.204.281 I slot print_timing: id 2 | task 4794 | total time = 3177.84 ms / 714 tokens 11.49.204.281 I slot print_timing: id 2 | task 4794 | graphs reused = 3264 11.49.204.281 I slot print_timing: id 2 | task 4794 | graph reallocs = 0 / 0 (same size) / (changed size) 11.49.204.315 I slot release: id 2 | task 4794 | stop processing: n_tokens = 713, truncated = 0 11.53.419.259 I srv operator(): operator(): cleaning up before exit...