/Users/minipro/quantdiff/work/llama-b11869/src/build/bin/llama-server -m /Users/minipro/quantdiff/models/campaign/a64fe0bbf936/Sage-A1.5-Q4_K_M.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.154.832 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.154.889 I srv llama_server: initializing ... 0.00.154.895 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.154.980 I srv init_listene: The UI is disabled 0.00.154.981 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.155.023 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) 0.00.156.648 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/a64fe0bbf936/Sage-A1.5-Q4_K_M.gguf' 0.00.460.849 W model has unused tensor blk.40.attn_norm.weight (size = 8192 bytes) -- ignoring 0.00.460.859 W model has unused tensor blk.40.post_attention_norm.weight (size = 8192 bytes) -- ignoring 0.00.460.865 W model has unused tensor blk.40.attn_q.weight (size = 9437184 bytes) -- ignoring 0.00.460.868 W model has unused tensor blk.40.attn_k.weight (size = 589824 bytes) -- ignoring 0.00.460.870 W model has unused tensor blk.40.attn_v.weight (size = 860160 bytes) -- ignoring 0.00.460.878 W model has unused tensor blk.40.attn_output.weight (size = 4718592 bytes) -- ignoring 0.00.460.880 W model has unused tensor blk.40.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.460.882 W model has unused tensor blk.40.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.460.884 W model has unused tensor blk.40.ffn_gate_inp.weight (size = 2097152 bytes) -- ignoring 0.00.460.886 W model has unused tensor blk.40.ffn_down_exps.weight (size = 220200960 bytes) -- ignoring 0.00.460.891 W model has unused tensor blk.40.ffn_gate_exps.weight (size = 150994944 bytes) -- ignoring 0.00.460.893 W model has unused tensor blk.40.ffn_up_exps.weight (size = 150994944 bytes) -- ignoring 0.00.460.895 W model has unused tensor blk.40.ffn_gate_inp_shexp.weight (size = 8192 bytes) -- ignoring 0.00.460.898 W model has unused tensor blk.40.ffn_gate_shexp.weight (size = 589824 bytes) -- ignoring 0.00.460.900 W model has unused tensor blk.40.ffn_up_shexp.weight (size = 589824 bytes) -- ignoring 0.00.460.902 W model has unused tensor blk.40.ffn_down_shexp.weight (size = 860160 bytes) -- ignoring 0.00.460.905 W model has unused tensor blk.40.nextn.eh_proj.weight (size = 4718592 bytes) -- ignoring 0.00.460.908 W model has unused tensor blk.40.nextn.enorm.weight (size = 8192 bytes) -- ignoring 0.00.460.910 W model has unused tensor blk.40.nextn.hnorm.weight (size = 8192 bytes) -- ignoring 0.00.460.917 W model has unused tensor blk.40.nextn.shared_head_norm.weight (size = 8192 bytes) -- ignoring 0.01.535.169 I cmn init: llama threadpool init, n_threads = 8 0.01.633.020 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.01.637.626 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.637.641 I srv server_run_i: model loaded 0.01.637.642 I srv server_on_li: listening on http://127.0.0.1:8091 0.48.065.274 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.48.065.303 I slot launch_slot_: id 0 | task 1 | processing task, is_child = 0 0.48.065.305 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.48.065.321 I slot launch_slot_: id 1 | task 0 | processing task, is_child = 0 0.48.065.322 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.48.065.338 I slot launch_slot_: id 2 | task 2 | processing task, is_child = 0 0.48.957.134 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.48.957.215 I slot launch_slot_: id 3 | task 4 | processing task, is_child = 0 0.49.540.804 I slot print_timing: id 0 | task 1 | prompt eval time = 1369.47 ms / 115 tokens ( 11.91 ms per token, 83.97 tokens per second) 0.49.540.810 I slot print_timing: id 0 | task 1 | eval time = 105.98 ms / 2 tokens ( 105.98 ms per token, 9.44 tokens per second) 0.49.540.811 I slot print_timing: id 0 | task 1 | total time = 1475.45 ms / 117 tokens 0.49.540.812 I slot print_timing: id 0 | task 1 | graphs reused = 1 0.49.540.812 I slot print_timing: id 0 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.540.839 I slot release: id 0 | task 1 | stop processing: n_tokens = 116, truncated = 0 0.49.541.130 I slot print_timing: id 1 | task 0 | prompt eval time = 1370.88 ms / 122 tokens ( 11.24 ms per token, 88.99 tokens per second) 0.49.541.134 I slot print_timing: id 1 | task 0 | eval time = 104.90 ms / 2 tokens ( 104.90 ms per token, 9.53 tokens per second) 0.49.541.135 I slot print_timing: id 1 | task 0 | total time = 1475.78 ms / 124 tokens 0.49.541.135 I slot print_timing: id 1 | task 0 | graphs reused = 1 0.49.541.136 I slot print_timing: id 1 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.541.155 I slot release: id 1 | task 0 | stop processing: n_tokens = 123, truncated = 0 0.49.541.464 I slot print_timing: id 2 | task 2 | prompt eval time = 1371.93 ms / 130 tokens ( 10.55 ms per token, 94.76 tokens per second) 0.49.541.469 I slot print_timing: id 2 | task 2 | eval time = 104.17 ms / 2 tokens ( 104.17 ms per token, 9.60 tokens per second) 0.49.541.469 I slot print_timing: id 2 | task 2 | total time = 1476.11 ms / 132 tokens 0.49.541.470 I slot print_timing: id 2 | task 2 | graphs reused = 1 0.49.541.470 I slot print_timing: id 2 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.541.489 I slot release: id 2 | task 2 | stop processing: n_tokens = 131, truncated = 0 0.49.567.629 I slot print_timing: id 3 | task 4 | prompt eval time = 519.45 ms / 115 tokens ( 4.52 ms per token, 221.39 tokens per second) 0.49.567.633 I slot print_timing: id 3 | task 4 | eval time = 25.32 ms / 2 tokens ( 25.32 ms per token, 39.49 tokens per second) 0.49.567.634 I slot print_timing: id 3 | task 4 | total time = 544.78 ms / 117 tokens 0.49.567.635 I slot print_timing: id 3 | task 4 | graphs reused = 1 0.49.567.635 I slot print_timing: id 3 | task 4 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.567.658 I slot release: id 3 | task 4 | stop processing: n_tokens = 116, truncated = 0 0.49.567.664 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.241 0.49.582.729 I slot launch_slot_: id 0 | task 8 | processing task, is_child = 0 0.49.619.843 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.236 0.49.619.935 I slot launch_slot_: id 1 | task 9 | processing task, is_child = 0 0.49.619.980 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.214 0.49.620.024 I slot launch_slot_: id 2 | task 10 | processing task, is_child = 0 0.49.620.044 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.250 0.49.620.084 I slot launch_slot_: id 3 | task 11 | processing task, is_child = 0 0.51.119.190 I slot print_timing: id 0 | task 8 | prompt eval time = 1443.78 ms / 200 tokens ( 7.22 ms per token, 138.53 tokens per second) 0.51.119.195 I slot print_timing: id 0 | task 8 | eval time = 55.31 ms / 2 tokens ( 55.31 ms per token, 18.08 tokens per second) 0.51.119.196 I slot print_timing: id 0 | task 8 | total time = 1499.09 ms / 202 tokens 0.51.119.196 I slot print_timing: id 0 | task 8 | graphs reused = 1 0.51.119.197 I slot print_timing: id 0 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.119.228 I slot release: id 0 | task 8 | stop processing: n_tokens = 201, truncated = 0 0.51.119.535 I slot print_timing: id 1 | task 9 | prompt eval time = 1444.18 ms / 152 tokens ( 9.50 ms per token, 105.25 tokens per second) 0.51.119.539 I slot print_timing: id 1 | task 9 | eval time = 55.23 ms / 2 tokens ( 55.23 ms per token, 18.11 tokens per second) 0.51.119.539 I slot print_timing: id 1 | task 9 | total time = 1499.41 ms / 154 tokens 0.51.119.540 I slot print_timing: id 1 | task 9 | graphs reused = 1 0.51.119.541 I slot print_timing: id 1 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.119.564 I slot release: id 1 | task 9 | stop processing: n_tokens = 153, truncated = 0 0.51.119.863 I slot print_timing: id 2 | task 10 | prompt eval time = 1444.60 ms / 160 tokens ( 9.03 ms per token, 110.76 tokens per second) 0.51.119.866 I slot print_timing: id 2 | task 10 | eval time = 55.13 ms / 2 tokens ( 55.13 ms per token, 18.14 tokens per second) 0.51.119.867 I slot print_timing: id 2 | task 10 | total time = 1499.73 ms / 162 tokens 0.51.119.867 I slot print_timing: id 2 | task 10 | graphs reused = 1 0.51.119.868 I slot print_timing: id 2 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.119.885 I slot release: id 2 | task 10 | stop processing: n_tokens = 161, truncated = 0 0.51.120.179 I slot print_timing: id 3 | task 11 | prompt eval time = 1445.00 ms / 108 tokens ( 13.38 ms per token, 74.74 tokens per second) 0.51.120.183 I slot print_timing: id 3 | task 11 | eval time = 55.03 ms / 2 tokens ( 55.03 ms per token, 18.17 tokens per second) 0.51.120.184 I slot print_timing: id 3 | task 11 | total time = 1500.03 ms / 110 tokens 0.51.120.184 I slot print_timing: id 3 | task 11 | graphs reused = 1 0.51.120.185 I slot print_timing: id 3 | task 11 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.120.201 I slot release: id 3 | task 11 | stop processing: n_tokens = 109, truncated = 0 0.51.128.090 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.139 0.51.142.240 I slot launch_slot_: id 0 | task 15 | processing task, is_child = 0 0.51.181.805 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.190 0.51.181.900 I slot launch_slot_: id 1 | task 16 | processing task, is_child = 0 0.51.181.943 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.174 0.51.181.988 I slot launch_slot_: id 2 | task 17 | processing task, is_child = 0 0.51.182.009 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.257 0.51.182.046 I slot launch_slot_: id 3 | task 18 | processing task, is_child = 0 0.52.427.255 I slot print_timing: id 0 | task 15 | prompt eval time = 1190.27 ms / 117 tokens ( 10.17 ms per token, 98.30 tokens per second) 0.52.427.260 I slot print_timing: id 0 | task 15 | eval time = 54.92 ms / 2 tokens ( 54.92 ms per token, 18.21 tokens per second) 0.52.427.261 I slot print_timing: id 0 | task 15 | total time = 1245.19 ms / 119 tokens 0.52.427.262 I slot print_timing: id 0 | task 15 | graphs reused = 1 0.52.427.263 I slot print_timing: id 0 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.427.292 I slot release: id 0 | task 15 | stop processing: n_tokens = 118, truncated = 0 0.52.427.598 I slot print_timing: id 1 | task 16 | prompt eval time = 1190.64 ms / 118 tokens ( 10.09 ms per token, 99.11 tokens per second) 0.52.427.601 I slot print_timing: id 1 | task 16 | eval time = 54.88 ms / 2 tokens ( 54.88 ms per token, 18.22 tokens per second) 0.52.427.602 I slot print_timing: id 1 | task 16 | total time = 1245.52 ms / 120 tokens 0.52.427.603 I slot print_timing: id 1 | task 16 | graphs reused = 1 0.52.427.603 I slot print_timing: id 1 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.427.623 I slot release: id 1 | task 16 | stop processing: n_tokens = 119, truncated = 0 0.52.427.921 I slot print_timing: id 2 | task 17 | prompt eval time = 1191.02 ms / 125 tokens ( 9.53 ms per token, 104.95 tokens per second) 0.52.427.925 I slot print_timing: id 2 | task 17 | eval time = 54.81 ms / 2 tokens ( 54.81 ms per token, 18.25 tokens per second) 0.52.427.925 I slot print_timing: id 2 | task 17 | total time = 1245.83 ms / 127 tokens 0.52.427.926 I slot print_timing: id 2 | task 17 | graphs reused = 1 0.52.427.926 I slot print_timing: id 2 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.427.942 I slot release: id 2 | task 17 | stop processing: n_tokens = 126, truncated = 0 0.52.428.287 I slot print_timing: id 3 | task 18 | prompt eval time = 1191.42 ms / 150 tokens ( 7.94 ms per token, 125.90 tokens per second) 0.52.428.292 I slot print_timing: id 3 | task 18 | eval time = 54.76 ms / 2 tokens ( 54.76 ms per token, 18.26 tokens per second) 0.52.428.293 I slot print_timing: id 3 | task 18 | total time = 1246.18 ms / 152 tokens 0.52.428.293 I slot print_timing: id 3 | task 18 | graphs reused = 1 0.52.428.294 I slot print_timing: id 3 | task 18 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.428.315 I slot release: id 3 | task 18 | stop processing: n_tokens = 151, truncated = 0 0.52.436.680 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.237 0.52.451.509 I slot launch_slot_: id 0 | task 22 | processing task, is_child = 0 0.52.490.709 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.235 (> 0.100 thold), f_keep = 0.235 0.52.490.803 I slot launch_slot_: id 1 | task 23 | processing task, is_child = 0 0.52.490.844 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.222 0.52.490.883 I slot launch_slot_: id 2 | task 24 | processing task, is_child = 0 0.52.490.903 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.185 0.52.490.948 I slot launch_slot_: id 3 | task 25 | processing task, is_child = 0 0.53.979.794 I slot print_timing: id 0 | task 22 | prompt eval time = 1433.47 ms / 143 tokens ( 10.02 ms per token, 99.76 tokens per second) 0.53.979.799 I slot print_timing: id 0 | task 22 | eval time = 55.36 ms / 2 tokens ( 55.36 ms per token, 18.06 tokens per second) 0.53.979.800 I slot print_timing: id 0 | task 22 | total time = 1488.83 ms / 145 tokens 0.53.979.800 I slot print_timing: id 0 | task 22 | graphs reused = 1 0.53.979.801 I slot print_timing: id 0 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.979.828 I slot release: id 0 | task 22 | stop processing: n_tokens = 144, truncated = 0 0.53.980.114 I slot print_timing: id 1 | task 23 | prompt eval time = 1433.85 ms / 119 tokens ( 12.05 ms per token, 82.99 tokens per second) 0.53.980.118 I slot print_timing: id 1 | task 23 | eval time = 55.28 ms / 2 tokens ( 55.28 ms per token, 18.09 tokens per second) 0.53.980.118 I slot print_timing: id 1 | task 23 | total time = 1489.13 ms / 121 tokens 0.53.980.119 I slot print_timing: id 1 | task 23 | graphs reused = 1 0.53.980.120 I slot print_timing: id 1 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.980.139 I slot release: id 1 | task 23 | stop processing: n_tokens = 120, truncated = 0 0.53.980.445 I slot print_timing: id 2 | task 24 | prompt eval time = 1434.26 ms / 181 tokens ( 7.92 ms per token, 126.20 tokens per second) 0.53.980.451 I slot print_timing: id 2 | task 24 | eval time = 55.19 ms / 2 tokens ( 55.19 ms per token, 18.12 tokens per second) 0.53.980.452 I slot print_timing: id 2 | task 24 | total time = 1489.45 ms / 183 tokens 0.53.980.452 I slot print_timing: id 2 | task 24 | graphs reused = 1 0.53.980.453 I slot print_timing: id 2 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.980.470 I slot release: id 2 | task 24 | stop processing: n_tokens = 182, truncated = 0 0.53.980.774 I slot print_timing: id 3 | task 25 | prompt eval time = 1434.65 ms / 136 tokens ( 10.55 ms per token, 94.80 tokens per second) 0.53.980.780 I slot print_timing: id 3 | task 25 | eval time = 55.11 ms / 2 tokens ( 55.11 ms per token, 18.14 tokens per second) 0.53.980.781 I slot print_timing: id 3 | task 25 | total time = 1489.76 ms / 138 tokens 0.53.980.781 I slot print_timing: id 3 | task 25 | graphs reused = 1 0.53.980.782 I slot print_timing: id 3 | task 25 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.980.797 I slot release: id 3 | task 25 | stop processing: n_tokens = 137, truncated = 0 0.53.989.479 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.194 0.54.005.676 I slot launch_slot_: id 0 | task 29 | processing task, is_child = 0 0.54.039.029 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.233 0.54.039.123 I slot launch_slot_: id 1 | task 30 | processing task, is_child = 0 0.54.039.170 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.154 0.54.041.478 I slot launch_slot_: id 2 | task 31 | processing task, is_child = 0 0.54.041.501 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.204 0.54.041.542 I slot launch_slot_: id 3 | task 32 | processing task, is_child = 0 0.55.463.456 I slot print_timing: id 0 | task 29 | prompt eval time = 1366.32 ms / 122 tokens ( 11.20 ms per token, 89.29 tokens per second) 0.55.463.461 I slot print_timing: id 0 | task 29 | eval time = 55.58 ms / 2 tokens ( 55.58 ms per token, 17.99 tokens per second) 0.55.463.463 I slot print_timing: id 0 | task 29 | total time = 1421.90 ms / 124 tokens 0.55.463.463 I slot print_timing: id 0 | task 29 | graphs reused = 1 0.55.463.464 I slot print_timing: id 0 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.463.498 I slot release: id 0 | task 29 | stop processing: n_tokens = 123, truncated = 0 0.55.463.787 I slot print_timing: id 1 | task 30 | prompt eval time = 1366.81 ms / 178 tokens ( 7.68 ms per token, 130.23 tokens per second) 0.55.463.792 I slot print_timing: id 1 | task 30 | eval time = 55.41 ms / 2 tokens ( 55.41 ms per token, 18.05 tokens per second) 0.55.463.793 I slot print_timing: id 1 | task 30 | total time = 1422.22 ms / 180 tokens 0.55.463.793 I slot print_timing: id 1 | task 30 | graphs reused = 1 0.55.463.794 I slot print_timing: id 1 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.463.819 I slot release: id 1 | task 30 | stop processing: n_tokens = 179, truncated = 0 0.55.464.128 I slot print_timing: id 2 | task 31 | prompt eval time = 1367.32 ms / 131 tokens ( 10.44 ms per token, 95.81 tokens per second) 0.55.464.134 I slot print_timing: id 2 | task 31 | eval time = 55.23 ms / 2 tokens ( 55.23 ms per token, 18.11 tokens per second) 0.55.464.135 I slot print_timing: id 2 | task 31 | total time = 1422.55 ms / 133 tokens 0.55.464.136 I slot print_timing: id 2 | task 31 | graphs reused = 1 0.55.464.136 I slot print_timing: id 2 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.464.158 I slot release: id 2 | task 31 | stop processing: n_tokens = 132, truncated = 0 0.55.464.461 I slot print_timing: id 3 | task 32 | prompt eval time = 1367.81 ms / 144 tokens ( 9.50 ms per token, 105.28 tokens per second) 0.55.464.465 I slot print_timing: id 3 | task 32 | eval time = 55.06 ms / 2 tokens ( 55.06 ms per token, 18.16 tokens per second) 0.55.464.467 I slot print_timing: id 3 | task 32 | total time = 1422.87 ms / 146 tokens 0.55.464.467 I slot print_timing: id 3 | task 32 | graphs reused = 1 0.55.464.468 I slot print_timing: id 3 | task 32 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.464.483 I slot release: id 3 | task 32 | stop processing: n_tokens = 145, truncated = 0 0.55.473.029 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.228 0.55.483.920 I slot launch_slot_: id 0 | task 36 | processing task, is_child = 0 0.55.521.742 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.220 0.55.521.806 I slot launch_slot_: id 2 | task 37 | processing task, is_child = 0 0.55.521.851 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.162 0.55.521.891 I slot launch_slot_: id 1 | task 38 | processing task, is_child = 0 0.55.521.913 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.193 0.55.521.953 I slot launch_slot_: id 3 | task 39 | processing task, is_child = 0 0.56.872.315 I slot print_timing: id 0 | task 36 | prompt eval time = 1294.50 ms / 113 tokens ( 11.46 ms per token, 87.29 tokens per second) 0.56.872.320 I slot print_timing: id 0 | task 36 | eval time = 55.84 ms / 2 tokens ( 55.84 ms per token, 17.91 tokens per second) 0.56.872.321 I slot print_timing: id 0 | task 36 | total time = 1350.35 ms / 115 tokens 0.56.872.322 I slot print_timing: id 0 | task 36 | graphs reused = 1 0.56.872.323 I slot print_timing: id 0 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.872.358 I slot release: id 0 | task 36 | stop processing: n_tokens = 114, truncated = 0 0.56.872.650 I slot print_timing: id 1 | task 38 | prompt eval time = 1295.08 ms / 144 tokens ( 8.99 ms per token, 111.19 tokens per second) 0.56.872.653 I slot print_timing: id 1 | task 38 | eval time = 55.59 ms / 2 tokens ( 55.59 ms per token, 17.99 tokens per second) 0.56.872.654 I slot print_timing: id 1 | task 38 | total time = 1350.67 ms / 146 tokens 0.56.872.655 I slot print_timing: id 1 | task 38 | graphs reused = 1 0.56.872.656 I slot print_timing: id 1 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.872.675 I slot release: id 1 | task 38 | stop processing: n_tokens = 145, truncated = 0 0.56.872.969 I slot print_timing: id 2 | task 37 | prompt eval time = 1295.75 ms / 120 tokens ( 10.80 ms per token, 92.61 tokens per second) 0.56.872.972 I slot print_timing: id 2 | task 37 | eval time = 55.22 ms / 2 tokens ( 55.22 ms per token, 18.11 tokens per second) 0.56.872.973 I slot print_timing: id 2 | task 37 | total time = 1350.97 ms / 122 tokens 0.56.872.973 I slot print_timing: id 2 | task 37 | graphs reused = 1 0.56.872.974 I slot print_timing: id 2 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.872.994 I slot release: id 2 | task 37 | stop processing: n_tokens = 121, truncated = 0 0.56.873.278 I slot print_timing: id 3 | task 39 | prompt eval time = 1296.37 ms / 142 tokens ( 9.13 ms per token, 109.54 tokens per second) 0.56.873.281 I slot print_timing: id 3 | task 39 | eval time = 54.90 ms / 2 tokens ( 54.90 ms per token, 18.22 tokens per second) 0.56.873.282 I slot print_timing: id 3 | task 39 | total time = 1351.27 ms / 144 tokens 0.56.873.283 I slot print_timing: id 3 | task 39 | graphs reused = 1 0.56.873.283 I slot print_timing: id 3 | task 39 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.873.300 I slot release: id 3 | task 39 | stop processing: n_tokens = 143, truncated = 0 0.56.880.939 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.240 0.56.896.709 I slot launch_slot_: id 2 | task 43 | processing task, is_child = 0 0.56.939.088 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.246 0.56.939.174 I slot launch_slot_: id 0 | task 44 | processing task, is_child = 0 0.56.939.216 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.193 0.56.939.257 I slot launch_slot_: id 1 | task 45 | processing task, is_child = 0 0.56.939.277 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.196 0.56.939.320 I slot launch_slot_: id 3 | task 46 | processing task, is_child = 0 0.58.176.633 I slot print_timing: id 0 | task 44 | prompt eval time = 1182.39 ms / 109 tokens ( 10.85 ms per token, 92.19 tokens per second) 0.58.176.638 I slot print_timing: id 0 | task 44 | eval time = 54.91 ms / 2 tokens ( 54.91 ms per token, 18.21 tokens per second) 0.58.176.639 I slot print_timing: id 0 | task 44 | total time = 1237.30 ms / 111 tokens 0.58.176.640 I slot print_timing: id 0 | task 44 | graphs reused = 1 0.58.176.641 I slot print_timing: id 0 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.176.669 I slot release: id 0 | task 44 | stop processing: n_tokens = 110, truncated = 0 0.58.176.959 I slot print_timing: id 1 | task 45 | prompt eval time = 1182.75 ms / 123 tokens ( 9.62 ms per token, 103.99 tokens per second) 0.58.176.962 I slot print_timing: id 1 | task 45 | eval time = 54.85 ms / 2 tokens ( 54.85 ms per token, 18.23 tokens per second) 0.58.176.963 I slot print_timing: id 1 | task 45 | total time = 1237.60 ms / 125 tokens 0.58.176.964 I slot print_timing: id 1 | task 45 | graphs reused = 1 0.58.176.965 I slot print_timing: id 1 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.176.984 I slot release: id 1 | task 45 | stop processing: n_tokens = 124, truncated = 0 0.58.177.277 I slot print_timing: id 2 | task 43 | prompt eval time = 1183.13 ms / 112 tokens ( 10.56 ms per token, 94.66 tokens per second) 0.58.177.280 I slot print_timing: id 2 | task 43 | eval time = 54.78 ms / 2 tokens ( 54.78 ms per token, 18.26 tokens per second) 0.58.177.281 I slot print_timing: id 2 | task 43 | total time = 1237.91 ms / 114 tokens 0.58.177.281 I slot print_timing: id 2 | task 43 | graphs reused = 1 0.58.177.282 I slot print_timing: id 2 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.177.296 I slot release: id 2 | task 43 | stop processing: n_tokens = 113, truncated = 0 0.58.177.618 I slot print_timing: id 3 | task 46 | prompt eval time = 1183.50 ms / 143 tokens ( 8.28 ms per token, 120.83 tokens per second) 0.58.177.621 I slot print_timing: id 3 | task 46 | eval time = 54.73 ms / 2 tokens ( 54.73 ms per token, 18.27 tokens per second) 0.58.177.622 I slot print_timing: id 3 | task 46 | total time = 1238.23 ms / 145 tokens 0.58.177.622 I slot print_timing: id 3 | task 46 | graphs reused = 1 0.58.177.623 I slot print_timing: id 3 | task 46 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.177.643 I slot release: id 3 | task 46 | stop processing: n_tokens = 144, truncated = 0 0.58.185.555 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.255 0.58.201.639 I slot launch_slot_: id 0 | task 50 | processing task, is_child = 0 0.58.243.268 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.283 0.58.243.362 I slot launch_slot_: id 2 | task 51 | processing task, is_child = 0 0.58.243.402 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.226 0.58.243.441 I slot launch_slot_: id 1 | task 52 | processing task, is_child = 0 0.58.243.462 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.194 0.58.245.725 I slot launch_slot_: id 3 | task 53 | processing task, is_child = 0 0.59.535.947 I slot print_timing: id 0 | task 50 | prompt eval time = 1235.42 ms / 102 tokens ( 12.11 ms per token, 82.56 tokens per second) 0.59.535.951 I slot print_timing: id 0 | task 50 | eval time = 54.78 ms / 2 tokens ( 54.78 ms per token, 18.26 tokens per second) 0.59.535.952 I slot print_timing: id 0 | task 50 | total time = 1290.20 ms / 104 tokens 0.59.535.953 I slot print_timing: id 0 | task 50 | graphs reused = 1 0.59.535.953 I slot print_timing: id 0 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.535.981 I slot release: id 0 | task 50 | stop processing: n_tokens = 103, truncated = 0 0.59.536.229 I slot print_timing: id 1 | task 52 | prompt eval time = 1235.89 ms / 136 tokens ( 9.09 ms per token, 110.04 tokens per second) 0.59.536.232 I slot print_timing: id 1 | task 52 | eval time = 54.58 ms / 2 tokens ( 54.58 ms per token, 18.32 tokens per second) 0.59.536.233 I slot print_timing: id 1 | task 52 | total time = 1290.47 ms / 138 tokens 0.59.536.233 I slot print_timing: id 1 | task 52 | graphs reused = 1 0.59.536.234 I slot print_timing: id 1 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.536.250 I slot release: id 1 | task 52 | stop processing: n_tokens = 137, truncated = 0 0.59.536.494 I slot print_timing: id 2 | task 51 | prompt eval time = 1236.41 ms / 129 tokens ( 9.58 ms per token, 104.33 tokens per second) 0.59.536.495 I slot print_timing: id 2 | task 51 | eval time = 54.31 ms / 2 tokens ( 54.31 ms per token, 18.41 tokens per second) 0.59.536.496 I slot print_timing: id 2 | task 51 | total time = 1290.72 ms / 131 tokens 0.59.536.496 I slot print_timing: id 2 | task 51 | graphs reused = 1 0.59.536.496 I slot print_timing: id 2 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.536.512 I slot release: id 2 | task 51 | stop processing: n_tokens = 130, truncated = 0 0.59.536.784 I slot print_timing: id 3 | task 53 | prompt eval time = 1236.88 ms / 112 tokens ( 11.04 ms per token, 90.55 tokens per second) 0.59.536.790 I slot print_timing: id 3 | task 53 | eval time = 54.12 ms / 2 tokens ( 54.12 ms per token, 18.48 tokens per second) 0.59.536.790 I slot print_timing: id 3 | task 53 | total time = 1290.99 ms / 114 tokens 0.59.536.791 I slot print_timing: id 3 | task 53 | graphs reused = 1 0.59.536.792 I slot print_timing: id 3 | task 53 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.536.812 I slot release: id 3 | task 53 | stop processing: n_tokens = 113, truncated = 0 0.59.548.186 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.272 0.59.552.498 I slot launch_slot_: id 0 | task 59 | processing task, is_child = 0 0.59.596.403 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.204 0.59.596.497 I slot launch_slot_: id 1 | task 57 | processing task, is_child = 0 0.59.596.540 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.215 0.59.596.586 I slot launch_slot_: id 2 | task 58 | processing task, is_child = 0 0.59.596.606 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.248 0.59.596.648 I slot launch_slot_: id 3 | task 60 | processing task, is_child = 0 1.01.130.522 I slot print_timing: id 0 | task 59 | prompt eval time = 1479.86 ms / 132 tokens ( 11.21 ms per token, 89.20 tokens per second) 1.01.130.526 I slot print_timing: id 0 | task 59 | eval time = 53.99 ms / 2 tokens ( 53.99 ms per token, 18.52 tokens per second) 1.01.130.527 I slot print_timing: id 0 | task 59 | total time = 1533.86 ms / 134 tokens 1.01.130.527 I slot print_timing: id 0 | task 59 | graphs reused = 1 1.01.130.528 I slot print_timing: id 0 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.130.556 I slot release: id 0 | task 59 | stop processing: n_tokens = 133, truncated = 0 1.01.130.805 I slot print_timing: id 1 | task 57 | prompt eval time = 1480.18 ms / 182 tokens ( 8.13 ms per token, 122.96 tokens per second) 1.01.130.813 I slot print_timing: id 1 | task 57 | eval time = 53.95 ms / 2 tokens ( 53.95 ms per token, 18.54 tokens per second) 1.01.130.814 I slot print_timing: id 1 | task 57 | total time = 1534.13 ms / 184 tokens 1.01.130.814 I slot print_timing: id 1 | task 57 | graphs reused = 1 1.01.130.815 I slot print_timing: id 1 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.130.838 I slot release: id 1 | task 57 | stop processing: n_tokens = 183, truncated = 0 1.01.131.098 I slot print_timing: id 2 | task 58 | prompt eval time = 1480.55 ms / 177 tokens ( 8.36 ms per token, 119.55 tokens per second) 1.01.131.102 I slot print_timing: id 2 | task 58 | eval time = 53.86 ms / 2 tokens ( 53.86 ms per token, 18.57 tokens per second) 1.01.131.102 I slot print_timing: id 2 | task 58 | total time = 1534.41 ms / 179 tokens 1.01.131.103 I slot print_timing: id 2 | task 58 | graphs reused = 1 1.01.131.103 I slot print_timing: id 2 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.131.121 I slot release: id 2 | task 58 | stop processing: n_tokens = 178, truncated = 0 1.01.131.373 I slot print_timing: id 3 | task 60 | prompt eval time = 1480.90 ms / 166 tokens ( 8.92 ms per token, 112.09 tokens per second) 1.01.131.376 I slot print_timing: id 3 | task 60 | eval time = 53.76 ms / 2 tokens ( 53.76 ms per token, 18.60 tokens per second) 1.01.131.377 I slot print_timing: id 3 | task 60 | total time = 1534.67 ms / 168 tokens 1.01.131.377 I slot print_timing: id 3 | task 60 | graphs reused = 1 1.01.131.378 I slot print_timing: id 3 | task 60 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.131.390 I slot release: id 3 | task 60 | stop processing: n_tokens = 167, truncated = 0 1.01.139.060 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.211 1.01.160.690 I slot launch_slot_: id 0 | task 64 | processing task, is_child = 0 1.01.215.906 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.153 1.01.215.988 I slot launch_slot_: id 1 | task 65 | processing task, is_child = 0 1.01.216.024 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.157 1.01.216.062 I slot launch_slot_: id 2 | task 66 | processing task, is_child = 0 1.01.216.083 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.168 1.01.222.050 I slot launch_slot_: id 3 | task 67 | processing task, is_child = 0 1.02.662.291 I slot print_timing: id 0 | task 64 | prompt eval time = 1386.17 ms / 169 tokens ( 8.20 ms per token, 121.92 tokens per second) 1.02.662.295 I slot print_timing: id 0 | task 64 | eval time = 54.05 ms / 2 tokens ( 54.05 ms per token, 18.50 tokens per second) 1.02.662.296 I slot print_timing: id 0 | task 64 | total time = 1440.22 ms / 171 tokens 1.02.662.297 I slot print_timing: id 0 | task 64 | graphs reused = 1 1.02.662.297 I slot print_timing: id 0 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.662.331 I slot release: id 0 | task 64 | stop processing: n_tokens = 170, truncated = 0 1.02.662.577 I slot print_timing: id 1 | task 65 | prompt eval time = 1386.58 ms / 123 tokens ( 11.27 ms per token, 88.71 tokens per second) 1.02.662.580 I slot print_timing: id 1 | task 65 | eval time = 53.92 ms / 2 tokens ( 53.92 ms per token, 18.55 tokens per second) 1.02.662.581 I slot print_timing: id 1 | task 65 | total time = 1440.50 ms / 125 tokens 1.02.662.582 I slot print_timing: id 1 | task 65 | graphs reused = 1 1.02.662.582 I slot print_timing: id 1 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.662.604 I slot release: id 1 | task 65 | stop processing: n_tokens = 124, truncated = 0 1.02.662.854 I slot print_timing: id 2 | task 66 | prompt eval time = 1387.00 ms / 149 tokens ( 9.31 ms per token, 107.43 tokens per second) 1.02.662.857 I slot print_timing: id 2 | task 66 | eval time = 53.76 ms / 2 tokens ( 53.76 ms per token, 18.60 tokens per second) 1.02.662.858 I slot print_timing: id 2 | task 66 | total time = 1440.76 ms / 151 tokens 1.02.662.858 I slot print_timing: id 2 | task 66 | graphs reused = 1 1.02.662.859 I slot print_timing: id 2 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.662.875 I slot release: id 2 | task 66 | stop processing: n_tokens = 150, truncated = 0 1.02.663.121 I slot print_timing: id 3 | task 67 | prompt eval time = 1387.42 ms / 140 tokens ( 9.91 ms per token, 100.91 tokens per second) 1.02.663.124 I slot print_timing: id 3 | task 67 | eval time = 53.59 ms / 2 tokens ( 53.59 ms per token, 18.66 tokens per second) 1.02.663.125 I slot print_timing: id 3 | task 67 | total time = 1441.01 ms / 142 tokens 1.02.663.125 I slot print_timing: id 3 | task 67 | graphs reused = 1 1.02.663.126 I slot print_timing: id 3 | task 67 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.663.142 I slot release: id 3 | task 67 | stop processing: n_tokens = 141, truncated = 0 1.02.671.437 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.165 1.02.693.535 I slot launch_slot_: id 0 | task 71 | processing task, is_child = 0 1.02.830.259 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.206 1.02.830.372 I slot launch_slot_: id 3 | task 72 | processing task, is_child = 0 1.02.830.413 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.234 1.02.830.461 I slot launch_slot_: id 1 | task 73 | processing task, is_child = 0 1.02.830.479 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.187 1.02.830.531 I slot launch_slot_: id 2 | task 74 | processing task, is_child = 0 1.04.224.583 I slot print_timing: id 0 | task 71 | prompt eval time = 1338.83 ms / 128 tokens ( 10.46 ms per token, 95.61 tokens per second) 1.04.224.588 I slot print_timing: id 0 | task 71 | eval time = 55.21 ms / 2 tokens ( 55.21 ms per token, 18.11 tokens per second) 1.04.224.589 I slot print_timing: id 0 | task 71 | total time = 1394.04 ms / 130 tokens 1.04.224.589 I slot print_timing: id 0 | task 71 | graphs reused = 1 1.04.224.590 I slot print_timing: id 0 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.224.619 I slot release: id 0 | task 71 | stop processing: n_tokens = 129, truncated = 0 1.04.224.917 I slot print_timing: id 1 | task 73 | prompt eval time = 1339.29 ms / 161 tokens ( 8.32 ms per token, 120.21 tokens per second) 1.04.224.921 I slot print_timing: id 1 | task 73 | eval time = 55.07 ms / 2 tokens ( 55.07 ms per token, 18.16 tokens per second) 1.04.224.922 I slot print_timing: id 1 | task 73 | total time = 1394.36 ms / 163 tokens 1.04.224.922 I slot print_timing: id 1 | task 73 | graphs reused = 1 1.04.224.923 I slot print_timing: id 1 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.224.943 I slot release: id 1 | task 73 | stop processing: n_tokens = 162, truncated = 0 1.04.225.239 I slot print_timing: id 2 | task 74 | prompt eval time = 1339.78 ms / 163 tokens ( 8.22 ms per token, 121.66 tokens per second) 1.04.225.243 I slot print_timing: id 2 | task 74 | eval time = 54.89 ms / 2 tokens ( 54.89 ms per token, 18.22 tokens per second) 1.04.225.244 I slot print_timing: id 2 | task 74 | total time = 1394.67 ms / 165 tokens 1.04.225.244 I slot print_timing: id 2 | task 74 | graphs reused = 1 1.04.225.245 I slot print_timing: id 2 | task 74 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.225.266 I slot release: id 2 | task 74 | stop processing: n_tokens = 164, truncated = 0 1.04.225.552 I slot print_timing: id 3 | task 72 | prompt eval time = 1340.30 ms / 111 tokens ( 12.07 ms per token, 82.82 tokens per second) 1.04.225.557 I slot print_timing: id 3 | task 72 | eval time = 54.66 ms / 2 tokens ( 54.66 ms per token, 18.29 tokens per second) 1.04.225.558 I slot print_timing: id 3 | task 72 | total time = 1394.97 ms / 113 tokens 1.04.225.558 I slot print_timing: id 3 | task 72 | graphs reused = 1 1.04.225.559 I slot print_timing: id 3 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.225.573 I slot release: id 3 | task 72 | stop processing: n_tokens = 112, truncated = 0 1.04.233.780 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 1.04.286.140 I slot launch_slot_: id 0 | task 78 | processing task, is_child = 0 1.04.461.667 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.173 1.04.461.715 I slot launch_slot_: id 1 | task 79 | processing task, is_child = 0 1.04.461.748 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.177 1.04.461.783 I slot launch_slot_: id 2 | task 80 | processing task, is_child = 0 1.04.461.801 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.250 1.04.461.833 I slot launch_slot_: id 3 | task 81 | processing task, is_child = 0 1.05.871.454 I slot print_timing: id 0 | task 78 | prompt eval time = 1354.39 ms / 112 tokens ( 12.09 ms per token, 82.69 tokens per second) 1.05.871.459 I slot print_timing: id 0 | task 78 | eval time = 55.22 ms / 2 tokens ( 55.22 ms per token, 18.11 tokens per second) 1.05.871.460 I slot print_timing: id 0 | task 78 | total time = 1409.61 ms / 114 tokens 1.05.871.461 I slot print_timing: id 0 | task 78 | graphs reused = 1 1.05.871.461 I slot print_timing: id 0 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.871.490 I slot release: id 0 | task 78 | stop processing: n_tokens = 113, truncated = 0 1.05.871.733 I slot print_timing: id 1 | task 79 | prompt eval time = 1354.80 ms / 167 tokens ( 8.11 ms per token, 123.27 tokens per second) 1.05.871.740 I slot print_timing: id 1 | task 79 | eval time = 55.08 ms / 2 tokens ( 55.08 ms per token, 18.16 tokens per second) 1.05.871.741 I slot print_timing: id 1 | task 79 | total time = 1409.88 ms / 169 tokens 1.05.871.742 I slot print_timing: id 1 | task 79 | graphs reused = 1 1.05.871.742 I slot print_timing: id 1 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.871.760 I slot release: id 1 | task 79 | stop processing: n_tokens = 168, truncated = 0 1.05.872.014 I slot print_timing: id 2 | task 80 | prompt eval time = 1355.22 ms / 109 tokens ( 12.43 ms per token, 80.43 tokens per second) 1.05.872.016 I slot print_timing: id 2 | task 80 | eval time = 54.93 ms / 2 tokens ( 54.93 ms per token, 18.21 tokens per second) 1.05.872.018 I slot print_timing: id 2 | task 80 | total time = 1410.14 ms / 111 tokens 1.05.872.018 I slot print_timing: id 2 | task 80 | graphs reused = 1 1.05.872.019 I slot print_timing: id 2 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.872.038 I slot release: id 2 | task 80 | stop processing: n_tokens = 110, truncated = 0 1.05.872.289 I slot print_timing: id 3 | task 81 | prompt eval time = 1355.67 ms / 164 tokens ( 8.27 ms per token, 120.97 tokens per second) 1.05.872.292 I slot print_timing: id 3 | task 81 | eval time = 54.73 ms / 2 tokens ( 54.73 ms per token, 18.27 tokens per second) 1.05.872.293 I slot print_timing: id 3 | task 81 | total time = 1410.41 ms / 166 tokens 1.05.872.294 I slot print_timing: id 3 | task 81 | graphs reused = 1 1.05.872.294 I slot print_timing: id 3 | task 81 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.872.314 I slot release: id 3 | task 81 | stop processing: n_tokens = 165, truncated = 0 1.05.880.339 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.248 1.05.927.489 I slot launch_slot_: id 0 | task 85 | processing task, is_child = 0 1.06.100.734 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.167 1.06.100.796 I slot launch_slot_: id 1 | task 86 | processing task, is_child = 0 1.06.100.830 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.255 1.06.102.893 I slot launch_slot_: id 2 | task 87 | processing task, is_child = 0 1.06.102.918 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.170 1.06.102.952 I slot launch_slot_: id 3 | task 88 | processing task, is_child = 0 1.07.395.073 I slot print_timing: id 0 | task 85 | prompt eval time = 1237.66 ms / 147 tokens ( 8.42 ms per token, 118.77 tokens per second) 1.07.395.078 I slot print_timing: id 0 | task 85 | eval time = 54.44 ms / 2 tokens ( 54.44 ms per token, 18.37 tokens per second) 1.07.395.080 I slot print_timing: id 0 | task 85 | total time = 1292.11 ms / 149 tokens 1.07.395.080 I slot print_timing: id 0 | task 85 | graphs reused = 1 1.07.395.081 I slot print_timing: id 0 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.395.118 I slot release: id 0 | task 85 | stop processing: n_tokens = 148, truncated = 0 1.07.395.362 I slot print_timing: id 1 | task 86 | prompt eval time = 1238.21 ms / 131 tokens ( 9.45 ms per token, 105.80 tokens per second) 1.07.395.369 I slot print_timing: id 1 | task 86 | eval time = 54.17 ms / 2 tokens ( 54.17 ms per token, 18.46 tokens per second) 1.07.395.370 I slot print_timing: id 1 | task 86 | total time = 1292.39 ms / 133 tokens 1.07.395.371 I slot print_timing: id 1 | task 86 | graphs reused = 1 1.07.395.371 I slot print_timing: id 1 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.395.390 I slot release: id 1 | task 86 | stop processing: n_tokens = 132, truncated = 0 1.07.395.638 I slot print_timing: id 2 | task 87 | prompt eval time = 1238.84 ms / 122 tokens ( 10.15 ms per token, 98.48 tokens per second) 1.07.395.642 I slot print_timing: id 2 | task 87 | eval time = 53.81 ms / 2 tokens ( 53.81 ms per token, 18.58 tokens per second) 1.07.395.643 I slot print_timing: id 2 | task 87 | total time = 1292.65 ms / 124 tokens 1.07.395.643 I slot print_timing: id 2 | task 87 | graphs reused = 1 1.07.395.644 I slot print_timing: id 2 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.395.661 I slot release: id 2 | task 87 | stop processing: n_tokens = 123, truncated = 0 1.07.395.936 I slot print_timing: id 3 | task 88 | prompt eval time = 1239.40 ms / 120 tokens ( 10.33 ms per token, 96.82 tokens per second) 1.07.395.939 I slot print_timing: id 3 | task 88 | eval time = 53.53 ms / 2 tokens ( 53.53 ms per token, 18.68 tokens per second) 1.07.395.940 I slot print_timing: id 3 | task 88 | total time = 1292.92 ms / 122 tokens 1.07.395.940 I slot print_timing: id 3 | task 88 | graphs reused = 1 1.07.395.941 I slot print_timing: id 3 | task 88 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.395.961 I slot release: id 3 | task 88 | stop processing: n_tokens = 121, truncated = 0 1.07.404.116 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.189 1.07.438.644 I slot launch_slot_: id 0 | task 93 | processing task, is_child = 0 1.07.557.207 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.236 1.07.557.437 I slot launch_slot_: id 2 | task 92 | processing task, is_child = 0 1.07.557.473 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.212 1.07.557.506 I slot launch_slot_: id 1 | task 94 | processing task, is_child = 0 1.07.557.522 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.231 1.07.559.301 I slot launch_slot_: id 3 | task 95 | processing task, is_child = 0 1.08.836.453 I slot print_timing: id 0 | task 93 | prompt eval time = 1222.51 ms / 124 tokens ( 9.86 ms per token, 101.43 tokens per second) 1.08.836.460 I slot print_timing: id 0 | task 93 | eval time = 54.62 ms / 2 tokens ( 54.62 ms per token, 18.31 tokens per second) 1.08.836.465 I slot print_timing: id 0 | task 93 | total time = 1277.13 ms / 126 tokens 1.08.836.466 I slot print_timing: id 0 | task 93 | graphs reused = 1 1.08.836.466 I slot print_timing: id 0 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.836.585 I slot release: id 0 | task 93 | stop processing: n_tokens = 125, truncated = 0 1.08.836.894 I slot print_timing: id 1 | task 94 | prompt eval time = 1222.91 ms / 144 tokens ( 8.49 ms per token, 117.75 tokens per second) 1.08.836.899 I slot print_timing: id 1 | task 94 | eval time = 54.66 ms / 2 tokens ( 54.66 ms per token, 18.30 tokens per second) 1.08.836.900 I slot print_timing: id 1 | task 94 | total time = 1277.56 ms / 146 tokens 1.08.836.901 I slot print_timing: id 1 | task 94 | graphs reused = 1 1.08.836.902 I slot print_timing: id 1 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.836.968 I slot release: id 1 | task 94 | stop processing: n_tokens = 145, truncated = 0 1.08.837.297 I slot print_timing: id 2 | task 92 | prompt eval time = 1223.35 ms / 131 tokens ( 9.34 ms per token, 107.08 tokens per second) 1.08.837.304 I slot print_timing: id 2 | task 92 | eval time = 54.60 ms / 2 tokens ( 54.60 ms per token, 18.32 tokens per second) 1.08.837.304 I slot print_timing: id 2 | task 92 | total time = 1277.95 ms / 133 tokens 1.08.837.305 I slot print_timing: id 2 | task 92 | graphs reused = 1 1.08.837.305 I slot print_timing: id 2 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.837.333 I slot release: id 2 | task 92 | stop processing: n_tokens = 132, truncated = 0 1.08.837.649 I slot print_timing: id 3 | task 95 | prompt eval time = 1223.79 ms / 141 tokens ( 8.68 ms per token, 115.22 tokens per second) 1.08.837.658 I slot print_timing: id 3 | task 95 | eval time = 54.51 ms / 2 tokens ( 54.51 ms per token, 18.34 tokens per second) 1.08.837.659 I slot print_timing: id 3 | task 95 | total time = 1278.30 ms / 143 tokens 1.08.837.659 I slot print_timing: id 3 | task 95 | graphs reused = 1 1.08.837.660 I slot print_timing: id 3 | task 95 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.837.696 I slot release: id 3 | task 95 | stop processing: n_tokens = 142, truncated = 0 1.08.853.872 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.200 1.08.871.331 I slot launch_slot_: id 1 | task 99 | processing task, is_child = 0 1.08.955.067 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.224 1.08.955.125 I slot launch_slot_: id 0 | task 100 | processing task, is_child = 0 1.08.955.162 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.204 1.08.955.196 I slot launch_slot_: id 3 | task 101 | processing task, is_child = 0 1.08.955.214 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.220 1.08.955.247 I slot launch_slot_: id 2 | task 102 | processing task, is_child = 0 1.10.285.118 I slot print_timing: id 0 | task 100 | prompt eval time = 1275.07 ms / 121 tokens ( 10.54 ms per token, 94.90 tokens per second) 1.10.285.126 I slot print_timing: id 0 | task 100 | eval time = 54.79 ms / 2 tokens ( 54.79 ms per token, 18.25 tokens per second) 1.10.285.127 I slot print_timing: id 0 | task 100 | total time = 1329.86 ms / 123 tokens 1.10.285.127 I slot print_timing: id 0 | task 100 | graphs reused = 1 1.10.285.128 I slot print_timing: id 0 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.285.181 I slot release: id 0 | task 100 | stop processing: n_tokens = 122, truncated = 0 1.10.285.486 I slot print_timing: id 1 | task 99 | prompt eval time = 1275.47 ms / 118 tokens ( 10.81 ms per token, 92.51 tokens per second) 1.10.285.493 I slot print_timing: id 1 | task 99 | eval time = 54.74 ms / 2 tokens ( 54.74 ms per token, 18.27 tokens per second) 1.10.285.495 I slot print_timing: id 1 | task 99 | total time = 1330.21 ms / 120 tokens 1.10.285.496 I slot print_timing: id 1 | task 99 | graphs reused = 1 1.10.285.497 I slot print_timing: id 1 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.285.538 I slot release: id 1 | task 99 | stop processing: n_tokens = 119, truncated = 0 1.10.285.883 I slot print_timing: id 2 | task 102 | prompt eval time = 1275.94 ms / 107 tokens ( 11.92 ms per token, 83.86 tokens per second) 1.10.285.886 I slot print_timing: id 2 | task 102 | eval time = 54.65 ms / 2 tokens ( 54.65 ms per token, 18.30 tokens per second) 1.10.285.887 I slot print_timing: id 2 | task 102 | total time = 1330.60 ms / 109 tokens 1.10.285.888 I slot print_timing: id 2 | task 102 | graphs reused = 1 1.10.285.888 I slot print_timing: id 2 | task 102 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.285.952 I slot release: id 2 | task 102 | stop processing: n_tokens = 108, truncated = 0 1.10.286.272 I slot print_timing: id 3 | task 101 | prompt eval time = 1276.46 ms / 172 tokens ( 7.42 ms per token, 134.75 tokens per second) 1.10.286.276 I slot print_timing: id 3 | task 101 | eval time = 54.51 ms / 2 tokens ( 54.51 ms per token, 18.34 tokens per second) 1.10.286.277 I slot print_timing: id 3 | task 101 | total time = 1330.98 ms / 174 tokens 1.10.286.277 I slot print_timing: id 3 | task 101 | graphs reused = 1 1.10.286.278 I slot print_timing: id 3 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.286.314 I slot release: id 3 | task 101 | stop processing: n_tokens = 173, truncated = 0 1.10.295.707 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.244 1.10.326.963 I slot launch_slot_: id 1 | task 106 | processing task, is_child = 0 1.10.449.003 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.269 1.10.449.116 I slot launch_slot_: id 2 | task 107 | processing task, is_child = 0 1.10.449.160 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 1.10.449.206 I slot launch_slot_: id 0 | task 108 | processing task, is_child = 0 1.10.449.235 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.162 1.10.449.299 I slot launch_slot_: id 3 | task 109 | processing task, is_child = 0 1.12.125.812 I slot print_timing: id 0 | task 108 | prompt eval time = 1621.69 ms / 177 tokens ( 9.16 ms per token, 109.15 tokens per second) 1.12.125.816 I slot print_timing: id 0 | task 108 | eval time = 54.81 ms / 2 tokens ( 54.81 ms per token, 18.24 tokens per second) 1.12.125.817 I slot print_timing: id 0 | task 108 | total time = 1676.50 ms / 179 tokens 1.12.125.818 I slot print_timing: id 0 | task 108 | graphs reused = 1 1.12.125.818 I slot print_timing: id 0 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.125.893 I slot release: id 0 | task 108 | stop processing: n_tokens = 178, truncated = 0 1.12.126.154 I slot print_timing: id 1 | task 106 | prompt eval time = 1622.15 ms / 116 tokens ( 13.98 ms per token, 71.51 tokens per second) 1.12.126.157 I slot print_timing: id 1 | task 106 | eval time = 54.68 ms / 2 tokens ( 54.68 ms per token, 18.29 tokens per second) 1.12.126.159 I slot print_timing: id 1 | task 106 | total time = 1676.82 ms / 118 tokens 1.12.126.160 I slot print_timing: id 1 | task 106 | graphs reused = 1 1.12.126.160 I slot print_timing: id 1 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.126.209 I slot release: id 1 | task 106 | stop processing: n_tokens = 117, truncated = 0 1.12.126.466 I slot print_timing: id 2 | task 107 | prompt eval time = 1622.67 ms / 136 tokens ( 11.93 ms per token, 83.81 tokens per second) 1.12.126.472 I slot print_timing: id 2 | task 107 | eval time = 54.46 ms / 2 tokens ( 54.46 ms per token, 18.36 tokens per second) 1.12.126.473 I slot print_timing: id 2 | task 107 | total time = 1677.13 ms / 138 tokens 1.12.126.474 I slot print_timing: id 2 | task 107 | graphs reused = 1 1.12.126.475 I slot print_timing: id 2 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.126.542 I slot release: id 2 | task 107 | stop processing: n_tokens = 137, truncated = 0 1.12.126.814 I slot print_timing: id 3 | task 109 | prompt eval time = 1623.18 ms / 240 tokens ( 6.76 ms per token, 147.86 tokens per second) 1.12.126.817 I slot print_timing: id 3 | task 109 | eval time = 54.27 ms / 2 tokens ( 54.27 ms per token, 18.43 tokens per second) 1.12.126.818 I slot print_timing: id 3 | task 109 | total time = 1677.46 ms / 242 tokens 1.12.126.818 I slot print_timing: id 3 | task 109 | graphs reused = 1 1.12.126.819 I slot print_timing: id 3 | task 109 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.126.939 I slot release: id 3 | task 109 | stop processing: n_tokens = 241, truncated = 0 1.12.143.553 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.265 1.12.186.010 I slot launch_slot_: id 1 | task 113 | processing task, is_child = 0 1.12.297.795 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.212 1.12.299.635 I slot launch_slot_: id 2 | task 114 | processing task, is_child = 0 1.12.299.681 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 1.12.299.725 I slot launch_slot_: id 0 | task 115 | processing task, is_child = 0 1.12.299.746 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.116 1.12.299.789 I slot launch_slot_: id 3 | task 116 | processing task, is_child = 0 1.14.139.250 I slot print_timing: id 0 | task 115 | prompt eval time = 1785.50 ms / 160 tokens ( 11.16 ms per token, 89.61 tokens per second) 1.14.139.257 I slot print_timing: id 0 | task 115 | eval time = 53.95 ms / 2 tokens ( 53.95 ms per token, 18.53 tokens per second) 1.14.139.258 I slot print_timing: id 0 | task 115 | total time = 1839.45 ms / 162 tokens 1.14.139.259 I slot print_timing: id 0 | task 115 | graphs reused = 1 1.14.139.259 I slot print_timing: id 0 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.139.344 I slot release: id 0 | task 115 | stop processing: n_tokens = 161, truncated = 0 1.14.139.595 I slot print_timing: id 1 | task 113 | prompt eval time = 1785.83 ms / 142 tokens ( 12.58 ms per token, 79.52 tokens per second) 1.14.139.602 I slot print_timing: id 1 | task 113 | eval time = 53.95 ms / 2 tokens ( 53.95 ms per token, 18.53 tokens per second) 1.14.139.602 I slot print_timing: id 1 | task 113 | total time = 1839.78 ms / 144 tokens 1.14.139.603 I slot print_timing: id 1 | task 113 | graphs reused = 1 1.14.139.603 I slot print_timing: id 1 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.139.641 I slot release: id 1 | task 113 | stop processing: n_tokens = 143, truncated = 0 1.14.139.912 I slot print_timing: id 2 | task 114 | prompt eval time = 1786.19 ms / 155 tokens ( 11.52 ms per token, 86.78 tokens per second) 1.14.139.915 I slot print_timing: id 2 | task 114 | eval time = 53.90 ms / 2 tokens ( 53.90 ms per token, 18.55 tokens per second) 1.14.139.916 I slot print_timing: id 2 | task 114 | total time = 1840.09 ms / 157 tokens 1.14.139.916 I slot print_timing: id 2 | task 114 | graphs reused = 1 1.14.139.917 I slot print_timing: id 2 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.139.972 I slot release: id 2 | task 114 | stop processing: n_tokens = 156, truncated = 0 1.14.140.228 I slot print_timing: id 3 | task 116 | prompt eval time = 1786.54 ms / 226 tokens ( 7.91 ms per token, 126.50 tokens per second) 1.14.140.234 I slot print_timing: id 3 | task 116 | eval time = 53.85 ms / 2 tokens ( 53.85 ms per token, 18.57 tokens per second) 1.14.140.235 I slot print_timing: id 3 | task 116 | total time = 1840.39 ms / 228 tokens 1.14.140.235 I slot print_timing: id 3 | task 116 | graphs reused = 1 1.14.140.236 I slot print_timing: id 3 | task 116 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.140.340 I slot release: id 3 | task 116 | stop processing: n_tokens = 227, truncated = 0 1.14.149.607 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.295 (> 0.100 thold), f_keep = 0.217 1.14.162.491 I slot launch_slot_: id 1 | task 120 | processing task, is_child = 0 1.14.259.519 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.186 1.14.259.637 I slot launch_slot_: id 2 | task 121 | processing task, is_child = 0 1.14.259.681 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 1.14.259.720 I slot launch_slot_: id 0 | task 122 | processing task, is_child = 0 1.14.259.741 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.123 1.14.262.805 I slot launch_slot_: id 3 | task 123 | processing task, is_child = 0 1.15.789.311 I slot print_timing: id 0 | task 122 | prompt eval time = 1471.88 ms / 141 tokens ( 10.44 ms per token, 95.80 tokens per second) 1.15.789.316 I slot print_timing: id 0 | task 122 | eval time = 54.61 ms / 2 tokens ( 54.61 ms per token, 18.31 tokens per second) 1.15.789.317 I slot print_timing: id 0 | task 122 | total time = 1526.49 ms / 143 tokens 1.15.789.317 I slot print_timing: id 0 | task 122 | graphs reused = 1 1.15.789.328 I slot print_timing: id 0 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.789.422 I slot release: id 0 | task 122 | stop processing: n_tokens = 142, truncated = 0 1.15.789.730 I slot print_timing: id 1 | task 120 | prompt eval time = 1472.25 ms / 105 tokens ( 14.02 ms per token, 71.32 tokens per second) 1.15.789.734 I slot print_timing: id 1 | task 120 | eval time = 54.63 ms / 2 tokens ( 54.63 ms per token, 18.30 tokens per second) 1.15.789.736 I slot print_timing: id 1 | task 120 | total time = 1526.88 ms / 107 tokens 1.15.789.737 I slot print_timing: id 1 | task 120 | graphs reused = 1 1.15.789.737 I slot print_timing: id 1 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.789.766 I slot release: id 1 | task 120 | stop processing: n_tokens = 106, truncated = 0 1.15.790.085 I slot print_timing: id 2 | task 121 | prompt eval time = 1472.66 ms / 114 tokens ( 12.92 ms per token, 77.41 tokens per second) 1.15.790.093 I slot print_timing: id 2 | task 121 | eval time = 54.57 ms / 2 tokens ( 54.57 ms per token, 18.32 tokens per second) 1.15.790.093 I slot print_timing: id 2 | task 121 | total time = 1527.23 ms / 116 tokens 1.15.790.094 I slot print_timing: id 2 | task 121 | graphs reused = 1 1.15.790.095 I slot print_timing: id 2 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.790.159 I slot release: id 2 | task 121 | stop processing: n_tokens = 115, truncated = 0 1.15.790.497 I slot print_timing: id 3 | task 123 | prompt eval time = 1473.05 ms / 192 tokens ( 7.67 ms per token, 130.34 tokens per second) 1.15.790.501 I slot print_timing: id 3 | task 123 | eval time = 54.58 ms / 2 tokens ( 54.58 ms per token, 18.32 tokens per second) 1.15.790.502 I slot print_timing: id 3 | task 123 | total time = 1527.63 ms / 194 tokens 1.15.790.502 I slot print_timing: id 3 | task 123 | graphs reused = 1 1.15.790.503 I slot print_timing: id 3 | task 123 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.790.637 I slot release: id 3 | task 123 | stop processing: n_tokens = 193, truncated = 0 1.15.799.348 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 1.15.811.334 I slot launch_slot_: id 0 | task 127 | processing task, is_child = 0 1.15.913.182 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.895 MiB) 1.15.950.480 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.264 1.15.950.580 I slot launch_slot_: id 1 | task 128 | processing task, is_child = 0 1.15.950.619 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.252 1.15.950.655 I slot launch_slot_: id 2 | task 129 | processing task, is_child = 0 1.15.950.676 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.145 1.15.952.953 I slot launch_slot_: id 3 | task 130 | processing task, is_child = 0 1.17.390.235 I slot print_timing: id 0 | task 127 | prompt eval time = 1383.55 ms / 135 tokens ( 10.25 ms per token, 97.58 tokens per second) 1.17.390.239 I slot print_timing: id 0 | task 127 | eval time = 53.72 ms / 2 tokens ( 53.72 ms per token, 18.62 tokens per second) 1.17.390.240 I slot print_timing: id 0 | task 127 | total time = 1437.27 ms / 137 tokens 1.17.390.241 I slot print_timing: id 0 | task 127 | graphs reused = 1 1.17.390.241 I slot print_timing: id 0 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.390.320 I slot release: id 0 | task 127 | stop processing: n_tokens = 136, truncated = 0 1.17.390.563 I slot print_timing: id 1 | task 128 | prompt eval time = 1383.82 ms / 172 tokens ( 8.05 ms per token, 124.29 tokens per second) 1.17.390.566 I slot print_timing: id 1 | task 128 | eval time = 53.76 ms / 2 tokens ( 53.76 ms per token, 18.60 tokens per second) 1.17.390.567 I slot print_timing: id 1 | task 128 | total time = 1437.58 ms / 174 tokens 1.17.390.568 I slot print_timing: id 1 | task 128 | graphs reused = 1 1.17.390.568 I slot print_timing: id 1 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.390.616 I slot release: id 1 | task 128 | stop processing: n_tokens = 173, truncated = 0 1.17.390.877 I slot print_timing: id 2 | task 129 | prompt eval time = 1384.08 ms / 108 tokens ( 12.82 ms per token, 78.03 tokens per second) 1.17.390.880 I slot print_timing: id 2 | task 129 | eval time = 53.80 ms / 2 tokens ( 53.80 ms per token, 18.59 tokens per second) 1.17.390.881 I slot print_timing: id 2 | task 129 | total time = 1437.88 ms / 110 tokens 1.17.390.881 I slot print_timing: id 2 | task 129 | graphs reused = 1 1.17.390.882 I slot print_timing: id 2 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.390.989 I slot release: id 2 | task 129 | stop processing: n_tokens = 109, truncated = 0 1.17.391.247 I slot print_timing: id 3 | task 130 | prompt eval time = 1384.39 ms / 122 tokens ( 11.35 ms per token, 88.13 tokens per second) 1.17.391.251 I slot print_timing: id 3 | task 130 | eval time = 53.84 ms / 2 tokens ( 53.84 ms per token, 18.57 tokens per second) 1.17.391.252 I slot print_timing: id 3 | task 130 | total time = 1438.24 ms / 124 tokens 1.17.391.252 I slot print_timing: id 3 | task 130 | graphs reused = 1 1.17.391.253 I slot print_timing: id 3 | task 130 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.391.291 I slot release: id 3 | task 130 | stop processing: n_tokens = 123, truncated = 0 1.17.399.018 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 1.17.409.424 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 1.17.409.457 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 1.17.433.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 1.17.465.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.557 MiB) 1.17.494.806 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.266 1.17.497.189 I slot launch_slot_: id 2 | task 135 | processing task, is_child = 0 1.17.497.236 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.162 1.17.497.276 I slot launch_slot_: id 1 | task 136 | processing task, is_child = 0 1.17.497.295 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.228 1.17.497.332 I slot launch_slot_: id 3 | task 137 | processing task, is_child = 0 1.18.888.029 I slot print_timing: id 0 | task 134 | prompt eval time = 1336.85 ms / 135 tokens ( 9.90 ms per token, 100.98 tokens per second) 1.18.888.033 I slot print_timing: id 0 | task 134 | eval time = 53.84 ms / 2 tokens ( 53.84 ms per token, 18.57 tokens per second) 1.18.888.034 I slot print_timing: id 0 | task 134 | total time = 1390.68 ms / 137 tokens 1.18.888.035 I slot print_timing: id 0 | task 134 | graphs reused = 1 1.18.888.035 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.888.082 I slot release: id 0 | task 134 | stop processing: n_tokens = 136, truncated = 0 1.18.888.329 I slot print_timing: id 1 | task 136 | prompt eval time = 1337.17 ms / 134 tokens ( 9.98 ms per token, 100.21 tokens per second) 1.18.888.333 I slot print_timing: id 1 | task 136 | eval time = 53.80 ms / 2 tokens ( 53.80 ms per token, 18.59 tokens per second) 1.18.888.333 I slot print_timing: id 1 | task 136 | total time = 1390.97 ms / 136 tokens 1.18.888.334 I slot print_timing: id 1 | task 136 | graphs reused = 1 1.18.888.335 I slot print_timing: id 1 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.888.384 I slot release: id 1 | task 136 | stop processing: n_tokens = 135, truncated = 0 1.18.888.630 I slot print_timing: id 2 | task 135 | prompt eval time = 1337.54 ms / 120 tokens ( 11.15 ms per token, 89.72 tokens per second) 1.18.888.633 I slot print_timing: id 2 | task 135 | eval time = 53.72 ms / 2 tokens ( 53.72 ms per token, 18.62 tokens per second) 1.18.888.634 I slot print_timing: id 2 | task 135 | total time = 1391.26 ms / 122 tokens 1.18.888.634 I slot print_timing: id 2 | task 135 | graphs reused = 1 1.18.888.635 I slot print_timing: id 2 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.888.755 I slot release: id 2 | task 135 | stop processing: n_tokens = 121, truncated = 0 1.18.889.025 I slot print_timing: id 3 | task 137 | prompt eval time = 1337.91 ms / 159 tokens ( 8.41 ms per token, 118.84 tokens per second) 1.18.889.028 I slot print_timing: id 3 | task 137 | eval time = 53.73 ms / 2 tokens ( 53.73 ms per token, 18.61 tokens per second) 1.18.889.029 I slot print_timing: id 3 | task 137 | total time = 1391.64 ms / 161 tokens 1.18.889.029 I slot print_timing: id 3 | task 137 | graphs reused = 1 1.18.889.030 I slot print_timing: id 3 | task 137 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.889.115 I slot release: id 3 | task 137 | stop processing: n_tokens = 160, truncated = 0 1.18.896.475 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 1.18.917.150 I slot launch_slot_: id 0 | task 141 | processing task, is_child = 0 1.18.917.180 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.618 MiB) 1.18.952.606 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.775 MiB) 1.18.982.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.934 MiB) 1.19.022.817 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.207 1.19.022.917 I slot launch_slot_: id 1 | task 142 | processing task, is_child = 0 1.19.022.953 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.231 1.19.022.988 I slot launch_slot_: id 2 | task 143 | processing task, is_child = 0 1.19.023.008 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.175 1.19.023.040 I slot launch_slot_: id 3 | task 144 | processing task, is_child = 0 1.20.454.332 I slot print_timing: id 0 | task 141 | prompt eval time = 1376.68 ms / 130 tokens ( 10.59 ms per token, 94.43 tokens per second) 1.20.454.336 I slot print_timing: id 0 | task 141 | eval time = 54.59 ms / 2 tokens ( 54.59 ms per token, 18.32 tokens per second) 1.20.454.337 I slot print_timing: id 0 | task 141 | total time = 1431.27 ms / 132 tokens 1.20.454.338 I slot print_timing: id 0 | task 141 | graphs reused = 1 1.20.454.338 I slot print_timing: id 0 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.454.436 I slot release: id 0 | task 141 | stop processing: n_tokens = 131, truncated = 0 1.20.454.722 I slot print_timing: id 1 | task 142 | prompt eval time = 1377.07 ms / 172 tokens ( 8.01 ms per token, 124.90 tokens per second) 1.20.454.729 I slot print_timing: id 1 | task 142 | eval time = 54.58 ms / 2 tokens ( 54.58 ms per token, 18.32 tokens per second) 1.20.454.730 I slot print_timing: id 1 | task 142 | total time = 1431.65 ms / 174 tokens 1.20.454.731 I slot print_timing: id 1 | task 142 | graphs reused = 1 1.20.454.731 I slot print_timing: id 1 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.454.790 I slot release: id 1 | task 142 | stop processing: n_tokens = 173, truncated = 0 1.20.455.084 I slot print_timing: id 2 | task 143 | prompt eval time = 1377.49 ms / 175 tokens ( 7.87 ms per token, 127.04 tokens per second) 1.20.455.087 I slot print_timing: id 2 | task 143 | eval time = 54.52 ms / 2 tokens ( 54.52 ms per token, 18.34 tokens per second) 1.20.455.088 I slot print_timing: id 2 | task 143 | total time = 1432.00 ms / 177 tokens 1.20.455.088 I slot print_timing: id 2 | task 143 | graphs reused = 1 1.20.455.089 I slot print_timing: id 2 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.455.139 I slot release: id 2 | task 143 | stop processing: n_tokens = 176, truncated = 0 1.20.455.423 I slot print_timing: id 3 | task 144 | prompt eval time = 1377.88 ms / 180 tokens ( 7.65 ms per token, 130.64 tokens per second) 1.20.455.426 I slot print_timing: id 3 | task 144 | eval time = 54.45 ms / 2 tokens ( 54.45 ms per token, 18.37 tokens per second) 1.20.455.427 I slot print_timing: id 3 | task 144 | total time = 1432.33 ms / 182 tokens 1.20.455.428 I slot print_timing: id 3 | task 144 | graphs reused = 1 1.20.455.438 I slot print_timing: id 3 | task 144 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.455.471 I slot release: id 3 | task 144 | stop processing: n_tokens = 181, truncated = 0 1.20.463.059 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.214 1.20.463.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.954 MiB) 1.20.507.138 I slot launch_slot_: id 0 | task 148 | processing task, is_child = 0 1.20.507.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.091 MiB) 1.20.637.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.579 MiB) 1.20.672.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.442 MiB) 1.20.710.284 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.162 1.20.721.005 I slot launch_slot_: id 1 | task 150 | processing task, is_child = 0 1.20.721.056 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.159 1.20.721.101 I slot launch_slot_: id 2 | task 149 | processing task, is_child = 0 1.20.721.121 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 1.20.722.586 I slot launch_slot_: id 3 | task 151 | processing task, is_child = 0 1.21.804.506 I slot print_timing: id 0 | task 148 | prompt eval time = 1025.94 ms / 123 tokens ( 8.34 ms per token, 119.89 tokens per second) 1.21.804.511 I slot print_timing: id 0 | task 148 | eval time = 55.97 ms / 2 tokens ( 55.97 ms per token, 17.87 tokens per second) 1.21.804.512 I slot print_timing: id 0 | task 148 | total time = 1081.90 ms / 125 tokens 1.21.804.515 I slot print_timing: id 0 | task 148 | graphs reused = 1 1.21.804.516 I slot print_timing: id 0 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.804.552 I slot release: id 0 | task 148 | stop processing: n_tokens = 124, truncated = 0 1.21.805.099 I slot print_timing: id 1 | task 150 | prompt eval time = 1026.93 ms / 115 tokens ( 8.93 ms per token, 111.98 tokens per second) 1.21.805.102 I slot print_timing: id 1 | task 150 | eval time = 55.56 ms / 2 tokens ( 55.56 ms per token, 18.00 tokens per second) 1.21.805.103 I slot print_timing: id 1 | task 150 | total time = 1082.49 ms / 117 tokens 1.21.805.103 I slot print_timing: id 1 | task 150 | graphs reused = 1 1.21.805.104 I slot print_timing: id 1 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.805.134 I slot release: id 1 | task 150 | stop processing: n_tokens = 116, truncated = 0 1.21.805.555 I slot print_timing: id 2 | task 149 | prompt eval time = 1028.20 ms / 115 tokens ( 8.94 ms per token, 111.85 tokens per second) 1.21.805.558 I slot print_timing: id 2 | task 149 | eval time = 54.74 ms / 2 tokens ( 54.74 ms per token, 18.27 tokens per second) 1.21.805.559 I slot print_timing: id 2 | task 149 | total time = 1082.94 ms / 117 tokens 1.21.805.559 I slot print_timing: id 2 | task 149 | graphs reused = 1 1.21.805.560 I slot print_timing: id 2 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.805.604 I slot release: id 2 | task 149 | stop processing: n_tokens = 116, truncated = 0 1.21.805.834 I slot print_timing: id 3 | task 151 | prompt eval time = 1029.41 ms / 123 tokens ( 8.37 ms per token, 119.49 tokens per second) 1.21.805.837 I slot print_timing: id 3 | task 151 | eval time = 53.79 ms / 2 tokens ( 53.79 ms per token, 18.59 tokens per second) 1.21.805.838 I slot print_timing: id 3 | task 151 | total time = 1083.20 ms / 125 tokens 1.21.805.838 I slot print_timing: id 3 | task 151 | graphs reused = 1 1.21.805.839 I slot print_timing: id 3 | task 151 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.805.924 I slot release: id 3 | task 151 | stop processing: n_tokens = 124, truncated = 0 1.21.811.948 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.276 1.21.828.244 I slot launch_slot_: id 1 | task 155 | processing task, is_child = 0 1.21.849.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.973 MiB) 1.21.897.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.186 MiB) 1.21.909.251 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 1.22.093.334 I slot launch_slot_: id 0 | task 156 | processing task, is_child = 0 1.22.093.412 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.241 1.22.093.452 I slot launch_slot_: id 2 | task 157 | processing task, is_child = 0 1.22.093.470 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.226 1.22.093.508 I slot launch_slot_: id 3 | task 158 | processing task, is_child = 0 1.23.454.003 I slot print_timing: id 0 | task 156 | prompt eval time = 1307.38 ms / 128 tokens ( 10.21 ms per token, 97.91 tokens per second) 1.23.454.010 I slot print_timing: id 0 | task 156 | eval time = 53.10 ms / 2 tokens ( 53.10 ms per token, 18.83 tokens per second) 1.23.454.010 I slot print_timing: id 0 | task 156 | total time = 1360.48 ms / 130 tokens 1.23.454.011 I slot print_timing: id 0 | task 156 | graphs reused = 1 1.23.454.011 I slot print_timing: id 0 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.454.132 I slot release: id 0 | task 156 | stop processing: n_tokens = 129, truncated = 0 1.23.454.351 I slot print_timing: id 1 | task 155 | prompt eval time = 1307.38 ms / 127 tokens ( 10.29 ms per token, 97.14 tokens per second) 1.23.454.355 I slot print_timing: id 1 | task 155 | eval time = 53.10 ms / 2 tokens ( 53.10 ms per token, 18.83 tokens per second) 1.23.454.355 I slot print_timing: id 1 | task 155 | total time = 1360.49 ms / 129 tokens 1.23.454.356 I slot print_timing: id 1 | task 155 | graphs reused = 1 1.23.454.356 I slot print_timing: id 1 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.454.391 I slot release: id 1 | task 155 | stop processing: n_tokens = 128, truncated = 0 1.23.454.616 I slot print_timing: id 2 | task 157 | prompt eval time = 1307.68 ms / 141 tokens ( 9.27 ms per token, 107.82 tokens per second) 1.23.454.622 I slot print_timing: id 2 | task 157 | eval time = 53.05 ms / 2 tokens ( 53.05 ms per token, 18.85 tokens per second) 1.23.454.623 I slot print_timing: id 2 | task 157 | total time = 1360.74 ms / 143 tokens 1.23.454.623 I slot print_timing: id 2 | task 157 | graphs reused = 1 1.23.454.624 I slot print_timing: id 2 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.454.660 I slot release: id 2 | task 157 | stop processing: n_tokens = 142, truncated = 0 1.23.454.889 I slot print_timing: id 3 | task 158 | prompt eval time = 1308.06 ms / 130 tokens ( 10.06 ms per token, 99.38 tokens per second) 1.23.454.893 I slot print_timing: id 3 | task 158 | eval time = 52.94 ms / 2 tokens ( 52.94 ms per token, 18.89 tokens per second) 1.23.454.893 I slot print_timing: id 3 | task 158 | total time = 1360.99 ms / 132 tokens 1.23.454.894 I slot print_timing: id 3 | task 158 | graphs reused = 1 1.23.454.894 I slot print_timing: id 3 | task 158 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.454.908 I slot release: id 3 | task 158 | stop processing: n_tokens = 131, truncated = 0 1.23.463.183 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.227 1.23.480.346 I slot launch_slot_: id 1 | task 162 | processing task, is_child = 0 1.23.480.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.306 MiB) 1.23.590.473 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 1.23.615.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.127 MiB) 1.23.643.940 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.217 1.23.644.034 I slot launch_slot_: id 0 | task 163 | processing task, is_child = 0 1.23.644.070 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.197 1.23.644.111 I slot launch_slot_: id 2 | task 164 | processing task, is_child = 0 1.23.644.129 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.214 1.23.644.162 I slot launch_slot_: id 3 | task 165 | processing task, is_child = 0 1.25.057.091 I slot print_timing: id 0 | task 163 | prompt eval time = 1357.89 ms / 129 tokens ( 10.53 ms per token, 95.00 tokens per second) 1.25.057.096 I slot print_timing: id 0 | task 163 | eval time = 55.02 ms / 2 tokens ( 55.02 ms per token, 18.18 tokens per second) 1.25.057.097 I slot print_timing: id 0 | task 163 | total time = 1412.91 ms / 131 tokens 1.25.057.097 I slot print_timing: id 0 | task 163 | graphs reused = 1 1.25.057.098 I slot print_timing: id 0 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.057.192 I slot release: id 0 | task 163 | stop processing: n_tokens = 130, truncated = 0 1.25.057.493 I slot print_timing: id 1 | task 162 | prompt eval time = 1358.27 ms / 105 tokens ( 12.94 ms per token, 77.30 tokens per second) 1.25.057.496 I slot print_timing: id 1 | task 162 | eval time = 55.03 ms / 2 tokens ( 55.03 ms per token, 18.17 tokens per second) 1.25.057.498 I slot print_timing: id 1 | task 162 | total time = 1413.30 ms / 107 tokens 1.25.057.498 I slot print_timing: id 1 | task 162 | graphs reused = 1 1.25.057.499 I slot print_timing: id 1 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.057.567 I slot release: id 1 | task 162 | stop processing: n_tokens = 106, truncated = 0 1.25.057.863 I slot print_timing: id 2 | task 164 | prompt eval time = 1358.67 ms / 123 tokens ( 11.05 ms per token, 90.53 tokens per second) 1.25.057.870 I slot print_timing: id 2 | task 164 | eval time = 54.99 ms / 2 tokens ( 54.99 ms per token, 18.18 tokens per second) 1.25.057.870 I slot print_timing: id 2 | task 164 | total time = 1413.66 ms / 125 tokens 1.25.057.871 I slot print_timing: id 2 | task 164 | graphs reused = 1 1.25.057.871 I slot print_timing: id 2 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.057.904 I slot release: id 2 | task 164 | stop processing: n_tokens = 124, truncated = 0 1.25.058.226 I slot print_timing: id 3 | task 165 | prompt eval time = 1359.10 ms / 161 tokens ( 8.44 ms per token, 118.46 tokens per second) 1.25.058.229 I slot print_timing: id 3 | task 165 | eval time = 54.91 ms / 2 tokens ( 54.91 ms per token, 18.21 tokens per second) 1.25.058.230 I slot print_timing: id 3 | task 165 | total time = 1414.00 ms / 163 tokens 1.25.058.231 I slot print_timing: id 3 | task 165 | graphs reused = 1 1.25.058.231 I slot print_timing: id 3 | task 165 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.058.357 I slot release: id 3 | task 165 | stop processing: n_tokens = 162, truncated = 0 1.25.066.984 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.215 1.25.067.031 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.208 MiB) 1.25.222.484 I slot launch_slot_: id 0 | task 169 | processing task, is_child = 0 1.25.222.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 1.25.412.836 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.993 MiB) 1.25.812.194 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.856 MiB) 1.26.199.466 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.264 1.26.199.580 I slot launch_slot_: id 1 | task 170 | processing task, is_child = 0 1.26.199.616 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.226 1.26.210.531 I slot launch_slot_: id 2 | task 171 | processing task, is_child = 0 1.26.210.560 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 1.26.210.603 I slot launch_slot_: id 3 | task 172 | processing task, is_child = 0 1.27.693.261 I slot print_timing: id 0 | task 169 | prompt eval time = 1426.65 ms / 141 tokens ( 10.12 ms per token, 98.83 tokens per second) 1.27.693.266 I slot print_timing: id 0 | task 169 | eval time = 56.00 ms / 2 tokens ( 56.00 ms per token, 17.86 tokens per second) 1.27.693.269 I slot print_timing: id 0 | task 169 | total time = 1482.64 ms / 143 tokens 1.27.693.269 I slot print_timing: id 0 | task 169 | graphs reused = 1 1.27.693.270 I slot print_timing: id 0 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.693.337 I slot release: id 0 | task 169 | stop processing: n_tokens = 142, truncated = 0 1.27.693.629 I slot print_timing: id 1 | task 170 | prompt eval time = 1427.13 ms / 164 tokens ( 8.70 ms per token, 114.92 tokens per second) 1.27.693.636 I slot print_timing: id 1 | task 170 | eval time = 55.87 ms / 2 tokens ( 55.87 ms per token, 17.90 tokens per second) 1.27.693.637 I slot print_timing: id 1 | task 170 | total time = 1483.00 ms / 166 tokens 1.27.693.638 I slot print_timing: id 1 | task 170 | graphs reused = 1 1.27.693.638 I slot print_timing: id 1 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.693.717 I slot release: id 1 | task 170 | stop processing: n_tokens = 165, truncated = 0 1.27.694.003 I slot print_timing: id 2 | task 171 | prompt eval time = 1427.65 ms / 110 tokens ( 12.98 ms per token, 77.05 tokens per second) 1.27.694.006 I slot print_timing: id 2 | task 171 | eval time = 55.71 ms / 2 tokens ( 55.71 ms per token, 17.95 tokens per second) 1.27.694.007 I slot print_timing: id 2 | task 171 | total time = 1483.36 ms / 112 tokens 1.27.694.008 I slot print_timing: id 2 | task 171 | graphs reused = 1 1.27.694.008 I slot print_timing: id 2 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.694.073 I slot release: id 2 | task 171 | stop processing: n_tokens = 111, truncated = 0 1.27.694.359 I slot print_timing: id 3 | task 172 | prompt eval time = 1428.54 ms / 154 tokens ( 9.28 ms per token, 107.80 tokens per second) 1.27.694.362 I slot print_timing: id 3 | task 172 | eval time = 55.16 ms / 2 tokens ( 55.16 ms per token, 18.13 tokens per second) 1.27.694.363 I slot print_timing: id 3 | task 172 | total time = 1483.71 ms / 156 tokens 1.27.694.364 I slot print_timing: id 3 | task 172 | graphs reused = 1 1.27.694.364 I slot print_timing: id 3 | task 172 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.694.415 I slot release: id 3 | task 172 | stop processing: n_tokens = 155, truncated = 0 1.27.704.245 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.197 1.27.727.686 I slot launch_slot_: id 0 | task 176 | processing task, is_child = 0 1.27.727.722 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 1.27.911.485 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.423 MiB) 1.28.201.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 1.28.416.297 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.261 1.28.416.408 I slot launch_slot_: id 2 | task 177 | processing task, is_child = 0 1.28.416.449 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.170 1.28.416.490 I slot launch_slot_: id 1 | task 178 | processing task, is_child = 0 1.28.416.508 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 1.28.416.548 I slot launch_slot_: id 3 | task 179 | processing task, is_child = 0 1.29.683.465 I slot print_timing: id 0 | task 176 | prompt eval time = 1212.74 ms / 110 tokens ( 11.02 ms per token, 90.70 tokens per second) 1.29.683.473 I slot print_timing: id 0 | task 176 | eval time = 54.17 ms / 2 tokens ( 54.17 ms per token, 18.46 tokens per second) 1.29.683.475 I slot print_timing: id 0 | task 176 | total time = 1266.90 ms / 112 tokens 1.29.683.475 I slot print_timing: id 0 | task 176 | graphs reused = 1 1.29.683.476 I slot print_timing: id 0 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.683.563 I slot release: id 0 | task 176 | stop processing: n_tokens = 111, truncated = 0 1.29.683.850 I slot print_timing: id 1 | task 178 | prompt eval time = 1213.08 ms / 137 tokens ( 8.85 ms per token, 112.94 tokens per second) 1.29.683.858 I slot print_timing: id 1 | task 178 | eval time = 54.20 ms / 2 tokens ( 54.20 ms per token, 18.45 tokens per second) 1.29.683.859 I slot print_timing: id 1 | task 178 | total time = 1267.28 ms / 139 tokens 1.29.683.859 I slot print_timing: id 1 | task 178 | graphs reused = 1 1.29.683.860 I slot print_timing: id 1 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.683.917 I slot release: id 1 | task 178 | stop processing: n_tokens = 138, truncated = 0 1.29.684.246 I slot print_timing: id 2 | task 177 | prompt eval time = 1213.47 ms / 110 tokens ( 11.03 ms per token, 90.65 tokens per second) 1.29.684.252 I slot print_timing: id 2 | task 177 | eval time = 54.19 ms / 2 tokens ( 54.19 ms per token, 18.45 tokens per second) 1.29.684.253 I slot print_timing: id 2 | task 177 | total time = 1267.66 ms / 112 tokens 1.29.684.253 I slot print_timing: id 2 | task 177 | graphs reused = 1 1.29.684.254 I slot print_timing: id 2 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.684.317 I slot release: id 2 | task 177 | stop processing: n_tokens = 111, truncated = 0 1.29.684.617 I slot print_timing: id 3 | task 179 | prompt eval time = 1213.87 ms / 148 tokens ( 8.20 ms per token, 121.92 tokens per second) 1.29.684.622 I slot print_timing: id 3 | task 179 | eval time = 54.15 ms / 2 tokens ( 54.15 ms per token, 18.47 tokens per second) 1.29.684.622 I slot print_timing: id 3 | task 179 | total time = 1268.02 ms / 150 tokens 1.29.684.623 I slot print_timing: id 3 | task 179 | graphs reused = 1 1.29.684.623 I slot print_timing: id 3 | task 179 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.684.685 I slot release: id 3 | task 179 | stop processing: n_tokens = 149, truncated = 0 1.29.693.035 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.252 1.29.693.078 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.442 MiB) 1.30.039.955 I slot launch_slot_: id 0 | task 183 | processing task, is_child = 0 1.30.039.985 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.641 MiB) 1.30.411.227 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.306 MiB) 1.30.740.423 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.169 MiB) 1.30.977.633 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.203 1.30.977.729 I slot launch_slot_: id 1 | task 184 | processing task, is_child = 0 1.30.977.765 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.252 1.30.977.807 I slot launch_slot_: id 2 | task 185 | processing task, is_child = 0 1.30.977.825 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.188 1.30.988.472 I slot launch_slot_: id 3 | task 186 | processing task, is_child = 0 1.32.351.415 I slot print_timing: id 0 | task 183 | prompt eval time = 1307.47 ms / 152 tokens ( 8.60 ms per token, 116.25 tokens per second) 1.32.351.420 I slot print_timing: id 0 | task 183 | eval time = 55.45 ms / 2 tokens ( 55.45 ms per token, 18.03 tokens per second) 1.32.351.421 I slot print_timing: id 0 | task 183 | total time = 1362.92 ms / 154 tokens 1.32.351.421 I slot print_timing: id 0 | task 183 | graphs reused = 1 1.32.351.428 I slot print_timing: id 0 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.351.494 I slot release: id 0 | task 183 | stop processing: n_tokens = 153, truncated = 0 1.32.351.747 I slot print_timing: id 1 | task 184 | prompt eval time = 1307.95 ms / 130 tokens ( 10.06 ms per token, 99.39 tokens per second) 1.32.351.752 I slot print_timing: id 1 | task 184 | eval time = 55.29 ms / 2 tokens ( 55.29 ms per token, 18.09 tokens per second) 1.32.351.753 I slot print_timing: id 1 | task 184 | total time = 1363.24 ms / 132 tokens 1.32.351.753 I slot print_timing: id 1 | task 184 | graphs reused = 1 1.32.351.754 I slot print_timing: id 1 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.361.502 I slot release: id 1 | task 184 | stop processing: n_tokens = 131, truncated = 0 1.32.361.813 I slot print_timing: id 2 | task 185 | prompt eval time = 1308.50 ms / 123 tokens ( 10.64 ms per token, 94.00 tokens per second) 1.32.361.818 I slot print_timing: id 2 | task 185 | eval time = 64.79 ms / 2 tokens ( 64.79 ms per token, 15.43 tokens per second) 1.32.361.819 I slot print_timing: id 2 | task 185 | total time = 1373.29 ms / 125 tokens 1.32.361.819 I slot print_timing: id 2 | task 185 | graphs reused = 1 1.32.361.820 I slot print_timing: id 2 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.361.858 I slot release: id 2 | task 185 | stop processing: n_tokens = 124, truncated = 0 1.32.362.098 I slot print_timing: id 3 | task 186 | prompt eval time = 1309.02 ms / 112 tokens ( 11.69 ms per token, 85.56 tokens per second) 1.32.362.102 I slot print_timing: id 3 | task 186 | eval time = 64.55 ms / 2 tokens ( 64.55 ms per token, 15.49 tokens per second) 1.32.362.103 I slot print_timing: id 3 | task 186 | total time = 1373.57 ms / 114 tokens 1.32.362.103 I slot print_timing: id 3 | task 186 | graphs reused = 1 1.32.362.104 I slot print_timing: id 3 | task 186 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.362.157 I slot release: id 3 | task 186 | stop processing: n_tokens = 113, truncated = 0 1.32.363.394 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.257 1.32.378.352 I slot launch_slot_: id 3 | task 190 | processing task, is_child = 0 1.32.378.392 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.227 MiB) 1.32.553.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.205 MiB) 1.32.782.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.107 MiB) 1.33.080.743 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.183 1.33.080.855 I slot launch_slot_: id 0 | task 191 | processing task, is_child = 0 1.33.080.892 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.214 1.33.080.932 I slot launch_slot_: id 1 | task 192 | processing task, is_child = 0 1.33.080.950 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.226 1.33.080.988 I slot launch_slot_: id 2 | task 193 | processing task, is_child = 0 1.34.509.925 I slot print_timing: id 0 | task 191 | prompt eval time = 1374.88 ms / 157 tokens ( 8.76 ms per token, 114.19 tokens per second) 1.34.509.930 I slot print_timing: id 0 | task 191 | eval time = 54.05 ms / 2 tokens ( 54.05 ms per token, 18.50 tokens per second) 1.34.509.931 I slot print_timing: id 0 | task 191 | total time = 1428.92 ms / 159 tokens 1.34.509.932 I slot print_timing: id 0 | task 191 | graphs reused = 1 1.34.509.932 I slot print_timing: id 0 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.510.837 I slot release: id 0 | task 191 | stop processing: n_tokens = 158, truncated = 0 1.34.511.097 I slot print_timing: id 1 | task 192 | prompt eval time = 1375.28 ms / 166 tokens ( 8.28 ms per token, 120.70 tokens per second) 1.34.511.103 I slot print_timing: id 1 | task 192 | eval time = 54.80 ms / 2 tokens ( 54.80 ms per token, 18.25 tokens per second) 1.34.511.104 I slot print_timing: id 1 | task 192 | total time = 1430.08 ms / 168 tokens 1.34.511.105 I slot print_timing: id 1 | task 192 | graphs reused = 1 1.34.511.109 I slot print_timing: id 1 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.511.212 I slot release: id 1 | task 192 | stop processing: n_tokens = 167, truncated = 0 1.34.511.465 I slot print_timing: id 2 | task 193 | prompt eval time = 1375.69 ms / 128 tokens ( 10.75 ms per token, 93.04 tokens per second) 1.34.511.469 I slot print_timing: id 2 | task 193 | eval time = 54.74 ms / 2 tokens ( 54.74 ms per token, 18.27 tokens per second) 1.34.511.470 I slot print_timing: id 2 | task 193 | total time = 1430.43 ms / 130 tokens 1.34.511.470 I slot print_timing: id 2 | task 193 | graphs reused = 1 1.34.511.471 I slot print_timing: id 2 | task 193 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.511.553 I slot release: id 2 | task 193 | stop processing: n_tokens = 129, truncated = 0 1.34.511.816 I slot print_timing: id 3 | task 190 | prompt eval time = 1376.13 ms / 114 tokens ( 12.07 ms per token, 82.84 tokens per second) 1.34.511.820 I slot print_timing: id 3 | task 190 | eval time = 54.65 ms / 2 tokens ( 54.65 ms per token, 18.30 tokens per second) 1.34.511.821 I slot print_timing: id 3 | task 190 | total time = 1430.78 ms / 116 tokens 1.34.511.821 I slot print_timing: id 3 | task 190 | graphs reused = 1 1.34.511.822 I slot print_timing: id 3 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.512.186 I slot release: id 3 | task 190 | stop processing: n_tokens = 115, truncated = 0 1.34.520.129 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.177 1.34.520.174 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.892 MiB) 1.34.878.444 I slot launch_slot_: id 0 | task 197 | processing task, is_child = 0 1.34.878.478 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.951 MiB) 1.35.055.486 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 1.35.196.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.560 MiB) 1.35.391.865 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.168 1.35.402.493 I slot launch_slot_: id 1 | task 198 | processing task, is_child = 0 1.35.402.538 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.217 1.35.402.585 I slot launch_slot_: id 2 | task 199 | processing task, is_child = 0 1.35.402.605 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.243 1.35.402.662 I slot launch_slot_: id 3 | task 200 | processing task, is_child = 0 1.36.939.356 I slot print_timing: id 0 | task 197 | prompt eval time = 1481.94 ms / 108 tokens ( 13.72 ms per token, 72.88 tokens per second) 1.36.939.363 I slot print_timing: id 0 | task 197 | eval time = 54.73 ms / 2 tokens ( 54.73 ms per token, 18.27 tokens per second) 1.36.939.364 I slot print_timing: id 0 | task 197 | total time = 1536.68 ms / 110 tokens 1.36.939.364 I slot print_timing: id 0 | task 197 | graphs reused = 1 1.36.939.365 I slot print_timing: id 0 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.939.415 I slot release: id 0 | task 197 | stop processing: n_tokens = 109, truncated = 0 1.36.939.665 I slot print_timing: id 1 | task 198 | prompt eval time = 1482.40 ms / 141 tokens ( 10.51 ms per token, 95.12 tokens per second) 1.36.939.668 I slot print_timing: id 1 | task 198 | eval time = 54.57 ms / 2 tokens ( 54.57 ms per token, 18.33 tokens per second) 1.36.939.669 I slot print_timing: id 1 | task 198 | total time = 1536.97 ms / 143 tokens 1.36.939.669 I slot print_timing: id 1 | task 198 | graphs reused = 1 1.36.939.670 I slot print_timing: id 1 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.939.718 I slot release: id 1 | task 198 | stop processing: n_tokens = 142, truncated = 0 1.36.939.975 I slot print_timing: id 2 | task 199 | prompt eval time = 1483.09 ms / 179 tokens ( 8.29 ms per token, 120.69 tokens per second) 1.36.939.978 I slot print_timing: id 2 | task 199 | eval time = 54.18 ms / 2 tokens ( 54.18 ms per token, 18.46 tokens per second) 1.36.939.979 I slot print_timing: id 2 | task 199 | total time = 1537.27 ms / 181 tokens 1.36.939.979 I slot print_timing: id 2 | task 199 | graphs reused = 1 1.36.939.980 I slot print_timing: id 2 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.940.853 I slot release: id 2 | task 199 | stop processing: n_tokens = 180, truncated = 0 1.36.941.102 I slot print_timing: id 3 | task 200 | prompt eval time = 1483.69 ms / 153 tokens ( 9.70 ms per token, 103.12 tokens per second) 1.36.941.106 I slot print_timing: id 3 | task 200 | eval time = 54.68 ms / 2 tokens ( 54.68 ms per token, 18.29 tokens per second) 1.36.941.107 I slot print_timing: id 3 | task 200 | total time = 1538.37 ms / 155 tokens 1.36.941.107 I slot print_timing: id 3 | task 200 | graphs reused = 1 1.36.941.108 I slot print_timing: id 3 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.941.147 I slot release: id 3 | task 200 | stop processing: n_tokens = 154, truncated = 0 1.36.949.459 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.257 1.36.961.959 I slot launch_slot_: id 0 | task 204 | processing task, is_child = 0 1.37.100.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.384 MiB) 1.37.332.638 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.149 MiB) 1.37.548.130 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.197 1.37.548.467 I slot launch_slot_: id 1 | task 205 | processing task, is_child = 0 1.37.548.512 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.156 1.37.548.555 I slot launch_slot_: id 2 | task 206 | processing task, is_child = 0 1.37.548.573 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.182 1.37.548.614 I slot launch_slot_: id 3 | task 207 | processing task, is_child = 0 1.38.934.078 I slot print_timing: id 0 | task 204 | prompt eval time = 1329.55 ms / 116 tokens ( 11.46 ms per token, 87.25 tokens per second) 1.38.934.083 I slot print_timing: id 0 | task 204 | eval time = 55.90 ms / 2 tokens ( 55.90 ms per token, 17.89 tokens per second) 1.38.934.083 I slot print_timing: id 0 | task 204 | total time = 1385.45 ms / 118 tokens 1.38.934.084 I slot print_timing: id 0 | task 204 | graphs reused = 1 1.38.934.084 I slot print_timing: id 0 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.934.280 I slot release: id 0 | task 204 | stop processing: n_tokens = 117, truncated = 0 1.38.934.496 I slot print_timing: id 1 | task 205 | prompt eval time = 1329.90 ms / 134 tokens ( 9.92 ms per token, 100.76 tokens per second) 1.38.934.499 I slot print_timing: id 1 | task 205 | eval time = 55.95 ms / 2 tokens ( 55.95 ms per token, 17.87 tokens per second) 1.38.934.500 I slot print_timing: id 1 | task 205 | total time = 1385.85 ms / 136 tokens 1.38.934.500 I slot print_timing: id 1 | task 205 | graphs reused = 1 1.38.934.500 I slot print_timing: id 1 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.934.577 I slot release: id 1 | task 205 | stop processing: n_tokens = 135, truncated = 0 1.38.934.982 I slot print_timing: id 2 | task 206 | prompt eval time = 1331.37 ms / 135 tokens ( 9.86 ms per token, 101.40 tokens per second) 1.38.934.988 I slot print_timing: id 2 | task 206 | eval time = 54.95 ms / 2 tokens ( 54.95 ms per token, 18.20 tokens per second) 1.38.934.988 I slot print_timing: id 2 | task 206 | total time = 1386.31 ms / 137 tokens 1.38.934.989 I slot print_timing: id 2 | task 206 | graphs reused = 1 1.38.934.989 I slot print_timing: id 2 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.935.465 I slot release: id 2 | task 206 | stop processing: n_tokens = 136, truncated = 0 1.38.935.720 I slot print_timing: id 3 | task 207 | prompt eval time = 1331.79 ms / 158 tokens ( 8.43 ms per token, 118.64 tokens per second) 1.38.935.734 I slot print_timing: id 3 | task 207 | eval time = 55.24 ms / 2 tokens ( 55.24 ms per token, 18.10 tokens per second) 1.38.935.737 I slot print_timing: id 3 | task 207 | total time = 1387.03 ms / 160 tokens 1.38.935.738 I slot print_timing: id 3 | task 207 | graphs reused = 1 1.38.935.738 I slot print_timing: id 3 | task 207 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.935.808 I slot release: id 3 | task 207 | stop processing: n_tokens = 159, truncated = 0 1.38.948.406 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.248 1.38.948.444 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.794 MiB) 1.39.201.042 I slot launch_slot_: id 0 | task 211 | processing task, is_child = 0 1.39.216.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.834 MiB) 1.39.406.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.912 MiB) 1.39.608.696 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.207 1.39.610.241 I slot launch_slot_: id 1 | task 212 | processing task, is_child = 0 1.39.610.283 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 1.39.610.326 I slot launch_slot_: id 2 | task 213 | processing task, is_child = 0 1.39.610.344 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 1.39.610.381 I slot launch_slot_: id 3 | task 214 | processing task, is_child = 0 1.40.923.382 I slot print_timing: id 0 | task 211 | prompt eval time = 1259.51 ms / 122 tokens ( 10.32 ms per token, 96.86 tokens per second) 1.40.923.386 I slot print_timing: id 0 | task 211 | eval time = 53.48 ms / 2 tokens ( 53.48 ms per token, 18.70 tokens per second) 1.40.923.386 I slot print_timing: id 0 | task 211 | total time = 1312.99 ms / 124 tokens 1.40.923.387 I slot print_timing: id 0 | task 211 | graphs reused = 1 1.40.923.388 I slot print_timing: id 0 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.923.567 I slot release: id 0 | task 211 | stop processing: n_tokens = 123, truncated = 0 1.40.923.793 I slot print_timing: id 1 | task 212 | prompt eval time = 1259.98 ms / 117 tokens ( 10.77 ms per token, 92.86 tokens per second) 1.40.923.795 I slot print_timing: id 1 | task 212 | eval time = 53.41 ms / 2 tokens ( 53.41 ms per token, 18.72 tokens per second) 1.40.923.797 I slot print_timing: id 1 | task 212 | total time = 1313.39 ms / 119 tokens 1.40.923.797 I slot print_timing: id 1 | task 212 | graphs reused = 1 1.40.923.798 I slot print_timing: id 1 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.923.827 I slot release: id 1 | task 212 | stop processing: n_tokens = 118, truncated = 0 1.40.924.064 I slot print_timing: id 2 | task 213 | prompt eval time = 1260.29 ms / 149 tokens ( 8.46 ms per token, 118.23 tokens per second) 1.40.924.067 I slot print_timing: id 2 | task 213 | eval time = 53.35 ms / 2 tokens ( 53.35 ms per token, 18.74 tokens per second) 1.40.924.068 I slot print_timing: id 2 | task 213 | total time = 1313.64 ms / 151 tokens 1.40.924.068 I slot print_timing: id 2 | task 213 | graphs reused = 1 1.40.924.069 I slot print_timing: id 2 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.924.148 I slot release: id 2 | task 213 | stop processing: n_tokens = 150, truncated = 0 1.40.924.395 I slot print_timing: id 3 | task 214 | prompt eval time = 1260.62 ms / 157 tokens ( 8.03 ms per token, 124.54 tokens per second) 1.40.924.400 I slot print_timing: id 3 | task 214 | eval time = 53.34 ms / 2 tokens ( 53.34 ms per token, 18.75 tokens per second) 1.40.924.401 I slot print_timing: id 3 | task 214 | total time = 1313.96 ms / 159 tokens 1.40.924.401 I slot print_timing: id 3 | task 214 | graphs reused = 1 1.40.924.401 I slot print_timing: id 3 | task 214 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.924.533 I slot release: id 3 | task 214 | stop processing: n_tokens = 158, truncated = 0 1.40.944.513 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.228 1.40.950.840 I slot launch_slot_: id 0 | task 218 | processing task, is_child = 0 1.40.950.878 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.853 MiB) 1.41.215.895 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.521 MiB) 1.41.261.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.208 MiB) 1.41.382.915 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.237 1.41.383.024 I slot launch_slot_: id 1 | task 219 | processing task, is_child = 0 1.41.383.070 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.187 1.41.383.110 I slot launch_slot_: id 2 | task 220 | processing task, is_child = 0 1.41.383.129 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.177 1.41.383.169 I slot launch_slot_: id 3 | task 221 | processing task, is_child = 0 1.42.826.502 I slot print_timing: id 0 | task 218 | prompt eval time = 1388.23 ms / 155 tokens ( 8.96 ms per token, 111.65 tokens per second) 1.42.826.506 I slot print_timing: id 0 | task 218 | eval time = 55.09 ms / 2 tokens ( 55.09 ms per token, 18.15 tokens per second) 1.42.826.507 I slot print_timing: id 0 | task 218 | total time = 1443.32 ms / 157 tokens 1.42.826.507 I slot print_timing: id 0 | task 218 | graphs reused = 1 1.42.826.508 I slot print_timing: id 0 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.827.855 I slot release: id 0 | task 218 | stop processing: n_tokens = 156, truncated = 0 1.42.828.112 I slot print_timing: id 1 | task 219 | prompt eval time = 1388.61 ms / 154 tokens ( 9.02 ms per token, 110.90 tokens per second) 1.42.828.118 I slot print_timing: id 1 | task 219 | eval time = 56.30 ms / 2 tokens ( 56.30 ms per token, 17.76 tokens per second) 1.42.828.119 I slot print_timing: id 1 | task 219 | total time = 1444.92 ms / 156 tokens 1.42.828.119 I slot print_timing: id 1 | task 219 | graphs reused = 1 1.42.828.120 I slot print_timing: id 1 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.828.246 I slot release: id 1 | task 219 | stop processing: n_tokens = 155, truncated = 0 1.42.828.521 I slot print_timing: id 2 | task 220 | prompt eval time = 1389.23 ms / 149 tokens ( 9.32 ms per token, 107.25 tokens per second) 1.42.828.525 I slot print_timing: id 2 | task 220 | eval time = 56.08 ms / 2 tokens ( 56.08 ms per token, 17.83 tokens per second) 1.42.828.526 I slot print_timing: id 2 | task 220 | total time = 1445.31 ms / 151 tokens 1.42.828.527 I slot print_timing: id 2 | task 220 | graphs reused = 1 1.42.828.527 I slot print_timing: id 2 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.828.573 I slot release: id 2 | task 220 | stop processing: n_tokens = 150, truncated = 0 1.42.828.832 I slot print_timing: id 3 | task 221 | prompt eval time = 1390.43 ms / 160 tokens ( 8.69 ms per token, 115.07 tokens per second) 1.42.828.836 I slot print_timing: id 3 | task 221 | eval time = 55.18 ms / 2 tokens ( 55.18 ms per token, 18.12 tokens per second) 1.42.828.836 I slot print_timing: id 3 | task 221 | total time = 1445.61 ms / 162 tokens 1.42.828.845 I slot print_timing: id 3 | task 221 | graphs reused = 1 1.42.828.845 I slot print_timing: id 3 | task 221 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.828.898 I slot release: id 3 | task 221 | stop processing: n_tokens = 161, truncated = 0 1.42.842.940 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.179 1.42.842.994 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 1.43.058.511 I slot launch_slot_: id 0 | task 225 | processing task, is_child = 0 1.43.058.556 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.993 MiB) 1.43.276.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 1.43.571.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.071 MiB) 1.43.610.411 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.181 1.43.612.340 I slot launch_slot_: id 1 | task 226 | processing task, is_child = 0 1.43.612.404 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.187 1.43.612.479 I slot launch_slot_: id 2 | task 227 | processing task, is_child = 0 1.43.612.499 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.174 1.43.612.544 I slot launch_slot_: id 3 | task 228 | processing task, is_child = 0 1.44.976.595 I slot print_timing: id 0 | task 225 | prompt eval time = 1310.04 ms / 107 tokens ( 12.24 ms per token, 81.68 tokens per second) 1.44.976.599 I slot print_timing: id 0 | task 225 | eval time = 54.00 ms / 2 tokens ( 54.00 ms per token, 18.52 tokens per second) 1.44.976.605 I slot print_timing: id 0 | task 225 | total time = 1364.04 ms / 109 tokens 1.44.976.606 I slot print_timing: id 0 | task 225 | graphs reused = 1 1.44.976.607 I slot print_timing: id 0 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.976.790 I slot release: id 0 | task 225 | stop processing: n_tokens = 108, truncated = 0 1.44.977.013 I slot print_timing: id 1 | task 226 | prompt eval time = 1310.61 ms / 102 tokens ( 12.85 ms per token, 77.83 tokens per second) 1.44.977.017 I slot print_timing: id 1 | task 226 | eval time = 53.83 ms / 2 tokens ( 53.83 ms per token, 18.58 tokens per second) 1.44.977.017 I slot print_timing: id 1 | task 226 | total time = 1364.44 ms / 104 tokens 1.44.977.018 I slot print_timing: id 1 | task 226 | graphs reused = 1 1.44.977.018 I slot print_timing: id 1 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.978.410 I slot release: id 1 | task 226 | stop processing: n_tokens = 103, truncated = 0 1.44.978.679 I slot print_timing: id 2 | task 227 | prompt eval time = 1310.94 ms / 114 tokens ( 11.50 ms per token, 86.96 tokens per second) 1.44.978.687 I slot print_timing: id 2 | task 227 | eval time = 55.15 ms / 2 tokens ( 55.15 ms per token, 18.13 tokens per second) 1.44.978.688 I slot print_timing: id 2 | task 227 | total time = 1366.09 ms / 116 tokens 1.44.978.688 I slot print_timing: id 2 | task 227 | graphs reused = 1 1.44.978.689 I slot print_timing: id 2 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.979.557 I slot release: id 2 | task 227 | stop processing: n_tokens = 115, truncated = 0 1.44.979.784 I slot print_timing: id 3 | task 228 | prompt eval time = 1311.29 ms / 185 tokens ( 7.09 ms per token, 141.08 tokens per second) 1.44.979.788 I slot print_timing: id 3 | task 228 | eval time = 55.89 ms / 2 tokens ( 55.89 ms per token, 17.89 tokens per second) 1.44.979.789 I slot print_timing: id 3 | task 228 | total time = 1367.18 ms / 187 tokens 1.44.979.789 I slot print_timing: id 3 | task 228 | graphs reused = 1 1.44.979.789 I slot print_timing: id 3 | task 228 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.979.857 I slot release: id 3 | task 228 | stop processing: n_tokens = 186, truncated = 0 1.44.989.204 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 1.45.132.194 I slot launch_slot_: id 1 | task 232 | processing task, is_child = 0 1.45.132.220 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.208 MiB) 1.45.375.337 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 1.45.621.585 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.954 MiB) 1.45.938.010 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.259 1.45.938.110 I slot launch_slot_: id 0 | task 233 | processing task, is_child = 0 1.45.938.148 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.243 1.45.938.191 I slot launch_slot_: id 2 | task 234 | processing task, is_child = 0 1.45.938.210 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 1.45.938.252 I slot launch_slot_: id 3 | task 235 | processing task, is_child = 0 1.47.322.130 I slot print_timing: id 0 | task 233 | prompt eval time = 1328.23 ms / 126 tokens ( 10.54 ms per token, 94.86 tokens per second) 1.47.322.135 I slot print_timing: id 0 | task 233 | eval time = 55.63 ms / 2 tokens ( 55.63 ms per token, 17.98 tokens per second) 1.47.322.137 I slot print_timing: id 0 | task 233 | total time = 1383.86 ms / 128 tokens 1.47.322.137 I slot print_timing: id 0 | task 233 | graphs reused = 1 1.47.322.138 I slot print_timing: id 0 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.322.413 I slot release: id 0 | task 233 | stop processing: n_tokens = 127, truncated = 0 1.47.322.696 I slot print_timing: id 1 | task 232 | prompt eval time = 1328.63 ms / 110 tokens ( 12.08 ms per token, 82.79 tokens per second) 1.47.322.701 I slot print_timing: id 1 | task 232 | eval time = 55.77 ms / 2 tokens ( 55.77 ms per token, 17.93 tokens per second) 1.47.322.702 I slot print_timing: id 1 | task 232 | total time = 1384.41 ms / 112 tokens 1.47.322.703 I slot print_timing: id 1 | task 232 | graphs reused = 1 1.47.322.703 I slot print_timing: id 1 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.322.776 I slot release: id 1 | task 232 | stop processing: n_tokens = 111, truncated = 0 1.47.323.031 I slot print_timing: id 2 | task 234 | prompt eval time = 1329.93 ms / 122 tokens ( 10.90 ms per token, 91.73 tokens per second) 1.47.323.036 I slot print_timing: id 2 | task 234 | eval time = 54.80 ms / 2 tokens ( 54.80 ms per token, 18.25 tokens per second) 1.47.323.042 I slot print_timing: id 2 | task 234 | total time = 1384.73 ms / 124 tokens 1.47.323.043 I slot print_timing: id 2 | task 234 | graphs reused = 1 1.47.323.043 I slot print_timing: id 2 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.323.098 I slot release: id 2 | task 234 | stop processing: n_tokens = 123, truncated = 0 1.47.323.351 I slot print_timing: id 3 | task 235 | prompt eval time = 1330.55 ms / 164 tokens ( 8.11 ms per token, 123.26 tokens per second) 1.47.323.353 I slot print_timing: id 3 | task 235 | eval time = 54.49 ms / 2 tokens ( 54.49 ms per token, 18.35 tokens per second) 1.47.323.354 I slot print_timing: id 3 | task 235 | total time = 1385.04 ms / 166 tokens 1.47.323.360 I slot print_timing: id 3 | task 235 | graphs reused = 1 1.47.323.364 I slot print_timing: id 3 | task 235 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.323.435 I slot release: id 3 | task 235 | stop processing: n_tokens = 165, truncated = 0 1.47.335.462 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.261 1.47.335.543 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.012 MiB) 1.47.756.201 I slot launch_slot_: id 1 | task 240 | processing task, is_child = 0 1.47.756.230 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.010 MiB) 1.48.162.787 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.107 MiB) 1.48.435.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.306 MiB) 1.48.639.457 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.220 1.48.654.373 I slot launch_slot_: id 0 | task 239 | processing task, is_child = 0 1.48.654.432 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.228 1.48.654.473 I slot launch_slot_: id 2 | task 241 | processing task, is_child = 0 1.48.654.495 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.170 1.48.654.536 I slot launch_slot_: id 3 | task 242 | processing task, is_child = 0 1.49.918.790 I slot print_timing: id 0 | task 239 | prompt eval time = 1209.85 ms / 137 tokens ( 8.83 ms per token, 113.24 tokens per second) 1.49.918.794 I slot print_timing: id 0 | task 239 | eval time = 54.39 ms / 2 tokens ( 54.39 ms per token, 18.38 tokens per second) 1.49.918.795 I slot print_timing: id 0 | task 239 | total time = 1264.24 ms / 139 tokens 1.49.918.796 I slot print_timing: id 0 | task 239 | graphs reused = 1 1.49.918.796 I slot print_timing: id 0 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.919.543 I slot release: id 0 | task 239 | stop processing: n_tokens = 138, truncated = 0 1.49.919.774 I slot print_timing: id 1 | task 240 | prompt eval time = 1210.89 ms / 138 tokens ( 8.77 ms per token, 113.97 tokens per second) 1.49.919.777 I slot print_timing: id 1 | task 240 | eval time = 54.31 ms / 2 tokens ( 54.31 ms per token, 18.41 tokens per second) 1.49.919.778 I slot print_timing: id 1 | task 240 | total time = 1265.20 ms / 140 tokens 1.49.919.779 I slot print_timing: id 1 | task 240 | graphs reused = 1 1.49.919.779 I slot print_timing: id 1 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.920.660 I slot release: id 1 | task 240 | stop processing: n_tokens = 139, truncated = 0 1.49.920.886 I slot print_timing: id 2 | task 241 | prompt eval time = 1211.41 ms / 122 tokens ( 9.93 ms per token, 100.71 tokens per second) 1.49.920.892 I slot print_timing: id 2 | task 241 | eval time = 54.89 ms / 2 tokens ( 54.89 ms per token, 18.22 tokens per second) 1.49.920.893 I slot print_timing: id 2 | task 241 | total time = 1266.30 ms / 124 tokens 1.49.920.893 I slot print_timing: id 2 | task 241 | graphs reused = 1 1.49.920.894 I slot print_timing: id 2 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.920.929 I slot release: id 2 | task 241 | stop processing: n_tokens = 123, truncated = 0 1.49.921.158 I slot print_timing: id 3 | task 242 | prompt eval time = 1211.94 ms / 125 tokens ( 9.70 ms per token, 103.14 tokens per second) 1.49.921.161 I slot print_timing: id 3 | task 242 | eval time = 54.62 ms / 2 tokens ( 54.62 ms per token, 18.31 tokens per second) 1.49.921.162 I slot print_timing: id 3 | task 242 | total time = 1266.56 ms / 127 tokens 1.49.921.162 I slot print_timing: id 3 | task 242 | graphs reused = 1 1.49.921.163 I slot print_timing: id 3 | task 242 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.921.193 I slot release: id 3 | task 242 | stop processing: n_tokens = 126, truncated = 0 1.49.931.004 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.203 1.50.074.898 I slot launch_slot_: id 0 | task 246 | processing task, is_child = 0 1.50.105.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.339 MiB) 1.50.331.397 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.423 MiB) 1.50.494.831 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.201 1.50.494.926 I slot launch_slot_: id 1 | task 247 | processing task, is_child = 0 1.50.494.964 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.228 1.50.495.007 I slot launch_slot_: id 2 | task 248 | processing task, is_child = 0 1.50.495.027 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.222 1.50.495.064 I slot launch_slot_: id 3 | task 249 | processing task, is_child = 0 1.52.204.389 I slot print_timing: id 0 | task 246 | prompt eval time = 1656.09 ms / 158 tokens ( 10.48 ms per token, 95.41 tokens per second) 1.52.204.393 I slot print_timing: id 0 | task 246 | eval time = 53.22 ms / 2 tokens ( 53.22 ms per token, 18.79 tokens per second) 1.52.204.393 I slot print_timing: id 0 | task 246 | total time = 1709.31 ms / 160 tokens 1.52.204.394 I slot print_timing: id 0 | task 246 | graphs reused = 1 1.52.204.395 I slot print_timing: id 0 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.204.493 I slot release: id 0 | task 246 | stop processing: n_tokens = 159, truncated = 0 1.52.204.708 I slot print_timing: id 1 | task 247 | prompt eval time = 1656.30 ms / 120 tokens ( 13.80 ms per token, 72.45 tokens per second) 1.52.204.712 I slot print_timing: id 1 | task 247 | eval time = 53.32 ms / 2 tokens ( 53.32 ms per token, 18.76 tokens per second) 1.52.204.718 I slot print_timing: id 1 | task 247 | total time = 1709.62 ms / 122 tokens 1.52.204.718 I slot print_timing: id 1 | task 247 | graphs reused = 1 1.52.204.719 I slot print_timing: id 1 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.204.764 I slot release: id 1 | task 247 | stop processing: n_tokens = 121, truncated = 0 1.52.204.979 I slot print_timing: id 2 | task 248 | prompt eval time = 1656.79 ms / 140 tokens ( 11.83 ms per token, 84.50 tokens per second) 1.52.204.981 I slot print_timing: id 2 | task 248 | eval time = 53.08 ms / 2 tokens ( 53.08 ms per token, 18.84 tokens per second) 1.52.204.982 I slot print_timing: id 2 | task 248 | total time = 1709.88 ms / 142 tokens 1.52.204.982 I slot print_timing: id 2 | task 248 | graphs reused = 1 1.52.204.983 I slot print_timing: id 2 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.205.019 I slot release: id 2 | task 248 | stop processing: n_tokens = 141, truncated = 0 1.52.205.258 I slot print_timing: id 3 | task 249 | prompt eval time = 1657.41 ms / 168 tokens ( 9.87 ms per token, 101.36 tokens per second) 1.52.205.264 I slot print_timing: id 3 | task 249 | eval time = 52.74 ms / 2 tokens ( 52.74 ms per token, 18.96 tokens per second) 1.52.205.265 I slot print_timing: id 3 | task 249 | total time = 1710.15 ms / 170 tokens 1.52.205.265 I slot print_timing: id 3 | task 249 | graphs reused = 1 1.52.205.265 I slot print_timing: id 3 | task 249 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.206.876 I slot release: id 3 | task 249 | stop processing: n_tokens = 169, truncated = 0 1.52.213.568 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.176 1.52.213.605 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.775 MiB) 1.52.367.341 I slot launch_slot_: id 0 | task 253 | processing task, is_child = 0 1.52.375.300 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.677 MiB) 1.52.665.204 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.065 MiB) 1.52.825.360 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.231 1.52.825.441 I slot launch_slot_: id 1 | task 254 | processing task, is_child = 0 1.52.825.477 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 1.52.825.513 I slot launch_slot_: id 2 | task 255 | processing task, is_child = 0 1.52.825.531 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 1.52.825.570 I slot launch_slot_: id 3 | task 256 | processing task, is_child = 0 1.54.363.895 I slot print_timing: id 0 | task 253 | prompt eval time = 1484.63 ms / 133 tokens ( 11.16 ms per token, 89.58 tokens per second) 1.54.363.899 I slot print_timing: id 0 | task 253 | eval time = 53.68 ms / 2 tokens ( 53.68 ms per token, 18.63 tokens per second) 1.54.363.900 I slot print_timing: id 0 | task 253 | total time = 1538.31 ms / 135 tokens 1.54.363.900 I slot print_timing: id 0 | task 253 | graphs reused = 1 1.54.363.901 I slot print_timing: id 0 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.363.928 I slot release: id 0 | task 253 | stop processing: n_tokens = 134, truncated = 0 1.54.364.178 I slot print_timing: id 1 | task 254 | prompt eval time = 1484.89 ms / 103 tokens ( 14.42 ms per token, 69.37 tokens per second) 1.54.364.182 I slot print_timing: id 1 | task 254 | eval time = 53.69 ms / 2 tokens ( 53.69 ms per token, 18.63 tokens per second) 1.54.364.183 I slot print_timing: id 1 | task 254 | total time = 1538.57 ms / 105 tokens 1.54.364.184 I slot print_timing: id 1 | task 254 | graphs reused = 1 1.54.364.185 I slot print_timing: id 1 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.364.229 I slot release: id 1 | task 254 | stop processing: n_tokens = 104, truncated = 0 1.54.364.475 I slot print_timing: id 2 | task 255 | prompt eval time = 1485.17 ms / 182 tokens ( 8.16 ms per token, 122.55 tokens per second) 1.54.364.484 I slot print_timing: id 2 | task 255 | eval time = 53.69 ms / 2 tokens ( 53.69 ms per token, 18.62 tokens per second) 1.54.364.484 I slot print_timing: id 2 | task 255 | total time = 1538.86 ms / 184 tokens 1.54.364.485 I slot print_timing: id 2 | task 255 | graphs reused = 1 1.54.364.485 I slot print_timing: id 2 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.364.534 I slot release: id 2 | task 255 | stop processing: n_tokens = 183, truncated = 0 1.54.364.785 I slot print_timing: id 3 | task 256 | prompt eval time = 1485.46 ms / 155 tokens ( 9.58 ms per token, 104.35 tokens per second) 1.54.364.788 I slot print_timing: id 3 | task 256 | eval time = 53.70 ms / 2 tokens ( 53.70 ms per token, 18.62 tokens per second) 1.54.364.789 I slot print_timing: id 3 | task 256 | total time = 1539.16 ms / 157 tokens 1.54.364.789 I slot print_timing: id 3 | task 256 | graphs reused = 1 1.54.364.790 I slot print_timing: id 3 | task 256 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.366.569 I slot release: id 3 | task 256 | stop processing: n_tokens = 156, truncated = 0 1.54.373.510 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.209 1.54.373.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 1.54.576.363 I slot launch_slot_: id 0 | task 260 | processing task, is_child = 0 1.54.576.389 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.401 MiB) 1.54.835.547 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.286 MiB) 1.55.016.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.010 MiB) 1.55.379.961 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.269 1.55.380.425 I slot launch_slot_: id 1 | task 261 | processing task, is_child = 0 1.56.146.954 I slot print_timing: id 0 | task 260 | prompt eval time = 730.22 ms / 144 tokens ( 5.07 ms per token, 197.20 tokens per second) 1.56.146.958 I slot print_timing: id 0 | task 260 | eval time = 36.25 ms / 2 tokens ( 36.25 ms per token, 27.59 tokens per second) 1.56.146.958 I slot print_timing: id 0 | task 260 | total time = 766.47 ms / 146 tokens 1.56.146.961 I slot print_timing: id 0 | task 260 | graphs reused = 1 1.56.146.961 I slot print_timing: id 0 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.147.060 I slot release: id 0 | task 260 | stop processing: n_tokens = 145, truncated = 0 1.56.147.387 I slot print_timing: id 1 | task 261 | prompt eval time = 731.24 ms / 124 tokens ( 5.90 ms per token, 169.57 tokens per second) 1.56.147.391 I slot print_timing: id 1 | task 261 | eval time = 35.63 ms / 2 tokens ( 35.63 ms per token, 28.07 tokens per second) 1.56.147.392 I slot print_timing: id 1 | task 261 | total time = 766.87 ms / 126 tokens 1.56.147.392 I slot print_timing: id 1 | task 261 | graphs reused = 1 1.56.147.392 I slot print_timing: id 1 | task 261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.148.814 I slot release: id 1 | task 261 | stop processing: n_tokens = 125, truncated = 0 1.56.256.664 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 183, t_last = 386923804067 1.56.256.739 I slot launch_slot_: id 2 | task 265 | processing task, is_child = 0 1.56.256.777 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 1.56.493.502 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.286 MiB) 1.56.859.671 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 156, t_last = 386923806103 1.56.859.756 I slot launch_slot_: id 3 | task 266 | processing task, is_child = 0 1.56.859.792 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 145, t_last = 386925586593 1.56.859.838 I slot launch_slot_: id 0 | task 267 | processing task, is_child = 0 1.56.859.856 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 125, t_last = 386925588347 1.56.859.895 I slot launch_slot_: id 1 | task 268 | processing task, is_child = 0 2.01.811.239 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 718, progress = 0.58, t = 4.95 s / 145.01 tokens per second 2.01.875.549 I slot print_timing: id 1 | task 268 | prompt processing, n_tokens = 727, progress = 0.58, t = 4.95 s / 146.83 tokens per second 2.02.076.166 I slot print_timing: id 2 | task 265 | prompt processing, n_tokens = 714, progress = 0.58, t = 4.95 s / 144.21 tokens per second 2.02.090.596 I slot print_timing: id 3 | task 266 | prompt processing, n_tokens = 699, progress = 0.58, t = 4.95 s / 141.18 tokens per second 2.05.068.911 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 1125, progress = 0.91, t = 8.21 s / 137.05 tokens per second 2.05.166.977 I slot print_timing: id 1 | task 268 | prompt processing, n_tokens = 1125, progress = 0.91, t = 8.21 s / 137.05 tokens per second 2.05.179.724 I slot print_timing: id 2 | task 265 | prompt processing, n_tokens = 1125, progress = 0.91, t = 8.21 s / 137.05 tokens per second 2.05.209.335 I slot print_timing: id 3 | task 266 | prompt processing, n_tokens = 1125, progress = 0.93, t = 8.21 s / 137.05 tokens per second 2.06.161.269 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 1230, progress = 1.00, t = 9.30 s / 132.24 tokens per second 2.06.229.458 I slot print_timing: id 1 | task 268 | prompt processing, n_tokens = 1239, progress = 1.00, t = 9.30 s / 133.21 tokens per second 2.06.239.779 I slot print_timing: id 2 | task 265 | prompt processing, n_tokens = 1226, progress = 1.00, t = 9.30 s / 131.81 tokens per second 2.06.266.745 I slot print_timing: id 3 | task 266 | prompt processing, n_tokens = 1211, progress = 1.00, t = 9.30 s / 130.20 tokens per second 2.09.563.737 I slot print_timing: id 3 | task 266 | prompt eval time = 9551.20 ms / 1215 tokens ( 7.86 ms per token, 127.21 tokens per second) 2.09.563.744 I slot print_timing: id 3 | task 266 | eval time = 3152.55 ms / 63 tokens ( 50.85 ms per token, 19.67 tokens per second) 2.09.563.745 I slot print_timing: id 3 | task 266 | total time = 12703.76 ms / 1278 tokens 2.09.563.746 I slot print_timing: id 3 | task 266 | graphs reused = 63 2.09.563.747 I slot print_timing: id 3 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.566.922 I slot release: id 3 | task 266 | stop processing: n_tokens = 1277, truncated = 0 2.09.612.886 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 2.09.612.932 I slot launch_slot_: id 3 | task 338 | processing task, is_child = 0 2.10.399.017 I slot print_timing: id 2 | task 265 | prompt eval time = 9549.36 ms / 1230 tokens ( 7.76 ms per token, 128.80 tokens per second) 2.10.399.026 I slot print_timing: id 2 | task 265 | eval time = 3989.70 ms / 72 tokens ( 56.19 ms per token, 17.80 tokens per second) 2.10.399.027 I slot print_timing: id 2 | task 265 | total time = 13539.06 ms / 1302 tokens 2.10.399.027 I slot print_timing: id 2 | task 265 | graphs reused = 68 2.10.399.028 I slot print_timing: id 2 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.399.196 I slot release: id 2 | task 265 | stop processing: n_tokens = 1301, truncated = 0 2.10.463.162 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.881 2.10.463.207 I slot launch_slot_: id 2 | task 348 | processing task, is_child = 0 2.11.416.753 I slot print_timing: id 0 | task 267 | prompt eval time = 9548.65 ms / 1234 tokens ( 7.74 ms per token, 129.23 tokens per second) 2.11.416.764 I slot print_timing: id 0 | task 267 | eval time = 5008.20 ms / 83 tokens ( 61.08 ms per token, 16.37 tokens per second) 2.11.416.765 I slot print_timing: id 0 | task 267 | total time = 14556.85 ms / 1317 tokens 2.11.416.766 I slot print_timing: id 0 | task 267 | graphs reused = 75 2.11.416.768 I slot print_timing: id 0 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.418.376 I slot release: id 0 | task 267 | stop processing: n_tokens = 1316, truncated = 0 2.11.465.919 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.871 2.11.465.969 I slot launch_slot_: id 0 | task 360 | processing task, is_child = 0 2.12.684.107 I slot print_timing: id 1 | task 268 | n_gen = 100, tg = 15.78 t/s, tg_3s = 15.94 t/s 2.15.329.773 I slot print_timing: id 3 | task 338 | prompt eval time = 479.77 ms / 132 tokens ( 3.63 ms per token, 275.13 tokens per second) 2.15.329.778 I slot print_timing: id 3 | task 338 | eval time = 5237.06 ms / 87 tokens ( 60.90 ms per token, 16.42 tokens per second) 2.15.329.779 I slot print_timing: id 3 | task 338 | total time = 5716.83 ms / 219 tokens 2.15.329.780 I slot print_timing: id 3 | task 338 | graphs reused = 141 2.15.329.781 I slot print_timing: id 3 | task 338 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.331.013 I slot release: id 3 | task 338 | stop processing: n_tokens = 1343, truncated = 0 2.15.377.823 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.853 2.15.377.871 I slot launch_slot_: id 3 | task 430 | processing task, is_child = 0 2.15.748.399 I slot print_timing: id 1 | task 268 | n_gen = 154, tg = 16.38 t/s, tg_3s = 17.62 t/s 2.16.816.682 I slot print_timing: id 2 | task 348 | n_gen = 100, tg = 17.03 t/s, tg_3s = 17.20 t/s 2.17.373.854 I slot print_timing: id 0 | task 360 | n_gen = 100, tg = 18.31 t/s, tg_3s = 18.49 t/s 2.17.425.454 I slot print_timing: id 2 | task 348 | prompt eval time = 538.89 ms / 139 tokens ( 3.88 ms per token, 257.94 tokens per second) 2.17.425.461 I slot print_timing: id 2 | task 348 | eval time = 6423.34 ms / 112 tokens ( 57.87 ms per token, 17.28 tokens per second) 2.17.425.462 I slot print_timing: id 2 | task 348 | total time = 6962.24 ms / 251 tokens 2.17.425.463 I slot print_timing: id 2 | task 348 | graphs reused = 171 2.17.425.464 I slot print_timing: id 2 | task 348 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.425.575 I slot release: id 2 | task 348 | stop processing: n_tokens = 1375, truncated = 0 2.17.483.627 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.833 2.17.483.672 I slot launch_slot_: id 2 | task 465 | processing task, is_child = 0 2.18.792.406 I slot print_timing: id 1 | task 268 | n_gen = 204, tg = 16.39 t/s, tg_3s = 16.43 t/s 2.18.995.366 I slot print_timing: id 0 | task 360 | prompt eval time = 500.91 ms / 139 tokens ( 3.60 ms per token, 277.49 tokens per second) 2.18.995.371 I slot print_timing: id 0 | task 360 | eval time = 7028.48 ms / 123 tokens ( 57.61 ms per token, 17.36 tokens per second) 2.18.995.371 I slot print_timing: id 0 | task 360 | total time = 7529.39 ms / 262 tokens 2.18.995.385 I slot print_timing: id 0 | task 360 | graphs reused = 189 2.18.995.390 I slot print_timing: id 0 | task 360 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.996.981 I slot release: id 0 | task 360 | stop processing: n_tokens = 1386, truncated = 0 2.19.044.652 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.827 2.19.044.713 I slot launch_slot_: id 0 | task 488 | processing task, is_child = 0 2.21.785.101 I slot print_timing: id 3 | task 430 | n_gen = 100, tg = 16.68 t/s, tg_3s = 16.85 t/s 2.21.835.293 I slot print_timing: id 1 | task 268 | n_gen = 255, tg = 16.47 t/s, tg_3s = 16.76 t/s 2.22.290.689 I slot print_timing: id 2 | task 465 | prompt eval time = 545.66 ms / 141 tokens ( 3.87 ms per token, 258.40 tokens per second) 2.22.290.694 I slot print_timing: id 2 | task 465 | eval time = 4261.35 ms / 76 tokens ( 56.82 ms per token, 17.60 tokens per second) 2.22.290.695 I slot print_timing: id 2 | task 465 | total time = 4807.01 ms / 217 tokens 2.22.290.696 I slot print_timing: id 2 | task 465 | graphs reused = 242 2.22.290.697 I slot print_timing: id 2 | task 465 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.292.175 I slot release: id 2 | task 465 | stop processing: n_tokens = 1341, truncated = 0 2.22.292.422 I slot print_timing: id 3 | task 430 | prompt eval time = 472.53 ms / 114 tokens ( 4.15 ms per token, 241.25 tokens per second) 2.22.292.426 I slot print_timing: id 3 | task 430 | eval time = 6442.01 ms / 110 tokens ( 59.10 ms per token, 16.92 tokens per second) 2.22.292.426 I slot print_timing: id 3 | task 430 | total time = 6914.54 ms / 224 tokens 2.22.292.427 I slot print_timing: id 3 | task 430 | graphs reused = 242 2.22.292.428 I slot print_timing: id 3 | task 430 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.292.505 I slot release: id 3 | task 430 | stop processing: n_tokens = 1348, truncated = 0 2.22.328.946 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.855 2.22.328.988 I slot launch_slot_: id 2 | task 545 | processing task, is_child = 0 2.22.329.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.266 MiB) 2.22.329.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.755 MiB) 2.23.362.140 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.850 2.23.362.197 I slot launch_slot_: id 3 | task 546 | processing task, is_child = 0 2.24.838.858 I slot print_timing: id 1 | task 268 | n_gen = 281, tg = 15.19 t/s, tg_3s = 8.66 t/s 2.26.317.632 I slot print_timing: id 0 | task 488 | n_gen = 100, tg = 14.71 t/s, tg_3s = 14.86 t/s 2.27.842.374 I slot print_timing: id 1 | task 268 | prompt eval time = 9548.97 ms / 1243 tokens ( 7.68 ms per token, 130.17 tokens per second) 2.27.842.381 I slot print_timing: id 1 | task 268 | eval time = 21433.46 ms / 340 tokens ( 63.23 ms per token, 15.82 tokens per second) 2.27.842.382 I slot print_timing: id 1 | task 268 | total time = 30982.43 ms / 1583 tokens 2.27.842.383 I slot print_timing: id 1 | task 268 | graphs reused = 313 2.27.842.384 I slot print_timing: id 1 | task 268 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.842.466 I slot release: id 1 | task 268 | stop processing: n_tokens = 1582, truncated = 0 2.27.900.521 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.724 2.27.900.567 I slot launch_slot_: id 1 | task 623 | processing task, is_child = 0 2.28.556.724 I slot print_timing: id 2 | task 545 | prompt eval time = 757.56 ms / 101 tokens ( 7.50 ms per token, 133.32 tokens per second) 2.28.556.734 I slot print_timing: id 2 | task 545 | eval time = 4436.96 ms / 80 tokens ( 56.16 ms per token, 17.80 tokens per second) 2.28.556.736 I slot print_timing: id 2 | task 545 | total time = 5194.52 ms / 181 tokens 2.28.556.737 I slot print_timing: id 2 | task 545 | graphs reused = 315 2.28.556.738 I slot print_timing: id 2 | task 545 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.556.817 I slot release: id 2 | task 545 | stop processing: n_tokens = 1305, truncated = 0 2.28.613.880 I slot print_timing: id 3 | task 546 | prompt eval time = 754.28 ms / 125 tokens ( 6.03 ms per token, 165.72 tokens per second) 2.28.613.887 I slot print_timing: id 3 | task 546 | eval time = 4493.57 ms / 81 tokens ( 56.17 ms per token, 17.80 tokens per second) 2.28.613.888 I slot print_timing: id 3 | task 546 | total time = 5247.85 ms / 206 tokens 2.28.613.888 I slot print_timing: id 3 | task 546 | graphs reused = 315 2.28.613.889 I slot print_timing: id 3 | task 546 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.613.968 I slot release: id 3 | task 546 | stop processing: n_tokens = 1330, truncated = 0 2.28.613.977 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.878 2.28.614.024 I slot launch_slot_: id 2 | task 630 | processing task, is_child = 0 2.28.614.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 2.28.614.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.010 MiB) 2.28.615.512 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.068 MiB) 2.29.461.937 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.862 2.29.462.089 I slot launch_slot_: id 3 | task 631 | processing task, is_child = 0 2.30.084.491 I slot print_timing: id 0 | task 488 | n_gen = 138, tg = 13.05 t/s, tg_3s = 10.09 t/s 2.30.207.323 I slot print_timing: id 0 | task 488 | prompt eval time = 542.83 ms / 169 tokens ( 3.21 ms per token, 311.33 tokens per second) 2.30.207.330 I slot print_timing: id 0 | task 488 | eval time = 10619.76 ms / 139 tokens ( 76.95 ms per token, 12.99 tokens per second) 2.30.207.331 I slot print_timing: id 0 | task 488 | total time = 11162.60 ms / 308 tokens 2.30.207.332 I slot print_timing: id 0 | task 488 | graphs reused = 315 2.30.207.334 I slot print_timing: id 0 | task 488 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.207.497 I slot release: id 0 | task 488 | stop processing: n_tokens = 1432, truncated = 0 2.30.256.589 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.800 2.30.256.635 I slot launch_slot_: id 0 | task 635 | processing task, is_child = 0 2.33.368.330 I slot print_timing: id 1 | task 623 | prompt eval time = 501.04 ms / 101 tokens ( 4.96 ms per token, 201.58 tokens per second) 2.33.368.338 I slot print_timing: id 1 | task 623 | eval time = 4966.71 ms / 61 tokens ( 82.78 ms per token, 12.08 tokens per second) 2.33.368.339 I slot print_timing: id 1 | task 623 | total time = 5467.75 ms / 162 tokens 2.33.368.340 I slot print_timing: id 1 | task 623 | graphs reused = 365 2.33.368.341 I slot print_timing: id 1 | task 623 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.368.440 I slot release: id 1 | task 623 | stop processing: n_tokens = 1286, truncated = 0 2.33.426.780 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.891 2.33.426.840 I slot launch_slot_: id 1 | task 690 | processing task, is_child = 0 2.34.601.798 I slot print_timing: id 3 | task 631 | prompt eval time = 743.24 ms / 120 tokens ( 6.19 ms per token, 161.46 tokens per second) 2.34.601.805 I slot print_timing: id 3 | task 631 | eval time = 4392.77 ms / 72 tokens ( 61.87 ms per token, 16.16 tokens per second) 2.34.601.806 I slot print_timing: id 3 | task 631 | total time = 5136.01 ms / 192 tokens 2.34.601.807 I slot print_timing: id 3 | task 631 | graphs reused = 378 2.34.601.808 I slot print_timing: id 3 | task 631 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.601.943 I slot release: id 3 | task 631 | stop processing: n_tokens = 1316, truncated = 0 2.34.649.287 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.871 2.34.649.336 I slot launch_slot_: id 3 | task 708 | processing task, is_child = 0 2.36.416.526 I slot print_timing: id 2 | task 630 | n_gen = 100, tg = 15.95 t/s, tg_3s = 16.11 t/s 2.36.569.373 I slot print_timing: id 0 | task 635 | n_gen = 100, tg = 17.06 t/s, tg_3s = 17.23 t/s 2.36.569.957 I slot print_timing: id 2 | task 630 | prompt eval time = 746.33 ms / 95 tokens ( 7.86 ms per token, 127.29 tokens per second) 2.36.569.963 I slot print_timing: id 2 | task 630 | eval time = 6361.52 ms / 103 tokens ( 62.37 ms per token, 16.03 tokens per second) 2.36.569.964 I slot print_timing: id 2 | task 630 | total time = 7107.86 ms / 198 tokens 2.36.569.965 I slot print_timing: id 2 | task 630 | graphs reused = 405 2.36.569.966 I slot print_timing: id 2 | task 630 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.570.122 I slot release: id 2 | task 630 | stop processing: n_tokens = 1322, truncated = 0 2.36.628.548 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.867 2.36.628.592 I slot launch_slot_: id 2 | task 740 | processing task, is_child = 0 2.38.975.841 I slot print_timing: id 1 | task 690 | prompt eval time = 458.60 ms / 86 tokens ( 5.33 ms per token, 187.53 tokens per second) 2.38.975.846 I slot print_timing: id 1 | task 690 | eval time = 5090.39 ms / 86 tokens ( 59.89 ms per token, 16.70 tokens per second) 2.38.975.847 I slot print_timing: id 1 | task 690 | total time = 5548.99 ms / 172 tokens 2.38.975.848 I slot print_timing: id 1 | task 690 | graphs reused = 441 2.38.975.849 I slot print_timing: id 1 | task 690 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.975.933 I slot release: id 1 | task 690 | stop processing: n_tokens = 1296, truncated = 0 2.39.033.936 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.948 (> 0.100 thold), f_keep = 0.884 2.39.033.993 I slot launch_slot_: id 1 | task 781 | processing task, is_child = 0 2.39.589.510 I slot print_timing: id 0 | task 635 | n_gen = 145, tg = 16.32 t/s, tg_3s = 14.90 t/s 2.40.354.129 I slot print_timing: id 3 | task 708 | prompt eval time = 492.37 ms / 133 tokens ( 3.70 ms per token, 270.12 tokens per second) 2.40.354.134 I slot print_timing: id 3 | task 708 | eval time = 5212.41 ms / 89 tokens ( 59.23 ms per token, 16.88 tokens per second) 2.40.354.136 I slot print_timing: id 3 | task 708 | total time = 5704.78 ms / 222 tokens 2.40.354.137 I slot print_timing: id 3 | task 708 | graphs reused = 457 2.40.354.138 I slot print_timing: id 3 | task 708 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.354.252 I slot release: id 3 | task 708 | stop processing: n_tokens = 1346, truncated = 0 2.40.401.504 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.851 2.40.401.552 I slot launch_slot_: id 3 | task 802 | processing task, is_child = 0 2.40.954.269 I slot print_timing: id 0 | task 635 | prompt eval time = 509.41 ms / 148 tokens ( 3.44 ms per token, 290.53 tokens per second) 2.40.954.277 I slot print_timing: id 0 | task 635 | eval time = 10188.21 ms / 165 tokens ( 62.12 ms per token, 16.10 tokens per second) 2.40.954.278 I slot print_timing: id 0 | task 635 | total time = 10697.62 ms / 313 tokens 2.40.954.279 I slot print_timing: id 0 | task 635 | graphs reused = 458 2.40.954.280 I slot print_timing: id 0 | task 635 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.954.910 I slot release: id 0 | task 635 | stop processing: n_tokens = 1437, truncated = 0 2.41.003.035 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.797 2.41.003.084 I slot launch_slot_: id 0 | task 808 | processing task, is_child = 0 2.41.538.014 I slot print_timing: id 2 | task 740 | prompt eval time = 461.12 ms / 97 tokens ( 4.75 ms per token, 210.36 tokens per second) 2.41.538.020 I slot print_timing: id 2 | task 740 | eval time = 4448.29 ms / 68 tokens ( 66.39 ms per token, 15.06 tokens per second) 2.41.538.021 I slot print_timing: id 2 | task 740 | total time = 4909.41 ms / 165 tokens 2.41.538.022 I slot print_timing: id 2 | task 740 | graphs reused = 460 2.41.538.023 I slot print_timing: id 2 | task 740 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.538.137 I slot release: id 2 | task 740 | stop processing: n_tokens = 1289, truncated = 0 2.41.596.750 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.889 2.41.596.798 I slot launch_slot_: id 2 | task 814 | processing task, is_child = 0 2.44.260.760 I slot print_timing: id 1 | task 781 | prompt eval time = 449.34 ms / 84 tokens ( 5.35 ms per token, 186.94 tokens per second) 2.44.260.768 I slot print_timing: id 1 | task 781 | eval time = 4777.42 ms / 73 tokens ( 66.35 ms per token, 15.07 tokens per second) 2.44.260.771 I slot print_timing: id 1 | task 781 | total time = 5226.75 ms / 157 tokens 2.44.260.771 I slot print_timing: id 1 | task 781 | graphs reused = 500 2.44.260.772 I slot print_timing: id 1 | task 781 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.260.849 I slot release: id 1 | task 781 | stop processing: n_tokens = 1281, truncated = 0 2.44.319.136 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.895 2.44.319.212 I slot launch_slot_: id 1 | task 860 | processing task, is_child = 0 2.45.028.577 I slot print_timing: id 3 | task 802 | prompt eval time = 441.70 ms / 101 tokens ( 4.37 ms per token, 228.66 tokens per second) 2.45.028.586 I slot print_timing: id 3 | task 802 | eval time = 4185.30 ms / 61 tokens ( 69.76 ms per token, 14.34 tokens per second) 2.45.028.587 I slot print_timing: id 3 | task 802 | total time = 4627.01 ms / 162 tokens 2.45.028.587 I slot print_timing: id 3 | task 802 | graphs reused = 504 2.45.028.588 I slot print_timing: id 3 | task 802 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.028.675 I slot release: id 3 | task 802 | stop processing: n_tokens = 1286, truncated = 0 2.45.074.999 I slot print_timing: id 0 | task 808 | prompt eval time = 426.83 ms / 95 tokens ( 4.49 ms per token, 222.57 tokens per second) 2.45.075.006 I slot print_timing: id 0 | task 808 | eval time = 3645.08 ms / 57 tokens ( 65.09 ms per token, 15.36 tokens per second) 2.45.075.007 I slot print_timing: id 0 | task 808 | total time = 4071.91 ms / 152 tokens 2.45.075.007 I slot print_timing: id 0 | task 808 | graphs reused = 504 2.45.075.008 I slot print_timing: id 0 | task 808 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.075.075 I slot release: id 0 | task 808 | stop processing: n_tokens = 1276, truncated = 0 2.45.075.569 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.898 2.45.075.624 I slot launch_slot_: id 0 | task 869 | processing task, is_child = 0 2.45.075.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.166 MiB) 2.45.076.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 2.45.076.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 2.45.937.359 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.891 2.45.937.415 I slot launch_slot_: id 3 | task 870 | processing task, is_child = 0 2.49.010.835 I slot print_timing: id 2 | task 814 | n_gen = 100, tg = 14.35 t/s, tg_3s = 14.50 t/s 2.50.630.603 I slot print_timing: id 2 | task 814 | prompt eval time = 516.92 ms / 130 tokens ( 3.98 ms per token, 251.49 tokens per second) 2.50.630.610 I slot print_timing: id 2 | task 814 | eval time = 8516.87 ms / 132 tokens ( 65.01 ms per token, 15.38 tokens per second) 2.50.630.611 I slot print_timing: id 2 | task 814 | total time = 9033.79 ms / 262 tokens 2.50.630.612 I slot print_timing: id 2 | task 814 | graphs reused = 581 2.50.630.613 I slot print_timing: id 2 | task 814 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.630.701 I slot release: id 2 | task 814 | stop processing: n_tokens = 1386, truncated = 0 2.50.688.241 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.827 2.50.688.294 I slot launch_slot_: id 2 | task 952 | processing task, is_child = 0 2.51.257.315 I slot print_timing: id 0 | task 869 | prompt eval time = 738.62 ms / 96 tokens ( 7.69 ms per token, 129.97 tokens per second) 2.51.257.322 I slot print_timing: id 0 | task 869 | eval time = 4581.27 ms / 83 tokens ( 55.87 ms per token, 17.90 tokens per second) 2.51.257.323 I slot print_timing: id 0 | task 869 | total time = 5319.88 ms / 179 tokens 2.51.257.324 I slot print_timing: id 0 | task 869 | graphs reused = 581 2.51.257.324 I slot print_timing: id 0 | task 869 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.257.391 I slot release: id 0 | task 869 | stop processing: n_tokens = 1303, truncated = 0 2.51.304.158 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.880 2.51.304.200 I slot launch_slot_: id 0 | task 957 | processing task, is_child = 0 2.51.810.735 I slot print_timing: id 1 | task 860 | prompt eval time = 451.46 ms / 90 tokens ( 5.02 ms per token, 199.35 tokens per second) 2.51.810.743 I slot print_timing: id 1 | task 860 | eval time = 7040.03 ms / 94 tokens ( 75.70 ms per token, 13.21 tokens per second) 2.51.810.745 I slot print_timing: id 1 | task 860 | total time = 7491.50 ms / 184 tokens 2.51.810.746 I slot print_timing: id 1 | task 860 | graphs reused = 582 2.51.810.747 I slot print_timing: id 1 | task 860 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.810.907 I slot release: id 1 | task 860 | stop processing: n_tokens = 1308, truncated = 0 2.51.880.462 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.876 2.51.880.522 I slot launch_slot_: id 1 | task 961 | processing task, is_child = 0 2.52.998.379 I slot print_timing: id 3 | task 870 | n_gen = 100, tg = 15.66 t/s, tg_3s = 15.82 t/s 2.53.048.470 I slot print_timing: id 3 | task 870 | prompt eval time = 736.39 ms / 87 tokens ( 8.46 ms per token, 118.14 tokens per second) 2.53.048.474 I slot print_timing: id 3 | task 870 | eval time = 6371.37 ms / 101 tokens ( 63.71 ms per token, 15.70 tokens per second) 2.53.048.475 I slot print_timing: id 3 | task 870 | total time = 7107.77 ms / 188 tokens 2.53.048.476 I slot print_timing: id 3 | task 870 | graphs reused = 593 2.53.048.484 I slot print_timing: id 3 | task 870 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.048.566 I slot release: id 3 | task 870 | stop processing: n_tokens = 1312, truncated = 0 2.53.094.789 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.873 2.53.094.830 I slot launch_slot_: id 3 | task 977 | processing task, is_child = 0 2.57.037.127 I slot print_timing: id 3 | task 977 | prompt eval time = 429.25 ms / 93 tokens ( 4.62 ms per token, 216.66 tokens per second) 2.57.037.134 I slot print_timing: id 3 | task 977 | eval time = 3513.04 ms / 70 tokens ( 50.91 ms per token, 19.64 tokens per second) 2.57.037.135 I slot print_timing: id 3 | task 977 | total time = 3942.29 ms / 163 tokens 2.57.037.136 I slot print_timing: id 3 | task 977 | graphs reused = 661 2.57.037.136 I slot print_timing: id 3 | task 977 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.037.203 I slot release: id 3 | task 977 | stop processing: n_tokens = 1287, truncated = 0 2.57.084.025 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.890 2.57.084.073 I slot launch_slot_: id 3 | task 1050 | processing task, is_child = 0 2.57.770.157 I slot print_timing: id 2 | task 952 | n_gen = 100, tg = 15.08 t/s, tg_3s = 15.23 t/s 2.57.973.403 I slot print_timing: id 0 | task 957 | n_gen = 100, tg = 16.06 t/s, tg_3s = 16.23 t/s 2.58.126.522 I slot print_timing: id 1 | task 961 | n_gen = 100, tg = 17.39 t/s, tg_3s = 17.57 t/s 2.58.279.310 I slot print_timing: id 2 | task 952 | prompt eval time = 515.33 ms / 131 tokens ( 3.93 ms per token, 254.21 tokens per second) 2.58.279.314 I slot print_timing: id 2 | task 952 | eval time = 7075.67 ms / 110 tokens ( 64.91 ms per token, 15.40 tokens per second) 2.58.279.316 I slot print_timing: id 2 | task 952 | total time = 7591.01 ms / 241 tokens 2.58.279.317 I slot print_timing: id 2 | task 952 | graphs reused = 675 2.58.279.317 I slot print_timing: id 2 | task 952 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.280.016 I slot release: id 2 | task 952 | stop processing: n_tokens = 1365, truncated = 0 2.58.336.796 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 2.58.336.843 I slot launch_slot_: id 2 | task 1069 | processing task, is_child = 0 3.00.180.824 I slot print_timing: id 0 | task 957 | prompt eval time = 506.13 ms / 137 tokens ( 3.69 ms per token, 270.68 tokens per second) 3.00.180.832 I slot print_timing: id 0 | task 957 | eval time = 8370.48 ms / 136 tokens ( 62.00 ms per token, 16.13 tokens per second) 3.00.180.833 I slot print_timing: id 0 | task 957 | total time = 8876.61 ms / 273 tokens 3.00.180.833 I slot print_timing: id 0 | task 957 | graphs reused = 701 3.00.180.834 I slot print_timing: id 0 | task 957 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.180.914 I slot release: id 0 | task 957 | stop processing: n_tokens = 1397, truncated = 0 3.00.228.298 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.820 3.00.228.346 I slot launch_slot_: id 0 | task 1100 | processing task, is_child = 0 3.01.095.693 I slot print_timing: id 3 | task 1050 | prompt eval time = 423.98 ms / 87 tokens ( 4.87 ms per token, 205.20 tokens per second) 3.01.095.700 I slot print_timing: id 3 | task 1050 | eval time = 3587.63 ms / 57 tokens ( 64.06 ms per token, 15.61 tokens per second) 3.01.095.701 I slot print_timing: id 3 | task 1050 | total time = 4011.61 ms / 144 tokens 3.01.095.702 I slot print_timing: id 3 | task 1050 | graphs reused = 709 3.01.095.703 I slot print_timing: id 3 | task 1050 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.095.784 I slot release: id 3 | task 1050 | stop processing: n_tokens = 1268, truncated = 0 3.01.142.375 I slot print_timing: id 1 | task 961 | n_gen = 145, tg = 16.54 t/s, tg_3s = 14.92 t/s 3.01.142.633 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.905 3.01.142.673 I slot launch_slot_: id 3 | task 1112 | processing task, is_child = 0 3.01.925.987 I slot print_timing: id 2 | task 1069 | prompt eval time = 466.85 ms / 98 tokens ( 4.76 ms per token, 209.92 tokens per second) 3.01.925.993 I slot print_timing: id 2 | task 1069 | eval time = 3122.27 ms / 48 tokens ( 66.43 ms per token, 15.05 tokens per second) 3.01.925.994 I slot print_timing: id 2 | task 1069 | total time = 3589.12 ms / 146 tokens 3.01.925.995 I slot print_timing: id 2 | task 1069 | graphs reused = 714 3.01.925.996 I slot print_timing: id 2 | task 1069 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.927.142 I slot release: id 2 | task 1069 | stop processing: n_tokens = 1270, truncated = 0 3.01.985.676 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.902 3.01.985.727 I slot launch_slot_: id 2 | task 1122 | processing task, is_child = 0 3.04.158.418 I slot print_timing: id 1 | task 961 | n_gen = 189, tg = 16.03 t/s, tg_3s = 14.59 t/s 3.05.988.669 I slot print_timing: id 0 | task 1100 | prompt eval time = 452.13 ms / 105 tokens ( 4.31 ms per token, 232.23 tokens per second) 3.05.988.675 I slot print_timing: id 0 | task 1100 | eval time = 5308.18 ms / 90 tokens ( 59.64 ms per token, 16.77 tokens per second) 3.05.988.676 I slot print_timing: id 0 | task 1100 | total time = 5760.31 ms / 195 tokens 3.05.988.677 I slot print_timing: id 0 | task 1100 | graphs reused = 782 3.05.988.677 I slot print_timing: id 0 | task 1100 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.988.747 I slot release: id 0 | task 1100 | stop processing: n_tokens = 1319, truncated = 0 3.06.036.184 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 3.06.036.232 I slot launch_slot_: id 0 | task 1195 | processing task, is_child = 0 3.07.180.089 I slot print_timing: id 1 | task 961 | n_gen = 242, tg = 16.34 t/s, tg_3s = 17.54 t/s 3.07.383.164 I slot print_timing: id 1 | task 961 | prompt eval time = 553.47 ms / 153 tokens ( 3.62 ms per token, 276.44 tokens per second) 3.07.383.172 I slot print_timing: id 1 | task 961 | eval time = 14949.16 ms / 246 tokens ( 61.02 ms per token, 16.39 tokens per second) 3.07.383.172 I slot print_timing: id 1 | task 961 | total time = 15502.63 ms / 399 tokens 3.07.383.173 I slot print_timing: id 1 | task 961 | graphs reused = 800 3.07.383.174 I slot print_timing: id 1 | task 961 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.383.267 I slot release: id 1 | task 961 | stop processing: n_tokens = 1523, truncated = 0 3.07.383.887 I slot print_timing: id 3 | task 1112 | n_gen = 100, tg = 17.17 t/s, tg_3s = 17.34 t/s 3.07.441.230 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.752 3.07.441.277 I slot launch_slot_: id 1 | task 1217 | processing task, is_child = 0 3.08.256.943 I slot print_timing: id 2 | task 1122 | n_gen = 100, tg = 17.13 t/s, tg_3s = 17.30 t/s 3.08.460.485 I slot print_timing: id 2 | task 1122 | prompt eval time = 491.09 ms / 122 tokens ( 4.03 ms per token, 248.43 tokens per second) 3.08.460.491 I slot print_timing: id 2 | task 1122 | eval time = 5983.65 ms / 104 tokens ( 58.09 ms per token, 17.21 tokens per second) 3.08.460.491 I slot print_timing: id 2 | task 1122 | total time = 6474.74 ms / 226 tokens 3.08.460.492 I slot print_timing: id 2 | task 1122 | graphs reused = 809 3.08.460.493 I slot print_timing: id 2 | task 1122 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.460.574 I slot release: id 2 | task 1122 | stop processing: n_tokens = 1350, truncated = 0 3.08.518.598 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.849 3.08.518.643 I slot launch_slot_: id 2 | task 1231 | processing task, is_child = 0 3.09.116.589 I slot print_timing: id 3 | task 1112 | prompt eval time = 473.84 ms / 113 tokens ( 4.19 ms per token, 238.48 tokens per second) 3.09.116.595 I slot print_timing: id 3 | task 1112 | eval time = 7500.06 ms / 117 tokens ( 64.66 ms per token, 15.47 tokens per second) 3.09.116.596 I slot print_timing: id 3 | task 1112 | total time = 7973.90 ms / 230 tokens 3.09.116.597 I slot print_timing: id 3 | task 1112 | graphs reused = 809 3.09.116.598 I slot print_timing: id 3 | task 1112 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.116.669 I slot release: id 3 | task 1112 | stop processing: n_tokens = 1354, truncated = 0 3.09.163.276 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.846 3.09.163.316 I slot launch_slot_: id 3 | task 1236 | processing task, is_child = 0 3.12.765.093 I slot print_timing: id 0 | task 1195 | n_gen = 100, tg = 15.69 t/s, tg_3s = 15.85 t/s 3.13.171.725 I slot print_timing: id 0 | task 1195 | prompt eval time = 419.79 ms / 96 tokens ( 4.37 ms per token, 228.69 tokens per second) 3.13.171.732 I slot print_timing: id 0 | task 1195 | eval time = 6715.69 ms / 108 tokens ( 62.76 ms per token, 15.93 tokens per second) 3.13.171.733 I slot print_timing: id 0 | task 1195 | total time = 7135.48 ms / 204 tokens 3.13.171.733 I slot print_timing: id 0 | task 1195 | graphs reused = 876 3.13.171.734 I slot print_timing: id 0 | task 1195 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.171.813 I slot release: id 0 | task 1195 | stop processing: n_tokens = 1328, truncated = 0 3.13.219.760 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.863 3.13.219.811 I slot launch_slot_: id 0 | task 1309 | processing task, is_child = 0 3.14.202.518 I slot print_timing: id 1 | task 1217 | n_gen = 100, tg = 15.83 t/s, tg_3s = 15.99 t/s 3.14.661.024 I slot print_timing: id 1 | task 1217 | prompt eval time = 505.98 ms / 113 tokens ( 4.48 ms per token, 223.33 tokens per second) 3.14.661.031 I slot print_timing: id 1 | task 1217 | eval time = 6713.75 ms / 109 tokens ( 62.16 ms per token, 16.09 tokens per second) 3.14.661.032 I slot print_timing: id 1 | task 1217 | total time = 7219.73 ms / 222 tokens 3.14.661.033 I slot print_timing: id 1 | task 1217 | graphs reused = 895 3.14.661.033 I slot print_timing: id 1 | task 1217 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.661.144 I slot release: id 1 | task 1217 | stop processing: n_tokens = 1346, truncated = 0 3.14.718.953 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.851 3.14.719.013 I slot launch_slot_: id 1 | task 1332 | processing task, is_child = 0 3.15.288.293 I slot print_timing: id 2 | task 1231 | n_gen = 100, tg = 15.90 t/s, tg_3s = 16.06 t/s 3.15.492.455 I slot print_timing: id 3 | task 1236 | n_gen = 100, tg = 16.96 t/s, tg_3s = 17.13 t/s 3.15.849.361 I slot print_timing: id 3 | task 1236 | prompt eval time = 490.51 ms / 131 tokens ( 3.74 ms per token, 267.07 tokens per second) 3.15.849.366 I slot print_timing: id 3 | task 1236 | eval time = 6195.52 ms / 107 tokens ( 58.45 ms per token, 17.11 tokens per second) 3.15.849.368 I slot print_timing: id 3 | task 1236 | total time = 6686.03 ms / 238 tokens 3.15.849.369 I slot print_timing: id 3 | task 1236 | graphs reused = 906 3.15.849.370 I slot print_timing: id 3 | task 1236 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.850.552 I slot release: id 3 | task 1236 | stop processing: n_tokens = 1362, truncated = 0 3.15.897.739 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.841 3.15.897.795 I slot launch_slot_: id 3 | task 1348 | processing task, is_child = 0 3.18.256.067 I slot print_timing: id 0 | task 1309 | prompt eval time = 467.24 ms / 117 tokens ( 3.99 ms per token, 250.41 tokens per second) 3.18.256.072 I slot print_timing: id 0 | task 1309 | eval time = 4569.01 ms / 74 tokens ( 62.59 ms per token, 15.98 tokens per second) 3.18.256.073 I slot print_timing: id 0 | task 1309 | total time = 5036.25 ms / 191 tokens 3.18.256.074 I slot print_timing: id 0 | task 1309 | graphs reused = 941 3.18.256.075 I slot print_timing: id 0 | task 1309 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.256.162 I slot release: id 0 | task 1309 | stop processing: n_tokens = 1315, truncated = 0 3.18.304.059 I slot print_timing: id 2 | task 1231 | n_gen = 151, tg = 16.23 t/s, tg_3s = 16.91 t/s 3.18.304.308 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.871 3.18.304.366 I slot launch_slot_: id 0 | task 1388 | processing task, is_child = 0 3.19.957.282 I slot print_timing: id 2 | task 1231 | prompt eval time = 543.04 ms / 149 tokens ( 3.64 ms per token, 274.38 tokens per second) 3.19.957.287 I slot print_timing: id 2 | task 1231 | eval time = 10895.58 ms / 177 tokens ( 61.91 ms per token, 16.15 tokens per second) 3.19.957.288 I slot print_timing: id 2 | task 1231 | total time = 11438.62 ms / 326 tokens 3.19.957.289 I slot print_timing: id 2 | task 1231 | graphs reused = 965 3.19.957.290 I slot print_timing: id 2 | task 1231 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.958.423 I slot release: id 2 | task 1231 | stop processing: n_tokens = 1450, truncated = 0 3.20.016.574 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.790 3.20.016.625 I slot launch_slot_: id 2 | task 1416 | processing task, is_child = 0 3.21.430.831 I slot print_timing: id 1 | task 1332 | n_gen = 100, tg = 15.97 t/s, tg_3s = 16.14 t/s 3.21.940.019 I slot print_timing: id 1 | task 1332 | prompt eval time = 514.18 ms / 127 tokens ( 4.05 ms per token, 247.00 tokens per second) 3.21.940.025 I slot print_timing: id 1 | task 1332 | eval time = 6706.81 ms / 110 tokens ( 61.53 ms per token, 16.25 tokens per second) 3.21.940.026 I slot print_timing: id 1 | task 1332 | total time = 7220.99 ms / 237 tokens 3.21.940.026 I slot print_timing: id 1 | task 1332 | graphs reused = 992 3.21.940.027 I slot print_timing: id 1 | task 1332 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.940.105 I slot release: id 1 | task 1332 | stop processing: n_tokens = 1361, truncated = 0 3.21.998.351 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.842 3.21.998.403 I slot launch_slot_: id 1 | task 1448 | processing task, is_child = 0 3.22.566.107 I slot print_timing: id 3 | task 1348 | n_gen = 100, tg = 16.09 t/s, tg_3s = 16.25 t/s 3.23.789.216 I slot print_timing: id 0 | task 1388 | prompt eval time = 423.42 ms / 96 tokens ( 4.41 ms per token, 226.73 tokens per second) 3.23.789.223 I slot print_timing: id 0 | task 1388 | eval time = 5061.42 ms / 85 tokens ( 60.26 ms per token, 16.60 tokens per second) 3.23.789.224 I slot print_timing: id 0 | task 1388 | total time = 5484.84 ms / 181 tokens 3.23.789.225 I slot print_timing: id 0 | task 1388 | graphs reused = 1017 3.23.789.226 I slot print_timing: id 0 | task 1388 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.789.310 I slot release: id 0 | task 1388 | stop processing: n_tokens = 1305, truncated = 0 3.23.837.311 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.878 3.23.837.364 I slot launch_slot_: id 0 | task 1478 | processing task, is_child = 0 3.24.749.485 I slot print_timing: id 2 | task 1416 | prompt eval time = 495.61 ms / 104 tokens ( 4.77 ms per token, 209.84 tokens per second) 3.24.749.493 I slot print_timing: id 2 | task 1416 | eval time = 4237.24 ms / 70 tokens ( 61.41 ms per token, 16.28 tokens per second) 3.24.749.494 I slot print_timing: id 2 | task 1416 | total time = 4732.85 ms / 174 tokens 3.24.749.495 I slot print_timing: id 2 | task 1416 | graphs reused = 1026 3.24.749.496 I slot print_timing: id 2 | task 1416 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.750.269 I slot release: id 2 | task 1416 | stop processing: n_tokens = 1298, truncated = 0 3.24.808.997 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.883 3.24.809.061 I slot launch_slot_: id 2 | task 1491 | processing task, is_child = 0 3.25.566.118 I slot print_timing: id 3 | task 1348 | n_gen = 144, tg = 15.62 t/s, tg_3s = 14.67 t/s 3.26.328.612 I slot print_timing: id 3 | task 1348 | prompt eval time = 514.80 ms / 137 tokens ( 3.76 ms per token, 266.12 tokens per second) 3.26.328.620 I slot print_timing: id 3 | task 1348 | eval time = 9916.01 ms / 159 tokens ( 62.76 ms per token, 15.93 tokens per second) 3.26.328.621 I slot print_timing: id 3 | task 1348 | total time = 10430.81 ms / 296 tokens 3.26.328.622 I slot print_timing: id 3 | task 1348 | graphs reused = 1045 3.26.328.623 I slot print_timing: id 3 | task 1348 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.328.745 I slot release: id 3 | task 1348 | stop processing: n_tokens = 1420, truncated = 0 3.26.375.796 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.807 3.26.375.848 I slot launch_slot_: id 3 | task 1515 | processing task, is_child = 0 3.27.425.587 I slot print_timing: id 1 | task 1448 | prompt eval time = 461.75 ms / 98 tokens ( 4.71 ms per token, 212.23 tokens per second) 3.27.425.595 I slot print_timing: id 1 | task 1448 | eval time = 4965.41 ms / 76 tokens ( 66.21 ms per token, 15.10 tokens per second) 3.27.425.596 I slot print_timing: id 1 | task 1448 | total time = 5427.17 ms / 174 tokens 3.27.425.597 I slot print_timing: id 1 | task 1448 | graphs reused = 1055 3.27.425.597 I slot print_timing: id 1 | task 1448 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.425.672 I slot release: id 1 | task 1448 | stop processing: n_tokens = 1298, truncated = 0 3.27.483.682 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.883 3.27.483.734 I slot launch_slot_: id 1 | task 1530 | processing task, is_child = 0 3.28.923.234 I slot print_timing: id 0 | task 1478 | prompt eval time = 449.01 ms / 102 tokens ( 4.40 ms per token, 227.16 tokens per second) 3.28.923.241 I slot print_timing: id 0 | task 1478 | eval time = 4636.85 ms / 68 tokens ( 69.21 ms per token, 14.45 tokens per second) 3.28.923.242 I slot print_timing: id 0 | task 1478 | total time = 5085.86 ms / 170 tokens 3.28.923.242 I slot print_timing: id 0 | task 1478 | graphs reused = 1071 3.28.923.243 I slot print_timing: id 0 | task 1478 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.923.318 I slot release: id 0 | task 1478 | stop processing: n_tokens = 1294, truncated = 0 3.28.971.385 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 3.28.971.439 I slot launch_slot_: id 0 | task 1552 | processing task, is_child = 0 3.31.525.444 I slot print_timing: id 2 | task 1491 | n_gen = 100, tg = 15.91 t/s, tg_3s = 16.07 t/s 3.31.728.702 I slot print_timing: id 2 | task 1491 | prompt eval time = 494.78 ms / 108 tokens ( 4.58 ms per token, 218.28 tokens per second) 3.31.728.710 I slot print_timing: id 2 | task 1491 | eval time = 6424.85 ms / 104 tokens ( 62.38 ms per token, 16.03 tokens per second) 3.31.728.711 I slot print_timing: id 2 | task 1491 | total time = 6919.63 ms / 212 tokens 3.31.728.712 I slot print_timing: id 2 | task 1491 | graphs reused = 1116 3.31.728.713 I slot print_timing: id 2 | task 1491 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.728.805 I slot release: id 2 | task 1491 | stop processing: n_tokens = 1336, truncated = 0 3.31.787.205 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.858 3.31.787.258 I slot launch_slot_: id 2 | task 1601 | processing task, is_child = 0 3.32.289.811 I slot print_timing: id 3 | task 1515 | prompt eval time = 484.10 ms / 122 tokens ( 3.97 ms per token, 252.01 tokens per second) 3.32.289.819 I slot print_timing: id 3 | task 1515 | eval time = 5429.85 ms / 85 tokens ( 64.64 ms per token, 15.47 tokens per second) 3.32.289.820 I slot print_timing: id 3 | task 1515 | total time = 5913.95 ms / 207 tokens 3.32.289.834 I slot print_timing: id 3 | task 1515 | graphs reused = 1116 3.32.289.843 I slot print_timing: id 3 | task 1515 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.289.910 I slot release: id 3 | task 1515 | stop processing: n_tokens = 1331, truncated = 0 3.32.335.966 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.861 3.32.336.006 I slot launch_slot_: id 3 | task 1606 | processing task, is_child = 0 3.34.135.629 I slot print_timing: id 1 | task 1530 | n_gen = 100, tg = 16.13 t/s, tg_3s = 16.29 t/s 3.34.339.311 I slot print_timing: id 1 | task 1530 | prompt eval time = 512.58 ms / 124 tokens ( 4.13 ms per token, 241.91 tokens per second) 3.34.339.316 I slot print_timing: id 1 | task 1530 | eval time = 6342.98 ms / 104 tokens ( 61.58 ms per token, 16.24 tokens per second) 3.34.339.317 I slot print_timing: id 1 | task 1530 | total time = 6855.56 ms / 228 tokens 3.34.339.318 I slot print_timing: id 1 | task 1530 | graphs reused = 1145 3.34.339.319 I slot print_timing: id 1 | task 1530 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.339.395 I slot release: id 1 | task 1530 | stop processing: n_tokens = 1352, truncated = 0 3.34.397.517 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.848 3.34.397.569 I slot launch_slot_: id 1 | task 1640 | processing task, is_child = 0 3.35.575.832 I slot print_timing: id 0 | task 1552 | n_gen = 100, tg = 16.11 t/s, tg_3s = 16.27 t/s 3.35.780.020 I slot print_timing: id 2 | task 1601 | prompt eval time = 447.39 ms / 86 tokens ( 5.20 ms per token, 192.22 tokens per second) 3.35.780.025 I slot print_timing: id 2 | task 1601 | eval time = 3545.36 ms / 56 tokens ( 64.46 ms per token, 15.51 tokens per second) 3.35.780.026 I slot print_timing: id 2 | task 1601 | total time = 3992.75 ms / 142 tokens 3.35.780.027 I slot print_timing: id 2 | task 1601 | graphs reused = 1162 3.35.780.028 I slot print_timing: id 2 | task 1601 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.780.103 I slot release: id 2 | task 1601 | stop processing: n_tokens = 1266, truncated = 0 3.35.838.404 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.905 3.35.838.459 I slot launch_slot_: id 2 | task 1662 | processing task, is_child = 0 3.36.549.373 I slot print_timing: id 0 | task 1552 | prompt eval time = 458.95 ms / 111 tokens ( 4.13 ms per token, 241.86 tokens per second) 3.36.549.381 I slot print_timing: id 0 | task 1552 | eval time = 7118.97 ms / 112 tokens ( 64.13 ms per token, 15.59 tokens per second) 3.36.549.382 I slot print_timing: id 0 | task 1552 | total time = 7577.92 ms / 223 tokens 3.36.549.383 I slot print_timing: id 0 | task 1552 | graphs reused = 1166 3.36.549.384 I slot print_timing: id 0 | task 1552 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.549.460 I slot release: id 0 | task 1552 | stop processing: n_tokens = 1347, truncated = 0 3.36.597.232 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.851 3.36.597.275 I slot launch_slot_: id 0 | task 1671 | processing task, is_child = 0 3.38.960.945 I slot print_timing: id 3 | task 1606 | n_gen = 100, tg = 16.09 t/s, tg_3s = 16.25 t/s 3.39.622.416 I slot print_timing: id 3 | task 1606 | prompt eval time = 472.04 ms / 106 tokens ( 4.45 ms per token, 224.56 tokens per second) 3.39.622.424 I slot print_timing: id 3 | task 1606 | eval time = 6814.36 ms / 113 tokens ( 60.84 ms per token, 16.44 tokens per second) 3.39.622.425 I slot print_timing: id 3 | task 1606 | total time = 7286.40 ms / 219 tokens 3.39.622.426 I slot print_timing: id 3 | task 1606 | graphs reused = 1216 3.39.622.427 I slot print_timing: id 3 | task 1606 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.622.521 I slot release: id 3 | task 1606 | stop processing: n_tokens = 1343, truncated = 0 3.39.669.894 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.853 3.39.669.945 I slot launch_slot_: id 3 | task 1725 | processing task, is_child = 0 3.40.296.770 I slot print_timing: id 0 | task 1671 | prompt eval time = 474.48 ms / 121 tokens ( 3.92 ms per token, 255.02 tokens per second) 3.40.296.775 I slot print_timing: id 0 | task 1671 | eval time = 3225.00 ms / 57 tokens ( 57.59 ms per token, 17.36 tokens per second) 3.40.296.776 I slot print_timing: id 0 | task 1671 | total time = 3699.48 ms / 178 tokens 3.40.296.777 I slot print_timing: id 0 | task 1671 | graphs reused = 1218 3.40.296.778 I slot print_timing: id 0 | task 1671 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.297.384 I slot release: id 0 | task 1671 | stop processing: n_tokens = 1302, truncated = 0 3.40.344.975 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 3.40.345.028 I slot launch_slot_: id 0 | task 1732 | processing task, is_child = 0 3.41.332.441 I slot print_timing: id 1 | task 1640 | n_gen = 100, tg = 15.30 t/s, tg_3s = 15.45 t/s 3.42.197.502 I slot print_timing: id 1 | task 1640 | prompt eval time = 462.18 ms / 98 tokens ( 4.72 ms per token, 212.04 tokens per second) 3.42.197.508 I slot print_timing: id 1 | task 1640 | eval time = 7337.74 ms / 117 tokens ( 63.26 ms per token, 15.81 tokens per second) 3.42.197.509 I slot print_timing: id 1 | task 1640 | total time = 7799.92 ms / 215 tokens 3.42.197.510 I slot print_timing: id 1 | task 1640 | graphs reused = 1246 3.42.197.510 I slot print_timing: id 1 | task 1640 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.197.600 I slot release: id 1 | task 1640 | stop processing: n_tokens = 1339, truncated = 0 3.42.255.569 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 3.42.255.619 I slot launch_slot_: id 1 | task 1764 | processing task, is_child = 0 3.42.684.500 I slot print_timing: id 2 | task 1662 | prompt eval time = 453.62 ms / 91 tokens ( 4.98 ms per token, 200.61 tokens per second) 3.42.684.520 I slot print_timing: id 2 | task 1662 | eval time = 6392.39 ms / 98 tokens ( 65.90 ms per token, 15.17 tokens per second) 3.42.684.526 I slot print_timing: id 2 | task 1662 | total time = 6846.01 ms / 189 tokens 3.42.684.527 I slot print_timing: id 2 | task 1662 | graphs reused = 1246 3.42.684.529 I slot print_timing: id 2 | task 1662 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.684.741 I slot release: id 2 | task 1662 | stop processing: n_tokens = 1313, truncated = 0 3.42.786.695 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.873 3.42.786.762 I slot launch_slot_: id 2 | task 1767 | processing task, is_child = 0 3.45.024.161 I slot print_timing: id 3 | task 1725 | prompt eval time = 469.48 ms / 105 tokens ( 4.47 ms per token, 223.65 tokens per second) 3.45.024.169 I slot print_timing: id 3 | task 1725 | eval time = 4884.72 ms / 74 tokens ( 66.91 ms per token, 14.94 tokens per second) 3.45.024.171 I slot print_timing: id 3 | task 1725 | total time = 5354.20 ms / 179 tokens 3.45.024.171 I slot print_timing: id 3 | task 1725 | graphs reused = 1278 3.45.024.172 I slot print_timing: id 3 | task 1725 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.024.269 I slot release: id 3 | task 1725 | stop processing: n_tokens = 1303, truncated = 0 3.45.071.368 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.880 3.45.071.413 I slot launch_slot_: id 3 | task 1805 | processing task, is_child = 0 3.45.814.229 I slot print_timing: id 0 | task 1732 | prompt eval time = 419.57 ms / 95 tokens ( 4.42 ms per token, 226.42 tokens per second) 3.45.814.237 I slot print_timing: id 0 | task 1732 | eval time = 5049.62 ms / 75 tokens ( 68.24 ms per token, 14.65 tokens per second) 3.45.814.238 I slot print_timing: id 0 | task 1732 | total time = 5469.19 ms / 170 tokens 3.45.814.238 I slot print_timing: id 0 | task 1732 | graphs reused = 1281 3.45.814.239 I slot print_timing: id 0 | task 1732 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.814.318 I slot release: id 0 | task 1732 | stop processing: n_tokens = 1294, truncated = 0 3.45.862.447 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.886 3.45.862.491 I slot launch_slot_: id 0 | task 1813 | processing task, is_child = 0 3.47.503.005 I slot print_timing: id 2 | task 1767 | prompt eval time = 498.22 ms / 110 tokens ( 4.53 ms per token, 220.79 tokens per second) 3.47.503.010 I slot print_timing: id 2 | task 1767 | eval time = 4218.01 ms / 68 tokens ( 62.96 ms per token, 15.88 tokens per second) 3.47.503.011 I slot print_timing: id 2 | task 1767 | total time = 4716.23 ms / 178 tokens 3.47.503.012 I slot print_timing: id 2 | task 1767 | graphs reused = 1304 3.47.503.013 I slot print_timing: id 2 | task 1767 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.503.108 I slot release: id 2 | task 1767 | stop processing: n_tokens = 1302, truncated = 0 3.47.561.113 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.880 3.47.561.162 I slot launch_slot_: id 2 | task 1840 | processing task, is_child = 0 3.49.458.929 I slot print_timing: id 1 | task 1764 | n_gen = 100, tg = 14.84 t/s, tg_3s = 14.99 t/s 3.50.526.496 I slot print_timing: id 0 | task 1813 | prompt eval time = 461.80 ms / 115 tokens ( 4.02 ms per token, 249.03 tokens per second) 3.50.526.502 I slot print_timing: id 0 | task 1813 | eval time = 4202.19 ms / 75 tokens ( 56.79 ms per token, 17.61 tokens per second) 3.50.526.503 I slot print_timing: id 0 | task 1813 | total time = 4663.99 ms / 190 tokens 3.50.526.504 I slot print_timing: id 0 | task 1813 | graphs reused = 1351 3.50.526.505 I slot print_timing: id 0 | task 1813 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.526.609 I slot release: id 0 | task 1813 | stop processing: n_tokens = 1314, truncated = 0 3.50.574.533 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.872 3.50.574.587 I slot launch_slot_: id 0 | task 1892 | processing task, is_child = 0 3.51.747.605 I slot print_timing: id 3 | task 1805 | n_gen = 100, tg = 16.11 t/s, tg_3s = 16.28 t/s 3.52.460.260 I slot print_timing: id 1 | task 1764 | n_gen = 153, tg = 15.71 t/s, tg_3s = 17.66 t/s 3.52.561.941 I slot print_timing: id 1 | task 1764 | prompt eval time = 530.80 ms / 144 tokens ( 3.69 ms per token, 271.29 tokens per second) 3.52.561.948 I slot print_timing: id 1 | task 1764 | eval time = 9775.51 ms / 155 tokens ( 63.48 ms per token, 15.75 tokens per second) 3.52.561.949 I slot print_timing: id 1 | task 1764 | total time = 10306.31 ms / 299 tokens 3.52.561.950 I slot print_timing: id 1 | task 1764 | graphs reused = 1382 3.52.561.951 I slot print_timing: id 1 | task 1764 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.562.043 I slot release: id 1 | task 1764 | stop processing: n_tokens = 1423, truncated = 0 3.52.620.245 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 3.52.620.311 I slot launch_slot_: id 1 | task 1927 | processing task, is_child = 0 3.53.419.393 I slot print_timing: id 3 | task 1805 | prompt eval time = 531.87 ms / 158 tokens ( 3.37 ms per token, 297.07 tokens per second) 3.53.419.399 I slot print_timing: id 3 | task 1805 | eval time = 7816.10 ms / 125 tokens ( 63.03 ms per token, 15.86 tokens per second) 3.53.419.400 I slot print_timing: id 3 | task 1805 | total time = 8347.97 ms / 283 tokens 3.53.419.401 I slot print_timing: id 3 | task 1805 | graphs reused = 1387 3.53.419.402 I slot print_timing: id 3 | task 1805 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.419.487 I slot release: id 3 | task 1805 | stop processing: n_tokens = 1407, truncated = 0 3.53.466.531 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.814 3.53.466.587 I slot launch_slot_: id 3 | task 1937 | processing task, is_child = 0 3.54.207.605 I slot print_timing: id 2 | task 1840 | n_gen = 100, tg = 16.16 t/s, tg_3s = 16.32 t/s 3.54.715.235 I slot print_timing: id 0 | task 1892 | prompt eval time = 405.32 ms / 81 tokens ( 5.00 ms per token, 199.84 tokens per second) 3.54.715.240 I slot print_timing: id 0 | task 1892 | eval time = 3735.32 ms / 59 tokens ( 64.40 ms per token, 15.53 tokens per second) 3.54.715.241 I slot print_timing: id 0 | task 1892 | total time = 4140.64 ms / 140 tokens 3.54.715.242 I slot print_timing: id 0 | task 1892 | graphs reused = 1401 3.54.715.242 I slot print_timing: id 0 | task 1892 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.715.317 I slot release: id 0 | task 1892 | stop processing: n_tokens = 1264, truncated = 0 3.54.762.737 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.907 3.54.762.793 I slot launch_slot_: id 0 | task 1956 | processing task, is_child = 0 3.57.254.615 I slot print_timing: id 2 | task 1840 | n_gen = 153, tg = 16.57 t/s, tg_3s = 17.39 t/s 3.57.814.057 I slot print_timing: id 1 | task 1927 | prompt eval time = 489.54 ms / 104 tokens ( 4.71 ms per token, 212.44 tokens per second) 3.57.814.061 I slot print_timing: id 1 | task 1927 | eval time = 4704.19 ms / 79 tokens ( 60.31 ms per token, 16.58 tokens per second) 3.57.814.062 I slot print_timing: id 1 | task 1927 | total time = 5193.73 ms / 183 tokens 3.57.814.063 I slot print_timing: id 1 | task 1927 | graphs reused = 1452 3.57.814.064 I slot print_timing: id 1 | task 1927 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.814.139 I slot release: id 1 | task 1927 | stop processing: n_tokens = 1307, truncated = 0 3.57.872.458 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.877 3.57.872.510 I slot launch_slot_: id 1 | task 2011 | processing task, is_child = 0 3.59.103.678 I slot print_timing: id 3 | task 1937 | prompt eval time = 481.53 ms / 125 tokens ( 3.85 ms per token, 259.59 tokens per second) 3.59.103.688 I slot print_timing: id 3 | task 1937 | eval time = 5155.54 ms / 87 tokens ( 59.95 ms per token, 16.68 tokens per second) 3.59.103.689 I slot print_timing: id 3 | task 1937 | total time = 5637.07 ms / 212 tokens 3.59.103.690 I slot print_timing: id 3 | task 1937 | graphs reused = 1465 3.59.103.691 I slot print_timing: id 3 | task 1937 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.104.906 I slot release: id 3 | task 1937 | stop processing: n_tokens = 1336, truncated = 0 3.59.152.059 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.858 3.59.152.110 I slot launch_slot_: id 3 | task 2029 | processing task, is_child = 0 3.59.950.860 I slot print_timing: id 2 | task 1840 | prompt eval time = 520.06 ms / 128 tokens ( 4.06 ms per token, 246.13 tokens per second) 3.59.950.868 I slot print_timing: id 2 | task 1840 | eval time = 11869.63 ms / 190 tokens ( 62.80 ms per token, 15.92 tokens per second) 3.59.950.869 I slot print_timing: id 2 | task 1840 | total time = 12389.69 ms / 318 tokens 3.59.950.869 I slot print_timing: id 2 | task 1840 | graphs reused = 1470 3.59.950.870 I slot print_timing: id 2 | task 1840 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.950.950 I slot release: id 2 | task 1840 | stop processing: n_tokens = 1442, truncated = 0 4.00.009.488 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.797 4.00.009.546 I slot launch_slot_: id 2 | task 2039 | processing task, is_child = 0 4.01.469.272 I slot print_timing: id 0 | task 1956 | n_gen = 100, tg = 15.82 t/s, tg_3s = 15.98 t/s 4.01.978.033 I slot print_timing: id 0 | task 1956 | prompt eval time = 449.35 ms / 103 tokens ( 4.36 ms per token, 229.22 tokens per second) 4.01.978.041 I slot print_timing: id 0 | task 1956 | eval time = 6765.88 ms / 110 tokens ( 62.07 ms per token, 16.11 tokens per second) 4.01.978.042 I slot print_timing: id 0 | task 1956 | total time = 7215.23 ms / 213 tokens 4.01.978.043 I slot print_timing: id 0 | task 1956 | graphs reused = 1498 4.01.978.043 I slot print_timing: id 0 | task 1956 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.978.121 I slot release: id 0 | task 1956 | stop processing: n_tokens = 1337, truncated = 0 4.02.026.609 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.857 4.02.026.664 I slot launch_slot_: id 0 | task 2072 | processing task, is_child = 0 4.03.219.610 I slot print_timing: id 1 | task 2011 | prompt eval time = 514.91 ms / 126 tokens ( 4.09 ms per token, 244.70 tokens per second) 4.03.219.618 I slot print_timing: id 1 | task 2011 | eval time = 4832.18 ms / 74 tokens ( 66.19 ms per token, 15.11 tokens per second) 4.03.219.619 I slot print_timing: id 1 | task 2011 | total time = 5347.09 ms / 200 tokens 4.03.219.620 I slot print_timing: id 1 | task 2011 | graphs reused = 1513 4.03.219.621 I slot print_timing: id 1 | task 2011 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.219.703 I slot release: id 1 | task 2011 | stop processing: n_tokens = 1324, truncated = 0 4.03.277.692 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.866 4.03.277.743 I slot launch_slot_: id 1 | task 2091 | processing task, is_child = 0 4.05.396.601 I slot print_timing: id 2 | task 2039 | prompt eval time = 491.78 ms / 108 tokens ( 4.55 ms per token, 219.61 tokens per second) 4.05.396.612 I slot print_timing: id 2 | task 2039 | eval time = 4895.26 ms / 81 tokens ( 61.19 ms per token, 16.34 tokens per second) 4.05.396.613 I slot print_timing: id 2 | task 2039 | total time = 5387.04 ms / 189 tokens 4.05.396.614 I slot print_timing: id 2 | task 2039 | graphs reused = 1542 4.05.396.615 I slot print_timing: id 2 | task 2039 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.396.712 I slot release: id 2 | task 2039 | stop processing: n_tokens = 1313, truncated = 0 4.05.455.097 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.873 4.05.455.159 I slot launch_slot_: id 2 | task 2125 | processing task, is_child = 0 4.06.267.910 I slot print_timing: id 3 | task 2029 | n_gen = 100, tg = 14.94 t/s, tg_3s = 15.09 t/s 4.07.285.151 I slot print_timing: id 0 | task 2072 | prompt eval time = 424.50 ms / 100 tokens ( 4.25 ms per token, 235.57 tokens per second) 4.07.285.160 I slot print_timing: id 0 | task 2072 | eval time = 4833.97 ms / 79 tokens ( 61.97 ms per token, 16.14 tokens per second) 4.07.285.161 I slot print_timing: id 0 | task 2072 | total time = 5258.48 ms / 179 tokens 4.07.285.162 I slot print_timing: id 0 | task 2072 | graphs reused = 1568 4.07.285.163 I slot print_timing: id 0 | task 2072 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.285.237 I slot release: id 0 | task 2072 | stop processing: n_tokens = 1303, truncated = 0 4.07.333.092 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.949 (> 0.100 thold), f_keep = 0.880 4.07.333.144 I slot launch_slot_: id 0 | task 2156 | processing task, is_child = 0 4.07.798.532 I slot print_timing: id 1 | task 2091 | prompt eval time = 587.58 ms / 171 tokens ( 3.44 ms per token, 291.02 tokens per second) 4.07.798.537 I slot print_timing: id 1 | task 2091 | eval time = 3933.20 ms / 65 tokens ( 61.46 ms per token, 16.27 tokens per second) 4.07.798.539 I slot print_timing: id 1 | task 2091 | total time = 4520.77 ms / 236 tokens 4.07.798.540 I slot print_timing: id 1 | task 2091 | graphs reused = 1569 4.07.798.541 I slot print_timing: id 1 | task 2091 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.798.622 I slot release: id 1 | task 2091 | stop processing: n_tokens = 1360, truncated = 0 4.07.857.274 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.843 4.07.857.336 I slot launch_slot_: id 1 | task 2161 | processing task, is_child = 0 4.09.276.170 I slot print_timing: id 3 | task 2029 | n_gen = 145, tg = 14.94 t/s, tg_3s = 14.96 t/s 4.09.886.828 I slot print_timing: id 3 | task 2029 | prompt eval time = 487.77 ms / 125 tokens ( 3.90 ms per token, 256.27 tokens per second) 4.09.886.834 I slot print_timing: id 3 | task 2029 | eval time = 10246.94 ms / 157 tokens ( 65.69 ms per token, 15.22 tokens per second) 4.09.886.835 I slot print_timing: id 3 | task 2029 | total time = 10734.71 ms / 282 tokens 4.09.886.836 I slot print_timing: id 3 | task 2029 | graphs reused = 1598 4.09.886.836 I slot print_timing: id 3 | task 2029 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.886.925 I slot release: id 3 | task 2029 | stop processing: n_tokens = 1406, truncated = 0 4.09.934.203 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.815 4.09.934.254 I slot launch_slot_: id 3 | task 2195 | processing task, is_child = 0 4.10.681.313 I slot print_timing: id 2 | task 2125 | prompt eval time = 452.93 ms / 89 tokens ( 5.09 ms per token, 196.50 tokens per second) 4.10.681.320 I slot print_timing: id 2 | task 2125 | eval time = 4773.22 ms / 74 tokens ( 65.39 ms per token, 15.29 tokens per second) 4.10.681.321 I slot print_timing: id 2 | task 2125 | total time = 5226.14 ms / 163 tokens 4.10.681.322 I slot print_timing: id 2 | task 2125 | graphs reused = 1603 4.10.681.322 I slot print_timing: id 2 | task 2125 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.681.400 I slot release: id 2 | task 2125 | stop processing: n_tokens = 1287, truncated = 0 4.10.739.242 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.890 4.10.739.297 I slot launch_slot_: id 2 | task 2205 | processing task, is_child = 0 4.11.540.788 I slot print_timing: id 1 | task 2161 | prompt eval time = 498.31 ms / 114 tokens ( 4.37 ms per token, 228.77 tokens per second) 4.11.540.796 I slot print_timing: id 1 | task 2161 | eval time = 3185.13 ms / 49 tokens ( 66.36 ms per token, 15.07 tokens per second) 4.11.540.796 I slot print_timing: id 1 | task 2161 | total time = 3683.44 ms / 163 tokens 4.11.540.797 I slot print_timing: id 1 | task 2161 | graphs reused = 1608 4.11.540.798 I slot print_timing: id 1 | task 2161 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.540.880 I slot release: id 1 | task 2161 | stop processing: n_tokens = 1287, truncated = 0 4.11.599.013 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.890 4.11.599.068 I slot launch_slot_: id 1 | task 2215 | processing task, is_child = 0 4.12.116.536 I slot print_timing: id 0 | task 2156 | prompt eval time = 407.17 ms / 82 tokens ( 4.97 ms per token, 201.39 tokens per second) 4.12.116.542 I slot print_timing: id 0 | task 2156 | eval time = 4376.21 ms / 57 tokens ( 78.15 ms per token, 12.80 tokens per second) 4.12.116.543 I slot print_timing: id 0 | task 2156 | total time = 4783.38 ms / 139 tokens 4.12.116.544 I slot print_timing: id 0 | task 2156 | graphs reused = 1608 4.12.116.545 I slot print_timing: id 0 | task 2156 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.116.613 I slot release: id 0 | task 2156 | stop processing: n_tokens = 1263, truncated = 0 4.12.163.868 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.907 4.12.163.925 I slot launch_slot_: id 0 | task 2220 | processing task, is_child = 0 4.14.821.085 I slot print_timing: id 3 | task 2195 | prompt eval time = 437.37 ms / 98 tokens ( 4.46 ms per token, 224.07 tokens per second) 4.14.821.092 I slot print_timing: id 3 | task 2195 | eval time = 4449.45 ms / 66 tokens ( 68.45 ms per token, 14.61 tokens per second) 4.14.821.097 I slot print_timing: id 3 | task 2195 | total time = 4886.82 ms / 164 tokens 4.14.821.098 I slot print_timing: id 3 | task 2195 | graphs reused = 1650 4.14.821.099 I slot print_timing: id 3 | task 2195 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.821.181 I slot release: id 3 | task 2195 | stop processing: n_tokens = 1288, truncated = 0 4.14.867.870 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.890 4.14.867.924 I slot launch_slot_: id 3 | task 2267 | processing task, is_child = 0 4.17.388.945 I slot print_timing: id 2 | task 2205 | n_gen = 100, tg = 16.08 t/s, tg_3s = 16.24 t/s 4.17.490.135 I slot print_timing: id 0 | task 2220 | prompt eval time = 460.00 ms / 113 tokens ( 4.07 ms per token, 245.65 tokens per second) 4.17.490.141 I slot print_timing: id 0 | task 2220 | eval time = 4866.20 ms / 89 tokens ( 55.30 ms per token, 18.08 tokens per second) 4.17.490.142 I slot print_timing: id 0 | task 2220 | total time = 5326.20 ms / 202 tokens 4.17.490.143 I slot print_timing: id 0 | task 2220 | graphs reused = 1691 4.17.490.143 I slot print_timing: id 0 | task 2220 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.490.224 I slot release: id 0 | task 2220 | stop processing: n_tokens = 1326, truncated = 0 4.17.538.266 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.864 4.17.538.323 I slot launch_slot_: id 0 | task 2313 | processing task, is_child = 0 4.18.253.953 I slot print_timing: id 1 | task 2215 | n_gen = 100, tg = 15.99 t/s, tg_3s = 16.15 t/s 4.18.762.460 I slot print_timing: id 2 | task 2205 | prompt eval time = 493.41 ms / 109 tokens ( 4.53 ms per token, 220.91 tokens per second) 4.18.762.467 I slot print_timing: id 2 | task 2205 | eval time = 7529.74 ms / 119 tokens ( 63.81 ms per token, 15.67 tokens per second) 4.18.762.468 I slot print_timing: id 2 | task 2205 | total time = 8023.15 ms / 228 tokens 4.18.762.469 I slot print_timing: id 2 | task 2205 | graphs reused = 1705 4.18.762.470 I slot print_timing: id 2 | task 2205 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.762.547 I slot release: id 2 | task 2205 | stop processing: n_tokens = 1352, truncated = 0 4.18.819.571 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.848 4.18.819.633 I slot launch_slot_: id 2 | task 2331 | processing task, is_child = 0 4.19.526.838 I slot print_timing: id 1 | task 2215 | prompt eval time = 463.13 ms / 97 tokens ( 4.77 ms per token, 209.44 tokens per second) 4.19.526.843 I slot print_timing: id 1 | task 2215 | eval time = 7464.63 ms / 117 tokens ( 64.35 ms per token, 15.54 tokens per second) 4.19.526.844 I slot print_timing: id 1 | task 2215 | total time = 7927.76 ms / 214 tokens 4.19.526.845 I slot print_timing: id 1 | task 2215 | graphs reused = 1708 4.19.526.845 I slot print_timing: id 1 | task 2215 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.526.933 I slot release: id 1 | task 2215 | stop processing: n_tokens = 1338, truncated = 0 4.19.585.146 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.857 4.19.585.219 I slot launch_slot_: id 1 | task 2339 | processing task, is_child = 0 4.20.849.288 I slot print_timing: id 3 | task 2267 | prompt eval time = 480.32 ms / 119 tokens ( 4.04 ms per token, 247.75 tokens per second) 4.20.849.296 I slot print_timing: id 3 | task 2267 | eval time = 5501.03 ms / 85 tokens ( 65.49 ms per token, 15.27 tokens per second) 4.20.849.297 I slot print_timing: id 3 | task 2267 | total time = 5981.35 ms / 204 tokens 4.20.849.298 I slot print_timing: id 3 | task 2267 | graphs reused = 1722 4.20.849.298 I slot print_timing: id 3 | task 2267 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.849.374 I slot release: id 3 | task 2267 | stop processing: n_tokens = 1328, truncated = 0 4.20.896.005 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.863 4.20.896.052 I slot launch_slot_: id 3 | task 2358 | processing task, is_child = 0 4.24.245.009 I slot print_timing: id 0 | task 2313 | n_gen = 100, tg = 15.97 t/s, tg_3s = 16.13 t/s 4.25.111.081 I slot print_timing: id 2 | task 2331 | n_gen = 100, tg = 17.10 t/s, tg_3s = 17.27 t/s 4.25.468.088 I slot print_timing: id 1 | task 2339 | n_gen = 100, tg = 18.38 t/s, tg_3s = 18.57 t/s 4.25.926.673 I slot print_timing: id 1 | task 2339 | prompt eval time = 496.74 ms / 109 tokens ( 4.56 ms per token, 219.43 tokens per second) 4.25.926.681 I slot print_timing: id 1 | task 2339 | eval time = 5844.70 ms / 109 tokens ( 54.12 ms per token, 18.48 tokens per second) 4.25.926.682 I slot print_timing: id 1 | task 2339 | total time = 6341.44 ms / 218 tokens 4.25.926.683 I slot print_timing: id 1 | task 2339 | graphs reused = 1811 4.25.926.684 I slot print_timing: id 1 | task 2339 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.926.772 I slot release: id 1 | task 2339 | stop processing: n_tokens = 1342, truncated = 0 4.25.985.013 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.854 4.25.985.081 I slot launch_slot_: id 1 | task 2452 | processing task, is_child = 0 4.26.706.754 I slot print_timing: id 0 | task 2313 | prompt eval time = 506.74 ms / 134 tokens ( 3.78 ms per token, 264.44 tokens per second) 4.26.706.762 I slot print_timing: id 0 | task 2313 | eval time = 8661.68 ms / 141 tokens ( 61.87 ms per token, 16.16 tokens per second) 4.26.706.763 I slot print_timing: id 0 | task 2313 | total time = 9168.42 ms / 275 tokens 4.26.706.764 I slot print_timing: id 0 | task 2313 | graphs reused = 1815 4.26.706.765 I slot print_timing: id 0 | task 2313 | graph reallocs = 0 / 0 (same size) / (changed size) 4.26.707.859 I slot release: id 0 | task 2313 | stop processing: n_tokens = 1399, truncated = 0 4.26.755.753 I slot print_timing: id 3 | task 2358 | n_gen = 100, tg = 18.26 t/s, tg_3s = 18.44 t/s 4.26.755.761 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.819 4.26.755.808 I slot launch_slot_: id 0 | task 2461 | processing task, is_child = 0 4.28.150.507 I slot print_timing: id 2 | task 2331 | n_gen = 145, tg = 16.31 t/s, tg_3s = 14.81 t/s 4.29.270.901 I slot print_timing: id 3 | task 2358 | prompt eval time = 437.33 ms / 95 tokens ( 4.60 ms per token, 217.23 tokens per second) 4.29.270.909 I slot print_timing: id 3 | task 2358 | eval time = 7937.51 ms / 142 tokens ( 56.29 ms per token, 17.76 tokens per second) 4.29.270.909 I slot print_timing: id 3 | task 2358 | total time = 8374.83 ms / 237 tokens 4.29.270.910 I slot print_timing: id 3 | task 2358 | graphs reused = 1855 4.29.270.911 I slot print_timing: id 3 | task 2358 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.271.011 I slot release: id 3 | task 2358 | stop processing: n_tokens = 1361, truncated = 0 4.29.317.762 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.842 4.29.317.823 I slot launch_slot_: id 3 | task 2505 | processing task, is_child = 0 4.30.500.457 I slot print_timing: id 2 | task 2331 | prompt eval time = 500.74 ms / 112 tokens ( 4.47 ms per token, 223.67 tokens per second) 4.30.500.461 I slot print_timing: id 2 | task 2331 | eval time = 11180.07 ms / 182 tokens ( 61.77 ms per token, 16.19 tokens per second) 4.30.500.462 I slot print_timing: id 2 | task 2331 | total time = 11680.81 ms / 294 tokens 4.30.500.463 I slot print_timing: id 2 | task 2331 | graphs reused = 1866 4.30.500.464 I slot print_timing: id 2 | task 2331 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.500.605 I slot release: id 2 | task 2331 | stop processing: n_tokens = 1418, truncated = 0 4.30.559.631 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.808 4.30.559.682 I slot launch_slot_: id 2 | task 2521 | processing task, is_child = 0 4.32.598.285 I slot print_timing: id 1 | task 2452 | prompt eval time = 463.32 ms / 96 tokens ( 4.83 ms per token, 207.20 tokens per second) 4.32.598.293 I slot print_timing: id 1 | task 2452 | eval time = 6149.87 ms / 97 tokens ( 64.06 ms per token, 15.61 tokens per second) 4.32.598.294 I slot print_timing: id 1 | task 2452 | total time = 6613.19 ms / 193 tokens 4.32.598.295 I slot print_timing: id 1 | task 2452 | graphs reused = 1895 4.32.598.295 I slot print_timing: id 1 | task 2452 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.598.376 I slot release: id 1 | task 2452 | stop processing: n_tokens = 1317, truncated = 0 4.32.656.743 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.870 4.32.656.810 I slot launch_slot_: id 1 | task 2555 | processing task, is_child = 0 4.33.560.926 I slot print_timing: id 0 | task 2461 | n_gen = 100, tg = 15.63 t/s, tg_3s = 15.79 t/s 4.34.833.928 I slot print_timing: id 0 | task 2461 | prompt eval time = 470.86 ms / 122 tokens ( 3.86 ms per token, 259.10 tokens per second) 4.34.833.935 I slot print_timing: id 0 | task 2461 | eval time = 7607.25 ms / 125 tokens ( 61.35 ms per token, 16.30 tokens per second) 4.34.833.936 I slot print_timing: id 0 | task 2461 | total time = 8078.11 ms / 247 tokens 4.34.833.937 I slot print_timing: id 0 | task 2461 | graphs reused = 1927 4.34.833.938 I slot print_timing: id 0 | task 2461 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.834.022 I slot release: id 0 | task 2461 | stop processing: n_tokens = 1371, truncated = 0 4.34.882.255 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.836 4.34.882.298 I slot launch_slot_: id 0 | task 2592 | processing task, is_child = 0 4.36.108.286 I slot print_timing: id 3 | task 2505 | n_gen = 100, tg = 15.89 t/s, tg_3s = 16.05 t/s 4.36.312.357 I slot print_timing: id 3 | task 2505 | prompt eval time = 561.34 ms / 166 tokens ( 3.38 ms per token, 295.72 tokens per second) 4.36.312.362 I slot print_timing: id 3 | task 2505 | eval time = 6433.18 ms / 104 tokens ( 62.46 ms per token, 16.01 tokens per second) 4.36.312.363 I slot print_timing: id 3 | task 2505 | total time = 6994.52 ms / 270 tokens 4.36.312.364 I slot print_timing: id 3 | task 2505 | graphs reused = 1946 4.36.312.365 I slot print_timing: id 3 | task 2505 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.313.220 I slot release: id 3 | task 2505 | stop processing: n_tokens = 1394, truncated = 0 4.36.360.093 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.822 4.36.360.132 I slot launch_slot_: id 3 | task 2615 | processing task, is_child = 0 4.37.269.257 I slot print_timing: id 2 | task 2521 | n_gen = 100, tg = 15.96 t/s, tg_3s = 16.12 t/s 4.38.948.436 I slot print_timing: id 1 | task 2555 | n_gen = 100, tg = 17.08 t/s, tg_3s = 17.25 t/s 4.39.203.003 I slot print_timing: id 1 | task 2555 | prompt eval time = 493.91 ms / 104 tokens ( 4.75 ms per token, 210.57 tokens per second) 4.39.203.008 I slot print_timing: id 1 | task 2555 | eval time = 6052.27 ms / 105 tokens ( 58.19 ms per token, 17.18 tokens per second) 4.39.203.009 I slot print_timing: id 1 | task 2555 | total time = 6546.18 ms / 209 tokens 4.39.203.010 I slot print_timing: id 1 | task 2555 | graphs reused = 1991 4.39.203.010 I slot print_timing: id 1 | task 2555 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.203.123 I slot release: id 1 | task 2555 | stop processing: n_tokens = 1333, truncated = 0 4.39.261.494 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.860 4.39.261.544 I slot launch_slot_: id 1 | task 2665 | processing task, is_child = 0 4.39.814.688 I slot print_timing: id 2 | task 2521 | prompt eval time = 505.46 ms / 117 tokens ( 4.32 ms per token, 231.47 tokens per second) 4.39.814.695 I slot print_timing: id 2 | task 2521 | eval time = 8749.53 ms / 142 tokens ( 62.05 ms per token, 16.12 tokens per second) 4.39.814.696 I slot print_timing: id 2 | task 2521 | total time = 9255.00 ms / 259 tokens 4.39.814.697 I slot print_timing: id 2 | task 2521 | graphs reused = 1991 4.39.814.697 I slot print_timing: id 2 | task 2521 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.814.776 I slot release: id 2 | task 2521 | stop processing: n_tokens = 1383, truncated = 0 4.39.872.508 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.829 4.39.872.561 I slot launch_slot_: id 2 | task 2670 | processing task, is_child = 0 4.41.599.713 I slot print_timing: id 0 | task 2592 | n_gen = 100, tg = 15.81 t/s, tg_3s = 15.97 t/s 4.42.719.629 I slot print_timing: id 3 | task 2615 | n_gen = 100, tg = 16.87 t/s, tg_3s = 17.04 t/s 4.43.329.572 I slot print_timing: id 0 | task 2592 | prompt eval time = 454.50 ms / 108 tokens ( 4.21 ms per token, 237.62 tokens per second) 4.43.329.581 I slot print_timing: id 0 | task 2592 | eval time = 7992.77 ms / 134 tokens ( 60.10 ms per token, 16.64 tokens per second) 4.43.329.582 I slot print_timing: id 0 | task 2592 | total time = 8447.26 ms / 242 tokens 4.43.329.583 I slot print_timing: id 0 | task 2592 | graphs reused = 2048 4.43.329.584 I slot print_timing: id 0 | task 2592 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.329.671 I slot release: id 0 | task 2592 | stop processing: n_tokens = 1366, truncated = 0 4.43.377.600 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.839 4.43.377.658 I slot launch_slot_: id 0 | task 2732 | processing task, is_child = 0 4.44.665.637 I slot print_timing: id 3 | task 2615 | prompt eval time = 491.00 ms / 133 tokens ( 3.69 ms per token, 270.88 tokens per second) 4.44.665.644 I slot print_timing: id 3 | task 2615 | eval time = 7814.50 ms / 131 tokens ( 60.11 ms per token, 16.64 tokens per second) 4.44.665.647 I slot print_timing: id 3 | task 2615 | total time = 8305.50 ms / 264 tokens 4.44.665.647 I slot print_timing: id 3 | task 2615 | graphs reused = 2064 4.44.665.654 I slot print_timing: id 3 | task 2615 | graph reallocs = 0 / 0 (same size) / (changed size) 4.44.665.750 I slot release: id 3 | task 2615 | stop processing: n_tokens = 1388, truncated = 0 4.44.712.875 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.826 4.44.712.922 I slot launch_slot_: id 3 | task 2752 | processing task, is_child = 0 4.45.303.760 I slot print_timing: id 2 | task 2670 | prompt eval time = 503.66 ms / 116 tokens ( 4.34 ms per token, 230.32 tokens per second) 4.45.303.765 I slot print_timing: id 2 | task 2670 | eval time = 4927.53 ms / 83 tokens ( 60.09 ms per token, 16.64 tokens per second) 4.45.303.767 I slot print_timing: id 2 | task 2670 | total time = 5431.19 ms / 199 tokens 4.45.303.768 I slot print_timing: id 2 | task 2670 | graphs reused = 2065 4.45.303.769 I slot print_timing: id 2 | task 2670 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.303.893 I slot release: id 2 | task 2670 | stop processing: n_tokens = 1323, truncated = 0 4.45.362.673 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.866 4.45.362.737 I slot launch_slot_: id 2 | task 2758 | processing task, is_child = 0 4.46.213.326 I slot print_timing: id 1 | task 2665 | prompt eval time = 498.27 ms / 112 tokens ( 4.45 ms per token, 224.78 tokens per second) 4.46.213.336 I slot print_timing: id 1 | task 2665 | eval time = 6453.51 ms / 97 tokens ( 67.22 ms per token, 14.88 tokens per second) 4.46.213.338 I slot print_timing: id 1 | task 2665 | total time = 6951.77 ms / 209 tokens 4.46.213.339 I slot print_timing: id 1 | task 2665 | graphs reused = 2071 4.46.213.340 I slot print_timing: id 1 | task 2665 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.213.453 I slot release: id 1 | task 2665 | stop processing: n_tokens = 1333, truncated = 0 4.46.271.386 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.860 4.46.271.450 I slot launch_slot_: id 1 | task 2769 | processing task, is_child = 0 4.50.094.854 I slot print_timing: id 0 | task 2732 | n_gen = 100, tg = 15.84 t/s, tg_3s = 16.00 t/s 4.50.858.761 I slot print_timing: id 3 | task 2752 | prompt eval time = 481.57 ms / 119 tokens ( 4.05 ms per token, 247.11 tokens per second) 4.50.858.796 I slot print_timing: id 3 | task 2752 | eval time = 5664.26 ms / 96 tokens ( 59.62 ms per token, 16.77 tokens per second) 4.50.858.801 I slot print_timing: id 3 | task 2752 | total time = 6145.83 ms / 215 tokens 4.50.858.802 I slot print_timing: id 3 | task 2752 | graphs reused = 2149 4.50.858.803 I slot print_timing: id 3 | task 2752 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.860.069 I slot release: id 3 | task 2752 | stop processing: n_tokens = 1339, truncated = 0 4.50.907.095 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.856 4.50.907.149 I slot launch_slot_: id 3 | task 2853 | processing task, is_child = 0 4.51.437.357 I slot print_timing: id 1 | task 2769 | prompt eval time = 509.84 ms / 120 tokens ( 4.25 ms per token, 235.37 tokens per second) 4.51.437.362 I slot print_timing: id 1 | task 2769 | eval time = 4656.05 ms / 85 tokens ( 55.43 ms per token, 18.04 tokens per second) 4.51.437.363 I slot print_timing: id 1 | task 2769 | total time = 5165.89 ms / 205 tokens 4.51.437.364 I slot print_timing: id 1 | task 2769 | graphs reused = 2149 4.51.437.365 I slot print_timing: id 1 | task 2769 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.437.444 I slot release: id 1 | task 2769 | stop processing: n_tokens = 1329, truncated = 0 4.51.495.535 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.862 4.51.495.594 I slot launch_slot_: id 1 | task 2858 | processing task, is_child = 0 4.51.960.533 I slot print_timing: id 2 | task 2758 | prompt eval time = 490.14 ms / 103 tokens ( 4.76 ms per token, 210.15 tokens per second) 4.51.960.540 I slot print_timing: id 2 | task 2758 | eval time = 6107.65 ms / 98 tokens ( 62.97 ms per token, 15.88 tokens per second) 4.51.960.541 I slot print_timing: id 2 | task 2758 | total time = 6597.79 ms / 201 tokens 4.51.960.542 I slot print_timing: id 2 | task 2758 | graphs reused = 2149 4.51.960.543 I slot print_timing: id 2 | task 2758 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.960.610 I slot release: id 2 | task 2758 | stop processing: n_tokens = 1325, truncated = 0 4.52.018.574 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.865 4.52.018.623 I slot launch_slot_: id 2 | task 2862 | processing task, is_child = 0 4.53.100.334 I slot print_timing: id 0 | task 2732 | n_gen = 137, tg = 14.69 t/s, tg_3s = 12.31 t/s 4.55.849.552 I slot print_timing: id 1 | task 2858 | prompt eval time = 464.69 ms / 97 tokens ( 4.79 ms per token, 208.74 tokens per second) 4.55.849.556 I slot print_timing: id 1 | task 2858 | eval time = 3889.25 ms / 70 tokens ( 56.37 ms per token, 17.74 tokens per second) 4.55.849.558 I slot print_timing: id 1 | task 2858 | total time = 4353.94 ms / 167 tokens 4.55.849.559 I slot print_timing: id 1 | task 2858 | graphs reused = 2214 4.55.849.560 I slot print_timing: id 1 | task 2858 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.849.635 I slot release: id 1 | task 2858 | stop processing: n_tokens = 1291, truncated = 0 4.55.908.272 I slot print_timing: id 3 | task 2853 | prompt eval time = 473.14 ms / 108 tokens ( 4.38 ms per token, 228.26 tokens per second) 4.55.908.278 I slot print_timing: id 3 | task 2853 | eval time = 4527.97 ms / 75 tokens ( 61.19 ms per token, 16.34 tokens per second) 4.55.908.279 I slot print_timing: id 3 | task 2853 | total time = 5001.11 ms / 183 tokens 4.55.908.279 I slot print_timing: id 3 | task 2853 | graphs reused = 2214 4.55.908.280 I slot print_timing: id 3 | task 2853 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.908.365 I slot release: id 3 | task 2853 | stop processing: n_tokens = 1307, truncated = 0 4.55.908.377 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.888 4.55.908.428 I slot launch_slot_: id 1 | task 2932 | processing task, is_child = 0 4.55.908.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.149 MiB) 4.55.909.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 4.56.845.645 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.877 4.56.845.703 I slot launch_slot_: id 3 | task 2933 | processing task, is_child = 0 4.57.641.220 I slot print_timing: id 0 | task 2732 | n_gen = 193, tg = 13.92 t/s, tg_3s = 12.33 t/s 4.58.005.940 I slot print_timing: id 2 | task 2862 | prompt eval time = 466.29 ms / 100 tokens ( 4.66 ms per token, 214.46 tokens per second) 4.58.005.946 I slot print_timing: id 2 | task 2862 | eval time = 5521.01 ms / 74 tokens ( 75.63 ms per token, 13.22 tokens per second) 4.58.005.947 I slot print_timing: id 2 | task 2862 | total time = 5987.30 ms / 174 tokens 4.58.005.948 I slot print_timing: id 2 | task 2862 | graphs reused = 2217 4.58.005.954 I slot print_timing: id 2 | task 2862 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.006.044 I slot release: id 2 | task 2862 | stop processing: n_tokens = 1298, truncated = 0 4.58.064.633 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.883 4.58.064.693 I slot launch_slot_: id 2 | task 2941 | processing task, is_child = 0 5.00.657.105 I slot print_timing: id 0 | task 2732 | n_gen = 242, tg = 14.33 t/s, tg_3s = 16.25 t/s 5.02.440.943 I slot print_timing: id 2 | task 2941 | prompt eval time = 502.27 ms / 114 tokens ( 4.41 ms per token, 226.97 tokens per second) 5.02.440.951 I slot print_timing: id 2 | task 2941 | eval time = 3873.97 ms / 77 tokens ( 50.97 ms per token, 19.62 tokens per second) 5.02.440.952 I slot print_timing: id 2 | task 2941 | total time = 4376.24 ms / 191 tokens 5.02.440.952 I slot print_timing: id 2 | task 2941 | graphs reused = 2292 5.02.440.953 I slot print_timing: id 2 | task 2941 | graph reallocs = 0 / 0 (same size) / (changed size) 5.02.441.044 I slot release: id 2 | task 2941 | stop processing: n_tokens = 1315, truncated = 0 5.02.499.075 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.871 5.02.499.125 I slot launch_slot_: id 2 | task 3021 | processing task, is_child = 0 5.03.551.445 I slot print_timing: id 0 | task 2732 | prompt eval time = 466.70 ms / 119 tokens ( 3.92 ms per token, 254.98 tokens per second) 5.03.551.449 I slot print_timing: id 0 | task 2732 | eval time = 19707.07 ms / 291 tokens ( 67.96 ms per token, 14.72 tokens per second) 5.03.551.451 I slot print_timing: id 0 | task 2732 | total time = 20173.78 ms / 410 tokens 5.03.551.452 I slot print_timing: id 0 | task 2732 | graphs reused = 2302 5.03.551.462 I slot print_timing: id 0 | task 2732 | graph reallocs = 0 / 0 (same size) / (changed size) 5.03.551.543 I slot release: id 0 | task 2732 | stop processing: n_tokens = 1534, truncated = 0 5.03.599.001 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.747 5.03.599.055 I slot launch_slot_: id 0 | task 3036 | processing task, is_child = 0 5.03.963.712 I slot print_timing: id 1 | task 2932 | n_gen = 100, tg = 16.05 t/s, tg_3s = 16.21 t/s 5.03.965.302 I slot print_timing: id 3 | task 2933 | n_gen = 100, tg = 16.05 t/s, tg_3s = 16.21 t/s 5.06.150.088 I slot print_timing: id 1 | task 2932 | prompt eval time = 948.93 ms / 172 tokens ( 5.52 ms per token, 181.26 tokens per second) 5.06.150.096 I slot print_timing: id 1 | task 2932 | eval time = 8355.44 ms / 142 tokens ( 59.26 ms per token, 16.88 tokens per second) 5.06.150.097 I slot print_timing: id 1 | task 2932 | total time = 9304.37 ms / 314 tokens 5.06.150.098 I slot print_timing: id 1 | task 2932 | graphs reused = 2343 5.06.150.098 I slot print_timing: id 1 | task 2932 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.150.176 I slot release: id 1 | task 2932 | stop processing: n_tokens = 1438, truncated = 0 5.06.208.108 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.797 5.06.208.165 I slot launch_slot_: id 1 | task 3081 | processing task, is_child = 0 5.06.869.419 I slot print_timing: id 3 | task 2933 | prompt eval time = 945.66 ms / 119 tokens ( 7.95 ms per token, 125.84 tokens per second) 5.06.869.428 I slot print_timing: id 3 | task 2933 | eval time = 9074.15 ms / 149 tokens ( 61.31 ms per token, 16.31 tokens per second) 5.06.869.435 I slot print_timing: id 3 | task 2933 | total time = 10019.81 ms / 268 tokens 5.06.869.435 I slot print_timing: id 3 | task 2933 | graphs reused = 2346 5.06.869.436 I slot print_timing: id 3 | task 2933 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.869.515 I slot release: id 3 | task 2933 | stop processing: n_tokens = 1392, truncated = 0 5.06.916.273 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.823 5.06.916.327 I slot launch_slot_: id 3 | task 3089 | processing task, is_child = 0 5.07.870.375 I slot print_timing: id 2 | task 3021 | prompt eval time = 489.07 ms / 104 tokens ( 4.70 ms per token, 212.65 tokens per second) 5.07.870.382 I slot print_timing: id 2 | task 3021 | eval time = 4882.17 ms / 75 tokens ( 65.98 ms per token, 15.16 tokens per second) 5.07.870.383 I slot print_timing: id 2 | task 3021 | total time = 5371.24 ms / 179 tokens 5.07.870.384 I slot print_timing: id 2 | task 3021 | graphs reused = 2354 5.07.870.385 I slot print_timing: id 2 | task 3021 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.870.473 I slot release: id 2 | task 3021 | stop processing: n_tokens = 1303, truncated = 0 5.07.928.977 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.880 5.07.929.038 I slot launch_slot_: id 2 | task 3102 | processing task, is_child = 0 5.08.947.969 I slot print_timing: id 0 | task 3036 | prompt eval time = 461.86 ms / 117 tokens ( 3.95 ms per token, 253.33 tokens per second) 5.08.947.974 I slot print_timing: id 0 | task 3036 | eval time = 4887.05 ms / 75 tokens ( 66.04 ms per token, 15.14 tokens per second) 5.08.947.975 I slot print_timing: id 0 | task 3036 | total time = 5348.90 ms / 192 tokens 5.08.947.976 I slot print_timing: id 0 | task 3036 | graphs reused = 2364 5.08.947.976 I slot print_timing: id 0 | task 3036 | graph reallocs = 0 / 0 (same size) / (changed size) 5.08.948.071 I slot release: id 0 | task 3036 | stop processing: n_tokens = 1316, truncated = 0 5.08.995.926 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.871 5.08.995.974 I slot launch_slot_: id 0 | task 3117 | processing task, is_child = 0 5.11.347.859 I slot print_timing: id 2 | task 3102 | prompt eval time = 456.03 ms / 87 tokens ( 5.24 ms per token, 190.78 tokens per second) 5.11.347.864 I slot print_timing: id 2 | task 3102 | eval time = 2962.77 ms / 51 tokens ( 59.26 ms per token, 16.88 tokens per second) 5.11.347.865 I slot print_timing: id 2 | task 3102 | total time = 3418.81 ms / 138 tokens 5.11.347.866 I slot print_timing: id 2 | task 3102 | graphs reused = 2400 5.11.347.867 I slot print_timing: id 2 | task 3102 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.347.959 I slot release: id 2 | task 3102 | stop processing: n_tokens = 1262, truncated = 0 5.11.406.414 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.908 5.11.406.473 I slot launch_slot_: id 2 | task 3157 | processing task, is_child = 0 5.12.066.797 I slot print_timing: id 1 | task 3081 | prompt eval time = 454.34 ms / 88 tokens ( 5.16 ms per token, 193.69 tokens per second) 5.12.066.803 I slot print_timing: id 1 | task 3081 | eval time = 5404.28 ms / 76 tokens ( 72.06 ms per token, 13.88 tokens per second) 5.12.066.804 I slot print_timing: id 1 | task 3081 | total time = 5858.62 ms / 164 tokens 5.12.066.805 I slot print_timing: id 1 | task 3081 | graphs reused = 2402 5.12.066.806 I slot print_timing: id 1 | task 3081 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.066.873 I slot release: id 1 | task 3081 | stop processing: n_tokens = 1288, truncated = 0 5.12.124.589 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.890 5.12.124.635 I slot launch_slot_: id 1 | task 3164 | processing task, is_child = 0 5.14.048.692 I slot print_timing: id 3 | task 3089 | n_gen = 100, tg = 14.91 t/s, tg_3s = 15.06 t/s 5.15.371.511 I slot print_timing: id 0 | task 3117 | n_gen = 100, tg = 16.89 t/s, tg_3s = 17.06 t/s 5.15.423.295 I slot print_timing: id 3 | task 3089 | prompt eval time = 491.46 ms / 129 tokens ( 3.81 ms per token, 262.48 tokens per second) 5.15.423.299 I slot print_timing: id 3 | task 3089 | eval time = 8015.49 ms / 127 tokens ( 63.61 ms per token, 15.72 tokens per second) 5.15.423.300 I slot print_timing: id 3 | task 3089 | total time = 8506.95 ms / 256 tokens 5.15.423.301 I slot print_timing: id 3 | task 3089 | graphs reused = 2456 5.15.423.301 I slot print_timing: id 3 | task 3089 | graph reallocs = 0 / 0 (same size) / (changed size) 5.15.423.372 I slot release: id 3 | task 3089 | stop processing: n_tokens = 1380, truncated = 0 5.15.469.711 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.830 5.15.469.760 I slot launch_slot_: id 3 | task 3223 | processing task, is_child = 0 5.16.352.055 I slot print_timing: id 0 | task 3117 | prompt eval time = 513.90 ms / 152 tokens ( 3.38 ms per token, 295.78 tokens per second) 5.16.352.059 I slot print_timing: id 0 | task 3117 | eval time = 6842.15 ms / 111 tokens ( 62.20 ms per token, 16.08 tokens per second) 5.16.352.060 I slot print_timing: id 0 | task 3117 | total time = 7356.05 ms / 263 tokens 5.16.352.061 I slot print_timing: id 0 | task 3117 | graphs reused = 2462 5.16.352.062 I slot print_timing: id 0 | task 3117 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.352.139 I slot release: id 0 | task 3117 | stop processing: n_tokens = 1387, truncated = 0 5.16.400.009 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.826 5.16.400.059 I slot launch_slot_: id 0 | task 3234 | processing task, is_child = 0 5.17.383.183 I slot print_timing: id 2 | task 3157 | prompt eval time = 504.50 ms / 118 tokens ( 4.28 ms per token, 233.89 tokens per second) 5.17.383.189 I slot print_timing: id 2 | task 3157 | eval time = 5472.19 ms / 86 tokens ( 64.38 ms per token, 15.53 tokens per second) 5.17.383.190 I slot print_timing: id 2 | task 3157 | total time = 5976.70 ms / 204 tokens 5.17.383.190 I slot print_timing: id 2 | task 3157 | graphs reused = 2473 5.17.383.191 I slot print_timing: id 2 | task 3157 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.383.281 I slot release: id 2 | task 3157 | stop processing: n_tokens = 1328, truncated = 0 5.17.441.326 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.863 5.17.441.380 I slot launch_slot_: id 2 | task 3249 | processing task, is_child = 0 5.18.816.251 I slot print_timing: id 1 | task 3164 | n_gen = 100, tg = 15.98 t/s, tg_3s = 16.14 t/s 5.20.749.485 I slot print_timing: id 1 | task 3164 | prompt eval time = 495.44 ms / 110 tokens ( 4.50 ms per token, 222.02 tokens per second) 5.20.749.493 I slot print_timing: id 1 | task 3164 | eval time = 8129.39 ms / 138 tokens ( 59.34 ms per token, 16.85 tokens per second) 5.20.749.495 I slot print_timing: id 1 | task 3164 | total time = 8624.83 ms / 248 tokens 5.20.749.496 I slot print_timing: id 1 | task 3164 | graphs reused = 2527 5.20.749.497 I slot print_timing: id 1 | task 3164 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.750.900 I slot release: id 1 | task 3164 | stop processing: n_tokens = 1372, truncated = 0 5.20.808.885 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.835 5.20.808.937 I slot launch_slot_: id 1 | task 3308 | processing task, is_child = 0 5.21.737.545 I slot print_timing: id 3 | task 3223 | prompt eval time = 516.45 ms / 135 tokens ( 3.83 ms per token, 261.40 tokens per second) 5.21.737.550 I slot print_timing: id 3 | task 3223 | eval time = 5751.32 ms / 91 tokens ( 63.90 ms per token, 15.65 tokens per second) 5.21.737.551 I slot print_timing: id 3 | task 3223 | total time = 6267.77 ms / 226 tokens 5.21.737.552 I slot print_timing: id 3 | task 3223 | graphs reused = 2534 5.21.737.553 I slot print_timing: id 3 | task 3223 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.737.632 I slot release: id 3 | task 3223 | stop processing: n_tokens = 1350, truncated = 0 5.21.784.119 I slot print_timing: id 0 | task 3234 | prompt eval time = 416.51 ms / 92 tokens ( 4.53 ms per token, 220.89 tokens per second) 5.21.784.123 I slot print_timing: id 0 | task 3234 | eval time = 4967.54 ms / 82 tokens ( 61.33 ms per token, 16.31 tokens per second) 5.21.784.124 I slot print_timing: id 0 | task 3234 | total time = 5384.05 ms / 174 tokens 5.21.784.124 I slot print_timing: id 0 | task 3234 | graphs reused = 2534 5.21.784.125 I slot print_timing: id 0 | task 3234 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.784.188 I slot release: id 0 | task 3234 | stop processing: n_tokens = 1298, truncated = 0 5.21.784.685 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.883 5.21.784.732 I slot launch_slot_: id 0 | task 3320 | processing task, is_child = 0 5.21.784.854 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 5.21.785.708 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.169 MiB) 5.21.786.368 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 5.22.652.014 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.849 5.22.652.075 I slot launch_slot_: id 3 | task 3321 | processing task, is_child = 0 5.24.476.283 I slot print_timing: id 2 | task 3249 | prompt eval time = 507.79 ms / 120 tokens ( 4.23 ms per token, 236.32 tokens per second) 5.24.476.293 I slot print_timing: id 2 | task 3249 | eval time = 6527.10 ms / 91 tokens ( 72.52 ms per token, 13.79 tokens per second) 5.24.476.294 I slot print_timing: id 2 | task 3249 | total time = 7034.89 ms / 211 tokens 5.24.476.295 I slot print_timing: id 2 | task 3249 | graphs reused = 2554 5.24.476.296 I slot print_timing: id 2 | task 3249 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.477.322 I slot release: id 2 | task 3249 | stop processing: n_tokens = 1335, truncated = 0 5.24.535.530 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.858 5.24.535.593 I slot launch_slot_: id 2 | task 3346 | processing task, is_child = 0 5.28.298.114 I slot print_timing: id 1 | task 3308 | n_gen = 100, tg = 14.20 t/s, tg_3s = 14.34 t/s 5.28.705.463 I slot print_timing: id 3 | task 3321 | prompt eval time = 748.86 ms / 98 tokens ( 7.64 ms per token, 130.87 tokens per second) 5.28.705.468 I slot print_timing: id 3 | task 3321 | eval time = 5299.61 ms / 97 tokens ( 55.20 ms per token, 18.11 tokens per second) 5.28.705.469 I slot print_timing: id 3 | task 3321 | total time = 6048.47 ms / 195 tokens 5.28.705.470 I slot print_timing: id 3 | task 3321 | graphs reused = 2625 5.28.705.471 I slot print_timing: id 3 | task 3321 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.705.557 I slot release: id 3 | task 3321 | stop processing: n_tokens = 1319, truncated = 0 5.28.752.791 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.869 5.28.752.838 I slot launch_slot_: id 3 | task 3422 | processing task, is_child = 0 5.29.245.138 I slot print_timing: id 0 | task 3320 | n_gen = 100, tg = 16.95 t/s, tg_3s = 17.12 t/s 5.29.964.498 I slot print_timing: id 0 | task 3320 | prompt eval time = 752.73 ms / 95 tokens ( 7.92 ms per token, 126.21 tokens per second) 5.29.964.506 I slot print_timing: id 0 | task 3320 | eval time = 6559.68 ms / 114 tokens ( 58.05 ms per token, 17.23 tokens per second) 5.29.964.525 I slot print_timing: id 0 | task 3320 | total time = 7312.41 ms / 209 tokens 5.29.964.529 I slot print_timing: id 0 | task 3320 | graphs reused = 2638 5.29.964.530 I slot print_timing: id 0 | task 3320 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.964.609 I slot release: id 0 | task 3320 | stop processing: n_tokens = 1333, truncated = 0 5.30.012.598 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.860 5.30.012.646 I slot launch_slot_: id 0 | task 3440 | processing task, is_child = 0 5.30.824.523 I slot print_timing: id 2 | task 3346 | n_gen = 100, tg = 17.11 t/s, tg_3s = 17.28 t/s 5.30.927.157 I slot print_timing: id 2 | task 3346 | prompt eval time = 502.57 ms / 116 tokens ( 4.33 ms per token, 230.81 tokens per second) 5.30.927.165 I slot print_timing: id 2 | task 3346 | eval time = 5888.98 ms / 102 tokens ( 58.31 ms per token, 17.15 tokens per second) 5.30.927.166 I slot print_timing: id 2 | task 3346 | total time = 6391.55 ms / 218 tokens 5.30.927.167 I slot print_timing: id 2 | task 3346 | graphs reused = 2647 5.30.927.167 I slot print_timing: id 2 | task 3346 | graph reallocs = 0 / 0 (same size) / (changed size) 5.30.927.253 I slot release: id 2 | task 3346 | stop processing: n_tokens = 1342, truncated = 0 5.30.985.690 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.854 5.30.985.745 I slot launch_slot_: id 2 | task 3453 | processing task, is_child = 0 5.31.378.231 I slot print_timing: id 1 | task 3308 | n_gen = 139, tg = 13.73 t/s, tg_3s = 12.66 t/s 5.32.765.106 I slot print_timing: id 1 | task 3308 | prompt eval time = 517.42 ms / 131 tokens ( 3.95 ms per token, 253.18 tokens per second) 5.32.765.114 I slot print_timing: id 1 | task 3308 | eval time = 11438.73 ms / 165 tokens ( 69.75 ms per token, 14.34 tokens per second) 5.32.765.115 I slot print_timing: id 1 | task 3308 | total time = 11956.16 ms / 296 tokens 5.32.765.116 I slot print_timing: id 1 | task 3308 | graphs reused = 2671 5.32.765.116 I slot print_timing: id 1 | task 3308 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.765.205 I slot release: id 1 | task 3308 | stop processing: n_tokens = 1420, truncated = 0 5.32.822.333 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.807 5.32.822.379 I slot launch_slot_: id 1 | task 3482 | processing task, is_child = 0 5.35.478.498 I slot print_timing: id 3 | task 3422 | n_gen = 100, tg = 15.89 t/s, tg_3s = 16.05 t/s 5.36.342.769 I slot print_timing: id 0 | task 3440 | n_gen = 100, tg = 16.83 t/s, tg_3s = 17.00 t/s 5.36.445.826 I slot print_timing: id 3 | task 3422 | prompt eval time = 493.84 ms / 130 tokens ( 3.80 ms per token, 263.24 tokens per second) 5.36.445.831 I slot print_timing: id 3 | task 3422 | eval time = 7199.14 ms / 119 tokens ( 61.01 ms per token, 16.39 tokens per second) 5.36.445.832 I slot print_timing: id 3 | task 3422 | total time = 7692.98 ms / 249 tokens 5.36.445.833 I slot print_timing: id 3 | task 3422 | graphs reused = 2731 5.36.445.834 I slot print_timing: id 3 | task 3422 | graph reallocs = 0 / 0 (same size) / (changed size) 5.36.445.947 I slot release: id 3 | task 3422 | stop processing: n_tokens = 1373, truncated = 0 5.36.493.526 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.835 5.36.493.588 I slot launch_slot_: id 3 | task 3547 | processing task, is_child = 0 5.37.335.440 I slot print_timing: id 2 | task 3453 | n_gen = 100, tg = 16.94 t/s, tg_3s = 17.11 t/s 5.37.843.129 I slot print_timing: id 0 | task 3440 | prompt eval time = 448.02 ms / 103 tokens ( 4.35 ms per token, 229.90 tokens per second) 5.37.843.134 I slot print_timing: id 0 | task 3440 | eval time = 7382.44 ms / 122 tokens ( 61.01 ms per token, 16.39 tokens per second) 5.37.843.135 I slot print_timing: id 0 | task 3440 | total time = 7830.47 ms / 225 tokens 5.37.843.136 I slot print_timing: id 0 | task 3440 | graphs reused = 2747 5.37.843.137 I slot print_timing: id 0 | task 3440 | graph reallocs = 0 / 0 (same size) / (changed size) 5.37.843.225 I slot release: id 0 | task 3440 | stop processing: n_tokens = 1349, truncated = 0 5.37.891.299 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.850 5.37.891.349 I slot launch_slot_: id 0 | task 3568 | processing task, is_child = 0 5.39.126.555 I slot print_timing: id 1 | task 3482 | n_gen = 100, tg = 17.11 t/s, tg_3s = 17.28 t/s 5.40.196.805 I slot print_timing: id 2 | task 3453 | prompt eval time = 506.66 ms / 122 tokens ( 4.15 ms per token, 240.79 tokens per second) 5.40.196.810 I slot print_timing: id 2 | task 3453 | eval time = 8704.39 ms / 149 tokens ( 58.81 ms per token, 17.00 tokens per second) 5.40.196.811 I slot print_timing: id 2 | task 3453 | total time = 9211.05 ms / 271 tokens 5.40.196.811 I slot print_timing: id 2 | task 3453 | graphs reused = 2783 5.40.196.812 I slot print_timing: id 2 | task 3453 | graph reallocs = 0 / 0 (same size) / (changed size) 5.40.196.888 I slot release: id 2 | task 3453 | stop processing: n_tokens = 1395, truncated = 0 5.40.255.296 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 5.40.255.351 I slot launch_slot_: id 2 | task 3608 | processing task, is_child = 0 5.42.146.659 I slot print_timing: id 1 | task 3482 | n_gen = 152, tg = 17.14 t/s, tg_3s = 17.22 t/s 5.42.249.151 I slot print_timing: id 3 | task 3547 | prompt eval time = 481.24 ms / 123 tokens ( 3.91 ms per token, 255.59 tokens per second) 5.42.249.159 I slot print_timing: id 3 | task 3547 | eval time = 5274.31 ms / 90 tokens ( 59.26 ms per token, 16.87 tokens per second) 5.42.249.160 I slot print_timing: id 3 | task 3547 | total time = 5755.55 ms / 213 tokens 5.42.249.160 I slot print_timing: id 3 | task 3547 | graphs reused = 2812 5.42.249.161 I slot print_timing: id 3 | task 3547 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.249.250 I slot release: id 3 | task 3547 | stop processing: n_tokens = 1337, truncated = 0 5.42.296.801 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.857 5.42.296.853 I slot launch_slot_: id 3 | task 3642 | processing task, is_child = 0 5.42.991.023 I slot print_timing: id 1 | task 3482 | prompt eval time = 516.70 ms / 133 tokens ( 3.88 ms per token, 257.40 tokens per second) 5.42.991.030 I slot print_timing: id 1 | task 3482 | eval time = 9651.94 ms / 162 tokens ( 59.95 ms per token, 16.68 tokens per second) 5.42.991.031 I slot print_timing: id 1 | task 3482 | total time = 10168.63 ms / 295 tokens 5.42.991.032 I slot print_timing: id 1 | task 3482 | graphs reused = 2816 5.42.991.032 I slot print_timing: id 1 | task 3482 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.991.106 I slot release: id 1 | task 3482 | stop processing: n_tokens = 1419, truncated = 0 5.43.049.096 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.808 5.43.049.149 I slot launch_slot_: id 1 | task 3651 | processing task, is_child = 0 5.44.566.784 I slot print_timing: id 0 | task 3568 | n_gen = 100, tg = 15.94 t/s, tg_3s = 16.10 t/s 5.45.533.398 I slot print_timing: id 2 | task 3608 | prompt eval time = 462.19 ms / 101 tokens ( 4.58 ms per token, 218.53 tokens per second) 5.45.533.407 I slot print_timing: id 2 | task 3608 | eval time = 4815.85 ms / 80 tokens ( 60.96 ms per token, 16.40 tokens per second) 5.45.533.408 I slot print_timing: id 2 | task 3608 | total time = 5278.03 ms / 181 tokens 5.45.533.408 I slot print_timing: id 2 | task 3608 | graphs reused = 2853 5.45.533.409 I slot print_timing: id 2 | task 3608 | graph reallocs = 0 / 0 (same size) / (changed size) 5.45.533.494 I slot release: id 2 | task 3608 | stop processing: n_tokens = 1305, truncated = 0 5.45.591.833 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.878 5.45.591.882 I slot launch_slot_: id 2 | task 3693 | processing task, is_child = 0 5.46.506.958 I slot print_timing: id 0 | task 3568 | prompt eval time = 465.26 ms / 118 tokens ( 3.94 ms per token, 253.62 tokens per second) 5.46.506.965 I slot print_timing: id 0 | task 3568 | eval time = 8150.34 ms / 131 tokens ( 62.69 ms per token, 15.95 tokens per second) 5.46.506.966 I slot print_timing: id 0 | task 3568 | total time = 8615.60 ms / 249 tokens 5.46.506.967 I slot print_timing: id 0 | task 3568 | graphs reused = 2861 5.46.506.968 I slot print_timing: id 0 | task 3568 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.507.036 I slot release: id 0 | task 3568 | stop processing: n_tokens = 1373, truncated = 0 5.46.554.035 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.835 5.46.554.089 I slot launch_slot_: id 0 | task 3706 | processing task, is_child = 0 5.48.006.849 I slot print_timing: id 3 | task 3642 | prompt eval time = 434.73 ms / 95 tokens ( 4.58 ms per token, 218.52 tokens per second) 5.48.006.854 I slot print_timing: id 3 | task 3642 | eval time = 5275.25 ms / 82 tokens ( 65.13 ms per token, 15.35 tokens per second) 5.48.006.855 I slot print_timing: id 3 | task 3642 | total time = 5709.98 ms / 177 tokens 5.48.006.856 I slot print_timing: id 3 | task 3642 | graphs reused = 2881 5.48.006.857 I slot print_timing: id 3 | task 3642 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.006.968 I slot release: id 3 | task 3642 | stop processing: n_tokens = 1301, truncated = 0 5.48.054.433 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.881 5.48.054.482 I slot launch_slot_: id 3 | task 3730 | processing task, is_child = 0 5.49.664.625 I slot print_timing: id 1 | task 3651 | n_gen = 100, tg = 16.32 t/s, tg_3s = 16.49 t/s 5.49.817.819 I slot print_timing: id 2 | task 3693 | prompt eval time = 453.58 ms / 89 tokens ( 5.10 ms per token, 196.22 tokens per second) 5.49.817.833 I slot print_timing: id 2 | task 3693 | eval time = 3772.34 ms / 62 tokens ( 61.84 ms per token, 16.17 tokens per second) 5.49.817.833 I slot print_timing: id 2 | task 3693 | total time = 4225.92 ms / 151 tokens 5.49.817.834 I slot print_timing: id 2 | task 3693 | graphs reused = 2906 5.49.817.835 I slot print_timing: id 2 | task 3693 | graph reallocs = 0 / 0 (same size) / (changed size) 5.49.817.942 I slot release: id 2 | task 3693 | stop processing: n_tokens = 1275, truncated = 0 5.49.876.193 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.899 5.49.876.244 I slot launch_slot_: id 2 | task 3760 | processing task, is_child = 0 5.51.037.386 I slot print_timing: id 0 | task 3706 | prompt eval time = 429.95 ms / 99 tokens ( 4.34 ms per token, 230.26 tokens per second) 5.51.037.392 I slot print_timing: id 0 | task 3706 | eval time = 4053.34 ms / 66 tokens ( 62.36 ms per token, 16.04 tokens per second) 5.51.037.393 I slot print_timing: id 0 | task 3706 | total time = 4483.29 ms / 165 tokens 5.51.037.394 I slot print_timing: id 0 | task 3706 | graphs reused = 2918 5.51.037.395 I slot print_timing: id 0 | task 3706 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.037.473 I slot release: id 0 | task 3706 | stop processing: n_tokens = 1289, truncated = 0 5.51.085.480 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.889 5.51.085.540 I slot launch_slot_: id 0 | task 3777 | processing task, is_child = 0 5.52.077.191 I slot print_timing: id 3 | task 3730 | prompt eval time = 435.37 ms / 92 tokens ( 4.73 ms per token, 211.31 tokens per second) 5.52.077.197 I slot print_timing: id 3 | task 3730 | eval time = 3587.32 ms / 56 tokens ( 65.22 ms per token, 15.33 tokens per second) 5.52.077.198 I slot print_timing: id 3 | task 3730 | total time = 4022.70 ms / 148 tokens 5.52.077.199 I slot print_timing: id 3 | task 3730 | graphs reused = 2928 5.52.077.206 I slot print_timing: id 3 | task 3730 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.077.316 I slot release: id 3 | task 3730 | stop processing: n_tokens = 1272, truncated = 0 5.52.124.325 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.901 5.52.124.368 I slot launch_slot_: id 3 | task 3791 | processing task, is_child = 0 5.52.714.629 I slot print_timing: id 1 | task 3651 | n_gen = 138, tg = 15.03 t/s, tg_3s = 12.46 t/s 5.55.461.227 I slot print_timing: id 2 | task 3760 | prompt eval time = 497.04 ms / 113 tokens ( 4.40 ms per token, 227.35 tokens per second) 5.55.461.235 I slot print_timing: id 2 | task 3760 | eval time = 5087.93 ms / 87 tokens ( 59.16 ms per token, 16.90 tokens per second) 5.55.461.236 I slot print_timing: id 2 | task 3760 | total time = 5584.97 ms / 200 tokens 5.55.461.236 I slot print_timing: id 2 | task 3760 | graphs reused = 2984 5.55.461.237 I slot print_timing: id 2 | task 3760 | graph reallocs = 0 / 0 (same size) / (changed size) 5.55.461.323 I slot release: id 2 | task 3760 | stop processing: n_tokens = 1324, truncated = 0 5.55.519.166 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.866 5.55.519.217 I slot launch_slot_: id 2 | task 3852 | processing task, is_child = 0 5.55.986.417 I slot print_timing: id 1 | task 3651 | n_gen = 194, tg = 15.58 t/s, tg_3s = 17.12 t/s 5.56.099.859 I slot print_timing: id 1 | task 3651 | prompt eval time = 549.99 ms / 152 tokens ( 3.62 ms per token, 276.37 tokens per second) 5.56.099.866 I slot print_timing: id 1 | task 3651 | eval time = 12500.71 ms / 195 tokens ( 64.44 ms per token, 15.52 tokens per second) 5.56.099.867 I slot print_timing: id 1 | task 3651 | total time = 13050.70 ms / 347 tokens 5.56.099.867 I slot print_timing: id 1 | task 3651 | graphs reused = 2984 5.56.099.868 I slot print_timing: id 1 | task 3651 | graph reallocs = 0 / 0 (same size) / (changed size) 5.56.099.941 I slot release: id 1 | task 3651 | stop processing: n_tokens = 1471, truncated = 0 5.56.157.192 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.779 5.56.157.242 I slot launch_slot_: id 1 | task 3856 | processing task, is_child = 0 5.57.064.027 I slot print_timing: id 3 | task 3791 | prompt eval time = 433.10 ms / 90 tokens ( 4.81 ms per token, 207.80 tokens per second) 5.57.064.035 I slot print_timing: id 3 | task 3791 | eval time = 4506.55 ms / 72 tokens ( 63.47 ms per token, 15.75 tokens per second) 5.57.064.036 I slot print_timing: id 3 | task 3791 | total time = 4939.65 ms / 162 tokens 5.57.064.037 I slot print_timing: id 3 | task 3791 | graphs reused = 2991 5.57.064.038 I slot print_timing: id 3 | task 3791 | graph reallocs = 0 / 0 (same size) / (changed size) 5.57.064.125 I slot release: id 3 | task 3791 | stop processing: n_tokens = 1286, truncated = 0 5.57.111.763 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.891 5.57.111.828 I slot launch_slot_: id 3 | task 3868 | processing task, is_child = 0 5.58.246.408 I slot print_timing: id 0 | task 3777 | n_gen = 100, tg = 14.81 t/s, tg_3s = 14.96 t/s 6.00.891.844 I slot print_timing: id 0 | task 3777 | prompt eval time = 475.01 ms / 118 tokens ( 4.03 ms per token, 248.42 tokens per second) 6.00.891.852 I slot print_timing: id 0 | task 3777 | eval time = 9331.29 ms / 152 tokens ( 61.80 ms per token, 16.18 tokens per second) 6.00.891.853 I slot print_timing: id 0 | task 3777 | total time = 9806.29 ms / 270 tokens 6.00.891.853 I slot print_timing: id 0 | task 3777 | graphs reused = 3054 6.00.891.854 I slot print_timing: id 0 | task 3777 | graph reallocs = 0 / 0 (same size) / (changed size) 6.00.891.936 I slot release: id 0 | task 3777 | stop processing: n_tokens = 1394, truncated = 0 6.00.939.952 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.822 6.00.940.012 I slot launch_slot_: id 0 | task 3936 | processing task, is_child = 0 6.01.866.223 I slot print_timing: id 1 | task 3856 | prompt eval time = 494.25 ms / 107 tokens ( 4.62 ms per token, 216.49 tokens per second) 6.01.866.228 I slot print_timing: id 1 | task 3856 | eval time = 5214.72 ms / 88 tokens ( 59.94 ms per token, 16.68 tokens per second) 6.01.866.229 I slot print_timing: id 1 | task 3856 | total time = 5708.97 ms / 195 tokens 6.01.866.230 I slot print_timing: id 1 | task 3856 | graphs reused = 3063 6.01.866.230 I slot print_timing: id 1 | task 3856 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.866.306 I slot release: id 1 | task 3856 | stop processing: n_tokens = 1319, truncated = 0 6.01.924.789 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.869 6.01.924.852 I slot launch_slot_: id 1 | task 3949 | processing task, is_child = 0 6.02.778.216 I slot print_timing: id 2 | task 3852 | n_gen = 100, tg = 14.82 t/s, tg_3s = 14.97 t/s 6.03.491.821 I slot print_timing: id 3 | task 3868 | n_gen = 100, tg = 16.89 t/s, tg_3s = 17.06 t/s 6.03.746.425 I slot print_timing: id 2 | task 3852 | prompt eval time = 581.06 ms / 170 tokens ( 3.42 ms per token, 292.57 tokens per second) 6.03.746.434 I slot print_timing: id 2 | task 3852 | eval time = 7646.13 ms / 119 tokens ( 64.80 ms per token, 15.43 tokens per second) 6.03.746.435 I slot print_timing: id 2 | task 3852 | total time = 8227.20 ms / 289 tokens 6.03.746.436 I slot print_timing: id 2 | task 3852 | graphs reused = 3087 6.03.746.437 I slot print_timing: id 2 | task 3852 | graph reallocs = 0 / 0 (same size) / (changed size) 6.03.746.525 I slot release: id 2 | task 3852 | stop processing: n_tokens = 1413, truncated = 0 6.03.805.199 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.811 6.03.805.262 I slot launch_slot_: id 2 | task 3978 | processing task, is_child = 0 6.04.613.835 I slot print_timing: id 3 | task 3868 | prompt eval time = 519.23 ms / 147 tokens ( 3.53 ms per token, 283.11 tokens per second) 6.04.613.841 I slot print_timing: id 3 | task 3868 | eval time = 6982.76 ms / 114 tokens ( 61.79 ms per token, 16.18 tokens per second) 6.04.613.842 I slot print_timing: id 3 | task 3868 | total time = 7502.00 ms / 261 tokens 6.04.613.843 I slot print_timing: id 3 | task 3868 | graphs reused = 3092 6.04.613.844 I slot print_timing: id 3 | task 3868 | graph reallocs = 0 / 0 (same size) / (changed size) 6.04.613.953 I slot release: id 3 | task 3868 | stop processing: n_tokens = 1385, truncated = 0 6.04.661.024 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.827 6.04.661.077 I slot launch_slot_: id 3 | task 3988 | processing task, is_child = 0 6.06.354.767 I slot print_timing: id 0 | task 3936 | prompt eval time = 462.34 ms / 109 tokens ( 4.24 ms per token, 235.76 tokens per second) 6.06.354.772 I slot print_timing: id 0 | task 3936 | eval time = 4952.40 ms / 73 tokens ( 68.78 ms per token, 14.54 tokens per second) 6.06.354.773 I slot print_timing: id 0 | task 3936 | total time = 5414.74 ms / 182 tokens 6.06.354.774 I slot print_timing: id 0 | task 3936 | graphs reused = 3114 6.06.354.775 I slot print_timing: id 0 | task 3936 | graph reallocs = 0 / 0 (same size) / (changed size) 6.06.354.866 I slot release: id 0 | task 3936 | stop processing: n_tokens = 1306, truncated = 0 6.06.403.237 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.877 6.06.403.288 I slot launch_slot_: id 0 | task 4015 | processing task, is_child = 0 6.08.716.215 I slot print_timing: id 1 | task 3949 | n_gen = 100, tg = 15.85 t/s, tg_3s = 16.01 t/s 6.10.148.206 I slot print_timing: id 2 | task 3978 | n_gen = 100, tg = 16.94 t/s, tg_3s = 17.11 t/s 6.10.605.110 I slot print_timing: id 3 | task 3988 | n_gen = 100, tg = 18.25 t/s, tg_3s = 18.43 t/s 6.11.267.541 I slot print_timing: id 2 | task 3978 | prompt eval time = 499.11 ms / 110 tokens ( 4.54 ms per token, 220.39 tokens per second) 6.11.267.548 I slot print_timing: id 2 | task 3978 | eval time = 6963.15 ms / 122 tokens ( 57.55 ms per token, 17.38 tokens per second) 6.11.267.549 I slot print_timing: id 2 | task 3978 | total time = 7462.26 ms / 232 tokens 6.11.267.550 I slot print_timing: id 2 | task 3978 | graphs reused = 3200 6.11.267.551 I slot print_timing: id 2 | task 3978 | graph reallocs = 0 / 0 (same size) / (changed size) 6.11.267.633 I slot release: id 2 | task 3978 | stop processing: n_tokens = 1356, truncated = 0 6.11.325.977 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.845 6.11.326.040 I slot launch_slot_: id 2 | task 4105 | processing task, is_child = 0 6.11.789.038 I slot print_timing: id 1 | task 3949 | n_gen = 153, tg = 16.31 t/s, tg_3s = 17.25 t/s 6.11.894.890 I slot print_timing: id 3 | task 3988 | prompt eval time = 518.68 ms / 134 tokens ( 3.87 ms per token, 258.35 tokens per second) 6.11.894.898 I slot print_timing: id 3 | task 3988 | eval time = 6715.12 ms / 118 tokens ( 57.39 ms per token, 17.42 tokens per second) 6.11.894.899 I slot print_timing: id 3 | task 3988 | total time = 7233.80 ms / 252 tokens 6.11.894.900 I slot print_timing: id 3 | task 3988 | graphs reused = 3201 6.11.894.900 I slot print_timing: id 3 | task 3988 | graph reallocs = 0 / 0 (same size) / (changed size) 6.11.894.980 I slot release: id 3 | task 3988 | stop processing: n_tokens = 1376, truncated = 0 6.11.941.890 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.833 6.11.941.936 I slot launch_slot_: id 3 | task 4111 | processing task, is_child = 0 6.12.679.379 I slot print_timing: id 0 | task 4015 | n_gen = 100, tg = 17.05 t/s, tg_3s = 17.22 t/s 6.13.901.221 I slot print_timing: id 0 | task 4015 | prompt eval time = 470.30 ms / 122 tokens ( 3.85 ms per token, 259.41 tokens per second) 6.13.901.229 I slot print_timing: id 0 | task 4015 | eval time = 7027.62 ms / 124 tokens ( 57.14 ms per token, 17.50 tokens per second) 6.13.901.230 I slot print_timing: id 0 | task 4015 | total time = 7497.92 ms / 246 tokens 6.13.901.231 I slot print_timing: id 0 | task 4015 | graphs reused = 3229 6.13.901.232 I slot print_timing: id 0 | task 4015 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.901.313 I slot release: id 0 | task 4015 | stop processing: n_tokens = 1370, truncated = 0 6.13.949.054 I slot print_timing: id 1 | task 3949 | prompt eval time = 544.41 ms / 139 tokens ( 3.92 ms per token, 255.32 tokens per second) 6.13.949.061 I slot print_timing: id 1 | task 3949 | eval time = 11479.78 ms / 188 tokens ( 61.39 ms per token, 16.29 tokens per second) 6.13.949.062 I slot print_timing: id 1 | task 3949 | total time = 12024.19 ms / 327 tokens 6.13.949.062 I slot print_timing: id 1 | task 3949 | graphs reused = 3229 6.13.949.063 I slot print_timing: id 1 | task 3949 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.949.124 I slot release: id 1 | task 3949 | stop processing: n_tokens = 1451, truncated = 0 6.13.949.632 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.836 6.13.949.691 I slot launch_slot_: id 0 | task 4144 | processing task, is_child = 0 6.13.949.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.794 MiB) 6.13.950.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 6.13.951.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.853 MiB) 6.14.667.015 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.790 6.14.667.068 I slot launch_slot_: id 1 | task 4145 | processing task, is_child = 0 6.16.909.602 I slot print_timing: id 2 | task 4105 | prompt eval time = 463.31 ms / 96 tokens ( 4.83 ms per token, 207.21 tokens per second) 6.16.909.608 I slot print_timing: id 2 | task 4105 | eval time = 5120.24 ms / 69 tokens ( 75.30 ms per token, 13.28 tokens per second) 6.16.909.609 I slot print_timing: id 2 | task 4105 | total time = 5583.55 ms / 165 tokens 6.16.909.610 I slot print_timing: id 2 | task 4105 | graphs reused = 3258 6.16.909.610 I slot print_timing: id 2 | task 4105 | graph reallocs = 0 / 0 (same size) / (changed size) 6.16.909.866 I slot release: id 2 | task 4105 | stop processing: n_tokens = 1289, truncated = 0 6.16.967.875 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.889 6.16.967.927 I slot launch_slot_: id 2 | task 4180 | processing task, is_child = 0 6.19.231.040 I slot print_timing: id 3 | task 4111 | n_gen = 100, tg = 14.53 t/s, tg_3s = 14.67 t/s 6.19.485.038 I slot print_timing: id 3 | task 4111 | prompt eval time = 474.52 ms / 111 tokens ( 4.27 ms per token, 233.92 tokens per second) 6.19.485.043 I slot print_timing: id 3 | task 4111 | eval time = 7068.57 ms / 105 tokens ( 67.97 ms per token, 14.71 tokens per second) 6.19.485.044 I slot print_timing: id 3 | task 4111 | total time = 7543.09 ms / 216 tokens 6.19.485.045 I slot print_timing: id 3 | task 4111 | graphs reused = 3295 6.19.485.046 I slot print_timing: id 3 | task 4111 | graph reallocs = 0 / 0 (same size) / (changed size) 6.19.485.142 I slot release: id 3 | task 4111 | stop processing: n_tokens = 1340, truncated = 0 6.19.531.797 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.855 6.19.531.848 I slot launch_slot_: id 3 | task 4222 | processing task, is_child = 0 6.21.175.469 I slot print_timing: id 0 | task 4144 | prompt eval time = 657.40 ms / 101 tokens ( 6.51 ms per token, 153.64 tokens per second) 6.21.175.473 I slot print_timing: id 0 | task 4144 | eval time = 5850.99 ms / 99 tokens ( 59.70 ms per token, 16.75 tokens per second) 6.21.175.473 I slot print_timing: id 0 | task 4144 | total time = 6508.39 ms / 200 tokens 6.21.175.474 I slot print_timing: id 0 | task 4144 | graphs reused = 3317 6.21.175.474 I slot print_timing: id 0 | task 4144 | graph reallocs = 0 / 0 (same size) / (changed size) 6.21.175.563 I slot release: id 0 | task 4144 | stop processing: n_tokens = 1324, truncated = 0 6.21.221.012 I slot print_timing: id 1 | task 4145 | n_gen = 100, tg = 16.79 t/s, tg_3s = 16.96 t/s 6.21.221.325 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.866 6.21.221.376 I slot launch_slot_: id 0 | task 4249 | processing task, is_child = 0 6.23.074.775 I slot print_timing: id 1 | task 4145 | prompt eval time = 654.07 ms / 108 tokens ( 6.06 ms per token, 165.12 tokens per second) 6.23.074.780 I slot print_timing: id 1 | task 4145 | eval time = 7749.76 ms / 129 tokens ( 60.55 ms per token, 16.52 tokens per second) 6.23.074.781 I slot print_timing: id 1 | task 4145 | total time = 8403.83 ms / 237 tokens 6.23.074.782 I slot print_timing: id 1 | task 4145 | graphs reused = 3344 6.23.074.783 I slot print_timing: id 1 | task 4145 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.074.865 I slot release: id 1 | task 4145 | stop processing: n_tokens = 1361, truncated = 0 6.23.133.031 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.842 6.23.133.101 I slot launch_slot_: id 1 | task 4280 | processing task, is_child = 0 6.23.707.749 I slot print_timing: id 2 | task 4180 | n_gen = 100, tg = 16.08 t/s, tg_3s = 16.24 t/s 6.24.673.635 I slot print_timing: id 0 | task 4249 | prompt eval time = 474.06 ms / 128 tokens ( 3.70 ms per token, 270.01 tokens per second) 6.24.673.644 I slot print_timing: id 0 | task 4249 | eval time = 2978.19 ms / 52 tokens ( 58.40 ms per token, 17.12 tokens per second) 6.24.673.646 I slot print_timing: id 0 | task 4249 | total time = 3452.24 ms / 180 tokens 6.24.673.647 I slot print_timing: id 0 | task 4249 | graphs reused = 3364 6.24.673.648 I slot print_timing: id 0 | task 4249 | graph reallocs = 0 / 0 (same size) / (changed size) 6.24.673.787 I slot release: id 0 | task 4249 | stop processing: n_tokens = 1304, truncated = 0 6.24.722.142 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 6.24.722.195 I slot launch_slot_: id 0 | task 4305 | processing task, is_child = 0 6.25.484.907 I slot print_timing: id 2 | task 4180 | prompt eval time = 583.25 ms / 166 tokens ( 3.51 ms per token, 284.61 tokens per second) 6.25.484.914 I slot print_timing: id 2 | task 4180 | eval time = 7933.72 ms / 127 tokens ( 62.97 ms per token, 15.88 tokens per second) 6.25.484.915 I slot print_timing: id 2 | task 4180 | total time = 8516.97 ms / 293 tokens 6.25.484.916 I slot print_timing: id 2 | task 4180 | graphs reused = 3369 6.25.484.917 I slot print_timing: id 2 | task 4180 | graph reallocs = 0 / 0 (same size) / (changed size) 6.25.485.010 I slot release: id 2 | task 4180 | stop processing: n_tokens = 1417, truncated = 0 6.25.542.588 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.809 6.25.542.645 I slot launch_slot_: id 2 | task 4314 | processing task, is_child = 0 6.26.360.414 I slot print_timing: id 3 | task 4222 | prompt eval time = 473.66 ms / 110 tokens ( 4.31 ms per token, 232.23 tokens per second) 6.26.360.424 I slot print_timing: id 3 | task 4222 | eval time = 6354.89 ms / 96 tokens ( 66.89 ms per token, 14.95 tokens per second) 6.26.360.425 I slot print_timing: id 3 | task 4222 | total time = 6828.55 ms / 206 tokens 6.26.360.426 I slot print_timing: id 3 | task 4222 | graphs reused = 3375 6.26.360.427 I slot print_timing: id 3 | task 4222 | graph reallocs = 0 / 0 (same size) / (changed size) 6.26.361.658 I slot release: id 3 | task 4222 | stop processing: n_tokens = 1330, truncated = 0 6.28.506.562 I slot print_timing: id 1 | task 4280 | prompt eval time = 469.01 ms / 95 tokens ( 4.94 ms per token, 202.55 tokens per second) 6.28.506.566 I slot print_timing: id 1 | task 4280 | eval time = 4904.43 ms / 90 tokens ( 55.11 ms per token, 18.15 tokens per second) 6.28.506.567 I slot print_timing: id 1 | task 4280 | total time = 5373.45 ms / 185 tokens 6.28.506.568 I slot print_timing: id 1 | task 4280 | graphs reused = 3424 6.28.506.569 I slot print_timing: id 1 | task 4280 | graph reallocs = 0 / 0 (same size) / (changed size) 6.28.506.662 I slot release: id 1 | task 4280 | stop processing: n_tokens = 1309, truncated = 0 6.29.491.132 I slot print_timing: id 2 | task 4314 | prompt eval time = 457.66 ms / 96 tokens ( 4.77 ms per token, 209.76 tokens per second) 6.29.491.138 I slot print_timing: id 2 | task 4314 | eval time = 3490.81 ms / 80 tokens ( 44.19 ms per token, 22.63 tokens per second) 6.29.491.139 I slot print_timing: id 2 | task 4314 | total time = 3948.47 ms / 176 tokens 6.29.491.140 I slot print_timing: id 2 | task 4314 | graphs reused = 3424 6.29.491.140 I slot print_timing: id 2 | task 4314 | graph reallocs = 0 / 0 (same size) / (changed size) 6.29.491.203 I slot release: id 2 | task 4314 | stop processing: n_tokens = 1300, truncated = 0 6.29.734.759 I slot print_timing: id 0 | task 4305 | prompt eval time = 502.11 ms / 142 tokens ( 3.54 ms per token, 282.81 tokens per second) 6.29.734.765 I slot print_timing: id 0 | task 4305 | eval time = 4510.44 ms / 100 tokens ( 45.56 ms per token, 21.95 tokens per second) 6.29.734.765 I slot print_timing: id 0 | task 4305 | total time = 5012.56 ms / 242 tokens 6.29.734.766 I slot print_timing: id 0 | task 4305 | graphs reused = 3435 6.29.734.767 I slot print_timing: id 0 | task 4305 | graph reallocs = 0 / 0 (same size) / (changed size) 6.29.734.815 I slot release: id 0 | task 4305 | stop processing: n_tokens = 1366, truncated = 0 6.29.787.112 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1330, t_last = 387195801192 6.29.787.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.658 MiB) 6.29.787.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.797 MiB) 6.30.467.485 I slot launch_slot_: id 3 | task 4408 | processing task, is_child = 0 6.30.467.566 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.325 MiB) 6.30.467.587 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.540 MiB) 6.30.467.623 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.618 MiB) 6.31.236.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.188 MiB) 6.31.236.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.051 MiB) 6.31.236.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.716 MiB) 6.32.119.546 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.892 MiB) 6.32.119.911 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.149 MiB) 6.32.943.997 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1309, t_last = 387197946194 6.32.944.176 I slot launch_slot_: id 1 | task 4409 | processing task, is_child = 0 6.32.944.293 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1300, t_last = 387198930735 6.32.944.378 I slot launch_slot_: id 2 | task 4410 | processing task, is_child = 0 6.32.944.437 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1366, t_last = 387199174347 6.32.944.517 I slot launch_slot_: id 0 | task 4411 | processing task, is_child = 0 6.36.846.740 I slot print_timing: id 0 | task 4411 | prompt processing, n_tokens = 436, progress = 0.46, t = 3.90 s / 111.73 tokens per second 6.37.334.768 I slot print_timing: id 1 | task 4409 | prompt processing, n_tokens = 656, progress = 0.84, t = 3.90 s / 168.12 tokens per second 6.37.350.824 I slot print_timing: id 2 | task 4410 | prompt processing, n_tokens = 471, progress = 0.48, t = 3.90 s / 120.71 tokens per second 6.37.364.739 I slot print_timing: id 3 | task 4408 | prompt processing, n_tokens = 290, progress = 0.36, t = 3.90 s / 74.32 tokens per second 6.39.541.432 I slot print_timing: id 0 | task 4411 | prompt processing, n_tokens = 835, progress = 0.88, t = 6.60 s / 126.58 tokens per second 6.39.750.150 I slot print_timing: id 1 | task 4409 | prompt processing, n_tokens = 775, progress = 0.99, t = 6.60 s / 117.48 tokens per second 6.39.765.686 I slot print_timing: id 2 | task 4410 | prompt processing, n_tokens = 877, progress = 0.89, t = 6.60 s / 132.95 tokens per second 6.39.779.410 I slot print_timing: id 3 | task 4408 | prompt processing, n_tokens = 642, progress = 0.80, t = 6.60 s / 97.32 tokens per second 6.40.869.857 I slot print_timing: id 0 | task 4411 | prompt processing, n_tokens = 948, progress = 1.00, t = 7.92 s / 119.65 tokens per second 6.40.887.666 I slot print_timing: id 2 | task 4410 | prompt processing, n_tokens = 983, progress = 1.00, t = 7.92 s / 124.07 tokens per second 6.40.902.310 I slot print_timing: id 3 | task 4408 | prompt processing, n_tokens = 802, progress = 1.00, t = 7.92 s / 101.23 tokens per second 6.41.053.624 I slot print_timing: id 1 | task 4409 | prompt eval time = 7925.09 ms / 779 tokens ( 10.17 ms per token, 98.30 tokens per second) 6.41.053.632 I slot print_timing: id 1 | task 4409 | eval time = 183.85 ms / 2 tokens ( 183.85 ms per token, 5.44 tokens per second) 6.41.053.632 I slot print_timing: id 1 | task 4409 | total time = 8108.94 ms / 781 tokens 6.41.053.633 I slot print_timing: id 1 | task 4409 | graphs reused = 3435 6.41.053.634 I slot print_timing: id 1 | task 4409 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.054.901 I slot release: id 1 | task 4409 | stop processing: n_tokens = 780, truncated = 0 6.41.112.103 I slot print_timing: id 0 | task 4411 | prompt eval time = 8108.74 ms / 952 tokens ( 8.52 ms per token, 117.40 tokens per second) 6.41.112.109 I slot print_timing: id 0 | task 4411 | eval time = 58.84 ms / 2 tokens ( 58.84 ms per token, 17.00 tokens per second) 6.41.112.110 I slot print_timing: id 0 | task 4411 | total time = 8167.58 ms / 954 tokens 6.41.112.111 I slot print_timing: id 0 | task 4411 | graphs reused = 3435 6.41.112.111 I slot print_timing: id 0 | task 4411 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.114.086 I slot release: id 0 | task 4411 | stop processing: n_tokens = 953, truncated = 0 6.41.114.405 I slot print_timing: id 2 | task 4410 | prompt eval time = 8110.84 ms / 987 tokens ( 8.22 ms per token, 121.69 tokens per second) 6.41.114.417 I slot print_timing: id 2 | task 4410 | eval time = 58.80 ms / 2 tokens ( 58.80 ms per token, 17.01 tokens per second) 6.41.114.418 I slot print_timing: id 2 | task 4410 | total time = 8169.65 ms / 989 tokens 6.41.114.419 I slot print_timing: id 2 | task 4410 | graphs reused = 3435 6.41.114.420 I slot print_timing: id 2 | task 4410 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.115.216 I slot release: id 2 | task 4410 | stop processing: n_tokens = 988, truncated = 0 6.41.115.434 I slot print_timing: id 3 | task 4408 | prompt eval time = 8111.43 ms / 806 tokens ( 10.06 ms per token, 99.37 tokens per second) 6.41.115.438 I slot print_timing: id 3 | task 4408 | eval time = 59.16 ms / 2 tokens ( 59.16 ms per token, 16.90 tokens per second) 6.41.115.438 I slot print_timing: id 3 | task 4408 | total time = 8170.59 ms / 808 tokens 6.41.115.439 I slot print_timing: id 3 | task 4408 | graphs reused = 3435 6.41.115.439 I slot print_timing: id 3 | task 4408 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.115.864 I slot release: id 3 | task 4408 | stop processing: n_tokens = 807, truncated = 0 6.41.115.873 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 387210494435 6.41.115.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.875 MiB) 6.41.116.423 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.758 MiB) 6.41.116.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.403 MiB) 6.41.997.250 I slot launch_slot_: id 1 | task 4419 | processing task, is_child = 0 6.41.997.306 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.146 MiB) 6.41.997.665 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.638 MiB) 6.43.057.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.915 MiB) 6.43.057.903 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.266 MiB) 6.43.058.171 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.286 MiB) 6.43.504.124 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.736 MiB) 6.43.504.139 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 6.43.504.147 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.560 MiB) 6.44.175.344 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 387210553620 6.44.175.474 I slot launch_slot_: id 0 | task 4420 | processing task, is_child = 0 6.44.175.561 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 387210554750 6.44.175.625 I slot launch_slot_: id 2 | task 4421 | processing task, is_child = 0 6.44.175.664 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 387210555398 6.44.175.723 I slot launch_slot_: id 3 | task 4422 | processing task, is_child = 0 6.49.332.724 I slot print_timing: id 0 | task 4420 | prompt processing, n_tokens = 696, progress = 0.87, t = 5.16 s / 134.96 tokens per second 6.49.396.283 I slot print_timing: id 1 | task 4419 | prompt processing, n_tokens = 696, progress = 0.87, t = 5.16 s / 134.96 tokens per second 6.49.407.071 I slot print_timing: id 2 | task 4421 | prompt processing, n_tokens = 696, progress = 0.81, t = 5.16 s / 134.97 tokens per second 6.49.408.985 I slot print_timing: id 3 | task 4422 | prompt processing, n_tokens = 696, progress = 0.82, t = 5.16 s / 134.97 tokens per second 6.50.453.267 I slot print_timing: id 0 | task 4420 | prompt processing, n_tokens = 800, progress = 1.00, t = 6.28 s / 127.44 tokens per second 6.50.519.696 I slot print_timing: id 1 | task 4419 | prompt processing, n_tokens = 797, progress = 1.00, t = 6.28 s / 126.96 tokens per second 6.50.536.240 I slot print_timing: id 2 | task 4421 | prompt processing, n_tokens = 851, progress = 1.00, t = 6.28 s / 135.57 tokens per second 6.50.550.883 I slot print_timing: id 3 | task 4422 | prompt processing, n_tokens = 842, progress = 1.00, t = 6.28 s / 134.13 tokens per second 6.50.734.396 I slot print_timing: id 0 | task 4420 | prompt eval time = 6503.22 ms / 804 tokens ( 8.09 ms per token, 123.63 tokens per second) 6.50.734.401 I slot print_timing: id 0 | task 4420 | eval time = 55.44 ms / 2 tokens ( 55.44 ms per token, 18.04 tokens per second) 6.50.734.402 I slot print_timing: id 0 | task 4420 | total time = 6558.66 ms / 806 tokens 6.50.734.402 I slot print_timing: id 0 | task 4420 | graphs reused = 3435 6.50.734.403 I slot print_timing: id 0 | task 4420 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.736.083 I slot release: id 0 | task 4420 | stop processing: n_tokens = 805, truncated = 0 6.50.736.440 I slot print_timing: id 1 | task 4419 | prompt eval time = 6503.87 ms / 801 tokens ( 8.12 ms per token, 123.16 tokens per second) 6.50.736.446 I slot print_timing: id 1 | task 4419 | eval time = 56.77 ms / 2 tokens ( 56.77 ms per token, 17.61 tokens per second) 6.50.736.447 I slot print_timing: id 1 | task 4419 | total time = 6560.64 ms / 803 tokens 6.50.736.447 I slot print_timing: id 1 | task 4419 | graphs reused = 3435 6.50.736.448 I slot print_timing: id 1 | task 4419 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.736.483 I slot release: id 1 | task 4419 | stop processing: n_tokens = 802, truncated = 0 6.50.736.709 I slot print_timing: id 2 | task 4421 | prompt eval time = 6504.57 ms / 855 tokens ( 7.61 ms per token, 131.45 tokens per second) 6.50.736.715 I slot print_timing: id 2 | task 4421 | eval time = 56.28 ms / 2 tokens ( 56.28 ms per token, 17.77 tokens per second) 6.50.736.716 I slot print_timing: id 2 | task 4421 | total time = 6560.86 ms / 857 tokens 6.50.736.716 I slot print_timing: id 2 | task 4421 | graphs reused = 3435 6.50.736.717 I slot print_timing: id 2 | task 4421 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.736.775 I slot release: id 2 | task 4421 | stop processing: n_tokens = 856, truncated = 0 6.50.737.009 I slot print_timing: id 3 | task 4422 | prompt eval time = 6505.18 ms / 846 tokens ( 7.69 ms per token, 130.05 tokens per second) 6.50.737.012 I slot print_timing: id 3 | task 4422 | eval time = 55.92 ms / 2 tokens ( 55.92 ms per token, 17.88 tokens per second) 6.50.737.012 I slot print_timing: id 3 | task 4422 | total time = 6561.10 ms / 848 tokens 6.50.737.013 I slot print_timing: id 3 | task 4422 | graphs reused = 3435 6.50.737.013 I slot print_timing: id 3 | task 4422 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.737.738 I slot release: id 3 | task 4422 | stop processing: n_tokens = 847, truncated = 0 6.50.751.145 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.899 6.50.751.184 I slot launch_slot_: id 0 | task 4430 | processing task, is_child = 0 6.50.751.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.716 MiB) 6.50.751.514 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.677 MiB) 6.51.194.318 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.658 MiB) 6.51.194.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.560 MiB) 6.51.194.597 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.775 MiB) 6.51.720.582 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.641 MiB) 6.51.720.602 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.875 MiB) 6.52.381.630 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 802, t_last = 387220176015 6.52.381.786 I slot launch_slot_: id 1 | task 4431 | processing task, is_child = 0 6.52.381.901 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 387220176307 6.52.381.998 I slot launch_slot_: id 2 | task 4432 | processing task, is_child = 0 6.52.382.045 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 387220177272 6.52.382.107 I slot launch_slot_: id 3 | task 4433 | processing task, is_child = 0 6.55.390.525 I slot print_timing: id 0 | task 4430 | prompt eval time = 2382.66 ms / 129 tokens ( 18.47 ms per token, 54.14 tokens per second) 6.55.390.540 I slot print_timing: id 0 | task 4430 | eval time = 625.71 ms / 2 tokens ( 625.71 ms per token, 1.60 tokens per second) 6.55.390.548 I slot print_timing: id 0 | task 4430 | total time = 3008.38 ms / 131 tokens 6.55.390.550 I slot print_timing: id 0 | task 4430 | graphs reused = 3435 6.55.390.552 I slot print_timing: id 0 | task 4430 | graph reallocs = 0 / 0 (same size) / (changed size) 6.55.392.795 I slot release: id 0 | task 4430 | stop processing: n_tokens = 826, truncated = 0 6.55.392.882 I slot print_timing: id 1 | task 4431 | prompt processing, n_tokens = 380, progress = 0.42, t = 3.00 s / 126.65 tokens per second 6.55.415.653 I slot print_timing: id 2 | task 4432 | prompt processing, n_tokens = 447, progress = 0.46, t = 3.00 s / 148.98 tokens per second 6.55.418.105 I slot print_timing: id 3 | task 4433 | prompt processing, n_tokens = 364, progress = 0.41, t = 3.00 s / 121.32 tokens per second 6.57.544.309 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 387224832333 6.57.544.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.264 MiB) 6.57.545.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.797 MiB) 6.57.546.508 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.110 MiB) 6.58.172.966 I slot launch_slot_: id 0 | task 4438 | processing task, is_child = 0 6.58.173.046 I slot print_timing: id 1 | task 4431 | prompt processing, n_tokens = 754, progress = 0.84, t = 5.16 s / 146.27 tokens per second 6.58.174.938 I slot print_timing: id 2 | task 4432 | prompt processing, n_tokens = 831, progress = 0.86, t = 5.15 s / 161.20 tokens per second 6.58.176.849 I slot print_timing: id 3 | task 4433 | prompt processing, n_tokens = 754, progress = 0.86, t = 5.15 s / 146.27 tokens per second 6.59.479.137 I slot print_timing: id 1 | task 4431 | prompt processing, n_tokens = 892, progress = 1.00, t = 6.91 s / 129.17 tokens per second 6.59.503.851 I slot print_timing: id 2 | task 4432 | prompt processing, n_tokens = 959, progress = 1.00, t = 6.91 s / 138.87 tokens per second 6.59.529.365 I slot print_timing: id 3 | task 4433 | prompt processing, n_tokens = 876, progress = 1.00, t = 6.91 s / 126.86 tokens per second 7.00.388.369 I slot print_timing: id 1 | task 4431 | prompt eval time = 7709.18 ms / 896 tokens ( 8.60 ms per token, 116.23 tokens per second) 7.00.388.385 I slot print_timing: id 1 | task 4431 | eval time = 289.88 ms / 2 tokens ( 289.88 ms per token, 3.45 tokens per second) 7.00.388.388 I slot print_timing: id 1 | task 4431 | total time = 7999.06 ms / 898 tokens 7.00.388.393 I slot print_timing: id 1 | task 4431 | graphs reused = 3435 7.00.388.395 I slot print_timing: id 1 | task 4431 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.391.864 I slot release: id 1 | task 4431 | stop processing: n_tokens = 897, truncated = 0 7.00.392.792 I slot print_timing: id 2 | task 4432 | prompt eval time = 7712.24 ms / 963 tokens ( 8.01 ms per token, 124.87 tokens per second) 7.00.392.800 I slot print_timing: id 2 | task 4432 | eval time = 291.18 ms / 2 tokens ( 291.18 ms per token, 3.43 tokens per second) 7.00.392.801 I slot print_timing: id 2 | task 4432 | total time = 8003.41 ms / 965 tokens 7.00.392.803 I slot print_timing: id 2 | task 4432 | graphs reused = 3435 7.00.392.804 I slot print_timing: id 2 | task 4432 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.393.957 I slot release: id 2 | task 4432 | stop processing: n_tokens = 964, truncated = 0 7.00.394.647 I slot print_timing: id 3 | task 4433 | prompt eval time = 7713.97 ms / 880 tokens ( 8.77 ms per token, 114.08 tokens per second) 7.00.394.653 I slot print_timing: id 3 | task 4433 | eval time = 291.28 ms / 2 tokens ( 291.28 ms per token, 3.43 tokens per second) 7.00.394.658 I slot print_timing: id 3 | task 4433 | total time = 8005.24 ms / 882 tokens 7.00.394.659 I slot print_timing: id 3 | task 4433 | graphs reused = 3435 7.00.394.660 I slot print_timing: id 3 | task 4433 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.394.812 I slot release: id 3 | task 4433 | stop processing: n_tokens = 881, truncated = 0 7.00.421.448 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 387229831400 7.00.421.530 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 7.00.422.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.853 MiB) 7.01.154.310 I slot launch_slot_: id 1 | task 4443 | processing task, is_child = 0 7.01.154.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.325 MiB) 7.01.154.897 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.345 MiB) 7.01.155.365 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.032 MiB) 7.02.060.964 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.091 MiB) 7.02.061.246 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.736 MiB) 7.02.061.548 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.993 MiB) 7.03.087.488 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 964, t_last = 387229833491 7.03.087.645 I slot launch_slot_: id 2 | task 4444 | processing task, is_child = 0 7.03.087.689 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 387229834345 7.03.087.765 I slot launch_slot_: id 3 | task 4445 | processing task, is_child = 0 7.04.207.103 I slot print_timing: id 0 | task 4438 | prompt processing, n_tokens = 983, progress = 1.00, t = 6.03 s / 162.91 tokens per second 7.06.957.691 I slot print_timing: id 0 | task 4438 | prompt eval time = 7395.05 ms / 987 tokens ( 7.49 ms per token, 133.47 tokens per second) 7.06.957.702 I slot print_timing: id 0 | task 4438 | eval time = 1389.64 ms / 2 tokens ( 1389.64 ms per token, 0.72 tokens per second) 7.06.957.704 I slot print_timing: id 0 | task 4438 | total time = 8784.69 ms / 989 tokens 7.06.957.706 I slot print_timing: id 0 | task 4438 | graphs reused = 3435 7.06.957.708 I slot print_timing: id 0 | task 4438 | graph reallocs = 0 / 0 (same size) / (changed size) 7.06.960.309 I slot release: id 0 | task 4438 | stop processing: n_tokens = 988, truncated = 0 7.06.960.379 I slot print_timing: id 1 | task 4443 | prompt processing, n_tokens = 506, progress = 0.50, t = 3.74 s / 135.43 tokens per second 7.07.006.990 I slot print_timing: id 2 | task 4444 | prompt processing, n_tokens = 408, progress = 0.44, t = 3.74 s / 109.20 tokens per second 7.07.012.296 I slot print_timing: id 3 | task 4445 | prompt processing, n_tokens = 753, progress = 0.42, t = 3.74 s / 201.55 tokens per second 7.08.988.636 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 387236399844 7.08.988.782 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.384 MiB) 7.08.989.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.931 MiB) 7.09.390.514 I slot launch_slot_: id 0 | task 4450 | processing task, is_child = 0 7.09.390.613 I slot print_timing: id 1 | task 4443 | prompt processing, n_tokens = 872, progress = 0.85, t = 5.77 s / 151.18 tokens per second 7.09.392.494 I slot print_timing: id 2 | task 4444 | prompt processing, n_tokens = 753, progress = 0.81, t = 5.77 s / 130.55 tokens per second 7.09.395.599 I slot print_timing: id 3 | task 4445 | prompt processing, n_tokens = 1264, progress = 0.71, t = 5.77 s / 219.15 tokens per second 7.11.422.986 I slot print_timing: id 1 | task 4443 | prompt processing, n_tokens = 1018, progress = 1.00, t = 7.56 s / 134.73 tokens per second 7.11.624.400 I slot print_timing: id 2 | task 4444 | prompt processing, n_tokens = 920, progress = 1.00, t = 7.56 s / 121.76 tokens per second 7.11.796.921 I slot print_timing: id 3 | task 4445 | prompt processing, n_tokens = 1776, progress = 1.00, t = 7.56 s / 235.05 tokens per second 7.12.453.444 I slot print_timing: id 0 | task 4450 | prompt processing, n_tokens = 283, progress = 0.30, t = 3.06 s / 92.56 tokens per second 7.12.848.182 I slot print_timing: id 1 | task 4443 | prompt eval time = 9228.05 ms / 1022 tokens ( 9.03 ms per token, 110.75 tokens per second) 7.12.848.188 I slot print_timing: id 1 | task 4443 | eval time = 399.41 ms / 2 tokens ( 399.41 ms per token, 2.50 tokens per second) 7.12.848.189 I slot print_timing: id 1 | task 4443 | total time = 9627.46 ms / 1024 tokens 7.12.848.190 I slot print_timing: id 1 | task 4443 | graphs reused = 3435 7.12.848.191 I slot print_timing: id 1 | task 4443 | graph reallocs = 0 / 0 (same size) / (changed size) 7.12.849.091 I slot release: id 1 | task 4443 | stop processing: n_tokens = 1023, truncated = 0 7.12.850.220 I slot print_timing: id 2 | task 4444 | prompt eval time = 9230.75 ms / 924 tokens ( 9.99 ms per token, 100.10 tokens per second) 7.12.850.225 I slot print_timing: id 2 | task 4444 | eval time = 398.67 ms / 2 tokens ( 398.67 ms per token, 2.51 tokens per second) 7.12.850.226 I slot print_timing: id 2 | task 4444 | total time = 9629.42 ms / 926 tokens 7.12.850.227 I slot print_timing: id 2 | task 4444 | graphs reused = 3435 7.12.850.228 I slot print_timing: id 2 | task 4444 | graph reallocs = 0 / 0 (same size) / (changed size) 7.12.851.805 I slot release: id 2 | task 4444 | stop processing: n_tokens = 925, truncated = 0 7.12.852.718 I slot print_timing: id 3 | task 4445 | prompt eval time = 9232.52 ms / 1780 tokens ( 5.19 ms per token, 192.80 tokens per second) 7.12.852.722 I slot print_timing: id 3 | task 4445 | eval time = 399.34 ms / 2 tokens ( 399.34 ms per token, 2.50 tokens per second) 7.12.852.723 I slot print_timing: id 3 | task 4445 | total time = 9631.86 ms / 1782 tokens 7.12.852.724 I slot print_timing: id 3 | task 4445 | graphs reused = 3435 7.12.852.724 I slot print_timing: id 3 | task 4445 | graph reallocs = 0 / 0 (same size) / (changed size) 7.12.857.227 I slot release: id 3 | task 4445 | stop processing: n_tokens = 1781, truncated = 0 7.12.857.267 I slot print_timing: id 0 | task 4450 | prompt processing, n_tokens = 421, progress = 0.45, t = 3.46 s / 121.78 tokens per second 7.13.133.772 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1023, t_last = 387242288626 7.13.133.841 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.247 MiB) 7.13.134.472 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.660 MiB) 7.13.134.721 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.205 MiB) 7.14.105.907 I slot launch_slot_: id 1 | task 4455 | processing task, is_child = 0 7.14.105.962 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.677 MiB) 7.14.106.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.462 MiB) 7.14.962.576 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.071 MiB) 7.14.962.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.425 MiB) 7.15.654.267 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 387242291339 7.15.654.398 I slot launch_slot_: id 2 | task 4456 | processing task, is_child = 0 7.15.654.471 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1781, t_last = 387242296762 7.15.654.565 I slot launch_slot_: id 3 | task 4457 | processing task, is_child = 0 7.15.654.572 I slot print_timing: id 0 | task 4450 | prompt processing, n_tokens = 753, progress = 0.80, t = 3.74 s / 201.16 tokens per second 7.16.931.743 I slot print_timing: id 0 | task 4450 | prompt processing, n_tokens = 933, progress = 1.00, t = 7.54 s / 123.72 tokens per second 7.19.729.515 I slot print_timing: id 0 | task 4450 | prompt eval time = 8620.30 ms / 937 tokens ( 9.20 ms per token, 108.70 tokens per second) 7.19.729.534 I slot print_timing: id 0 | task 4450 | eval time = 1718.66 ms / 2 tokens ( 1718.66 ms per token, 0.58 tokens per second) 7.19.729.536 I slot print_timing: id 0 | task 4450 | total time = 10338.96 ms / 939 tokens 7.19.729.538 I slot print_timing: id 0 | task 4450 | graphs reused = 3435 7.19.729.540 I slot print_timing: id 0 | task 4450 | graph reallocs = 0 / 0 (same size) / (changed size) 7.19.730.340 I slot release: id 0 | task 4450 | stop processing: n_tokens = 938, truncated = 0 7.19.730.412 I slot print_timing: id 1 | task 4455 | prompt processing, n_tokens = 603, progress = 0.85, t = 3.89 s / 154.82 tokens per second 7.19.740.621 I slot print_timing: id 2 | task 4456 | prompt processing, n_tokens = 364, progress = 0.41, t = 3.89 s / 93.46 tokens per second 7.19.759.882 I slot print_timing: id 3 | task 4457 | prompt processing, n_tokens = 603, progress = 0.81, t = 3.89 s / 154.82 tokens per second 7.20.575.344 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 387249169876 7.20.575.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.073 MiB) 7.21.204.890 I slot launch_slot_: id 0 | task 4462 | processing task, is_child = 0 7.21.204.972 I slot print_timing: id 1 | task 4455 | prompt processing, n_tokens = 709, progress = 0.99, t = 4.74 s / 149.53 tokens per second 7.21.207.198 I slot print_timing: id 2 | task 4456 | prompt processing, n_tokens = 769, progress = 0.87, t = 4.74 s / 162.19 tokens per second 7.21.209.657 I slot print_timing: id 3 | task 4457 | prompt processing, n_tokens = 737, progress = 0.99, t = 4.74 s / 155.44 tokens per second 7.21.973.947 I slot print_timing: id 2 | task 4456 | prompt processing, n_tokens = 876, progress = 1.00, t = 6.13 s / 142.94 tokens per second 7.22.372.008 I slot print_timing: id 1 | task 4455 | prompt eval time = 6129.85 ms / 713 tokens ( 8.60 ms per token, 116.32 tokens per second) 7.22.372.022 I slot print_timing: id 1 | task 4455 | eval time = 408.30 ms / 2 tokens ( 408.30 ms per token, 2.45 tokens per second) 7.22.372.025 I slot print_timing: id 1 | task 4455 | total time = 6538.16 ms / 715 tokens 7.22.372.027 I slot print_timing: id 1 | task 4455 | graphs reused = 3435 7.22.372.029 I slot print_timing: id 1 | task 4455 | graph reallocs = 0 / 0 (same size) / (changed size) 7.22.374.744 I slot release: id 1 | task 4455 | stop processing: n_tokens = 714, truncated = 0 7.22.376.872 I slot print_timing: id 3 | task 4457 | prompt eval time = 6131.98 ms / 741 tokens ( 8.28 ms per token, 120.84 tokens per second) 7.22.376.879 I slot print_timing: id 3 | task 4457 | eval time = 410.92 ms / 2 tokens ( 410.92 ms per token, 2.43 tokens per second) 7.22.376.881 I slot print_timing: id 3 | task 4457 | total time = 6542.89 ms / 743 tokens 7.22.376.881 I slot print_timing: id 3 | task 4457 | graphs reused = 3435 7.22.376.882 I slot print_timing: id 3 | task 4457 | graph reallocs = 0 / 0 (same size) / (changed size) 7.22.377.017 I slot release: id 3 | task 4457 | stop processing: n_tokens = 742, truncated = 0 7.23.295.300 I slot print_timing: id 2 | task 4456 | prompt eval time = 6542.30 ms / 880 tokens ( 7.43 ms per token, 134.51 tokens per second) 7.23.295.322 I slot print_timing: id 2 | task 4456 | eval time = 919.05 ms / 2 tokens ( 919.05 ms per token, 1.09 tokens per second) 7.23.295.325 I slot print_timing: id 2 | task 4456 | total time = 7461.35 ms / 882 tokens 7.23.295.327 I slot print_timing: id 2 | task 4456 | graphs reused = 3435 7.23.295.330 I slot print_timing: id 2 | task 4456 | graph reallocs = 0 / 0 (same size) / (changed size) 7.23.296.708 I slot release: id 2 | task 4456 | stop processing: n_tokens = 881, truncated = 0 7.23.296.756 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 7.23.297.047 I slot launch_slot_: id 1 | task 4466 | processing task, is_child = 0 7.23.297.276 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.213 MiB) 7.24.180.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.624 MiB) 7.25.299.003 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 7.25.299.094 I slot launch_slot_: id 3 | task 4467 | processing task, is_child = 0 7.25.299.145 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 387252736243 7.25.299.210 I slot launch_slot_: id 2 | task 4468 | processing task, is_child = 0 7.26.453.170 I slot print_timing: id 0 | task 4462 | prompt processing, n_tokens = 712, progress = 0.99, t = 5.25 s / 135.66 tokens per second 7.27.354.705 I slot print_timing: id 0 | task 4462 | prompt eval time = 5830.82 ms / 716 tokens ( 8.14 ms per token, 122.80 tokens per second) 7.27.354.720 I slot print_timing: id 0 | task 4462 | eval time = 318.93 ms / 2 tokens ( 318.93 ms per token, 3.14 tokens per second) 7.27.354.722 I slot print_timing: id 0 | task 4462 | total time = 6149.75 ms / 718 tokens 7.27.354.728 I slot print_timing: id 0 | task 4462 | graphs reused = 3435 7.27.355.284 I slot print_timing: id 0 | task 4462 | graph reallocs = 0 / 0 (same size) / (changed size) 7.27.355.956 I slot release: id 0 | task 4462 | stop processing: n_tokens = 717, truncated = 0 7.27.356.740 I slot print_timing: id 1 | task 4466 | prompt eval time = 1548.33 ms / 116 tokens ( 13.35 ms per token, 74.92 tokens per second) 7.27.356.748 I slot print_timing: id 1 | task 4466 | eval time = 319.57 ms / 2 tokens ( 319.57 ms per token, 3.13 tokens per second) 7.27.356.749 I slot print_timing: id 1 | task 4466 | total time = 1867.90 ms / 118 tokens 7.27.356.750 I slot print_timing: id 1 | task 4466 | graphs reused = 3435 7.27.356.751 I slot print_timing: id 1 | task 4466 | graph reallocs = 0 / 0 (same size) / (changed size) 7.27.356.862 I slot release: id 1 | task 4466 | stop processing: n_tokens = 720, truncated = 0 7.27.357.575 I slot print_timing: id 3 | task 4467 | prompt eval time = 1546.53 ms / 122 tokens ( 12.68 ms per token, 78.89 tokens per second) 7.27.357.586 I slot print_timing: id 3 | task 4467 | eval time = 318.78 ms / 2 tokens ( 318.78 ms per token, 3.14 tokens per second) 7.27.357.587 I slot print_timing: id 3 | task 4467 | total time = 1865.31 ms / 124 tokens 7.27.357.588 I slot print_timing: id 3 | task 4467 | graphs reused = 3435 7.27.357.589 I slot print_timing: id 3 | task 4467 | graph reallocs = 0 / 0 (same size) / (changed size) 7.27.357.678 I slot release: id 3 | task 4467 | stop processing: n_tokens = 726, truncated = 0 7.28.094.533 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 387256795490 7.28.094.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.464 MiB) 7.29.037.611 I slot launch_slot_: id 0 | task 4474 | processing task, is_child = 0 7.29.037.662 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 342.439 MiB) 7.30.053.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.073 MiB) 7.30.981.447 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 387256796394 7.30.981.589 I slot launch_slot_: id 1 | task 4475 | processing task, is_child = 0 7.30.981.630 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 387256797210 7.30.981.699 I slot launch_slot_: id 3 | task 4476 | processing task, is_child = 0 7.33.241.336 I slot print_timing: id 2 | task 4468 | prompt eval time = 6561.38 ms / 876 tokens ( 7.49 ms per token, 133.51 tokens per second) 7.33.241.347 I slot print_timing: id 2 | task 4468 | eval time = 1187.74 ms / 2 tokens ( 1187.74 ms per token, 0.84 tokens per second) 7.33.241.349 I slot print_timing: id 2 | task 4468 | total time = 7749.12 ms / 878 tokens 7.33.241.350 I slot print_timing: id 2 | task 4468 | graphs reused = 3435 7.33.241.351 I slot print_timing: id 2 | task 4468 | graph reallocs = 0 / 0 (same size) / (changed size) 7.33.243.358 I slot release: id 2 | task 4468 | stop processing: n_tokens = 877, truncated = 0 7.33.839.491 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 387262682895 7.33.839.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.777 MiB) 7.34.526.921 I slot launch_slot_: id 2 | task 4480 | processing task, is_child = 0 7.36.484.035 I slot print_timing: id 0 | task 4474 | prompt processing, n_tokens = 861, progress = 0.87, t = 5.50 s / 156.48 tokens per second 7.36.913.832 I slot print_timing: id 1 | task 4475 | prompt processing, n_tokens = 861, progress = 0.86, t = 5.50 s / 156.48 tokens per second 7.37.083.764 I slot print_timing: id 3 | task 4476 | prompt processing, n_tokens = 861, progress = 0.83, t = 5.50 s / 156.54 tokens per second 7.38.405.576 I slot print_timing: id 0 | task 4474 | prompt processing, n_tokens = 988, progress = 1.00, t = 7.42 s / 133.08 tokens per second 7.38.585.599 I slot print_timing: id 1 | task 4475 | prompt processing, n_tokens = 1002, progress = 1.00, t = 7.42 s / 134.97 tokens per second 7.38.601.963 I slot print_timing: id 2 | task 4480 | prompt processing, n_tokens = 345, progress = 0.35, t = 3.86 s / 89.26 tokens per second 7.38.601.982 I slot print_timing: id 3 | task 4476 | prompt processing, n_tokens = 1030, progress = 1.00, t = 7.42 s / 138.78 tokens per second 7.39.071.688 I slot print_timing: id 2 | task 4480 | prompt processing, n_tokens = 483, progress = 0.48, t = 4.53 s / 106.71 tokens per second 7.39.818.954 I slot print_timing: id 0 | task 4474 | prompt eval time = 8087.08 ms / 992 tokens ( 8.15 ms per token, 122.66 tokens per second) 7.39.818.968 I slot print_timing: id 0 | task 4474 | eval time = 750.14 ms / 2 tokens ( 750.14 ms per token, 1.33 tokens per second) 7.39.818.969 I slot print_timing: id 0 | task 4474 | total time = 8837.22 ms / 994 tokens 7.39.818.970 I slot print_timing: id 0 | task 4474 | graphs reused = 3435 7.39.818.971 I slot print_timing: id 0 | task 4474 | graph reallocs = 0 / 0 (same size) / (changed size) 7.39.819.251 I slot release: id 0 | task 4474 | stop processing: n_tokens = 993, truncated = 0 7.39.820.139 I slot print_timing: id 1 | task 4475 | prompt eval time = 8088.56 ms / 1006 tokens ( 8.04 ms per token, 124.37 tokens per second) 7.39.820.147 I slot print_timing: id 1 | task 4475 | eval time = 749.79 ms / 2 tokens ( 749.79 ms per token, 1.33 tokens per second) 7.39.820.148 I slot print_timing: id 1 | task 4475 | total time = 8838.35 ms / 1008 tokens 7.39.820.148 I slot print_timing: id 1 | task 4475 | graphs reused = 3435 7.39.820.149 I slot print_timing: id 1 | task 4475 | graph reallocs = 0 / 0 (same size) / (changed size) 7.39.820.224 I slot release: id 1 | task 4475 | stop processing: n_tokens = 1007, truncated = 0 7.39.821.168 I slot print_timing: id 3 | task 4476 | prompt eval time = 8087.71 ms / 1034 tokens ( 7.82 ms per token, 127.85 tokens per second) 7.39.821.171 I slot print_timing: id 3 | task 4476 | eval time = 749.55 ms / 2 tokens ( 749.55 ms per token, 1.33 tokens per second) 7.39.821.174 I slot print_timing: id 3 | task 4476 | total time = 8837.26 ms / 1036 tokens 7.39.821.174 I slot print_timing: id 3 | task 4476 | graphs reused = 3435 7.39.821.175 I slot print_timing: id 3 | task 4476 | graph reallocs = 0 / 0 (same size) / (changed size) 7.39.821.295 I slot release: id 3 | task 4476 | stop processing: n_tokens = 1035, truncated = 0 7.39.821.335 I slot print_timing: id 2 | task 4480 | prompt processing, n_tokens = 861, progress = 0.86, t = 5.28 s / 163.15 tokens per second 7.39.844.050 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.895 7.39.844.099 I slot launch_slot_: id 0 | task 4486 | processing task, is_child = 0 7.39.844.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.663 MiB) 7.40.571.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.487 MiB) 7.41.369.379 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1007, t_last = 387269259756 7.41.369.794 I slot launch_slot_: id 1 | task 4487 | processing task, is_child = 0 7.41.369.844 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 387269260827 7.41.369.910 I slot launch_slot_: id 3 | task 4488 | processing task, is_child = 0 7.41.373.221 I slot print_timing: id 2 | task 4480 | prompt processing, n_tokens = 995, progress = 1.00, t = 5.30 s / 187.61 tokens per second 7.43.408.196 I slot print_timing: id 2 | task 4480 | prompt eval time = 8004.45 ms / 999 tokens ( 8.01 ms per token, 124.81 tokens per second) 7.43.408.213 I slot print_timing: id 2 | task 4480 | eval time = 863.11 ms / 2 tokens ( 863.11 ms per token, 1.16 tokens per second) 7.43.408.214 I slot print_timing: id 2 | task 4480 | total time = 8867.56 ms / 1001 tokens 7.43.408.216 I slot print_timing: id 2 | task 4480 | graphs reused = 3435 7.43.408.217 I slot print_timing: id 2 | task 4480 | graph reallocs = 0 / 0 (same size) / (changed size) 7.43.408.457 I slot release: id 2 | task 4480 | stop processing: n_tokens = 1000, truncated = 0 7.44.061.129 I slot print_timing: id 0 | task 4486 | prompt eval time = 2037.44 ms / 132 tokens ( 15.44 ms per token, 64.79 tokens per second) 7.44.061.142 I slot print_timing: id 0 | task 4486 | eval time = 653.76 ms / 2 tokens ( 653.76 ms per token, 1.53 tokens per second) 7.44.061.144 I slot print_timing: id 0 | task 4486 | total time = 2691.19 ms / 134 tokens 7.44.061.145 I slot print_timing: id 0 | task 4486 | graphs reused = 3435 7.44.061.146 I slot print_timing: id 0 | task 4486 | graph reallocs = 0 / 0 (same size) / (changed size) 7.44.061.286 I slot release: id 0 | task 4486 | stop processing: n_tokens = 994, truncated = 0 7.44.061.304 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 387272847992 7.44.061.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.319 MiB) 7.44.782.453 I slot launch_slot_: id 2 | task 4492 | processing task, is_child = 0 7.44.782.524 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.701 MiB) 7.45.266.945 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 387273500818 7.45.267.079 I slot launch_slot_: id 0 | task 4493 | processing task, is_child = 0 7.46.946.947 I slot print_timing: id 1 | task 4487 | prompt processing, n_tokens = 730, progress = 0.83, t = 5.21 s / 140.13 tokens per second 7.47.004.166 I slot print_timing: id 3 | task 4488 | prompt processing, n_tokens = 773, progress = 0.76, t = 5.21 s / 148.45 tokens per second 7.48.553.237 I slot print_timing: id 0 | task 4493 | prompt processing, n_tokens = 293, progress = 0.29, t = 3.29 s / 89.16 tokens per second 7.48.553.283 I slot print_timing: id 1 | task 4487 | prompt processing, n_tokens = 875, progress = 1.00, t = 7.18 s / 121.87 tokens per second 7.48.780.168 I slot print_timing: id 2 | task 4492 | prompt processing, n_tokens = 293, progress = 0.33, t = 3.28 s / 89.23 tokens per second 7.48.780.202 I slot print_timing: id 3 | task 4488 | prompt processing, n_tokens = 1014, progress = 1.00, t = 7.18 s / 141.27 tokens per second 7.49.822.171 I slot print_timing: id 0 | task 4493 | prompt processing, n_tokens = 493, progress = 0.49, t = 4.55 s / 108.32 tokens per second 7.50.018.571 I slot print_timing: id 2 | task 4492 | prompt processing, n_tokens = 380, progress = 0.42, t = 4.55 s / 83.54 tokens per second 7.51.311.584 I slot print_timing: id 1 | task 4487 | prompt eval time = 8447.08 ms / 879 tokens ( 9.61 ms per token, 104.06 tokens per second) 7.51.311.595 I slot print_timing: id 1 | task 4487 | eval time = 1491.33 ms / 2 tokens ( 1491.33 ms per token, 0.67 tokens per second) 7.51.311.596 I slot print_timing: id 1 | task 4487 | total time = 9938.41 ms / 881 tokens 7.51.311.597 I slot print_timing: id 1 | task 4487 | graphs reused = 3435 7.51.311.598 I slot print_timing: id 1 | task 4487 | graph reallocs = 0 / 0 (same size) / (changed size) 7.51.312.020 I slot release: id 1 | task 4487 | stop processing: n_tokens = 880, truncated = 0 7.51.312.801 I slot print_timing: id 3 | task 4488 | prompt eval time = 8446.60 ms / 1018 tokens ( 8.30 ms per token, 120.52 tokens per second) 7.51.312.809 I slot print_timing: id 3 | task 4488 | eval time = 1490.68 ms / 2 tokens ( 1490.68 ms per token, 0.67 tokens per second) 7.51.312.809 I slot print_timing: id 3 | task 4488 | total time = 9937.28 ms / 1020 tokens 7.51.312.810 I slot print_timing: id 3 | task 4488 | graphs reused = 3435 7.51.312.811 I slot print_timing: id 3 | task 4488 | graph reallocs = 0 / 0 (same size) / (changed size) 7.51.322.644 I slot release: id 3 | task 4488 | stop processing: n_tokens = 1019, truncated = 0 7.51.322.682 I slot print_timing: id 0 | task 4493 | prompt processing, n_tokens = 773, progress = 0.77, t = 6.04 s / 127.90 tokens per second 7.51.364.321 I slot print_timing: id 2 | task 4492 | prompt processing, n_tokens = 773, progress = 0.86, t = 6.04 s / 127.94 tokens per second 7.52.051.705 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 7.52.051.919 I slot launch_slot_: id 3 | task 4499 | processing task, is_child = 0 7.52.052.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.386 MiB) 7.52.796.874 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 387280751554 7.52.797.073 I slot launch_slot_: id 1 | task 4500 | processing task, is_child = 0 7.52.797.087 I slot print_timing: id 0 | task 4493 | prompt processing, n_tokens = 1005, progress = 1.00, t = 6.78 s / 148.13 tokens per second 7.52.808.431 I slot print_timing: id 2 | task 4492 | prompt processing, n_tokens = 892, progress = 1.00, t = 6.78 s / 131.52 tokens per second 7.54.082.007 I slot print_timing: id 0 | task 4493 | prompt eval time = 8290.19 ms / 1009 tokens ( 8.22 ms per token, 121.71 tokens per second) 7.54.082.019 I slot print_timing: id 0 | task 4493 | eval time = 524.70 ms / 2 tokens ( 524.70 ms per token, 1.91 tokens per second) 7.54.082.022 I slot print_timing: id 0 | task 4493 | total time = 8814.89 ms / 1011 tokens 7.54.082.024 I slot print_timing: id 0 | task 4493 | graphs reused = 3435 7.54.082.026 I slot print_timing: id 0 | task 4493 | graph reallocs = 0 / 0 (same size) / (changed size) 7.54.085.952 I slot release: id 0 | task 4493 | stop processing: n_tokens = 1010, truncated = 0 7.54.086.635 I slot print_timing: id 2 | task 4492 | prompt eval time = 8288.72 ms / 896 tokens ( 9.25 ms per token, 108.10 tokens per second) 7.54.086.640 I slot print_timing: id 2 | task 4492 | eval time = 528.51 ms / 2 tokens ( 528.51 ms per token, 1.89 tokens per second) 7.54.086.641 I slot print_timing: id 2 | task 4492 | total time = 8817.23 ms / 898 tokens 7.54.086.642 I slot print_timing: id 2 | task 4492 | graphs reused = 3435 7.54.086.643 I slot print_timing: id 2 | task 4492 | graph reallocs = 0 / 0 (same size) / (changed size) 7.54.086.881 I slot release: id 2 | task 4492 | stop processing: n_tokens = 897, truncated = 0 7.54.510.710 I slot print_timing: id 3 | task 4499 | prompt eval time = 1277.03 ms / 129 tokens ( 9.90 ms per token, 101.02 tokens per second) 7.54.510.728 I slot print_timing: id 3 | task 4499 | eval time = 421.93 ms / 2 tokens ( 421.93 ms per token, 2.37 tokens per second) 7.54.510.731 I slot print_timing: id 3 | task 4499 | total time = 1698.96 ms / 131 tokens 7.54.510.733 I slot print_timing: id 3 | task 4499 | graphs reused = 3435 7.54.510.735 I slot print_timing: id 3 | task 4499 | graph reallocs = 0 / 0 (same size) / (changed size) 7.54.511.019 I slot release: id 3 | task 4499 | stop processing: n_tokens = 903, truncated = 0 7.54.511.071 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.793 7.54.511.460 I slot launch_slot_: id 0 | task 4504 | processing task, is_child = 0 7.54.511.788 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.847 MiB) 7.55.129.704 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.749 MiB) 7.55.892.655 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 387283526416 7.55.892.799 I slot launch_slot_: id 2 | task 4505 | processing task, is_child = 0 7.55.892.845 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 387283950552 7.55.892.907 I slot launch_slot_: id 3 | task 4506 | processing task, is_child = 0 7.57.465.491 I slot print_timing: id 1 | task 4500 | prompt processing, n_tokens = 773, progress = 0.78, t = 4.25 s / 181.85 tokens per second 7.58.492.044 I slot print_timing: id 1 | task 4500 | prompt processing, n_tokens = 981, progress = 1.00, t = 5.68 s / 172.66 tokens per second 7.59.349.747 I slot print_timing: id 0 | task 4504 | prompt eval time = 2599.03 ms / 108 tokens ( 24.07 ms per token, 41.55 tokens per second) 7.59.349.762 I slot print_timing: id 0 | task 4504 | eval time = 857.77 ms / 2 tokens ( 857.77 ms per token, 1.17 tokens per second) 7.59.349.764 I slot print_timing: id 0 | task 4504 | total time = 3456.80 ms / 110 tokens 7.59.349.766 I slot print_timing: id 0 | task 4504 | graphs reused = 3435 7.59.349.768 I slot print_timing: id 0 | task 4504 | graph reallocs = 0 / 0 (same size) / (changed size) 7.59.350.527 I slot release: id 0 | task 4504 | stop processing: n_tokens = 882, truncated = 0 7.59.351.725 I slot print_timing: id 2 | task 4505 | prompt processing, n_tokens = 436, progress = 0.46, t = 3.20 s / 136.18 tokens per second 7.59.362.233 I slot print_timing: id 3 | task 4506 | prompt processing, n_tokens = 390, progress = 0.43, t = 3.20 s / 121.82 tokens per second 8.00.832.566 I slot print_timing: id 1 | task 4500 | prompt eval time = 6543.32 ms / 985 tokens ( 6.64 ms per token, 150.54 tokens per second) 8.00.832.587 I slot print_timing: id 1 | task 4500 | eval time = 1480.86 ms / 2 tokens ( 1480.86 ms per token, 0.68 tokens per second) 8.00.832.599 I slot print_timing: id 1 | task 4500 | total time = 8024.18 ms / 987 tokens 8.00.832.601 I slot print_timing: id 1 | task 4500 | graphs reused = 3435 8.00.832.603 I slot print_timing: id 1 | task 4500 | graph reallocs = 0 / 0 (same size) / (changed size) 8.00.835.001 I slot release: id 1 | task 4500 | stop processing: n_tokens = 986, truncated = 0 8.00.835.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 387288790063 8.00.835.325 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.805 MiB) 8.01.432.263 I slot launch_slot_: id 0 | task 4511 | processing task, is_child = 0 8.01.432.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.629 MiB) 8.02.332.514 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 387290274538 8.02.332.667 I slot launch_slot_: id 1 | task 4512 | processing task, is_child = 0 8.02.332.823 I slot print_timing: id 2 | task 4505 | prompt processing, n_tokens = 774, progress = 0.81, t = 4.68 s / 165.23 tokens per second 8.02.335.431 I slot print_timing: id 3 | task 4506 | prompt processing, n_tokens = 774, progress = 0.85, t = 4.68 s / 165.23 tokens per second 8.03.728.793 I slot print_timing: id 2 | task 4505 | prompt processing, n_tokens = 948, progress = 1.00, t = 7.55 s / 125.63 tokens per second 8.03.735.422 I slot print_timing: id 3 | task 4506 | prompt processing, n_tokens = 902, progress = 1.00, t = 7.55 s / 119.54 tokens per second 8.05.859.553 I slot print_timing: id 2 | task 4505 | prompt eval time = 8531.51 ms / 952 tokens ( 8.96 ms per token, 111.59 tokens per second) 8.05.859.568 I slot print_timing: id 2 | task 4505 | eval time = 1180.66 ms / 2 tokens ( 1180.66 ms per token, 0.85 tokens per second) 8.05.859.571 I slot print_timing: id 2 | task 4505 | total time = 9712.17 ms / 954 tokens 8.05.859.573 I slot print_timing: id 2 | task 4505 | graphs reused = 3435 8.05.859.575 I slot print_timing: id 2 | task 4505 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.863.606 I slot release: id 2 | task 4505 | stop processing: n_tokens = 953, truncated = 0 8.05.864.294 I slot print_timing: id 3 | task 4506 | prompt eval time = 8532.20 ms / 906 tokens ( 9.42 ms per token, 106.19 tokens per second) 8.05.864.300 I slot print_timing: id 3 | task 4506 | eval time = 1184.65 ms / 2 tokens ( 1184.65 ms per token, 0.84 tokens per second) 8.05.864.300 I slot print_timing: id 3 | task 4506 | total time = 9716.85 ms / 908 tokens 8.05.864.301 I slot print_timing: id 3 | task 4506 | graphs reused = 3435 8.05.864.302 I slot print_timing: id 3 | task 4506 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.864.458 I slot release: id 3 | task 4506 | stop processing: n_tokens = 907, truncated = 0 8.05.864.503 I slot print_timing: id 0 | task 4511 | prompt processing, n_tokens = 424, progress = 0.45, t = 3.53 s / 120.25 tokens per second 8.05.874.369 I slot print_timing: id 1 | task 4512 | prompt processing, n_tokens = 840, progress = 0.62, t = 3.53 s / 238.23 tokens per second 8.07.257.134 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 387295303141 8.07.257.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.218 MiB) 8.07.894.425 I slot launch_slot_: id 2 | task 4517 | processing task, is_child = 0 8.07.894.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.606 MiB) 8.08.574.354 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 387295303991 8.08.574.477 I slot launch_slot_: id 3 | task 4518 | processing task, is_child = 0 8.08.574.486 I slot print_timing: id 0 | task 4511 | prompt processing, n_tokens = 774, progress = 0.82, t = 4.92 s / 157.18 tokens per second 8.08.583.990 I slot print_timing: id 1 | task 4512 | prompt processing, n_tokens = 1152, progress = 0.85, t = 4.92 s / 233.94 tokens per second 8.10.199.251 I slot print_timing: id 0 | task 4511 | prompt processing, n_tokens = 936, progress = 1.00, t = 7.87 s / 118.98 tokens per second 8.10.344.159 I slot print_timing: id 1 | task 4512 | prompt processing, n_tokens = 1352, progress = 1.00, t = 7.87 s / 171.87 tokens per second 8.12.722.277 I slot print_timing: id 0 | task 4511 | prompt eval time = 8957.54 ms / 940 tokens ( 9.53 ms per token, 104.94 tokens per second) 8.12.723.626 I slot print_timing: id 0 | task 4511 | eval time = 1432.04 ms / 2 tokens ( 1432.04 ms per token, 0.70 tokens per second) 8.12.723.639 I slot print_timing: id 0 | task 4511 | total time = 10389.58 ms / 942 tokens 8.12.723.640 I slot print_timing: id 0 | task 4511 | graphs reused = 3435 8.12.723.642 I slot print_timing: id 0 | task 4511 | graph reallocs = 0 / 0 (same size) / (changed size) 8.12.724.353 I slot release: id 0 | task 4511 | stop processing: n_tokens = 941, truncated = 0 8.12.725.021 I slot print_timing: id 1 | task 4512 | prompt eval time = 8958.63 ms / 1356 tokens ( 6.61 ms per token, 151.36 tokens per second) 8.12.725.025 I slot print_timing: id 1 | task 4512 | eval time = 1433.63 ms / 2 tokens ( 1433.63 ms per token, 0.70 tokens per second) 8.12.725.026 I slot print_timing: id 1 | task 4512 | total time = 10392.26 ms / 1358 tokens 8.12.725.027 I slot print_timing: id 1 | task 4512 | graphs reused = 3435 8.12.725.028 I slot print_timing: id 1 | task 4512 | graph reallocs = 0 / 0 (same size) / (changed size) 8.12.728.181 I slot release: id 1 | task 4512 | stop processing: n_tokens = 1357, truncated = 0 8.12.728.229 I slot print_timing: id 2 | task 4517 | prompt processing, n_tokens = 743, progress = 0.59, t = 3.95 s / 188.11 tokens per second 8.12.772.878 I slot print_timing: id 3 | task 4518 | prompt processing, n_tokens = 826, progress = 0.62, t = 3.95 s / 209.13 tokens per second 8.13.987.262 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.870 8.13.987.470 I slot launch_slot_: id 1 | task 4523 | processing task, is_child = 0 8.13.987.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.917 MiB) 8.14.724.429 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 387302163888 8.14.724.553 I slot launch_slot_: id 0 | task 4524 | processing task, is_child = 0 8.14.729.977 I slot print_timing: id 2 | task 4517 | prompt processing, n_tokens = 1152, progress = 0.92, t = 5.22 s / 220.88 tokens per second 8.14.731.858 I slot print_timing: id 3 | task 4518 | prompt processing, n_tokens = 1152, progress = 0.86, t = 5.22 s / 220.89 tokens per second 8.16.062.313 I slot print_timing: id 2 | task 4517 | prompt processing, n_tokens = 1255, progress = 1.00, t = 7.02 s / 178.87 tokens per second 8.16.066.869 I slot print_timing: id 3 | task 4518 | prompt processing, n_tokens = 1338, progress = 1.00, t = 7.02 s / 190.70 tokens per second 8.17.311.645 I slot print_timing: id 1 | task 4523 | prompt eval time = 1804.58 ms / 148 tokens ( 12.19 ms per token, 82.01 tokens per second) 8.17.311.673 I slot print_timing: id 1 | task 4523 | eval time = 782.40 ms / 2 tokens ( 782.40 ms per token, 1.28 tokens per second) 8.17.311.682 I slot print_timing: id 1 | task 4523 | total time = 2586.98 ms / 150 tokens 8.17.311.687 I slot print_timing: id 1 | task 4523 | graphs reused = 3435 8.17.311.692 I slot print_timing: id 1 | task 4523 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.311.944 I slot release: id 1 | task 4523 | stop processing: n_tokens = 1301, truncated = 0 8.17.312.830 I slot print_timing: id 2 | task 4517 | prompt eval time = 7758.29 ms / 1259 tokens ( 6.16 ms per token, 162.28 tokens per second) 8.17.312.840 I slot print_timing: id 2 | task 4517 | eval time = 782.73 ms / 2 tokens ( 782.73 ms per token, 1.28 tokens per second) 8.17.312.842 I slot print_timing: id 2 | task 4517 | total time = 8541.02 ms / 1261 tokens 8.17.312.844 I slot print_timing: id 2 | task 4517 | graphs reused = 3435 8.17.312.847 I slot print_timing: id 2 | task 4517 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.313.015 I slot release: id 2 | task 4517 | stop processing: n_tokens = 1260, truncated = 0 8.17.314.124 I slot print_timing: id 3 | task 4518 | prompt eval time = 7760.06 ms / 1342 tokens ( 5.78 ms per token, 172.94 tokens per second) 8.17.314.128 I slot print_timing: id 3 | task 4518 | eval time = 782.16 ms / 2 tokens ( 782.16 ms per token, 1.28 tokens per second) 8.17.314.129 I slot print_timing: id 3 | task 4518 | total time = 8542.23 ms / 1344 tokens 8.17.314.130 I slot print_timing: id 3 | task 4518 | graphs reused = 3435 8.17.314.131 I slot print_timing: id 3 | task 4518 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.316.161 I slot release: id 3 | task 4518 | stop processing: n_tokens = 1343, truncated = 0 8.17.341.321 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1301, t_last = 387306751476 8.17.341.424 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.294 MiB) 8.18.006.699 I slot launch_slot_: id 1 | task 4529 | processing task, is_child = 0 8.18.006.774 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.386 MiB) 8.18.554.445 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.070 MiB) 8.19.395.641 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1260, t_last = 387306752547 8.19.395.777 I slot launch_slot_: id 2 | task 4530 | processing task, is_child = 0 8.19.395.837 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1343, t_last = 387306755695 8.19.395.913 I slot launch_slot_: id 3 | task 4531 | processing task, is_child = 0 8.21.379.990 I slot print_timing: id 0 | task 4524 | prompt eval time = 5817.12 ms / 792 tokens ( 7.34 ms per token, 136.15 tokens per second) 8.21.380.005 I slot print_timing: id 0 | task 4524 | eval time = 838.28 ms / 2 tokens ( 838.28 ms per token, 1.19 tokens per second) 8.21.380.007 I slot print_timing: id 0 | task 4524 | total time = 6655.40 ms / 794 tokens 8.21.380.009 I slot print_timing: id 0 | task 4524 | graphs reused = 3435 8.21.380.011 I slot print_timing: id 0 | task 4524 | graph reallocs = 0 / 0 (same size) / (changed size) 8.21.384.221 I slot release: id 0 | task 4524 | stop processing: n_tokens = 793, truncated = 0 8.21.758.744 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 387310823756 8.21.758.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.154 MiB) 8.22.105.067 I slot launch_slot_: id 0 | task 4535 | processing task, is_child = 0 8.24.759.103 I slot print_timing: id 1 | task 4529 | prompt processing, n_tokens = 681, progress = 0.84, t = 5.10 s / 133.55 tokens per second 8.24.766.464 I slot print_timing: id 2 | task 4530 | prompt processing, n_tokens = 741, progress = 0.86, t = 5.10 s / 145.32 tokens per second 8.24.932.392 I slot print_timing: id 3 | task 4531 | prompt processing, n_tokens = 741, progress = 0.83, t = 5.10 s / 145.32 tokens per second 8.25.860.393 I slot print_timing: id 0 | task 4535 | prompt processing, n_tokens = 274, progress = 0.35, t = 3.76 s / 72.96 tokens per second 8.26.005.139 I slot print_timing: id 1 | task 4529 | prompt processing, n_tokens = 804, progress = 1.00, t = 6.27 s / 128.27 tokens per second 8.26.020.677 I slot print_timing: id 2 | task 4530 | prompt processing, n_tokens = 855, progress = 1.00, t = 6.27 s / 136.41 tokens per second 8.26.034.447 I slot print_timing: id 3 | task 4531 | prompt processing, n_tokens = 887, progress = 1.00, t = 6.27 s / 141.51 tokens per second 8.26.815.151 I slot print_timing: id 0 | task 4535 | prompt processing, n_tokens = 655, progress = 0.83, t = 4.71 s / 139.19 tokens per second 8.27.239.582 I slot print_timing: id 1 | task 4529 | prompt eval time = 7220.24 ms / 808 tokens ( 8.94 ms per token, 111.91 tokens per second) 8.27.239.601 I slot print_timing: id 1 | task 4529 | eval time = 427.07 ms / 2 tokens ( 427.07 ms per token, 2.34 tokens per second) 8.27.239.603 I slot print_timing: id 1 | task 4529 | total time = 7647.31 ms / 810 tokens 8.27.239.606 I slot print_timing: id 1 | task 4529 | graphs reused = 3435 8.27.239.608 I slot print_timing: id 1 | task 4529 | graph reallocs = 0 / 0 (same size) / (changed size) 8.27.240.140 I slot release: id 1 | task 4529 | stop processing: n_tokens = 809, truncated = 0 8.27.241.663 I slot print_timing: id 2 | task 4530 | prompt eval time = 7221.57 ms / 859 tokens ( 8.41 ms per token, 118.95 tokens per second) 8.27.241.669 I slot print_timing: id 2 | task 4530 | eval time = 427.77 ms / 2 tokens ( 427.77 ms per token, 2.34 tokens per second) 8.27.241.670 I slot print_timing: id 2 | task 4530 | total time = 7649.34 ms / 861 tokens 8.27.241.671 I slot print_timing: id 2 | task 4530 | graphs reused = 3435 8.27.241.672 I slot print_timing: id 2 | task 4530 | graph reallocs = 0 / 0 (same size) / (changed size) 8.27.244.639 I slot release: id 2 | task 4530 | stop processing: n_tokens = 860, truncated = 0 8.27.246.022 I slot print_timing: id 3 | task 4531 | prompt eval time = 7222.68 ms / 891 tokens ( 8.11 ms per token, 123.36 tokens per second) 8.27.246.026 I slot print_timing: id 3 | task 4531 | eval time = 430.92 ms / 2 tokens ( 430.92 ms per token, 2.32 tokens per second) 8.27.246.028 I slot print_timing: id 3 | task 4531 | total time = 7653.61 ms / 893 tokens 8.27.246.028 I slot print_timing: id 3 | task 4531 | graphs reused = 3435 8.27.246.029 I slot print_timing: id 3 | task 4531 | graph reallocs = 0 / 0 (same size) / (changed size) 8.27.246.153 I slot release: id 3 | task 4531 | stop processing: n_tokens = 892, truncated = 0 8.27.246.195 I slot print_timing: id 0 | task 4535 | prompt processing, n_tokens = 786, progress = 0.99, t = 5.13 s / 153.13 tokens per second 8.27.316.504 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 809, t_last = 387316679679 8.27.316.582 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 348.892 MiB) 8.28.167.488 I slot launch_slot_: id 1 | task 4541 | processing task, is_child = 0 8.28.167.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.408 MiB) 8.29.282.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.294 MiB) 8.30.249.495 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 387316684175 8.30.249.630 I slot launch_slot_: id 2 | task 4542 | processing task, is_child = 0 8.30.249.672 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 892, t_last = 387316685686 8.30.249.733 I slot launch_slot_: id 3 | task 4543 | processing task, is_child = 0 8.31.161.076 I slot print_timing: id 0 | task 4535 | prompt eval time = 5211.42 ms / 790 tokens ( 6.60 ms per token, 151.59 tokens per second) 8.31.161.097 I slot print_timing: id 0 | task 4535 | eval time = 3844.48 ms / 2 tokens ( 3844.48 ms per token, 0.26 tokens per second) 8.31.161.099 I slot print_timing: id 0 | task 4535 | total time = 9055.89 ms / 792 tokens 8.31.161.102 I slot print_timing: id 0 | task 4535 | graphs reused = 3435 8.31.161.104 I slot print_timing: id 0 | task 4535 | graph reallocs = 0 / 0 (same size) / (changed size) 8.31.161.857 I slot release: id 0 | task 4535 | stop processing: n_tokens = 791, truncated = 0 8.31.763.778 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.852 (> 0.100 thold), f_keep = 0.863 8.31.763.874 I slot launch_slot_: id 0 | task 4546 | processing task, is_child = 0 8.33.921.059 I slot print_timing: id 1 | task 4541 | prompt processing, n_tokens = 655, progress = 0.85, t = 3.06 s / 214.08 tokens per second 8.33.930.103 I slot print_timing: id 2 | task 4542 | prompt processing, n_tokens = 339, progress = 0.40, t = 3.06 s / 110.80 tokens per second 8.33.958.632 I slot print_timing: id 3 | task 4543 | prompt processing, n_tokens = 655, progress = 0.84, t = 3.06 s / 214.09 tokens per second 8.35.179.553 I slot print_timing: id 1 | task 4541 | prompt processing, n_tokens = 770, progress = 0.99, t = 4.93 s / 156.23 tokens per second 8.35.199.841 I slot print_timing: id 2 | task 4542 | prompt processing, n_tokens = 655, progress = 0.77, t = 4.93 s / 132.90 tokens per second 8.35.204.128 I slot print_timing: id 3 | task 4543 | prompt processing, n_tokens = 774, progress = 0.99, t = 4.93 s / 157.04 tokens per second 8.35.800.950 I slot print_timing: id 0 | task 4546 | prompt eval time = 3415.56 ms / 147 tokens ( 23.24 ms per token, 43.04 tokens per second) 8.35.800.969 I slot print_timing: id 0 | task 4546 | eval time = 621.47 ms / 2 tokens ( 621.47 ms per token, 1.61 tokens per second) 8.35.800.971 I slot print_timing: id 0 | task 4546 | total time = 4037.03 ms / 149 tokens 8.35.800.973 I slot print_timing: id 0 | task 4546 | graphs reused = 3435 8.35.800.975 I slot print_timing: id 0 | task 4546 | graph reallocs = 0 / 0 (same size) / (changed size) 8.35.803.231 I slot release: id 0 | task 4546 | stop processing: n_tokens = 803, truncated = 0 8.35.804.956 I slot print_timing: id 2 | task 4542 | prompt processing, n_tokens = 851, progress = 1.00, t = 5.55 s / 153.33 tokens per second 8.35.911.097 I slot print_timing: id 1 | task 4541 | prompt eval time = 5554.36 ms / 774 tokens ( 7.18 ms per token, 139.35 tokens per second) 8.35.911.103 I slot print_timing: id 1 | task 4541 | eval time = 106.99 ms / 2 tokens ( 106.99 ms per token, 9.35 tokens per second) 8.35.911.104 I slot print_timing: id 1 | task 4541 | total time = 5661.35 ms / 776 tokens 8.35.911.105 I slot print_timing: id 1 | task 4541 | graphs reused = 3435 8.35.911.105 I slot print_timing: id 1 | task 4541 | graph reallocs = 0 / 0 (same size) / (changed size) 8.35.911.154 I slot release: id 1 | task 4541 | stop processing: n_tokens = 775, truncated = 0 8.35.911.794 I slot print_timing: id 3 | task 4543 | prompt eval time = 5555.04 ms / 778 tokens ( 7.14 ms per token, 140.05 tokens per second) 8.35.911.797 I slot print_timing: id 3 | task 4543 | eval time = 106.89 ms / 2 tokens ( 106.89 ms per token, 9.36 tokens per second) 8.35.911.798 I slot print_timing: id 3 | task 4543 | total time = 5661.93 ms / 780 tokens 8.35.911.798 I slot print_timing: id 3 | task 4543 | graphs reused = 3435 8.35.911.799 I slot print_timing: id 3 | task 4543 | graph reallocs = 0 / 0 (same size) / (changed size) 8.35.911.868 I slot release: id 3 | task 4543 | stop processing: n_tokens = 779, truncated = 0 8.35.911.876 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 387325242768 8.35.911.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.576 MiB) 8.36.897.348 I slot launch_slot_: id 0 | task 4551 | processing task, is_child = 0 8.36.897.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.087 MiB) 8.37.696.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.145 MiB) 8.38.669.993 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 775, t_last = 387325350686 8.38.670.154 I slot launch_slot_: id 1 | task 4552 | processing task, is_child = 0 8.38.670.194 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 387325351400 8.38.670.256 I slot launch_slot_: id 3 | task 4553 | processing task, is_child = 0 8.39.833.246 I slot print_timing: id 2 | task 4542 | prompt eval time = 5661.63 ms / 855 tokens ( 6.62 ms per token, 151.02 tokens per second) 8.39.833.263 I slot print_timing: id 2 | task 4542 | eval time = 3921.74 ms / 2 tokens ( 3921.74 ms per token, 0.25 tokens per second) 8.39.833.266 I slot print_timing: id 2 | task 4542 | total time = 9583.38 ms / 857 tokens 8.39.833.268 I slot print_timing: id 2 | task 4542 | graphs reused = 3435 8.39.833.270 I slot print_timing: id 2 | task 4542 | graph reallocs = 0 / 0 (same size) / (changed size) 8.39.833.880 I slot release: id 2 | task 4542 | stop processing: n_tokens = 856, truncated = 0 8.40.433.393 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 387329273416 8.40.433.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.263 MiB) 8.40.842.776 I slot launch_slot_: id 2 | task 4556 | processing task, is_child = 0 8.41.756.239 I slot print_timing: id 0 | task 4551 | prompt processing, n_tokens = 455, progress = 0.47, t = 3.09 s / 147.44 tokens per second 8.41.998.436 I slot print_timing: id 1 | task 4552 | prompt processing, n_tokens = 448, progress = 0.46, t = 3.09 s / 145.18 tokens per second 8.42.012.416 I slot print_timing: id 3 | task 4553 | prompt processing, n_tokens = 428, progress = 0.45, t = 3.09 s / 138.70 tokens per second 8.43.949.574 I slot print_timing: id 0 | task 4551 | prompt processing, n_tokens = 836, progress = 0.86, t = 5.28 s / 158.35 tokens per second 8.44.478.904 I slot print_timing: id 1 | task 4552 | prompt processing, n_tokens = 836, progress = 0.87, t = 5.28 s / 158.36 tokens per second 8.44.483.601 I slot print_timing: id 2 | task 4556 | prompt processing, n_tokens = 333, progress = 0.35, t = 3.11 s / 107.19 tokens per second 8.44.483.622 I slot print_timing: id 3 | task 4553 | prompt processing, n_tokens = 836, progress = 0.89, t = 5.28 s / 158.36 tokens per second 8.45.499.751 I slot print_timing: id 0 | task 4551 | prompt processing, n_tokens = 967, progress = 1.00, t = 6.83 s / 141.59 tokens per second 8.45.663.251 I slot print_timing: id 1 | task 4552 | prompt processing, n_tokens = 960, progress = 1.00, t = 6.83 s / 140.57 tokens per second 8.45.686.638 I slot print_timing: id 2 | task 4556 | prompt processing, n_tokens = 431, progress = 0.46, t = 4.66 s / 92.55 tokens per second 8.45.886.615 I slot print_timing: id 3 | task 4553 | prompt processing, n_tokens = 940, progress = 1.00, t = 6.83 s / 137.64 tokens per second 8.46.715.695 I slot print_timing: id 2 | task 4556 | prompt processing, n_tokens = 836, progress = 0.88, t = 5.87 s / 142.42 tokens per second 8.47.137.797 I slot print_timing: id 0 | task 4551 | prompt eval time = 8043.20 ms / 971 tokens ( 8.28 ms per token, 120.72 tokens per second) 8.47.137.816 I slot print_timing: id 0 | task 4551 | eval time = 424.29 ms / 2 tokens ( 424.29 ms per token, 2.36 tokens per second) 8.47.137.818 I slot print_timing: id 0 | task 4551 | total time = 8467.49 ms / 973 tokens 8.47.137.820 I slot print_timing: id 0 | task 4551 | graphs reused = 3435 8.47.137.822 I slot print_timing: id 0 | task 4551 | graph reallocs = 0 / 0 (same size) / (changed size) 8.47.139.037 I slot release: id 0 | task 4551 | stop processing: n_tokens = 972, truncated = 0 8.47.139.955 I slot print_timing: id 1 | task 4552 | prompt eval time = 8044.39 ms / 964 tokens ( 8.34 ms per token, 119.84 tokens per second) 8.47.139.964 I slot print_timing: id 1 | task 4552 | eval time = 425.18 ms / 2 tokens ( 425.18 ms per token, 2.35 tokens per second) 8.47.139.966 I slot print_timing: id 1 | task 4552 | total time = 8469.57 ms / 966 tokens 8.47.139.968 I slot print_timing: id 1 | task 4552 | graphs reused = 3435 8.47.139.969 I slot print_timing: id 1 | task 4552 | graph reallocs = 0 / 0 (same size) / (changed size) 8.47.140.117 I slot release: id 1 | task 4552 | stop processing: n_tokens = 965, truncated = 0 8.47.140.986 I slot print_timing: id 3 | task 4553 | prompt eval time = 8045.21 ms / 944 tokens ( 8.52 ms per token, 117.34 tokens per second) 8.47.140.990 I slot print_timing: id 3 | task 4553 | eval time = 425.35 ms / 2 tokens ( 425.35 ms per token, 2.35 tokens per second) 8.47.140.995 I slot print_timing: id 3 | task 4553 | total time = 8470.56 ms / 946 tokens 8.47.141.004 I slot print_timing: id 3 | task 4553 | graphs reused = 3435 8.47.141.004 I slot print_timing: id 3 | task 4553 | graph reallocs = 0 / 0 (same size) / (changed size) 8.47.141.063 I slot release: id 3 | task 4553 | stop processing: n_tokens = 945, truncated = 0 8.47.141.100 I slot print_timing: id 2 | task 4556 | prompt processing, n_tokens = 943, progress = 1.00, t = 6.29 s / 149.82 tokens per second 8.47.199.865 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 8.47.199.919 I slot launch_slot_: id 0 | task 4563 | processing task, is_child = 0 8.47.200.026 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.215 MiB) 8.48.235.448 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.757 MiB) 8.48.988.491 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 387336579649 8.48.988.640 I slot launch_slot_: id 1 | task 4564 | processing task, is_child = 0 8.48.988.686 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 387336580595 8.48.988.753 I slot launch_slot_: id 3 | task 4565 | processing task, is_child = 0 8.50.190.780 I slot print_timing: id 2 | task 4556 | prompt eval time = 6357.05 ms / 947 tokens ( 6.71 ms per token, 148.97 tokens per second) 8.50.190.800 I slot print_timing: id 2 | task 4556 | eval time = 2990.89 ms / 2 tokens ( 2990.89 ms per token, 0.33 tokens per second) 8.50.190.806 I slot print_timing: id 2 | task 4556 | total time = 9347.94 ms / 949 tokens 8.50.190.808 I slot print_timing: id 2 | task 4556 | graphs reused = 3435 8.50.190.810 I slot print_timing: id 2 | task 4556 | graph reallocs = 0 / 0 (same size) / (changed size) 8.50.191.319 I slot release: id 2 | task 4556 | stop processing: n_tokens = 948, truncated = 0 8.50.905.400 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 387339630853 8.50.905.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.305 MiB) 8.51.134.144 I slot launch_slot_: id 2 | task 4568 | processing task, is_child = 0 8.53.142.765 I slot print_timing: id 0 | task 4563 | prompt eval time = 1916.57 ms / 133 tokens ( 14.41 ms per token, 69.39 tokens per second) 8.53.142.786 I slot print_timing: id 0 | task 4563 | eval time = 2237.39 ms / 2 tokens ( 2237.39 ms per token, 0.45 tokens per second) 8.53.142.789 I slot print_timing: id 0 | task 4563 | total time = 4153.97 ms / 135 tokens 8.53.142.791 I slot print_timing: id 0 | task 4563 | graphs reused = 3435 8.53.142.793 I slot print_timing: id 0 | task 4563 | graph reallocs = 0 / 0 (same size) / (changed size) 8.53.144.749 I slot release: id 0 | task 4563 | stop processing: n_tokens = 970, truncated = 0 8.53.144.817 I slot print_timing: id 1 | task 4564 | prompt processing, n_tokens = 679, progress = 0.85, t = 4.15 s / 163.70 tokens per second 8.53.210.463 I slot print_timing: id 3 | task 4565 | prompt processing, n_tokens = 679, progress = 0.85, t = 4.15 s / 163.71 tokens per second 8.54.071.080 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 387342584287 8.54.071.192 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.620 MiB) 8.54.956.395 I slot launch_slot_: id 0 | task 4571 | processing task, is_child = 0 8.54.956.502 I slot print_timing: id 1 | task 4564 | prompt processing, n_tokens = 795, progress = 0.99, t = 5.08 s / 156.59 tokens per second 8.54.958.561 I slot print_timing: id 3 | task 4565 | prompt processing, n_tokens = 794, progress = 0.99, t = 5.08 s / 156.39 tokens per second 8.55.749.926 I slot print_timing: id 2 | task 4568 | prompt processing, n_tokens = 459, progress = 0.47, t = 4.40 s / 104.35 tokens per second 8.56.909.223 I slot print_timing: id 1 | task 4564 | prompt eval time = 6743.89 ms / 799 tokens ( 8.44 ms per token, 118.48 tokens per second) 8.56.909.239 I slot print_timing: id 1 | task 4564 | eval time = 1171.27 ms / 2 tokens ( 1171.27 ms per token, 0.85 tokens per second) 8.56.909.241 I slot print_timing: id 1 | task 4564 | total time = 7915.16 ms / 801 tokens 8.56.909.243 I slot print_timing: id 1 | task 4564 | graphs reused = 3435 8.56.909.245 I slot print_timing: id 1 | task 4564 | graph reallocs = 0 / 0 (same size) / (changed size) 8.56.910.691 I slot release: id 1 | task 4564 | stop processing: n_tokens = 800, truncated = 0 8.56.911.521 I slot print_timing: id 3 | task 4565 | prompt eval time = 6745.42 ms / 798 tokens ( 8.45 ms per token, 118.30 tokens per second) 8.56.911.531 I slot print_timing: id 3 | task 4565 | eval time = 1171.95 ms / 2 tokens ( 1171.95 ms per token, 0.85 tokens per second) 8.56.911.538 I slot print_timing: id 3 | task 4565 | total time = 7917.38 ms / 800 tokens 8.56.911.539 I slot print_timing: id 3 | task 4565 | graphs reused = 3435 8.56.911.542 I slot print_timing: id 3 | task 4565 | graph reallocs = 0 / 0 (same size) / (changed size) 8.56.912.407 I slot release: id 3 | task 4565 | stop processing: n_tokens = 799, truncated = 0 8.56.912.496 I slot print_timing: id 2 | task 4568 | prompt processing, n_tokens = 826, progress = 0.85, t = 5.57 s / 148.29 tokens per second 8.57.456.879 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 387346350228 8.57.457.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.503 MiB) 8.58.158.854 I slot launch_slot_: id 1 | task 4575 | processing task, is_child = 0 8.58.158.904 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.274 MiB) 8.59.229.368 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 387346351943 8.59.229.518 I slot launch_slot_: id 3 | task 4576 | processing task, is_child = 0 8.59.237.178 I slot print_timing: id 2 | task 4568 | prompt processing, n_tokens = 971, progress = 1.00, t = 6.12 s / 158.70 tokens per second 9.00.759.374 I slot print_timing: id 0 | task 4571 | prompt processing, n_tokens = 826, progress = 0.87, t = 5.80 s / 142.37 tokens per second 9.01.956.533 I slot print_timing: id 2 | task 4568 | prompt eval time = 9421.06 ms / 975 tokens ( 9.66 ms per token, 103.49 tokens per second) 9.01.956.551 I slot print_timing: id 2 | task 4568 | eval time = 1197.20 ms / 2 tokens ( 1197.20 ms per token, 0.84 tokens per second) 9.01.956.554 I slot print_timing: id 2 | task 4568 | total time = 10618.27 ms / 977 tokens 9.01.956.559 I slot print_timing: id 2 | task 4568 | graphs reused = 3435 9.01.956.561 I slot print_timing: id 2 | task 4568 | graph reallocs = 0 / 0 (same size) / (changed size) 9.01.961.217 I slot release: id 2 | task 4568 | stop processing: n_tokens = 976, truncated = 0 9.01.961.297 I slot print_timing: id 0 | task 4571 | prompt processing, n_tokens = 949, progress = 1.00, t = 7.00 s / 135.58 tokens per second 9.02.645.135 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 387351400752 9.02.645.504 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.606 MiB) 9.03.195.259 I slot launch_slot_: id 2 | task 4580 | processing task, is_child = 0 9.03.195.273 I slot print_timing: id 1 | task 4575 | prompt processing, n_tokens = 445, progress = 0.46, t = 3.41 s / 130.61 tokens per second 9.03.217.396 I slot print_timing: id 3 | task 4576 | prompt processing, n_tokens = 414, progress = 0.45, t = 3.40 s / 121.59 tokens per second 9.04.971.640 I slot print_timing: id 0 | task 4571 | prompt eval time = 7688.67 ms / 953 tokens ( 8.07 ms per token, 123.95 tokens per second) 9.04.971.668 I slot print_timing: id 0 | task 4571 | eval time = 2326.50 ms / 2 tokens ( 2326.50 ms per token, 0.43 tokens per second) 9.04.971.670 I slot print_timing: id 0 | task 4571 | total time = 10015.17 ms / 955 tokens 9.04.971.673 I slot print_timing: id 0 | task 4571 | graphs reused = 3435 9.04.971.675 I slot print_timing: id 0 | task 4571 | graph reallocs = 0 / 0 (same size) / (changed size) 9.04.973.533 I slot release: id 0 | task 4571 | stop processing: n_tokens = 954, truncated = 0 9.04.973.631 I slot print_timing: id 1 | task 4575 | prompt processing, n_tokens = 826, progress = 0.86, t = 5.73 s / 144.07 tokens per second 9.04.997.883 I slot print_timing: id 3 | task 4576 | prompt processing, n_tokens = 779, progress = 0.84, t = 5.73 s / 135.92 tokens per second 9.05.907.284 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 387354413067 9.05.907.428 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.724 MiB) 9.06.374.975 I slot launch_slot_: id 0 | task 4583 | processing task, is_child = 0 9.06.375.079 I slot print_timing: id 1 | task 4575 | prompt processing, n_tokens = 957, progress = 1.00, t = 6.67 s / 143.47 tokens per second 9.06.377.362 I slot print_timing: id 3 | task 4576 | prompt processing, n_tokens = 926, progress = 1.00, t = 6.67 s / 138.87 tokens per second 9.07.102.905 I slot print_timing: id 2 | task 4580 | prompt processing, n_tokens = 382, progress = 0.43, t = 3.87 s / 98.64 tokens per second 9.08.276.502 I slot print_timing: id 1 | task 4575 | prompt eval time = 7854.34 ms / 961 tokens ( 8.17 ms per token, 122.35 tokens per second) 9.08.276.521 I slot print_timing: id 1 | task 4575 | eval time = 1185.02 ms / 2 tokens ( 1185.02 ms per token, 0.84 tokens per second) 9.08.276.574 I slot print_timing: id 1 | task 4575 | total time = 9039.36 ms / 963 tokens 9.08.276.592 I slot print_timing: id 1 | task 4575 | graphs reused = 3435 9.08.276.595 I slot print_timing: id 1 | task 4575 | graph reallocs = 0 / 0 (same size) / (changed size) 9.08.276.912 I slot release: id 1 | task 4575 | stop processing: n_tokens = 962, truncated = 0 9.08.278.064 I slot print_timing: id 3 | task 4576 | prompt eval time = 7853.09 ms / 930 tokens ( 8.44 ms per token, 118.42 tokens per second) 9.08.278.073 I slot print_timing: id 3 | task 4576 | eval time = 1185.77 ms / 2 tokens ( 1185.77 ms per token, 0.84 tokens per second) 9.08.278.075 I slot print_timing: id 3 | task 4576 | total time = 9038.86 ms / 932 tokens 9.08.278.077 I slot print_timing: id 3 | task 4576 | graphs reused = 3435 9.08.278.078 I slot print_timing: id 3 | task 4576 | graph reallocs = 0 / 0 (same size) / (changed size) 9.08.283.377 I slot release: id 3 | task 4576 | stop processing: n_tokens = 931, truncated = 0 9.08.283.442 I slot print_timing: id 2 | task 4580 | prompt processing, n_tokens = 779, progress = 0.87, t = 5.06 s / 154.01 tokens per second 9.08.758.376 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.867 9.08.758.655 I slot launch_slot_: id 3 | task 4587 | processing task, is_child = 0 9.08.758.821 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.313 MiB) 9.09.567.810 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 387357716445 9.09.567.930 I slot launch_slot_: id 1 | task 4588 | processing task, is_child = 0 9.09.577.431 I slot print_timing: id 2 | task 4580 | prompt processing, n_tokens = 894, progress = 1.00, t = 5.54 s / 161.34 tokens per second 9.11.045.215 I slot print_timing: id 0 | task 4583 | prompt processing, n_tokens = 779, progress = 0.86, t = 4.67 s / 166.84 tokens per second 9.11.833.278 I slot print_timing: id 2 | task 4580 | prompt eval time = 7827.77 ms / 898 tokens ( 8.72 ms per token, 114.72 tokens per second) 9.11.833.295 I slot print_timing: id 2 | task 4580 | eval time = 788.16 ms / 2 tokens ( 788.16 ms per token, 1.27 tokens per second) 9.11.833.297 I slot print_timing: id 2 | task 4580 | total time = 8615.93 ms / 900 tokens 9.11.833.299 I slot print_timing: id 2 | task 4580 | graphs reused = 3435 9.11.833.301 I slot print_timing: id 2 | task 4580 | graph reallocs = 0 / 0 (same size) / (changed size) 9.11.837.441 I slot release: id 2 | task 4580 | stop processing: n_tokens = 899, truncated = 0 9.11.838.074 I slot print_timing: id 0 | task 4583 | prompt processing, n_tokens = 898, progress = 1.00, t = 5.46 s / 164.54 tokens per second 9.12.191.102 I slot print_timing: id 3 | task 4587 | prompt eval time = 2258.58 ms / 111 tokens ( 20.35 ms per token, 49.15 tokens per second) 9.12.191.117 I slot print_timing: id 3 | task 4587 | eval time = 353.06 ms / 2 tokens ( 353.06 ms per token, 2.83 tokens per second) 9.12.191.119 I slot print_timing: id 3 | task 4587 | total time = 2611.64 ms / 113 tokens 9.12.191.120 I slot print_timing: id 3 | task 4587 | graphs reused = 3435 9.12.191.121 I slot print_timing: id 3 | task 4587 | graph reallocs = 0 / 0 (same size) / (changed size) 9.12.191.326 I slot release: id 3 | task 4587 | stop processing: n_tokens = 891, truncated = 0 9.12.191.358 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 387361276976 9.12.191.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.347 MiB) 9.13.326.112 I slot launch_slot_: id 2 | task 4592 | processing task, is_child = 0 9.13.326.166 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.701 MiB) 9.14.067.411 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 387361630858 9.14.067.561 I slot launch_slot_: id 3 | task 4593 | processing task, is_child = 0 9.15.634.083 I slot print_timing: id 0 | task 4583 | prompt eval time = 5815.44 ms / 902 tokens ( 6.45 ms per token, 155.10 tokens per second) 9.15.634.097 I slot print_timing: id 0 | task 4583 | eval time = 3443.60 ms / 2 tokens ( 3443.60 ms per token, 0.29 tokens per second) 9.15.634.104 I slot print_timing: id 0 | task 4583 | total time = 9259.03 ms / 904 tokens 9.15.634.106 I slot print_timing: id 0 | task 4583 | graphs reused = 3435 9.15.634.107 I slot print_timing: id 0 | task 4583 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.635.046 I slot release: id 0 | task 4583 | stop processing: n_tokens = 903, truncated = 0 9.15.635.117 I slot print_timing: id 1 | task 4588 | prompt processing, n_tokens = 779, progress = 0.87, t = 6.05 s / 128.67 tokens per second 9.16.303.134 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 387365074580 9.16.303.294 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.802 MiB) 9.16.828.510 I slot launch_slot_: id 0 | task 4596 | processing task, is_child = 0 9.16.828.602 I slot print_timing: id 1 | task 4588 | prompt processing, n_tokens = 895, progress = 1.00, t = 6.73 s / 133.07 tokens per second 9.18.495.129 I slot print_timing: id 2 | task 4592 | prompt processing, n_tokens = 709, progress = 0.58, t = 4.41 s / 160.77 tokens per second 9.18.502.903 I slot print_timing: id 3 | task 4593 | prompt processing, n_tokens = 720, progress = 0.58, t = 4.41 s / 163.27 tokens per second 9.20.495.820 I slot print_timing: id 1 | task 4588 | prompt eval time = 8905.45 ms / 899 tokens ( 9.91 ms per token, 100.95 tokens per second) 9.20.495.834 I slot print_timing: id 1 | task 4588 | eval time = 2013.00 ms / 2 tokens ( 2013.00 ms per token, 0.50 tokens per second) 9.20.495.837 I slot print_timing: id 1 | task 4588 | total time = 10918.45 ms / 901 tokens 9.20.495.839 I slot print_timing: id 1 | task 4588 | graphs reused = 3435 9.20.495.841 I slot print_timing: id 1 | task 4588 | graph reallocs = 0 / 0 (same size) / (changed size) 9.20.497.716 I slot release: id 1 | task 4588 | stop processing: n_tokens = 900, truncated = 0 9.20.497.786 I slot print_timing: id 0 | task 4596 | prompt processing, n_tokens = 402, progress = 0.31, t = 3.67 s / 109.64 tokens per second 9.20.497.836 I slot print_timing: id 2 | task 4592 | prompt processing, n_tokens = 1061, progress = 0.87, t = 6.42 s / 165.17 tokens per second 9.20.509.275 I slot print_timing: id 3 | task 4593 | prompt processing, n_tokens = 1061, progress = 0.86, t = 6.42 s / 165.17 tokens per second 9.21.794.608 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 900, t_last = 387369937251 9.21.794.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.467 MiB) 9.22.907.713 I slot launch_slot_: id 1 | task 4600 | processing task, is_child = 0 9.22.907.728 I slot print_timing: id 0 | task 4596 | prompt processing, n_tokens = 774, progress = 0.60, t = 4.97 s / 155.86 tokens per second 9.22.920.665 I slot print_timing: id 2 | task 4592 | prompt processing, n_tokens = 1221, progress = 1.00, t = 7.72 s / 158.09 tokens per second 9.22.922.713 I slot print_timing: id 3 | task 4593 | prompt processing, n_tokens = 1232, progress = 1.00, t = 7.72 s / 159.52 tokens per second 9.24.429.057 I slot print_timing: id 0 | task 4596 | prompt processing, n_tokens = 1061, progress = 0.82, t = 7.60 s / 139.61 tokens per second 9.25.884.797 I slot print_timing: id 2 | task 4592 | prompt eval time = 10357.46 ms / 1225 tokens ( 8.46 ms per token, 118.27 tokens per second) 9.25.884.831 I slot print_timing: id 2 | task 4592 | eval time = 1456.03 ms / 2 tokens ( 1456.03 ms per token, 0.69 tokens per second) 9.25.884.834 I slot print_timing: id 2 | task 4592 | total time = 11813.49 ms / 1227 tokens 9.25.884.836 I slot print_timing: id 2 | task 4592 | graphs reused = 3435 9.25.884.842 I slot print_timing: id 2 | task 4592 | graph reallocs = 0 / 0 (same size) / (changed size) 9.25.888.241 I slot release: id 2 | task 4592 | stop processing: n_tokens = 1226, truncated = 0 9.25.889.162 I slot print_timing: id 3 | task 4593 | prompt eval time = 10357.71 ms / 1236 tokens ( 8.38 ms per token, 119.33 tokens per second) 9.25.889.167 I slot print_timing: id 3 | task 4593 | eval time = 1460.10 ms / 2 tokens ( 1460.10 ms per token, 0.68 tokens per second) 9.25.889.168 I slot print_timing: id 3 | task 4593 | total time = 11817.81 ms / 1238 tokens 9.25.889.169 I slot print_timing: id 3 | task 4593 | graphs reused = 3435 9.25.889.170 I slot print_timing: id 3 | task 4593 | graph reallocs = 0 / 0 (same size) / (changed size) 9.25.889.281 I slot release: id 3 | task 4593 | stop processing: n_tokens = 1237, truncated = 0 9.25.889.345 I slot print_timing: id 0 | task 4596 | prompt processing, n_tokens = 1286, progress = 1.00, t = 9.06 s / 142.02 tokens per second 9.27.945.633 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1226, t_last = 387375327776 9.27.946.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.506 MiB) 9.29.068.175 I slot launch_slot_: id 2 | task 4604 | processing task, is_child = 0 9.29.068.251 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 338.705 MiB) 9.29.843.320 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1237, t_last = 387375328813 9.29.843.450 I slot launch_slot_: id 3 | task 4605 | processing task, is_child = 0 9.29.843.463 I slot print_timing: id 1 | task 4600 | prompt processing, n_tokens = 2071, progress = 0.80, t = 5.02 s / 412.23 tokens per second 9.31.881.051 I slot print_timing: id 0 | task 4596 | prompt eval time = 11117.02 ms / 1290 tokens ( 8.62 ms per token, 116.04 tokens per second) 9.31.881.065 I slot print_timing: id 0 | task 4596 | eval time = 3935.48 ms / 2 tokens ( 3935.48 ms per token, 0.25 tokens per second) 9.31.881.070 I slot print_timing: id 0 | task 4596 | total time = 15052.51 ms / 1292 tokens 9.31.881.072 I slot print_timing: id 0 | task 4596 | graphs reused = 3435 9.31.881.074 I slot print_timing: id 0 | task 4596 | graph reallocs = 0 / 0 (same size) / (changed size) 9.31.883.173 I slot release: id 0 | task 4596 | stop processing: n_tokens = 1291, truncated = 0 9.31.883.258 I slot print_timing: id 1 | task 4600 | prompt processing, n_tokens = 2288, progress = 0.88, t = 8.96 s / 255.37 tokens per second 9.34.297.016 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 387381322708 9.34.297.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 340.328 MiB) 9.34.874.863 I slot launch_slot_: id 0 | task 4608 | processing task, is_child = 0 9.34.874.985 I slot print_timing: id 1 | task 4600 | prompt processing, n_tokens = 2583, progress = 1.00, t = 11.38 s / 227.05 tokens per second 9.34.877.215 I slot print_timing: id 2 | task 4604 | prompt processing, n_tokens = 961, progress = 0.38, t = 4.45 s / 215.95 tokens per second 9.34.877.241 I slot print_timing: id 3 | task 4605 | prompt processing, n_tokens = 961, progress = 0.35, t = 4.45 s / 215.95 tokens per second 9.38.538.177 I slot print_timing: id 0 | task 4608 | prompt processing, n_tokens = 402, progress = 0.15, t = 3.66 s / 109.76 tokens per second 9.38.547.692 I slot print_timing: id 2 | task 4604 | prompt processing, n_tokens = 1984, progress = 0.79, t = 8.69 s / 228.29 tokens per second 9.38.555.463 I slot print_timing: id 3 | task 4605 | prompt processing, n_tokens = 1580, progress = 0.58, t = 8.69 s / 181.80 tokens per second 9.41.428.099 I slot print_timing: id 1 | task 4600 | prompt eval time = 15617.54 ms / 2587 tokens ( 6.04 ms per token, 165.65 tokens per second) 9.41.428.132 I slot print_timing: id 1 | task 4600 | eval time = 2889.94 ms / 2 tokens ( 2889.94 ms per token, 0.35 tokens per second) 9.41.428.135 I slot print_timing: id 1 | task 4600 | total time = 18507.49 ms / 2589 tokens 9.41.428.138 I slot print_timing: id 1 | task 4600 | graphs reused = 3435 9.41.428.140 I slot print_timing: id 1 | task 4600 | graph reallocs = 0 / 0 (same size) / (changed size) 9.41.444.915 I slot release: id 1 | task 4600 | stop processing: n_tokens = 2588, truncated = 0 9.41.444.970 I slot print_timing: id 0 | task 4608 | prompt processing, n_tokens = 961, progress = 0.36, t = 6.55 s / 146.67 tokens per second 9.41.445.058 I slot print_timing: id 2 | task 4604 | prompt processing, n_tokens = 2288, progress = 0.92, t = 11.58 s / 197.58 tokens per second 9.41.471.678 I slot print_timing: id 3 | task 4605 | prompt processing, n_tokens = 2226, progress = 0.81, t = 11.58 s / 192.23 tokens per second 9.43.893.331 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2588, t_last = 387390884452 9.43.893.628 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.573 MiB) 9.44.485.849 I slot launch_slot_: id 1 | task 4612 | processing task, is_child = 0 9.44.485.868 I slot print_timing: id 0 | task 4608 | prompt processing, n_tokens = 2139, progress = 0.81, t = 9.02 s / 237.18 tokens per second 9.44.491.907 I slot print_timing: id 2 | task 4604 | prompt processing, n_tokens = 2496, progress = 1.00, t = 14.05 s / 177.70 tokens per second 9.44.494.115 I slot print_timing: id 3 | task 4605 | prompt processing, n_tokens = 2288, progress = 0.83, t = 14.05 s / 162.89 tokens per second 9.46.213.617 I slot print_timing: id 0 | task 4608 | prompt processing, n_tokens = 2288, progress = 0.86, t = 11.34 s / 201.81 tokens per second 9.46.247.799 I slot print_timing: id 3 | task 4605 | prompt processing, n_tokens = 2738, progress = 1.00, t = 16.37 s / 167.30 tokens per second 9.47.911.573 I slot print_timing: id 2 | task 4604 | prompt eval time = 16366.65 ms / 2500 tokens ( 6.55 ms per token, 152.75 tokens per second) 9.47.911.592 I slot print_timing: id 2 | task 4604 | eval time = 1698.07 ms / 2 tokens ( 1698.07 ms per token, 0.59 tokens per second) 9.47.911.594 I slot print_timing: id 2 | task 4604 | total time = 18064.71 ms / 2502 tokens 9.47.911.596 I slot print_timing: id 2 | task 4604 | graphs reused = 3435 9.47.911.599 I slot print_timing: id 2 | task 4604 | graph reallocs = 0 / 0 (same size) / (changed size) 9.47.914.810 I slot release: id 2 | task 4604 | stop processing: n_tokens = 2501, truncated = 0 9.47.915.453 I slot print_timing: id 0 | task 4608 | prompt processing, n_tokens = 2651, progress = 1.00, t = 13.04 s / 203.36 tokens per second 9.47.930.596 I slot print_timing: id 1 | task 4612 | prompt processing, n_tokens = 520, progress = 0.29, t = 3.42 s / 152.10 tokens per second 9.49.356.423 I slot print_timing: id 3 | task 4605 | prompt eval time = 18068.46 ms / 2742 tokens ( 6.59 ms per token, 151.76 tokens per second) 9.49.356.481 I slot print_timing: id 3 | task 4605 | eval time = 1441.01 ms / 2 tokens ( 1441.01 ms per token, 0.69 tokens per second) 9.49.356.494 I slot print_timing: id 3 | task 4605 | total time = 19509.47 ms / 2744 tokens 9.49.356.496 I slot print_timing: id 3 | task 4605 | graphs reused = 3435 9.49.356.498 I slot print_timing: id 3 | task 4605 | graph reallocs = 0 / 0 (same size) / (changed size) 9.49.357.953 I slot release: id 3 | task 4605 | stop processing: n_tokens = 2743, truncated = 0 9.49.358.014 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2501, t_last = 387397354345 9.49.358.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.886 MiB) 9.50.378.542 I slot launch_slot_: id 2 | task 4616 | processing task, is_child = 0 9.50.378.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.883 MiB) 9.51.309.383 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2743, t_last = 387398797488 9.51.309.563 I slot launch_slot_: id 3 | task 4617 | processing task, is_child = 0 9.51.309.579 I slot print_timing: id 1 | task 4612 | prompt processing, n_tokens = 1263, progress = 0.71, t = 4.86 s / 259.71 tokens per second 9.52.607.746 I slot print_timing: id 0 | task 4608 | prompt eval time = 14480.67 ms / 2655 tokens ( 5.45 ms per token, 183.35 tokens per second) 9.52.607.820 I slot print_timing: id 0 | task 4608 | eval time = 3252.15 ms / 2 tokens ( 3252.15 ms per token, 0.31 tokens per second) 9.52.607.828 I slot print_timing: id 0 | task 4608 | total time = 17732.82 ms / 2657 tokens 9.52.607.831 I slot print_timing: id 0 | task 4608 | graphs reused = 3435 9.52.607.834 I slot print_timing: id 0 | task 4608 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.611.384 I slot release: id 0 | task 4608 | stop processing: n_tokens = 2656, truncated = 0 9.52.611.446 I slot print_timing: id 1 | task 4612 | prompt processing, n_tokens = 1447, progress = 0.81, t = 8.11 s / 178.32 tokens per second 9.54.239.647 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2656, t_last = 387402050919 9.54.239.975 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.509 MiB) 9.54.897.246 I slot launch_slot_: id 0 | task 4620 | processing task, is_child = 0 9.54.897.434 I slot print_timing: id 1 | task 4612 | prompt processing, n_tokens = 1775, progress = 1.00, t = 9.75 s / 182.09 tokens per second 9.58.491.835 I slot print_timing: id 0 | task 4620 | prompt processing, n_tokens = 208, progress = 0.11, t = 3.59 s / 57.88 tokens per second 9.58.503.221 I slot print_timing: id 2 | task 4616 | prompt processing, n_tokens = 1325, progress = 0.72, t = 7.15 s / 185.37 tokens per second 9.58.514.584 I slot print_timing: id 3 | task 4617 | prompt processing, n_tokens = 1447, progress = 0.71, t = 7.15 s / 202.45 tokens per second 9.59.922.902 I slot print_timing: id 1 | task 4612 | prompt eval time = 13999.98 ms / 1779 tokens ( 7.87 ms per token, 127.07 tokens per second) 9.59.922.919 I slot print_timing: id 1 | task 4612 | eval time = 1431.16 ms / 2 tokens ( 1431.16 ms per token, 0.70 tokens per second) 9.59.922.922 I slot print_timing: id 1 | task 4612 | total time = 15431.15 ms / 1781 tokens 9.59.922.923 I slot print_timing: id 1 | task 4612 | graphs reused = 3435 9.59.922.926 I slot print_timing: id 1 | task 4612 | graph reallocs = 0 / 0 (same size) / (changed size) 9.59.928.414 I slot release: id 1 | task 4612 | stop processing: n_tokens = 1780, truncated = 0 9.59.928.490 I slot print_timing: id 0 | task 4620 | prompt processing, n_tokens = 520, progress = 0.28, t = 5.02 s / 103.48 tokens per second 9.59.928.554 I slot print_timing: id 2 | task 4616 | prompt processing, n_tokens = 1447, progress = 0.79, t = 8.58 s / 168.66 tokens per second 9.59.943.354 I slot print_timing: id 3 | task 4617 | prompt processing, n_tokens = 1532, progress = 0.75, t = 8.58 s / 178.57 tokens per second 10.02.826.263 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.756 (> 0.100 thold), f_keep = 0.834 10.02.826.395 I slot launch_slot_: id 1 | task 4624 | processing task, is_child = 0 10.02.826.417 I slot print_timing: id 0 | task 4620 | prompt processing, n_tokens = 1336, progress = 0.72, t = 7.93 s / 168.50 tokens per second 10.03.159.492 I slot print_timing: id 2 | task 4616 | prompt processing, n_tokens = 1837, progress = 1.00, t = 11.48 s / 159.97 tokens per second 10.03.164.060 I slot print_timing: id 3 | task 4617 | prompt processing, n_tokens = 2044, progress = 1.00, t = 11.48 s / 178.00 tokens per second 10.04.704.467 I slot print_timing: id 0 | task 4620 | prompt processing, n_tokens = 1447, progress = 0.78, t = 9.80 s / 147.58 tokens per second 10.05.602.865 I slot print_timing: id 2 | task 4616 | prompt eval time = 13359.74 ms / 1841 tokens ( 7.26 ms per token, 137.80 tokens per second) 10.05.602.884 I slot print_timing: id 2 | task 4616 | eval time = 900.16 ms / 2 tokens ( 900.16 ms per token, 1.11 tokens per second) 10.05.602.887 I slot print_timing: id 2 | task 4616 | total time = 14259.90 ms / 1843 tokens 10.05.602.890 I slot print_timing: id 2 | task 4616 | graphs reused = 3435 10.05.602.892 I slot print_timing: id 2 | task 4616 | graph reallocs = 0 / 0 (same size) / (changed size) 10.05.604.821 I slot release: id 2 | task 4616 | stop processing: n_tokens = 1842, truncated = 0 10.05.606.296 I slot print_timing: id 3 | task 4617 | prompt eval time = 13361.24 ms / 2048 tokens ( 6.52 ms per token, 153.28 tokens per second) 10.05.606.303 I slot print_timing: id 3 | task 4617 | eval time = 901.93 ms / 2 tokens ( 901.93 ms per token, 1.11 tokens per second) 10.05.606.304 I slot print_timing: id 3 | task 4617 | total time = 14263.17 ms / 2050 tokens 10.05.606.305 I slot print_timing: id 3 | task 4617 | graphs reused = 3435 10.05.606.305 I slot print_timing: id 3 | task 4617 | graph reallocs = 0 / 0 (same size) / (changed size) 10.05.609.961 I slot release: id 3 | task 4617 | stop processing: n_tokens = 2049, truncated = 0 10.05.610.036 I slot print_timing: id 0 | task 4620 | prompt processing, n_tokens = 1848, progress = 1.00, t = 10.70 s / 172.67 tokens per second 10.05.710.805 I slot print_timing: id 1 | task 4624 | prompt eval time = 2452.06 ms / 515 tokens ( 4.76 ms per token, 210.03 tokens per second) 10.05.710.810 I slot print_timing: id 1 | task 4624 | eval time = 109.06 ms / 2 tokens ( 109.06 ms per token, 9.17 tokens per second) 10.05.710.811 I slot print_timing: id 1 | task 4624 | total time = 2561.13 ms / 517 tokens 10.05.710.811 I slot print_timing: id 1 | task 4624 | graphs reused = 3435 10.05.710.812 I slot print_timing: id 1 | task 4624 | graph reallocs = 0 / 0 (same size) / (changed size) 10.05.712.895 I slot release: id 1 | task 4624 | stop processing: n_tokens = 1963, truncated = 0 10.05.712.908 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1842, t_last = 387415044356 10.05.713.029 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.768 MiB) 10.06.610.981 I slot launch_slot_: id 2 | task 4628 | processing task, is_child = 0 10.06.611.076 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.221 MiB) 10.07.544.953 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.299 MiB) 10.08.547.699 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.833 (> 0.100 thold), f_keep = 0.756 10.08.548.178 I slot launch_slot_: id 1 | task 4629 | processing task, is_child = 0 10.08.548.274 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2049, t_last = 387415049503 10.08.548.379 I slot launch_slot_: id 3 | task 4630 | processing task, is_child = 0 10.09.802.691 I slot print_timing: id 0 | task 4620 | prompt eval time = 10813.31 ms / 1852 tokens ( 5.84 ms per token, 171.27 tokens per second) 10.09.802.707 I slot print_timing: id 0 | task 4620 | eval time = 4092.05 ms / 2 tokens ( 4092.05 ms per token, 0.24 tokens per second) 10.09.802.708 I slot print_timing: id 0 | task 4620 | total time = 14905.35 ms / 1854 tokens 10.09.802.710 I slot print_timing: id 0 | task 4620 | graphs reused = 3435 10.09.802.711 I slot print_timing: id 0 | task 4620 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.805.082 I slot release: id 0 | task 4620 | stop processing: n_tokens = 1853, truncated = 0 10.10.378.300 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1853, t_last = 387419244617 10.10.378.955 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.805 MiB) 10.10.380.749 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.936 MiB) 10.11.246.884 I slot launch_slot_: id 0 | task 4633 | processing task, is_child = 0 10.13.194.375 I slot print_timing: id 1 | task 4629 | prompt eval time = 1829.86 ms / 334 tokens ( 5.48 ms per token, 182.53 tokens per second) 10.13.194.392 I slot print_timing: id 1 | task 4629 | eval time = 2816.08 ms / 2 tokens ( 2816.08 ms per token, 0.36 tokens per second) 10.13.194.395 I slot print_timing: id 1 | task 4629 | total time = 4645.94 ms / 336 tokens 10.13.194.400 I slot print_timing: id 1 | task 4629 | graphs reused = 3435 10.13.194.402 I slot print_timing: id 1 | task 4629 | graph reallocs = 0 / 0 (same size) / (changed size) 10.13.195.200 I slot release: id 1 | task 4629 | stop processing: n_tokens = 1782, truncated = 0 10.13.289.959 I slot print_timing: id 2 | task 4628 | prompt processing, n_tokens = 615, progress = 0.85, t = 4.64 s / 132.54 tokens per second 10.13.552.672 I slot print_timing: id 3 | task 4630 | prompt processing, n_tokens = 615, progress = 0.82, t = 4.64 s / 132.54 tokens per second 10.14.509.837 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1782, t_last = 387422634737 10.14.510.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.545 MiB) 10.15.171.266 I slot launch_slot_: id 1 | task 4636 | processing task, is_child = 0 10.15.171.294 I slot print_timing: id 0 | task 4633 | prompt processing, n_tokens = 245, progress = 0.32, t = 3.26 s / 75.09 tokens per second 10.15.185.724 I slot print_timing: id 2 | task 4628 | prompt processing, n_tokens = 722, progress = 0.99, t = 5.96 s / 121.21 tokens per second 10.15.187.757 I slot print_timing: id 3 | task 4630 | prompt processing, n_tokens = 744, progress = 0.99, t = 5.96 s / 124.91 tokens per second 10.16.297.675 I slot print_timing: id 0 | task 4633 | prompt processing, n_tokens = 615, progress = 0.81, t = 5.05 s / 121.87 tokens per second 10.16.977.464 I slot print_timing: id 2 | task 4628 | prompt eval time = 7741.35 ms / 726 tokens ( 10.66 ms per token, 93.78 tokens per second) 10.16.977.474 I slot print_timing: id 2 | task 4628 | eval time = 682.86 ms / 2 tokens ( 682.86 ms per token, 1.46 tokens per second) 10.16.977.475 I slot print_timing: id 2 | task 4628 | total time = 8424.22 ms / 728 tokens 10.16.977.477 I slot print_timing: id 2 | task 4628 | graphs reused = 3435 10.16.977.478 I slot print_timing: id 2 | task 4628 | graph reallocs = 0 / 0 (same size) / (changed size) 10.16.977.808 I slot release: id 2 | task 4628 | stop processing: n_tokens = 727, truncated = 0 10.16.979.053 I slot print_timing: id 3 | task 4630 | prompt eval time = 7744.21 ms / 748 tokens ( 10.35 ms per token, 96.59 tokens per second) 10.16.979.059 I slot print_timing: id 3 | task 4630 | eval time = 681.48 ms / 2 tokens ( 681.48 ms per token, 1.47 tokens per second) 10.16.979.060 I slot print_timing: id 3 | task 4630 | total time = 8425.69 ms / 750 tokens 10.16.979.061 I slot print_timing: id 3 | task 4630 | graphs reused = 3435 10.16.979.063 I slot print_timing: id 3 | task 4630 | graph reallocs = 0 / 0 (same size) / (changed size) 10.16.979.138 I slot release: id 3 | task 4630 | stop processing: n_tokens = 749, truncated = 0 10.16.979.173 I slot print_timing: id 0 | task 4633 | prompt processing, n_tokens = 757, progress = 0.99, t = 5.73 s / 132.12 tokens per second 10.17.954.695 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.884 10.17.955.117 I slot launch_slot_: id 2 | task 4640 | processing task, is_child = 0 10.17.955.434 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.604 MiB) 10.18.534.578 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 749, t_last = 387426418670 10.18.534.728 I slot launch_slot_: id 3 | task 4641 | processing task, is_child = 0 10.19.378.371 I slot print_timing: id 0 | task 4633 | prompt eval time = 6707.68 ms / 761 tokens ( 8.81 ms per token, 113.45 tokens per second) 10.19.378.378 I slot print_timing: id 0 | task 4633 | eval time = 1423.78 ms / 2 tokens ( 1423.78 ms per token, 0.70 tokens per second) 10.19.378.379 I slot print_timing: id 0 | task 4633 | total time = 8131.45 ms / 763 tokens 10.19.378.385 I slot print_timing: id 0 | task 4633 | graphs reused = 3435 10.19.378.386 I slot print_timing: id 0 | task 4633 | graph reallocs = 0 / 0 (same size) / (changed size) 10.19.378.483 I slot release: id 0 | task 4633 | stop processing: n_tokens = 762, truncated = 0 10.19.378.515 I slot print_timing: id 1 | task 4636 | prompt processing, n_tokens = 721, progress = 0.99, t = 4.19 s / 171.99 tokens per second 10.19.844.815 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 387428818016 10.19.845.494 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.034 MiB) 10.20.697.225 I slot launch_slot_: id 0 | task 4644 | processing task, is_child = 0 10.21.276.222 I slot print_timing: id 1 | task 4636 | prompt eval time = 4658.39 ms / 725 tokens ( 6.43 ms per token, 155.63 tokens per second) 10.21.276.230 I slot print_timing: id 1 | task 4636 | eval time = 1432.22 ms / 2 tokens ( 1432.22 ms per token, 0.70 tokens per second) 10.21.276.232 I slot print_timing: id 1 | task 4636 | total time = 6090.61 ms / 727 tokens 10.21.276.242 I slot print_timing: id 1 | task 4636 | graphs reused = 3435 10.21.276.243 I slot print_timing: id 1 | task 4636 | graph reallocs = 0 / 0 (same size) / (changed size) 10.21.276.402 I slot release: id 1 | task 4636 | stop processing: n_tokens = 726, truncated = 0 10.21.277.050 I slot print_timing: id 2 | task 4640 | prompt eval time = 1285.72 ms / 124 tokens ( 10.37 ms per token, 96.44 tokens per second) 10.21.277.054 I slot print_timing: id 2 | task 4640 | eval time = 1432.23 ms / 2 tokens ( 1432.23 ms per token, 0.70 tokens per second) 10.21.277.061 I slot print_timing: id 2 | task 4640 | total time = 2717.95 ms / 126 tokens 10.21.277.068 I slot print_timing: id 2 | task 4640 | graphs reused = 3435 10.21.277.068 I slot print_timing: id 2 | task 4640 | graph reallocs = 0 / 0 (same size) / (changed size) 10.21.277.198 I slot release: id 2 | task 4640 | stop processing: n_tokens = 740, truncated = 0 10.21.712.307 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 387430715936 10.21.712.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.710 MiB) 10.22.506.683 I slot launch_slot_: id 1 | task 4647 | processing task, is_child = 0 10.22.506.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.690 MiB) 10.23.505.782 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 387430716731 10.23.505.974 I slot launch_slot_: id 2 | task 4648 | processing task, is_child = 0 10.23.506.112 I slot print_timing: id 3 | task 4641 | prompt processing, n_tokens = 631, progress = 0.79, t = 3.15 s / 200.61 tokens per second 10.24.841.824 I slot print_timing: id 0 | task 4644 | prompt processing, n_tokens = 526, progress = 0.50, t = 4.14 s / 126.91 tokens per second 10.24.918.517 I slot print_timing: id 3 | task 4641 | prompt processing, n_tokens = 794, progress = 0.99, t = 6.27 s / 126.54 tokens per second 10.26.162.643 I slot print_timing: id 0 | task 4644 | prompt processing, n_tokens = 893, progress = 0.86, t = 5.46 s / 163.42 tokens per second 10.26.751.910 I slot print_timing: id 3 | task 4641 | prompt eval time = 7595.65 ms / 798 tokens ( 9.52 ms per token, 105.06 tokens per second) 10.26.751.926 I slot print_timing: id 3 | task 4641 | eval time = 589.33 ms / 2 tokens ( 589.33 ms per token, 1.70 tokens per second) 10.26.751.929 I slot print_timing: id 3 | task 4641 | total time = 8184.97 ms / 800 tokens 10.26.751.934 I slot print_timing: id 3 | task 4641 | graphs reused = 3435 10.26.751.936 I slot print_timing: id 3 | task 4641 | graph reallocs = 0 / 0 (same size) / (changed size) 10.26.752.371 I slot release: id 3 | task 4641 | stop processing: n_tokens = 799, truncated = 0 10.26.752.440 I slot print_timing: id 0 | task 4644 | prompt processing, n_tokens = 1038, progress = 1.00, t = 6.05 s / 171.46 tokens per second 10.26.791.009 I slot print_timing: id 1 | task 4647 | prompt processing, n_tokens = 283, progress = 0.35, t = 3.25 s / 87.21 tokens per second 10.26.831.184 I slot print_timing: id 2 | task 4648 | prompt processing, n_tokens = 293, progress = 0.36, t = 3.25 s / 90.29 tokens per second 10.28.488.861 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 387436191907 10.28.489.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.151 MiB) 10.29.516.701 I slot launch_slot_: id 3 | task 4653 | processing task, is_child = 0 10.29.516.719 I slot print_timing: id 1 | task 4647 | prompt processing, n_tokens = 679, progress = 0.85, t = 4.98 s / 136.30 tokens per second 10.29.524.990 I slot print_timing: id 2 | task 4648 | prompt processing, n_tokens = 679, progress = 0.84, t = 4.98 s / 136.30 tokens per second 10.30.422.346 I slot print_timing: id 0 | task 4644 | prompt eval time = 7791.56 ms / 1042 tokens ( 7.48 ms per token, 133.73 tokens per second) 10.30.422.371 I slot print_timing: id 0 | task 4644 | eval time = 1933.52 ms / 2 tokens ( 1933.52 ms per token, 0.52 tokens per second) 10.30.422.373 I slot print_timing: id 0 | task 4644 | total time = 9725.08 ms / 1044 tokens 10.30.422.375 I slot print_timing: id 0 | task 4644 | graphs reused = 3435 10.30.422.377 I slot print_timing: id 0 | task 4644 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.422.963 I slot release: id 0 | task 4644 | stop processing: n_tokens = 1043, truncated = 0 10.30.423.018 I slot print_timing: id 1 | task 4647 | prompt processing, n_tokens = 795, progress = 0.99, t = 6.92 s / 114.96 tokens per second 10.30.432.319 I slot print_timing: id 2 | task 4648 | prompt processing, n_tokens = 805, progress = 1.00, t = 6.92 s / 116.41 tokens per second 10.30.934.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1043, t_last = 387439862498 10.30.935.424 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.721 MiB) 10.31.866.139 I slot launch_slot_: id 0 | task 4656 | processing task, is_child = 0 10.32.326.571 I slot print_timing: id 1 | task 4647 | prompt eval time = 7427.19 ms / 799 tokens ( 9.30 ms per token, 107.58 tokens per second) 10.32.326.601 I slot print_timing: id 1 | task 4647 | eval time = 1393.33 ms / 2 tokens ( 1393.33 ms per token, 0.72 tokens per second) 10.32.326.604 I slot print_timing: id 1 | task 4647 | total time = 8820.52 ms / 801 tokens 10.32.326.606 I slot print_timing: id 1 | task 4647 | graphs reused = 3435 10.32.326.608 I slot print_timing: id 1 | task 4647 | graph reallocs = 0 / 0 (same size) / (changed size) 10.32.328.441 I slot release: id 1 | task 4647 | stop processing: n_tokens = 800, truncated = 0 10.32.329.452 I slot print_timing: id 2 | task 4648 | prompt eval time = 7428.87 ms / 809 tokens ( 9.18 ms per token, 108.90 tokens per second) 10.32.329.458 I slot print_timing: id 2 | task 4648 | eval time = 1394.52 ms / 2 tokens ( 1394.52 ms per token, 0.72 tokens per second) 10.32.329.459 I slot print_timing: id 2 | task 4648 | total time = 8823.39 ms / 811 tokens 10.32.329.460 I slot print_timing: id 2 | task 4648 | graphs reused = 3435 10.32.329.461 I slot print_timing: id 2 | task 4648 | graph reallocs = 0 / 0 (same size) / (changed size) 10.32.329.615 I slot release: id 2 | task 4648 | stop processing: n_tokens = 810, truncated = 0 10.32.744.221 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 387441767976 10.32.744.362 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.877 MiB) 10.33.572.545 I slot launch_slot_: id 1 | task 4659 | processing task, is_child = 0 10.33.572.596 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.646 MiB) 10.34.535.502 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 387441769149 10.34.535.628 I slot launch_slot_: id 2 | task 4660 | processing task, is_child = 0 10.34.535.758 I slot print_timing: id 3 | task 4653 | prompt processing, n_tokens = 723, progress = 0.86, t = 3.22 s / 224.83 tokens per second 10.35.279.117 I slot print_timing: id 0 | task 4656 | prompt processing, n_tokens = 323, progress = 0.38, t = 3.41 s / 94.64 tokens per second 10.35.454.740 I slot print_timing: id 3 | task 4653 | prompt processing, n_tokens = 841, progress = 1.00, t = 5.75 s / 146.24 tokens per second 10.36.981.604 I slot print_timing: id 0 | task 4656 | prompt processing, n_tokens = 723, progress = 0.86, t = 5.11 s / 141.37 tokens per second 10.37.755.537 I slot print_timing: id 3 | task 4653 | prompt eval time = 7453.03 ms / 845 tokens ( 8.82 ms per token, 113.38 tokens per second) 10.37.757.010 I slot print_timing: id 3 | task 4653 | eval time = 774.04 ms / 2 tokens ( 774.04 ms per token, 1.29 tokens per second) 10.37.757.025 I slot print_timing: id 3 | task 4653 | total time = 8227.08 ms / 847 tokens 10.37.757.028 I slot print_timing: id 3 | task 4653 | graphs reused = 3435 10.37.757.031 I slot print_timing: id 3 | task 4653 | graph reallocs = 0 / 0 (same size) / (changed size) 10.37.758.444 I slot release: id 3 | task 4653 | stop processing: n_tokens = 846, truncated = 0 10.37.758.510 I slot print_timing: id 0 | task 4656 | prompt processing, n_tokens = 835, progress = 1.00, t = 5.89 s / 141.80 tokens per second 10.37.778.078 I slot print_timing: id 1 | task 4659 | prompt processing, n_tokens = 394, progress = 0.43, t = 3.22 s / 122.39 tokens per second 10.37.792.099 I slot print_timing: id 2 | task 4660 | prompt processing, n_tokens = 385, progress = 0.43, t = 3.22 s / 119.60 tokens per second 10.39.110.416 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.888 10.39.111.462 I slot launch_slot_: id 3 | task 4665 | processing task, is_child = 0 10.39.111.508 I slot print_timing: id 1 | task 4659 | prompt processing, n_tokens = 723, progress = 0.79, t = 4.57 s / 158.08 tokens per second 10.39.129.764 I slot print_timing: id 2 | task 4660 | prompt processing, n_tokens = 723, progress = 0.80, t = 4.57 s / 158.08 tokens per second 10.40.227.577 I slot print_timing: id 0 | task 4656 | prompt eval time = 7244.20 ms / 839 tokens ( 8.63 ms per token, 115.82 tokens per second) 10.40.227.598 I slot print_timing: id 0 | task 4656 | eval time = 1117.16 ms / 2 tokens ( 1117.16 ms per token, 0.90 tokens per second) 10.40.227.610 I slot print_timing: id 0 | task 4656 | total time = 8361.37 ms / 841 tokens 10.40.227.612 I slot print_timing: id 0 | task 4656 | graphs reused = 3435 10.40.227.629 I slot print_timing: id 0 | task 4656 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.227.972 I slot release: id 0 | task 4656 | stop processing: n_tokens = 840, truncated = 0 10.40.228.042 I slot print_timing: id 1 | task 4659 | prompt processing, n_tokens = 906, progress = 1.00, t = 5.69 s / 159.21 tokens per second 10.40.237.478 I slot print_timing: id 2 | task 4660 | prompt processing, n_tokens = 897, progress = 1.00, t = 5.69 s / 157.63 tokens per second 10.40.364.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 840, t_last = 387449667504 10.40.364.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.489 MiB) 10.41.558.329 I slot launch_slot_: id 0 | task 4668 | processing task, is_child = 0 10.41.948.593 I slot print_timing: id 1 | task 4659 | prompt eval time = 5827.44 ms / 910 tokens ( 6.40 ms per token, 156.16 tokens per second) 10.41.948.600 I slot print_timing: id 1 | task 4659 | eval time = 1585.49 ms / 2 tokens ( 1585.49 ms per token, 0.63 tokens per second) 10.41.948.600 I slot print_timing: id 1 | task 4659 | total time = 7412.94 ms / 912 tokens 10.41.948.601 I slot print_timing: id 1 | task 4659 | graphs reused = 3435 10.41.948.601 I slot print_timing: id 1 | task 4659 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.950.176 I slot release: id 1 | task 4659 | stop processing: n_tokens = 911, truncated = 0 10.41.951.380 I slot print_timing: id 2 | task 4660 | prompt eval time = 5827.94 ms / 901 tokens ( 6.47 ms per token, 154.60 tokens per second) 10.41.951.390 I slot print_timing: id 2 | task 4660 | eval time = 1587.71 ms / 2 tokens ( 1587.71 ms per token, 0.63 tokens per second) 10.41.951.390 I slot print_timing: id 2 | task 4660 | total time = 7415.65 ms / 903 tokens 10.41.951.391 I slot print_timing: id 2 | task 4660 | graphs reused = 3435 10.41.951.391 I slot print_timing: id 2 | task 4660 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.951.479 I slot release: id 2 | task 4660 | stop processing: n_tokens = 902, truncated = 0 10.41.952.556 I slot print_timing: id 3 | task 4665 | prompt eval time = 1219.64 ms / 139 tokens ( 8.77 ms per token, 113.97 tokens per second) 10.41.952.558 I slot print_timing: id 3 | task 4665 | eval time = 1588.29 ms / 2 tokens ( 1588.29 ms per token, 0.63 tokens per second) 10.41.952.558 I slot print_timing: id 3 | task 4665 | total time = 2807.93 ms / 141 tokens 10.41.952.558 I slot print_timing: id 3 | task 4665 | graphs reused = 3435 10.41.952.559 I slot print_timing: id 3 | task 4665 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.952.634 I slot release: id 3 | task 4665 | stop processing: n_tokens = 863, truncated = 0 10.42.180.787 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 387451389710 10.42.180.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.724 MiB) 10.42.889.032 I slot launch_slot_: id 1 | task 4672 | processing task, is_child = 0 10.42.889.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.665 MiB) 10.44.019.415 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 338.040 MiB) 10.44.855.120 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 902, t_last = 387451391011 10.44.855.256 I slot launch_slot_: id 2 | task 4673 | processing task, is_child = 0 10.44.855.299 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 387451392168 10.44.855.386 I slot launch_slot_: id 3 | task 4674 | processing task, is_child = 0 10.45.802.260 I slot print_timing: id 0 | task 4668 | prompt processing, n_tokens = 684, progress = 0.99, t = 4.24 s / 161.17 tokens per second 10.47.891.748 I slot print_timing: id 0 | task 4668 | prompt eval time = 5126.19 ms / 688 tokens ( 7.45 ms per token, 134.21 tokens per second) 10.47.891.763 I slot print_timing: id 0 | task 4668 | eval time = 1207.18 ms / 2 tokens ( 1207.18 ms per token, 0.83 tokens per second) 10.47.891.766 I slot print_timing: id 0 | task 4668 | total time = 6333.37 ms / 690 tokens 10.47.891.768 I slot print_timing: id 0 | task 4668 | graphs reused = 3435 10.47.891.770 I slot print_timing: id 0 | task 4668 | graph reallocs = 0 / 0 (same size) / (changed size) 10.47.893.600 I slot release: id 0 | task 4668 | stop processing: n_tokens = 689, truncated = 0 10.47.893.695 I slot print_timing: id 1 | task 4672 | prompt processing, n_tokens = 632, progress = 0.82, t = 3.03 s / 208.40 tokens per second 10.47.949.207 I slot print_timing: id 2 | task 4673 | prompt processing, n_tokens = 335, progress = 0.39, t = 3.03 s / 110.47 tokens per second 10.47.981.311 I slot print_timing: id 3 | task 4674 | prompt processing, n_tokens = 309, progress = 0.37, t = 3.03 s / 101.90 tokens per second 10.49.498.805 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 689, t_last = 387457333136 10.49.649.359 I slot launch_slot_: id 0 | task 4679 | processing task, is_child = 0 10.49.649.456 I slot print_timing: id 1 | task 4672 | prompt processing, n_tokens = 765, progress = 0.99, t = 4.64 s / 164.85 tokens per second 10.49.651.807 I slot print_timing: id 2 | task 4673 | prompt processing, n_tokens = 708, progress = 0.83, t = 4.64 s / 152.57 tokens per second 10.49.654.009 I slot print_timing: id 3 | task 4674 | prompt processing, n_tokens = 708, progress = 0.86, t = 4.64 s / 152.57 tokens per second 10.50.696.702 I slot print_timing: id 2 | task 4673 | prompt processing, n_tokens = 847, progress = 1.00, t = 5.83 s / 145.34 tokens per second 10.50.702.581 I slot print_timing: id 3 | task 4674 | prompt processing, n_tokens = 821, progress = 1.00, t = 5.83 s / 140.88 tokens per second 10.51.129.124 I slot print_timing: id 1 | task 4672 | prompt eval time = 5828.86 ms / 769 tokens ( 7.58 ms per token, 131.93 tokens per second) 10.51.129.130 I slot print_timing: id 1 | task 4672 | eval time = 442.05 ms / 2 tokens ( 442.05 ms per token, 2.26 tokens per second) 10.51.129.133 I slot print_timing: id 1 | task 4672 | total time = 6270.91 ms / 771 tokens 10.51.129.134 I slot print_timing: id 1 | task 4672 | graphs reused = 3435 10.51.129.135 I slot print_timing: id 1 | task 4672 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.130.700 I slot release: id 1 | task 4672 | stop processing: n_tokens = 770, truncated = 0 10.51.873.082 I slot print_timing: id 2 | task 4673 | prompt eval time = 6274.07 ms / 851 tokens ( 7.37 ms per token, 135.64 tokens per second) 10.51.873.093 I slot print_timing: id 2 | task 4673 | eval time = 740.71 ms / 2 tokens ( 740.71 ms per token, 1.35 tokens per second) 10.51.873.094 I slot print_timing: id 2 | task 4673 | total time = 7014.77 ms / 853 tokens 10.51.873.096 I slot print_timing: id 2 | task 4673 | graphs reused = 3435 10.51.873.097 I slot print_timing: id 2 | task 4673 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.873.523 I slot release: id 2 | task 4673 | stop processing: n_tokens = 852, truncated = 0 10.51.874.593 I slot print_timing: id 3 | task 4674 | prompt eval time = 6274.47 ms / 825 tokens ( 7.61 ms per token, 131.49 tokens per second) 10.51.874.601 I slot print_timing: id 3 | task 4674 | eval time = 741.78 ms / 2 tokens ( 741.78 ms per token, 1.35 tokens per second) 10.51.874.602 I slot print_timing: id 3 | task 4674 | total time = 7016.25 ms / 827 tokens 10.51.874.604 I slot print_timing: id 3 | task 4674 | graphs reused = 3435 10.51.874.605 I slot print_timing: id 3 | task 4674 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.874.749 I slot release: id 3 | task 4674 | stop processing: n_tokens = 826, truncated = 0 10.51.874.782 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 387460570240 10.51.875.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 338.255 MiB) 10.53.021.027 I slot launch_slot_: id 1 | task 4683 | processing task, is_child = 0 10.53.021.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 339.311 MiB) 10.54.068.283 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 364.672 MiB) 10.54.736.525 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 852, t_last = 387461313058 10.54.736.654 I slot launch_slot_: id 2 | task 4684 | processing task, is_child = 0 10.54.736.695 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 387461314281 10.54.736.763 I slot launch_slot_: id 3 | task 4685 | processing task, is_child = 0 10.55.616.092 I slot print_timing: id 0 | task 4679 | prompt processing, n_tokens = 748, progress = 0.99, t = 5.97 s / 125.36 tokens per second 10.58.749.254 I slot print_timing: id 0 | task 4679 | prompt eval time = 6862.66 ms / 752 tokens ( 9.13 ms per token, 109.58 tokens per second) 10.58.749.260 I slot print_timing: id 0 | task 4679 | eval time = 2237.20 ms / 2 tokens ( 2237.20 ms per token, 0.45 tokens per second) 10.58.749.261 I slot print_timing: id 0 | task 4679 | total time = 9099.86 ms / 754 tokens 10.58.749.262 I slot print_timing: id 0 | task 4679 | graphs reused = 3435 10.58.749.263 I slot print_timing: id 0 | task 4679 | graph reallocs = 0 / 0 (same size) / (changed size) 10.58.750.899 I slot release: id 0 | task 4679 | stop processing: n_tokens = 753, truncated = 0 10.58.750.985 I slot print_timing: id 1 | task 4683 | prompt processing, n_tokens = 603, progress = 0.85, t = 3.97 s / 151.78 tokens per second 10.58.769.129 I slot print_timing: id 2 | task 4684 | prompt processing, n_tokens = 603, progress = 0.84, t = 3.97 s / 151.78 tokens per second 10.58.783.787 I slot print_timing: id 3 | task 4685 | prompt processing, n_tokens = 603, progress = 0.82, t = 3.97 s / 151.78 tokens per second 10.59.480.564 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 387468190434 10.59.480.736 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 362.971 MiB) 11.00.431.667 I slot launch_slot_: id 0 | task 4690 | processing task, is_child = 0 11.00.431.746 I slot print_timing: id 1 | task 4683 | prompt processing, n_tokens = 709, progress = 0.99, t = 4.70 s / 150.70 tokens per second 11.00.433.734 I slot print_timing: id 2 | task 4684 | prompt processing, n_tokens = 715, progress = 0.99, t = 4.70 s / 151.98 tokens per second 11.00.436.146 I slot print_timing: id 3 | task 4685 | prompt processing, n_tokens = 732, progress = 0.99, t = 4.70 s / 155.60 tokens per second 11.01.178.980 I slot print_timing: id 1 | task 4683 | prompt eval time = 6077.47 ms / 713 tokens ( 8.52 ms per token, 117.32 tokens per second) 11.01.178.997 I slot print_timing: id 1 | task 4683 | eval time = 325.50 ms / 2 tokens ( 325.50 ms per token, 3.07 tokens per second) 11.01.178.999 I slot print_timing: id 1 | task 4683 | total time = 6402.96 ms / 715 tokens 11.01.179.001 I slot print_timing: id 1 | task 4683 | graphs reused = 3435 11.01.179.003 I slot print_timing: id 1 | task 4683 | graph reallocs = 0 / 0 (same size) / (changed size) 11.01.179.778 I slot release: id 1 | task 4683 | stop processing: n_tokens = 714, truncated = 0 11.01.181.461 I slot print_timing: id 2 | task 4684 | prompt eval time = 6078.55 ms / 719 tokens ( 8.45 ms per token, 118.28 tokens per second) 11.01.181.479 I slot print_timing: id 2 | task 4684 | eval time = 326.80 ms / 2 tokens ( 326.80 ms per token, 3.06 tokens per second) 11.01.181.481 I slot print_timing: id 2 | task 4684 | total time = 6405.34 ms / 721 tokens 11.01.181.482 I slot print_timing: id 2 | task 4684 | graphs reused = 3435 11.01.181.484 I slot print_timing: id 2 | task 4684 | graph reallocs = 0 / 0 (same size) / (changed size) 11.01.181.587 I slot release: id 2 | task 4684 | stop processing: n_tokens = 720, truncated = 0 11.01.182.757 I slot print_timing: id 3 | task 4685 | prompt eval time = 6079.87 ms / 736 tokens ( 8.26 ms per token, 121.06 tokens per second) 11.01.182.762 I slot print_timing: id 3 | task 4685 | eval time = 326.71 ms / 2 tokens ( 326.71 ms per token, 3.06 tokens per second) 11.01.182.763 I slot print_timing: id 3 | task 4685 | total time = 6406.58 ms / 738 tokens 11.01.182.764 I slot print_timing: id 3 | task 4685 | graphs reused = 3435 11.01.182.764 I slot print_timing: id 3 | task 4685 | graph reallocs = 0 / 0 (same size) / (changed size) 11.01.183.410 I slot release: id 3 | task 4685 | stop processing: n_tokens = 737, truncated = 0 11.01.220.806 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.884 11.01.220.847 I slot launch_slot_: id 1 | task 4694 | processing task, is_child = 0 11.01.220.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 367.703 MiB) 11.02.119.082 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 366.002 MiB) 11.03.254.111 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.876 11.03.254.234 I slot launch_slot_: id 2 | task 4695 | processing task, is_child = 0 11.03.254.285 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.856 11.03.254.310 I slot launch_slot_: id 3 | task 4696 | processing task, is_child = 0 11.04.170.878 I slot print_timing: id 0 | task 4690 | prompt processing, n_tokens = 706, progress = 0.99, t = 3.74 s / 188.81 tokens per second 11.04.431.357 I slot print_timing: id 0 | task 4690 | prompt eval time = 3945.83 ms / 710 tokens ( 5.56 ms per token, 179.94 tokens per second) 11.04.431.360 I slot print_timing: id 0 | task 4690 | eval time = 53.84 ms / 2 tokens ( 53.84 ms per token, 18.57 tokens per second) 11.04.431.361 I slot print_timing: id 0 | task 4690 | total time = 3999.67 ms / 712 tokens 11.04.431.362 I slot print_timing: id 0 | task 4690 | graphs reused = 3435 11.04.431.362 I slot print_timing: id 0 | task 4690 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.432.480 I slot release: id 0 | task 4690 | stop processing: n_tokens = 711, truncated = 0 11.04.432.698 I slot print_timing: id 1 | task 4694 | prompt eval time = 1097.15 ms / 106 tokens ( 10.35 ms per token, 96.61 tokens per second) 11.04.432.701 I slot print_timing: id 1 | task 4694 | eval time = 54.91 ms / 2 tokens ( 54.91 ms per token, 18.21 tokens per second) 11.04.432.702 I slot print_timing: id 1 | task 4694 | total time = 1152.07 ms / 108 tokens 11.04.432.702 I slot print_timing: id 1 | task 4694 | graphs reused = 3435 11.04.432.703 I slot print_timing: id 1 | task 4694 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.432.756 I slot release: id 1 | task 4694 | stop processing: n_tokens = 710, truncated = 0 11.04.433.013 I slot print_timing: id 2 | task 4695 | prompt eval time = 1071.24 ms / 112 tokens ( 9.56 ms per token, 104.55 tokens per second) 11.04.433.019 I slot print_timing: id 2 | task 4695 | eval time = 54.40 ms / 2 tokens ( 54.40 ms per token, 18.38 tokens per second) 11.04.433.019 I slot print_timing: id 2 | task 4695 | total time = 1125.64 ms / 114 tokens 11.04.433.019 I slot print_timing: id 2 | task 4695 | graphs reused = 3435 11.04.433.020 I slot print_timing: id 2 | task 4695 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.433.054 I slot release: id 2 | task 4695 | stop processing: n_tokens = 716, truncated = 0 11.04.433.279 I slot print_timing: id 3 | task 4696 | prompt eval time = 1043.24 ms / 104 tokens ( 10.03 ms per token, 99.69 tokens per second) 11.04.433.282 I slot print_timing: id 3 | task 4696 | eval time = 54.13 ms / 2 tokens ( 54.13 ms per token, 18.47 tokens per second) 11.04.433.282 I slot print_timing: id 3 | task 4696 | total time = 1097.37 ms / 106 tokens 11.04.433.283 I slot print_timing: id 3 | task 4696 | graphs reused = 3435 11.04.433.283 I slot print_timing: id 3 | task 4696 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.433.338 I slot release: id 3 | task 4696 | stop processing: n_tokens = 708, truncated = 0 11.04.446.779 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.887 11.04.446.811 I slot launch_slot_: id 0 | task 4700 | processing task, is_child = 0 11.04.446.870 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 350.085 MiB) 11.05.343.881 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 352.451 MiB) 11.06.553.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 354.133 MiB) 11.07.312.354 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.893 11.07.312.467 I slot launch_slot_: id 3 | task 4701 | processing task, is_child = 0 11.07.312.551 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.893 11.07.312.581 I slot launch_slot_: id 1 | task 4702 | processing task, is_child = 0 11.07.312.619 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.881 11.07.312.640 I slot launch_slot_: id 2 | task 4703 | processing task, is_child = 0 11.08.773.399 I slot print_timing: id 0 | task 4700 | prompt eval time = 1406.16 ms / 106 tokens ( 13.27 ms per token, 75.38 tokens per second) 11.08.773.406 I slot print_timing: id 0 | task 4700 | eval time = 54.57 ms / 2 tokens ( 54.57 ms per token, 18.33 tokens per second) 11.08.773.406 I slot print_timing: id 0 | task 4700 | total time = 1460.73 ms / 108 tokens 11.08.773.407 I slot print_timing: id 0 | task 4700 | graphs reused = 3435 11.08.773.408 I slot print_timing: id 0 | task 4700 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.773.706 I slot release: id 0 | task 4700 | stop processing: n_tokens = 710, truncated = 0 11.08.773.929 I slot print_timing: id 1 | task 4702 | prompt eval time = 1399.01 ms / 114 tokens ( 12.27 ms per token, 81.49 tokens per second) 11.08.773.934 I slot print_timing: id 1 | task 4702 | eval time = 54.78 ms / 2 tokens ( 54.78 ms per token, 18.25 tokens per second) 11.08.773.935 I slot print_timing: id 1 | task 4702 | total time = 1453.79 ms / 116 tokens 11.08.773.935 I slot print_timing: id 1 | task 4702 | graphs reused = 3435 11.08.773.936 I slot print_timing: id 1 | task 4702 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.775.846 I slot release: id 1 | task 4702 | stop processing: n_tokens = 718, truncated = 0 11.08.776.376 I slot print_timing: id 2 | task 4703 | prompt eval time = 1394.59 ms / 148 tokens ( 9.42 ms per token, 106.12 tokens per second) 11.08.776.380 I slot print_timing: id 2 | task 4703 | eval time = 56.28 ms / 2 tokens ( 56.28 ms per token, 17.77 tokens per second) 11.08.776.380 I slot print_timing: id 2 | task 4703 | total time = 1450.87 ms / 150 tokens 11.08.776.381 I slot print_timing: id 2 | task 4703 | graphs reused = 3435 11.08.776.381 I slot print_timing: id 2 | task 4703 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.776.428 I slot release: id 2 | task 4703 | stop processing: n_tokens = 752, truncated = 0 11.08.776.671 I slot print_timing: id 3 | task 4701 | prompt eval time = 1386.30 ms / 113 tokens ( 12.27 ms per token, 81.51 tokens per second) 11.08.776.675 I slot print_timing: id 3 | task 4701 | eval time = 56.19 ms / 2 tokens ( 56.19 ms per token, 17.80 tokens per second) 11.08.776.684 I slot print_timing: id 3 | task 4701 | total time = 1442.48 ms / 115 tokens 11.08.776.688 I slot print_timing: id 3 | task 4701 | graphs reused = 3435 11.08.776.688 I slot print_timing: id 3 | task 4701 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.777.339 I slot release: id 3 | task 4701 | stop processing: n_tokens = 717, truncated = 0 11.08.796.273 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 387478213242 11.08.796.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 350.300 MiB) 11.09.697.357 I slot launch_slot_: id 0 | task 4707 | processing task, is_child = 0 11.09.697.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 348.912 MiB) 11.10.378.666 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.712 MiB) 11.11.365.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.967 MiB) 11.12.253.131 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 718, t_last = 387478215380 11.12.253.257 I slot launch_slot_: id 1 | task 4708 | processing task, is_child = 0 11.12.253.333 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 752, t_last = 387478215960 11.12.253.391 I slot launch_slot_: id 2 | task 4709 | processing task, is_child = 0 11.12.253.437 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 387478216872 11.12.253.493 I slot launch_slot_: id 3 | task 4710 | processing task, is_child = 0 11.15.900.632 I slot print_timing: id 0 | task 4707 | prompt processing, n_tokens = 566, progress = 0.52, t = 3.65 s / 155.19 tokens per second 11.16.002.738 I slot print_timing: id 1 | task 4708 | prompt processing, n_tokens = 575, progress = 0.53, t = 3.65 s / 157.66 tokens per second 11.16.010.800 I slot print_timing: id 2 | task 4709 | prompt processing, n_tokens = 364, progress = 0.41, t = 3.65 s / 99.81 tokens per second 11.16.015.119 I slot print_timing: id 3 | task 4710 | prompt processing, n_tokens = 380, progress = 0.42, t = 3.65 s / 104.20 tokens per second 11.18.709.170 I slot print_timing: id 0 | task 4707 | prompt processing, n_tokens = 905, progress = 0.84, t = 6.46 s / 140.19 tokens per second 11.18.808.149 I slot print_timing: id 1 | task 4708 | prompt processing, n_tokens = 905, progress = 0.83, t = 6.46 s / 140.19 tokens per second 11.18.819.897 I slot print_timing: id 2 | task 4709 | prompt processing, n_tokens = 762, progress = 0.87, t = 6.46 s / 118.04 tokens per second 11.18.880.617 I slot print_timing: id 3 | task 4710 | prompt processing, n_tokens = 762, progress = 0.85, t = 6.46 s / 118.04 tokens per second 11.20.103.504 I slot print_timing: id 0 | task 4707 | prompt processing, n_tokens = 1078, progress = 1.00, t = 7.85 s / 137.33 tokens per second 11.20.206.295 I slot print_timing: id 1 | task 4708 | prompt processing, n_tokens = 1087, progress = 1.00, t = 7.85 s / 138.47 tokens per second 11.20.211.114 I slot print_timing: id 2 | task 4709 | prompt processing, n_tokens = 876, progress = 1.00, t = 7.85 s / 111.59 tokens per second 11.20.219.268 I slot print_timing: id 3 | task 4710 | prompt processing, n_tokens = 892, progress = 1.00, t = 7.85 s / 113.63 tokens per second 11.20.405.993 I slot print_timing: id 0 | task 4707 | prompt eval time = 8096.79 ms / 1082 tokens ( 7.48 ms per token, 133.63 tokens per second) 11.20.406.001 I slot print_timing: id 0 | task 4707 | eval time = 55.70 ms / 2 tokens ( 55.70 ms per token, 17.95 tokens per second) 11.20.406.001 I slot print_timing: id 0 | task 4707 | total time = 8152.49 ms / 1084 tokens 11.20.406.002 I slot print_timing: id 0 | task 4707 | graphs reused = 3435 11.20.406.003 I slot print_timing: id 0 | task 4707 | graph reallocs = 0 / 0 (same size) / (changed size) 11.20.407.716 I slot release: id 0 | task 4707 | stop processing: n_tokens = 1083, truncated = 0 11.20.407.987 I slot print_timing: id 1 | task 4708 | prompt eval time = 8097.14 ms / 1091 tokens ( 7.42 ms per token, 134.74 tokens per second) 11.20.407.996 I slot print_timing: id 1 | task 4708 | eval time = 57.27 ms / 2 tokens ( 57.27 ms per token, 17.46 tokens per second) 11.20.407.996 I slot print_timing: id 1 | task 4708 | total time = 8154.41 ms / 1093 tokens 11.20.407.997 I slot print_timing: id 1 | task 4708 | graphs reused = 3435 11.20.407.997 I slot print_timing: id 1 | task 4708 | graph reallocs = 0 / 0 (same size) / (changed size) 11.20.408.076 I slot release: id 1 | task 4708 | stop processing: n_tokens = 1092, truncated = 0 11.20.408.337 I slot print_timing: id 2 | task 4709 | prompt eval time = 8097.49 ms / 880 tokens ( 9.20 ms per token, 108.68 tokens per second) 11.20.408.340 I slot print_timing: id 2 | task 4709 | eval time = 57.19 ms / 2 tokens ( 57.19 ms per token, 17.49 tokens per second) 11.20.408.341 I slot print_timing: id 2 | task 4709 | total time = 8154.68 ms / 882 tokens 11.20.408.342 I slot print_timing: id 2 | task 4709 | graphs reused = 3435 11.20.408.342 I slot print_timing: id 2 | task 4709 | graph reallocs = 0 / 0 (same size) / (changed size) 11.20.411.562 I slot release: id 2 | task 4709 | stop processing: n_tokens = 881, truncated = 0 11.20.411.815 I slot print_timing: id 3 | task 4710 | prompt eval time = 8098.19 ms / 896 tokens ( 9.04 ms per token, 110.64 tokens per second) 11.20.411.819 I slot print_timing: id 3 | task 4710 | eval time = 59.90 ms / 2 tokens ( 59.90 ms per token, 16.70 tokens per second) 11.20.411.820 I slot print_timing: id 3 | task 4710 | total time = 8158.09 ms / 898 tokens 11.20.411.823 I slot print_timing: id 3 | task 4710 | graphs reused = 3435 11.20.411.823 I slot print_timing: id 3 | task 4710 | graph reallocs = 0 / 0 (same size) / (changed size) 11.20.411.873 I slot release: id 3 | task 4710 | stop processing: n_tokens = 897, truncated = 0 11.20.427.364 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.895 11.20.427.408 I slot launch_slot_: id 1 | task 4719 | processing task, is_child = 0 11.20.427.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.263 MiB) 11.21.380.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.536 MiB) 11.22.181.763 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.690 MiB) 11.23.103.772 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.901 11.23.103.888 I slot launch_slot_: id 0 | task 4718 | processing task, is_child = 0 11.23.103.984 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 387489851096 11.23.106.693 I slot launch_slot_: id 2 | task 4720 | processing task, is_child = 0 11.23.106.741 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 387489851405 11.23.106.802 I slot launch_slot_: id 3 | task 4721 | processing task, is_child = 0 11.25.773.476 I slot print_timing: id 0 | task 4718 | prompt eval time = 2159.47 ms / 180 tokens ( 12.00 ms per token, 83.35 tokens per second) 11.25.774.990 I slot print_timing: id 0 | task 4718 | eval time = 507.17 ms / 2 tokens ( 507.17 ms per token, 1.97 tokens per second) 11.25.775.007 I slot print_timing: id 0 | task 4718 | total time = 2666.64 ms / 182 tokens 11.25.775.010 I slot print_timing: id 0 | task 4718 | graphs reused = 3435 11.25.775.013 I slot print_timing: id 0 | task 4718 | graph reallocs = 0 / 0 (same size) / (changed size) 11.25.775.889 I slot release: id 0 | task 4718 | stop processing: n_tokens = 1086, truncated = 0 11.25.776.668 I slot print_timing: id 1 | task 4719 | prompt eval time = 2155.88 ms / 174 tokens ( 12.39 ms per token, 80.71 tokens per second) 11.25.776.674 I slot print_timing: id 1 | task 4719 | eval time = 508.61 ms / 2 tokens ( 508.61 ms per token, 1.97 tokens per second) 11.25.776.675 I slot print_timing: id 1 | task 4719 | total time = 2664.48 ms / 176 tokens 11.25.776.676 I slot print_timing: id 1 | task 4719 | graphs reused = 3435 11.25.776.677 I slot print_timing: id 1 | task 4719 | graph reallocs = 0 / 0 (same size) / (changed size) 11.25.776.778 I slot release: id 1 | task 4719 | stop processing: n_tokens = 1080, truncated = 0 11.25.777.472 I slot print_timing: id 2 | task 4720 | prompt eval time = 2152.71 ms / 166 tokens ( 12.97 ms per token, 77.11 tokens per second) 11.25.777.476 I slot print_timing: id 2 | task 4720 | eval time = 508.27 ms / 2 tokens ( 508.27 ms per token, 1.97 tokens per second) 11.25.778.021 I slot print_timing: id 2 | task 4720 | total time = 2660.97 ms / 168 tokens 11.25.778.034 I slot print_timing: id 2 | task 4720 | graphs reused = 3435 11.25.778.035 I slot print_timing: id 2 | task 4720 | graph reallocs = 0 / 0 (same size) / (changed size) 11.25.778.142 I slot release: id 2 | task 4720 | stop processing: n_tokens = 1072, truncated = 0 11.26.439.089 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.900 11.26.439.150 I slot launch_slot_: id 0 | task 4727 | processing task, is_child = 0 11.26.859.474 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.461 MiB) 11.27.616.878 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.905 11.27.616.975 I slot launch_slot_: id 1 | task 4728 | processing task, is_child = 0 11.27.617.034 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.911 11.27.617.059 I slot launch_slot_: id 2 | task 4729 | processing task, is_child = 0 11.27.644.367 I slot print_timing: id 3 | task 4721 | prompt processing, n_tokens = 1076, progress = 1.00, t = 3.30 s / 325.71 tokens per second 11.28.907.052 I slot print_timing: id 3 | task 4721 | prompt eval time = 5617.61 ms / 1080 tokens ( 5.20 ms per token, 192.25 tokens per second) 11.28.907.059 I slot print_timing: id 3 | task 4721 | eval time = 153.94 ms / 2 tokens ( 153.94 ms per token, 6.50 tokens per second) 11.28.907.060 I slot print_timing: id 3 | task 4721 | total time = 5771.55 ms / 1082 tokens 11.28.907.061 I slot print_timing: id 3 | task 4721 | graphs reused = 3435 11.28.907.062 I slot print_timing: id 3 | task 4721 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.907.282 I slot release: id 3 | task 4721 | stop processing: n_tokens = 1081, truncated = 0 11.28.953.413 I slot print_timing: id 0 | task 4727 | prompt eval time = 1288.62 ms / 168 tokens ( 7.67 ms per token, 130.37 tokens per second) 11.28.953.417 I slot print_timing: id 0 | task 4727 | eval time = 47.73 ms / 2 tokens ( 47.73 ms per token, 20.95 tokens per second) 11.28.953.418 I slot print_timing: id 0 | task 4727 | total time = 1336.34 ms / 170 tokens 11.28.953.419 I slot print_timing: id 0 | task 4727 | graphs reused = 3435 11.28.953.420 I slot print_timing: id 0 | task 4727 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.953.485 I slot release: id 0 | task 4727 | stop processing: n_tokens = 1074, truncated = 0 11.28.953.731 I slot print_timing: id 1 | task 4728 | prompt eval time = 1281.44 ms / 177 tokens ( 7.24 ms per token, 138.13 tokens per second) 11.28.953.735 I slot print_timing: id 1 | task 4728 | eval time = 47.50 ms / 2 tokens ( 47.50 ms per token, 21.05 tokens per second) 11.28.953.736 I slot print_timing: id 1 | task 4728 | total time = 1328.94 ms / 179 tokens 11.28.953.736 I slot print_timing: id 1 | task 4728 | graphs reused = 3435 11.28.953.741 I slot print_timing: id 1 | task 4728 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.953.797 I slot release: id 1 | task 4728 | stop processing: n_tokens = 1083, truncated = 0 11.28.954.060 I slot print_timing: id 2 | task 4729 | prompt eval time = 1278.02 ms / 183 tokens ( 6.98 ms per token, 143.19 tokens per second) 11.28.954.063 I slot print_timing: id 2 | task 4729 | eval time = 47.34 ms / 2 tokens ( 47.34 ms per token, 21.12 tokens per second) 11.28.954.064 I slot print_timing: id 2 | task 4729 | total time = 1325.36 ms / 185 tokens 11.28.954.064 I slot print_timing: id 2 | task 4729 | graphs reused = 3435 11.28.954.065 I slot print_timing: id 2 | task 4729 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.954.846 I slot release: id 2 | task 4729 | stop processing: n_tokens = 1089, truncated = 0 11.28.954.864 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.910 11.28.954.940 I slot launch_slot_: id 0 | task 4733 | processing task, is_child = 0 11.28.955.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.710 MiB) 11.29.717.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.905 MiB) 11.30.646.585 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.492 MiB) 11.31.447.293 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.902 11.31.447.375 I slot launch_slot_: id 1 | task 4734 | processing task, is_child = 0 11.31.447.486 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.897 11.31.447.507 I slot launch_slot_: id 2 | task 4735 | processing task, is_child = 0 11.31.447.557 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.904 11.31.447.577 I slot launch_slot_: id 3 | task 4736 | processing task, is_child = 0 11.33.069.072 I slot print_timing: id 0 | task 4733 | prompt eval time = 1567.61 ms / 178 tokens ( 8.81 ms per token, 113.55 tokens per second) 11.33.069.076 I slot print_timing: id 0 | task 4733 | eval time = 53.87 ms / 2 tokens ( 53.87 ms per token, 18.56 tokens per second) 11.33.069.077 I slot print_timing: id 0 | task 4733 | total time = 1621.48 ms / 180 tokens 11.33.069.077 I slot print_timing: id 0 | task 4733 | graphs reused = 3435 11.33.070.138 I slot print_timing: id 0 | task 4733 | graph reallocs = 0 / 0 (same size) / (changed size) 11.33.070.242 I slot release: id 0 | task 4733 | stop processing: n_tokens = 1084, truncated = 0 11.33.070.452 I slot print_timing: id 1 | task 4734 | prompt eval time = 1560.26 ms / 171 tokens ( 9.12 ms per token, 109.60 tokens per second) 11.33.070.456 I slot print_timing: id 1 | task 4734 | eval time = 54.94 ms / 2 tokens ( 54.94 ms per token, 18.20 tokens per second) 11.33.070.456 I slot print_timing: id 1 | task 4734 | total time = 1615.21 ms / 173 tokens 11.33.070.457 I slot print_timing: id 1 | task 4734 | graphs reused = 3435 11.33.070.461 I slot print_timing: id 1 | task 4734 | graph reallocs = 0 / 0 (same size) / (changed size) 11.33.070.505 I slot release: id 1 | task 4734 | stop processing: n_tokens = 1077, truncated = 0 11.33.070.740 I slot print_timing: id 2 | task 4735 | prompt eval time = 1557.38 ms / 170 tokens ( 9.16 ms per token, 109.16 tokens per second) 11.33.070.744 I slot print_timing: id 2 | task 4735 | eval time = 54.77 ms / 2 tokens ( 54.77 ms per token, 18.26 tokens per second) 11.33.070.744 I slot print_timing: id 2 | task 4735 | total time = 1612.15 ms / 172 tokens 11.33.070.744 I slot print_timing: id 2 | task 4735 | graphs reused = 3435 11.33.070.745 I slot print_timing: id 2 | task 4735 | graph reallocs = 0 / 0 (same size) / (changed size) 11.33.070.783 I slot release: id 2 | task 4735 | stop processing: n_tokens = 1076, truncated = 0 11.33.071.005 I slot print_timing: id 3 | task 4736 | prompt eval time = 1554.10 ms / 175 tokens ( 8.88 ms per token, 112.61 tokens per second) 11.33.071.009 I slot print_timing: id 3 | task 4736 | eval time = 54.73 ms / 2 tokens ( 54.73 ms per token, 18.27 tokens per second) 11.33.071.009 I slot print_timing: id 3 | task 4736 | total time = 1608.83 ms / 177 tokens 11.33.071.010 I slot print_timing: id 3 | task 4736 | graphs reused = 3435 11.33.071.010 I slot print_timing: id 3 | task 4736 | graph reallocs = 0 / 0 (same size) / (changed size) 11.33.071.369 I slot release: id 3 | task 4736 | stop processing: n_tokens = 1081, truncated = 0 11.33.085.297 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 11.33.085.340 I slot launch_slot_: id 0 | task 4740 | processing task, is_child = 0 11.33.085.417 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.880 MiB) 11.34.008.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.704 MiB) 11.34.880.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.942 MiB) 11.35.655.840 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 11.35.656.289 I slot launch_slot_: id 1 | task 4741 | processing task, is_child = 0 11.35.656.421 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1076, t_last = 387502510315 11.35.656.513 I slot launch_slot_: id 2 | task 4742 | processing task, is_child = 0 11.35.656.563 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1081, t_last = 387502510903 11.35.656.650 I slot launch_slot_: id 3 | task 4743 | processing task, is_child = 0 11.38.721.046 I slot print_timing: id 0 | task 4740 | prompt eval time = 2505.82 ms / 173 tokens ( 14.48 ms per token, 69.04 tokens per second) 11.38.721.066 I slot print_timing: id 0 | task 4740 | eval time = 558.53 ms / 2 tokens ( 558.53 ms per token, 1.79 tokens per second) 11.38.721.068 I slot print_timing: id 0 | task 4740 | total time = 3064.34 ms / 175 tokens 11.38.721.071 I slot print_timing: id 0 | task 4740 | graphs reused = 3435 11.38.721.073 I slot print_timing: id 0 | task 4740 | graph reallocs = 0 / 0 (same size) / (changed size) 11.38.721.871 I slot release: id 0 | task 4740 | stop processing: n_tokens = 1079, truncated = 0 11.38.722.861 I slot print_timing: id 1 | task 4741 | prompt eval time = 2498.30 ms / 174 tokens ( 14.36 ms per token, 69.65 tokens per second) 11.38.722.869 I slot print_timing: id 1 | task 4741 | eval time = 560.11 ms / 2 tokens ( 560.11 ms per token, 1.79 tokens per second) 11.38.722.871 I slot print_timing: id 1 | task 4741 | total time = 3058.42 ms / 176 tokens 11.38.722.873 I slot print_timing: id 1 | task 4741 | graphs reused = 3435 11.38.722.875 I slot print_timing: id 1 | task 4741 | graph reallocs = 0 / 0 (same size) / (changed size) 11.38.723.084 I slot release: id 1 | task 4741 | stop processing: n_tokens = 1080, truncated = 0 11.38.723.131 I slot print_timing: id 2 | task 4742 | prompt processing, n_tokens = 515, progress = 0.50, t = 3.05 s / 168.71 tokens per second 11.38.731.808 I slot print_timing: id 3 | task 4743 | prompt processing, n_tokens = 501, progress = 0.49, t = 3.05 s / 164.13 tokens per second 11.40.071.529 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1079, t_last = 387508161407 11.40.071.713 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.539 MiB) 11.40.979.593 I slot launch_slot_: id 0 | task 4748 | processing task, is_child = 0 11.40.979.656 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.123 MiB) 11.41.743.330 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1080, t_last = 387508162616 11.41.743.426 I slot launch_slot_: id 1 | task 4749 | processing task, is_child = 0 11.41.743.578 I slot print_timing: id 2 | task 4742 | prompt processing, n_tokens = 878, progress = 0.85, t = 4.40 s / 199.38 tokens per second 11.41.745.768 I slot print_timing: id 3 | task 4743 | prompt processing, n_tokens = 878, progress = 0.86, t = 4.40 s / 199.38 tokens per second 11.43.290.652 I slot print_timing: id 2 | task 4742 | prompt processing, n_tokens = 1027, progress = 1.00, t = 7.33 s / 140.07 tokens per second 11.43.295.560 I slot print_timing: id 3 | task 4743 | prompt processing, n_tokens = 1013, progress = 1.00, t = 7.33 s / 138.17 tokens per second 11.44.851.689 I slot print_timing: id 2 | task 4742 | prompt eval time = 8377.33 ms / 1031 tokens ( 8.13 ms per token, 123.07 tokens per second) 11.44.851.705 I slot print_timing: id 2 | task 4742 | eval time = 806.55 ms / 2 tokens ( 806.55 ms per token, 1.24 tokens per second) 11.44.851.708 I slot print_timing: id 2 | task 4742 | total time = 9183.88 ms / 1033 tokens 11.44.851.710 I slot print_timing: id 2 | task 4742 | graphs reused = 3435 11.44.851.715 I slot print_timing: id 2 | task 4742 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.855.560 I slot release: id 2 | task 4742 | stop processing: n_tokens = 1032, truncated = 0 11.44.856.444 I slot print_timing: id 3 | task 4743 | prompt eval time = 8378.15 ms / 1017 tokens ( 8.24 ms per token, 121.39 tokens per second) 11.44.856.452 I slot print_timing: id 3 | task 4743 | eval time = 810.41 ms / 2 tokens ( 810.41 ms per token, 1.23 tokens per second) 11.44.856.453 I slot print_timing: id 3 | task 4743 | total time = 9188.57 ms / 1019 tokens 11.44.856.454 I slot print_timing: id 3 | task 4743 | graphs reused = 3435 11.44.856.454 I slot print_timing: id 3 | task 4743 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.856.538 I slot release: id 3 | task 4743 | stop processing: n_tokens = 1018, truncated = 0 11.44.856.581 I slot print_timing: id 0 | task 4748 | prompt processing, n_tokens = 555, progress = 0.52, t = 3.11 s / 178.62 tokens per second 11.44.866.819 I slot print_timing: id 1 | task 4749 | prompt processing, n_tokens = 590, progress = 0.53, t = 3.11 s / 189.88 tokens per second 11.45.947.134 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.878 11.45.947.340 I slot launch_slot_: id 2 | task 4754 | processing task, is_child = 0 11.45.947.501 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.726 MiB) 11.46.740.961 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.890 11.46.741.042 I slot launch_slot_: id 3 | task 4755 | processing task, is_child = 0 11.46.741.052 I slot print_timing: id 0 | task 4748 | prompt processing, n_tokens = 878, progress = 0.82, t = 4.20 s / 208.86 tokens per second 11.46.756.435 I slot print_timing: id 1 | task 4749 | prompt processing, n_tokens = 878, progress = 0.79, t = 4.20 s / 208.87 tokens per second 11.48.491.996 I slot print_timing: id 0 | task 4748 | prompt processing, n_tokens = 1067, progress = 1.00, t = 6.75 s / 158.11 tokens per second 11.48.671.529 I slot print_timing: id 1 | task 4749 | prompt processing, n_tokens = 1102, progress = 1.00, t = 6.75 s / 163.30 tokens per second 11.49.064.061 I slot print_timing: id 0 | task 4748 | prompt eval time = 7266.13 ms / 1071 tokens ( 6.78 ms per token, 147.40 tokens per second) 11.49.064.065 I slot print_timing: id 0 | task 4748 | eval time = 54.49 ms / 2 tokens ( 54.49 ms per token, 18.35 tokens per second) 11.49.064.066 I slot print_timing: id 0 | task 4748 | total time = 7320.62 ms / 1073 tokens 11.49.064.066 I slot print_timing: id 0 | task 4748 | graphs reused = 3435 11.49.064.067 I slot print_timing: id 0 | task 4748 | graph reallocs = 0 / 0 (same size) / (changed size) 11.49.067.597 I slot release: id 0 | task 4748 | stop processing: n_tokens = 1072, truncated = 0 11.49.067.804 I slot print_timing: id 1 | task 4749 | prompt eval time = 7266.29 ms / 1106 tokens ( 6.57 ms per token, 152.21 tokens per second) 11.49.067.811 I slot print_timing: id 1 | task 4749 | eval time = 58.00 ms / 2 tokens ( 58.00 ms per token, 17.24 tokens per second) 11.49.067.812 I slot print_timing: id 1 | task 4749 | total time = 7324.29 ms / 1108 tokens 11.49.067.812 I slot print_timing: id 1 | task 4749 | graphs reused = 3435 11.49.067.812 I slot print_timing: id 1 | task 4749 | graph reallocs = 0 / 0 (same size) / (changed size) 11.49.069.514 I slot release: id 1 | task 4749 | stop processing: n_tokens = 1107, truncated = 0 11.49.069.809 I slot print_timing: id 2 | task 4754 | prompt eval time = 2141.99 ms / 167 tokens ( 12.83 ms per token, 77.96 tokens per second) 11.49.069.812 I slot print_timing: id 2 | task 4754 | eval time = 59.41 ms / 2 tokens ( 59.41 ms per token, 16.83 tokens per second) 11.49.069.813 I slot print_timing: id 2 | task 4754 | total time = 2201.40 ms / 169 tokens 11.49.069.814 I slot print_timing: id 2 | task 4754 | graphs reused = 3435 11.49.069.814 I slot print_timing: id 2 | task 4754 | graph reallocs = 0 / 0 (same size) / (changed size) 11.49.069.884 I slot release: id 2 | task 4754 | stop processing: n_tokens = 1046, truncated = 0 11.49.070.122 I slot print_timing: id 3 | task 4755 | prompt eval time = 2137.02 ms / 152 tokens ( 14.06 ms per token, 71.13 tokens per second) 11.49.070.125 I slot print_timing: id 3 | task 4755 | eval time = 59.00 ms / 2 tokens ( 59.00 ms per token, 16.95 tokens per second) 11.49.070.126 I slot print_timing: id 3 | task 4755 | total time = 2196.02 ms / 154 tokens 11.49.070.126 I slot print_timing: id 3 | task 4755 | graphs reused = 3435 11.49.070.126 I slot print_timing: id 3 | task 4755 | graph reallocs = 0 / 0 (same size) / (changed size) 11.49.071.396 I slot release: id 3 | task 4755 | stop processing: n_tokens = 1031, truncated = 0 11.49.089.286 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1072, t_last = 387518507134 11.49.089.358 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 330.218 MiB) 11.49.975.975 I slot launch_slot_: id 0 | task 4759 | processing task, is_child = 0 11.49.976.045 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.791 MiB) 11.50.932.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.145 MiB) 11.51.728.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.478 MiB) 11.52.728.953 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1107, t_last = 387518509048 11.52.729.099 I slot launch_slot_: id 1 | task 4760 | processing task, is_child = 0 11.52.729.198 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1046, t_last = 387518509416 11.52.729.271 I slot launch_slot_: id 2 | task 4761 | processing task, is_child = 0 11.52.729.317 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 387518510929 11.52.729.386 I slot launch_slot_: id 3 | task 4762 | processing task, is_child = 0 11.56.388.671 I slot print_timing: id 0 | task 4759 | prompt processing, n_tokens = 623, progress = 0.84, t = 3.66 s / 170.25 tokens per second 11.57.035.458 I slot print_timing: id 1 | task 4760 | prompt processing, n_tokens = 623, progress = 0.85, t = 3.66 s / 170.26 tokens per second 11.57.084.162 I slot print_timing: id 2 | task 4761 | prompt processing, n_tokens = 281, progress = 0.35, t = 3.66 s / 76.80 tokens per second 11.57.091.815 I slot print_timing: id 3 | task 4762 | prompt processing, n_tokens = 623, progress = 0.83, t = 3.66 s / 170.27 tokens per second 11.58.093.311 I slot print_timing: id 0 | task 4759 | prompt processing, n_tokens = 736, progress = 0.99, t = 5.36 s / 137.21 tokens per second 11.58.542.833 I slot print_timing: id 1 | task 4760 | prompt processing, n_tokens = 725, progress = 0.99, t = 5.36 s / 135.17 tokens per second 11.58.579.265 I slot print_timing: id 2 | task 4761 | prompt processing, n_tokens = 623, progress = 0.78, t = 5.36 s / 116.15 tokens per second 11.58.591.579 I slot print_timing: id 3 | task 4762 | prompt processing, n_tokens = 749, progress = 0.99, t = 5.36 s / 139.64 tokens per second 11.59.146.628 I slot print_timing: id 2 | task 4761 | prompt processing, n_tokens = 793, progress = 0.99, t = 6.41 s / 123.68 tokens per second 11.59.272.603 I slot print_timing: id 0 | task 4759 | prompt eval time = 6414.01 ms / 740 tokens ( 8.67 ms per token, 115.37 tokens per second) 11.59.272.607 I slot print_timing: id 0 | task 4759 | eval time = 129.19 ms / 2 tokens ( 129.19 ms per token, 7.74 tokens per second) 11.59.272.608 I slot print_timing: id 0 | task 4759 | total time = 6543.20 ms / 742 tokens 11.59.272.608 I slot print_timing: id 0 | task 4759 | graphs reused = 3435 11.59.272.609 I slot print_timing: id 0 | task 4759 | graph reallocs = 0 / 0 (same size) / (changed size) 11.59.274.571 I slot release: id 0 | task 4759 | stop processing: n_tokens = 741, truncated = 0 11.59.274.901 I slot print_timing: id 1 | task 4760 | prompt eval time = 6415.44 ms / 729 tokens ( 8.80 ms per token, 113.63 tokens per second) 11.59.274.908 I slot print_timing: id 1 | task 4760 | eval time = 129.95 ms / 2 tokens ( 129.95 ms per token, 7.70 tokens per second) 11.59.274.909 I slot print_timing: id 1 | task 4760 | total time = 6545.38 ms / 731 tokens 11.59.274.910 I slot print_timing: id 1 | task 4760 | graphs reused = 3435 11.59.274.911 I slot print_timing: id 1 | task 4760 | graph reallocs = 0 / 0 (same size) / (changed size) 11.59.274.958 I slot release: id 1 | task 4760 | stop processing: n_tokens = 730, truncated = 0 11.59.276.197 I slot print_timing: id 3 | task 4762 | prompt eval time = 6416.89 ms / 753 tokens ( 8.52 ms per token, 117.35 tokens per second) 11.59.276.199 I slot print_timing: id 3 | task 4762 | eval time = 129.64 ms / 2 tokens ( 129.64 ms per token, 7.71 tokens per second) 11.59.276.200 I slot print_timing: id 3 | task 4762 | total time = 6546.53 ms / 755 tokens 11.59.276.201 I slot print_timing: id 3 | task 4762 | graphs reused = 3435 11.59.276.201 I slot print_timing: id 3 | task 4762 | graph reallocs = 0 / 0 (same size) / (changed size) 11.59.276.330 I slot release: id 3 | task 4762 | stop processing: n_tokens = 754, truncated = 0 11.59.299.438 I slot print_timing: id 2 | task 4761 | prompt eval time = 6546.37 ms / 797 tokens ( 8.21 ms per token, 121.75 tokens per second) 11.59.299.441 I slot print_timing: id 2 | task 4761 | eval time = 23.46 ms / 2 tokens ( 23.46 ms per token, 42.62 tokens per second) 11.59.299.441 I slot print_timing: id 2 | task 4761 | total time = 6569.83 ms / 799 tokens 11.59.299.441 I slot print_timing: id 2 | task 4761 | graphs reused = 3435 11.59.299.442 I slot print_timing: id 2 | task 4761 | graph reallocs = 0 / 0 (same size) / (changed size) 11.59.299.564 I slot release: id 2 | task 4761 | stop processing: n_tokens = 798, truncated = 0 11.59.299.575 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.879 11.59.299.612 I slot launch_slot_: id 0 | task 4770 | processing task, is_child = 0 11.59.299.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.950 MiB) 12.00.247.789 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.067 MiB) 12.01.446.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.911 MiB) 12.02.429.235 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.866 12.02.429.341 I slot launch_slot_: id 3 | task 4771 | processing task, is_child = 0 12.02.429.423 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.892 12.02.429.445 I slot launch_slot_: id 1 | task 4772 | processing task, is_child = 0 12.02.429.484 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.862 (> 0.100 thold), f_keep = 0.816 12.02.429.507 I slot launch_slot_: id 2 | task 4773 | processing task, is_child = 0 12.03.811.374 I slot print_timing: id 0 | task 4770 | prompt eval time = 1326.01 ms / 110 tokens ( 12.05 ms per token, 82.96 tokens per second) 12.03.811.379 I slot print_timing: id 0 | task 4770 | eval time = 55.84 ms / 2 tokens ( 55.84 ms per token, 17.91 tokens per second) 12.03.811.380 I slot print_timing: id 0 | task 4770 | total time = 1381.85 ms / 112 tokens 12.03.811.381 I slot print_timing: id 0 | task 4770 | graphs reused = 3435 12.03.811.381 I slot print_timing: id 0 | task 4770 | graph reallocs = 0 / 0 (same size) / (changed size) 12.03.814.994 I slot release: id 0 | task 4770 | stop processing: n_tokens = 734, truncated = 0 12.03.815.260 I slot print_timing: id 1 | task 4772 | prompt eval time = 1314.75 ms / 123 tokens ( 10.69 ms per token, 93.55 tokens per second) 12.03.815.264 I slot print_timing: id 1 | task 4772 | eval time = 59.22 ms / 2 tokens ( 59.22 ms per token, 16.89 tokens per second) 12.03.815.265 I slot print_timing: id 1 | task 4772 | total time = 1373.98 ms / 125 tokens 12.03.815.266 I slot print_timing: id 1 | task 4772 | graphs reused = 3435 12.03.815.266 I slot print_timing: id 1 | task 4772 | graph reallocs = 0 / 0 (same size) / (changed size) 12.03.815.349 I slot release: id 1 | task 4772 | stop processing: n_tokens = 747, truncated = 0 12.03.815.717 I slot print_timing: id 2 | task 4773 | prompt eval time = 1298.41 ms / 132 tokens ( 9.84 ms per token, 101.66 tokens per second) 12.03.815.721 I slot print_timing: id 2 | task 4773 | eval time = 58.65 ms / 2 tokens ( 58.65 ms per token, 17.05 tokens per second) 12.03.815.721 I slot print_timing: id 2 | task 4773 | total time = 1357.06 ms / 134 tokens 12.03.815.722 I slot print_timing: id 2 | task 4773 | graphs reused = 3435 12.03.815.722 I slot print_timing: id 2 | task 4773 | graph reallocs = 0 / 0 (same size) / (changed size) 12.03.816.287 I slot release: id 2 | task 4773 | stop processing: n_tokens = 756, truncated = 0 12.03.816.527 I slot print_timing: id 3 | task 4771 | prompt eval time = 1293.49 ms / 116 tokens ( 11.15 ms per token, 89.68 tokens per second) 12.03.816.531 I slot print_timing: id 3 | task 4771 | eval time = 58.48 ms / 2 tokens ( 58.48 ms per token, 17.10 tokens per second) 12.03.816.532 I slot print_timing: id 3 | task 4771 | total time = 1351.97 ms / 118 tokens 12.03.816.532 I slot print_timing: id 3 | task 4771 | graphs reused = 3435 12.03.816.533 I slot print_timing: id 3 | task 4771 | graph reallocs = 0 / 0 (same size) / (changed size) 12.03.816.571 I slot release: id 3 | task 4771 | stop processing: n_tokens = 740, truncated = 0 12.03.835.188 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.887 12.03.835.231 I slot launch_slot_: id 0 | task 4777 | processing task, is_child = 0 12.03.835.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.950 MiB) 12.04.718.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.106 MiB) 12.05.680.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.771 MiB) 12.06.395.651 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 747, t_last = 387533254881 12.06.395.770 I slot launch_slot_: id 1 | task 4778 | processing task, is_child = 0 12.06.395.845 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 387533255823 12.06.395.903 I slot launch_slot_: id 2 | task 4779 | processing task, is_child = 0 12.06.395.944 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 387533256103 12.06.396.005 I slot launch_slot_: id 3 | task 4780 | processing task, is_child = 0 12.09.455.289 I slot print_timing: id 0 | task 4777 | prompt eval time = 2260.95 ms / 124 tokens ( 18.23 ms per token, 54.84 tokens per second) 12.09.455.299 I slot print_timing: id 0 | task 4777 | eval time = 798.31 ms / 2 tokens ( 798.31 ms per token, 1.25 tokens per second) 12.09.455.301 I slot print_timing: id 0 | task 4777 | total time = 3059.26 ms / 126 tokens 12.09.455.302 I slot print_timing: id 0 | task 4777 | graphs reused = 3435 12.09.455.303 I slot print_timing: id 0 | task 4777 | graph reallocs = 0 / 0 (same size) / (changed size) 12.09.457.123 I slot release: id 0 | task 4777 | stop processing: n_tokens = 748, truncated = 0 12.09.457.195 I slot print_timing: id 1 | task 4778 | prompt processing, n_tokens = 457, progress = 0.47, t = 3.05 s / 149.83 tokens per second 12.09.483.559 I slot print_timing: id 2 | task 4779 | prompt processing, n_tokens = 474, progress = 0.48, t = 3.05 s / 155.41 tokens per second 12.09.512.207 I slot print_timing: id 3 | task 4780 | prompt processing, n_tokens = 439, progress = 0.46, t = 3.05 s / 143.94 tokens per second 12.11.428.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 387538896658 12.11.428.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.087 MiB) 12.12.361.703 I slot launch_slot_: id 0 | task 4785 | processing task, is_child = 0 12.12.361.800 I slot print_timing: id 1 | task 4778 | prompt processing, n_tokens = 820, progress = 0.84, t = 5.02 s / 163.24 tokens per second 12.12.364.333 I slot print_timing: id 2 | task 4779 | prompt processing, n_tokens = 820, progress = 0.83, t = 5.02 s / 163.24 tokens per second 12.12.367.999 I slot print_timing: id 3 | task 4780 | prompt processing, n_tokens = 820, progress = 0.86, t = 5.02 s / 163.24 tokens per second 12.13.765.654 I slot print_timing: id 1 | task 4778 | prompt processing, n_tokens = 969, progress = 1.00, t = 7.24 s / 133.81 tokens per second 12.13.772.115 I slot print_timing: id 2 | task 4779 | prompt processing, n_tokens = 986, progress = 1.00, t = 7.24 s / 136.16 tokens per second 12.13.820.102 I slot print_timing: id 3 | task 4780 | prompt processing, n_tokens = 951, progress = 1.00, t = 7.24 s / 131.33 tokens per second 12.14.791.987 I slot print_timing: id 1 | task 4778 | prompt eval time = 7936.26 ms / 973 tokens ( 8.16 ms per token, 122.60 tokens per second) 12.14.792.002 I slot print_timing: id 1 | task 4778 | eval time = 450.82 ms / 2 tokens ( 450.82 ms per token, 2.22 tokens per second) 12.14.792.004 I slot print_timing: id 1 | task 4778 | total time = 8387.08 ms / 975 tokens 12.14.792.006 I slot print_timing: id 1 | task 4778 | graphs reused = 3435 12.14.792.007 I slot print_timing: id 1 | task 4778 | graph reallocs = 0 / 0 (same size) / (changed size) 12.14.796.405 I slot release: id 1 | task 4778 | stop processing: n_tokens = 974, truncated = 0 12.14.797.614 I slot print_timing: id 2 | task 4779 | prompt eval time = 7937.86 ms / 990 tokens ( 8.02 ms per token, 124.72 tokens per second) 12.14.797.624 I slot print_timing: id 2 | task 4779 | eval time = 454.80 ms / 2 tokens ( 454.80 ms per token, 2.20 tokens per second) 12.14.797.625 I slot print_timing: id 2 | task 4779 | total time = 8392.66 ms / 992 tokens 12.14.797.626 I slot print_timing: id 2 | task 4779 | graphs reused = 3435 12.14.797.627 I slot print_timing: id 2 | task 4779 | graph reallocs = 0 / 0 (same size) / (changed size) 12.14.798.760 I slot release: id 2 | task 4779 | stop processing: n_tokens = 991, truncated = 0 12.14.800.039 I slot print_timing: id 3 | task 4780 | prompt eval time = 7939.25 ms / 955 tokens ( 8.31 ms per token, 120.29 tokens per second) 12.14.800.048 I slot print_timing: id 3 | task 4780 | eval time = 455.79 ms / 2 tokens ( 455.79 ms per token, 2.19 tokens per second) 12.14.800.049 I slot print_timing: id 3 | task 4780 | total time = 8395.04 ms / 957 tokens 12.14.800.050 I slot print_timing: id 3 | task 4780 | graphs reused = 3435 12.14.800.051 I slot print_timing: id 3 | task 4780 | graph reallocs = 0 / 0 (same size) / (changed size) 12.14.801.115 I slot release: id 3 | task 4780 | stop processing: n_tokens = 956, truncated = 0 12.15.414.468 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 974, t_last = 387544235940 12.15.414.556 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.294 MiB) 12.16.420.830 I slot launch_slot_: id 1 | task 4791 | processing task, is_child = 0 12.16.420.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.606 MiB) 12.17.293.162 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.185 MiB) 12.17.491.736 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 387544238302 12.17.491.923 I slot launch_slot_: id 2 | task 4792 | processing task, is_child = 0 12.17.491.969 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 387544240651 12.17.492.042 I slot launch_slot_: id 3 | task 4793 | processing task, is_child = 0 12.17.492.059 I slot print_timing: id 0 | task 4785 | prompt processing, n_tokens = 1040, progress = 1.00, t = 3.05 s / 340.68 tokens per second 12.20.422.626 I slot print_timing: id 0 | task 4785 | prompt eval time = 6925.56 ms / 1044 tokens ( 6.63 ms per token, 150.75 tokens per second) 12.20.422.648 I slot print_timing: id 0 | task 4785 | eval time = 1135.32 ms / 2 tokens ( 1135.32 ms per token, 0.88 tokens per second) 12.20.422.654 I slot print_timing: id 0 | task 4785 | total time = 8060.88 ms / 1046 tokens 12.20.422.658 I slot print_timing: id 0 | task 4785 | graphs reused = 3435 12.20.422.663 I slot print_timing: id 0 | task 4785 | graph reallocs = 0 / 0 (same size) / (changed size) 12.20.425.670 I slot release: id 0 | task 4785 | stop processing: n_tokens = 1045, truncated = 0 12.22.923.453 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1045, t_last = 387549865205 12.22.923.616 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.028 MiB) 12.23.463.990 I slot launch_slot_: id 0 | task 4797 | processing task, is_child = 0 12.23.464.105 I slot print_timing: id 1 | task 4791 | prompt processing, n_tokens = 608, progress = 0.54, t = 5.28 s / 115.25 tokens per second 12.23.466.486 I slot print_timing: id 2 | task 4792 | prompt processing, n_tokens = 645, progress = 0.56, t = 5.28 s / 122.26 tokens per second 12.23.468.675 I slot print_timing: id 3 | task 4793 | prompt processing, n_tokens = 1575, progress = 0.75, t = 5.28 s / 298.56 tokens per second 12.25.924.965 I slot print_timing: id 1 | task 4791 | prompt processing, n_tokens = 977, progress = 0.87, t = 8.24 s / 118.55 tokens per second 12.25.944.504 I slot print_timing: id 2 | task 4792 | prompt processing, n_tokens = 977, progress = 0.84, t = 8.24 s / 118.56 tokens per second 12.25.949.333 I slot print_timing: id 3 | task 4793 | prompt processing, n_tokens = 1761, progress = 0.84, t = 8.24 s / 213.69 tokens per second 12.27.712.548 I slot print_timing: id 0 | task 4797 | prompt processing, n_tokens = 640, progress = 0.31, t = 4.25 s / 150.64 tokens per second 12.27.712.603 I slot print_timing: id 1 | task 4791 | prompt processing, n_tokens = 1120, progress = 1.00, t = 10.06 s / 111.28 tokens per second 12.28.077.915 I slot print_timing: id 2 | task 4792 | prompt processing, n_tokens = 1157, progress = 1.00, t = 10.06 s / 114.96 tokens per second 12.28.275.830 I slot print_timing: id 3 | task 4793 | prompt processing, n_tokens = 2087, progress = 1.00, t = 10.06 s / 207.36 tokens per second 12.30.199.463 I slot print_timing: id 0 | task 4797 | prompt processing, n_tokens = 1578, progress = 0.75, t = 6.73 s / 234.39 tokens per second 12.30.680.668 I slot print_timing: id 1 | task 4791 | prompt eval time = 12549.71 ms / 1124 tokens ( 11.17 ms per token, 89.56 tokens per second) 12.30.680.680 I slot print_timing: id 1 | task 4791 | eval time = 483.06 ms / 2 tokens ( 483.06 ms per token, 2.07 tokens per second) 12.30.680.683 I slot print_timing: id 1 | task 4791 | total time = 13032.77 ms / 1126 tokens 12.30.680.685 I slot print_timing: id 1 | task 4791 | graphs reused = 3435 12.30.680.687 I slot print_timing: id 1 | task 4791 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.684.372 I slot release: id 1 | task 4791 | stop processing: n_tokens = 1125, truncated = 0 12.30.685.059 I slot print_timing: id 2 | task 4792 | prompt eval time = 12550.59 ms / 1161 tokens ( 10.81 ms per token, 92.51 tokens per second) 12.30.685.066 I slot print_timing: id 2 | task 4792 | eval time = 486.47 ms / 2 tokens ( 486.47 ms per token, 2.06 tokens per second) 12.30.685.067 I slot print_timing: id 2 | task 4792 | total time = 13037.06 ms / 1163 tokens 12.30.685.067 I slot print_timing: id 2 | task 4792 | graphs reused = 3435 12.30.685.068 I slot print_timing: id 2 | task 4792 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.685.177 I slot release: id 2 | task 4792 | stop processing: n_tokens = 1162, truncated = 0 12.30.685.864 I slot print_timing: id 3 | task 4793 | prompt eval time = 12551.28 ms / 2091 tokens ( 6.00 ms per token, 166.60 tokens per second) 12.30.685.868 I slot print_timing: id 3 | task 4793 | eval time = 486.51 ms / 2 tokens ( 486.51 ms per token, 2.06 tokens per second) 12.30.685.869 I slot print_timing: id 3 | task 4793 | total time = 13037.79 ms / 2093 tokens 12.30.685.870 I slot print_timing: id 3 | task 4793 | graphs reused = 3435 12.30.685.870 I slot print_timing: id 3 | task 4793 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.690.089 I slot release: id 3 | task 4793 | stop processing: n_tokens = 2092, truncated = 0 12.30.690.121 I slot print_timing: id 0 | task 4797 | prompt processing, n_tokens = 1761, progress = 0.84, t = 7.22 s / 244.05 tokens per second 12.30.724.046 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 12.30.724.092 I slot launch_slot_: id 3 | task 4803 | processing task, is_child = 0 12.30.724.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.243 MiB) 12.31.534.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.361 MiB) 12.32.377.284 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1125, t_last = 387560123906 12.32.377.607 I slot launch_slot_: id 1 | task 4804 | processing task, is_child = 0 12.32.377.660 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1162, t_last = 387560124709 12.32.377.737 I slot launch_slot_: id 2 | task 4805 | processing task, is_child = 0 12.32.377.748 I slot print_timing: id 0 | task 4797 | prompt processing, n_tokens = 2090, progress = 1.00, t = 7.26 s / 287.88 tokens per second 12.35.456.146 I slot print_timing: id 0 | task 4797 | prompt eval time = 10910.88 ms / 2094 tokens ( 5.21 ms per token, 191.92 tokens per second) 12.35.456.169 I slot print_timing: id 0 | task 4797 | eval time = 1081.21 ms / 2 tokens ( 1081.21 ms per token, 0.92 tokens per second) 12.35.456.172 I slot print_timing: id 0 | task 4797 | total time = 11992.09 ms / 2096 tokens 12.35.456.174 I slot print_timing: id 0 | task 4797 | graphs reused = 3435 12.35.456.176 I slot print_timing: id 0 | task 4797 | graph reallocs = 0 / 0 (same size) / (changed size) 12.35.459.696 I slot release: id 0 | task 4797 | stop processing: n_tokens = 2095, truncated = 0 12.35.460.579 I slot print_timing: id 1 | task 4804 | prompt processing, n_tokens = 640, progress = 0.30, t = 3.06 s / 209.04 tokens per second 12.35.460.641 I slot print_timing: id 2 | task 4805 | prompt processing, n_tokens = 640, progress = 0.31, t = 3.06 s / 209.05 tokens per second 12.38.647.904 I slot print_timing: id 3 | task 4803 | prompt eval time = 3066.86 ms / 296 tokens ( 10.36 ms per token, 96.52 tokens per second) 12.38.647.922 I slot print_timing: id 3 | task 4803 | eval time = 3187.34 ms / 2 tokens ( 3187.34 ms per token, 0.31 tokens per second) 12.38.647.933 I slot print_timing: id 3 | task 4803 | total time = 6254.19 ms / 298 tokens 12.38.647.936 I slot print_timing: id 3 | task 4803 | graphs reused = 3435 12.38.647.946 I slot print_timing: id 3 | task 4803 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.650.944 I slot release: id 3 | task 4803 | stop processing: n_tokens = 2058, truncated = 0 12.38.650.992 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 12.38.651.280 I slot launch_slot_: id 0 | task 4809 | processing task, is_child = 0 12.38.651.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.204 MiB) 12.39.555.626 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 12.39.555.694 I slot launch_slot_: id 3 | task 4810 | processing task, is_child = 0 12.39.562.871 I slot print_timing: id 1 | task 4804 | prompt processing, n_tokens = 1589, progress = 0.75, t = 6.25 s / 254.10 tokens per second 12.39.567.277 I slot print_timing: id 2 | task 4805 | prompt processing, n_tokens = 1525, progress = 0.75, t = 6.25 s / 243.87 tokens per second 12.41.903.181 I slot print_timing: id 1 | task 4804 | prompt processing, n_tokens = 1761, progress = 0.84, t = 9.28 s / 189.67 tokens per second 12.41.949.630 I slot print_timing: id 2 | task 4805 | prompt processing, n_tokens = 1761, progress = 0.86, t = 9.28 s / 189.68 tokens per second 12.43.413.580 I slot print_timing: id 1 | task 4804 | prompt processing, n_tokens = 2101, progress = 1.00, t = 11.02 s / 190.68 tokens per second 12.43.442.180 I slot print_timing: id 2 | task 4805 | prompt processing, n_tokens = 2037, progress = 1.00, t = 11.02 s / 184.87 tokens per second 12.43.577.441 I slot print_timing: id 0 | task 4809 | prompt eval time = 3856.99 ms / 369 tokens ( 10.45 ms per token, 95.67 tokens per second) 12.43.577.451 I slot print_timing: id 0 | task 4809 | eval time = 164.74 ms / 2 tokens ( 164.74 ms per token, 6.07 tokens per second) 12.43.577.452 I slot print_timing: id 0 | task 4809 | total time = 4021.73 ms / 371 tokens 12.43.577.452 I slot print_timing: id 0 | task 4809 | graphs reused = 3435 12.43.577.453 I slot print_timing: id 0 | task 4809 | graph reallocs = 0 / 0 (same size) / (changed size) 12.43.578.336 I slot release: id 0 | task 4809 | stop processing: n_tokens = 2131, truncated = 0 12.43.579.683 I slot print_timing: id 3 | task 4810 | prompt eval time = 3841.89 ms / 300 tokens ( 12.81 ms per token, 78.09 tokens per second) 12.43.579.689 I slot print_timing: id 3 | task 4810 | eval time = 166.18 ms / 2 tokens ( 166.18 ms per token, 6.02 tokens per second) 12.43.580.003 I slot print_timing: id 3 | task 4810 | total time = 4008.07 ms / 302 tokens 12.43.580.009 I slot print_timing: id 3 | task 4810 | graphs reused = 3435 12.43.580.009 I slot print_timing: id 3 | task 4810 | graph reallocs = 0 / 0 (same size) / (changed size) 12.43.580.767 I slot release: id 3 | task 4810 | stop processing: n_tokens = 2062, truncated = 0 12.43.616.024 I slot print_timing: id 1 | task 4804 | prompt eval time = 11185.43 ms / 2105 tokens ( 5.31 ms per token, 188.19 tokens per second) 12.43.616.027 I slot print_timing: id 1 | task 4804 | eval time = 37.11 ms / 2 tokens ( 37.11 ms per token, 26.95 tokens per second) 12.43.616.028 I slot print_timing: id 1 | task 4804 | total time = 11222.54 ms / 2107 tokens 12.43.616.028 I slot print_timing: id 1 | task 4804 | graphs reused = 3435 12.43.616.029 I slot print_timing: id 1 | task 4804 | graph reallocs = 0 / 0 (same size) / (changed size) 12.43.616.927 I slot release: id 1 | task 4804 | stop processing: n_tokens = 2106, truncated = 0 12.43.617.134 I slot print_timing: id 2 | task 4805 | prompt eval time = 11185.91 ms / 2041 tokens ( 5.48 ms per token, 182.46 tokens per second) 12.43.617.137 I slot print_timing: id 2 | task 4805 | eval time = 37.65 ms / 2 tokens ( 37.65 ms per token, 26.56 tokens per second) 12.43.617.137 I slot print_timing: id 2 | task 4805 | total time = 11223.56 ms / 2043 tokens 12.43.617.138 I slot print_timing: id 2 | task 4805 | graphs reused = 3435 12.43.617.138 I slot print_timing: id 2 | task 4805 | graph reallocs = 0 / 0 (same size) / (changed size) 12.43.617.213 I slot release: id 2 | task 4805 | stop processing: n_tokens = 2042, truncated = 0 12.43.617.225 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 12.43.617.273 I slot launch_slot_: id 0 | task 4815 | processing task, is_child = 0 12.43.617.413 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.126 MiB) 12.44.672.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.107 MiB) 12.45.606.418 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.204 MiB) 12.46.509.227 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.803 (> 0.100 thold), f_keep = 0.850 12.46.509.318 I slot launch_slot_: id 1 | task 4816 | processing task, is_child = 0 12.46.509.495 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.877 12.46.509.521 I slot launch_slot_: id 2 | task 4817 | processing task, is_child = 0 12.46.509.607 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.868 12.46.509.627 I slot launch_slot_: id 3 | task 4818 | processing task, is_child = 0 12.49.729.827 I slot print_timing: id 0 | task 4815 | prompt eval time = 3163.91 ms / 380 tokens ( 8.33 ms per token, 120.10 tokens per second) 12.49.729.831 I slot print_timing: id 0 | task 4815 | eval time = 56.27 ms / 2 tokens ( 56.27 ms per token, 17.77 tokens per second) 12.49.729.832 I slot print_timing: id 0 | task 4815 | total time = 3220.18 ms / 382 tokens 12.49.729.832 I slot print_timing: id 0 | task 4815 | graphs reused = 3435 12.49.729.833 I slot print_timing: id 0 | task 4815 | graph reallocs = 0 / 0 (same size) / (changed size) 12.49.730.033 I slot release: id 0 | task 4815 | stop processing: n_tokens = 2142, truncated = 0 12.49.730.364 I slot print_timing: id 1 | task 4816 | prompt eval time = 3148.22 ms / 467 tokens ( 6.74 ms per token, 148.34 tokens per second) 12.49.730.369 I slot print_timing: id 1 | task 4816 | eval time = 55.76 ms / 2 tokens ( 55.76 ms per token, 17.93 tokens per second) 12.49.730.369 I slot print_timing: id 1 | task 4816 | total time = 3203.97 ms / 469 tokens 12.49.730.370 I slot print_timing: id 1 | task 4816 | graphs reused = 3435 12.49.730.371 I slot print_timing: id 1 | task 4816 | graph reallocs = 0 / 0 (same size) / (changed size) 12.49.730.488 I slot release: id 1 | task 4816 | stop processing: n_tokens = 2229, truncated = 0 12.49.730.709 I slot print_timing: id 2 | task 4817 | prompt eval time = 3125.32 ms / 258 tokens ( 12.11 ms per token, 82.55 tokens per second) 12.49.730.712 I slot print_timing: id 2 | task 4817 | eval time = 55.30 ms / 2 tokens ( 55.30 ms per token, 18.08 tokens per second) 12.49.730.712 I slot print_timing: id 2 | task 4817 | total time = 3180.62 ms / 260 tokens 12.49.730.713 I slot print_timing: id 2 | task 4817 | graphs reused = 3435 12.49.730.713 I slot print_timing: id 2 | task 4817 | graph reallocs = 0 / 0 (same size) / (changed size) 12.49.732.861 I slot release: id 2 | task 4817 | stop processing: n_tokens = 2020, truncated = 0 12.49.733.088 I slot print_timing: id 3 | task 4818 | prompt eval time = 3122.67 ms / 210 tokens ( 14.87 ms per token, 67.25 tokens per second) 12.49.733.093 I slot print_timing: id 3 | task 4818 | eval time = 56.88 ms / 2 tokens ( 56.88 ms per token, 17.58 tokens per second) 12.49.733.094 I slot print_timing: id 3 | task 4818 | total time = 3179.55 ms / 212 tokens 12.49.733.094 I slot print_timing: id 3 | task 4818 | graphs reused = 3435 12.49.733.095 I slot print_timing: id 3 | task 4818 | graph reallocs = 0 / 0 (same size) / (changed size) 12.49.734.030 I slot release: id 3 | task 4818 | stop processing: n_tokens = 1972, truncated = 0 12.49.748.898 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.835 12.49.748.938 I slot launch_slot_: id 0 | task 4822 | processing task, is_child = 0 12.49.749.075 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.165 MiB) 12.50.559.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.185 MiB) 12.51.389.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.972 MiB) 12.52.167.709 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.850 (> 0.100 thold), f_keep = 0.803 12.52.167.809 I slot launch_slot_: id 1 | task 4823 | processing task, is_child = 0 12.52.167.989 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.886 12.52.168.026 I slot launch_slot_: id 2 | task 4824 | processing task, is_child = 0 12.52.168.112 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.908 12.52.168.140 I slot launch_slot_: id 3 | task 4825 | processing task, is_child = 0 12.54.858.101 I slot print_timing: id 0 | task 4822 | prompt eval time = 2632.27 ms / 212 tokens ( 12.42 ms per token, 80.54 tokens per second) 12.54.858.105 I slot print_timing: id 0 | task 4822 | eval time = 57.67 ms / 2 tokens ( 57.67 ms per token, 17.34 tokens per second) 12.54.861.036 I slot print_timing: id 0 | task 4822 | total time = 2689.94 ms / 214 tokens 12.54.861.042 I slot print_timing: id 0 | task 4822 | graphs reused = 3435 12.54.861.043 I slot print_timing: id 0 | task 4822 | graph reallocs = 0 / 0 (same size) / (changed size) 12.54.861.701 I slot release: id 0 | task 4822 | stop processing: n_tokens = 1974, truncated = 0 12.54.861.958 I slot print_timing: id 1 | task 4823 | prompt eval time = 2618.38 ms / 345 tokens ( 7.59 ms per token, 131.76 tokens per second) 12.54.861.964 I slot print_timing: id 1 | task 4823 | eval time = 60.52 ms / 2 tokens ( 60.52 ms per token, 16.52 tokens per second) 12.54.861.965 I slot print_timing: id 1 | task 4823 | total time = 2678.90 ms / 347 tokens 12.54.861.966 I slot print_timing: id 1 | task 4823 | graphs reused = 3435 12.54.861.966 I slot print_timing: id 1 | task 4823 | graph reallocs = 0 / 0 (same size) / (changed size) 12.54.862.607 I slot release: id 1 | task 4823 | stop processing: n_tokens = 2107, truncated = 0 12.54.862.884 I slot print_timing: id 2 | task 4824 | prompt eval time = 2615.59 ms / 253 tokens ( 10.34 ms per token, 96.73 tokens per second) 12.54.862.889 I slot print_timing: id 2 | task 4824 | eval time = 60.51 ms / 2 tokens ( 60.51 ms per token, 16.53 tokens per second) 12.54.862.889 I slot print_timing: id 2 | task 4824 | total time = 2676.11 ms / 255 tokens 12.54.862.890 I slot print_timing: id 2 | task 4824 | graphs reused = 3435 12.54.862.891 I slot print_timing: id 2 | task 4824 | graph reallocs = 0 / 0 (same size) / (changed size) 12.54.862.979 I slot release: id 2 | task 4824 | stop processing: n_tokens = 2015, truncated = 0 12.54.863.257 I slot print_timing: id 3 | task 4825 | prompt eval time = 2612.96 ms / 304 tokens ( 8.60 ms per token, 116.34 tokens per second) 12.54.863.260 I slot print_timing: id 3 | task 4825 | eval time = 60.03 ms / 2 tokens ( 60.03 ms per token, 16.66 tokens per second) 12.54.863.261 I slot print_timing: id 3 | task 4825 | total time = 2672.99 ms / 306 tokens 12.54.863.262 I slot print_timing: id 3 | task 4825 | graphs reused = 3435 12.54.863.262 I slot print_timing: id 3 | task 4825 | graph reallocs = 0 / 0 (same size) / (changed size) 12.54.864.419 I slot release: id 3 | task 4825 | stop processing: n_tokens = 2066, truncated = 0 12.54.883.643 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.847 (> 0.100 thold), f_keep = 0.850 12.54.883.683 I slot launch_slot_: id 1 | task 4829 | processing task, is_child = 0 12.54.883.826 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.028 MiB) 12.55.886.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.713 MiB) 12.57.052.290 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.520 MiB) 12.57.882.865 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 12.57.882.943 I slot launch_slot_: id 3 | task 4830 | processing task, is_child = 0 12.57.883.115 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.906 12.57.883.139 I slot launch_slot_: id 0 | task 4831 | processing task, is_child = 0 12.57.883.230 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.888 12.57.883.249 I slot launch_slot_: id 2 | task 4832 | processing task, is_child = 0 13.00.855.165 I slot print_timing: id 0 | task 4831 | prompt eval time = 2915.62 ms / 405 tokens ( 7.20 ms per token, 138.91 tokens per second) 13.00.855.171 I slot print_timing: id 0 | task 4831 | eval time = 56.27 ms / 2 tokens ( 56.27 ms per token, 17.77 tokens per second) 13.00.855.171 I slot print_timing: id 0 | task 4831 | total time = 2971.90 ms / 407 tokens 13.00.855.172 I slot print_timing: id 0 | task 4831 | graphs reused = 3435 13.00.855.173 I slot print_timing: id 0 | task 4831 | graph reallocs = 0 / 0 (same size) / (changed size) 13.00.856.399 I slot release: id 0 | task 4831 | stop processing: n_tokens = 2167, truncated = 0 13.00.856.705 I slot print_timing: id 1 | task 4829 | prompt eval time = 2905.51 ms / 353 tokens ( 8.23 ms per token, 121.49 tokens per second) 13.00.856.709 I slot print_timing: id 1 | task 4829 | eval time = 57.11 ms / 2 tokens ( 57.11 ms per token, 17.51 tokens per second) 13.00.856.710 I slot print_timing: id 1 | task 4829 | total time = 2962.62 ms / 355 tokens 13.00.856.711 I slot print_timing: id 1 | task 4829 | graphs reused = 3435 13.00.856.712 I slot print_timing: id 1 | task 4829 | graph reallocs = 0 / 0 (same size) / (changed size) 13.00.856.852 I slot release: id 1 | task 4829 | stop processing: n_tokens = 2115, truncated = 0 13.00.857.385 I slot print_timing: id 2 | task 4832 | prompt eval time = 2902.86 ms / 304 tokens ( 9.55 ms per token, 104.72 tokens per second) 13.00.857.389 I slot print_timing: id 2 | task 4832 | eval time = 57.11 ms / 2 tokens ( 57.11 ms per token, 17.51 tokens per second) 13.00.857.390 I slot print_timing: id 2 | task 4832 | total time = 2959.97 ms / 306 tokens 13.00.857.390 I slot print_timing: id 2 | task 4832 | graphs reused = 3435 13.00.857.391 I slot print_timing: id 2 | task 4832 | graph reallocs = 0 / 0 (same size) / (changed size) 13.00.857.487 I slot release: id 2 | task 4832 | stop processing: n_tokens = 2066, truncated = 0 13.00.857.708 I slot print_timing: id 3 | task 4830 | prompt eval time = 2900.22 ms / 210 tokens ( 13.81 ms per token, 72.41 tokens per second) 13.00.857.712 I slot print_timing: id 3 | task 4830 | eval time = 56.70 ms / 2 tokens ( 56.70 ms per token, 17.64 tokens per second) 13.00.857.713 I slot print_timing: id 3 | task 4830 | total time = 2956.92 ms / 212 tokens 13.00.857.713 I slot print_timing: id 3 | task 4830 | graphs reused = 3435 13.00.857.713 I slot print_timing: id 3 | task 4830 | graph reallocs = 0 / 0 (same size) / (changed size) 13.00.858.085 I slot release: id 3 | task 4830 | stop processing: n_tokens = 1972, truncated = 0 13.00.876.856 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.826 13.00.876.901 I slot launch_slot_: id 0 | task 4836 | processing task, is_child = 0 13.00.877.064 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.227 MiB) 13.00.877.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.341 MiB) 13.01.660.209 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.671 MiB) 13.02.784.450 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.810 MiB) 13.03.878.078 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.846 13.03.878.536 I slot launch_slot_: id 1 | task 4837 | processing task, is_child = 0 13.03.878.735 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.908 13.03.878.797 I slot launch_slot_: id 3 | task 4838 | processing task, is_child = 0 13.03.878.887 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.866 13.03.878.908 I slot launch_slot_: id 2 | task 4839 | processing task, is_child = 0 13.06.644.129 I slot print_timing: id 0 | task 4836 | prompt eval time = 2706.73 ms / 236 tokens ( 11.47 ms per token, 87.19 tokens per second) 13.06.644.133 I slot print_timing: id 0 | task 4836 | eval time = 58.47 ms / 2 tokens ( 58.47 ms per token, 17.10 tokens per second) 13.06.644.134 I slot print_timing: id 0 | task 4836 | total time = 2765.20 ms / 238 tokens 13.06.644.135 I slot print_timing: id 0 | task 4836 | graphs reused = 3435 13.06.644.136 I slot print_timing: id 0 | task 4836 | graph reallocs = 0 / 0 (same size) / (changed size) 13.06.645.104 I slot release: id 0 | task 4836 | stop processing: n_tokens = 1998, truncated = 0 13.06.645.639 I slot print_timing: id 1 | task 4837 | prompt eval time = 2700.73 ms / 264 tokens ( 10.23 ms per token, 97.75 tokens per second) 13.06.645.642 I slot print_timing: id 1 | task 4837 | eval time = 59.02 ms / 2 tokens ( 59.02 ms per token, 16.94 tokens per second) 13.06.645.914 I slot print_timing: id 1 | task 4837 | total time = 2759.75 ms / 266 tokens 13.06.645.922 I slot print_timing: id 1 | task 4837 | graphs reused = 3435 13.06.645.923 I slot print_timing: id 1 | task 4837 | graph reallocs = 0 / 0 (same size) / (changed size) 13.06.646.027 I slot release: id 1 | task 4837 | stop processing: n_tokens = 2026, truncated = 0 13.06.646.502 I slot print_timing: id 2 | task 4839 | prompt eval time = 2697.59 ms / 272 tokens ( 9.92 ms per token, 100.83 tokens per second) 13.06.646.507 I slot print_timing: id 2 | task 4839 | eval time = 58.91 ms / 2 tokens ( 58.91 ms per token, 16.97 tokens per second) 13.06.646.508 I slot print_timing: id 2 | task 4839 | total time = 2756.50 ms / 274 tokens 13.06.646.508 I slot print_timing: id 2 | task 4839 | graphs reused = 3435 13.06.646.509 I slot print_timing: id 2 | task 4839 | graph reallocs = 0 / 0 (same size) / (changed size) 13.06.646.987 I slot release: id 2 | task 4839 | stop processing: n_tokens = 2034, truncated = 0 13.06.647.216 I slot print_timing: id 3 | task 4838 | prompt eval time = 2673.89 ms / 413 tokens ( 6.47 ms per token, 154.46 tokens per second) 13.06.647.221 I slot print_timing: id 3 | task 4838 | eval time = 58.88 ms / 2 tokens ( 58.88 ms per token, 16.98 tokens per second) 13.06.647.221 I slot print_timing: id 3 | task 4838 | total time = 2732.77 ms / 415 tokens 13.06.647.222 I slot print_timing: id 3 | task 4838 | graphs reused = 3435 13.06.647.222 I slot print_timing: id 3 | task 4838 | graph reallocs = 0 / 0 (same size) / (changed size) 13.06.647.334 I slot release: id 3 | task 4838 | stop processing: n_tokens = 2175, truncated = 0 13.06.663.819 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.895 13.06.663.858 I slot launch_slot_: id 0 | task 4843 | processing task, is_child = 0 13.06.664.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.673 MiB) 13.07.513.975 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.849 MiB) 13.08.785.718 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.536 MiB) 13.09.526.494 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.883 13.09.526.622 I slot launch_slot_: id 1 | task 4844 | processing task, is_child = 0 13.09.526.817 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.823 13.09.526.857 I slot launch_slot_: id 3 | task 4845 | processing task, is_child = 0 13.09.526.949 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2034, t_last = 387596086521 13.09.527.060 I slot launch_slot_: id 2 | task 4846 | processing task, is_child = 0 13.13.242.429 I slot print_timing: id 0 | task 4843 | prompt eval time = 2959.50 ms / 149 tokens ( 19.86 ms per token, 50.35 tokens per second) 13.13.242.438 I slot print_timing: id 0 | task 4843 | eval time = 755.83 ms / 2 tokens ( 755.83 ms per token, 1.32 tokens per second) 13.13.242.439 I slot print_timing: id 0 | task 4843 | total time = 3715.33 ms / 151 tokens 13.13.242.440 I slot print_timing: id 0 | task 4843 | graphs reused = 3435 13.13.242.441 I slot print_timing: id 0 | task 4843 | graph reallocs = 0 / 0 (same size) / (changed size) 13.13.243.037 I slot release: id 0 | task 4843 | stop processing: n_tokens = 1911, truncated = 0 13.13.244.592 I slot print_timing: id 1 | task 4844 | prompt eval time = 2948.34 ms / 196 tokens ( 15.04 ms per token, 66.48 tokens per second) 13.13.244.642 I slot print_timing: id 1 | task 4844 | eval time = 755.87 ms / 2 tokens ( 755.87 ms per token, 1.32 tokens per second) 13.13.244.647 I slot print_timing: id 1 | task 4844 | total time = 3704.21 ms / 198 tokens 13.13.244.649 I slot print_timing: id 1 | task 4844 | graphs reused = 3435 13.13.244.650 I slot print_timing: id 1 | task 4844 | graph reallocs = 0 / 0 (same size) / (changed size) 13.13.246.359 I slot release: id 1 | task 4844 | stop processing: n_tokens = 1958, truncated = 0 13.13.247.895 I slot print_timing: id 3 | task 4845 | prompt eval time = 2914.08 ms / 230 tokens ( 12.67 ms per token, 78.93 tokens per second) 13.13.247.902 I slot print_timing: id 3 | task 4845 | eval time = 757.52 ms / 2 tokens ( 757.52 ms per token, 1.32 tokens per second) 13.13.247.906 I slot print_timing: id 3 | task 4845 | total time = 3671.60 ms / 232 tokens 13.13.247.907 I slot print_timing: id 3 | task 4845 | graphs reused = 3435 13.13.247.908 I slot print_timing: id 3 | task 4845 | graph reallocs = 0 / 0 (same size) / (changed size) 13.13.248.269 I slot release: id 3 | task 4845 | stop processing: n_tokens = 1992, truncated = 0 13.13.248.425 I slot print_timing: id 2 | task 4846 | prompt processing, n_tokens = 959, progress = 0.65, t = 3.67 s / 261.62 tokens per second 13.13.273.979 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1911, t_last = 387602682573 13.13.274.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.693 MiB) 13.14.005.445 I slot launch_slot_: id 0 | task 4851 | processing task, is_child = 0 13.14.005.565 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.112 MiB) 13.15.227.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.444 MiB) 13.16.392.370 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1958, t_last = 387602685895 13.16.393.097 I slot launch_slot_: id 1 | task 4852 | processing task, is_child = 0 13.16.393.212 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1992, t_last = 387602687804 13.16.393.332 I slot launch_slot_: id 3 | task 4853 | processing task, is_child = 0 13.16.393.807 I slot print_timing: id 2 | task 4846 | prompt processing, n_tokens = 1275, progress = 0.86, t = 3.70 s / 344.79 tokens per second 13.18.927.536 I slot print_timing: id 2 | task 4846 | prompt processing, n_tokens = 1471, progress = 1.00, t = 8.94 s / 164.55 tokens per second 13.20.346.133 I slot print_timing: id 0 | task 4851 | prompt processing, n_tokens = 409, progress = 0.41, t = 3.95 s / 103.52 tokens per second 13.20.346.195 I slot print_timing: id 1 | task 4852 | prompt processing, n_tokens = 575, progress = 0.37, t = 3.95 s / 145.54 tokens per second 13.20.346.266 I slot print_timing: id 3 | task 4853 | prompt processing, n_tokens = 575, progress = 0.34, t = 3.95 s / 145.71 tokens per second 13.22.566.855 I slot print_timing: id 2 | task 4846 | prompt eval time = 10769.88 ms / 1475 tokens ( 7.30 ms per token, 136.96 tokens per second) 13.22.566.869 I slot print_timing: id 2 | task 4846 | eval time = 2220.86 ms / 2 tokens ( 2220.86 ms per token, 0.45 tokens per second) 13.22.566.871 I slot print_timing: id 2 | task 4846 | total time = 12990.73 ms / 1477 tokens 13.22.566.872 I slot print_timing: id 2 | task 4846 | graphs reused = 3435 13.22.566.873 I slot print_timing: id 2 | task 4846 | graph reallocs = 0 / 0 (same size) / (changed size) 13.22.572.781 I slot release: id 2 | task 4846 | stop processing: n_tokens = 1476, truncated = 0 13.22.572.919 I slot print_timing: id 0 | task 4851 | prompt processing, n_tokens = 483, progress = 0.48, t = 6.17 s / 78.24 tokens per second 13.22.617.768 I slot print_timing: id 1 | task 4852 | prompt processing, n_tokens = 1039, progress = 0.67, t = 6.17 s / 168.32 tokens per second 13.22.652.611 I slot print_timing: id 3 | task 4853 | prompt processing, n_tokens = 1161, progress = 0.69, t = 6.17 s / 188.22 tokens per second 13.23.840.110 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 387612012319 13.23.840.315 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.760 MiB) 13.24.447.150 I slot launch_slot_: id 2 | task 4858 | processing task, is_child = 0 13.24.447.173 I slot print_timing: id 0 | task 4851 | prompt processing, n_tokens = 853, progress = 0.85, t = 7.45 s / 114.55 tokens per second 13.24.449.575 I slot print_timing: id 1 | task 4852 | prompt processing, n_tokens = 1275, progress = 0.82, t = 7.45 s / 171.22 tokens per second 13.24.451.979 I slot print_timing: id 3 | task 4853 | prompt processing, n_tokens = 1275, progress = 0.76, t = 7.44 s / 171.33 tokens per second 13.26.361.482 I slot print_timing: id 0 | task 4851 | prompt processing, n_tokens = 995, progress = 1.00, t = 9.97 s / 99.82 tokens per second 13.26.720.633 I slot print_timing: id 1 | task 4852 | prompt processing, n_tokens = 1551, progress = 1.00, t = 9.97 s / 155.60 tokens per second 13.26.739.736 I slot print_timing: id 3 | task 4853 | prompt processing, n_tokens = 1673, progress = 1.00, t = 9.96 s / 167.92 tokens per second 13.27.695.413 I slot print_timing: id 0 | task 4851 | prompt eval time = 11017.70 ms / 999 tokens ( 11.03 ms per token, 90.67 tokens per second) 13.27.695.420 I slot print_timing: id 0 | task 4851 | eval time = 284.34 ms / 2 tokens ( 284.34 ms per token, 3.52 tokens per second) 13.27.695.421 I slot print_timing: id 0 | task 4851 | total time = 11302.04 ms / 1001 tokens 13.27.695.422 I slot print_timing: id 0 | task 4851 | graphs reused = 3435 13.27.695.423 I slot print_timing: id 0 | task 4851 | graph reallocs = 0 / 0 (same size) / (changed size) 13.27.697.749 I slot release: id 0 | task 4851 | stop processing: n_tokens = 1000, truncated = 0 13.27.698.987 I slot print_timing: id 1 | task 4852 | prompt eval time = 11017.84 ms / 1555 tokens ( 7.09 ms per token, 141.13 tokens per second) 13.27.698.995 I slot print_timing: id 1 | task 4852 | eval time = 287.51 ms / 2 tokens ( 287.51 ms per token, 3.48 tokens per second) 13.27.698.996 I slot print_timing: id 1 | task 4852 | total time = 11305.36 ms / 1557 tokens 13.27.698.996 I slot print_timing: id 1 | task 4852 | graphs reused = 3435 13.27.698.997 I slot print_timing: id 1 | task 4852 | graph reallocs = 0 / 0 (same size) / (changed size) 13.27.700.661 I slot release: id 1 | task 4852 | stop processing: n_tokens = 1556, truncated = 0 13.27.701.592 I slot print_timing: id 3 | task 4853 | prompt eval time = 11013.74 ms / 1677 tokens ( 6.57 ms per token, 152.26 tokens per second) 13.27.701.602 I slot print_timing: id 3 | task 4853 | eval time = 289.66 ms / 2 tokens ( 289.66 ms per token, 3.45 tokens per second) 13.27.701.603 I slot print_timing: id 3 | task 4853 | total time = 11303.41 ms / 1679 tokens 13.27.701.604 I slot print_timing: id 3 | task 4853 | graphs reused = 3435 13.27.701.605 I slot print_timing: id 3 | task 4853 | graph reallocs = 0 / 0 (same size) / (changed size) 13.27.702.357 I slot release: id 3 | task 4853 | stop processing: n_tokens = 1678, truncated = 0 13.27.702.390 I slot print_timing: id 2 | task 4858 | prompt processing, n_tokens = 473, progress = 0.48, t = 3.24 s / 145.85 tokens per second 13.27.741.091 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.881 13.27.741.151 I slot launch_slot_: id 0 | task 4863 | processing task, is_child = 0 13.27.741.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.500 MiB) 13.28.415.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 336.065 MiB) 13.29.397.744 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1556, t_last = 387617140196 13.29.397.907 I slot launch_slot_: id 1 | task 4864 | processing task, is_child = 0 13.29.397.980 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1678, t_last = 387617141892 13.29.398.069 I slot launch_slot_: id 3 | task 4865 | processing task, is_child = 0 13.29.401.477 I slot print_timing: id 2 | task 4858 | prompt processing, n_tokens = 853, progress = 0.86, t = 3.29 s / 259.33 tokens per second 13.31.087.754 I slot print_timing: id 2 | task 4858 | prompt processing, n_tokens = 985, progress = 1.00, t = 6.28 s / 156.77 tokens per second 13.32.423.907 I slot print_timing: id 0 | task 4863 | prompt eval time = 2578.01 ms / 130 tokens ( 19.83 ms per token, 50.43 tokens per second) 13.32.423.919 I slot print_timing: id 0 | task 4863 | eval time = 447.81 ms / 2 tokens ( 447.81 ms per token, 2.23 tokens per second) 13.32.423.920 I slot print_timing: id 0 | task 4863 | total time = 3025.81 ms / 132 tokens 13.32.423.922 I slot print_timing: id 0 | task 4863 | graphs reused = 3435 13.32.423.923 I slot print_timing: id 0 | task 4863 | graph reallocs = 0 / 0 (same size) / (changed size) 13.32.424.153 I slot release: id 0 | task 4863 | stop processing: n_tokens = 984, truncated = 0 13.32.425.140 I slot print_timing: id 2 | task 4858 | prompt eval time = 7525.39 ms / 989 tokens ( 7.61 ms per token, 131.42 tokens per second) 13.32.425.146 I slot print_timing: id 2 | task 4858 | eval time = 447.89 ms / 2 tokens ( 447.89 ms per token, 2.23 tokens per second) 13.32.425.148 I slot print_timing: id 2 | task 4858 | total time = 7973.28 ms / 991 tokens 13.32.425.149 I slot print_timing: id 2 | task 4858 | graphs reused = 3435 13.32.425.150 I slot print_timing: id 2 | task 4858 | graph reallocs = 0 / 0 (same size) / (changed size) 13.32.426.366 I slot release: id 2 | task 4858 | stop processing: n_tokens = 990, truncated = 0 13.32.426.416 I slot print_timing: id 1 | task 4864 | prompt processing, n_tokens = 461, progress = 0.47, t = 3.02 s / 152.56 tokens per second 13.32.433.674 I slot print_timing: id 3 | task 4865 | prompt processing, n_tokens = 444, progress = 0.46, t = 3.02 s / 147.04 tokens per second 13.33.154.743 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.895 13.33.155.004 I slot launch_slot_: id 0 | task 4870 | processing task, is_child = 0 13.33.155.155 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 336.788 MiB) 13.34.208.496 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.890 13.34.208.593 I slot launch_slot_: id 2 | task 4871 | processing task, is_child = 0 13.34.217.368 I slot print_timing: id 1 | task 4864 | prompt processing, n_tokens = 853, progress = 0.87, t = 3.75 s / 227.26 tokens per second 13.34.222.555 I slot print_timing: id 3 | task 4865 | prompt processing, n_tokens = 853, progress = 0.89, t = 3.75 s / 227.39 tokens per second 13.35.218.986 I slot print_timing: id 1 | task 4864 | prompt processing, n_tokens = 973, progress = 1.00, t = 5.80 s / 167.80 tokens per second 13.35.268.583 I slot print_timing: id 3 | task 4865 | prompt processing, n_tokens = 956, progress = 1.00, t = 5.80 s / 164.93 tokens per second 13.35.460.162 I slot print_timing: id 0 | task 4870 | prompt eval time = 1197.44 ms / 123 tokens ( 9.74 ms per token, 102.72 tokens per second) 13.35.460.168 I slot print_timing: id 0 | task 4870 | eval time = 54.10 ms / 2 tokens ( 54.10 ms per token, 18.48 tokens per second) 13.35.460.168 I slot print_timing: id 0 | task 4870 | total time = 1251.55 ms / 125 tokens 13.35.460.169 I slot print_timing: id 0 | task 4870 | graphs reused = 3435 13.35.460.169 I slot print_timing: id 0 | task 4870 | graph reallocs = 0 / 0 (same size) / (changed size) 13.35.460.310 I slot release: id 0 | task 4870 | stop processing: n_tokens = 977, truncated = 0 13.35.460.523 I slot print_timing: id 1 | task 4864 | prompt eval time = 6004.92 ms / 977 tokens ( 6.15 ms per token, 162.70 tokens per second) 13.35.460.528 I slot print_timing: id 1 | task 4864 | eval time = 54.23 ms / 2 tokens ( 54.23 ms per token, 18.44 tokens per second) 13.35.460.528 I slot print_timing: id 1 | task 4864 | total time = 6059.15 ms / 979 tokens 13.35.460.529 I slot print_timing: id 1 | task 4864 | graphs reused = 3435 13.35.460.529 I slot print_timing: id 1 | task 4864 | graph reallocs = 0 / 0 (same size) / (changed size) 13.35.460.589 I slot release: id 1 | task 4864 | stop processing: n_tokens = 978, truncated = 0 13.35.460.824 I slot print_timing: id 2 | task 4871 | prompt eval time = 1187.30 ms / 119 tokens ( 9.98 ms per token, 100.23 tokens per second) 13.35.460.827 I slot print_timing: id 2 | task 4871 | eval time = 54.26 ms / 2 tokens ( 54.26 ms per token, 18.43 tokens per second) 13.35.460.827 I slot print_timing: id 2 | task 4871 | total time = 1241.56 ms / 121 tokens 13.35.460.828 I slot print_timing: id 2 | task 4871 | graphs reused = 3435 13.35.460.828 I slot print_timing: id 2 | task 4871 | graph reallocs = 0 / 0 (same size) / (changed size) 13.35.460.874 I slot release: id 2 | task 4871 | stop processing: n_tokens = 973, truncated = 0 13.35.461.108 I slot print_timing: id 3 | task 4865 | prompt eval time = 6003.86 ms / 960 tokens ( 6.25 ms per token, 159.90 tokens per second) 13.35.461.111 I slot print_timing: id 3 | task 4865 | eval time = 53.86 ms / 2 tokens ( 53.86 ms per token, 18.57 tokens per second) 13.35.461.112 I slot print_timing: id 3 | task 4865 | total time = 6057.72 ms / 962 tokens 13.35.461.112 I slot print_timing: id 3 | task 4865 | graphs reused = 3435 13.35.461.112 I slot print_timing: id 3 | task 4865 | graph reallocs = 0 / 0 (same size) / (changed size) 13.35.461.145 I slot release: id 3 | task 4865 | stop processing: n_tokens = 961, truncated = 0 13.35.480.224 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 387624899844 13.35.480.299 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 354.309 MiB) 13.36.634.917 I slot launch_slot_: id 0 | task 4875 | processing task, is_child = 0 13.36.634.975 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 355.247 MiB) 13.37.484.394 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.996 MiB) 13.38.476.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 354.387 MiB) 13.39.318.889 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 978, t_last = 387624900121 13.39.319.011 I slot launch_slot_: id 1 | task 4876 | processing task, is_child = 0 13.39.319.106 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 387624900406 13.39.319.178 I slot launch_slot_: id 2 | task 4877 | processing task, is_child = 0 13.39.319.223 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 387624900677 13.39.319.286 I slot launch_slot_: id 3 | task 4878 | processing task, is_child = 0 13.42.673.212 I slot print_timing: id 0 | task 4875 | prompt processing, n_tokens = 309, progress = 0.37, t = 3.35 s / 92.13 tokens per second 13.42.934.209 I slot print_timing: id 1 | task 4876 | prompt processing, n_tokens = 533, progress = 0.33, t = 3.35 s / 158.92 tokens per second 13.42.934.269 I slot print_timing: id 2 | task 4877 | prompt processing, n_tokens = 533, progress = 0.34, t = 3.35 s / 158.93 tokens per second 13.42.935.837 I slot print_timing: id 3 | task 4878 | prompt processing, n_tokens = 533, progress = 0.33, t = 3.35 s / 158.93 tokens per second 13.46.433.184 I slot print_timing: id 0 | task 4875 | prompt processing, n_tokens = 706, progress = 0.86, t = 7.11 s / 99.24 tokens per second 13.46.615.355 I slot print_timing: id 1 | task 4876 | prompt processing, n_tokens = 1113, progress = 0.68, t = 7.11 s / 156.46 tokens per second 13.46.665.156 I slot print_timing: id 2 | task 4877 | prompt processing, n_tokens = 1071, progress = 0.67, t = 7.11 s / 150.55 tokens per second 13.46.673.803 I slot print_timing: id 3 | task 4878 | prompt processing, n_tokens = 1066, progress = 0.66, t = 7.11 s / 149.85 tokens per second 13.48.096.968 I slot print_timing: id 0 | task 4875 | prompt processing, n_tokens = 821, progress = 1.00, t = 8.78 s / 93.53 tokens per second 13.48.285.620 I slot print_timing: id 1 | task 4876 | prompt processing, n_tokens = 1374, progress = 0.84, t = 8.78 s / 156.54 tokens per second 13.48.302.219 I slot print_timing: id 2 | task 4877 | prompt processing, n_tokens = 1374, progress = 0.87, t = 8.78 s / 156.54 tokens per second 13.48.315.861 I slot print_timing: id 3 | task 4878 | prompt processing, n_tokens = 1099, progress = 0.68, t = 8.78 s / 125.21 tokens per second 13.50.052.361 I slot print_timing: id 1 | task 4876 | prompt processing, n_tokens = 1625, progress = 1.00, t = 10.73 s / 151.42 tokens per second 13.50.072.529 I slot print_timing: id 2 | task 4877 | prompt processing, n_tokens = 1583, progress = 1.00, t = 10.73 s / 147.51 tokens per second 13.50.087.009 I slot print_timing: id 3 | task 4878 | prompt processing, n_tokens = 1374, progress = 0.85, t = 10.73 s / 128.03 tokens per second 13.50.718.299 I slot print_timing: id 0 | task 4875 | prompt eval time = 10732.94 ms / 825 tokens ( 13.01 ms per token, 76.87 tokens per second) 13.50.718.317 I slot print_timing: id 0 | task 4875 | eval time = 666.03 ms / 2 tokens ( 666.03 ms per token, 1.50 tokens per second) 13.50.718.319 I slot print_timing: id 0 | task 4875 | total time = 11398.98 ms / 827 tokens 13.50.718.321 I slot print_timing: id 0 | task 4875 | graphs reused = 3436 13.50.718.323 I slot print_timing: id 0 | task 4875 | graph reallocs = 0 / 0 (same size) / (changed size) 13.50.718.756 I slot release: id 0 | task 4875 | stop processing: n_tokens = 826, truncated = 0 13.50.721.986 I slot print_timing: id 3 | task 4878 | prompt processing, n_tokens = 1611, progress = 1.00, t = 11.40 s / 141.34 tokens per second 13.50.821.446 I slot print_timing: id 1 | task 4876 | prompt eval time = 11401.30 ms / 1629 tokens ( 7.00 ms per token, 142.88 tokens per second) 13.50.821.454 I slot print_timing: id 1 | task 4876 | eval time = 100.76 ms / 2 tokens ( 100.76 ms per token, 9.92 tokens per second) 13.50.821.456 I slot print_timing: id 1 | task 4876 | total time = 11502.06 ms / 1631 tokens 13.50.821.456 I slot print_timing: id 1 | task 4876 | graphs reused = 3436 13.50.821.457 I slot print_timing: id 1 | task 4876 | graph reallocs = 0 / 0 (same size) / (changed size) 13.50.823.784 I slot release: id 1 | task 4876 | stop processing: n_tokens = 1630, truncated = 0 13.50.824.246 I slot print_timing: id 2 | task 4877 | prompt eval time = 11402.49 ms / 1587 tokens ( 7.18 ms per token, 139.18 tokens per second) 13.50.824.250 I slot print_timing: id 2 | task 4877 | eval time = 102.31 ms / 2 tokens ( 102.31 ms per token, 9.77 tokens per second) 13.50.824.251 I slot print_timing: id 2 | task 4877 | total time = 11504.80 ms / 1589 tokens 13.50.824.252 I slot print_timing: id 2 | task 4877 | graphs reused = 3436 13.50.824.253 I slot print_timing: id 2 | task 4877 | graph reallocs = 0 / 0 (same size) / (changed size) 13.50.824.339 I slot release: id 2 | task 4877 | stop processing: n_tokens = 1588, truncated = 0 13.50.825.077 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.861 (> 0.100 thold), f_keep = 0.860 13.50.825.199 I slot launch_slot_: id 1 | task 4886 | processing task, is_child = 0 13.50.825.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 357.653 MiB) 13.51.481.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.566 MiB) 13.52.511.847 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 387640158292 13.52.511.992 I slot launch_slot_: id 0 | task 4887 | processing task, is_child = 0 13.52.512.063 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.816 (> 0.100 thold), f_keep = 0.883 13.52.512.089 I slot launch_slot_: id 2 | task 4888 | processing task, is_child = 0 13.54.059.714 I slot print_timing: id 3 | task 4878 | prompt eval time = 11505.54 ms / 1615 tokens ( 7.12 ms per token, 140.37 tokens per second) 13.54.059.735 I slot print_timing: id 3 | task 4878 | eval time = 3234.61 ms / 2 tokens ( 3234.61 ms per token, 0.31 tokens per second) 13.54.059.737 I slot print_timing: id 3 | task 4878 | total time = 14740.16 ms / 1617 tokens 13.54.059.739 I slot print_timing: id 3 | task 4878 | graphs reused = 3436 13.54.059.741 I slot print_timing: id 3 | task 4878 | graph reallocs = 0 / 0 (same size) / (changed size) 13.54.060.535 I slot release: id 3 | task 4878 | stop processing: n_tokens = 1616, truncated = 0 13.54.517.407 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1616, t_last = 387643500071 13.54.517.693 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 352.627 MiB) 13.55.474.045 I slot launch_slot_: id 3 | task 4891 | processing task, is_child = 0 13.56.097.669 I slot print_timing: id 1 | task 4886 | prompt eval time = 2004.43 ms / 255 tokens ( 7.86 ms per token, 127.22 tokens per second) 13.56.097.698 I slot print_timing: id 1 | task 4886 | eval time = 1581.03 ms / 2 tokens ( 1581.03 ms per token, 0.63 tokens per second) 13.56.097.700 I slot print_timing: id 1 | task 4886 | total time = 3585.46 ms / 257 tokens 13.56.097.702 I slot print_timing: id 1 | task 4886 | graphs reused = 3436 13.56.097.703 I slot print_timing: id 1 | task 4886 | graph reallocs = 0 / 0 (same size) / (changed size) 13.56.099.553 I slot release: id 1 | task 4886 | stop processing: n_tokens = 1630, truncated = 0 13.56.100.459 I slot print_timing: id 2 | task 4888 | prompt eval time = 1979.56 ms / 344 tokens ( 5.75 ms per token, 173.78 tokens per second) 13.56.100.465 I slot print_timing: id 2 | task 4888 | eval time = 1583.08 ms / 2 tokens ( 1583.08 ms per token, 0.63 tokens per second) 13.56.100.466 I slot print_timing: id 2 | task 4888 | total time = 3562.64 ms / 346 tokens 13.56.100.466 I slot print_timing: id 2 | task 4888 | graphs reused = 3436 13.56.100.467 I slot print_timing: id 2 | task 4888 | graph reallocs = 0 / 0 (same size) / (changed size) 13.56.102.027 I slot release: id 2 | task 4888 | stop processing: n_tokens = 1719, truncated = 0 13.56.102.073 I slot print_timing: id 0 | task 4887 | prompt processing, n_tokens = 322, progress = 0.38, t = 3.58 s / 89.83 tokens per second 13.56.845.409 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 387645539088 13.56.845.648 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 352.666 MiB) 13.58.085.846 I slot launch_slot_: id 1 | task 4894 | processing task, is_child = 0 13.58.085.926 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.468 MiB) 13.58.826.406 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1719, t_last = 387645541562 13.58.826.577 I slot launch_slot_: id 2 | task 4895 | processing task, is_child = 0 13.58.826.587 I slot print_timing: id 0 | task 4887 | prompt processing, n_tokens = 725, progress = 0.87, t = 4.33 s / 167.31 tokens per second 13.59.682.609 I slot print_timing: id 0 | task 4887 | prompt processing, n_tokens = 834, progress = 1.00, t = 7.17 s / 116.31 tokens per second 13.59.917.096 I slot print_timing: id 3 | task 4891 | prompt processing, n_tokens = 349, progress = 0.40, t = 4.21 s / 82.93 tokens per second 14.01.199.341 I slot print_timing: id 3 | task 4891 | prompt processing, n_tokens = 725, progress = 0.84, t = 5.72 s / 126.65 tokens per second 14.01.990.018 I slot print_timing: id 0 | task 4887 | prompt eval time = 8687.09 ms / 838 tokens ( 10.37 ms per token, 96.46 tokens per second) 14.01.990.036 I slot print_timing: id 0 | task 4887 | eval time = 790.80 ms / 2 tokens ( 790.80 ms per token, 1.26 tokens per second) 14.01.990.038 I slot print_timing: id 0 | task 4887 | total time = 9477.89 ms / 840 tokens 14.01.991.420 I slot print_timing: id 0 | task 4887 | graphs reused = 3436 14.01.991.438 I slot print_timing: id 0 | task 4887 | graph reallocs = 0 / 0 (same size) / (changed size) 14.01.992.548 I slot release: id 0 | task 4887 | stop processing: n_tokens = 839, truncated = 0 14.01.992.616 I slot print_timing: id 1 | task 4894 | prompt processing, n_tokens = 343, progress = 0.40, t = 3.16 s / 108.63 tokens per second 14.02.038.793 I slot print_timing: id 2 | task 4895 | prompt processing, n_tokens = 326, progress = 0.39, t = 3.16 s / 103.25 tokens per second 14.02.041.158 I slot print_timing: id 3 | task 4891 | prompt processing, n_tokens = 861, progress = 1.00, t = 6.52 s / 132.15 tokens per second 14.03.550.050 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 839, t_last = 387651432086 14.03.550.394 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 354.465 MiB) 14.04.268.514 I slot launch_slot_: id 0 | task 4900 | processing task, is_child = 0 14.04.268.592 I slot print_timing: id 1 | task 4894 | prompt processing, n_tokens = 716, progress = 0.83, t = 4.72 s / 151.79 tokens per second 14.04.270.598 I slot print_timing: id 2 | task 4895 | prompt processing, n_tokens = 716, progress = 0.85, t = 4.72 s / 151.79 tokens per second 14.05.214.349 I slot print_timing: id 3 | task 4891 | prompt eval time = 8075.86 ms / 865 tokens ( 9.34 ms per token, 107.11 tokens per second) 14.05.214.380 I slot print_timing: id 3 | task 4891 | eval time = 1664.36 ms / 2 tokens ( 1664.36 ms per token, 0.60 tokens per second) 14.05.214.383 I slot print_timing: id 3 | task 4891 | total time = 9740.21 ms / 867 tokens 14.05.214.385 I slot print_timing: id 3 | task 4891 | graphs reused = 3436 14.05.214.388 I slot print_timing: id 3 | task 4891 | graph reallocs = 0 / 0 (same size) / (changed size) 14.05.214.822 I slot release: id 3 | task 4891 | stop processing: n_tokens = 866, truncated = 0 14.05.224.698 I slot print_timing: id 1 | task 4894 | prompt processing, n_tokens = 855, progress = 1.00, t = 6.38 s / 133.98 tokens per second 14.05.229.302 I slot print_timing: id 2 | task 4895 | prompt processing, n_tokens = 838, progress = 1.00, t = 6.38 s / 131.32 tokens per second 14.05.824.571 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 866, t_last = 387654654357 14.05.824.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 355.423 MiB) 14.06.610.311 I slot launch_slot_: id 3 | task 4903 | processing task, is_child = 0 14.07.250.692 I slot print_timing: id 1 | task 4894 | prompt eval time = 6990.54 ms / 859 tokens ( 8.14 ms per token, 122.88 tokens per second) 14.07.250.708 I slot print_timing: id 1 | task 4894 | eval time = 1428.47 ms / 2 tokens ( 1428.47 ms per token, 0.70 tokens per second) 14.07.250.709 I slot print_timing: id 1 | task 4894 | total time = 8419.02 ms / 861 tokens 14.07.250.710 I slot print_timing: id 1 | task 4894 | graphs reused = 3436 14.07.250.711 I slot print_timing: id 1 | task 4894 | graph reallocs = 0 / 0 (same size) / (changed size) 14.07.252.160 I slot release: id 1 | task 4894 | stop processing: n_tokens = 860, truncated = 0 14.07.253.968 I slot print_timing: id 2 | task 4895 | prompt eval time = 6992.76 ms / 842 tokens ( 8.30 ms per token, 120.41 tokens per second) 14.07.253.974 I slot print_timing: id 2 | task 4895 | eval time = 1429.43 ms / 2 tokens ( 1429.43 ms per token, 0.70 tokens per second) 14.07.253.975 I slot print_timing: id 2 | task 4895 | total time = 8422.19 ms / 844 tokens 14.07.253.975 I slot print_timing: id 2 | task 4895 | graphs reused = 3436 14.07.253.976 I slot print_timing: id 2 | task 4895 | graph reallocs = 0 / 0 (same size) / (changed size) 14.07.254.658 I slot release: id 2 | task 4895 | stop processing: n_tokens = 843, truncated = 0 14.07.905.465 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 387656691696 14.07.905.617 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 354.465 MiB) 14.08.860.765 I slot launch_slot_: id 1 | task 4906 | processing task, is_child = 0 14.08.860.818 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 352.627 MiB) 14.09.428.301 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 387656694193 14.09.428.430 I slot launch_slot_: id 2 | task 4907 | processing task, is_child = 0 14.09.428.451 I slot print_timing: id 0 | task 4900 | prompt processing, n_tokens = 716, progress = 0.81, t = 3.64 s / 196.87 tokens per second 14.10.535.772 I slot print_timing: id 0 | task 4900 | prompt processing, n_tokens = 882, progress = 1.00, t = 6.27 s / 140.73 tokens per second 14.10.768.089 I slot print_timing: id 3 | task 4903 | prompt processing, n_tokens = 264, progress = 0.34, t = 3.93 s / 67.25 tokens per second 14.12.096.756 I slot print_timing: id 3 | task 4903 | prompt processing, n_tokens = 628, progress = 0.81, t = 5.44 s / 115.46 tokens per second 14.13.761.546 I slot print_timing: id 0 | task 4900 | prompt eval time = 7781.90 ms / 886 tokens ( 8.78 ms per token, 113.85 tokens per second) 14.13.761.560 I slot print_timing: id 0 | task 4900 | eval time = 1711.09 ms / 2 tokens ( 1711.09 ms per token, 0.58 tokens per second) 14.13.761.563 I slot print_timing: id 0 | task 4900 | total time = 9493.00 ms / 888 tokens 14.13.761.565 I slot print_timing: id 0 | task 4900 | graphs reused = 3436 14.13.761.566 I slot print_timing: id 0 | task 4900 | graph reallocs = 0 / 0 (same size) / (changed size) 14.13.762.410 I slot release: id 0 | task 4900 | stop processing: n_tokens = 887, truncated = 0 14.13.762.500 I slot print_timing: id 1 | task 4906 | prompt processing, n_tokens = 628, progress = 0.84, t = 4.13 s / 151.97 tokens per second 14.13.989.780 I slot print_timing: id 2 | task 4907 | prompt processing, n_tokens = 571, progress = 0.83, t = 4.13 s / 138.18 tokens per second 14.13.993.413 I slot print_timing: id 3 | task 4903 | prompt processing, n_tokens = 776, progress = 0.99, t = 7.15 s / 108.53 tokens per second 14.14.797.654 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 387663201947 14.15.292.413 I slot launch_slot_: id 0 | task 4912 | processing task, is_child = 0 14.15.292.508 I slot print_timing: id 1 | task 4906 | prompt processing, n_tokens = 745, progress = 0.99, t = 5.17 s / 144.13 tokens per second 14.15.298.484 I slot print_timing: id 2 | task 4907 | prompt processing, n_tokens = 687, progress = 0.99, t = 5.17 s / 132.91 tokens per second 14.15.722.425 I slot print_timing: id 3 | task 4903 | prompt eval time = 8187.28 ms / 780 tokens ( 10.50 ms per token, 95.27 tokens per second) 14.15.722.441 I slot print_timing: id 3 | task 4903 | eval time = 924.76 ms / 2 tokens ( 924.76 ms per token, 1.08 tokens per second) 14.15.722.443 I slot print_timing: id 3 | task 4903 | total time = 9112.05 ms / 782 tokens 14.15.722.446 I slot print_timing: id 3 | task 4903 | graphs reused = 3436 14.15.722.448 I slot print_timing: id 3 | task 4903 | graph reallocs = 0 / 0 (same size) / (changed size) 14.15.726.373 I slot release: id 3 | task 4903 | stop processing: n_tokens = 781, truncated = 0 14.16.026.853 I slot print_timing: id 1 | task 4906 | prompt eval time = 6092.83 ms / 749 tokens ( 8.13 ms per token, 122.93 tokens per second) 14.16.027.516 I slot print_timing: id 1 | task 4906 | eval time = 305.79 ms / 2 tokens ( 305.79 ms per token, 3.27 tokens per second) 14.16.027.527 I slot print_timing: id 1 | task 4906 | total time = 6398.62 ms / 751 tokens 14.16.027.529 I slot print_timing: id 1 | task 4906 | graphs reused = 3436 14.16.027.533 I slot print_timing: id 1 | task 4906 | graph reallocs = 0 / 0 (same size) / (changed size) 14.16.028.271 I slot release: id 1 | task 4906 | stop processing: n_tokens = 750, truncated = 0 14.16.028.992 I slot print_timing: id 2 | task 4907 | prompt eval time = 6093.35 ms / 691 tokens ( 8.82 ms per token, 113.40 tokens per second) 14.16.028.997 I slot print_timing: id 2 | task 4907 | eval time = 307.31 ms / 2 tokens ( 307.31 ms per token, 3.25 tokens per second) 14.16.028.998 I slot print_timing: id 2 | task 4907 | total time = 6400.67 ms / 693 tokens 14.16.028.999 I slot print_timing: id 2 | task 4907 | graphs reused = 3436 14.16.029.000 I slot print_timing: id 2 | task 4907 | graph reallocs = 0 / 0 (same size) / (changed size) 14.16.030.649 I slot release: id 2 | task 4907 | stop processing: n_tokens = 692, truncated = 0 14.16.030.684 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.866 14.16.030.939 I slot launch_slot_: id 2 | task 4915 | processing task, is_child = 0 14.16.031.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.683 MiB) 14.17.092.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 353.839 MiB) 14.18.830.545 I slot print_timing: id 0 | task 4912 | prompt processing, n_tokens = 571, progress = 0.80, t = 3.54 s / 161.39 tokens per second 14.19.542.737 I slot print_timing: id 0 | task 4912 | prompt processing, n_tokens = 708, progress = 0.99, t = 4.25 s / 166.64 tokens per second 14.19.628.232 I slot print_timing: id 2 | task 4915 | prompt eval time = 1416.14 ms / 107 tokens ( 13.23 ms per token, 75.56 tokens per second) 14.19.628.237 I slot print_timing: id 2 | task 4915 | eval time = 85.61 ms / 2 tokens ( 85.61 ms per token, 11.68 tokens per second) 14.19.628.238 I slot print_timing: id 2 | task 4915 | total time = 1501.75 ms / 109 tokens 14.19.628.239 I slot print_timing: id 2 | task 4915 | graphs reused = 3436 14.19.628.239 I slot print_timing: id 2 | task 4915 | graph reallocs = 0 / 0 (same size) / (changed size) 14.19.628.433 I slot release: id 2 | task 4915 | stop processing: n_tokens = 679, truncated = 0 14.19.652.587 I slot print_timing: id 0 | task 4912 | prompt eval time = 4335.54 ms / 712 tokens ( 6.09 ms per token, 164.22 tokens per second) 14.19.652.592 I slot print_timing: id 0 | task 4912 | eval time = 24.62 ms / 2 tokens ( 24.62 ms per token, 40.62 tokens per second) 14.19.652.592 I slot print_timing: id 0 | task 4912 | total time = 4360.16 ms / 714 tokens 14.19.652.593 I slot print_timing: id 0 | task 4912 | graphs reused = 3436 14.19.652.593 I slot print_timing: id 0 | task 4912 | graph reallocs = 0 / 0 (same size) / (changed size) 14.19.652.653 I slot release: id 0 | task 4912 | stop processing: n_tokens = 713, truncated = 0 14.24.275.001 I srv operator(): operator(): cleaning up before exit...